Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7ae3f97789 | ||
|
|
0f7061195b | ||
|
|
ece7653ca0 | ||
|
|
a0209ee102 |
@@ -46,28 +46,6 @@ steps:
|
||||
# [0] of the pnpm chain, so severing that chain would silence it together
|
||||
# with everything it guards; this direct line keeps one instrument running.
|
||||
- bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh
|
||||
# Tool-index gate: a shipped wrapper that appears in no resident index doc
|
||||
# is undiscoverable from inside a session, and an agent that cannot learn a
|
||||
# wrapper exists reaches for raw curl instead — which is how a Gitea review
|
||||
# got filed PENDING three times. Ships-and-documented is one commit, or red.
|
||||
- bash packages/mosaic/framework/tools/quality/scripts/check-tools-index.sh --self-test
|
||||
- bash packages/mosaic/framework/tools/quality/scripts/check-tools-index.sh
|
||||
# Hermetic regression for issue-close.sh (#1081): mocks tea/curl onto PATH
|
||||
# and sandboxes a throwaway git repo, so it resolves no real credentials and
|
||||
# joins CI directly rather than the exclusions file.
|
||||
- bash packages/mosaic/framework/tools/git/test-issue-close-fail-closed.sh
|
||||
# Hermetic behavioural regression for the PreToolUse wrapper guard: proves
|
||||
# it still blocks the three mistakes AND still lets reads, unwrapped
|
||||
# endpoints and ordinary commands through. Both directions are asserted —
|
||||
# a guard that over-blocks gets routed around, which fails just as hard.
|
||||
- bash packages/mosaic/framework/tools/git/test-wrapper-guard.sh
|
||||
# Hermetic regression for mosaic-worktree.sh at fleet scale: stubs git onto
|
||||
# PATH so `list` faces ~450 KB of porcelain. The defect it pins is invisible
|
||||
# at small size — `git … | awk '…exit'` gives the producer SIGPIPE, which
|
||||
# under `set -euo pipefail` aborts the caller silently with rc=141 and no
|
||||
# output. A repo only reaches that once it has enough worktrees, so the
|
||||
# stub supplies the scale instead of the host's own checkout.
|
||||
- bash packages/mosaic/framework/tools/git/test-mosaic-worktree-large-repo.sh
|
||||
|
||||
# Blocking gate (#791): a framework upgrade must never write or delete an
|
||||
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
|
||||
|
||||
@@ -60,14 +60,6 @@ The launcher verifies your config, checks for `SOUL.md`, injects your `AGENTS.md
|
||||
|
||||
Pi launches default to a token-lean skill posture: `mosaic pi` passes `--no-skills` so Pi does not preload every global skill description into the system prompt. Use `MOSAIC_PI_SKILL_MODE=all mosaic pi` for the legacy all-skills catalog, or `MOSAIC_PI_SKILL_MODE=discover mosaic pi` to let Pi use its native settings/project skill discovery.
|
||||
|
||||
Mosaic also loads its Pi extensions from `~/.config/mosaic/runtime/pi/`. Inside Pi,
|
||||
`/goal set <statement>` starts a bounded persistent loop that checks every turn and successful
|
||||
compaction, requires two evidence-bearing completion reports, and can be inspected or stopped with
|
||||
`/goal status`, `/goal pause`, `/goal resume`, and `/goal cancel`. Controller-owned goal-state
|
||||
entries redact common credential shapes, but Pi's model/tool-call history is separate, so goals and
|
||||
evidence must never contain secrets or raw sensitive output. Mosaic does not install this extension
|
||||
into `~/.pi/agent/extensions/`.
|
||||
|
||||
### TUI & Gateway
|
||||
|
||||
```bash
|
||||
@@ -215,13 +207,6 @@ pnpm install
|
||||
|
||||
# Verify dependencies and generated state before running source-quality gates.
|
||||
# Missing dependencies exit 42; stale/foreign apps/web/.next state exits 43.
|
||||
# The web build certifies its exact standalone symlink manifest; added, removed,
|
||||
# retargeted, or manifest-only-tampered generated links also exit 43. This detects
|
||||
# accidental, independent, stale, and foreign-residue mutation—the class exposed by
|
||||
# a five-month-stale .next that produced 19 phantom TS2307 errors.
|
||||
# It does NOT defend against a same-UID actor that can rewrite both manifest and
|
||||
# marker consistently (CWE-345). RM-59 tracks the required executor/spine-side
|
||||
# trust anchor outside worktree authority.
|
||||
pnpm preflight
|
||||
|
||||
# Optional local queue service only. This does not start PostgreSQL.
|
||||
|
||||
@@ -245,21 +245,9 @@ describe('EnrollmentService.createToken', () => {
|
||||
const after = Date.now();
|
||||
|
||||
const expiresMs = new Date(result.expiresAt).getTime();
|
||||
|
||||
// The property under test is CLAMPING: a 9999s request must come back as 900s.
|
||||
// The gap between clamped and unclamped is 9_099_000 ms, so the tolerance below
|
||||
// only has to exceed CI scheduling jitter — it does not need to be tight to keep
|
||||
// the assertion discriminating. A 5s allowance consumes 0.05% of that margin and
|
||||
// an unclamped result still misses by three orders of magnitude.
|
||||
//
|
||||
// It was 100ms and failed on a loaded agent at 900_106 — 6ms over (#1090). A
|
||||
// wall-clock budget sized to a fast machine is a flake, not a tighter test.
|
||||
const CI_JITTER_MS = 5_000;
|
||||
expect(expiresMs - before).toBeLessThanOrEqual(900_000 + CI_JITTER_MS);
|
||||
// Should be at most 900s from now
|
||||
expect(expiresMs - before).toBeLessThanOrEqual(900_000 + 100);
|
||||
expect(expiresMs - after).toBeGreaterThanOrEqual(0);
|
||||
// Explicitly pin the clamp itself, independent of any timing allowance:
|
||||
// unclamped (9999s) would exceed this by ~9_099_000 ms.
|
||||
expect(expiresMs - before).toBeLessThan(1_000_000);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
-246
@@ -1,14 +1,5 @@
|
||||
# PRD: Mosaic Stack v0.1.0
|
||||
|
||||
## Current addendum: #1194 — Installed framework-tool drift detection
|
||||
|
||||
- Compare the framework tools shipped with the executing Mosaic package against the deployed `$MOSAIC_HOME/tools` tree by content hash.
|
||||
- Treat every shipped `tools/**` file as framework-owned/required according to `framework-manifest.txt`, while excluding the explicit operator-owned credential carve-out and preserving installed-only operator/unknown files.
|
||||
- Distinguish and count `IN_SYNC`, `STALE`, `NOT_INSTALLED`, and installed-only classifications; fail non-zero when shipped tools are stale or absent and refuse self-comparison that would make drift unobservable.
|
||||
- Surface the observational check through `mosaic doctor`; do not refresh files, restart seats, or mutate live tooling.
|
||||
- Document identity/messaging/gate behavior changes in the current stale set, the reviewed quiet-window keep-mode refresh command, and post-refresh probes against the installed path.
|
||||
- Prove by construction that a stale and missing deployed tool are detected; that regression must fail before this checker exists.
|
||||
|
||||
## Metadata
|
||||
|
||||
- **Owner:** Jason Woltje
|
||||
@@ -111,128 +102,6 @@ Context compaction, session replacement, and same-PID runtime reloads can leave
|
||||
|
||||
---
|
||||
|
||||
## Pi Persistent Goal Loop (#1150)
|
||||
|
||||
### Problem and objective
|
||||
|
||||
A Pi agent can stop after a plausible-looking answer even when the operator's broader objective is
|
||||
not complete, and ordinary compaction can weaken or omit the original objective. Mosaic needs an
|
||||
optional, operator-controlled goal loop that keeps a Pi session oriented, checks progress at native
|
||||
lifecycle boundaries, and resumes work until completion is verified or a bounded safety state is
|
||||
reached.
|
||||
|
||||
The objective is a Mosaic-owned Pi extension deployed from the framework into
|
||||
`~/.config/mosaic/runtime/pi/`. It must not install into or depend on `~/.pi/agent/extensions/`.
|
||||
|
||||
### Scope
|
||||
|
||||
#### In scope
|
||||
|
||||
1. `PGL-REQ-01`: The framework SHALL ship a dedicated Pi goal extension under
|
||||
`packages/mosaic/framework/runtime/pi/`, seed it under `$MOSAIC_HOME/runtime/pi/`, and make
|
||||
`mosaic pi` load it alongside the core Mosaic extension when present.
|
||||
2. `PGL-REQ-02`: `/goal` SHALL support setting a goal plus status, pause, resume, cancel, and help
|
||||
operations without silently replacing an active goal.
|
||||
3. `PGL-REQ-03`: Active branch-specific goal state SHALL be persisted in Pi custom session entries,
|
||||
restored on session start and tree navigation, and never rely on a compaction summary as its
|
||||
source of truth.
|
||||
4. `PGL-REQ-04`: A hidden goal contract SHALL be injected through Pi's `context` event before every
|
||||
model request so it remains effective across tool turns, retries, and post-compaction requests.
|
||||
5. `PGL-REQ-05`: The harness SHALL inspect every `turn_end` and successful `session_compact` event.
|
||||
A structured terminating goal-report tool SHALL capture `continue`, evidence-bearing `achieved`,
|
||||
or `blocked` status without requiring a redundant model turn.
|
||||
6. `PGL-REQ-06`: An achievement claim SHALL remain provisional until a second consecutive
|
||||
evidence-bearing verification report. Any continuation report or successful compaction during
|
||||
verification SHALL reset the verification sequence.
|
||||
7. `PGL-REQ-07`: Continuation SHALL be initiated at safe lifecycle boundaries, primarily
|
||||
`agent_settled`; manual compaction and restored active sessions may schedule a deferred idle
|
||||
continuation without re-entering compaction handlers.
|
||||
8. `PGL-REQ-08`: The loop SHALL have operator cancellation plus bounded turn and repeated-no-progress
|
||||
limits. Exhausted or blocked goals pause rather than continuing indefinitely.
|
||||
9. `PGL-REQ-09`: Framework installation and update SHALL preserve normal manifest ownership: the
|
||||
goal extension is framework-owned under `runtime/**`, while no goal extension or configuration
|
||||
asset is created or modified under the operator's main Pi configuration. Pi remains the owner of
|
||||
its native session files used by `appendEntry()`.
|
||||
|
||||
#### Out of scope
|
||||
|
||||
1. A mathematical guarantee that an arbitrary natural-language goal is semantically complete.
|
||||
2. Automatically executing user-supplied shell predicates or accepting executable validation code in
|
||||
`/goal` arguments.
|
||||
3. Restarting Pi after process, host, or supervisor failure; the existing Mosaic fleet/runtime
|
||||
supervisor owns process durability.
|
||||
4. Gateway, database, web UI, Discord, or cross-harness goal orchestration in this slice.
|
||||
|
||||
### User and stakeholder requirements
|
||||
|
||||
- An operator can start a goal from Pi and see its current phase, evidence, limits, and latest report.
|
||||
- The agent remains oriented after each turn and compaction until verified, paused, blocked,
|
||||
exhausted, or cancelled.
|
||||
- Local testing uses a file under `~/.config/mosaic/runtime/pi/`; the feature never writes an
|
||||
extension asset to `~/.pi/agent/extensions/`.
|
||||
- Framework updates deploy the same reviewed extension source through Mosaic's existing manifest
|
||||
sync path.
|
||||
|
||||
### Non-functional requirements
|
||||
|
||||
1. **Safety:** bounded continuation, explicit cancellation, no arbitrary command execution, and no
|
||||
completion without non-empty reported evidence.
|
||||
2. **Reliability:** serialized continuation scheduling, branch-aware restoration, compaction-safe
|
||||
context injection, and stale-timer cancellation on session shutdown.
|
||||
3. **Performance:** no extra nested judge-model request on every turn; structured reporting uses the
|
||||
active agent's final terminating tool call.
|
||||
4. **Observability:** Pi status/notifications expose phase and bounded counters without recording
|
||||
credentials or hidden model reasoning.
|
||||
5. **Maintainability:** the state machine is deterministic and behavior-tested independently from Pi
|
||||
provider/network access.
|
||||
|
||||
### Acceptance criteria
|
||||
|
||||
1. `AC-PGL-01`: A framework-sync fixture installs the extension at
|
||||
`$MOSAIC_HOME/runtime/pi/goal-extension.ts`, and launcher tests prove both Mosaic Pi extensions are
|
||||
emitted in deterministic order while absent optional files remain backward-compatible.
|
||||
2. `AC-PGL-02`: Command tests prove set/status/pause/resume/cancel behavior, active-goal replacement
|
||||
refusal, and bounded input handling.
|
||||
3. `AC-PGL-03`: Lifecycle tests prove every turn is recorded, active context is injected on every
|
||||
request, two evidence-bearing achievement reports are required, and `agent_settled` continues an
|
||||
unmet goal without duplicate scheduling.
|
||||
4. `AC-PGL-04`: Compaction and restoration tests prove goal state survives, verification is reset and
|
||||
rechecked after compaction, manual compaction continuation is deferred until idle, and tree/session
|
||||
branch state is reconstructed correctly.
|
||||
5. `AC-PGL-05`: Limit tests prove max-turn and repeated-no-progress exhaustion stop autonomous
|
||||
continuation, while pause/cancel/blocked states do not restart.
|
||||
6. `AC-PGL-06`: Focused tests, package typecheck/lint/test, repository quality gates, a local Pi load
|
||||
smoke test from `~/.config/mosaic/runtime/pi/`, independent review, and terminal-green CI pass before
|
||||
issue #1150 closes.
|
||||
|
||||
### Constraints, risks, and assumptions
|
||||
|
||||
- Dependency: Pi's extension API must continue to provide `registerCommand`, `registerTool`,
|
||||
`context`, `turn_end`, `agent_settled`, `session_compact`, session custom entries, and terminating
|
||||
tool results.
|
||||
- Risk: the working agent can overstate completion. Mitigation: structured evidence, a mandatory
|
||||
second verification pass, explicit semantic limitations, and operator-visible reports.
|
||||
- Risk: an impossible goal can consume unbounded resources. Mitigation: hard turn/no-progress bounds
|
||||
and paused terminal states.
|
||||
- Risk: automatic continuation can race compaction or session replacement. Mitigation: drive from
|
||||
`agent_settled`, defer idle restarts, generation-check timers, and clear timers on shutdown.
|
||||
- `ASSUMPTION:` Two consecutive evidence-bearing reports are the initial local verification policy;
|
||||
rationale: it provides a real recheck without doubling every turn's model cost. Future policy may
|
||||
add independent or deterministic validators.
|
||||
- `ASSUMPTION:` Default limits are 40 turns and 6 repeated no-progress reports, configurable only by
|
||||
bounded Mosaic environment settings; rationale: useful persistence with a finite autonomous budget.
|
||||
- `ASSUMPTION:` Documentation remains canonical in-repo for this slice; no external docs publication
|
||||
is requested.
|
||||
|
||||
### Testing and delivery intent
|
||||
|
||||
Use TDD for the deterministic controller and lifecycle invariants. Test with fake Pi lifecycle
|
||||
objects first, then run a local load/smoke test from the deployed Mosaic path. Deliver source, tests,
|
||||
launcher wiring, framework/runtime documentation, user/developer guides, and sitemap updates in one
|
||||
reviewed squash PR to `main` with terminal-green CI.
|
||||
|
||||
---
|
||||
|
||||
## Fleet Declarative Configuration Management Workstream (FCM, #758)
|
||||
|
||||
### Problem and objective
|
||||
@@ -277,68 +146,6 @@ lands. M0 consists only of these normative requirements, the complete task DAG,
|
||||
documentation IA checklist, and the legacy example/profile disposition inventory. Subsequent cards
|
||||
are defined in [docs/TASKS.md](./TASKS.md) and must remain one card/one PR.
|
||||
|
||||
### Fleet git identity launch propagation (#1043)
|
||||
|
||||
#### Problem and objective
|
||||
|
||||
A fleet seat can have a registered per-agent Git credential while its launched runtime process lacks
|
||||
`MOSAIC_GIT_IDENTITY`. The credential resolver then cannot select the seat identity reliably, which
|
||||
blocks repository operations on fail-closed estates and can fall through to an unrelated identity on
|
||||
estates where that refusal is not active. The objective is to make Git identity a deterministic,
|
||||
roster-derived part of the generated launch projection and prove it reaches the launched process.
|
||||
|
||||
#### Normative requirements
|
||||
|
||||
1. `FGI-REQ-01`: Every generated fleet agent projection SHALL declare
|
||||
`MOSAIC_GIT_IDENTITY=<MOSAIC_AGENT_NAME>`; a differing or unsafe identity SHALL fail closed before
|
||||
tmux launch.
|
||||
2. `FGI-REQ-02`: The clean `/usr/bin/env -i` pane boundary SHALL pass every variable declared by the
|
||||
generated projection, including `MOSAIC_GIT_IDENTITY`, to the launched runtime process.
|
||||
3. `FGI-REQ-03`: A behavioral integration test SHALL set-compare the complete generated projection
|
||||
against the launched process environment. Source-text/string-presence assertions are insufficient.
|
||||
4. `FGI-REQ-04`: Verification SHALL include RED-first evidence and a delete-the-subject mutation that
|
||||
removes Git-identity pane propagation and makes the behavioral test fail.
|
||||
|
||||
#### Acceptance criteria
|
||||
|
||||
1. `AC-FGI-01`: A launched seat process contains every key/value pair declared by its generated
|
||||
environment projection, including the roster-derived Git identity.
|
||||
2. `AC-FGI-02`: Missing, unsafe, or split Git identity is rejected before a tmux session is created.
|
||||
3. `AC-FGI-03`: Focused launcher and generated-environment tests, repository quality gates,
|
||||
independent review, and the required RED/green/R7 evidence are recorded before push.
|
||||
|
||||
### Framework shell assertion portability (#1098)
|
||||
|
||||
#### Problem and objective
|
||||
|
||||
The blocking framework-shell chain can report that a pane command omitted `/usr/bin/env -i` even when
|
||||
`-i` matched successfully. A short-circuiting `grep -q` under `set -o pipefail` may close its pipe after
|
||||
the match and cause an upstream producer to exit with SIGPIPE, turning a valid semantic result into a
|
||||
nonzero aggregate pipeline. The objective is to inspect the captured NUL-delimited argv directly and
|
||||
make failures carry the observed records needed for diagnosis.
|
||||
|
||||
#### Normative requirements
|
||||
|
||||
1. `FSP-REQ-01`: The pane-boundary test SHALL validate an adjacent `/usr/bin/env`, `-i` argv pair from
|
||||
the authoritative NUL-delimited tmux capture without a short-circuit pipeline whose upstream status
|
||||
can override a successful match.
|
||||
2. `FSP-REQ-02`: Missing, reversed, or non-adjacent boundary tokens SHALL fail, while valid boundaries
|
||||
SHALL remain valid regardless of trailing argv size, pipe capacity, process scheduling, or host/CI
|
||||
utility implementation.
|
||||
3. `FSP-REQ-03`: A failed boundary check SHALL print stable indexed, shell-escaped observed argv records
|
||||
before exiting nonzero; the fixture SHALL continue to contain generated non-secret launch data only.
|
||||
4. `FSP-REQ-04`: Verification SHALL include RED-first large-payload evidence, negative token-order
|
||||
controls, the complete focused launcher suite, canonical Woodpecker CI, and independent review.
|
||||
|
||||
#### Acceptance criteria
|
||||
|
||||
1. `AC-FSP-01`: A large captured argv with adjacent `/usr/bin/env`, `-i` passes even when the former
|
||||
`grep -q` pipeline returns nonzero from an upstream SIGPIPE.
|
||||
2. `AC-FSP-02`: Missing executable, missing flag, and detached/reversed flag fixtures return nonzero and
|
||||
emit the indexed observed argv.
|
||||
3. `AC-FSP-03`: The focused suite passes on the development host and CI image, and the merged-main
|
||||
Woodpecker pipeline is terminal green before #1098 closes.
|
||||
|
||||
---
|
||||
|
||||
## Exact Cross-Harness Fleet Communications Contract (#766)
|
||||
@@ -1538,59 +1345,6 @@ All work is **alpha** (< 0.1.0) until Jason approves 0.1.0 beta release.
|
||||
|
||||
---
|
||||
|
||||
## Workspace placement guard hardening (#1174)
|
||||
|
||||
### Problem and objective
|
||||
|
||||
The Bash pre-tool guard must prevent Git checkouts and repository state from being placed under
|
||||
`$HOME` without refusing ordinary Git commands merely because a source, option value, branch name,
|
||||
or metadata mentions `$HOME`. A guard that over-blocks routine work is unsafe because operators
|
||||
will route around it.
|
||||
|
||||
### Scope and requirements
|
||||
|
||||
1. `WPG-REQ-01`: `git clone` and `git worktree add` placement SHALL be judged from their placement
|
||||
operands, not from every HOME-shaped word in the command.
|
||||
2. `WPG-REQ-02`: Clone sources, references, templates, environment assignments, and non-placement
|
||||
worktree metadata MAY resolve under HOME when all placement operands resolve elsewhere.
|
||||
3. `WPG-REQ-03`: Both attached and separate-value `--separate-git-dir` forms SHALL remain placement
|
||||
operands and SHALL be refused when they resolve under HOME.
|
||||
4. `WPG-REQ-04`: Option classification SHALL account for Git's rule-generated boolean negations
|
||||
without relying on an enumerable allowlist of flag spellings.
|
||||
5. `WPG-REQ-05`: Quote removal, escapes, shell command boundaries, redirections, and end-of-options
|
||||
handling SHALL preserve existing fail-closed checkout coverage.
|
||||
6. `WPG-REQ-06`: Absolute placement aliases SHALL resolve shell-known HOME spellings, dot segments,
|
||||
repeated separators, and existing symlink parents before the HOME boundary comparison.
|
||||
7. Relative targets whose effective path depends on the shell cwd are out of scope and tracked by
|
||||
#1197.
|
||||
|
||||
### Acceptance and verification
|
||||
|
||||
1. Git's own option parser accepts each tested flag, including generated `--no-*` forms, while the
|
||||
guard allows a HOME-valued source with an explicit safe destination.
|
||||
2. Equivalent clone and worktree fixtures cover rule-generated negations and remain discriminating
|
||||
against the prior head where the defect existed.
|
||||
3. Real HOME destinations and both `--separate-git-dir` forms remain blocked, including placements
|
||||
after shell command boundaries.
|
||||
4. The full hermetic guard suite, syntax/static checks, adversarial probes, independent review, and
|
||||
terminal-green CI pass before merge.
|
||||
5. Any option-classification residual is documented with its deliberate failure direction.
|
||||
|
||||
### Constraints, risks, and assumptions
|
||||
|
||||
- Security and usability are co-equal: neither a placement bypass nor routine over-block is an
|
||||
acceptable repair.
|
||||
- `ASSUMPTION:` The value-taking option surface exposed by the installed Git version is closed and
|
||||
measurable through Git's own parser/help output; rationale: boolean flags are rule-generated,
|
||||
while separate-value options have explicit grammar and must be classified as such.
|
||||
- Risk: a future Git release may add a new value-taking placement option. Mitigation: document the
|
||||
chosen residual direction and pin every currently supported placement option in behavior tests.
|
||||
- Risk: a symlink can be replaced after pre-execution canonicalization. Mitigation: resolve every
|
||||
existing parent physically and document the remaining inherent TOCTOU window; the worktree helper
|
||||
remains the authoritative path-derivation mechanism, with atomic closure tracked by #1199.
|
||||
|
||||
---
|
||||
|
||||
## Assumptions
|
||||
|
||||
1. RESOLVED: **pgvector is sufficient** for semantic search at v0.1.0 scale (personal/family/team = thousands to low hundreds-of-thousands of vectors). `@mosaicstack/memory` defines a `VectorStore` interface with pgvector as the default adapter. The interface boundary makes Qdrant a drop-in migration if PG resource contention or scale demands it later. Zero additional infrastructure for v0.1.0. Rationale: Reduces ops burden; pgvector HNSW indexes are fast at this scale; interface abstraction costs almost nothing now.
|
||||
|
||||
@@ -14,13 +14,6 @@
|
||||
- [Skill registration user guide](guides/user-guide.md#claude-code-skill-registration) — register, unregister, list statuses, automatic install/update reconciliation, and Claude reload behavior.
|
||||
- [Skill bridge developer guide](guides/dev-guide.md#claude-code-skill-bridge) — path-validation, ownership, clobber-protection, install/update wiring, tests, and Pi/Codex scope notes.
|
||||
|
||||
## Pi persistent goals
|
||||
|
||||
- [Persistent goal user guide](guides/user-guide.md#pi-persistent-goals) — `/goal` commands, verification behavior, limits, compaction/resume semantics, and limitations.
|
||||
- [Goal extension developer guide](guides/dev-guide.md#pi-persistent-goal-extension) — framework ownership, launcher ordering, lifecycle design, tests, and local Mosaic-path smoke workflow.
|
||||
- [Goal loop operations](guides/admin-guide.md#pi-goal-loop-operations) — deployment ownership, bounded settings, pause/resume procedures, and supervisor boundary.
|
||||
- [Pi runtime reference](../packages/mosaic/framework/runtime/pi/RUNTIME.md#extensions) — deployed paths, command summary, and bounded environment settings.
|
||||
|
||||
## Fleet configuration management
|
||||
|
||||
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
|
||||
|
||||
+10
-13
@@ -5,14 +5,14 @@ Generated environment files are rebuildable projections, not an operator-editabl
|
||||
|
||||
## Launch chain
|
||||
|
||||
| Layer | Responsibility |
|
||||
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Roster | `fleet/roster.yaml` supplies the agent name, class, supported runtime, model, reasoning, tool policy, workdir, and tmux socket; Git identity is derived from the exact agent name. |
|
||||
| Projection writer | Renders deterministic fleet/agents/<name>.env.generated from the roster. |
|
||||
| Optional local data | Reads a strict, data-only fleet/agents/<name>.env.local; it cannot shadow generated keys. |
|
||||
| systemd | Starts the launcher with env -i and fixed bootstrap data. It does not preload either environment file. |
|
||||
| session launcher | Validates generated and local data before it queries, creates, or stops an exact tmux session. |
|
||||
| runtime launch | Derives the fixed mosaic yolo <runtime> argument array from validated roster data, then seeds the runtime contract. |
|
||||
| Layer | Responsibility |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Roster | `fleet/roster.yaml` supplies the agent name, class, supported runtime, model, reasoning, tool policy, workdir, and tmux socket. |
|
||||
| Projection writer | Renders deterministic fleet/agents/<name>.env.generated from the roster. |
|
||||
| Optional local data | Reads a strict, data-only fleet/agents/<name>.env.local; it cannot shadow generated keys. |
|
||||
| systemd | Starts the launcher with env -i and fixed bootstrap data. It does not preload either environment file. |
|
||||
| session launcher | Validates generated and local data before it queries, creates, or stops an exact tmux session. |
|
||||
| runtime launch | Derives the fixed mosaic yolo <runtime> argument array from validated roster data, then seeds the runtime contract. |
|
||||
|
||||
The launcher never `source`s or `eval`s an environment file and never accepts an environment-supplied
|
||||
command. `MOSAIC_AGENT_COMMAND`, command/channel overrides, unknown keys, generated-key shadowing,
|
||||
@@ -24,7 +24,6 @@ secret-like key names, duplicate keys, comments, quoted/export syntax, and unsaf
|
||||
|
||||
```dotenv
|
||||
MOSAIC_AGENT_NAME=<roster name>
|
||||
MOSAIC_GIT_IDENTITY=<roster name>
|
||||
MOSAIC_AGENT_CLASS=<roster class>
|
||||
MOSAIC_AGENT_RUNTIME=<roster runtime>
|
||||
MOSAIC_AGENT_MODEL=<roster model hint>
|
||||
@@ -34,10 +33,8 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
|
||||
MOSAIC_TMUX_SOCKET=<roster socket or empty>
|
||||
```
|
||||
|
||||
`MOSAIC_GIT_IDENTITY` is not independently configurable: it must equal `MOSAIC_AGENT_NAME`, preventing
|
||||
split runtime and repository identity authority. The generated launch contract supports `claude`,
|
||||
`codex`, `opencode`, and `pi`. mosaic fleet add rejects another runtime before it writes the roster or
|
||||
modifies generated, local, or quarantine state.
|
||||
The generated launch contract supports `claude`, `codex`, `opencode`, and `pi`. mosaic fleet add
|
||||
rejects another runtime before it writes the roster or modifies generated, local, or quarantine state.
|
||||
The legacy dogfood stub remains an observability-only canary on its separate `mosaic-factory` socket;
|
||||
it has no generated-launch adapter and cannot be added through this path.
|
||||
|
||||
|
||||
@@ -3,12 +3,11 @@
|
||||
The launcher consumes validated data, not shell configuration.
|
||||
|
||||
1. Read and validate the canonical roster.
|
||||
2. Render deterministic <name>.env.generated data from that roster, including `MOSAIC_GIT_IDENTITY` derived exactly from the roster agent name.
|
||||
2. Render deterministic <name>.env.generated data from that roster.
|
||||
3. Parse optional <name>.env.local through a strict allowlist.
|
||||
4. Reject generated-key shadowing, unknown or sensitive-looking keys, unsafe paths/values, duplicates, malformed lines, shell syntax, and command overrides.
|
||||
5. Reject a Git identity that is unsafe or differs from the generated agent name.
|
||||
6. Derive the runtime command from validated runtime/model/reasoning data and pass every generated projection entry through the clean process environment boundary.
|
||||
7. Target only the exact configured tmux socket and roster session after ownership checks.
|
||||
5. Derive the runtime command from validated runtime/model/reasoning data.
|
||||
6. Target only the exact configured tmux socket and roster session after ownership checks.
|
||||
|
||||
## File precedence and ownership
|
||||
|
||||
|
||||
@@ -35,7 +35,6 @@ values, credential material, or command text.
|
||||
|
||||
```dotenv
|
||||
MOSAIC_AGENT_NAME=<roster name>
|
||||
MOSAIC_GIT_IDENTITY=<roster name>
|
||||
MOSAIC_AGENT_CLASS=<roster class>
|
||||
MOSAIC_AGENT_RUNTIME=<roster runtime>
|
||||
MOSAIC_AGENT_MODEL=<roster model hint>
|
||||
@@ -45,9 +44,8 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
|
||||
MOSAIC_TMUX_SOCKET=<roster socket or empty>
|
||||
```
|
||||
|
||||
`MOSAIC_GIT_IDENTITY` is derived from and must equal `MOSAIC_AGENT_NAME`; it is not a separate
|
||||
operator-controlled identity authority. The generated launch contract supports only `claude`, `codex`,
|
||||
`opencode`, and `pi`. fleet add uses that same runtime authority and rejects any other runtime before it writes the roster or changes
|
||||
The generated launch contract supports only `claude`, `codex`, `opencode`, and `pi`. fleet add
|
||||
uses that same runtime authority and rejects any other runtime before it writes the roster or changes
|
||||
projection, local, or quarantine files. The legacy dogfood stub on its separate `mosaic-factory`
|
||||
socket remains an observability canary; it has no generated-launch adapter and cannot be added through
|
||||
this projection path.
|
||||
|
||||
@@ -7,8 +7,7 @@
|
||||
3. [Provider Configuration](#provider-configuration)
|
||||
4. [MCP Server Configuration](#mcp-server-configuration)
|
||||
5. [Environment Variables Reference](#environment-variables-reference)
|
||||
6. [Pi Goal Loop Operations](#pi-goal-loop-operations)
|
||||
7. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
6. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -265,16 +264,6 @@ Each OIDC provider requires its client ID, client secret, and issuer URL togethe
|
||||
| `AGENT_SYSTEM_PROMPT` | — | Platform-level system prompt injected into all sessions |
|
||||
| `AGENT_USER_TOOLS` | all tools | Comma-separated allowlist of tools for non-admin users |
|
||||
|
||||
### Mosaic Pi goal loop
|
||||
|
||||
| Variable | Default | Description |
|
||||
| ----------------------------- | ------- | -------------------------------------------------------------------- |
|
||||
| `MOSAIC_GOAL_MAX_TURNS` | `40` | Per-goal autonomous turn limit; accepted range `1..500` |
|
||||
| `MOSAIC_GOAL_MAX_NO_PROGRESS` | `6` | Consecutive identical progress-report limit; accepted range `1..100` |
|
||||
|
||||
These variables are consumed by the framework-owned Pi goal extension at goal creation. Invalid or
|
||||
out-of-range values fall back to the defaults; they do not disable the bounds.
|
||||
|
||||
### Providers
|
||||
|
||||
| Variable | Default | Description |
|
||||
@@ -385,29 +374,3 @@ Session cleanup is scoped to one session identifier and only removes that sessio
|
||||
| Variable | Default | Description |
|
||||
| ----------------------- | ----------------------------- | ------------------------------------------ |
|
||||
| `MOSAIC_WORKSPACE_ROOT` | monorepo root (auto-detected) | Root path for mission workspace operations |
|
||||
|
||||
---
|
||||
|
||||
## Pi Goal Loop Operations
|
||||
|
||||
The reviewed runtime asset is deployed at
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts` by framework install/update. Do not install another
|
||||
copy under `~/.pi/agent/extensions/`; duplicate registration can create suffixed commands and two
|
||||
competing lifecycle controllers.
|
||||
|
||||
Operational checks:
|
||||
|
||||
1. Run `mosaic pi` and verify `/goal help` is available.
|
||||
2. Use `/goal status` to inspect phase, turn/no-progress limits, compaction checks, and evidence.
|
||||
Reports persist in Pi session data; controller-owned state redacts common credential shapes, but
|
||||
Pi's model/tool-call history is separate. Operators must not place secrets or raw sensitive output
|
||||
in goals, pause reasons, or evidence.
|
||||
3. Use `/goal pause <reason>` before planned maintenance or manual investigation. Pause and cancel
|
||||
abort the current goal-driven run when Pi is busy.
|
||||
4. Use `/goal resume` only after addressing a blocker; counters restart with the configured bounds.
|
||||
5. Use `/goal cancel` before replacing an unfinished goal.
|
||||
|
||||
A blocked or exhausted goal remains stopped and visible; Mosaic does not automatically raise its
|
||||
limits or restart the process. Framework sync owns file deployment, while Pi's native session file
|
||||
owns branch replay. Process/host restart remains the responsibility of the existing runtime or fleet
|
||||
supervisor.
|
||||
|
||||
@@ -9,9 +9,8 @@
|
||||
5. [Adding New MCP Tools](#adding-new-mcp-tools)
|
||||
6. [Database Schema and Migrations](#database-schema-and-migrations)
|
||||
7. [Claude Code Skill Bridge](#claude-code-skill-bridge)
|
||||
8. [Pi Persistent Goal Extension](#pi-persistent-goal-extension)
|
||||
9. [API Endpoint Reference](#api-endpoint-reference)
|
||||
10. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
8. [API Endpoint Reference](#api-endpoint-reference)
|
||||
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -386,85 +385,6 @@ M1 intentionally manages Claude Code only. Pi's Mosaic launcher can discover the
|
||||
canonical root directly. Codex still relies on the existing full skill-sync
|
||||
linker and needs separate parity analysis before this lifecycle API is extended.
|
||||
|
||||
## Pi Persistent Goal Extension
|
||||
|
||||
The source of the Mosaic-owned Pi goal controller is:
|
||||
|
||||
```text
|
||||
packages/mosaic/framework/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
The framework manifest classifies `runtime/**` as framework-owned. Both the bash installer and the
|
||||
TypeScript file adapter therefore deploy the same reviewed source to:
|
||||
|
||||
```text
|
||||
$MOSAIC_HOME/runtime/pi/goal-extension.ts
|
||||
# default: ~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
Do not copy or link this extension into `~/.pi/agent/extensions/`. The launcher function
|
||||
`discoverPiExtensionArgs()` emits the core `mosaic-extension.ts` first and the optional
|
||||
`goal-extension.ts` second, preserving compatibility with an older installed framework that does
|
||||
not have the goal file yet.
|
||||
|
||||
### Lifecycle design
|
||||
|
||||
| Pi API | Goal-controller responsibility |
|
||||
| ------------------------------ | --------------------------------------------------------------------------------- |
|
||||
| `registerCommand('goal')` | Set, inspect, pause, resume, or cancel one branch-specific goal |
|
||||
| `registerTool(...)` | Record a terminating structured progress report with evidence |
|
||||
| `context` | Inject the active goal contract before every provider request |
|
||||
| `turn_end` | Record every turn, reject mixed final reports, and enforce the turn bound |
|
||||
| `agent_settled` | Start one deduplicated continuation only after Pi has no retry/compact/queue work |
|
||||
| `session_compact` | Record the compact check, reset provisional verification, and defer idle work |
|
||||
| `session_start`/`session_tree` | Rebuild state from custom entries on the active branch |
|
||||
| `session_shutdown` | Invalidate deferred callbacks and clear UI state |
|
||||
|
||||
State is appended as `mosaic-goal-state` custom entries, which do not enter model context. The
|
||||
`context` hook creates a fresh hidden `mosaic-goal-context` message for each request instead of
|
||||
trusting compaction summaries. The `mosaic_goal_report` result uses `terminate: true`; when it is the
|
||||
sole final tool call, Pi avoids an unnecessary model response before the controller decides whether
|
||||
to verify, continue, or stop.
|
||||
|
||||
Before state is appended or displayed, the controller applies bounded credential-pattern redaction
|
||||
to the goal statement, report summary/evidence/next step, and stop reason. Fingerprints are computed
|
||||
over redacted report content. Pi session entries are append-only, so a credential-bearing legacy
|
||||
entry cannot honestly be erased by the extension: restoration fails closed, emits a warning, and
|
||||
requires removal of the affected session before setting a new goal. This is defense-in-depth rather
|
||||
than a secret-storage contract, and it does not rewrite Pi's separate model-message/tool-call
|
||||
history. Goal prompts tell the agent not to submit credentials or raw sensitive output, and tests use
|
||||
canaries to prove known forms do not reach new custom entries, status text, context, or tool details
|
||||
while ordinary typed fields such as `token: string` remain intact.
|
||||
|
||||
Completion remains evidence-gated but semantic: two consecutive `achieved` reports are required,
|
||||
and the second run is explicitly a verification pass. This avoids an extra judge-model request after
|
||||
every turn. Deterministic validator commands are intentionally not accepted as `/goal` input in this
|
||||
slice, so never describe this mechanism as proof of arbitrary natural-language completion.
|
||||
|
||||
### Tests and local smoke workflow
|
||||
|
||||
```bash
|
||||
pnpm --filter @mosaicstack/mosaic exec vitest run \
|
||||
src/runtime/pi-goal-extension.spec.ts \
|
||||
src/commands/launch.spec.ts \
|
||||
src/config/file-adapter.test.ts
|
||||
|
||||
bash packages/mosaic/framework/tools/quality/scripts/test-install-migration.sh
|
||||
```
|
||||
|
||||
For an additive local smoke test without reseeding unrelated live framework files:
|
||||
|
||||
```bash
|
||||
install -D -m 0644 \
|
||||
packages/mosaic/framework/runtime/pi/goal-extension.ts \
|
||||
~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
|
||||
pi --extension ~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
Use `/goal help`, `/goal set ...`, and `/goal status` in that test session. A released framework
|
||||
sync installs the file, and a released Mosaic CLI loads it automatically through `mosaic pi`.
|
||||
|
||||
## API Endpoint Reference
|
||||
|
||||
All endpoints are served by the gateway at `http://localhost:14242` by default.
|
||||
|
||||
@@ -8,10 +8,9 @@
|
||||
4. [Tasks](#tasks)
|
||||
5. [Settings](#settings)
|
||||
6. [CLI Usage](#cli-usage)
|
||||
7. [Pi Persistent Goals](#pi-persistent-goals)
|
||||
8. [Sub-package Commands](#sub-package-commands)
|
||||
9. [Telemetry](#telemetry)
|
||||
10. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
7. [Sub-package Commands](#sub-package-commands)
|
||||
8. [Telemetry](#telemetry)
|
||||
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -308,57 +307,6 @@ mosaic prdy
|
||||
mosaic quality-rails
|
||||
```
|
||||
|
||||
## Pi Persistent Goals
|
||||
|
||||
`mosaic pi` loads a Mosaic-owned goal extension from
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts`. It is deliberately not installed in
|
||||
`~/.pi/agent/extensions/`; framework installation and updates manage it with the rest of the Mosaic
|
||||
runtime assets.
|
||||
|
||||
Start Pi, then set a goal:
|
||||
|
||||
```text
|
||||
/goal set Deliver the feature, tests, documentation, and verification evidence
|
||||
# Shorthand:
|
||||
/goal Deliver the feature, tests, documentation, and verification evidence
|
||||
```
|
||||
|
||||
Control and inspect the loop with:
|
||||
|
||||
| Command | Behavior |
|
||||
| ---------------------- | ------------------------------------------------------------------ |
|
||||
| `/goal status` | Show phase, limits, compaction checks, latest report, and evidence |
|
||||
| `/goal pause [reason]` | Stop autonomous continuation while preserving the goal |
|
||||
| `/goal resume` | Resume with fresh turn and no-progress counters |
|
||||
| `/goal cancel` | Cancel the goal and remove its active status |
|
||||
| `/goal help` | Show command help |
|
||||
|
||||
While a goal is active, Mosaic injects its contract before every Pi model request and checks every
|
||||
completed model/tool turn. The agent ends each work cycle with the structured
|
||||
`mosaic_goal_report` tool. `achieved` is provisional until a second consecutive report rechecks the
|
||||
whole goal with evidence. A continuation report or a successful compaction resets provisional
|
||||
verification.
|
||||
|
||||
Goal statements and reports are stored in Pi session data. Mosaic redacts common credential shapes
|
||||
before appending its goal-state entries and before goal tool output or `/goal status`, but
|
||||
pattern-based redaction is not a secret store. Pi's own model-message and tool-call records are
|
||||
outside that redactor. Never put tokens, passwords, private keys, connection strings, or raw
|
||||
sensitive output in a goal or report; cite the command, artifact, and pass/fail result instead.
|
||||
|
||||
The loop stops instead of running forever when it is paused, blocked, cancelled, verified, reaches
|
||||
its turn limit, or repeats the same no-progress report too many times. Defaults are 40 turns and 6
|
||||
repeated no-progress reports. Operators may lower or raise them within enforced bounds before
|
||||
launching Pi:
|
||||
|
||||
```bash
|
||||
MOSAIC_GOAL_MAX_TURNS=60 MOSAIC_GOAL_MAX_NO_PROGRESS=8 mosaic pi
|
||||
```
|
||||
|
||||
Goal state is branch-specific Pi session data. It survives compaction and session resume, but Pi's
|
||||
process still must be relaunched or supervised after a process/host failure. This initial verifier
|
||||
checks structured evidence twice; it cannot mathematically prove every arbitrary natural-language
|
||||
goal. Use explicit acceptance criteria and inspect `/goal status` for consequential work.
|
||||
|
||||
---
|
||||
|
||||
### Claude Code Skill Registration
|
||||
|
||||
@@ -13,13 +13,3 @@ Correct for the CI container (runs as root), fatal for EVERY non-root local chec
|
||||
### **D-2 / hygiene — husky `prepare` fails `EPERM` copying into root-owned `.husky/_/`.** Repo working
|
||||
|
||||
tree has root-owned dirs (`.husky/`, repo root) under a non-root agent. Worked around with the intended `HUSKY=0` escape hatch (does NOT disable the existing pre-commit/pre-push hooks).
|
||||
|
||||
<!-- board-roll: 2 entries rolled from BOARD.md -->
|
||||
|
||||
### **D-5 / P-QUEUE-001 + P-CONFORMANCE-001 — KEYSTONE: an inert gate that erased its own evidence.**
|
||||
|
||||
Merged PR #868 (`b79336a8`) shipped a file that FAILS `pnpm format:check` ⇒ the CI format gate did not block. An unrelated later PR (#872) then reformatted that file via its own `lint-staged`, so `main` went green again and nobody learned the gate had failed to fire. Verified blob-level under the repo's own config. **Detection must be per-merge-commit against that commit's own tree** — a "is main green today" check reports all-clear on this exact defect. Binding on RM-02/RM-55. Full chain in `TASKS.md` §1a. NOT quiet-patched, by Mos's ruling: patching the symptom destroys the signal.
|
||||
|
||||
### **D-4 / P-LIFECYCLE + hygiene — a dispatched agent silently IGNORED an in-message context reset.**
|
||||
|
||||
planner-sol was at 64.3%/372k; the brief asked it to reset first; it began work on dirty context anyway. Only an out-of-band `/new` driven by the orchestrator guaranteed clean state. Confirms the postmortem thesis: **instructions are not enforcement.** Reset must be a mechanical pre-dispatch step, not a request.
|
||||
|
||||
+17
-16
@@ -1,6 +1,6 @@
|
||||
# mos-remediation — LIVE BOARD (keep < 8 KB)
|
||||
|
||||
**Phase:** EXECUTING — P0 open. RM-01 MERGED; RM-02 (keystone gate registry) is next.
|
||||
**Phase:** EXECUTING — first PR merged; RM-01 in flight; all 3 decisions ruled.
|
||||
**Updated:** 2026-07-31 (mos-remediation orchestrator; seat active on `mosaic-fleet`).
|
||||
|
||||
## Head
|
||||
@@ -16,13 +16,14 @@
|
||||
|
||||
## In-flight
|
||||
|
||||
| Task | Owner | State |
|
||||
| ----------------------------------- | --------------- | ------------------------------------------------------------------------- |
|
||||
| RM-01 reproducible checkout | — | **MERGED** `f58b3699` (PR #1027) — rev-974 APPROVE + CI #2172 8/8 green |
|
||||
| RM-02 gate registry ★keystone | unassigned | **READY** — depends only on RM-01; not held by RM-03 |
|
||||
| RM-03 queue guard (3 defects) | — | HOLD — #1023 SUPERSEDED-PENDING-JASON |
|
||||
| RM-59 close D-19 residual risk | — | BLOCKED by RM-12/RM-21/RM-25 (spine + executor) — tracked edge, not prose |
|
||||
| `remediation/state` snapshot → main | mos-remediation | opening at this mission seam |
|
||||
| Task | Owner | State |
|
||||
| ------------------------------------------------- | --------------- | ------------------------------------------------------------------ |
|
||||
| PR #1026 docs (mission record + backlog) | mos-remediation | OPEN, retargeted to main, rebased; diff verified docs-only |
|
||||
| PR #1025 hygiene | — | **MERGED** 52414605; rev-974 APPROVE + CI #2158 8/8 terminal-green |
|
||||
| DECISION-1 wire-in point (charter change) | Mos / Jason | ESCALATED — both planners reject the charter's target |
|
||||
| DECISION-2 rollback artifact + availability trade | Jason | ESCALATED |
|
||||
| DECISION-3 RM-03 vs parked PR #1023 ownership | Mos | ESCALATED |
|
||||
| RM-01 reproducible checkout (unblocks everything) | unassigned | READY TO DISPATCH |
|
||||
|
||||
## Fleet seats
|
||||
|
||||
@@ -38,14 +39,6 @@
|
||||
- Freeze: LIFTED for this workstream only.
|
||||
- Git identity: `MOSAIC_GIT_IDENTITY=mos-dt-0` INTERIM. Mos ruled gate-16 HOLDS (author≠reviewer is what
|
||||
gate-16 protects; rev-974 reviews, mos-dt-0 never self-reviews). Dedicated identity TRACKED, Mos provisions.
|
||||
- Capability check (D-11b): before dispatching seat X to provider Y, verify
|
||||
`~/.config/mosaic/secrets/gitea-tokens/gitea-<Y>-<X>.token` exists. Token-file set = authoritative
|
||||
capability registry. Mos owns provisioning; escalate missing pairs to him.
|
||||
- Seat identity (D-11a): token identity AND `git config user.name`/`user.email` must BOTH be set and
|
||||
agree. Exporting `MOSAIC_GIT_IDENTITY` alone does NOT fix commit authorship.
|
||||
- Standing worker-brief doctrine (accreted, mandatory in every brief): don't weaken a RED test to make
|
||||
it pass; if a check is unrunnable as written SAY SO, never silently substitute; `agent-send -f` never
|
||||
`-m`; heavy artifacts off shared `/tmp`.
|
||||
- Remote control: native `/remote-control` NOT wired in this runtime. Path is **Mos-relay**
|
||||
(Jason ↔ mos-claude via Discord ↔ mos-remediation via agent-send). Not a blocker.
|
||||
|
||||
@@ -79,6 +72,14 @@ PR #1025 AC2's fixture `mkdir -p apps/*/venv/lib` creates a literal `apps/*/venv
|
||||
|
||||
Running the required `ci-queue-wait.sh --purpose push` before pushing produced `state=unknown ... exit 0` — the exact defect at `ci-queue-wait.sh:282-288` that PR #1023 is parked on. It also evaluated `branch=main` rather than the branch being pushed. The mission's own required pre-push gate passed me on an indeterminate result. Third independent live instance of the class.
|
||||
|
||||
### **D-5 / P-QUEUE-001 + P-CONFORMANCE-001 — KEYSTONE: an inert gate that erased its own evidence.**
|
||||
|
||||
Merged PR #868 (`b79336a8`) shipped a file that FAILS `pnpm format:check` ⇒ the CI format gate did not block. An unrelated later PR (#872) then reformatted that file via its own `lint-staged`, so `main` went green again and nobody learned the gate had failed to fire. Verified blob-level under the repo's own config. **Detection must be per-merge-commit against that commit's own tree** — a "is main green today" check reports all-clear on this exact defect. Binding on RM-02/RM-55. Full chain in `TASKS.md` §1a. NOT quiet-patched, by Mos's ruling: patching the symptom destroys the signal.
|
||||
|
||||
### **D-4 / P-LIFECYCLE + hygiene — a dispatched agent silently IGNORED an in-message context reset.**
|
||||
|
||||
planner-sol was at 64.3%/372k; the brief asked it to reset first; it began work on dirty context anyway. Only an out-of-band `/new` driven by the orchestrator guaranteed clean state. Confirms the postmortem thesis: **instructions are not enforcement.** Reset must be a mechanical pre-dispatch step, not a request.
|
||||
|
||||
<!-- BOARD-ROLL:END -->
|
||||
|
||||
## Decisions log
|
||||
|
||||
@@ -7,15 +7,10 @@ mechanically until Build 3 (rotation) makes it automatic.
|
||||
|
||||
## On resume (do in order, before any orchestration action)
|
||||
|
||||
1. `cd /src/mosaic-stack`, then **`git fetch origin remediation/state`**.
|
||||
⚠ **The live board is on the rolling branch `remediation/state`, NOT on `main`.** `main` carries only
|
||||
periodic snapshots, so reading the board from `main` will silently give you a STALE tick. Read the
|
||||
live files at `origin/remediation/state` (e.g. `git show origin/remediation/state:docs/remediation/BOARD.md`),
|
||||
or check that branch out. Every tick is pushed there immediately, so its HEAD is always the newest state.
|
||||
1. `cd /src/mosaic-stack` and confirm you are on the remediation working branch.
|
||||
2. Read `docs/remediation/MISSION.md` — the charter (goal, 4 builds, 15 decisions, sequencing, directives).
|
||||
3. Read `docs/remediation/BOARD.md` **at `origin/remediation/state`** — the LIVE state: current phase,
|
||||
in-flight tasks, fleet seat assignments, gate status. Single source of in-flight truth (kept < 8 KB;
|
||||
older entries roll to `BOARD-LEDGER.md` via `board-roll.sh`).
|
||||
3. Read `docs/remediation/BOARD.md` — the LIVE state: current phase, in-flight tasks, fleet seat assignments,
|
||||
gate status. This is your single source of in-flight truth (kept small).
|
||||
4. Read the discussion checkpoint for full rationale if needed:
|
||||
`../jarvis-brain/docs/scratchpads/postmortem/REMEDIATION-DISCUSSION-STATE.md` (or the jarvis-brain repo path).
|
||||
5. **Residency attestation (fail-closed):** restate from the reloaded files — (a) the goal in one line, (b) the
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Mosaic Stack Remediation — Mission Charter
|
||||
|
||||
**Owner:** project orchestrator `mos-remediation` (Claude, launched in `/src/mosaic-stack`).
|
||||
**Origin:** 2026-07-16..31 fleet lifecycle postmortem. **Status:** EXECUTING (planning complete; RM-01 in flight).
|
||||
**Origin:** 2026-07-16..31 fleet lifecycle postmortem. **Status:** PLANNING (task decomposition).
|
||||
**HOLD lifted** for this workstream by Jason, 2026-07-31 — "begin full mosaic fleet operation on this."
|
||||
|
||||
## Goal
|
||||
@@ -10,104 +10,23 @@ Convert the 15 accepted postmortem remediation proposals into a working, **dogfo
|
||||
**North star:** anything with a deterministic right answer moves OUT of the LLM into a deterministic
|
||||
gate/program; the LLM handles only genuine judgment.
|
||||
|
||||
### First-class principle — observe the property, not the exit code
|
||||
|
||||
> **No write is done until the requested PROPERTY is observed. A success exit code is not evidence.**
|
||||
>
|
||||
> **Success output is designed to be believed.** That is the whole reason the inert-gate class exists
|
||||
> and why P-WRAPPER-001's tri-state (`verified` / `written-unverified` / `failed`) is not optional. The
|
||||
> failure is not carelessness — a green is _engineered_ to be trusted, so trusting it is the default
|
||||
> behaviour of a competent operator, not a lapse.
|
||||
>
|
||||
> Promoted to the charter by Mos (2026-07-31) after the orchestrator committed this exact error: a
|
||||
> `--draft` flag was silently dropped by a wrapper fallback that still exited 0, and the PR was reported
|
||||
> as a draft on the strength of the exit code rather than an observed `draft: true` (D-12). Twelve
|
||||
> failure instances were banked in that session; **three of them were the orchestrator's own.** That
|
||||
> ratio is the point — the mechanism must catch the mechanic too, or it is not a mechanism.
|
||||
>
|
||||
> Operationally: after any write, read back the property you required. Applies to gates, wrappers, PR
|
||||
> flags, commit authorship, file installs, and message delivery alike.
|
||||
|
||||
### First-class principle — pre-registration prevents retrofitting, and nothing else
|
||||
|
||||
> **A pre-registered check set can fail in three distinct ways:**
|
||||
>
|
||||
> | mode | the set is… | found as |
|
||||
> | --------------------------- | ------------------------------------------------- | -------- |
|
||||
> | **WRONG** | a check does not test what it claims | D-8 |
|
||||
> | **INCOMPLETE** | green while a criterion's requirement is untested | D-17 |
|
||||
> | **INTERNALLY INCONSISTENT** | two criteria cannot both hold | D-18 |
|
||||
>
|
||||
> **Pre-registration protects against exactly one thing: retrofitting a check to fit the implementation
|
||||
> it is supposed to judge.** It confers neither correctness, nor coverage, nor consistency. "We
|
||||
> pre-registered the checks" has been treated as though it settled the question — it settles one of
|
||||
> three.
|
||||
>
|
||||
> Promoted to the charter by Mos (2026-07-31). All three modes were found on this mission's own **first
|
||||
> delivery**, by the machinery applied to its own work — not by inspection, and not by looking for them.
|
||||
>
|
||||
> **Enforceable form — RM-02's four clauses.** The registry must establish that: (1) each check is
|
||||
> **right** — proven red for its own stated reason before its green counts; (2) the set **covers** —
|
||||
> every criterion bound to a case that actually exercises it; (3) no two criteria **conflict** —
|
||||
> mutual unsatisfiability is a registry defect discoverable by construction; (4) when a criterion's
|
||||
> meaning changes, the registry **retains original text, restatement, and reason**, so evolution stays
|
||||
> auditable. A criterion with no case that can fail for its own reason is unregistered in substance,
|
||||
> however it reads in the manifest.
|
||||
|
||||
### Corollary — never ship an integrity claim dressed as a property
|
||||
|
||||
> A verification artifact that can be forged by whoever it is meant to catch verifies nothing. If a
|
||||
> manifest, marker, ledger, or receipt is writable by the same actor whose behaviour it certifies, it
|
||||
> **certifies the attack.** Such an artifact must sit inside the integrity envelope it belongs to,
|
||||
> publish atomically, and carry a **tamper negative-control observed red** — otherwise its integrity is
|
||||
> a _claim_, not a _property_.
|
||||
>
|
||||
> **If it cannot be made tamper-evident, say so and reconsider the approach.** Laundering foreign
|
||||
> content as certified is the only unacceptable outcome; an honest "this cannot be verified" is always
|
||||
> available and always preferable.
|
||||
|
||||
### First-class principle — when a property cannot exist at the layer it was specified
|
||||
|
||||
> Some required properties are **impossible at the layer that asked for them** — not hard, impossible.
|
||||
> A local check cannot defend against an actor who can rewrite the check itself. When that happens,
|
||||
> there are exactly three honest moves, and all three are mandatory:
|
||||
>
|
||||
> 1. **Implement what the layer _can_ guarantee.** Partial protection against the class it was actually
|
||||
> born from is worth having.
|
||||
> 2. **State the boundary precisely, in BOTH directions.** What it does _not_ defend, **and** beside it
|
||||
> what it _does_. A reader who sees only the negative dismisses the check as worthless; one who sees
|
||||
> only the positive over-trusts it. **Both together is the honest artifact** — either alone misleads.
|
||||
> 3. **Record where the real guarantee will come from — as a TRACKED DEPENDENCY, not prose.** It must
|
||||
> name a task that someone must close. _A documented gap with no owner becomes a permanent gap that
|
||||
> reads as intentional._
|
||||
>
|
||||
> **A written-down gap is acceptable engineering. An implied-fixed gap is this mission's core failure in
|
||||
> a new costume** — a verification artifact that verifies nothing, with a green to prove it.
|
||||
>
|
||||
> Promoted to the charter by Mos (2026-07-31) from D-19. Origin: the RM-01 symlink manifest could not be
|
||||
> made tamper-evident against a same-UID actor (CWE-345), because the manifest and its marker share one
|
||||
> writable tree. The implementing seat **escalated rather than relabelling self-authentication as
|
||||
> tamper-resistance** — the corollary above firing on its first real adversarial test, on the cheapest
|
||||
> seat in the loop. Residual risk bound to **RM-59** (`depends_on: RM-12, RM-21, RM-25`), where the
|
||||
> choke-point executor and spine verify from _outside_ the worktree's authority.
|
||||
|
||||
## Decision record (authoritative, immutable)
|
||||
|
||||
- **15/15 proposals decided: 13 accept, 2 modify (P-AUTHORITY-001, P-INBOX-001), 0 reject.**
|
||||
- Site + `annotations.json`: `jarvis-brain/docs/postmortem-spec/site/` (committed, origin/main).
|
||||
- Discussion checkpoint (rich rationale per proposal): `jarvis-brain/docs/scratchpads/postmortem/REMEDIATION-DISCUSSION-STATE.md`.
|
||||
- Postmortem report: mosaicstack/stack PR #107 (merged 88f4ee04).
|
||||
- MACP wiring scout (verdict c=STRANDED): [`MACP-WIRING-SCOUT.md`](./MACP-WIRING-SCOUT.md) (copied into this dir; TODO discharged). Its findings are sound; its _recommended wire-in point_ is superseded by DECISION-1.
|
||||
- MACP wiring scout (verdict c=STRANDED): `/tmp/macp-wiring-investigation.md` (copy into this dir — see TODO).
|
||||
|
||||
## The plan — 15 proposals collapse to 4 builds + hygiene
|
||||
|
||||
| Build | Absorbs | What it is |
|
||||
| ------------------------------------------------------------ | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| **1. One choke-point service** (mechanical enforcer) | MISSION, STATE, AUDIT, WRAPPER, QUEUE | Deterministic program every task/data mutation flows through. **Wire the stranded `@mosaicstack/macp`** — typed tasks, gate-runner, event ledger, credential binding, tri-state write outcomes. ⚠ **Target CORRECTED 2026-07-31 (DECISION-1, Mos):** a new production Node `TaskExecutor` on the **live** dispatch path (`packages/mosaic` launch + `packages/coord`), which Coord/Forge/live-dispatch submit through. **NOT** `mosaic_orchestrator.py::run_single_task` — that controller is `"enabled": false` and references a dispatcher absent from this checkout; wiring it would strand the executor, reproducing this mission's own disease. The Python rail is **deleted**, not ported. Both planners reached this independently. |
|
||||
| **2. One durable spine + hot path** | (storage under everything) | **PG system-of-record + Redis hot queue** (transactional-outbox). Mission/tasks/state-claims/audit-ledger/comms-inbox all land here. |
|
||||
| **3. Rotation lifecycle** (finish the Mission Control Plane) | LIFECYCLE, CONTRACT, GUIDE, RECOVERY | Coordinator daemon: contract-hash binding, compaction-detected → rotate-not-compact, checkpoint→fresh-session→rehydrate, broker-independent recovery. Deterministic, not an LLM. Reuse `packages/coord`; existing PRD at `docs/mission-control/`. |
|
||||
| **4. Comms service** | AUTHORITY, INBOX (+ versioning roadmap) | Envelope (comms/v1) → sole-path service → PG/Redis → pluggable adapters (tmux→Matrix/Discord/Slack/Telegram). Version the protocol, not participants. |
|
||||
| **+ Hygiene & proof** | FLEET, WORKFLOW, CONFORMANCE | One roster-owned socket/host + stale GC; allowlist auto-sync; the conformance harness that fault-injects the failure classes and proves builds 1–4 hold. |
|
||||
| Build | Absorbs | What it is |
|
||||
| ------------------------------------------------------------ | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| **1. One choke-point service** (mechanical enforcer) | MISSION, STATE, AUDIT, WRAPPER, QUEUE | Deterministic program every task/data mutation flows through. **Wire the stranded `@mosaicstack/macp`** in at `mosaic_orchestrator.py::run_single_task` — typed tasks, gate-runner, event ledger, credential binding, tri-state write outcomes. |
|
||||
| **2. One durable spine + hot path** | (storage under everything) | **PG system-of-record + Redis hot queue** (transactional-outbox). Mission/tasks/state-claims/audit-ledger/comms-inbox all land here. |
|
||||
| **3. Rotation lifecycle** (finish the Mission Control Plane) | LIFECYCLE, CONTRACT, GUIDE, RECOVERY | Coordinator daemon: contract-hash binding, compaction-detected → rotate-not-compact, checkpoint→fresh-session→rehydrate, broker-independent recovery. Deterministic, not an LLM. Reuse `packages/coord`; existing PRD at `docs/mission-control/`. |
|
||||
| **4. Comms service** | AUTHORITY, INBOX (+ versioning roadmap) | Envelope (comms/v1) → sole-path service → PG/Redis → pluggable adapters (tmux→Matrix/Discord/Slack/Telegram). Version the protocol, not participants. |
|
||||
| **+ Hygiene & proof** | FLEET, WORKFLOW, CONFORMANCE | One roster-owned socket/host + stale GC; allowlist auto-sync; the conformance harness that fault-injects the failure classes and proves builds 1–4 hold. |
|
||||
|
||||
## The finding that sets the cost
|
||||
|
||||
@@ -118,7 +37,6 @@ orphaned context loader, a fail-open bypass. **Work = wire + consolidate + retir
|
||||
## Sequencing (skeleton — adversarial decomposition refines this)
|
||||
|
||||
1. **Spine + choke-point service** (builds 1+2) — foundation; unlocks MISSION/STATE/AUDIT/WRAPPER/QUEUE at one integration point.
|
||||
(Per DECISION-1, a P0 phase of provable-gate + activation work precedes this; see `TASKS.md` §3.)
|
||||
2. **Rotation daemon** (build 3) on that spine — the drift fix proper.
|
||||
3. **Comms service** (build 4) — envelope → service → PG/Redis → adapters; retire direct-tmux.
|
||||
4. **Hygiene + conformance** (build 5) — fleet convergence, allowlist sync, dogfood harness.
|
||||
@@ -132,11 +50,6 @@ orphaned context loader, a fail-open bypass. **Work = wire + consolidate + retir
|
||||
(WRAPPER), auto-sync sweep (WORKFLOW), #1018 stale-consumed (INBOX). The fleet is its own test bed.
|
||||
- **Orchestration tracking → DB**, hard cutover ("rip off the bandaid"), NO flat-file interim. jarvis-brain
|
||||
PDA flat-files untouched. Current flat-file tracking runs as-is/unhardened until DB tracking is real, then one clean replace.
|
||||
- ⚠ **QUALIFIED 2026-07-31 (DECISION-2, Mos):** the DB spine **must NOT be a single-point hard-stop.**
|
||||
A broker-independent / degraded mode **and** a rehearsed rollback artifact are **design requirements**
|
||||
(P-RECOVERY-001), binding now on RM-12, RM-13, RM-23, RM-36 and RM-53. This **supersedes** the earlier
|
||||
orchestrator recommendation to pre-commit "no DB ⇒ the fleet stops" — that answer is _not_ on record.
|
||||
Only the specific availability _target_ remains open, queued for Jason; it does **not** block current work.
|
||||
|
||||
## The 15 decisions (one-line; full rationale in the checkpoint)
|
||||
|
||||
|
||||
+11
-526
@@ -93,520 +93,6 @@ and must not be cited as merge evidence. Rely on reviewer clearance + real CI.
|
||||
Three independent live instances in a single session — format gate, agent context reset, queue guard —
|
||||
is the class confirmed, not anecdote.
|
||||
|
||||
### D-20 — the orchestrator's own documentation overclaimed, and a reviewer disproved it empirically
|
||||
|
||||
`rev-974` blocked PR #1027 a second time. **The defect was not in the code — it was in this file**, at
|
||||
D-18's entry, written by the orchestrator.
|
||||
|
||||
Two faults, both mine:
|
||||
|
||||
1. **D-18's AC2 restatement omitted the scope clause** that D-19 later established as mandatory
|
||||
("within an accidental/independent-mutation threat model").
|
||||
2. **D-18 asserted that the tampered-manifest control turns integrity "from a claim into a property."**
|
||||
It does not, and _cannot_. That sentence was written **before** D-19 proved the property impossible
|
||||
at this layer, and was never revised when D-19 landed.
|
||||
|
||||
**The reviewer did not merely read it — it disproved it.** It performed a **same-UID consistent
|
||||
manifest + marker rewrite**, and **preflight passed**. My documented claim was falsified by experiment.
|
||||
Code, README, scratchpad and PR body all stated both threat-model directions correctly; **this file was
|
||||
the only place still overclaiming.**
|
||||
|
||||
**This is two banked findings firing on the orchestrator at once:**
|
||||
|
||||
- **The integrity-claim corollary** — I wrote an integrity _claim_ in the voice of an integrity
|
||||
_property_, in the very document that defines the rule against doing so.
|
||||
- **D-14 (propagation)** — D-19 superseded D-18's assertion. I propagated the consequence into the
|
||||
charter and the delivery conditions, but **not back into D-18 itself.** A ruling that fails to
|
||||
propagate _backwards_ into the finding it supersedes is the same defect as one that fails to
|
||||
propagate forwards, and I did not audit for that direction.
|
||||
|
||||
**Corrected in place**, with the original wording quoted and the empirical disproof recorded, rather
|
||||
than silently rewritten — the same standard demanded of any restated criterion.
|
||||
|
||||
**Requirement on RM-02 (fifth clause).** Documentation asserting a _security or integrity_ property is
|
||||
itself a claim requiring a negative control. Where a document states "X is guaranteed", the registry
|
||||
must hold a case that **fails if X is not guaranteed** — and that case must have been observed red.
|
||||
**Prose is not exempt from the mission's own evidentiary standard**, and prose in the _governing_
|
||||
document least of all: it is the artifact most likely to be quoted as authority long after the code has
|
||||
moved on.
|
||||
|
||||
**Reviewer credit.** rev-974 was briefed that its highest-priority check was "confirm the PR claims no
|
||||
more than it can deliver, and a softened or omitted boundary is a finding even though the code works."
|
||||
It applied that instruction **to the orchestrator's own governing document** and produced an experiment
|
||||
to settle it. That is the review standard this mission is trying to make ordinary.
|
||||
|
||||
### D-19 — an integrity property that cannot exist at the layer it was specified
|
||||
|
||||
Implementing D-18's manifest, the seat + a Codex security review reached **CWE-345**: the symlink
|
||||
manifest and the source-hash marker both live in the **same same-UID writable generated tree**, so an
|
||||
actor with that UID can plant a rogue link, regenerate _both_, retain the fingerprint, and pass. **No
|
||||
local cryptographic construction fixes self-authentication** without a key outside that actor's
|
||||
authority; relocating the marker changes the path, not the authority.
|
||||
|
||||
The seat **escalated rather than describing self-authentication as tamper-resistant** — the explicit
|
||||
failure mode the charter corollary demands. That is the corollary working, on its first real test.
|
||||
|
||||
**Ruling — Option A: scope AC2 to accidental / independent / stale mutation; retain the design.**
|
||||
Rationale, recorded so it can be challenged:
|
||||
|
||||
1. **The undefendable boundary is not the weak link.** An actor with same-UID write can already edit the
|
||||
source, the tests, `scripts/preflight.mjs` itself, and `.husky/*`. If they have that, _nothing_ in the
|
||||
local checkout is trustworthy — hardening the manifest buys no real security while **implying
|
||||
protection that does not exist**, which is worse than the gap.
|
||||
2. **What AC2 is actually for.** These checks exist because a five-month-stale `.next` produced 19
|
||||
phantom `TS2307` errors indistinguishable from real ones (**D-5**). That is staleness, drift and
|
||||
foreign residue — and against that class the design demonstrably works.
|
||||
3. **A real trust anchor arrives later, from this mission's own architecture.** An anchor must live
|
||||
outside the actor's authority; for a fleet running as one user that means a separate service —
|
||||
precisely the **choke-point executor + PG spine** of Builds 1–2, which verify outside the worktree's
|
||||
authority. Hand-rolling key distribution for a local preflight now would duplicate that work badly.
|
||||
4. Option C (structural policy, no manifest) is strictly worse — it cannot detect a **removed** expected link.
|
||||
|
||||
**Option A is acceptable only with honest labelling**, or it becomes the disease it is meant to cure.
|
||||
Conditions (last two added/sharpened by Mos):
|
||||
|
||||
- Threat model stated verbatim in the code **and** the PR; the words _tamper-proof / tamper-evident /
|
||||
secure_ **barred** from that context; the scope carried in AC2's restatement; every control kept
|
||||
RED-first including manifest-only tamper.
|
||||
- **State the boundary in BOTH directions.** Not only what it does _not_ defend (same-UID write; no
|
||||
local construction can) but, beside it, what it **does** defend: accidental / independent / stale /
|
||||
foreign-residue mutation — the **D-5** class it was born from (the five-month `.next` and its 19
|
||||
phantom `TS2307`s). _A reader who sees only the negative dismisses the check as worthless; one who
|
||||
sees only the positive over-trusts it. Both together is the honest artifact._
|
||||
- **The residual risk is a HARD TRACKED DEPENDENCY EDGE, not a comment.** It is **RM-59**, owned by the
|
||||
choke-point executor + spine work (`depends_on: RM-12, RM-21, RM-25`), and the AC2 scope note must
|
||||
cite that id. _"Record where the real guarantee comes from" only holds if the record is a live
|
||||
dependency someone must close._ **A documented gap with no owner becomes a permanent gap that reads
|
||||
as intentional.**
|
||||
|
||||
**The generalizable rule.** When a required property **cannot exist at the layer where it was
|
||||
specified**, the honest moves are: implement what the layer _can_ guarantee, **state the boundary
|
||||
precisely**, and record where the real guarantee will come from. **A known gap that is written down is
|
||||
acceptable; a gap that is implied fixed is not.** Silence here would have shipped a verification
|
||||
artifact that verifies nothing — with a green to prove it.
|
||||
|
||||
### D-18 — two pre-registered criteria were mutually unsatisfiable, discoverable only at implementation
|
||||
|
||||
Implementing D-17's fix surfaced a conflict **between** pre-registered criteria:
|
||||
|
||||
- **AC2** (as written) — reject symlinked generated state.
|
||||
- **AC4** — the canonical `pnpm -w build` succeeds and leaves no residue.
|
||||
|
||||
Verified independently rather than taken on report: `apps/web/next.config.ts:4` sets
|
||||
`output: 'standalone'`, and the built tree contains **42 legitimate pnpm dependency symlinks** under
|
||||
`.next/standalone/node_modules`. A blanket descendant-symlink rejection makes the canonical build fail
|
||||
its own preflight with exit 43. **AC2 read literally is unsatisfiable alongside AC4 under this
|
||||
configuration**, and nothing short of building the tree would have revealed it.
|
||||
|
||||
**Third distinct failure mode of a pre-registered check set**, completing the chain:
|
||||
|
||||
| finding | a pre-registered check set can be… |
|
||||
| ------- | ------------------------------------------------------------------ |
|
||||
| D-8 | **wrong** — a check that does not test what it claims |
|
||||
| D-17 | **incomplete** — green while a criterion's requirement is untested |
|
||||
| D-18 | **internally inconsistent** — two criteria that cannot both hold |
|
||||
|
||||
The implementing seat escalated instead of silently picking a winner. That matters: **quietly resolving
|
||||
a conflict between pre-registered criteria destroys the point of pre-registering them** — the registration
|
||||
exists so that changes of meaning are auditable rather than absorbed.
|
||||
|
||||
**Resolution (orchestrator ruling).** Approved a **build-certified symlink manifest**: `.next` itself is
|
||||
still rejected as a symlink; descendants are rejected unless _exactly_ certified by a manifest the build
|
||||
publishes atomically. Strictly **stronger** than blanket rejection — it also catches a **retargeted**
|
||||
symlink, which blanket rejection cannot distinguish from a legitimate one.
|
||||
|
||||
**AC2 restated (recorded, not absorbed).** _Generated state must reject `.next` itself being a symlink
|
||||
or non-directory, and must reject any descendant symlink not exactly certified by the build manifest —
|
||||
added, removed, retargeted, or manifest-only-tampered all fail with exit 43 — **within an accidental /
|
||||
independent-mutation threat model.**_
|
||||
|
||||
> ⚠ **This entry is superseded in part by [D-19](#d-19). Do not read D-18 standalone.** The scope clause
|
||||
> above is load-bearing: the design **cannot** defend against a same-UID actor, which can rewrite the
|
||||
> manifest and the marker consistently (CWE-345). D-18 was written **before** that impossibility was
|
||||
> established.
|
||||
|
||||
**Hardening required before this counts.** The manifest is itself generated state, so **a manifest
|
||||
writable by whoever plants a rogue symlink certifies the attack** — that is the one way this design
|
||||
fails. It must sit inside the same ownership/fingerprint envelope, published atomically via the existing
|
||||
marker mechanism, with negative controls **observed red first** for: added, removed, retargeted,
|
||||
**manifest-only-tampered**, plus a positive control that the canonical build passes.
|
||||
|
||||
> ⚠ **CORRECTED (D-20).** This paragraph originally ended: _"without it, integrity is a claim rather
|
||||
> than a property."_ **That overclaimed**, by implying the control makes integrity a _property_. It does
|
||||
> not, and cannot. The manifest-only-tamper control detects **independent** mutation of the manifest;
|
||||
> it confers **no authenticity** against an actor who rewrites manifest _and_ marker together.
|
||||
> `rev-974` disproved the original wording empirically — a same-UID consistent manifest+marker rewrite
|
||||
> **passed preflight**. Integrity here remains a scoped **drift-detection** property, never an
|
||||
> authenticity one. See D-19 and the charter principle on properties that cannot exist at their
|
||||
> specified layer.
|
||||
|
||||
**Requirement on RM-02 (fourth clause).** The registry must detect **conflicts between registered
|
||||
criteria**, not only wrongness and coverage. Two criteria that cannot simultaneously hold is a registry
|
||||
defect discoverable by construction — and when a criterion is restated, the registry must retain the
|
||||
original text, the restatement, and the reason, so the evolution stays auditable.
|
||||
|
||||
### D-17 — a pre-registered criterion passed a green suite without being satisfied
|
||||
|
||||
`rev-974` returned **CHANGES REQUESTED** on PR #1027 with one blocking finding, and it is the sharpest
|
||||
instance of the session's theme because it occurred **inside our own verification machinery**.
|
||||
|
||||
**AC2** was pre-registered before any code was written, and explicitly required that **symlinked
|
||||
generated state be rejected**. The implementation does not do it:
|
||||
|
||||
```sh
|
||||
ln -s /etc/hosts apps/web/.next/reviewer-symlink
|
||||
pnpm preflight # → "checkout preflight passed", exit 0
|
||||
# → required: generated-state exit 43
|
||||
```
|
||||
|
||||
The acceptance suite was **21/21 green** throughout. Confirmed independently rather than relayed:
|
||||
`scripts/preflight.mjs:82-92` rejects symlinks on the **source** path; `:28` merely _skips_ symlinked
|
||||
directories rather than rejecting them; and the **generated-state** path at `:141-163` `lstat`s and
|
||||
checks `uid` (ownership) but **never** calls `isSymbolicLink()`. The suite's only symlink cases
|
||||
(`preflight.test.mjs:59`, `:115`) cover the turbo binary and a _source_ file. No generated-state case
|
||||
exists anywhere.
|
||||
|
||||
**So: criterion pre-registered, suite green, requirement unmet.** Nobody was careless — the coverage gap
|
||||
is _invisible from a green_, which is the entire problem.
|
||||
|
||||
**This sharpens D-8 rather than repeating it.** D-8 established that pre-registration does not confer
|
||||
_correctness_ (a check can be wrong when written). D-17 establishes the adjacent failure:
|
||||
**pre-registration does not confer _coverage_** — a suite can be green, and every registered criterion
|
||||
can appear satisfied, while a criterion's actual requirement is untested. The two together mean a
|
||||
registry of checks needs **two** properties, not one: each check must be _right_, and the set must
|
||||
_actually exercise_ what it claims.
|
||||
|
||||
**Requirement on RM-02 (third clause).** The registry must bind each acceptance criterion to the
|
||||
**specific case that exercises it**, and prove that case red before trusting its green. A criterion with
|
||||
no case that can fail for _that criterion's stated reason_ is unregistered in substance however it
|
||||
appears in the manifest. This is mutation testing pointed at the **criterion-to-case mapping**, not
|
||||
merely at the gate.
|
||||
|
||||
**Credit where due:** the reviewer also declined to re-run AC8, stating plainly that the PR carried it
|
||||
forward with no runnable command rather than silently substituting a different boundary test. That is
|
||||
the D-8 clause working a second time, in the same review that produced D-17.
|
||||
|
||||
### D-16 — the local test gate and the CI test gate disagree by environment
|
||||
|
||||
Mos flagged a shape worth chasing: if `pnpm test` exits non-zero on a _pre-existing_ guard, then either
|
||||
`main` is red and merges step around it (the #868 shape again), or CI does not run that path. **Both
|
||||
branches turned out wrong, and the truth is a third thing.** Established by running it, not by asking:
|
||||
|
||||
CI runs **exactly** `pnpm test` (`.woodpecker/ci.yml`, `test` step) — the same command. So the path _is_
|
||||
exercised. Yet:
|
||||
|
||||
| environment | result |
|
||||
| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| CI container | `test` step **green** (#2158, #2167) |
|
||||
| this host, clean worktree | **exit 97** — `WAKE-ASSERT INIT ABORT: BASH_LINENO convention violated on bash 5.2.15(1)-release … expected [3 4], probe reported [3 5] (#973)`, after `PASS=18 FAIL=0` |
|
||||
| this host, main checkout | **exit 1** — a _different_, second defect (below) |
|
||||
|
||||
The guard is **environment-dependent**: it aborts on this host's bash and not in CI's container. `git
|
||||
diff origin/main...` confirms PR #1027 touches **zero** files under `packages/mosaic`, so the guard is
|
||||
genuinely pre-existing and unrelated — **f10-coder's report was accurate in every particular**, and
|
||||
`main` is equally affected on this host.
|
||||
|
||||
**So it is not "merges step around a red" — it is worse in one specific way: the local gate and the CI
|
||||
gate do not agree about what passing means.** No agent on this host can obtain a green `pnpm test` at
|
||||
all, on any branch, including `main`. A gate an operator cannot run is a gate that only CI enforces,
|
||||
and a gate only CI enforces cannot be a pre-push gate. This is the hermeticity/portability class
|
||||
already live as #1007 (PR #1024).
|
||||
|
||||
**Second, independent defect found while establishing the above.** In the main checkout the same
|
||||
package fails differently — exit 1 — because a test **scans the working tree** and asserts on files it
|
||||
finds, picking up `apps/coordinator/venv/**` (third-party `site-packages`: `pi = math.pi` in `rich`,
|
||||
`setuptools`, `mypy`). **A test whose result depends on untracked files present in the tree is not
|
||||
hermetic.** This is the _same_ contamination source that made `pnpm format:check` unpassable (D-1/D-7
|
||||
hygiene) — one untracked foreign tree silently breaking two independent gates.
|
||||
|
||||
**Requirements.** RM-01/RM-04: a gate must produce the same verdict on a developer host and in CI, or
|
||||
declare loudly that it cannot run here — never diverge silently. RM-02 registers both as cases: the
|
||||
environment-divergence guard, and a hermeticity control asserting a suite's verdict is unchanged by the
|
||||
presence of untracked directories. Coordinate with #1007/#1024 rather than opening a third lane.
|
||||
|
||||
**Ownership (Mos, 2026-07-31).** The hermeticity fix **is** PR #1024, which sits in **Jason's parked
|
||||
delivery stack** — so, like #1023, its disposition is Jason's. Marked `SUPERSEDED-PENDING-JASON`
|
||||
alongside #1023. D-16 strengthens the urgency but does not transfer ownership: **we do not open a third
|
||||
lane on a parked PR.** The one-line escalation for Jason: _two independent gates
|
||||
(`format:check`, `pnpm test`) were broken by a single untracked directory, and a third
|
||||
(`pnpm test`) disagrees between host and CI — non-hermetic gates make every green host-dependent._
|
||||
|
||||
**Sharpened statement of the class (Mos).** A pre-push gate an operator _cannot run locally_ is a gate
|
||||
only CI enforces — so pointing `.husky/pre-push` at it **misrepresents where the gate lives**. Combined
|
||||
with the shared root cause across two gates, the finding is: **non-hermetic gates make every green
|
||||
host-dependent.** A gate that only appears to pass depending on which host runs it is this mission's
|
||||
exact subject, one meta-level up.
|
||||
|
||||
**#1027 disposition (Mos):** proceeds on **CI-green**. CI is the authoritative gate; the local exit-97
|
||||
is a known host-specific guard abort, irrelevant to the merge decision.
|
||||
|
||||
### D-15 — token scope is not repository permission (a THIRD capability layer)
|
||||
|
||||
`f10-coder` was provisioned with `gitea-mosaicstack-f10-coder.token`, scopes `write:repository` +
|
||||
`write:issue`, and the mint was verified by "repo access returns 200". It then failed to push:
|
||||
|
||||
```
|
||||
remote: error: User permission denied for writing.
|
||||
remote: error: pre-receive hook declined
|
||||
```
|
||||
|
||||
Verified objectively rather than inferred (per the charter principle):
|
||||
|
||||
| probe | result |
|
||||
| ------------------------------------------------------ | ------------------------------------------- |
|
||||
| `GET /repos/mosaicstack/stack/collaborators/f10-coder` | **404** — not a collaborator |
|
||||
| repo permissions as seen by **its own token** | `admin: false`, `push: false`, `pull: true` |
|
||||
|
||||
**Capability has at least three independent layers, and satisfying two proves nothing about the third:**
|
||||
|
||||
1. **Token file exists** → raw-API authentication works (D-11b).
|
||||
2. **`tea` login exists** → tea-dependent wrapper paths work (D-13).
|
||||
3. **Repository permission granted** (collaborator/team membership) → _writes_ are actually authorised.
|
||||
|
||||
A token can carry `write:repository` scope and still be refused, because **scope bounds what a token
|
||||
may attempt; repository permission decides what the user may do.** They are different systems.
|
||||
|
||||
**This is the charter principle failing on the very check meant to confirm capability.** The mint was
|
||||
validated by an HTTP 200 on a _read_. A 200 proves reachability; it does not prove the property that
|
||||
was required, which was **write**. Both the provisioner and I accepted it — the same
|
||||
`written-unverified` treated as `verified` as D-12, one layer up, on a check whose entire purpose was
|
||||
verification.
|
||||
|
||||
**Requirements.** RM-50's pre-dispatch capability check must probe the **effective permission for the
|
||||
operation intended** — for push authority, assert `permissions.push == true` as that seat, not token
|
||||
existence and not a 200 on a read. RM-04's registry reconciliation covers all three layers, with a
|
||||
must-fail control for each. A capability check that cannot fail on a seat lacking write permission is
|
||||
itself an inert gate.
|
||||
|
||||
### D-14 — a ruled decision did not propagate to the authoritative record
|
||||
|
||||
DECISION-1 (the corrected choke-point wire-in target) was ruled by the coordinator and applied to
|
||||
`TASKS.md`. **`MISSION.md` — the charter, the document a cold-starting seat reads first — kept the
|
||||
superseded target for hours.** It was flagged `CONTESTED` in a board note, then the ruling landed and
|
||||
nobody edited the charter. A seat resuming from the charter would have read the _rejected_ target as
|
||||
authoritative and wired the choke point into a disabled rail — the precise failure the ruling existed
|
||||
to prevent.
|
||||
|
||||
Caught by hand, during an unrelated edit. Nothing would have caught it otherwise.
|
||||
|
||||
**This is P-MISSION-001 turned on ourselves.** The mission's own thesis is that convention exists and
|
||||
_enforcement_ is the gap: a decision that lives in a chat ruling and a board note, but not in the
|
||||
source of truth, has not actually been made — it has been _agreed_. The two are different, and the
|
||||
difference is exactly what this mission is about.
|
||||
|
||||
> ⚠ **AMENDED by D-20 — propagation is BIDIRECTIONAL.** As first written, this requirement was read by
|
||||
> both the orchestrator and the coordinator as _forward_ propagation only: a ruling reaches the
|
||||
> documents that state the new rule. **D-20 proved that insufficient.** When D-19 superseded part of
|
||||
> D-18, the consequence propagated forward into the charter and the delivery conditions but **never
|
||||
> backward into D-18 itself**, which went on asserting a withdrawn claim — and a reviewer disproved it
|
||||
> by experiment. **A supersession must update BOTH the documents that render the new rule AND the
|
||||
> finding it retires, with the retired wording quoted rather than deleted.** Backward propagation is
|
||||
> the same defect as forward; neither of us audited that direction until it bit.
|
||||
|
||||
**Requirement (not merely a fix).** A ruled decision must propagate **mechanically** to the
|
||||
authoritative record; it must not depend on someone remembering to edit a second file. Concretely, once
|
||||
mission state is DB-backed (RM-53 / the P-MISSION cutover):
|
||||
|
||||
- a decision is a **record**, not prose duplicated across documents;
|
||||
- documents _render_ decisions rather than restating them, so there is one place to be wrong;
|
||||
- and where duplication is unavoidable, a check asserts the authoritative record and the derived
|
||||
document agree — with a must-fail control proving divergence is detected.
|
||||
|
||||
Until then, the interim rule: **the same commit that records a ruling updates every document that
|
||||
states it — and every finding it supersedes.** Interim rules are exactly what the DB cutover exists to replace.
|
||||
|
||||
**The rule found a second instance within minutes of being written.** Auditing the charter against all
|
||||
rulings to date (rather than waiting to be bitten again) surfaced that **DECISION-2 had also not
|
||||
propagated**: `MISSION.md`'s standing directives still stated the DB hard-cutover with no mention of
|
||||
Mos's binding qualification that _the spine must not be a single-point hard-stop_ (degraded mode +
|
||||
rollback artifact required). A seat reading the charter would have designed toward an availability
|
||||
posture the coordinator had explicitly rejected — and would have found the superseded
|
||||
"no DB ⇒ the fleet stops" recommendation nowhere contradicted. Now corrected in place.
|
||||
|
||||
**Two un-propagated rulings out of two rulings that touched charter text.** The propagation gap is not
|
||||
an oversight that happened once; without a mechanism it is the _default outcome_. That is the argument
|
||||
for making this a requirement rather than a discipline.
|
||||
|
||||
### D-13 — two credential registries that can disagree (why the `--draft` fallback fired at all)
|
||||
|
||||
Diagnosing D-12's root cause surfaced a distinct defect. There are **two parallel credential
|
||||
registries**, and capability in one does not imply capability in the other:
|
||||
|
||||
| registry | contents for identity `mos-dt-0` on `mosaicstack` |
|
||||
| ------------------------------------------------------ | -------------------------------------------------------------------------------------------- |
|
||||
| token files — `~/.config/mosaic/secrets/gitea-tokens/` | `gitea-mosaicstack-mos-dt-0.token` **EXISTS** |
|
||||
| `tea login list` | **NO** `mosaicstack` login for `mos-dt-0` (only `mosaicstack-mos` and `mosaicstack-rev-974`) |
|
||||
|
||||
So `get_gitea_token` succeeds and every raw-API path works, while every **tea-dependent** wrapper path
|
||||
fails its login validation and silently degrades to the API fallback — which is exactly what dropped
|
||||
`--draft`. **tea is not "stale"; the login simply does not exist for that identity.**
|
||||
|
||||
This matters beyond one flag: capability was declared authoritative by the token-file set (D-11b), but
|
||||
that registry does not govern the tea path. A seat can be _fully provisioned_ by the authoritative
|
||||
registry and still lose functionality with no error — only a warning, and only on the degraded path.
|
||||
|
||||
**Requirements.** RM-04 (activation coherence): the two registries must be reconciled — one source of
|
||||
truth, or a startup check asserting they agree, with a must-fail control proving disagreement is
|
||||
detected. RM-50: the pre-dispatch capability check must verify capability for the **path actually
|
||||
used**, not merely token-file presence.
|
||||
|
||||
**Confirmed working despite the gap** (so this is degradation, not outage): pushes, `pr-merge.sh`,
|
||||
PR/issue creation via API fallback, comment posting, and all reads. Impact is confined to
|
||||
tea-only features — `--draft`, `--labels`, `--milestone`.
|
||||
|
||||
**Reconciliation run by Mos (the manual form of RM-04's assert-agreement, done once by hand).** For
|
||||
`git.mosaicstack.dev`, the token-file registry holds **six** seats; `tea` holds logins for **two**:
|
||||
|
||||
| state | seats |
|
||||
| ------------------------------------------------ | -------------------------------------------------------- |
|
||||
| token file present, **no** mosaicstack tea login | `f10-coder`, `jarvis`, `mos-admin`, `mos-dt-0`, `pepper` |
|
||||
| token file present **and** tea login present | `rev-974` (only) |
|
||||
|
||||
**Five of six provisioned seats are silently degraded on tea-only features.** This is _systemic_, not
|
||||
a one-off — which is why the fix is registry reconciliation (RM-04) and not a per-seat mint. Minting
|
||||
one seat would clear a symptom and leave the class live.
|
||||
|
||||
Mos deliberately deferred the mint: it is not on RM-01's critical path, and additively editing shared
|
||||
`tea` config underneath running work is a change he declined to make without cause. Full remediation —
|
||||
mint the five missing logins **and** wire the startup must-fail assertion that _detects_ disagreement —
|
||||
lands as RM-04 at a non-critical seam, or immediately if any seat needs a tea-only feature to progress.
|
||||
|
||||
**Correction of record:** this supersedes D-11(b)'s claim that the token-file set is _the_ authoritative
|
||||
capability registry. It is **necessary but not sufficient**. Capability is **per-path**: the token file
|
||||
governs the raw-API path, the tea login governs the tea path, and the two can disagree silently.
|
||||
|
||||
### D-12 — a requested SAFETY flag was silently degraded, and I did not check
|
||||
|
||||
I created PR #1027 with `pr-create.sh ... -d` (draft) because it carries **partial, unproven work**.
|
||||
`tea` authentication was stale, so the wrapper fell back to its raw-API path — which cannot set draft —
|
||||
and emitted:
|
||||
|
||||
```
|
||||
Warning: API fallback applies title/body/head/base only; labels/milestone/draft require authenticated tea setup.
|
||||
```
|
||||
|
||||
The PR was created **not-draft**. I read the success output, saw the PR number, and moved on. I then
|
||||
reported to the coordinator that the PR was "opened as draft". **It was open, mergeable, and marked
|
||||
ready for ~25 minutes**, protected only by the words "DRAFT" and "do not merge" in its title and body —
|
||||
i.e. by prose a human might read, not by the platform control I asked for. Detected only because a
|
||||
watcher polled `draft:` and the value disagreed with my belief. Corrected by setting the `WIP:` title
|
||||
prefix (Gitea's draft mechanism); `draft: True` verified after.
|
||||
|
||||
**Three distinct failures, and the third is mine:**
|
||||
|
||||
1. **Silent degradation of a safety flag.** The fallback path dropped `--draft` and still exited 0. A
|
||||
fallback that cannot honour a _safety_ argument must fail, not proceed — degrading `--labels` is a
|
||||
nuisance; degrading `--draft` publishes unproven work as ready to merge.
|
||||
2. **The warning went to stderr and nothing consumed it.** It was correct, specific, and ignored — a
|
||||
warning nobody acts on is indistinguishable from no warning.
|
||||
3. **I did not verify the flag took effect.** I checked that the PR existed, not that it had the
|
||||
property I required. This is the mission's own thesis turned on me: **I trusted a success exit code
|
||||
over an observed state**, on exactly the class of tool this mission exists to distrust.
|
||||
|
||||
**Requirements.** RM-02: a wrapper that cannot honour a safety-relevant argument must exit non-zero —
|
||||
registered with a must-fail control asserting `--draft` on a degraded path fails rather than proceeds.
|
||||
RM-24 (tri-state write outcomes): this is precisely `written-unverified` being treated as `verified` —
|
||||
the PR write succeeded, the _requested property_ was never confirmed, and no one looked.
|
||||
|
||||
### D-11 — seat identity did not survive into git, and seat capability is invisible at dispatch
|
||||
|
||||
Two defects, one dispatch (RM-01 → `f10-coder`):
|
||||
|
||||
**(a) Identity drift — P-WRAPPER-001, reproduced on our own delivery.** The seat's commits are
|
||||
authored `mosaic-coder <[email protected]>` — the generic fallback. **You cannot tell from
|
||||
git history which seat did this work.** Recorded, not rewritten: the drift is the evidence.
|
||||
|
||||
> **Mechanism, corrected (Mos).** My original framing here was wrong, and the error was in the brief
|
||||
> before it was in the finding. `MOSAIC_GIT_IDENTITY` resolves the **token** (which per-slot credential
|
||||
> the wrappers act with). The **commit author** comes from `git config user.name` / `user.email`, which
|
||||
> is a **separate setting** — it fell back to the generic value because nothing set it. Exporting the
|
||||
> identity could never have fixed authorship. **My worker brief instructed only the export, so the
|
||||
> seat did exactly what it was told and the commits were still mis-attributed.**
|
||||
>
|
||||
> **The requirement is coherence: token and authorship must agree.** A seat acting with
|
||||
> `gitea-mosaicstack-f10-coder` must also commit as `f10-coder <[email protected]>`.
|
||||
> Either half alone is identity drift — one produces the right credential with the wrong author, the
|
||||
> other the reverse. That coherence _is_ P-WRAPPER-001, and it belongs in seat setup, not in prose
|
||||
> instructions a seat may follow correctly and still end up wrong.
|
||||
|
||||
**(b) Capability opacity.** Nothing at dispatch time revealed that `f10-coder` had no credential for
|
||||
the target provider. Per-slot tokens live at `~/.config/mosaic/secrets/gitea-tokens/`; the seat holds
|
||||
`gitea-usc-f10-coder` but not `gitea-mosaicstack-f10-coder`. This surfaced only when the seat failed
|
||||
**mid-task, after ~$9 and 69% of its context.** The orchestrator (me) selected a seat without any way
|
||||
to check it could act on the target repo — and there was no way to check.
|
||||
|
||||
`get_gitea_token` behaved **correctly**: it refused to fall through and borrow another slot's token,
|
||||
failing loud precisely to protect gate-16 attribution. The tooling was right; the _dispatch-time
|
||||
information_ did not exist.
|
||||
|
||||
**This is P-RECOVERY-001's "honest capability labeling" applied to seats rather than services.** A seat
|
||||
should declare what it can actually do — which providers, which repos, which credentials — and that
|
||||
declaration must be **checkable before dispatch**, not discovered by failure after the budget is spent.
|
||||
|
||||
**Requirements.**
|
||||
|
||||
- **RM-04 (activation coherence)** gains the identity-binding half: seat setup must set **both** the
|
||||
token identity **and** `git config user.name`/`user.email`, coherently. Verified by an
|
||||
exit-asserting test that makes a commit and asserts its author — never assumed from an instruction
|
||||
in a brief.
|
||||
- **RM-50 (roster ownership)** gains per-seat capability declaration plus a **pre-dispatch capability
|
||||
check**. Mos (who owns provisioning) confirms the check is mechanically trivial: **capability is
|
||||
token-file existence.** Before dispatching seat `X` to provider `Y`, test that
|
||||
`~/.config/mosaic/secrets/gitea-tokens/gitea-<Y>-<X>.token` exists; if absent, provision it or pick a
|
||||
provisioned seat. **The token-file set is the authoritative capability registry.** A one-second check
|
||||
would have replaced a mid-task failure that cost ~$9 and 69% of a seat's context.
|
||||
|
||||
### D-10 — the queue guard's failure modes are exactly backwards
|
||||
|
||||
`ci-queue-wait.sh` — a **required** pre-push/pre-merge gate — was observed this session doing both of
|
||||
these:
|
||||
|
||||
- **Fails OPEN on an unknown result.** `state=unknown ⇒ exit 0`, five times, during real pushes and
|
||||
real merges. It also evaluates `branch=main` rather than the branch being acted on.
|
||||
- **Fails CLOSED on credential resolution.** In a worker seat it aborted with
|
||||
`Gitea token not found`, hard-blocking a legitimate push of completed, tested work. The worker
|
||||
correctly stopped (Constitution gate 8). The identical command run from that worker's _own worktree_
|
||||
in another shell succeeded, so the checkout and remote were fine — the difference was the worker's
|
||||
process environment.
|
||||
|
||||
**A gate that waves through work it never checked, and blocks work that is ready, has its failure
|
||||
modes inverted.** Availability failures (cannot reach the provider, cannot resolve a credential)
|
||||
should degrade to a loud, auditable _inability to assert_ — never to a hard stop on delivery, and
|
||||
never to a silent pass. Correctness failures (unknown, malformed, terminal-failure) are what must
|
||||
block.
|
||||
|
||||
This is also the **Pi-brick shape** (P-RECOVERY-001): a gate whose own unavailability prevents the
|
||||
work needed to recover from it.
|
||||
|
||||
**Requirement on RM-03, extending its existing two defects:** the guard must distinguish
|
||||
`CANNOT_ASSERT` (credential/transport/provider unavailable — loud, audited, does not silently pass and
|
||||
does not permanently block) from `ASSERTED_NOT_READY` (a real non-green CI state — blocks). Both are
|
||||
registered R-002 cases with must-fail controls; neither may exit 0 silently.
|
||||
|
||||
### D-9 — the comms path shell-interprets message bodies (injection-shaped, found by accident)
|
||||
|
||||
Sending a status message with `agent-send.sh -m "...`backticks`..."` caused bash to **execute** the
|
||||
backticked text as command substitution. The recipient received a mangled body plus a
|
||||
`No such file or directory` error; the intended sentence never arrived. The message was reported as
|
||||
delivered.
|
||||
|
||||
This is the **same class** as the already-noted `pr-create.sh` backtick-quoting bug (M2 scratchpad):
|
||||
**two tools in the comms path treat a message body as shell input.** A body that can execute on the
|
||||
sender is a _correctness_ bug before it is ever a security one — and note the failure mode: the
|
||||
send reported success while silently transmitting something other than what was written. Silent
|
||||
corruption with a success receipt is precisely the pattern this mission exists to eliminate.
|
||||
|
||||
**Requirement on RM-40 / RM-42 (comms/v1), hardened by Mos.** The envelope must carry its payload
|
||||
**verbatim** and must not be subject to shell interpretation at **any** hop — sender, transport, or
|
||||
adapter. Concretely: **file/stdin transport, never argv interpolation.**
|
||||
|
||||
**Standing interim rule, effective now (Mos).** Until the envelope lands, use `agent-send.sh -f
|
||||
<file>` for any message body containing special characters — **never `-m`**. Passing a file sidesteps
|
||||
argv interpolation entirely. **This rule is mandatory in every worker brief this mission issues**,
|
||||
alongside the D-8 "if a check is unrunnable, say so" clause. Round-trip fidelity (send a body containing backticks, `$(…)`, quotes, and newlines; assert
|
||||
byte-identical receipt) is a required registered test case under RM-02, including a must-fail control
|
||||
proving the assertion can detect corruption.
|
||||
|
||||
### D-8 — a PRE-REGISTERED acceptance check that was not runnable as written
|
||||
|
||||
On PR #1025 the author (me) pre-registered AC2 with the fixture snippet `mkdir -p apps/*/venv/lib`.
|
||||
@@ -811,18 +297,17 @@ spread is itself information, and X1 says we calibrate on real merged PRs.
|
||||
|
||||
### P5 — Retirements, hygiene, conformance
|
||||
|
||||
| id | task | src | depends_on | est (S/O) | tier |
|
||||
| ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- | -------------------------- | ---------------- | ------ |
|
||||
| RM-50 | One roster-owned socket/host; quarantine unmanaged; **deterministic reaper for stale sessions AND dead-session disk scratch** (D-7) | O+S+live | RM-04 | 14K / 150K | sonnet |
|
||||
| RM-51 | Auto-sync **allowlist** (never auto-stage unknown paths) + worktree/lease isolation | O+S | RM-02 | 8K / 110K | sonnet |
|
||||
| RM-52 | Retire the Python controller + duplicate MACP islands (3 → 1) | O+S | RM-26, RM-27, RM-25, RM-28 | 14K / 110K | codex |
|
||||
| RM-53 | Flat-file orchestration → DB hard cutover, with rehearsed rollback artifact | O+S | RM-27, RM-30, RM-34, RM-29 | (in S-10) / 200K | opus |
|
||||
| RM-54 | Fleet-wide inert-gate audit against the RM-02 registry | O | RM-02 | — / 120K | sonnet |
|
||||
| RM-55 | **Conformance harness:** fault-inject the live failure classes on real artifacts | O+S | RM-35, RM-41, RM-53 | 18K / 260K | opus |
|
||||
| RM-56 | Retirement proof: CI asserts all three retirements are complete **and stay complete** | O | RM-52, RM-45, RM-53 | — / 90K | codex |
|
||||
| RM-57 | Operator cutover docs + activation proof; map all 15 decisions to evidence | S | RM-04, RM-36, RM-45, RM-55 | 6K / — | codex |
|
||||
| RM-59 | **Close the D-19 residual risk** — generated-state verification anchored **outside** the worktree's authority (executor/spine-side attestation), retiring the same-UID self-authentication gap | mos-remediation (D-19) | RM-12, RM-21, RM-25 | 20K | opus |
|
||||
| RM-58 | **Mechanical pre-dispatch context reset** — the orchestrator resets a seat out-of-band and verifies it, rather than asking the agent to reset itself | mos-remediation (D-4) | RM-31, RM-50 | 8K | sonnet |
|
||||
| id | task | src | depends_on | est (S/O) | tier |
|
||||
| ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- | -------------------------- | ---------------- | ------ |
|
||||
| RM-50 | One roster-owned socket/host; quarantine unmanaged; **deterministic reaper for stale sessions AND dead-session disk scratch** (D-7) | O+S+live | RM-04 | 14K / 150K | sonnet |
|
||||
| RM-51 | Auto-sync **allowlist** (never auto-stage unknown paths) + worktree/lease isolation | O+S | RM-02 | 8K / 110K | sonnet |
|
||||
| RM-52 | Retire the Python controller + duplicate MACP islands (3 → 1) | O+S | RM-26, RM-27, RM-25, RM-28 | 14K / 110K | codex |
|
||||
| RM-53 | Flat-file orchestration → DB hard cutover, with rehearsed rollback artifact | O+S | RM-27, RM-30, RM-34, RM-29 | (in S-10) / 200K | opus |
|
||||
| RM-54 | Fleet-wide inert-gate audit against the RM-02 registry | O | RM-02 | — / 120K | sonnet |
|
||||
| RM-55 | **Conformance harness:** fault-inject the live failure classes on real artifacts | O+S | RM-35, RM-41, RM-53 | 18K / 260K | opus |
|
||||
| RM-56 | Retirement proof: CI asserts all three retirements are complete **and stay complete** | O | RM-52, RM-45, RM-53 | — / 90K | codex |
|
||||
| RM-57 | Operator cutover docs + activation proof; map all 15 decisions to evidence | S | RM-04, RM-36, RM-45, RM-55 | 6K / — | codex |
|
||||
| RM-58 | **Mechanical pre-dispatch context reset** — the orchestrator resets a seat out-of-band and verifies it, rather than asking the agent to reset itself | mos-remediation (D-4) | RM-31, RM-50 | 8K | sonnet |
|
||||
|
||||
**Critical path:** `RM-01 → RM-02 → RM-10 → RM-11 → RM-12 → RM-21 → RM-23 → RM-31 → RM-33 → RM-34 → RM-53 → RM-55`.
|
||||
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
# #1099 pipefail + early-exit sweep
|
||||
|
||||
Baseline: `df4c591ab42aa1ae62c12935fdc0e772684864a0`
|
||||
|
||||
This is a site inventory, not a risk count. `FIXED` means the early-exiting consumer no longer has a piped upstream process whose SIGPIPE can become the result under `pipefail`. `NOT-LOAD-BEARING` means the pipeline status is explicitly discarded. `UNREACHABLE-AND-WHY` describes designed input, not a payload-size safety claim.
|
||||
|
||||
## Tranche 1 — runtime and general scripts
|
||||
|
||||
| Baseline site | Verdict | Construction / reason |
|
||||
| --- | --- | --- |
|
||||
| `tools/matrix-presence-harness/run.sh:38` | FIXED | nullglob array selects the first path; no pipeline |
|
||||
| `tools/e2e-install-test.sh:139` | FIXED | capture help completely, then grep via redirection |
|
||||
| `tools/install.sh:312` | FIXED | NUL `mapfile` reads all roots; count != 1 reaches the named malformed-archive diagnostic |
|
||||
| `scripts/analysis/reflect-board-history.sh:76` | FIXED | capture Git history completely, then grep via redirection |
|
||||
| `scripts/analysis/reflect-git-history.sh:67` | FIXED | grep reads from a here-string |
|
||||
| `scripts/analysis/reflect-git-history.sh:69` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/authentik/user-create.sh:72` | FIXED | jq `first(...)` reads the response directly |
|
||||
| `packages/mosaic/framework/tools/git/mutate-push-guard.sh:87` | FIXED | grep `-m1` reads the file directly; downstream `cut` consumes its complete scalar output |
|
||||
| `packages/mosaic/framework/tools/orchestrator/session-resume.sh:94` | FIXED | `mapfile` plus bounded indexed loop replaces `head` pipeline |
|
||||
| `packages/mosaic/framework/tools/prdy/prdy-status.sh:69` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:172` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:173` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:174` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:175` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:176` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:177` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:178` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/typecheck-hook.sh:16` | FIXED | Bash regex extracts the first field without a pipeline |
|
||||
| `packages/mosaic/framework/tools/qa/typecheck-hook.sh:56` | FIXED | grep and bounded sed each read from a here-string |
|
||||
| `packages/mosaic/framework/tools/tmux/send-message.sh:113` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/tmux/send-message.sh:124` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:126` | FIXED | one awk reads the manifest directly and exits after the first exact key |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:270` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:278` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/digest.sh:647` | FIXED | capture complete locator output, then select first line by parameter expansion |
|
||||
| `packages/mosaic/framework/tools/wake/reconcile.sh:149` | FIXED | one awk reads the manifest directly and exits after the first exact key |
|
||||
|
||||
## Explicit withdrawn / non-load-bearing sites
|
||||
|
||||
| Baseline site | Verdict | Reason |
|
||||
| --- | --- | --- |
|
||||
| `tools/install.sh:182` | NOT-LOAD-BEARING | `|| true` explicitly discards lookup status |
|
||||
| `tools/install.sh:356` | UNREACHABLE-AND-WHY | `pnpm pack` writes one matching CLI tarball into a fresh directory immediately before lookup; citation withdrawn in #1099 |
|
||||
| `tools/install.sh:357` | UNREACHABLE-AND-WHY | same fresh-directory invariant for gateway tarball; citation withdrawn in #1099 |
|
||||
| `tools/install.sh:627` | NOT-LOAD-BEARING | `|| true` explicitly discards lookup status |
|
||||
| `scripts/agent/session-start.sh:70` | NOT-LOAD-BEARING | optional scratchpad lookup has `|| true` |
|
||||
| `packages/mosaic/framework/templates/repo/scripts/agent/session-start.sh:58` | NOT-LOAD-BEARING | optional scratchpad lookup has `|| true` |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:25` | UNREACHABLE-AND-WHY | withdrawn in #1099 after designed-input reachability measurement; preserved without re-litigation |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:27` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:30` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:32` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:34` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
|
||||
## Tranche 2 — non-wake test harnesses
|
||||
|
||||
All 22 baseline sites below are `FIXED`; the checked-in tranche fixture is passed through the same scanner and asserts all 22 occurrences and 21 normalized identities (the same response-split line occurs twice).
|
||||
|
||||
| Baseline site(s) | Verdict | Construction |
|
||||
| --- | --- | --- |
|
||||
| `systemd/user/test-fleet-units.sh:148` | FIXED | capture tmux output, then grep via redirection |
|
||||
| `git/test-issue-comment-readback.sh:283,302` | FIXED | parameter expansion splits status/body without `head` |
|
||||
| `git/test-pr-review-gitea-comment.sh:228` | FIXED | parameter expansion splits status/body |
|
||||
| `git/test-lane-brief-pr-linkage.sh:72` | FIXED | grep reads from a here-string |
|
||||
| `git/test-pr-review-repo-host-override.sh:225-226` | FIXED | grep reads from a here-string |
|
||||
| `orchestrator/smoke-test.sh:67,72` | FIXED | parameter expansion selects first line |
|
||||
| `orchestrator/test-board-roll.sh:99-100` | FIXED | grep reads from a here-string |
|
||||
| `quality/scripts/test-upgrade-durable-snapshot.sh:180` | FIXED | complete sorted output is read with `mapfile`, then indexed |
|
||||
| `quality/scripts/test-upgrade-rollback.sh:339,356` | FIXED | direct `grep -m1` file reads; cleanup captures before testing |
|
||||
| `tmux/test-send-message-socket.sh:37,38,44-46,68,72` | FIXED | capture commands complete before redirected grep assertions |
|
||||
| `tmux/test-send-message-verdict.sh:34` | FIXED | grep reads from a here-string |
|
||||
|
||||
## Tranche 3 — wake validation harnesses
|
||||
|
||||
All 26 baseline occurrences (25 normalized identities; one preimage selector occurs twice) are `FIXED` and mechanically bound through the wake fixture and shared scanner.
|
||||
|
||||
| Baseline site(s) | Verdict | Construction |
|
||||
| --- | --- | --- |
|
||||
| `wake/test-wake-digest-quarantine.sh:567` | FIXED | complete match populations are captured, then first line selected by parameter expansion |
|
||||
| `wake/test-wake-preimage.sh:182-183,346-347` | FIXED | jq `first(...)` reads each JSONL file directly |
|
||||
| `wake/validate-973/microtest-wake-assert.sh:153,170-171,176,204-209,233-234,251-252,286-287` | FIXED | scalar assertions use here-strings; diagnostics use non-early sed ranges; source line captured before matching |
|
||||
| `wake/validate-973/validate-973.sh:110,119,180,182,187` | FIXED | scalar assertions use here-strings; diagnostic truncation uses consuming sed ranges |
|
||||
|
||||
The scoped inventory is complete: 26 runtime/general + 22 non-wake tests + 26 wake tests fixed; 11 explicitly withdrawn or non-load-bearing sites retain their documented verdicts.
|
||||
@@ -1,118 +0,0 @@
|
||||
# RM-61 — CI contract exemption for #1000 teardown artifact
|
||||
|
||||
**Tracking:** RM-61 / issue #1000
|
||||
|
||||
**Branch:** `fix/rm-61-ci-contract-exemption`
|
||||
**Owner:** `coder-mos1`
|
||||
|
||||
## Objective
|
||||
|
||||
Determine, by red-first provider controls, whether the `ci-postgres` pod-not-found teardown signature discriminates from a real PostgreSQL failure. Only if it discriminates may a named, bounded CI-contract exemption be implemented. The exemption must retire when #1000 is fixed; fixing #1000 is the closure path.
|
||||
|
||||
## Pre-registered kill criterion
|
||||
|
||||
If an injected real `ci-postgres` failure also yields `pods "wp-svc-<ULID>-ci-postgres" not found` as the service's provider-visible failure, the signature does not discriminate. Option B is unsafe; stop exemption implementation and fall to Option A (#1000).
|
||||
|
||||
## Plan
|
||||
|
||||
1. Capture full `-f json` records for the 11 supplied observations and state counts.
|
||||
2. Run one startup-failure control using the real pgvector/PostgreSQL image with an invalid `initdb` argument.
|
||||
3. Run one post-readiness crash control using real PostgreSQL, `pg_isready`, and a deliberate postmaster kill while a DB-dependent probe is active.
|
||||
4. Compare the raw `ci-postgres` service record independently of failures in dependent steps.
|
||||
5. Investigate runner/time/head clustering only as a hypothesis; never encode incidental correlates or retries into policy.
|
||||
6. If and only if the controls discriminate, implement and test the exact exemption, document its two-way boundary, and track retirement at #1000.
|
||||
|
||||
## Budget
|
||||
|
||||
No explicit token cap supplied. Working estimate: 20K–30K tokens. Limit provider controls to the two pre-registered runs; no retries or re-roll policy.
|
||||
|
||||
## Initial evidence
|
||||
|
||||
Historical JSON saved locally under `.evidence/rm-61/` (not for commit). Supplied pipelines: 11 total. Child-step counts: five pipelines with 9 children and six with 10 children. Seven contain the `ci-postgres` pod-not-found failure (#2170, #2175, #2180, #2181, #2182, #2187, #2188); four do not (#2158, #2167, #2184, #2186). Every observed workflow reports `agent_id=44`, so the available JSON does not separate clean and artifact runs by runner. This refutes runner identity as a discriminator in the sampled record.
|
||||
|
||||
## Progress
|
||||
|
||||
- [x] Requirements and kill criterion recorded before control implementation.
|
||||
- [x] Historical full-JSON records captured.
|
||||
- [x] Startup-failure control observed terminal.
|
||||
- [x] Post-readiness crash control observed terminal.
|
||||
- [x] Discrimination verdict recorded: Option B may proceed.
|
||||
- [x] Conditional exemption implementation.
|
||||
|
||||
## Tests / evidence
|
||||
|
||||
### Control 1 — real startup failure
|
||||
|
||||
- Commit: `3931b0e29eb834914f7b17e4db7e221481d436fa`
|
||||
- Pipeline: #2189, exact commit match.
|
||||
- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
|
||||
- `ci-postgres`: `state=failure`, `exit_code=1`, `error=null`, with a five-second execution window.
|
||||
- `test`: `state=failure`, `exit_code=1` after the readiness budget expired.
|
||||
- Pipeline/workflow: terminal `failure`.
|
||||
|
||||
This control is red and its service record differs from #1000 (`exit_code=0` plus pod-not-found). It proves the startup-failure direction only. It does not settle the dangerous post-readiness crash/garbage-collection path.
|
||||
|
||||
### Control 2 — real post-readiness crash
|
||||
|
||||
- Commit: `25ac59715a94dd1b52ef42577472eb44ecc4b446`
|
||||
- Pipeline: #2191, exact commit match.
|
||||
- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
|
||||
- Service log proves PostgreSQL reached `database system is ready to accept connections`, the test created the arm table, and the service then killed postmaster PID 7.
|
||||
- Test log proves a successful `SELECT 1` followed by `Connection refused`; it exited the pre-registered control code 61.
|
||||
- `ci-postgres`: `state=failure`, `exit_code=137`, `error=null`, with a 203-second execution window.
|
||||
- `test`: `state=failure`, `exit_code=61`.
|
||||
- Pipeline/workflow: terminal `failure`.
|
||||
|
||||
This is the dangerous post-readiness crash path. Its service record is not pod-not-found and therefore differs from #1000 independently of the dependent test failure.
|
||||
|
||||
### Discrimination verdict
|
||||
|
||||
Both real failures are provider-visible as process exits (`exit_code=1` startup; `exit_code=137` crash) with no pod-not-found error. The seven observed #1000 artifacts are provider reconciliation misses (`exit_code=0` plus the exact pod-not-found error). The declared kill criterion did not fire, so Option B may proceed with a matcher requiring the full conjunction. This evidence does **not** prove every future Kubernetes failure is distinguishable; it proves these two concrete real-failure classes remain blocking and bounds the exemption to the observed reconciliation shape.
|
||||
|
||||
### Unit red-first checkpoint
|
||||
|
||||
The nine-case contract harness was written before the verifier. First execution exited 1 because `verify-terminal-green.py` did not exist; no exemption implementation was live. Cases pre-register ordinary green, the exact artifact, both provider controls, near-miss signatures, an independent failure, and a skipped step.
|
||||
|
||||
### Control 2 setup attempt — invalid, excluded from evidence
|
||||
|
||||
- Commit: `9455cd6a2650b2b7e70f746c07933d96e5cb3d20`
|
||||
- Pipeline: #2190, exact commit match.
|
||||
- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
|
||||
- Service log: `/bin/sh: 0: -c requires an argument`.
|
||||
- Root cause: Woodpecker service `commands` did not become the third `sh -c` argument. PostgreSQL never started, so this run is **not** the post-readiness crash control and provides no discrimination evidence.
|
||||
- Focused remediation: place the script directly in the third `entrypoint` element and supply `PGPASSWORD` for the marker query. This is a control-fixture correction, not a retry of #1000 and not evidence for either verdict.
|
||||
|
||||
## Implementation evidence
|
||||
|
||||
- `verify-terminal-green.py` consumes only the full JSON/API record; it performs no fetch, retry, or trigger.
|
||||
- Exact #2188 record: exit 0, 10 children, 9 success + 1 named exemption.
|
||||
- Historical set: #2158/#2167/#2184/#2186 pass with no exemption; #2170/#2175/#2182/#2187/#2188 pass with one named exemption; #2180/#2181 remain red because independent failures exist.
|
||||
- Provider controls: #2189 and #2191 both exit 1 under the verifier; neither is exempted.
|
||||
- Unit harness: initial 9/9 cases passed after the red-first checkpoint; review remediation expands this to 12 cases with expected-head match/missing/mismatch coverage.
|
||||
- Test-membership guard: PASS, population 45; 26 enumerated, 19 signed exclusions; all 39 surface paths present.
|
||||
- Python compile: PASS.
|
||||
- `pnpm typecheck`: PASS, 45/45 tasks.
|
||||
- `pnpm lint`: PASS, 25/25 tasks.
|
||||
- `pnpm format:check`: PASS after moving local evidence outside the repository tree.
|
||||
- `test:framework-shell`: RM-61 and all preceding suites passed, then the pre-existing wake assertion aborted with exit 97 because this host's Bash 5.2.15 reports `BASH_LINENO [3 5]` where that suite requires `[3 4]`. RM-61 does not modify the wake suite; the command is not fully runnable on this host as written and no substitute result is claimed.
|
||||
|
||||
## Independent review
|
||||
|
||||
- Review 67 / comment 20403 at exact head `e7b29219e11efd0a19395156ac0b154bec0c3a73`: **REQUEST CHANGES**.
|
||||
- Blocker: the verifier echoed the pipeline commit but did not bind it to the current PR head; mutating only #2188's commit still returned terminal-green.
|
||||
- Remediation: require `--expect-commit <full-40>`, add a pipeline anomaly on missing/mismatched record commits, emit expected and observed values, wire both CI documentation and the merge-gate baseline to pass provider PR head, and add match/missing/mismatch tests.
|
||||
- This binding is not prohibited head-based clustering policy: it proves the evidence belongs to the commit under verdict. Runner/node/time/head correlation remains excluded from the teardown signature itself.
|
||||
- Review 69 later approved the commit-binding remediation at exact head `033b2ffb46674b2c0bcc5197273c109b461f62d9`; pipeline #2193 was 9/9 success. Before merge-gate, an independent adjudicator found that Python treats JSON `false == 0`, allowing a non-integer exit value to match. The prior gate-ready state was withdrawn. The type-strict set distinguishes genuine red-first controls (`false`, `0.0`, which wrongly exempted) from regression guards (`true`, `"0"`, `null`, which already blocked). Remediation requires the decoded type to be exactly `int` and excludes `bool` explicitly.
|
||||
|
||||
## Documentation checklist
|
||||
|
||||
- [x] CI contract documented in the canonical framework CI/CD guide.
|
||||
- [x] Operator command documented in the Woodpecker tool README.
|
||||
- [x] Merge-gate baseline points to the deterministic verifier and named retirement.
|
||||
- [x] Tracking and retirement cite issue #1000.
|
||||
- [x] Both positive and negative guarantee boundaries are stated.
|
||||
- [x] No API/auth/schema/user-facing navigation change; OpenAPI, user guide, and sitemap are not applicable.
|
||||
|
||||
## Risks
|
||||
|
||||
The controls establish discrimination for deterministic startup failure and an armed post-readiness postmaster crash on the current Woodpecker Kubernetes provider. They cannot prove that every future Kubernetes failure mode will preserve a non-zero exit before reconciliation. The exact matcher minimizes that residual risk, and issue #1000 remains the mandatory provider-seam closure and retirement trigger.
|
||||
@@ -1,71 +0,0 @@
|
||||
# #1019 — Zero-timeout queue-guard harness race
|
||||
|
||||
- **Issue:** #1019 (parent status remains `believed-fixed, pending jarvis validation`; do not close)
|
||||
- **Branch:** `fix/1019-ci-queue-timeout-harness`
|
||||
- **Owner:** `be-coder-08`
|
||||
- **Base:** `origin/main` at `5916aeefd6ed12bcac086c6834c7f6c4ae38e1bc`
|
||||
- **Charter:** `/home/hermes/agent-work/tl-mosaic/CHARTER-1019-HARNESS-FIX.md`
|
||||
|
||||
## Objective
|
||||
|
||||
Make `test-ci-queue-wait-tristate.sh` deterministic without changing any asserted outcome. Remove the indiscriminate zero-timeout race, require every status-classification case to prove the provider was observed, and prove the harness-controlled virtual clock is active.
|
||||
|
||||
## Scope
|
||||
|
||||
- In scope: `packages/mosaic/framework/tools/git/test-ci-queue-wait-tristate.sh` only, plus this evidence scratchpad.
|
||||
- Out of scope: guard parsers, D2/D3 behavior, installer/reseed staleness, PR #1060, and issue closure.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. RED deterministically reproduces deadline pre-emption before the provider call.
|
||||
2. Every case that intends status classification positively proves provider observation.
|
||||
3. Pending observes `pending` before deterministic virtual-time expiration.
|
||||
4. The virtual clock has a positive interception control; a broken-clock mutant makes the suite red.
|
||||
5. The exact CI-base image passes the final harness repeatedly with zero failures.
|
||||
6. Baseline gates, independent code/security review, exact-head CI, and coordinator-authorized squash merge pass.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Add deterministic RED instrumentation for the known merge/provider-unreachable pre-emption.
|
||||
2. Replace global `-t 0` with a nonzero timeout interpreted under an event-driven virtual clock; stub sleep without wall waiting.
|
||||
3. Add provider-observation and virtual-clock positive controls without changing outcome assertions.
|
||||
4. Run focused shell checks, repeat in exact CI-base image, baseline gates, and independent reviews.
|
||||
5. Commit with both identity layers, queue-guard plus direct Woodpecker terminal-state verification, push, self-post PR, verify poster/head/CI, obtain coordinator merge authorization, then squash merge without closing #1019.
|
||||
|
||||
## Budget
|
||||
|
||||
- No explicit token cap supplied. Keep scope to one harness file and one scratchpad; stop/report at the charter's 60% context gate.
|
||||
|
||||
## Evidence
|
||||
|
||||
- RED, deterministic pre-provider expiry: `evidence/1019-harness-fix/red-pre-provider-expiry.log` — rc 1; merge/provider-unreachable got rc 124 instead of 75, omitted CANNOT_ASSERT, did not observe the status provider, and wrote no additional audit record (four named failures).
|
||||
- GREEN host focused harness: `evidence/1019-harness-fix/green-host.log` — rc 0, all outcome classes passed.
|
||||
- Load-bearing clock negative control: a temporary same-directory mutant replaced the virtual `date` body with `/bin/date`; `evidence/1019-harness-fix/red-clock-not-intercepted.log` — rc 1 with named `virtual clock interception did not run` failures. The mutant file was removed after the run.
|
||||
- Exact CI-base repeat: `git.mosaicstack.dev/mosaicstack/stack/ci-base:latest`, repository mounted read-only, harness work under container `/tmp`; `evidence/1019-harness-fix/ci-image-repeat/summary.log` — **100 pass / 0 fail / 100 total**.
|
||||
- Synchronization design: provider-status observation creates the event marker; virtual time is 1000 before the event and 1002 afterward. Pending alone reaches the stubbed no-op sleep and a post-observation deadline check. `-t 1` is uniquely load-bearing because removing it restores the 900-second default deadline at virtual time 1900, which 1002 does not cross. The numeric timeout is subject semantics under virtual time, not a wall-clock synchronization duration.
|
||||
|
||||
## Review remediation — semantic timeout vs. liveness bound
|
||||
|
||||
Security review found that virtual time remained at 1000 forever before provider observation and stubbed sleep never waited. A regression looping before the status endpoint—or blocking in the first provider call—therefore could prevent `run_guard` from returning, so the post-return provider assertion could never fire.
|
||||
|
||||
**General rule:** A timeout usually serves two purposes: semantics and liveness. Removing wall time from semantic synchronization can silently remove the only independent hang bound. Preserve deterministic virtual time for subject semantics, but provide a separately implemented real-clock liveness watchdog and prove that watchdog fires.
|
||||
|
||||
Remediation:
|
||||
|
||||
- Every guard subject invocation is launched by absolute `/usr/bin/python3` in a new session. Python's internal monotonic `wait(timeout=...)` provides real-clock liveness independently of PATH; expiry kills the entire isolated process group, so neither PATH-front shims nor a blocked provider descendant can retain the capture pipe.
|
||||
- Watchdog expiry returns distinct harness rc 90 plus `FAIL HANG watchdog`, separate from subject timeout rc 124.
|
||||
- A first attempt using absolute `/usr/bin/timeout -s KILL` passed on GNU coreutils but failed in the exact Alpine CI-base image: BusyBox killed the immediate wrapper while the guard/provider descendants survived and retained the command-substitution pipe. The process-group kill is therefore required behavior, not portability polish.
|
||||
- A committed positive control hangs the branch-provider stub before the status endpoint. It must terminate through the watchdog, emit the hang-specific diagnostic, return rc 90, and prove the status provider was never reached.
|
||||
- RED before remediation: a temporary ordinary-success mutant hung before provider observation; only an external control could kill the suite (rc 137), and there was no internal hang-specific diagnostic (`red-watchdog-absent.log`).
|
||||
- The watchdog mutant/control is load-bearing: removing the internal watchdog leaves the control unable to produce its required rc 90 and diagnostic.
|
||||
|
||||
Post-review evidence:
|
||||
|
||||
- Host focused harness with process-group watchdog: rc 0 (`green-watchdog-process-group-host.log`).
|
||||
- Exact Alpine CI-base focused harness with process-group watchdog: rc 0 (`green-watchdog-ci-image.log`).
|
||||
- Hanging ordinary-success mutant: suite rc 1; success returned rc 90, emitted `FAIL HANG watchdog`, and loudly reported that provider/clock observation did not occur (`red-watchdog-fires.log`).
|
||||
- Removed-`-t 1` mutant: suite rc 1; pending was terminated by the watchdog instead of producing `ASSERTED_NOT_READY`, proving the explicit timeout is load-bearing (`red-timeout-argument-removed.log`).
|
||||
|
||||
## 60% context hold
|
||||
|
||||
Stopped before baseline/review/commit as required by the charter. Remaining: inspect final diff, shell/static/baseline gates, independent code/security review, remediation if any, identity-bound commit/trailer verification, mandatory queue guard plus direct terminal Woodpecker `mosaic` enumeration, push, self-posted PR/provider poster read-back, exact-head terminal-green CI, coordinator merge authorization, squash merge, main CI verification, and leave #1019 unclosed as `believed-fixed, pending jarvis validation`.
|
||||
@@ -1,229 +0,0 @@
|
||||
# #1043 — Fleet pane git-identity propagation
|
||||
|
||||
## Objective
|
||||
|
||||
Ensure a fleet seat's launched runtime process receives its roster-derived `MOSAIC_GIT_IDENTITY`, and lock the complete generated-environment propagation boundary with an enumerated set comparison.
|
||||
|
||||
## Tracking
|
||||
|
||||
- External issue: `mosaicstack/stack#1043`
|
||||
- Branch: `fix/1043-pane-git-identity`
|
||||
- Coordinator: `tl-mosaic`
|
||||
- `docs/TASKS.md`: read-only by project worker contract; not modified.
|
||||
|
||||
## Constraints
|
||||
|
||||
- RED-first bug reproducer is mandatory.
|
||||
- R7 delete-the-subject mutation must turn the behavioral test red.
|
||||
- Assert launched-process environment, not source text.
|
||||
- One push only; do not poll CI after push.
|
||||
- Run the CI queue guard immediately before push and report its `state=` line as state, not evidence.
|
||||
- Do not modify a live host launcher or obtain/copy another credential.
|
||||
- Self-post the PR, verify provider attribution, then stop.
|
||||
- Final status wording: `believed-fixed, pending jarvis validation`.
|
||||
|
||||
## Scope inventory
|
||||
|
||||
Re-derived against `origin/main` at `85d2108e`:
|
||||
|
||||
- Launch consumer: `packages/mosaic/framework/tools/fleet/start-agent-session.sh`
|
||||
- Behavioral launch test: `packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
- Generated-environment contract/parser: `packages/mosaic/src/fleet/generated-env-boundary.ts`
|
||||
- Roster projection producers:
|
||||
- `packages/mosaic/src/commands/fleet.ts`
|
||||
- `packages/mosaic/src/fleet/fleet-reconciler.ts`
|
||||
- `packages/mosaic/src/fleet/fleet-agent-crud.ts`
|
||||
- `packages/mosaic/src/fleet/v1-v2-migration.ts`
|
||||
- Contract and producer tests discovered by repository search.
|
||||
- Generated-environment operator/developer docs and their executable documentation contract test.
|
||||
|
||||
Discrepancy sent to `tl-mosaic`: current main no longer contains the charter's `PANE_SHELL_SNIPPET`; #772 replaced it with an `/usr/bin/env -i` argv launch boundary, and current generated projections do not declare git identity. Code-read inventory is **NOT MEASURED** behavior.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Add the process-environment set-comparison regression first and record RED.
|
||||
2. Add roster-derived `MOSAIC_GIT_IDENTITY=<agent name>` to the complete generated projection contract.
|
||||
3. Validate identity syntax and equality with `MOSAIC_AGENT_NAME`; pass it through the clean pane environment.
|
||||
4. Update affected projection tests and generated-environment docs.
|
||||
5. Run focused and baseline gates.
|
||||
6. Perform R7 by deleting the pane propagation entry, prove RED, restore, and prove GREEN.
|
||||
7. Run independent review, remediate, commit, queue guard, one push, self-post PR, verify provider attribution, and stop without CI polling.
|
||||
|
||||
## Budget
|
||||
|
||||
No explicit token cap was provided. Working cap: one narrow logical unit, no dependency installation unless existing tooling requires it, no unrelated refactor.
|
||||
|
||||
## Evidence log
|
||||
|
||||
### TDD and mutation evidence
|
||||
|
||||
- RED-first, repository launcher: `bash packages/mosaic/framework/tools/fleet/test-start-agent-session.sh` exited 64 on pre-fix source with `code=unknown-key key=MOSAIC_GIT_IDENTITY`. The generated seat could not launch with the required declared identity.
|
||||
- GREEN: the same repository launcher test emitted `ok - start-agent-session generated environment boundary`.
|
||||
- R7 delete-the-subject: removed only `"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"` from the repository launch array; the same test exited 1 with `FAIL: runtime pane omitted or changed generated environment keys: MOSAIC_GIT_IDENTITY`.
|
||||
- R7 restoration: restored that launch entry; the same test returned green.
|
||||
- Launcher under test is explicitly `packages/mosaic/framework/tools/fleet/start-agent-session.sh` through the test's `$START`, **not** the stale installed host copy.
|
||||
|
||||
### Situational and focused tests
|
||||
|
||||
- Repository launcher boundary: green, including set comparison of all nine generated projection entries and fail-before-tmux cases for missing, unsafe, mismatched, and local-shadow Git identity.
|
||||
- Fleet systemd launcher integration: `bash packages/mosaic/framework/systemd/user/test-fleet-units.sh` — green.
|
||||
- Focused Mosaic Vitest set: 6 files, 311 tests — green.
|
||||
- `bash -n` on changed shell files — green.
|
||||
- `git diff --check` — green.
|
||||
|
||||
### Baseline gates
|
||||
|
||||
- `pnpm typecheck` — 45/45 tasks green.
|
||||
- `pnpm lint` — 25/25 tasks green.
|
||||
- `pnpm format:check` — green.
|
||||
- `pnpm test:checkout` — green.
|
||||
- Repository-wide Vitest under a hermetic current-version npm prefix: Mosaic 81/81 files and 1510/1510 tests green; other workspace test tasks shown green before the framework-shell phase.
|
||||
- Canonical `pnpm test` is not fully green on this host for unrelated environment-sensitive gates:
|
||||
1. the first two runs exposed the globally installed Mosaic 0.0.48 update banner in three CLI smoke tests expecting empty stderr;
|
||||
2. after isolating that global-version input, the framework wake assertion aborted at the known `#973` Bash `BASH_LINENO` convention check (exit 97; observed `[3 5]`, expected `[3 4]`).
|
||||
No tests were weakened or bypassed; focused changed-surface tests are green. CI remains the canonical clean-environment result and is intentionally not polled after push per charter.
|
||||
|
||||
### Independent review
|
||||
|
||||
- Codex code review first pass: request changes for missing shell rejection-path coverage.
|
||||
- Remediation: added table-driven missing/unsafe/mismatch/local-shadow launcher cases, each asserting no tmux call.
|
||||
- Codex code re-review: **approve**, no findings, confidence 0.88.
|
||||
- Codex security review: risk `none`, no findings, confidence 0.97.
|
||||
|
||||
### Acceptance criteria mapping
|
||||
|
||||
| Acceptance criterion | Evidence |
|
||||
| --- | --- |
|
||||
| AC-FGI-01: launched process receives every generated key/value | Repository launcher process-environment `comm -23` set comparison; GREEN and R7 RED evidence above |
|
||||
| AC-FGI-02: missing, unsafe, or split identity fails before tmux | Table-driven shell cases plus TypeScript generated-boundary tests |
|
||||
| AC-FGI-03: focused/baseline/review evidence recorded | Commands and review outcomes above; host-sensitive full-suite limitations stated explicitly |
|
||||
|
||||
### Documentation checklist
|
||||
|
||||
- PRD updated with #1043 requirements and acceptance criteria.
|
||||
- Fleet launch runbook, generated-env concept, and generated-env reference updated.
|
||||
- No API/OpenAPI, sitemap, user publishing target, deployment, or external docs publication change applies.
|
||||
- `docs/TASKS.md` remains unmodified per its single-writer project contract.
|
||||
|
||||
## Round 2 — PR #1073 review 97 remediation
|
||||
|
||||
### Review blocker
|
||||
|
||||
The launched-process suite was signed-excluded from CI enumeration. Manual GREEN/R7 evidence therefore did not prove a PR workflow could detect regression.
|
||||
|
||||
### RED-first and canonical wiring
|
||||
|
||||
1. Removed the suite's signed exclusion before adding a CI execution path.
|
||||
2. `check-test-enumeration.sh` went RED with exact `UNENUMERATED` output for `test-start-agent-session.sh`: population 49, enumerated 30, excluded 18.
|
||||
3. Added both `framework/tools/fleet/test-start-agent-session.sh` and `framework/systemd/user/test-fleet-units.sh` to `@mosaicstack/mosaic`'s canonical `test:framework-shell` chain.
|
||||
4. The guard returned GREEN: population 49, enumerated 32, excluded 18, surfaces 45. The systemd suite is outside the guard's tools-only population but now has the same explicit canonical execution disposition.
|
||||
|
||||
### Workflow-level R7
|
||||
|
||||
- Deleted only the pane launch entry `"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"`.
|
||||
- Ran the exact `.woodpecker/ci.yml` test-step command, `pnpm test`, with only a temporary PATH-scoped npm shim reporting the checkout's current 0.0.49 version so the unrelated global 0.0.48 banner could not preempt the shell chain.
|
||||
- Result: exit 1 at `@mosaicstack/mosaic#test`, with the enumeration guard GREEN followed by `FAIL: runtime pane omitted or changed generated environment keys: MOSAIC_GIT_IDENTITY`.
|
||||
- Restored the launch entry. The canonical `test:framework-shell` chain then reached both newly wired suites and printed both GREEN markers before the known unrelated #973 host-only `BASH_LINENO` abort.
|
||||
- An actual provider PR workflow on the intentionally broken mutant is **NOT MEASURED**: the one-push constraint forbids pushing a red mutant and then a repaired head. Local execution proves the exact PR workflow command and dependency chain go RED on the subject deletion; CI on the repaired pushed head remains canonical.
|
||||
|
||||
### Workflow population
|
||||
|
||||
- **DEFINED:** 3 workflows (`ci.yml`, `ci-image.yml`, `publish.yml`).
|
||||
- **ELIGIBLE for `pull_request`:** 1/3 (`ci.yml`), based on top-level `when:` clauses.
|
||||
- **REPORTED:** Round-1 exact-head provider read reported 1/1 eligible context (`ci/woodpecker/pr/ci`). Post-remediation-head reported count is **NOT MEASURED** by this seat because CI polling is prohibited; workflow definitions and eligibility did not change.
|
||||
|
||||
### Independent remediation review
|
||||
|
||||
- First Round-2 review identified a CI-image blocker: the newly wired launcher suite used Perl, which the Alpine CI base does not install.
|
||||
- Replaced the suite's three Perl-only fixture mutations with POSIX/BusyBox-compatible `sed -i` substitutions; production behavior and assertions are unchanged.
|
||||
- Codex re-review: **APPROVE**, confidence 0.93, no findings.
|
||||
|
||||
### Vitest denominator reconciliation
|
||||
|
||||
The PR's `311/311` is correct for its explicitly named six-file command at both the original and remediation worktrees:
|
||||
|
||||
- generated environment boundary: 24
|
||||
- fleet documentation: 23
|
||||
- Tess service profile: 6
|
||||
- fleet regen command: 27
|
||||
- fleet agent CRUD command: 22
|
||||
- fleet command: 209
|
||||
- total: **311**
|
||||
|
||||
Review 97 reported 312/312 without naming its six files. That is a different or miscounted population and cannot replace the command-scoped 311 denominator; the PR follow-up will name the exact files and arithmetic.
|
||||
|
||||
## Round 3 — Alpine stale-marker portability
|
||||
|
||||
### Objective and plan
|
||||
|
||||
- Replace the GNU-only relative-date fixture with a deterministic POSIX/BusyBox timestamp while preserving the required stale-marker assertion.
|
||||
- Re-run the launcher suite in the canonical `ci-base:latest` Alpine image, then run applicable repository gates and independent review.
|
||||
- Update the PR body to name the repeated GNU-host/Alpine-CI portability pattern, run the mandatory queue guard, push once, verify provider attribution, and stop without CI polling.
|
||||
- Working budget: 8K tokens; scope is one fixture line plus delivery evidence. No production behavior changes.
|
||||
|
||||
### RED-first evidence
|
||||
|
||||
Before the fix, the canonical CI image command
|
||||
`docker run --rm -v "$PWD:/work" -w /work git.mosaicstack.dev/mosaicstack/stack/ci-base:latest bash packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
exited 1 at the stale-marker setup with exact BusyBox output
|
||||
`touch: invalid date '10 seconds ago'`. The prior fresh-marker assertions had already executed, matching pipeline 2233's failure location.
|
||||
|
||||
### Root cause and fix
|
||||
|
||||
The test used GNU `touch -d` relative-date parsing although the PR workflow runs on Alpine/BusyBox. The fixture now uses POSIX `touch -t 200001010000.00`, a fixed timestamp that is unconditionally stale; the stale assertion remains mandatory and was not made tolerant of missing timestamp metadata.
|
||||
|
||||
### Structural pattern
|
||||
|
||||
This is the third GNU-host/Alpine-CI portability defect in the lane: GNU `grep` multi-match counting, Perl-only fixture mutation, and GNU `touch -d` date parsing. The repeated cause is shell suites authored on a GNU host but executed in an Alpine CI image; durable prevention belongs in CI-image execution or portability lint, not assertion weakening.
|
||||
|
||||
### GREEN and quality evidence
|
||||
|
||||
- Focused launcher suite in `ci-base:latest`: exit 0, `ok - start-agent-session generated environment boundary`.
|
||||
- Canonical test step in `ci-base:latest` with the pipeline's `pgvector/pgvector:pg17` service, readiness check, migration, and `pnpm test`: exit 0; 46/46 Turbo tasks; Mosaic 81/81 files and 1510/1510 tests; Gateway 57 passed/5 skipped files and 629 passed/11 skipped tests; enumeration 49 population / 32 enumerated / 18 signed exclusions / 45 named surfaces.
|
||||
- The first image-only `pnpm test` attempt lacked the pipeline PostgreSQL service and failed only on connection refusal after the launcher suite was GREEN. The rerun supplied the canonical service precondition and passed.
|
||||
- Canonical-image baseline: typecheck 45/45 tasks, lint 25/25 tasks, format check GREEN; `git diff --check` GREEN.
|
||||
- Independent Codex code review: APPROVE, confidence 0.96, 2/2 Round-3 files, no findings.
|
||||
- Independent Codex security review: risk none, confidence 0.99, 2/2 Round-3 files, no findings.
|
||||
|
||||
### Re-derived inventory and denominators
|
||||
|
||||
- Round-3 git delta: **2/2 files** — launcher suite and task scratchpad; 25 insertions / 1 deletion before evidence finalization.
|
||||
- Full PR path inventory against `origin/main` at `85d2108e`: **19/19 changed paths**; Round 3 adds no new PR path.
|
||||
- Workflow definition population: **1/3 pull-request-eligible** (`ci.yml` of `ci.yml`, `ci-image.yml`, `publish.yml`).
|
||||
- Do not re-litigate the settled 311/312 populations; both are valid for their separately named Tess6 and CRUD-core7 sets.
|
||||
|
||||
## Round 4 — bound stale-marker observation
|
||||
|
||||
### Objective and plan
|
||||
|
||||
- Make the heartbeat assertion discriminate an initially stale native marker from a fresh marker without changing the production staleness threshold or shortening the polling window.
|
||||
- Freeze only the sidecar's numeric observation clock during the stale-fixture arm so elapsed assertion time cannot turn a fresh mutant stale.
|
||||
- Prove two independent mutants RED: disable production stale-marker detection while retaining the stale fixture; replace the stale fixture with a fresh marker. Restore the tree and prove GREEN in the canonical Alpine image.
|
||||
- Re-derive the changed-path inventory, run applicable quality and independent review gates, commit with environment-only author/committer identity, queue-guard, push once, verify provider attribution using curl stdin config, and stop without CI polling.
|
||||
- Working budget: 8K tokens. Scope is the launcher test and its scratchpad evidence; production launcher behavior remains unchanged.
|
||||
|
||||
### Root cause and bounded observation
|
||||
|
||||
The 30 × 0.1-second assertion window overlaps the production `now - marker > interval * 2 + 1` threshold at interval 1. Depending on second boundaries and load, a fresh marker can age past the threshold before the assertion ends. A focused pre-fix fresh-mutant attempt returned RED while Review 101's full-suite run returned GREEN; the differing result is itself timing dependence, not a discriminating assertion.
|
||||
|
||||
The test now supplies a fixed numeric epoch only to the stale-fixture sidecar. Its real marker mtime is still read from the filesystem, but assertion runtime cannot advance `now`. Date formatting still delegates to the image's real `/bin/date`. Neither the production threshold nor the 30 × 0.1-second polling window changed.
|
||||
|
||||
### Two-mutant RED / restored GREEN
|
||||
|
||||
All three runs used `git.mosaicstack.dev/mosaicstack/stack/ci-base:latest`:
|
||||
|
||||
1. **Stale-detection mutant RED:** replaced only the production stale-age predicate with `false` while retaining the fixed stale marker; suite exit 1 with `FAIL: heartbeat sidecar did not resume after native marker became stale or absent`.
|
||||
2. **Fresh-marker mutant RED:** replaced only `touch -t 200001010000.00` with fresh `touch`; suite exit 1 with the same failed stale-resumption assertion. The fixed observation epoch kept the mutant fresh throughout all 30 polls.
|
||||
3. **Restored tree GREEN:** suite exit 0 with `ok - start-agent-session generated environment boundary`.
|
||||
|
||||
### Re-derived inventory
|
||||
|
||||
- Round-4 delta: **2/2 files** — launcher test plus task scratchpad; production launcher delta is empty.
|
||||
- Full PR inventory against `origin/main`: **19/19 paths**; Round 4 adds no path.
|
||||
- Production stale threshold remains `now - marker > iv * 2 + 1`; assertion polling remains 30 × 0.1 seconds.
|
||||
- Review 101's confirmed enumeration/workflow/CI and attribution evidence is accepted without re-polling or re-derivation.
|
||||
|
||||
## Residual risk
|
||||
|
||||
- Landing on `main` does not update the currently installed host launcher. Host framework installation/reseed and Jarvis live-seat validation are separate downstream events.
|
||||
- Canonical CI result is pending and will not be polled by this seat.
|
||||
@@ -1,97 +0,0 @@
|
||||
# #1098 — Framework shell portability / red main
|
||||
|
||||
## Objective
|
||||
|
||||
Restore terminal-green `main` by making the `test-start-agent-session.sh` clean-environment assertion semantic and portable without removing either newly enumerated framework-shell suite.
|
||||
|
||||
## Scope
|
||||
|
||||
- Tracking issue: `mosaicstack/stack#1098`
|
||||
- Branch: `fix/framework-shell-portability`
|
||||
- Base: `origin/main` at `4fa2768962702d53e16e8b67ee6ad52ebcb0910e`
|
||||
- Primary file: `packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
- Requirements source: `docs/PRD.md` § Framework shell assertion portability (#1098)
|
||||
- Out of scope: deployed files under `~/.config/mosaic`, pnpm-store cleanup, checkout deletion, and changes to the launcher’s `/usr/bin/env -i` behavior.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. The test inspects the captured NUL-delimited tmux argv semantically and accepts an adjacent `/usr/bin/env`, `-i` pair regardless of trailing payload size or pipe scheduling.
|
||||
2. Missing `/usr/bin/env`, missing `-i`, and non-adjacent `-i` remain failures.
|
||||
3. Failure output includes the observed argv records with stable indexes and shell escaping; it exposes no credentials because this fixture supplies only generated non-secret launch data.
|
||||
4. The focused suite passes on the dev host and in the repository CI image; the blocking PR/main pipeline returns terminal green.
|
||||
5. Independent review passes; PR is squash-merged and #1098 is closed only after merged-main CI is terminal green.
|
||||
|
||||
## Budget
|
||||
|
||||
- ASSUMPTION: 30K-token working budget; rationale: one shell-test defect plus full PR/CI lifecycle.
|
||||
- Auto-reduction: focused shell and package gates first; rely on canonical Woodpecker for the full monorepo suite rather than duplicating a dependency install under constrained `/home`.
|
||||
- Disk baseline before clone/build: `/home` 7.1G free (99% used), `/tmp` 2.4G free (92% used).
|
||||
|
||||
## Investigation
|
||||
|
||||
### First-hand CI evidence
|
||||
|
||||
- Public log: `GET https://ci.mosaicstack.dev/api/repos/47/logs/2269/53041`
|
||||
- Decoded 1,436 entries (11 null `data` entries treated as empty log rows), 190,756 bytes.
|
||||
- Failure: `FAIL: pane command did not clear its environment` immediately after the expected pane-PID warning.
|
||||
- BusyBox primitives, complete assertion pipeline, real CI image, stale/current image digests, Turbo cache masking, gateway failure, and heartbeat-sidecar concurrent writing were independently excluded.
|
||||
|
||||
### Root cause
|
||||
|
||||
The assertion ends in:
|
||||
|
||||
```bash
|
||||
printf '%s\n' "$pane_args" | tail -n +"$after_pane_env" | grep -qxF -- '-i'
|
||||
```
|
||||
|
||||
The script has `set -o pipefail`. `grep -q` exits as soon as it finds the valid `-i` record. Upstream `tail`/`printf` can then receive SIGPIPE, making the aggregate pipeline nonzero even though grep returned 0 and the semantic property is true. This depends on payload size, pipe capacity, and scheduling, explaining a local/image pass with a CI failure.
|
||||
|
||||
Discriminating stress control with `/usr/bin/env` followed immediately by `-i`:
|
||||
|
||||
- 8,192-byte trailing payload: `printf=0 tail=0 grep=0`, aggregate 0.
|
||||
- 16,384-byte trailing payload: `printf=0 tail=141 grep=0`, aggregate 141.
|
||||
- 32,768+ bytes: `printf=141 tail=141 grep=0`, aggregate 141.
|
||||
- A full-reading `grep -xF` control remained 0 for every payload.
|
||||
|
||||
This is a third branch omitted by the earlier present-vs-corrupted split: the pair can be present and intact while `pipefail` reports an upstream SIGPIPE.
|
||||
|
||||
## TDD plan
|
||||
|
||||
1. RED: preserve the one-off stress reproducer above and add an automated large-argv semantic regression that fails under the current pipeline implementation.
|
||||
2. GREEN: parse the authoritative NUL-delimited capture into a Bash array and search for an adjacent `/usr/bin/env`, `-i` pair without a short-circuit pipeline.
|
||||
3. Add negative controls for missing, detached, and reversed tokens.
|
||||
4. On failure, print indexed `%q` argv records before returning nonzero.
|
||||
5. Run focused suite, mutation controls, shell syntax/format checks, then repository baseline gates feasible without dependency installation.
|
||||
6. Independent review, queue guard, push, PR, CI, coordinator merge authorization, squash merge, merged-main CI, issue close.
|
||||
|
||||
## Progress
|
||||
|
||||
- [x] Checkout created and based on `origin/main` `4fa27689`.
|
||||
- [x] CI log decoded directly.
|
||||
- [x] Root-cause stress control reproduced semantic match + aggregate pipeline failure.
|
||||
- [x] RED evidence: intact `/usr/bin/env`, `-i` fixture produced component statuses `0/141/0` and aggregate 141 under the former `grep -q` pipeline; full-reading semantic control stayed 0.
|
||||
- [x] GREEN implementation: direct NUL-argv adjacency parser, indexed diagnostics, and full-reading scalar predicates replace all load-bearing early-exit pipelines in this test.
|
||||
- [x] Baseline/situational tests:
|
||||
- focused launcher suite: PASS on GNU host and cached Alpine CI image;
|
||||
- paired `test-fleet-units.sh`: PASS;
|
||||
- enumeration guard: PASS (`population=53`, `enumerated=36`, `excluded=18`), 14/14 mutation needles;
|
||||
- `bash -n`, ShellCheck, `git diff --check`: PASS;
|
||||
- static denominator after change: zero load-bearing `grep -q`/`head`/`-m1` pipeline candidates in `test-start-agent-session.sh`;
|
||||
- delete-the-subject mutation removing production `-i`: RED with 78 indexed argv records, byte count, and explicit boundary failure.
|
||||
- [x] Independent review:
|
||||
- first Codex review: request changes — negative fixtures did not each assert diagnostics;
|
||||
- remediation: centralized predicate + diagnostic wrapper and exercised all four negative fixtures;
|
||||
- second Codex review: APPROVE, 0 blockers/should-fix/suggestions;
|
||||
- Codex security review: risk none, 0 findings.
|
||||
- [ ] PR CI, formal fleet review, merge, merged-main CI, issue closure.
|
||||
|
||||
## Documentation disposition
|
||||
|
||||
- Updated canonical `docs/PRD.md` with FSP requirements and acceptance criteria.
|
||||
- This is an internal test/reliability change with no API, user workflow, deployment, navigation, or publishing-surface change; no user/admin/API/sitemap update is required.
|
||||
- `docs/TASKS.md` remains unchanged because the project contract makes it orchestrator-only.
|
||||
|
||||
## Risks
|
||||
|
||||
- The CI failure did not print its captured argv, so the exact CI payload is unavailable. The stress control proves the assertion is non-portable and can emit the exact false verdict; branch CI is the canonical confirmation that replacing it resolves pipeline 2269’s failure class.
|
||||
- Printing fixture argv is safe only while this test’s projection remains non-secret. The diagnostic must stay scoped to the test capture and shell-escaped.
|
||||
@@ -1,41 +0,0 @@
|
||||
# #1099 — pipefail + early-exit sweep
|
||||
|
||||
## Scope and decisions
|
||||
|
||||
- Baseline `df4c591ab42aa1ae62c12935fdc0e772684864a0`, after #1100 removed its 35 sites.
|
||||
- Split into review-sized non-closing tranches: runtime/general; tmux/git/quality tests; wake validation/tests.
|
||||
- Do not equate class membership with demonstrated risk. Do not use payload size or pipeline stage count as a safety proxy.
|
||||
- Preserve the issue's withdrawn findings for `qa-hook-stdin.sh` and the two fresh-directory `pnpm pack` lookups. Fix `install.sh:312` because malformed multi-root input must reach its named handler.
|
||||
|
||||
## Tranche 1 TDD
|
||||
|
||||
RED-first control: `node --test scripts/pipefail-early-exit.test.mjs` reported exactly 26 non-accepted runtime/general sites, including `install.sh:312`, and exited 1. A checked-in fixture generated from immutable baseline `df4c591a` records all 26 normalized sites; the control passes every fixture entry through the same scanner, asserts exact identity/count/uniqueness, and separately requires zero findings in the current tree. It also inventories accepted sites rather than silently excluding whole files.
|
||||
|
||||
Construction choices:
|
||||
|
||||
- here-string/file redirection for scalar grep assertions;
|
||||
- full capture then parameter expansion for first-line selection;
|
||||
- arrays/`mapfile` for complete populations;
|
||||
- direct jq/awk/grep selection where one tool can express the property;
|
||||
- no `|| true` added to a load-bearing assertion.
|
||||
|
||||
Site-by-site verdicts: `docs/reports/quality/1099-pipefail-sweep.md`.
|
||||
|
||||
## Tranche 2 TDD
|
||||
|
||||
Expanded the unconditional scanner over 11 non-wake test harnesses. RED named exactly 22 source lines; a second immutable-baseline fixture now asserts those 22 entries through the same scanner. Rewrites preserve command status by capturing producers before redirected assertions, use parameter expansion for line selection, and use complete `mapfile` populations where ordering matters. Current-tree finding count is zero for tranches 1 and 2.
|
||||
|
||||
## Tranche 3 TDD
|
||||
|
||||
Expanded the shared scanner over four wake validation harnesses. RED named 26 occurrences. The wake fixture asserts 26 occurrences / 25 normalized identities through the same scanner; all scalar assertions now use redirection, direct jq selection, complete capture, or consuming diagnostic ranges. Current-tree finding count is zero across the full scoped population.
|
||||
|
||||
## Verification so far
|
||||
|
||||
- `bash -n` on every changed shell script: pass.
|
||||
- structural Node control: pass.
|
||||
- `test-mutate-push-guard.sh`: 8/8 pass.
|
||||
- `test-send-message-verdict.sh`: 3/3 pass.
|
||||
- `test-send-message-socket.sh`: pass.
|
||||
- Independent review 143 found two semantic regressions: a help-probe `|| true` changed the failure truth table, and an unguarded Git capture changed non-Git data-dir behavior from rc 0 + JSON to silent rc 128. Both received RED-first regressions before correction; help status is now separate and required, and Git status remains condition-guarded.
|
||||
- Wake static inventory remains aligned at 261/261 after line-neutral rewrites; no static-set mismatch. Wake detector/reconcile/digest/preimage suites terminate at their existing fail-closed #973 `BASH_LINENO` environment probe (exit 97, observed `[3 5]`, expected `[3 4]`) before subject tests. No bypass or skip was used; canonical CI remains required.
|
||||
- ShellCheck reports only pre-existing source-following, unused-variable, and untouched `ls | head` findings; no new diagnostic was introduced.
|
||||
@@ -1,156 +0,0 @@
|
||||
# #1150 — Pi persistent goal extension
|
||||
|
||||
- **Task ID:** ISSUE-1150 (no `docs/TASKS.md` row; that file is orchestrator-only)
|
||||
- **Issue:** #1150 — `pi: add persistent /goal controller extension to Mosaic framework`
|
||||
- **Branch:** `feat/1150-pi-goal-extension`
|
||||
- **Mode:** Delivery
|
||||
- **Status:** in progress
|
||||
|
||||
## Objective
|
||||
|
||||
Build and locally validate a Mosaic-owned Pi `/goal` extension. Source must ship from
|
||||
`packages/mosaic/framework/runtime/pi/`, framework sync must deploy it under
|
||||
`~/.config/mosaic/runtime/pi/`, and no extension/configuration asset may be written into `~/.pi`.
|
||||
Pi's native session manager remains the owner of session entries.
|
||||
|
||||
## Scope and acceptance source
|
||||
|
||||
- Canonical requirements: `docs/PRD.md`, section **Pi Persistent Goal Loop (#1150)**.
|
||||
- User intent: continuous goal orientation and status checking after each Pi turn and compaction,
|
||||
tested locally before framework delivery.
|
||||
- Documentation target: canonical in-repo user/developer/runtime docs; no external publication.
|
||||
|
||||
## Assumptions
|
||||
|
||||
- `ASSUMPTION:` Initial semantic verification uses two consecutive structured, evidence-bearing
|
||||
reports from the working agent rather than a second model request after every turn. This keeps the
|
||||
loop testable and avoids doubling model cost while making the limitation explicit.
|
||||
- `ASSUMPTION:` Default autonomous bounds are 40 turns and 6 repeated no-progress reports, with only
|
||||
bounded numeric environment overrides.
|
||||
- `ASSUMPTION:` A local smoke copy to `~/.config/mosaic/runtime/pi/goal-extension.ts` is authorized by
|
||||
the user's explicit request. Full framework reseed into the live home is not required for the smoke
|
||||
test and would touch unrelated framework-owned files.
|
||||
|
||||
## Budget
|
||||
|
||||
- Working estimate: 30K implementation/review tokens.
|
||||
- Hard user cap: none stated.
|
||||
- Cost control: deterministic fake-Pi tests; no nested evaluator calls; only bounded arithmetic/load
|
||||
smoke workflows against the installed runtime.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Update PRD and create tracking/scratchpad artifacts.
|
||||
2. Read launcher, installer ownership, Pi extension, and documentation surfaces.
|
||||
3. TDD: add fake-Pi behavior tests for commands, state restoration, turn checks, compaction, limits,
|
||||
verification, and continuation deduplication.
|
||||
4. Implement `runtime/pi/goal-extension.ts` and deterministic launcher discovery.
|
||||
5. Add framework-sync/deployment acceptance coverage.
|
||||
6. Update user, developer, runtime, framework README, and sitemap documentation.
|
||||
7. Run focused tests, local Mosaic-path smoke test, then baseline repository gates.
|
||||
8. Run independent review, remediate, commit, push/PR/CI/merge/issue closure per delivery gates.
|
||||
|
||||
## TDD decision
|
||||
|
||||
Applied. The continuation state machine and lifecycle scheduling are control-path logic where a race
|
||||
or false terminal state can cause unbounded work or premature completion.
|
||||
|
||||
## Progress checkpoints
|
||||
|
||||
- [x] Issue #1150 created through Mosaic wrapper.
|
||||
- [x] Isolated worktree created from `origin/main`.
|
||||
- [x] PRD requirements and acceptance criteria added.
|
||||
- [x] Task scratchpad created.
|
||||
- [x] RED controller and security-regression tests written and observed failing before implementation.
|
||||
- [x] Goal controller, launcher discovery, framework deployment coverage, and bounded state machine
|
||||
implemented.
|
||||
- [x] User, admin, developer, runtime, adapter, README, and sitemap documentation updated.
|
||||
- [x] Final source copied additively to `~/.config/mosaic/runtime/pi/goal-extension.ts`; source and
|
||||
deployed SHA-256 are identical.
|
||||
- [x] Live Pi RPC smoke from the exact Mosaic path reached `achieved` with two verification passes and
|
||||
no extension errors.
|
||||
- [x] Baseline and situational checks completed, except the explicitly documented unavailable
|
||||
PostgreSQL-only root integration case.
|
||||
- [x] Independent code and OWASP/security reviews completed; all findings remediated and re-reviewed.
|
||||
- [ ] Commit, push, PR, terminal-green CI, squash merge, and issue closure complete.
|
||||
|
||||
## Tests and evidence
|
||||
|
||||
### Situational
|
||||
|
||||
- `pnpm --filter @mosaicstack/mosaic exec vitest run src/runtime/pi-goal-extension.spec.ts`
|
||||
- final: 25 passed.
|
||||
- Covers commands, per-turn checks, context injection, two-pass verification, mixed-report
|
||||
rejection, bounded limits, compaction, branch restore, stale timers, credential redaction,
|
||||
typed-field false-positive protection, and append-only legacy-state fail-closed behavior.
|
||||
- Final focused launcher/controller/file-adapter run: 3 files / 67 tests passed.
|
||||
- Final V8 coverage for `framework/runtime/pi/goal-extension.ts`:
|
||||
- 99.17% statements/lines, 93.78% branches, 100% functions.
|
||||
- Installer migration fixture: 24 passed and byte-compared the deployed framework asset.
|
||||
- Standalone extension TypeScript check against installed Pi 0.84.1 types passed:
|
||||
`pnpm --filter @mosaicstack/mosaic exec tsc --noEmit --pretty false --module NodeNext
|
||||
--moduleResolution NodeNext --target ES2022 --skipLibCheck framework/runtime/pi/goal-extension.ts`.
|
||||
- Live deployment/load evidence:
|
||||
- source/deployed SHA-256:
|
||||
`1f0a3806e0948ad5f49684273a7e535e9880c148f7fd16d13ee487fcd601f637`.
|
||||
- `get_commands` identified `/goal` as an extension command sourced from
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts`; `/goal help` succeeded; zero extension errors.
|
||||
- live arithmetic goal ended `achieved`, verification `2/2`, with 3 goal reports / 3 agent starts
|
||||
and zero extension errors.
|
||||
- no goal extension exists under `~/.pi` extension paths.
|
||||
|
||||
### Baseline
|
||||
|
||||
- `pnpm build`: passed before the final framework-only redaction remediation; the extension is not a
|
||||
package build input and its final source passed the standalone Pi type check.
|
||||
- `pnpm typecheck`: 45/45 tasks passed.
|
||||
- `pnpm lint`: 25/25 tasks passed.
|
||||
- `pnpm format:check`: passed.
|
||||
- Final Mosaic package components:
|
||||
- Vitest: 82 files / 1,539 tests passed.
|
||||
- full `test:framework-shell` harness passed.
|
||||
- the discovered pre-existing tmux loader-marker race was reproduced with constructor PID
|
||||
evidence, fixed with a pane readiness/FIFO barrier, passed 3 consecutive focused runs, and passed
|
||||
in the full shell harness.
|
||||
- one combined rerun encountered the separate existing real-lease probe TOCTOU in
|
||||
`install-ordering-guard.spec.ts`; an earlier final Vitest run was fully green and the changed
|
||||
focused suites remained green.
|
||||
- Gateway safe baseline excluding the prohibited PostgreSQL-only fixture: 55 files / 600 tests passed
|
||||
(6 files / 12 tests skipped by their existing environment gates).
|
||||
- Root `pnpm test` reached 43 successful workspace tasks and all changed-package Vitest tests, but
|
||||
the unchanged `apps/gateway/src/__tests__/cross-user-isolation.test.ts` afterAll hook retried a
|
||||
PostgreSQL connection and failed authentication (`28P01`). This checkout explicitly forbids local
|
||||
PostgreSQL startup/access; the failure is unrelated to #1150 and cannot be remediated by starting
|
||||
the database. The gateway suite excluding that PostgreSQL-only file and required CI are used as
|
||||
the safe verification paths.
|
||||
|
||||
### Independent review
|
||||
|
||||
- Codex code review: approved, 0 findings across 15 files.
|
||||
- Initial Codex security review: one medium CWE-532/A09 finding for raw report persistence.
|
||||
- Remediation added central credential-pattern redaction, prompt/docs guidance, canary tests, typed
|
||||
field false-positive guards, and sticky fail-closed restore for credential-bearing append-only
|
||||
history.
|
||||
- Codex security re-review: risk `none`, 0 findings, confidence 0.87.
|
||||
- Focused remediation review findings were fixed; final focused re-review verdict: `APPROVE`.
|
||||
- Focused independent review of the tmux readiness barrier: `APPROVE`, no actionable findings.
|
||||
|
||||
## Risks and blockers
|
||||
|
||||
- Live `~/.config/mosaic` is shared by active Pi/fleet processes. Local deployment remained a single
|
||||
additive framework file and did not reload or restart unrelated sessions.
|
||||
- Completion verification is semantic, not mathematical: the active agent supplies structured
|
||||
evidence twice. Operators must still inspect consequential outcomes.
|
||||
- Credential redaction is pattern-based defense-in-depth, not a secret store. It covers
|
||||
controller-owned state/status/tool details, not Pi's separate model-message/tool-call history.
|
||||
Goals and reports must never contain real secrets or raw sensitive output. Because Pi session
|
||||
entries are append-only, a detected credential-bearing legacy branch fails closed and the affected
|
||||
session must be removed.
|
||||
- Current installed Pi is newer than the repository's historical gateway Pi dependency. The
|
||||
extension was checked and smoke-tested against installed Pi 0.84.1 using stable documented APIs.
|
||||
- Local root testing cannot safely execute the unchanged PostgreSQL-only integration fixture under
|
||||
the checkout's explicit database safety constraints. Terminal-green PR CI remains mandatory before
|
||||
merge.
|
||||
- The unchanged real-lease default-probe test can observe different broker availability across its two
|
||||
sequential probes; one combined package rerun hit that existing TOCTOU. The same final Vitest suite
|
||||
passed in a separate run, and CI remains the merge authority.
|
||||
@@ -1,89 +0,0 @@
|
||||
# #1174 — Wrapper guard rounds 10–11
|
||||
|
||||
## Objective
|
||||
|
||||
Make checkout enforcement judge Git placement operands rather than every HOME-shaped word in the command, without reopening `--separate-git-dir` placement under HOME.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Reproduce the four over-blocks and the placement-option control at head `20d86e39`.
|
||||
2. Add RED fixtures before production changes.
|
||||
3. Extract clone/worktree placement operands from the existing shell-aware normalized stream.
|
||||
4. Run the full guard corpus, historical-head discrimination, syntax/static checks, probes, review, and CI.
|
||||
|
||||
## Progress and evidence
|
||||
|
||||
- Reproduced: `NOTE=$HOME`, `--reference=$HOME`, `GIT_DIR=$HOME/x`, and `--template=$HOME/t` all blocked despite explicit `/src/wt` destinations.
|
||||
- RED at `20d86e39`: expanded suite had 8 failures, all HOME-valued non-placement cases.
|
||||
- GREEN: expanded suite passes 242/242.
|
||||
- Round-10 probes: 7/7 placement expectations and 4/4 placement-option controls pass.
|
||||
- Earlier path probes remain green: 60/60, 24/24, and 17/17.
|
||||
- Historical discrimination with the 242-fixture suite:
|
||||
- `3d0a882a`: 216 pass / 26 fail.
|
||||
- `4b8eba95`: 222 pass / 20 fail.
|
||||
- `20d86e39`: 234 pass / 8 fail.
|
||||
- `bash -n`, ShellCheck warning-or-higher, and `git diff --check`: pass.
|
||||
|
||||
## Residual / risk
|
||||
|
||||
- Relative destinations whose effective path depends on cwd are tracked separately by #1197 and remain out of scope.
|
||||
- Unknown future Git options with a separate following value fail closed when that value is HOME-shaped. This may require classification when Git adds an unrelated path-taking option, but prevents a new placement option from silently bypassing the guard.
|
||||
|
||||
## Round 11 objective and intake
|
||||
|
||||
- **Issue / PR:** #1174.
|
||||
- **Objective:** Remove the finite boolean-flag allowlists that turn accepted clone/worktree flags into fake placement operands, while preserving all real HOME placement blocks.
|
||||
- **Scope:** `wrapper-guard.sh`, its hermetic fixtures, and task documentation. Relative cwd-dependent destinations remain in #1197.
|
||||
- **Surfaces:** security-sensitive Bash hook behavior and shell/Git option grammar; no API, DB, UI, auth, deploy, or dependency changes.
|
||||
- **Budget assumption:** 25K working tokens; reduce exploratory matrices before reducing acceptance coverage.
|
||||
|
||||
### Round 11 plan
|
||||
|
||||
1. Use Git itself to classify accepted/rejected clone and worktree options, and Bash itself to resolve path-word expectations.
|
||||
2. Add RED fixtures for all six reported clone flags, generated negations, and equivalent worktree grammar.
|
||||
3. Replace the open-ended unknown-option fail-closed fallback with a parser based on the closed value-taking option surface; keep explicit placement options special.
|
||||
4. Run the full corpus, historical discrimination, shell/static checks, targeted probes, independent code/security review, one push, and exact-head CI.
|
||||
|
||||
### Root-cause evidence
|
||||
|
||||
- Git 2.39.5 accepts all six reported clone flags and the broader generated family measured in the brief: `--bare`, `--mirror`, `--ipv4`, `--ipv6`, `-4`, `-6`, `--no-local`, `--no-reject-shallow`, `--no-bare`, `--no-sparse`, `--no-dissociate`, `--no-shallow-submodules`, `--no-quiet`, `--no-progress`, and `--no-recurse-submodules`; it rejects `--relative-paths` as unknown.
|
||||
- Git 2.39.5 accepts worktree negations including `--no-force`, `--no-detach`, `--no-lock`, `--no-guess-remote`, and `--no-track`; the current finite worktree flag list does not describe that generated family.
|
||||
- `bash -c "printf '%s' <word>"` resolves `$HOME/source`, `${HOME}/source`, and `"$HOME"/source` under HOME while `/src/wt` remains outside it.
|
||||
- **Hypothesis:** only separate-value options need positive classification. Treat every other option token as a no-value flag unless it is the explicit placement option; this matches Git's non-enumerable boolean family and confines the residual to genuinely new future value-taking options.
|
||||
|
||||
### TDD and verification checkpoints
|
||||
|
||||
- RED against the unmodified `91cc37bc` guard: 253 pass / 22 fail in the initial expanded 275-fixture suite. Failures include all 15 accepted clone flags, accepted long abbreviations, short value-taking bundles, abbreviated placement, worktree metadata abbreviation, and both directions of bundled worktree branch parsing.
|
||||
- An exploratory fail-closed residual test drove emission of every worktree positional. Re-review correctly showed that this over-blocked HOME-shaped commit-ish metadata; a new commit-ish fixture failed RED against that intermediate implementation (278 pass / 2 fail, including one transient message assertion) and the parser was restored to emit only the actual path.
|
||||
- GREEN after remediation: 280/280.
|
||||
- Ultron's 13-shape option probe: 13/13 correct, including the six reported over-blocks, HOME destinations, end-of-options, worktree controls, and a later-command placement.
|
||||
- Round-10 probes remain green: 7/7 subject-placement expectations and 4/4 `--separate-git-dir` controls.
|
||||
- Earlier shell/path probes remain green: 60/60, 24/24, and 17/17.
|
||||
- `bash -n`, ShellCheck warning-or-higher, and `git diff --check`: pass.
|
||||
|
||||
### Deliberate residual
|
||||
|
||||
A future Git release could add a new separate-value option absent from the closed value grammar. It defaults to no-value flag parsing, which leaves the following word positional. For clone, this can fail open if that future option itself creates repository state at its value. For worktree, it can shift which word is read as the path. This hypothetical future ambiguity is accepted deliberately because failing closed on every unclassified option is proven to over-block Git's open-ended present-day boolean/`--no-*` family. Every value-taking and placement option Git currently supports is classified, including accepted abbreviations of `--separate-git-dir`. Relative cwd-dependent targets remain in #1197.
|
||||
|
||||
### Independent review checkpoint
|
||||
|
||||
- Initial Codex code/security review raised `--orphan` as value-taking. Upstream Git `master` contradicts that premise: the synopsis is `[--orphan] [(-b | -B) <new-branch>] <path> [<commit-ish>]`, and the prose derives the branch from the path when `-b`/`-B` is absent. `--orphan` is therefore correctly handled as a boolean flag.
|
||||
- The security review separately identified the generic future worktree shift residual. An attempted fail-closed remediation emitted every positional, but code re-review correctly rejected it because valid grammar has only one placement positional and an optional commit-ish. Final behavior checks only the path and documents the hypothetical future option shift deliberately; paired actual-grammar `--orphan` fixtures cover safe/HOME paths and `-b` metadata.
|
||||
- Security re-review initially had no findings. Code re-review's commit-ish blocker was remediated with a RED fixture and path-only restoration; final code re-review approved with no findings.
|
||||
- Final security review then found non-canonical absolute and symlink aliases. Eight lexical fixtures failed RED against the prior implementation, followed by three symlink fixtures failing RED. Remediation expands only shell-visible HOME tokens, resolves the longest existing directory prefix physically, and lexically normalizes the nonexistent suffix. The suite is now 292/292.
|
||||
- Inherent residual: a symlink can be replaced between pre-tool inspection and Git execution. Existing aliases are resolved; eliminating the race requires enforcement inside the filesystem mutation path rather than a text pre-hook. Security review classified this medium, and architectural closure is tracked in #1199.
|
||||
- Final independent code review: APPROVE, 0 findings. Final security review: no critical/high findings; the single medium TOCTOU residual is explicitly tracked in #1199.
|
||||
|
||||
### Final local evidence
|
||||
|
||||
- Final hermetic suite: 292/292; the same suite against `91cc37bc` discriminates at 256 pass / 36 fail.
|
||||
- Ultron option probe: 13/13; round-10 probes: 7/7 plus 4/4 controls; earlier shell/path probes: 60/60, 24/24, and 17/17.
|
||||
- `bash -n`, ShellCheck warning-or-higher, `git diff --check`, sanitization gate, and test-enumeration gate (population 55; 38 enumerated; 18 signed exclusions): pass.
|
||||
- Independent code review: APPROVE, 0 findings. Security review's remaining medium TOCTOU architecture residual is tracked in #1199; no critical/high findings remain.
|
||||
- Repository-wide TypeScript gates require dependencies absent from this worktree; the canonical Woodpecker pipeline will run them against the pushed exact head.
|
||||
|
||||
### Documentation checklist
|
||||
|
||||
- `docs/PRD.md` updated with WPG requirements, acceptance, canonicalization, and residual risk.
|
||||
- Task scratchpad updated in the same logical change set; `docs/TASKS.md` remains orchestrator-only.
|
||||
- No API, auth, UI, navigation, deployment, user-guide, or admin-guide surface changed; OpenAPI, endpoint index, sitemap, and publishing are not applicable.
|
||||
@@ -1,71 +0,0 @@
|
||||
# #1194 — Installed framework-tool drift detection and refresh analysis
|
||||
|
||||
## Decision
|
||||
|
||||
The reported queue-guard source defect was already fixed on `main` by `58b971ab`; the live failure came from a stale `~/.config/mosaic/tools/git/ci-queue-wait.sh`. The durable fix is therefore a detector, not a duplicate queue-guard patch.
|
||||
|
||||
`mosaic doctor` now compares the framework tools bundled with the executing Mosaic package against the deployed tools tree. Doctor is the selected visibility boundary because it is observational and operator-invoked: unlike session start, it does not add a repository/network scan to every seat launch, and it cannot silently replace identity or messaging tools while seats are active. It reports drift without changing files. `--fail-on-warn` converts detected drift into a non-zero doctor result.
|
||||
|
||||
## Classification
|
||||
|
||||
The existing `framework-manifest.txt` is authoritative. The detector invokes the canonical shared `tools/_lib/manifest.sh classify` implementation over the complete source census and refuses missing, unreadable, malformed, incomplete, or zero-framework ownership output. Policy is therefore read rather than duplicated:
|
||||
|
||||
- Current policy classifies source files under `tools/**` as framework-owned and required in the deployed tools tree.
|
||||
- Current policy explicitly classifies `tools/_lib/credentials.json` operator-owned and excludes it from byte comparison; future policy changes take effect without a detector edit.
|
||||
- A file present only in the deployed tools tree is operator-owned/unknown by the manifest's fail-safe default. The detector reports it as `INSTALLED_ONLY operator-or-unknown` under `--verbose` but does not fail or delete it.
|
||||
- Empty/partial source traversal, unreadable directories/files, symlinked census entries, root aliases, and descendant source aliases all return `CANNOT_ASSERT` rather than manufacturing agreement.
|
||||
|
||||
This means `NOT_INSTALLED` is not suppressed by filename guesses such as “test” or “README”: if it ships below source `tools/**`, the installer contract says it should be installed. Source-only implementation files outside `tools/**` are outside this detector population by construction.
|
||||
|
||||
## Current host analysis (observation only; no refresh performed)
|
||||
|
||||
A direct source-vs-installed census showed broad drift, including identity and messaging behavior:
|
||||
|
||||
- Identity/provider operations: stale `git/detect-platform.sh`, `issue-comment.sh`, `issue-create.sh`, `issue-close.sh`, `issue-view.sh`, `pr-create.sh`, `pr-merge.sh`, `pr-review.sh`, `pr-metadata.sh`; missing `pr-edit.sh` and several identity/read-back regression tools.
|
||||
- Messaging/session: stale `tmux/agent-send.sh`, `tmux/send-message.sh`, their regressions, and `fleet/start-agent-session.sh`.
|
||||
- Gate enforcement: stale `git/ci-queue-wait.sh`; missing the queue tri-state/process-level suites and terminal-green verifier.
|
||||
- Lease/QA behavior: stale lease-broker launch/mutation/receipt tools and QA hooks.
|
||||
|
||||
Counts vary with source head and installed local/operator files; the detector prints measured counts every run rather than baking this snapshot into policy.
|
||||
|
||||
## Reviewed refresh command — analyse only, do not run during active seats
|
||||
|
||||
Use the package/release updater's manifest-driven keep-mode sync during a quiet maintenance window:
|
||||
|
||||
```bash
|
||||
MOSAIC_SYNC_ONLY=1 \
|
||||
MOSAIC_INSTALL_MODE=keep \
|
||||
MOSAIC_HOME="$HOME/.config/mosaic" \
|
||||
bash /path/to/reviewed/@mosaicstack/mosaic/framework/install.sh
|
||||
```
|
||||
|
||||
For the globally installed package, resolve the reviewed installer rather than guessing its path:
|
||||
|
||||
```bash
|
||||
PACKAGE_ROOT="$(dirname "$(node -p "require.resolve('@mosaicstack/mosaic/package.json')")")"
|
||||
MOSAIC_SYNC_ONLY=1 MOSAIC_INSTALL_MODE=keep MOSAIC_HOME="$HOME/.config/mosaic" \
|
||||
bash "$PACKAGE_ROOT/framework/install.sh"
|
||||
```
|
||||
|
||||
Do not run this while agent seats are active: the stale set includes identity selection, provider mutation, messaging, queue/merge guards, lease enforcement, and session launch. Syncing those files in place can change behavior between a seat's preflight and mutation.
|
||||
|
||||
## Post-refresh verification
|
||||
|
||||
1. Run `mosaic doctor --fail-on-warn`; require `stale=0 not-installed=0` from the framework drift summary (other unrelated doctor warnings must also be adjudicated).
|
||||
2. Re-run the constructed process-level queue probes against the **installed path**, not the source checkout. Use the source suite while overriding its subject path in a reviewed scratch copy, or reproduce these exact observations:
|
||||
- pending provider payload: guard must print `state=pending`, print the pending context, wait, and exit non-zero/timeout — never return immediately with rc 0;
|
||||
- malformed payload: guard must print `state=malformed` and exit non-zero;
|
||||
- unsupported but valid status vocabulary: guard must print `state=unknown` and exit non-zero.
|
||||
3. Run provider author read-back for one deliberately low-risk wrapper operation before resuming fleet mutation work; wrapper self-report is not identity evidence.
|
||||
4. Relaunch seats only after the quiet-window verification, because existing processes retain loaded environment/context.
|
||||
|
||||
## Probe evidence
|
||||
|
||||
The detector regression constructs a stale installed tool plus a missing shipped tool and observes rc 1 with distinct `STALE` and `NOT_INSTALLED` lines. That case would pass or be invisible before this change because no installed-vs-shipped comparison existed. Additional review-red controls prove:
|
||||
|
||||
- empty and unreadable source censuses return `CANNOT_ASSERT` (they returned clean rc 0 at the first PR head);
|
||||
- deleting the manifest returns `CANNOT_ASSERT`, while changing manifest ownership changes the verdict through the canonical resolver (the first head never opened the manifest);
|
||||
- root and descendant symlink/source aliases cannot return clean (the first head returned clean for a source-backed installed subtree);
|
||||
- a checker hung during doctor is terminated by a bounded watchdog, emits `CANNOT_ASSERT`, and doctor reaches its final warnings line (the first head hung and suppressed the remaining audit).
|
||||
|
||||
Controls retain byte-identical success, exact credential carve-out behavior, and installed-only preservation.
|
||||
@@ -1,99 +0,0 @@
|
||||
# PR merge squash message field
|
||||
|
||||
- **Charter:** `/home/hermes/agent-work/CHARTER-PRMERGE-MESSAGE-FIELD.md`
|
||||
- **Owner:** `be-coder-08`
|
||||
- **Branch:** `fix/pr-merge-message-field`
|
||||
- **Base:** remote `main` / local `origin/main` at `85d2108e4ed15c744ad3b87a5b629e7b2d39405a`
|
||||
- **Estate:** HOMELAB tooling shared by HOMELAB and USC
|
||||
|
||||
## Objective
|
||||
|
||||
Add an optional, identity-checked Gitea squash message to `pr-merge.sh` so genuine multi-author PRs retain non-poster branch authors without weakening hardcoded squash behavior.
|
||||
|
||||
## Binding requirements
|
||||
|
||||
1. `Do` remains hardcoded to `squash`; no provider/repository default may select merge style.
|
||||
2. A verified trailer uses a PR commit's linked `author.login` and that same commit's author email. No `/users/{login}` primary-email lookup occurs. Recorded rationale: this asks only what the provider can answer.
|
||||
3. A commit with `author.login` null blocks before merge, prints both the null provider fact and commit email fact, and names the escalation principal.
|
||||
4. The BLOCK arm must be observed firing; a normal canonical single-author API payload remains explicit squash plus its reviewed `head_commit_id`.
|
||||
5. Every provider mutation is read back from the provider; no real PR is merged during tests.
|
||||
|
||||
## Derived interface decisions
|
||||
|
||||
- Add `--co-author-trailers` rather than accepting arbitrary message text. The wrapper enumerates PR commits and constructs trailers, making an unchecked `Co-authored-by` line unexpressible.
|
||||
- Require `--escalate-to PRINCIPAL` with `--co-author-trailers`, so the BLOCK diagnostic always names a principal rather than a generic role.
|
||||
- Do not expose `MergeTitleField` separately. When trailers exist, set it from the provider PR title and set `MergeMessageField` only to construction-generated trailers. This preserves one provider source for the title and avoids an unrelated caller-controlled degree of freedom.
|
||||
- Preserve first-commit order and emit one trailer per distinct non-poster `author.login`, using that first linked commit's own email.
|
||||
|
||||
## Canonical delivery plan
|
||||
|
||||
1. Port the capability into the installed source of truth, `packages/mosaic/framework/tools/git/pr-merge.sh`; do not retain `infra/fleet/tools/git` as a second copy.
|
||||
2. Preserve canonical `--expect-head`, exact head branch/repository/SHA queue inspection, Gitea atomic head pinning, GitHub `--match-head-commit`, and delete-after-merge semantics.
|
||||
3. Do not port the deployed-only `--skip-queue-guard` bypass. Add the focused harness to the canonical framework-shell suite and re-establish RED/GREEN on the packaged baseline.
|
||||
4. Deliver through a reviewed package release followed by `mosaic update` with its default framework reseed. The installer snapshots, manifest-syncs framework-owned `tools/**`, and rolls back on failure.
|
||||
5. Before either estate relies on the change, require installed/package hash equality, `MergeMessageField` presence, and a green focused harness. Release/reseed ownership is currently unassigned and blocks activation after source merge.
|
||||
|
||||
## Evidence
|
||||
|
||||
- RED against the byte-identical deployed baseline (`sha256 08a65e8584c5…`): rc 1 with eight named failures. The wrapper rejected `--co-author-trailers`; the null-login path emitted none of the required BLOCK facts/principal; and both verified/ordinary API paths failed the stdin-config credential assertion (ordinary path exposed the fixture token through curl argv). Log: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-message-field-red.log`.
|
||||
- GREEN on the deployed-baseline candidate: verified linked multi-author payload, null-login BLOCK, required named principal, explicit squash, stdin-config token transport, and absence of `/users` lookup all passed. Log: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-message-field-green.log`.
|
||||
- RED against canonical packaged baseline `c581ef48…`: rc 1 with 32 assertions. It rejects the new option, and the first harness version did not satisfy canonical head branch/repository/SHA metadata. Log: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-packaged-baseline-red.log`. The port adapts the fixture rather than weakening canonical head controls.
|
||||
- Provider capability probe against `git.mosaicstack.dev`: authenticated `be-coder-08` POST to deliberately nonexistent PR `2147483647` with both message fields returned JSON HTTP 404; the unauthenticated same request returned JSON HTTP 401 (not the charter's predicted 403). The authenticated-vs-unauthenticated differential proves write authorization resolved while no mergeable subject existed. `tl-mosaic` ruled the literal non-load-bearing: preserve the observed 404/401 pair and do not manufacture a 403 case. No cause was inferred and no real PR was targeted.
|
||||
- Provider-generated trailer behavior is not treated as exclusive or absent. The wrapper's VERIFIED/BLOCK decision binds each requested non-poster trailer to commit `author.login` plus that commit's email; it does not assume `MergeMessageField` is the squash's only trailer source. The poster is omitted from the constructed list because the resulting squash author already records the poster; any additional provider-generated trailer is outside this change's unmeasured mechanism.
|
||||
- An early candidate SHA-256 `5de32876990e4f26920448cb3220cc7f1146d558b4dd2bc1ee1a2abee2f2cbe6` passed the initial harness, then author-side review found credential-fallback and argv-exposure defects. The live deployed wrapper was atomically restored to baseline SHA-256 `08a65e8584c52c6d41ea1c686f8b95585c21e4b37320a2447eba09359a0e02c1`; the remediated candidate remains only in the worktree.
|
||||
|
||||
## Remediation and current review state
|
||||
|
||||
1. Token and Basic Auth now use stdin curl configuration, not argv. PR title, contributor email, and the JSON payload also remain out of child argv.
|
||||
2. Each credential attempt binds commit inspection and merge. A token failure during either inspection or mutation causes Basic fallback to repeat inspection before mutation; the payload pins the inspected `head_commit_id`.
|
||||
3. Focused tests cover token-resolution fail-closed behavior, both HTTP-401 fallback seams, metadata/credential argv absence, null-login BLOCK, explicit squash, canonical reviewed-head binding, unchanged ordinary payload, and retained log-safe provider diagnostics. Token-resolution RED: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-token-resolution-red.log`.
|
||||
4. Codex review rounds 3–5 requested retained provider error text, log-safe provider diagnostics, fail-closed credential fallback, stable value-option parsing, and PR-title trailer-injection prevention. These are remediated with regression assertions. A post-remediation independent review is still required.
|
||||
5. **Accepted linkage limitation:** `author.login` resolution proves that the commit address maps to a registered provider account. It does not prove that the named principal authored the commit because Git author metadata is self-asserted. This gate checks attribution linkage, not authorship; commit signing is out of scope and currently unadopted. Coordinators explicitly ruled that this does not add a third state.
|
||||
6. Codex's sandbox could not execute the harness because its checkout was read-only; that environmental limitation is recorded separately from host-side test results.
|
||||
|
||||
## Disposable provider fixture acceptance
|
||||
|
||||
- Use a retained scratch repository only, with two branch authors and `author != committer` on at least one commit.
|
||||
- Arm A supplies a message-field trailer for one non-poster; record whether that value lands without forcing the partial-pair result into under-specified `APPENDS`/`REPLACES` labels. Demonstrate an absence control.
|
||||
- Arm B includes a registered trailer for a different non-poster on a branch commit; record whether it survives or drops. Verify identity through an existing commit whose `author.login` resolves and demonstrate an absence control.
|
||||
- Parse landed trailers key-agnostically with `^[A-Za-z-]+-[Bb]y:` and record generated poster pair presence/absence plus resulting poster attribution.
|
||||
- Record `/users/<login>` status and raw email only as non-gating estate telemetry. Never read `active`, `visibility`, or any profile field as an identity gate.
|
||||
- Use distinct principals: poster `be-coder-08`, merger `Mos`, Arm A `be-coder-07`, and Arm B `be-coder-06`. Capture every trailer-shaped line verbatim and in order. Zero trailer lines means the generator did not fire and the run is `VOID`, not evidence that either arm dropped.
|
||||
- Report the same read-back evidence to `mos-claude` on socket `default` and `tl-mosaic` on socket `mosaic-fleet`. Report values rather than mechanism inferences and stop on any poster-attribution regression.
|
||||
|
||||
## Fixture preflight
|
||||
|
||||
- Retained public repository: `mosaicstack/prmerge-trailer-fixture`; PR `#1`, posted by `be-coder-08` and reserved for merge by `Mos`.
|
||||
- Existing `mosaicstack/stack` commits resolve `be-coder-07` and `be-coder-06` through `author.login`; exact addresses are `[email protected]` and `[email protected]`.
|
||||
- Non-gating HOMELAB telemetry for authenticated reader `be-coder-08`: `/api/v1/users/be-coder-06` returned HTTP 200 with raw `email` value `[email protected]`.
|
||||
- Provider preflight showed PR commit enumeration is newest-first. A new RED test proved that deriving `head_commit_id` from the final array element selected the wrong commit. The candidate now reads `.head.sha` from the authenticated PR endpoint before enumeration, verifies it appears in the commit set, and atomically pins that SHA in the explicit squash payload. RED: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-head-order-red.log`.
|
||||
- Fixture PR head `f6ba6e5105031fa21f5ff7bd8e4379d99c16e1de` has `author.login=be-coder-07`, `committer.login=be-coder-08`, and branch-message trailer `Co-authored-by: be-coder-06 <[email protected]>`.
|
||||
|
||||
## Fixture result
|
||||
|
||||
- `Mos` merged retained fixture PR `#1` through staged candidate SHA-256 `60e779a85fd13b729d859ea7c986d1e9b1641b97991611329226c1b3113ffb6e`; resulting squash commit: `3f550715d9bc716426fd355a65fe997b3a90fa7d` with one parent.
|
||||
- Provider read-back: poster/commit author `be-coder-08`, committer/merger `Mos`. The run is non-void.
|
||||
- Trailer-shaped lines, verbatim and in order:
|
||||
1. `Co-authored-by: be-coder-07 <[email protected]>`
|
||||
2. `Co-authored-by: be-coder-08 <[email protected]>`
|
||||
- Arm A supplied field value (`be-coder-07`) landed. Arm B branch trailer (`be-coder-06`) dropped. Both fabricated absence controls remained absent. No `Co-committed-by:` line landed.
|
||||
- The candidate payload construction explicitly excludes the poster and supplied only the Arm A `be-coder-07` line. Therefore the landed poster line was provider-generated, not candidate-composed. The raw result supports `FIELD LANDS`, `BRANCH DROPS`, and `POSTER GENERATED`; it does not support a claim that candidate code supplied the poster. Evidence: `/home/hermes/agent-work/be-coder-08/evidence/prmerge-fixture-readback.log` and the retained provider object.
|
||||
- Retained fixture PR `#2` measured the N=2 shape needed by `#1030`: supplied `be-coder-07` then `be-coder-06`; both landed in that order, followed by the provider-generated poster line. No truncation or dedup occurred at N=2. Resulting squash: `39db9d13aed0…`.
|
||||
|
||||
## Current hold point
|
||||
|
||||
PR `mosaicstack/stack#1066` is open. Its first frozen head `f4b162fa…` was terminal-green in Woodpecker `mosaic` pipeline `#2225`, but that evidence becomes stale when the canonical port moves the head. The deployed wrapper remains baseline `08a65e85…`; no manual copy will occur. Canonical port tests, commit amendment, rebase, one guarded force-with-lease, exact-head CI, and new independent review remain. Even after source merge, activation remains blocked on an assigned package-release/reseed owner and installed-byte read-back.
|
||||
|
||||
## Security review 96 remediation
|
||||
|
||||
Exact reviewed predecessor head: `1ceb11058f64dd7f4a817ceb2124f980a1c4dd23`.
|
||||
|
||||
RED-first focused harness produced 10 named failures: all curl calls lacked size/time/connect bounds; raw ESC email reached mutation; oversized and stalled curl failures were discarded and reached mutation; nonempty Basic output with resolver rc 91 authorized mutation.
|
||||
|
||||
Security remediation:
|
||||
|
||||
- Removed the cross-principal HTTP-401 Basic fallback. Both inspection-401 and merge-401 paths now refuse without Basic resolution or mutation; `get_gitea_basic_auth` references in the merge subject are 0.
|
||||
- Applied `--max-filesize`, `--max-time`, and `--connect-timeout` to all 3/3 provider curl sites and fail closed on curl transport rc at all 3/3 sites.
|
||||
- Required linked email bytes to be ASCII and printable before constructing `MergeMessageField`; guarded construction sites 1/1.
|
||||
|
||||
GREEN: message-field, exact-head, empty-UID/API, queue branch/repository/SHA, bash syntax, ShellCheck, and diff check pass. R7 total-removal mutants went RED: email guard 3 rows; bound switches 1 row; transport-rc guards 4 rows; HTTP-401 refusal 3 rows. R7 bound: mutants prove total removal only; explicit denominators above prove site coverage.
|
||||
@@ -40,15 +40,6 @@
|
||||
- AC4 DONE at `0f706119`: in that same fresh clone and CI image, `pnpm -w build` completed 25/25 tasks and the immediately following `git status --porcelain` was empty; combined assertion exit 0.
|
||||
- Push BLOCKED after the required queue guard: `git push origin fix/rm-01-reproducible-checkout` was rejected by Gitea with `User permission denied for writing` / `pre-receive hook declined`, despite `MOSAIC_GIT_IDENTITY=f10-coder` resolving username `f10-coder` from the provisioned `gitea-mosaicstack-f10-coder.token`.
|
||||
|
||||
## Review remediation — restated AC2
|
||||
|
||||
- Independent review correctly found that an added symlink under a successfully built `.next` tree passed preflight. The exact reviewer control, `ln -s /etc/hosts apps/web/.next/reviewer-symlink && pnpm preflight`, was observed passing before remediation.
|
||||
- The original blanket symlink wording conflicts with AC4 because canonical Next `output: 'standalone'` emits legitimate pnpm dependency symlinks. The coordinator independently verified 42 such links and approved the operative restatement: `.next` itself must not be a symlink; descendant symlinks must exactly match the successful build's certified manifest.
|
||||
- RED-first controls were observed failing together against the prior implementation (exit 1): `.next` root, added, removed, retargeted, tampered-manifest, and canonical-style certified-link cases. The build now publishes the manifest atomically before the existing source certification commit marker; that marker binds the manifest SHA-256. Missing/partial/modified manifests remain untrusted.
|
||||
- GREEN evidence: the six-case symlink control passes; the exact reviewer-added link exits 43; removing it restores preflight exit 0. The added RED-first build-publication control also proves a symlinked `.next` cannot redirect certification writes outside the checkout. `pnpm test:checkout` passes 23 top-level tests / 29 including subtests. Canonical `pnpm --filter @mosaicstack/web build` and the following `pnpm preflight` both exit 0.
|
||||
- Threat-model ruling: the manifest detects accidental, independent, stale, and foreign-residue mutation—the class exposed by the five-month-stale `.next` that produced 19 phantom TS2307 errors. It does not defend against a same-UID actor able to rewrite both manifest and marker consistently (CWE-345); no local worktree construction can without an external trust anchor. RM-59 tracks the residual: executor/spine-side attestation outside worktree authority, dependent on RM-12, RM-21, and RM-25.
|
||||
- AC8 concrete proof at `df7530ae`: a clean clone ran in `ci-base:latest` with Docker `--read-only`; its only writable mounts were `/workspace` (the worktree) and `/home/ci` (`HOME`, with `NPM_CONFIG_STORE_DIR=/home/ci/store`). `pnpm install --frozen-lockfile && pnpm -w typecheck` exited 0 with 45/45 uncached tasks. This proves the implemented checkout path requires no writable location outside `$HOME` and the worktree. An initial fixture attempt failed only because Git required `/workspace` safe-directory setup; it is not counted as evidence.
|
||||
|
||||
## Handoff
|
||||
|
||||
1. Keep the newly committed RED tests red until implementing: (a) source-fingerprint marker support for valid incremental `.next` output, and (b) ownership-safe concurrent hook activation.
|
||||
|
||||
@@ -1,120 +0,0 @@
|
||||
# RM-03 — CI Queue Guard Repair
|
||||
|
||||
- **Task:** RM-03
|
||||
- **Issue:** #1019
|
||||
- **Branch:** `fix/rm-03-queue-guard`
|
||||
- **Owner:** coder-mos1
|
||||
- **Reviewer:** rev-974 (independent; author != reviewer)
|
||||
- **Started:** 2026-08-01
|
||||
|
||||
## Objective
|
||||
|
||||
Repair the mandatory CI queue guard so it reads provider payloads, blocks asserted non-green CI, distinguishes provider unavailability from a real non-green result, and inspects the branch actually being pushed or merged.
|
||||
|
||||
## Constraints
|
||||
|
||||
- Worktree only: `/home/hermes/agent-work/rm-03`; never mutate `/src/mosaic-stack`.
|
||||
- JSON payload travels through stdin; never argv. Large payload must remain below no ARG_MAX dependency.
|
||||
- TDD is mandatory. Every behavior case must be observed red before implementation.
|
||||
- No bypass flags or hook suppression.
|
||||
- Do not cite the existing guard's green as evidence; D-23 establishes it is zero-information.
|
||||
- Gate-ready is a frozen exact head. Any push after a merge-gate verdict voids that verdict.
|
||||
- No merge: coordinator holds the merge hand pending Jason.
|
||||
|
||||
## Design
|
||||
|
||||
1. Feed JSON to `python3 -c` on stdin, including pending-context rendering.
|
||||
2. Classify valid green as `READY`; pending/failure/no-status/malformed/mixed as `ASSERTED_NOT_READY`; provider/credential/transport inability as `CANNOT_ASSERT`.
|
||||
3. `ASSERTED_NOT_READY` exits nonzero. `CANNOT_ASSERT` emits a loud diagnostic and appends a local JSONL audit record. Push degrades to exit 0; merge holds with distinct retryable exit 75 until provider recovery, then self-clears without manual reset. Inability to write the audit exits nonzero.
|
||||
4. Derive the current branch when `-B` is omitted. The merge wrapper passes the exact PR head branch, repository, and full commit SHA—not its `main` base—so fork PRs cannot resolve against an adjacent base-repository branch.
|
||||
|
||||
## Test matrix
|
||||
|
||||
| Case | Required outcome |
|
||||
| --- | --- |
|
||||
| success | exit 0; terminal-success |
|
||||
| pending | nonzero after bounded timeout |
|
||||
| failure | nonzero |
|
||||
| no-status | nonzero |
|
||||
| malformed | nonzero |
|
||||
| >=150 KiB payload | unchanged classification; never rc126 |
|
||||
| provider unreachable on push | loud audited CANNOT_ASSERT; degraded exit 0 |
|
||||
| provider unreachable on merge | loud audited CANNOT_ASSERT; retryable exit 75/HOLD |
|
||||
| audit unavailable | nonzero |
|
||||
| implicit push branch | provider URL uses checked-out feature branch |
|
||||
| merge wrapper | queue guard receives exact PR head branch/repository/full SHA |
|
||||
|
||||
## RED-first evidence
|
||||
|
||||
Observed against the unmodified `origin/main` implementation before source edits:
|
||||
|
||||
- `bash packages/mosaic/framework/tools/git/test-ci-queue-wait-tristate.sh` → rc 1 with 15 failed assertions.
|
||||
- Success payload was reported `state=unknown`.
|
||||
- Pending, failure, no-status, and malformed payloads each exited 0 and omitted `ASSERTED_NOT_READY`.
|
||||
- The 160 KiB payload produced rc 141 because Python never consumed the pipe; it did not classify success.
|
||||
- Provider-unreachable exited 7 with no `CANNOT_ASSERT` audit record.
|
||||
- Implicit push queried `/branches/main`, not `/branches/fix/rm-03-fixture`.
|
||||
- Audit-unavailable emitted no audit diagnostic.
|
||||
- A credential-resolution hard-block mutant was then run before trusting that added case: `credential-unresolvable` returned rc 1 and omitted `CANNOT_ASSERT`; the matrix returned rc 1 with two named assertion failures.
|
||||
- Review-blocker controls were observed red: structurally invalid `statuses` string and null-entry payloads each exited 0 as `terminal-success`; unsupported-platform discovery exited 1 without diagnostic or audit (seven named assertion failures total).
|
||||
- After the push/merge asymmetry ruling, merge-side provider unavailability was observed red at rc 0; its registered case required distinct retryable rc 75.
|
||||
- Aggregate `state=success` with zero contexts was observed red: it exited 0 as `terminal-success`; the registered case requires `no-status`/nonzero.
|
||||
- Fork/exact-head controls were observed red: `pr-merge.sh` omitted the fork repository and full SHA, and an ignored-arguments mutant re-resolved through `/branches/` instead of the exact fork commit (two named failures).
|
||||
- GitHub check-run-only success/pending/failure were each misclassified as `no-status`; the RED run had five named failures and proved the Checks API was never queried.
|
||||
- The first merge-pin control was unrunnable because one `local` declaration referenced a variable before assignment under `set -u`; this was disclosed and corrected rather than counted. The runnable RED then showed Gitea payload `{"Do":"squash"}` lacked `head_commit_id`; a separate GitHub run showed `gh pr merge 123 --squash` lacked `--match-head-commit`.
|
||||
- A stale-verdict mutant removed the `--expect-head` comparison and was observed red because a moved head reached the provider merge call.
|
||||
- `bash packages/mosaic/framework/tools/git/test-pr-merge-queue-branch.sh` initially returned rc 1; captured call was `--purpose merge -B main -t 900 -i 15`.
|
||||
|
||||
Logs remain untracked under the worktree as `.mosaic-test-work-red-*.log` and will not be committed.
|
||||
|
||||
## Progress
|
||||
|
||||
- [x] Mission, remediation charter, task evidence, board, issue #1019, and superseded PR #1023 read.
|
||||
- [x] Isolated worktree created and identity configured coherently.
|
||||
- [x] Mutant tests authored and observed red.
|
||||
- [x] Implementation green.
|
||||
- [x] Baseline and focused situational gates green; full package suite has an unrelated framework-shell environment abort recorded below.
|
||||
- [ ] Independent review clean (rev-974 requested changes at `44ffa99a`; bypass remediation committed and awaiting re-review).
|
||||
- [ ] PR CI terminal-green at exact head by full step scan.
|
||||
- [ ] Merge-gate verdict issued against frozen head.
|
||||
|
||||
## Scope disposition
|
||||
|
||||
- The five framework guides are consequential documentation: they define the purpose-aware tri-state contract, including audited push degradation and merge HOLD.
|
||||
- The agent templates are consequential because they ship the same queue-guard instructions into newly seeded agent contracts; leaving them binary/stale would contradict the repaired tool.
|
||||
- `pr-merge.sh` is consequential: it must inspect the PR's exact head branch/repository/SHA and enforce the exact-head merge pin.
|
||||
- `pr-metadata.sh` is consequential only as the normalized source of that head branch/repository/SHA. Its diff is limited to exposing those fields on GitHub and Gitea.
|
||||
- `test-pr-merge-gitea-empty-uid.sh` changes because exact-head Gitea merges now always use the API path (the only path that can send `head_commit_id`), superseding the prior tea-empty-identity fallback behavior.
|
||||
|
||||
## Review remediation
|
||||
|
||||
- rev-974 independently proved that the documented `--skip-queue-guard` merge option bypassed an exit-99 guard stub, reached the provider merge payload, printed success, and exited 0 at head `44ffa99a`.
|
||||
- RED-first reproduction was added to `test-pr-merge-head-pin.sh` before the production fix: `FAIL merge-bypass: --skip-queue-guard reached the provider merge path`, suite rc 1. The test-only commit is `241113e6`.
|
||||
- Production remediation `37aae650` removes the option from parsing, usage, help, and examples. Every merge-capable path now invokes the queue guard; `--dry-run` alone omits it and has a regression proving that it exits before provider dispatch and creates no merge payload.
|
||||
- Existing Gitea merge tests now exercise a successful guard response rather than bypassing the guard.
|
||||
|
||||
## Risks / boundaries
|
||||
|
||||
- The local JSONL audit is durable operational evidence but not tamper-resistant against the same UID. RM-03 does not claim otherwise.
|
||||
- Push-side audited exit 0 is an explicit owner ruling (Option B), accepted to avoid bricking recovery work; merge-side CANNOT_ASSERT remains retryable exit 75/HOLD. The automated security reviewer continues to flag the deliberate push availability tradeoff.
|
||||
- Source/deployed-copy equality is owned by RM-02/D-22; this branch changes repository source and its tests only.
|
||||
|
||||
## Test evidence
|
||||
|
||||
Fresh after rescue checkpoint `b7175012`:
|
||||
|
||||
- Focused situational matrix: tri-state, GitHub checks pagination, branch-absent, merge head branch/repository/SHA, exact-head pin, and Gitea exact-head API regressions all passed.
|
||||
- `bash -n` on the three production shell scripts passed.
|
||||
- `shellcheck -x -P packages/mosaic/framework/tools/git ...` on all changed shell scripts passed.
|
||||
- `pnpm typecheck` passed (45/45 Turbo tasks).
|
||||
- `pnpm lint` passed (25/25 Turbo tasks).
|
||||
- `pnpm format:check` passed.
|
||||
- `pnpm --filter @mosaicstack/mosaic test`: Vitest passed 1508/1508 on the confirmation run; framework-shell then aborted at the pre-existing wake coordinate assertion with exit 97: `BASH_LINENO ... probe reported [3 5], expected [3 4] ... (#973)`. This is outside the RM-03 diff and is disclosed rather than substituted or called green.
|
||||
- The prior package-suite attempt had one transient, out-of-diff `install-ordering-guard.spec.ts` failure (1/1508); its isolated rerun passed 19/19 and the confirmation full Vitest run passed 1508/1508.
|
||||
- After bypass remediation: all six focused RM-03 queue/merge regressions passed, including bypass refusal and dry-run non-dispatch; shell syntax and source-aware ShellCheck passed; `pnpm typecheck`, `pnpm lint`, and `pnpm format:check` passed.
|
||||
- Fresh `test:framework-shell` reached and passed every RM-03 test, then again aborted at the unrelated wake coordinate assertion with exit 97; it remains explicitly non-green rather than substituted.
|
||||
- An ad hoc raw Prettier invocation over `.template` and `.sh` files was unrunnable because no parser is registered for those extensions; it was not used as a substitute for canonical `pnpm format:check`.
|
||||
|
||||
## Final evidence
|
||||
|
||||
Pending.
|
||||
@@ -13,8 +13,7 @@ Pi is the native Mosaic agent runtime. The `mosaic pi` launcher:
|
||||
|
||||
1. Injects the full runtime contract via `--append-system-prompt`
|
||||
2. Loads Mosaic skills via `--skill` flags
|
||||
3. Loads framework-owned `mosaic-extension.ts` and `goal-extension.ts` from
|
||||
`~/.config/mosaic/runtime/pi/` via ordered `--extension` flags
|
||||
3. Loads the Mosaic extension via `--extension` for lifecycle hooks
|
||||
4. Detects active missions and injects initial prompts
|
||||
|
||||
## Capabilities vs Other Runtimes
|
||||
@@ -23,7 +22,6 @@ Pi is the native Mosaic agent runtime. The `mosaic pi` launcher:
|
||||
- Native thinking levels replace sequential-thinking MCP
|
||||
- Native skill discovery compatible with Mosaic SKILL.md format
|
||||
- Native extension system for lifecycle hooks (TypeScript, not bash shims)
|
||||
- Bounded persistent `/goal` loop with per-turn, post-compaction, and two-pass evidence checks
|
||||
- Native session persistence and resume
|
||||
- Model-agnostic (Anthropic, OpenAI, Google, Ollama, custom providers)
|
||||
|
||||
|
||||
@@ -94,14 +94,7 @@ The launcher:
|
||||
1. Verifies `~/.config/mosaic` exists
|
||||
2. Verifies `SOUL.md` exists (auto-runs `mosaic init` if missing)
|
||||
3. Injects `AGENTS.md` into the runtime
|
||||
4. For Pi, loads the framework-owned core and persistent-goal extensions from
|
||||
`~/.config/mosaic/runtime/pi/`
|
||||
5. Forwards all arguments to the runtime CLI
|
||||
|
||||
Inside `mosaic pi`, `/goal set <statement>` starts a bounded persistent goal loop. Use `/goal status`,
|
||||
`/goal pause`, `/goal resume`, or `/goal cancel` to control it. The extension remains part of Mosaic
|
||||
under `~/.config/mosaic/runtime/pi/goal-extension.ts`; it is not installed in Pi's main extension
|
||||
directory.
|
||||
4. Forwards all arguments to the runtime CLI
|
||||
|
||||
You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtime adapters will tell the agent to read `~/.config/mosaic/AGENTS.md`.
|
||||
|
||||
@@ -121,7 +114,7 @@ You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtim
|
||||
│ ├── claude/ ← CLAUDE.md, RUNTIME.md, settings.json, hooks
|
||||
│ ├── codex/ ← instructions.md, RUNTIME.md
|
||||
│ ├── opencode/ ← AGENTS.md, RUNTIME.md
|
||||
│ ├── pi/ ← RUNTIME.md, mosaic-extension.ts, goal-extension.ts
|
||||
│ ├── pi/ ← RUNTIME.md, mosaic-extension.ts
|
||||
│ └── mcp/ ← MCP server configs
|
||||
├── skills/ ← Universal skills (synced from mosaic/agent-skills)
|
||||
├── skills-local/ ← Local cross-runtime skills
|
||||
@@ -133,7 +126,7 @@ You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtim
|
||||
|
||||
| Launch method | Injection mechanism |
|
||||
| ------------------- | ----------------------------------------------------------------------------------------- |
|
||||
| `mosaic pi` | `--append-system-prompt` with composed runtime contract + skills + Mosaic extensions |
|
||||
| `mosaic pi` | `--append-system-prompt` with composed runtime contract + skills + extension |
|
||||
| `mosaic claude` | `--append-system-prompt` with composed runtime contract (`AGENTS.md` + runtime reference) |
|
||||
| `mosaic codex` | Writes composed runtime contract to `~/.codex/instructions.md` before launch |
|
||||
| `mosaic opencode` | Writes composed runtime contract to `~/.config/opencode/AGENTS.md` before launch |
|
||||
|
||||
@@ -52,52 +52,6 @@ If a repo does not expose these scripts, run equivalent local workflow commands
|
||||
- Do not auto-resolve data conflicts in shared state files.
|
||||
- Keep commits scoped to a single logical change set.
|
||||
|
||||
## Model Tiering
|
||||
|
||||
Model choice is a standard, not a preference. Delegating a mechanical grep to a
|
||||
frontier reasoning model wastes budget; sending a security review to a cheap tier
|
||||
produces a review that passes and proves nothing. Both are defects.
|
||||
|
||||
Tiers are named by **capability class**, so the standard survives a model
|
||||
generation. An operator binds each class to a concrete model id.
|
||||
|
||||
| Class | Use for |
|
||||
| ------------- | ----------------------------------------------------------------------------------------- |
|
||||
| `search` | grep/glob, file location, status and health checks, one-line mechanical edits |
|
||||
| `build` | feature implementation, test writing, bugfixes, routine refactors |
|
||||
| `judge` | code review, planning, API/compat-sensitive changes |
|
||||
| `adversarial` | security review, ambiguous architecture, anything where a wrong "looks fine" is expensive |
|
||||
|
||||
Rules:
|
||||
|
||||
1. **Start at the cheapest class that can do the task; escalate on evidence, not
|
||||
on nerves.** Omitting a tier is not neutral — it inherits the caller's model,
|
||||
which is usually the most expensive one.
|
||||
2. **Compat-sensitive work escalates one class.** A change that must interoperate
|
||||
with an existing contract is judged, not just built.
|
||||
3. **A tier assignment is benchmarked, not asserted.** Move a task class to a
|
||||
cheaper tier only against a blind A/B on real work from this codebase, ranked
|
||||
by someone other than the author. "It seemed fine" is not evidence.
|
||||
4. **Reviewer independence beats reviewer size.** An `adversarial` verdict from
|
||||
the model that wrote the code is not a second opinion (see Constitution gate 16).
|
||||
|
||||
### Where the binding lives
|
||||
|
||||
The class→model map is operator configuration, never framework source: model
|
||||
availability, cost, and quotas differ per operator and per host.
|
||||
|
||||
Resolution order, first hit wins:
|
||||
|
||||
1. the config service (DB-backed, surfaced and editable in the Mosaic webUI)
|
||||
2. a local operator file (`STANDARDS.local.md`, or `policy/` where the runtime
|
||||
injects it)
|
||||
3. the framework default — the class names above, with no binding
|
||||
|
||||
Only layer 1 is auditable across a fleet, so it is the target end state; layers 2
|
||||
and 3 exist so a host with no config service still runs. A local override that
|
||||
silently disagrees with the config service is drift — the same failure class the
|
||||
tool-index gate exists to catch, and it belongs in `mosaic doctor`.
|
||||
|
||||
## Prompting Contract
|
||||
|
||||
All runtime adapters should inject:
|
||||
|
||||
@@ -13,14 +13,7 @@ It is a **gate** role: the one and only merge path.
|
||||
2. **Use the wrapped scripts as the ONLY merge path** — the merge-gate merges
|
||||
**exclusively** by calling **`pr-merge.sh`** (the merge action, which carries the
|
||||
authoritative forbidden-path guard) and **`pr-ci-wait.sh`** (to wait for green
|
||||
CI before merging). Before issuing a verdict, scan the full JSON/API child-step
|
||||
record (including `clone`) with **`verify-terminal-green.py --expect-commit
|
||||
<current-provider-PR-head>`** and record the equal expected/observed full-40
|
||||
commits, exact step count, anomalies, and named exemptions. Missing or mismatched
|
||||
commit binding is a hard refusal. The verifier's sole interim
|
||||
exemption is `WP-K8S-1000-CI-POSTGRES-TEARDOWN`; it is signature-scoped, tracked
|
||||
by #1000, and retires when #1000 is fixed. These scripts are the _only_
|
||||
sanctioned merge path.
|
||||
CI before merging). These two scripts are the _only_ sanctioned merge path.
|
||||
3. **Never call the raw API** — the merge-gate **does NOT** call `tea`, the raw
|
||||
Gitea/forge HTTP API, or any other merge mechanism directly. Only `pr-merge.sh`
|
||||
and `pr-ci-wait.sh`.
|
||||
|
||||
@@ -868,38 +868,6 @@ steps:
|
||||
7. **Test on a short-lived non-main branch first** — open a PR and verify quality gates before merging to `main`
|
||||
8. **Verify images appear** in Gitea Packages tab after successful pipeline
|
||||
|
||||
## Terminal-Green Full-Step Contract
|
||||
|
||||
A successful pipeline summary is not sufficient: verification MUST consume the full JSON/API child-step record, including `clone`.
|
||||
|
||||
```bash
|
||||
PR_HEAD=<full-40-hex-provider-head>
|
||||
~/.config/mosaic/tools/woodpecker/pipeline-status.sh \
|
||||
-r mosaicstack/stack -n <pipeline-number> -f json \
|
||||
| ~/.config/mosaic/tools/woodpecker/verify-terminal-green.py \
|
||||
--expect-commit "$PR_HEAD" -
|
||||
```
|
||||
|
||||
`PR_HEAD` MUST come from the current provider PR metadata and MUST be the full 40-hex head, not a local branch guess. The verifier fails if the argument is missing, malformed, absent from the pipeline record, or differs from that record.
|
||||
|
||||
The verifier reports the expected and observed commits, total step count, state counts, anomalies, and any applied exemption. Exit `0` means the record satisfies the contract; exit `1` means the commit binding or at least one pipeline, workflow, or child-step state blocks terminal-green; exit `2` means the invocation or JSON input could not be verified.
|
||||
|
||||
### Named interim exemption: `WP-K8S-1000-CI-POSTGRES-TEARDOWN`
|
||||
|
||||
Only this exact conjunction is exempted:
|
||||
|
||||
- pipeline and workflow state are `success`;
|
||||
- exactly one non-success child exists;
|
||||
- its name is `ci-postgres` and type is `service`;
|
||||
- its state is `failure`, exit code is the JSON integer `0` (not boolean, float, string, or null); and
|
||||
- its error exactly matches `pods "wp-svc-<ULID>-ci-postgres" not found`.
|
||||
|
||||
Every near miss remains blocking, including non-zero service exits, startup failures, post-readiness crashes, connection errors, image-pull errors, skipped steps, another failed child, malformed pod names, duplicate matches, or a non-success pipeline/workflow.
|
||||
|
||||
**Boundary in both directions:** this exemption recognizes the observed Woodpecker Kubernetes reconciliation miss after an otherwise-successful run. It does not prove that every future PostgreSQL or Kubernetes failure is distinguishable. It does prove, through provider controls, that a deterministic startup failure (`exit_code=1`) and an armed post-readiness postmaster crash (`exit_code=137`, dependent probe `Connection refused`) do not match and remain red.
|
||||
|
||||
**Tracking and retirement:** [mosaicstack/stack#1000](https://git.mosaicstack.dev/mosaicstack/stack/issues/1000) owns the provider-seam fix. This exemption MUST be removed when #1000 is fixed. It is not authority to retry or re-trigger a pipeline, and no per-PR re-roll is part of the contract.
|
||||
|
||||
## Post-Merge CI Monitoring (Hard Rule)
|
||||
|
||||
For source-code delivery, completion is not allowed at "PR opened" stage.
|
||||
@@ -925,16 +893,14 @@ Woodpecker note:
|
||||
Before pushing a branch or merging a PR, guard against overlapping project pipelines:
|
||||
|
||||
```bash
|
||||
~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push
|
||||
~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>
|
||||
~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main
|
||||
~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main
|
||||
```
|
||||
|
||||
Behavior:
|
||||
|
||||
- If pipeline state is running/queued/pending, wait until queue clears; timeout is `ASSERTED_NOT_READY` and exits nonzero.
|
||||
- Failure, missing status, malformed status, or any other provider-asserted non-green state is `ASSERTED_NOT_READY` and exits nonzero.
|
||||
- Credential, transport, or provider unavailability is `CANNOT_ASSERT`: the guard emits a loud diagnostic and durable JSONL audit record. For push it exits 0 so recovery work is not bricked. For merge it returns distinct retryable exit 75 and holds until provider recovery; rerunning then self-clears without manual reset. This result is never evidence that CI was clear. If the audit cannot be written, the guard exits nonzero.
|
||||
- `pr-merge.sh` resolves and guards the exact PR head repository and full SHA automatically, including fork PRs.
|
||||
- If pipeline state is running/queued/pending, wait until queue clears.
|
||||
- If timeout or API/auth failure occurs, treat as `blocked`, report exact failed wrapper command, and stop.
|
||||
|
||||
## Gitea as Unified Platform
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ Merge strategy enforcement (HARD RULE):
|
||||
- PR target for delivery is `main`.
|
||||
- Direct pushes to `main` are prohibited.
|
||||
- Merge to `main` MUST be squash-only.
|
||||
- Use `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}` (or PowerShell equivalent).
|
||||
- Use `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash` (or PowerShell equivalent).
|
||||
|
||||
## Review Checklist
|
||||
|
||||
|
||||
@@ -79,7 +79,7 @@ For implementation work, you MUST run this cycle in order:
|
||||
8. `pre-push queue guard` - before pushing, wait for running/queued project pipelines to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
9. `push` - push immediately after queue guard passes.
|
||||
10. `PR integration` - if external git provider is available, create/update PR to `main` and merge with required strategy via Mosaic wrappers.
|
||||
11. `pre-merge queue guard` - before merging PR, wait for running/queued project pipelines on the exact PR head to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
11. `pre-merge queue guard` - before merging PR, wait for running/queued project pipelines to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge`.
|
||||
12. `CI/pipeline verification` - wait for terminal CI status and require green before completion (`~/.config/mosaic/tools/git/pr-ci-wait.sh` for PR-based workflow).
|
||||
13. `issue closure` - close linked external issue (or close internal `docs/TASKS.md` task ref when provider is unavailable).
|
||||
14. `greenfield situational test` - validate required user flows in a clean environment/startup path (post-merge for trunk workflow changes).
|
||||
@@ -93,8 +93,8 @@ For implementation work, you MUST run this cycle in order:
|
||||
> the gate (AGENTS.md hard gate "Merge authority"). Solo delivery proceeds
|
||||
> without asking.
|
||||
|
||||
1. `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`
|
||||
2. `~/.config/mosaic/tools/git/pr-merge.sh -n <PR_NUMBER> -m squash --expect-head <APPROVED_FULL_SHA>`
|
||||
1. `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`
|
||||
2. `~/.config/mosaic/tools/git/pr-merge.sh -n <PR_NUMBER> -m squash`
|
||||
3. `~/.config/mosaic/tools/git/pr-ci-wait.sh -n <PR_NUMBER>`
|
||||
4. `~/.config/mosaic/tools/git/issue-close.sh -i <ISSUE_NUMBER>` (or close internal `docs/TASKS.md` ref when no provider exists)
|
||||
5. If any step fails: set status `blocked`, report the exact failed wrapper command, and stop.
|
||||
|
||||
@@ -425,11 +425,11 @@ git push
|
||||
and checklist completed (`~/.config/mosaic/templates/docs/DOCUMENTATION-CHECKLIST.md`) when applicable.
|
||||
13. **PR + CI + Issue Closure Gate** (HARD RULE for source-code tasks):
|
||||
- Before merging, run queue guard:
|
||||
`~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`
|
||||
`~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`
|
||||
- Ensure PR exists for the task branch (create/update via wrappers if needed):
|
||||
`~/.config/mosaic/tools/git/pr-create.sh ... -B main`
|
||||
- Merge via wrapper:
|
||||
`~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
||||
`~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash`
|
||||
- Wait for terminal CI status:
|
||||
`~/.config/mosaic/tools/git/pr-ci-wait.sh -n {PR_NUMBER}`
|
||||
- Close linked issue after merge + green CI:
|
||||
@@ -630,7 +630,7 @@ Construct this from the task row and pass to worker via Task tool:
|
||||
|
||||
**MANDATORY:** This ALWAYS includes linting. If the project has a linter configured
|
||||
(ESLint, Biome, ruff, etc.), you MUST run it and fix ALL violations in files you touched.
|
||||
Do NOT leave lint warnings or errors for someone else to clean up. 6. Run REQUIRED situational tests based on changed surfaces (see `~/.config/mosaic/guides/E2E-DELIVERY.md` and `~/.config/mosaic/guides/QA-TESTING.md`). 7. If task is bug fix/security/auth/critical business logic, apply REQUIRED TDD discipline per `~/.config/mosaic/guides/QA-TESTING.md`. 8. If gates or required situational tests fail: Fix and retry. Do NOT report success with failures. 9. Commit: `git commit -m "fix({finding_id}): brief description"` 10. Before push, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B {branch}` 11. Push: `git push origin {branch}` 12. Report result as JSON (see format below)
|
||||
Do NOT leave lint warnings or errors for someone else to clean up. 6. Run REQUIRED situational tests based on changed surfaces (see `~/.config/mosaic/guides/E2E-DELIVERY.md` and `~/.config/mosaic/guides/QA-TESTING.md`). 7. If task is bug fix/security/auth/critical business logic, apply REQUIRED TDD discipline per `~/.config/mosaic/guides/QA-TESTING.md`. 8. If gates or required situational tests fail: Fix and retry. Do NOT report success with failures. 9. Commit: `git commit -m "fix({finding_id}): brief description"` 10. Before push, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main` 11. Push: `git push origin {branch}` 12. Report result as JSON (see format below)
|
||||
|
||||
## Git Scripts
|
||||
|
||||
@@ -638,9 +638,8 @@ For issue/PR/milestone operations, use scripts (NOT raw tea/gh):
|
||||
|
||||
- `~/.config/mosaic/tools/git/issue-view.sh -i {N}`
|
||||
- `~/.config/mosaic/tools/git/pr-create.sh -t "Title" -b "Desc" -B main`
|
||||
- Push: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B {task_branch}`
|
||||
- Merge: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B {pr_head_branch} -R {pr_head_owner/repo} --sha {pr_head_full_sha}`
|
||||
- `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
||||
- `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`
|
||||
- `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash`
|
||||
- `~/.config/mosaic/tools/git/pr-ci-wait.sh -n {PR_NUMBER}`
|
||||
- `~/.config/mosaic/tools/git/issue-close.sh -i {N}`
|
||||
|
||||
|
||||
@@ -11,108 +11,22 @@ All tool suites are located at `~/.config/mosaic/tools/`.
|
||||
|
||||
Mosaic wrappers at `~/.config/mosaic/tools/git/*.sh` handle platform detection and edge cases. Always use these before raw CLI commands.
|
||||
|
||||
This index is complete and is kept complete mechanically: `tools/quality/scripts/check-tools-index.sh`
|
||||
fails CI when a wrapper ships without an entry here, or when an entry here names a wrapper that no
|
||||
longer exists. A wrapper missing from this list is, from inside an agent session, indistinguishable
|
||||
from a wrapper that was never written — which is how the APPROVE/APPROVED incident below happened.
|
||||
|
||||
Every command takes `--help`. All of them accept `--login <account>` to pin the acting identity;
|
||||
supply it explicitly on any host where the provider CLI's default account is an admin.
|
||||
|
||||
| Issues | |
|
||||
| ------------------ | --------------------------------- |
|
||||
| `issue-create.sh` | Create an issue (Gitea or GitHub) |
|
||||
| `issue-view.sh` | Show one issue |
|
||||
| `issue-list.sh` | List issues |
|
||||
| `issue-edit.sh` | Edit title/body/labels/milestone |
|
||||
| `issue-comment.sh` | Add a comment |
|
||||
| `issue-assign.sh` | Assign or unassign |
|
||||
| `issue-close.sh` | Close an issue |
|
||||
| `issue-reopen.sh` | Reopen a closed issue |
|
||||
|
||||
| Pull requests | |
|
||||
| ---------------- | --------------------------------------------------------- |
|
||||
| `pr-create.sh` | Open a pull request |
|
||||
| `pr-edit.sh` | Edit PR title, body, base branch, or draft/ready state |
|
||||
| `pr-view.sh` | Show one PR |
|
||||
| `pr-list.sh` | List PRs |
|
||||
| `pr-diff.sh` | Fetch a PR's diff |
|
||||
| `pr-metadata.sh` | PR metadata as JSON (head SHA, base, state, mergeability) |
|
||||
| `pr-review.sh` | **Place a review verdict — see the dialect note below** |
|
||||
| `pr-ci-wait.sh` | Block until the PR's CI reaches a terminal state |
|
||||
| `pr-merge.sh` | Merge a PR |
|
||||
| `pr-close.sh` | Close a PR without merging |
|
||||
|
||||
| Milestones | |
|
||||
| --------------------- | ------------------ |
|
||||
| `milestone-create.sh` | Create a milestone |
|
||||
| `milestone-list.sh` | List milestones |
|
||||
| `milestone-close.sh` | Close a milestone |
|
||||
|
||||
| Gates and guards | |
|
||||
| ----------------------- | --------------------------------------------------------------------------------------------------------- |
|
||||
| `ci-queue-wait.sh` | CI queue guard — required before push/merge (see below) |
|
||||
| `push-guard.sh` | Refuse verifications that pass for the wrong reason (e.g. green against an unpushed tree) |
|
||||
| `mutate-push-guard.sh` | Regenerate the guard's mutation-coverage table from measurement, so the table cannot drift from the guard |
|
||||
| `verify-clean-clone.sh` | Prove the **committed** artifact runs, from a clean clone — not the working tree |
|
||||
|
||||
| Context | |
|
||||
| -------------------- | ---------------------------------------------------------------------------------------- |
|
||||
| `detect-platform.sh` | Resolve the provider (Gitea vs GitHub) for the current repo; every other wrapper uses it |
|
||||
| `lane-brief.sh` | Live dispatch brief for a repo "lane" (milestone/label) straight from the provider |
|
||||
|
||||
| Workspace | |
|
||||
| -------------------- | ------------------------------------------------------------------------ |
|
||||
| `mosaic-worktree.sh` | Create/list/remove git worktrees — **the only supported way**; see below |
|
||||
| `wrapper-guard.sh` | PreToolUse hook that enforces the two rules above; not called by hand |
|
||||
|
||||
**Workspace placement is derived, not chosen.** `mosaic-worktree.sh new <branch>` takes a branch
|
||||
name and nothing else. Every path comes out of `git worktree list --porcelain` — main worktree,
|
||||
repo name, parent dir, then `<parent>/<repo>-worktrees/<branch-slug>`. There is no placement flag
|
||||
because a decision an agent has to make is a decision that drifts: the rule "big work goes on a work
|
||||
filesystem" already existed in prose and 255 GB accumulated in `$HOME` across 842 directories
|
||||
anyway, under five simultaneous conventions on a single host.
|
||||
|
||||
```bash
|
||||
~/.config/mosaic/tools/git/mosaic-worktree.sh new <branch> [--from <base>]
|
||||
~/.config/mosaic/tools/git/mosaic-worktree.sh path <branch> # derived path, no side effect
|
||||
~/.config/mosaic/tools/git/mosaic-worktree.sh list # this repo's worktrees + state
|
||||
~/.config/mosaic/tools/git/mosaic-worktree.sh rm <branch> # removal is part of the task
|
||||
~/.config/mosaic/tools/git/mosaic-worktree.sh gc [--apply] # reclaim clean + fully-pushed ones
|
||||
```
|
||||
# Issues
|
||||
~/.config/mosaic/tools/git/issue-create.sh
|
||||
~/.config/mosaic/tools/git/issue-close.sh
|
||||
|
||||
Worktrees rather than clones, because `git worktree list` makes every checkout enumerable — a bare
|
||||
clone dropped somewhere on disk can never be safely reclaimed, so it is never reclaimed. `rm` and
|
||||
`gc` decide by **evidence, never by size or age**: a worktree is reclaimable only when
|
||||
`git status --porcelain` is empty _and_ `git rev-list --count HEAD --not --remotes` is 0. Anything
|
||||
else is preserved and reported. `--force` exists and is yours to type deliberately.
|
||||
# PRs
|
||||
~/.config/mosaic/tools/git/pr-create.sh
|
||||
~/.config/mosaic/tools/git/pr-merge.sh
|
||||
|
||||
`wrapper-guard.sh` is registered as a Claude Code `PreToolUse` hook on `Bash` (see
|
||||
`runtime/claude/settings.json`). It blocks exactly three things and lets everything else through:
|
||||
a `git clone`/`git worktree add` targeting `$HOME`; a raw provider-API **write** to an endpoint that
|
||||
already has a wrapper above (reads are untouched — they are how you gather evidence); and the
|
||||
literal `"event": "APPROVE"`. For a genuine gap no wrapper can express, prefix
|
||||
`MOSAIC_WRAPPER_OVERRIDE=1`. Reaching for the override twice for the same call means the wrapper has
|
||||
a missing flag — extend the wrapper.
|
||||
# Milestones
|
||||
~/.config/mosaic/tools/git/milestone-create.sh
|
||||
|
||||
```bash
|
||||
~/.config/mosaic/tools/git/issue-create.sh --help
|
||||
~/.config/mosaic/tools/git/pr-review.sh --pr 42 --event APPROVED --body "..."
|
||||
|
||||
# CI queue guard (required before push/merge; defaults to the checked-out branch)
|
||||
# CI queue guard (required before push/merge)
|
||||
~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge
|
||||
```
|
||||
|
||||
**Review dialect — the reason `pr-review.sh` is not optional.** Gitea's approve event is
|
||||
`APPROVED`; GitHub's is `APPROVE`. Send GitHub's spelling to a Gitea host and it answers **HTTP
|
||||
200**, files the review as PENDING, and then rejects the submit with `422 review stay pending` — the
|
||||
verdict looks placed and is not. (`REQUEST_CHANGES` is spelled identically on both, so only the
|
||||
approve path carries the trap.) `pr-review.sh` sends the correct token for the detected provider.
|
||||
Whatever you use, re-read `GET /pulls/{n}/reviews` and assert the state before reporting a verdict
|
||||
placed.
|
||||
|
||||
The guard exits nonzero for any provider-asserted non-green, missing, or malformed CI state. If credentials or the provider are unavailable, it emits `CANNOT_ASSERT` and writes a JSONL audit record. Push degrades to exit 0 so recovery work is not bricked; merge holds with retryable exit 75 until the provider recovers, then self-clears without manual reset. Neither outcome is evidence that CI was clear. `pr-merge.sh` automatically inspects the exact PR head repository and full commit SHA rather than its `main` base; this also handles fork PRs without branch-name ambiguity. Pass `--expect-head <approved-full-sha>` to bind a commit-specific review or merge-gate verdict; Gitea uses atomic `head_commit_id` and GitHub uses `--match-head-commit`.
|
||||
|
||||
### Code Review (Codex)
|
||||
|
||||
```bash
|
||||
|
||||
@@ -52,16 +52,6 @@
|
||||
"timeout": 10
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": "Bash",
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "~/.config/mosaic/tools/git/wrapper-guard.sh",
|
||||
"timeout": 10
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"PostToolUse": [
|
||||
|
||||
@@ -51,26 +51,12 @@ Skills are discovered from:
|
||||
|
||||
### Extensions
|
||||
|
||||
`mosaic pi` loads framework-owned extensions directly from `~/.config/mosaic/runtime/pi/` in this
|
||||
order:
|
||||
The Mosaic Pi extension (`~/.config/mosaic/runtime/pi/mosaic-extension.ts`) handles:
|
||||
|
||||
1. `mosaic-extension.ts` — session lifecycle, mission context, memory routing, lease/mutator gates,
|
||||
and fleet heartbeat reporting.
|
||||
2. `goal-extension.ts` — optional persistent `/goal` controller with per-turn and post-compaction
|
||||
checks.
|
||||
|
||||
The goal extension is deployed by Mosaic and MUST NOT be copied into `~/.pi/agent/extensions/`.
|
||||
Use `/goal set <statement>` (or `/goal <statement>`) to start, then `/goal status`, `/goal pause`,
|
||||
`/goal resume`, or `/goal cancel` to control it. An active goal is injected before every model
|
||||
request, restored from branch-specific session entries, and considered achieved only after two
|
||||
consecutive evidence-bearing reports. Common credential shapes are redacted before controller-owned
|
||||
goal-state entries are persisted or
|
||||
displayed; Pi's own model/tool-call history is separate. Goals and reports must contain references
|
||||
and pass/fail summaries rather than secrets or raw sensitive output.
|
||||
|
||||
- `MOSAIC_GOAL_MAX_TURNS` — autonomous turn limit, default `40`, accepted range `1..500`.
|
||||
- `MOSAIC_GOAL_MAX_NO_PROGRESS` — identical no-progress report limit, default `6`, accepted range
|
||||
`1..100`.
|
||||
- Session start/end lifecycle hooks
|
||||
- Active mission detection and context injection
|
||||
- Memory routing to `~/.config/mosaic/memory/`
|
||||
- MACP queue status reporting
|
||||
|
||||
### Sessions
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -66,10 +66,7 @@ if command -v tmux >/dev/null 2>&1 && command -v cc >/dev/null 2>&1; then
|
||||
trap 'tmux -L "$TEST_SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$TEST_ROOT"' EXIT
|
||||
MARKER="$TEST_ROOT/loader-marker"
|
||||
LIBRARY="$TEST_ROOT/marker.so"
|
||||
FIXTURE_READY="$TEST_ROOT/loader-ready"
|
||||
FIXTURE_FIFO="$TEST_ROOT/loader-block"
|
||||
HOLDER_HOME="$TEST_ROOT/holder-home"
|
||||
mkfifo "$FIXTURE_FIFO"
|
||||
mkdir -p "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||
chmod 700 "$HOLDER_HOME/.config" "$HOLDER_HOME/.config/mosaic" \
|
||||
"$HOLDER_HOME/.config/mosaic/fleet" "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||
@@ -90,17 +87,7 @@ __attribute__((constructor)) static void mark_loader(void) {
|
||||
EOF
|
||||
cc -shared -fPIC -o "$LIBRARY" "$TEST_ROOT/marker.c"
|
||||
MOSAIC_LOADER_MARKER="$MARKER" LD_PRELOAD="$LIBRARY" \
|
||||
tmux -L "$TEST_SOCKET" new-session -d -s _holder \
|
||||
"touch '$FIXTURE_READY'; read _ < '$FIXTURE_FIFO'"
|
||||
# tmux starts the pane asynchronously. Wait until its contaminated shell has
|
||||
# loaded the constructor and reached a builtin-only FIFO barrier before
|
||||
# clearing the marker; otherwise that expected constructor can race with the
|
||||
# clean holder assertion below and create a false failure.
|
||||
for _attempt in {1..100}; do
|
||||
[ -e "$FIXTURE_READY" ] && break
|
||||
sleep 0.01
|
||||
done
|
||||
[ -e "$FIXTURE_READY" ] || fail "contaminated fixture pane did not become ready"
|
||||
tmux -L "$TEST_SOCKET" new-session -d -s _holder 'sleep 60'
|
||||
[ -s "$MARKER" ] || fail "contaminated fixture did not execute loader constructor"
|
||||
server_pid=$(tmux -L "$TEST_SOCKET" display-message -p '#{pid}')
|
||||
: > "$MARKER"
|
||||
@@ -125,7 +112,6 @@ EOF
|
||||
chmod 700 "$AGENT_HOME/fleet/agents"
|
||||
cat > "$AGENT_HOME/fleet/agents/$AGENT_NAME.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$AGENT_NAME
|
||||
MOSAIC_GIT_IDENTITY=$AGENT_NAME
|
||||
MOSAIC_AGENT_CLASS=code
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=
|
||||
@@ -158,8 +144,7 @@ EOF
|
||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin \
|
||||
MOSAIC_TMUX_SOCKET="$TEST_SOCKET" MOSAIC_TMUX_HOLDER=_holder "$HOLDER_START"
|
||||
tmux -L "$TEST_SOCKET" has-session -t '=_holder:0.0' || fail "fresh holder was not created"
|
||||
ld_preload_env="$(tmux -L "$TEST_SOCKET" show-environment -g LD_PRELOAD 2>/dev/null)" || true
|
||||
if grep -q '^LD_PRELOAD=' <<<"$ld_preload_env"; then
|
||||
if tmux -L "$TEST_SOCKET" show-environment -g LD_PRELOAD 2>/dev/null | grep -q '^LD_PRELOAD='; then
|
||||
fail "fresh holder retained LD_PRELOAD"
|
||||
fi
|
||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -88,7 +88,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
|
||||
@@ -147,9 +147,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -97,7 +97,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
@@ -198,9 +198,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -101,7 +101,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
@@ -230,9 +230,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
+2
-2
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -87,7 +87,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
|
||||
+2
-2
@@ -146,9 +146,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
+2
-2
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -84,7 +84,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
|
||||
+2
-2
@@ -136,9 +136,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
2. Do NOT ask for routine confirmation before required push/merge/issue-close/release/tag actions.
|
||||
3. Completion is forbidden at PR-open stage.
|
||||
4. Completion requires merged PR to `main` + terminal green CI + linked issue/internal task closed.
|
||||
5. Before push or merge, run the queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
5. Before push or merge, run queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
6. For issue/PR/milestone operations, use Mosaic wrappers first (`~/.config/mosaic/tools/git/*.sh`).
|
||||
7. If any required wrapper command fails: report `blocked` with the exact failed wrapper command and stop.
|
||||
8. Do NOT stop at "PR created" and do NOT ask "should I merge?" for routine flow.
|
||||
@@ -85,7 +85,7 @@ Reference:
|
||||
5. Do not mark implementation complete until PR is merged.
|
||||
6. Do not mark implementation complete until CI/pipeline status is terminal green.
|
||||
7. Close linked issues/tasks only after merge + green CI.
|
||||
8. Before push or merge, run the CI queue guard against the push branch or the merge PR's exact head repository/SHA (`ci-queue-wait.sh --help`); `pr-merge.sh` supplies exact merge metadata automatically.
|
||||
8. Before push or merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push|merge -B main`.
|
||||
|
||||
## Container Release Strategy (When Applicable)
|
||||
|
||||
|
||||
@@ -133,9 +133,9 @@ Do NOT stop at "PR created" and do NOT ask "should I merge?" or "should I close
|
||||
5. Ensure `docs/PRD.md` or `docs/PRD.json` exists and is current before coding.
|
||||
6. Create scratchpad: `docs/scratchpads/{task-id}-{short-name}.md` and include issue/internal ref.
|
||||
7. Update `docs/TASKS.md` status + issue/internal ref before coding.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||
8. Before push, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B main`.
|
||||
9. Open PR to `main` for delivery changes (no direct push to `main`).
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||
10. Before merge, run CI queue guard: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B main`.
|
||||
11. Merge PRs that pass required checks and review gates with squash strategy only.
|
||||
12. Reference issues/internal refs in commits (`Fixes #123`, `Refs #123`, or `Refs TASKS:T1`).
|
||||
13. Close issue/internal task only after testing and documentation gates pass, PR merge is complete, and CI/pipeline status is terminal green.
|
||||
|
||||
@@ -69,7 +69,7 @@ _manifest_glob_to_ere() {
|
||||
out="$out.*"
|
||||
fi
|
||||
else
|
||||
out="${out}[^/]*"
|
||||
out="$out[^/]*"
|
||||
fi
|
||||
else
|
||||
case "$c" in
|
||||
@@ -87,8 +87,7 @@ _manifest_compile_one() {
|
||||
local norm; norm="$(_manifest_norm "$1")"
|
||||
[[ -n "$norm" ]] || return 0
|
||||
if [[ "$norm" == *"*"* ]]; then
|
||||
local re
|
||||
re="^$(_manifest_glob_to_ere "$norm")\$"
|
||||
local re="^$(_manifest_glob_to_ere "$norm")\$"
|
||||
if [[ "$2" == F ]]; then
|
||||
_MF_KIND+=(re); _MF_EXACT+=(""); _MF_RE+=("$re")
|
||||
else
|
||||
@@ -184,10 +183,7 @@ _mo_matches() {
|
||||
for (( i = 0; i < n; i++ )); do
|
||||
if [[ "${_MO_KIND[i]}" == exact ]]; then
|
||||
pat="${_MO_EXACT[i]}"
|
||||
# Operator exact entries are file carve-outs, not implicit directory
|
||||
# prefixes. Subtree ownership must be declared explicitly as `dir/**`;
|
||||
# otherwise one bare directory entry can hide all drift beneath it.
|
||||
[[ "$path" == "$pat" ]] && return 0
|
||||
[[ "$path" == "$pat" || "$path" == "$pat/"* ]] && return 0
|
||||
else
|
||||
re="${_MO_RE[i]}"
|
||||
[[ "$path" =~ $re ]] && return 0
|
||||
|
||||
@@ -153,38 +153,6 @@ warn_if_symlink_tree_present() {
|
||||
|
||||
echo "[mosaic-doctor] Mosaic home: $MOSAIC_HOME"
|
||||
|
||||
# Compare the framework tools that this CLI/package ships with the deployed
|
||||
# ~/.config copy that direct wrappers and systemd units actually execute. Doctor
|
||||
# is the right boundary: observational, operator-invoked, and already designed
|
||||
# to report drift without mutating live tooling or restarting active seats.
|
||||
framework_drift_checker="$(cd -- "$(dirname -- "$0")/../quality/scripts" && pwd)/framework-drift-check.py"
|
||||
if [[ -f "$framework_drift_checker" ]]; then
|
||||
echo "[mosaic-doctor] Checking installed framework-tool drift..."
|
||||
drift_timeout="${MOSAIC_DOCTOR_DRIFT_TIMEOUT_SEC:-15}"
|
||||
if ! [[ "$drift_timeout" =~ ^[1-9][0-9]*$ ]]; then
|
||||
warn "Invalid MOSAIC_DOCTOR_DRIFT_TIMEOUT_SEC='$drift_timeout' (expected positive integer); using 15s"
|
||||
drift_timeout=15
|
||||
fi
|
||||
if command -v timeout >/dev/null 2>&1; then
|
||||
set +e
|
||||
timeout -s TERM -k 2 "${drift_timeout}s" \
|
||||
python3 "$framework_drift_checker" --installed-root "$MOSAIC_HOME/tools"
|
||||
drift_rc=$?
|
||||
set -e
|
||||
if [[ "$drift_rc" -eq 0 ]]; then
|
||||
pass "Installed framework tools match shipped source"
|
||||
elif [[ "$drift_rc" -eq 124 || "$drift_rc" -eq 137 || "$drift_rc" -eq 143 ]]; then
|
||||
warn "CANNOT_ASSERT framework drift checker timed out after ${drift_timeout}s; continuing remaining doctor checks"
|
||||
else
|
||||
warn "Installed framework-tool drift detected (checker exit $drift_rc; no files changed)"
|
||||
fi
|
||||
else
|
||||
warn "CANNOT_ASSERT timeout utility unavailable; refusing unbounded framework drift check and continuing remaining doctor checks"
|
||||
fi
|
||||
else
|
||||
warn "Framework drift checker is absent from the shipped tools tree"
|
||||
fi
|
||||
|
||||
# Canonical Mosaic checks
|
||||
expect_file "$MOSAIC_HOME/STANDARDS.md"
|
||||
expect_file "$MOSAIC_HOME/USER.md"
|
||||
|
||||
@@ -69,7 +69,7 @@ if [[ -n "$GROUP" ]]; then
|
||||
group_response=$(curl -sk \
|
||||
-H "Authorization: Bearer $TOKEN" \
|
||||
"${AUTHENTIK_URL}/api/v3/core/groups/?search=${GROUP}")
|
||||
group_pk=$(jq -r "first(.results[] | select(.name == \"$GROUP\") | .pk) // empty" <<<"$group_response")
|
||||
group_pk=$(echo "$group_response" | jq -r ".results[] | select(.name == \"$GROUP\") | .pk" | head -1)
|
||||
if [[ -n "$group_pk" ]]; then
|
||||
payload=$(echo "$payload" | jq --arg gk "$group_pk" '. + {groups: [$gk]}')
|
||||
else
|
||||
|
||||
@@ -97,7 +97,7 @@ is_sensitive_key() {
|
||||
|
||||
is_generated_key() {
|
||||
case "$1" in
|
||||
MOSAIC_AGENT_NAME|MOSAIC_GIT_IDENTITY|MOSAIC_AGENT_CLASS|MOSAIC_AGENT_RUNTIME|MOSAIC_AGENT_MODEL|MOSAIC_AGENT_REASONING|MOSAIC_AGENT_TOOL_POLICY|MOSAIC_AGENT_WORKDIR|MOSAIC_TMUX_SOCKET) return 0 ;;
|
||||
MOSAIC_AGENT_NAME|MOSAIC_AGENT_CLASS|MOSAIC_AGENT_RUNTIME|MOSAIC_AGENT_MODEL|MOSAIC_AGENT_REASONING|MOSAIC_AGENT_TOOL_POLICY|MOSAIC_AGENT_WORKDIR|MOSAIC_TMUX_SOCKET) return 0 ;;
|
||||
*) return 1 ;;
|
||||
esac
|
||||
}
|
||||
@@ -114,7 +114,6 @@ validate_generated_value() {
|
||||
local value="$2"
|
||||
case "$key" in
|
||||
MOSAIC_AGENT_NAME) safe_agent_name "$value" || fail_env unsafe-agent-name "$key" "$value" ;;
|
||||
MOSAIC_GIT_IDENTITY) safe_agent_name "$value" || fail_env unsafe-git-identity "$key" "$value" ;;
|
||||
MOSAIC_AGENT_CLASS) safe_policy_name "$value" || fail_env unsafe-class "$key" "$value" ;;
|
||||
MOSAIC_AGENT_RUNTIME)
|
||||
case "$value" in claude|codex|opencode|pi) ;; *) fail_env unsupported-runtime "$key" "$value" ;; esac
|
||||
@@ -176,7 +175,7 @@ load_environment_file() {
|
||||
|
||||
load_environment_file "$GENERATED_ENV" generated
|
||||
for required_key in \
|
||||
MOSAIC_AGENT_NAME MOSAIC_GIT_IDENTITY MOSAIC_AGENT_CLASS MOSAIC_AGENT_RUNTIME MOSAIC_AGENT_MODEL \
|
||||
MOSAIC_AGENT_NAME MOSAIC_AGENT_CLASS MOSAIC_AGENT_RUNTIME MOSAIC_AGENT_MODEL \
|
||||
MOSAIC_AGENT_REASONING MOSAIC_AGENT_TOOL_POLICY MOSAIC_AGENT_WORKDIR MOSAIC_TMUX_SOCKET; do
|
||||
[ -n "${GENERATED_VALUES[$required_key]+set}" ] || fail_env missing-key "$required_key" ''
|
||||
done
|
||||
@@ -184,15 +183,12 @@ load_environment_file "$LOCAL_ENV" local
|
||||
|
||||
[ "${GENERATED_VALUES[MOSAIC_AGENT_NAME]}" = "$AGENT_NAME" ] || \
|
||||
fail_env agent-name-mismatch MOSAIC_AGENT_NAME "${GENERATED_VALUES[MOSAIC_AGENT_NAME]}"
|
||||
[ "${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}" = "$AGENT_NAME" ] || \
|
||||
fail_env git-identity-mismatch MOSAIC_GIT_IDENTITY "${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}"
|
||||
|
||||
MOSAIC_TMUX_SOCKET=${GENERATED_VALUES[MOSAIC_TMUX_SOCKET]}
|
||||
MOSAIC_AGENT_RUNTIME=${GENERATED_VALUES[MOSAIC_AGENT_RUNTIME]}
|
||||
MOSAIC_AGENT_MODEL=${GENERATED_VALUES[MOSAIC_AGENT_MODEL]}
|
||||
MOSAIC_AGENT_REASONING=${GENERATED_VALUES[MOSAIC_AGENT_REASONING]}
|
||||
MOSAIC_AGENT_WORKDIR=${GENERATED_VALUES[MOSAIC_AGENT_WORKDIR]}
|
||||
MOSAIC_GIT_IDENTITY=${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}
|
||||
MOSAIC_AGENT_CLASS=${GENERATED_VALUES[MOSAIC_AGENT_CLASS]}
|
||||
MOSAIC_AGENT_TOOL_POLICY=${GENERATED_VALUES[MOSAIC_AGENT_TOOL_POLICY]}
|
||||
MOSAIC_RUNTIME_BIN=${LOCAL_VALUES[MOSAIC_RUNTIME_BIN]:-}
|
||||
@@ -347,7 +343,6 @@ LAUNCH_ENV=(
|
||||
"PATH=$PANE_PATH"
|
||||
"MOSAIC_HOME=$MOSAIC_HOME"
|
||||
"MOSAIC_AGENT_NAME=$AGENT_NAME"
|
||||
"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"
|
||||
"MOSAIC_AGENT_CLASS=$MOSAIC_AGENT_CLASS"
|
||||
"MOSAIC_AGENT_RUNTIME=$MOSAIC_AGENT_RUNTIME"
|
||||
"MOSAIC_AGENT_MODEL=$MOSAIC_AGENT_MODEL"
|
||||
|
||||
@@ -14,82 +14,6 @@ fail() {
|
||||
exit 1
|
||||
}
|
||||
|
||||
pane_command_clears_environment() {
|
||||
local calls_file="$1"
|
||||
local -a argv=()
|
||||
local index
|
||||
mapfile -d '' -t argv < "$calls_file"
|
||||
for ((index = 0; index + 1 < ${#argv[@]}; index++)); do
|
||||
if [ "${argv[$index]}" = /usr/bin/env ] && [ "${argv[$((index + 1))]}" = -i ]; then
|
||||
return 0
|
||||
fi
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
print_pane_argv() {
|
||||
local calls_file="$1"
|
||||
local -a argv=()
|
||||
local bytes index
|
||||
mapfile -d '' -t argv < "$calls_file"
|
||||
bytes=$(wc -c < "$calls_file")
|
||||
printf 'observed pane argv: records=%s bytes=%s\n' "${#argv[@]}" "$bytes" >&2
|
||||
for ((index = 0; index < ${#argv[@]}; index++)); do
|
||||
printf ' [%03d] %q\n' "$index" "${argv[$index]}" >&2
|
||||
done
|
||||
}
|
||||
|
||||
check_pane_environment_boundary() {
|
||||
local calls_file="$1"
|
||||
if pane_command_clears_environment "$calls_file"; then
|
||||
return 0
|
||||
fi
|
||||
print_pane_argv "$calls_file"
|
||||
return 1
|
||||
}
|
||||
|
||||
contains_literal() {
|
||||
grep -F -- "$2" <<< "$1" >/dev/null
|
||||
}
|
||||
|
||||
contains_line() {
|
||||
grep -xF -- "$2" <<< "$1" >/dev/null
|
||||
}
|
||||
|
||||
# Portability regression: inspect the authoritative NUL-delimited argv instead
|
||||
# of piping a newline reconstruction through `grep -q` under pipefail. The old
|
||||
# pipeline could report failure after a successful match when an upstream
|
||||
# producer received SIGPIPE. A large trailing argument keeps that failure class
|
||||
# covered without making stream size part of the semantic contract.
|
||||
PORTABILITY_CALLS="$ROOT/portability-calls"
|
||||
printf -v PORTABILITY_PADDING '%*s' 32768 ''
|
||||
PORTABILITY_PADDING=${PORTABILITY_PADDING// /x}
|
||||
printf '%s\0' /usr/bin/env -i "$PORTABILITY_PADDING" > "$PORTABILITY_CALLS"
|
||||
pane_command_clears_environment "$PORTABILITY_CALLS" || \
|
||||
fail "valid large pane argv was rejected by the environment-boundary assertion"
|
||||
|
||||
assert_pane_boundary_rejected() {
|
||||
local case_name="$1"
|
||||
local expected_records="$2"
|
||||
local diagnostic
|
||||
if diagnostic=$(check_pane_environment_boundary "$PORTABILITY_CALLS" 2>&1); then
|
||||
fail "pane boundary accepted invalid $case_name fixture"
|
||||
fi
|
||||
contains_literal "$diagnostic" "records=$expected_records bytes=" || \
|
||||
fail "pane argv diagnostic omitted counts for $case_name fixture"
|
||||
contains_literal "$diagnostic" '[000]' || \
|
||||
fail "pane argv diagnostic omitted indexed arguments for $case_name fixture"
|
||||
}
|
||||
|
||||
printf '%s\0' tmux -i > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected missing-env 2
|
||||
printf '%s\0' /usr/bin/env HOME=/untrusted > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected missing-i 2
|
||||
printf '%s\0' /usr/bin/env HOME=/untrusted -i > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected non-adjacent-i 3
|
||||
printf '%s\0' -i /usr/bin/env > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected reversed-boundary 2
|
||||
|
||||
cat > "$FAKE_BIN/tmux" <<'SHIM'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
@@ -138,19 +62,6 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/mosaic"
|
||||
|
||||
# Freeze numeric epoch reads only when a test arm supplies an observation bound.
|
||||
# Formatting reads still use the real BusyBox/POSIX date implementation.
|
||||
cat > "$FAKE_BIN/date" <<'SHIM'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
if [ -n "${MOSAIC_TEST_FIXED_EPOCH:-}" ] && [ "${1:-}" = '+%s' ]; then
|
||||
printf '%s\n' "$MOSAIC_TEST_FIXED_EPOCH"
|
||||
exit 0
|
||||
fi
|
||||
exec /bin/date "$@"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/date"
|
||||
|
||||
write_generated() {
|
||||
local home="$1"
|
||||
local agent="$2"
|
||||
@@ -160,7 +71,6 @@ write_generated() {
|
||||
chmod 600 "$home/fleet/run/holder-owner"
|
||||
cat > "$home/fleet/agents/$agent.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$agent
|
||||
MOSAIC_GIT_IDENTITY=$agent
|
||||
MOSAIC_AGENT_CLASS=code
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=openai-codex/gpt-5.6-sol
|
||||
@@ -178,7 +88,6 @@ run_start() {
|
||||
local agent="$2"
|
||||
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
||||
MOSAIC_TEST_FIXED_EPOCH="${MOSAIC_TEST_FIXED_EPOCH:-}" \
|
||||
MOSAIC_TEST_HOME="$home" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_HOME="$home" "$START" "$agent"
|
||||
@@ -191,55 +100,19 @@ AGENT_VALID="coder0"
|
||||
write_generated "$HOME_VALID" "$AGENT_VALID"
|
||||
run_start "$HOME_VALID" "$AGENT_VALID"
|
||||
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_literal "$valid_args" new-session || fail "valid generated projection did not reach tmux"
|
||||
contains_literal "$valid_args" mosaic || fail "fixed mosaic launcher command missing"
|
||||
contains_literal "$valid_args" yolo || fail "fixed yolo launcher command missing"
|
||||
contains_literal "$valid_args" pi || fail "roster runtime missing"
|
||||
if contains_literal "$valid_args" 'bash -c'; then
|
||||
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
||||
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
||||
echo "$valid_args" | grep -qF 'yolo' || fail "fixed yolo launcher command missing"
|
||||
echo "$valid_args" | grep -qF 'pi' || fail "roster runtime missing"
|
||||
if echo "$valid_args" | grep -qF 'bash -c'; then
|
||||
fail "launcher constructed a shell command payload"
|
||||
fi
|
||||
|
||||
# The pane must start through an absolute clean-environment boundary. Its
|
||||
# runtime command remains an argv vector, but no holder/session environment
|
||||
# control variable can pass through the pane command.
|
||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
||||
|
||||
# Git identity is generated authority, not an optional or independently mutable
|
||||
# local value. Each invalid form must fail before fake tmux receives a call.
|
||||
assert_git_identity_rejected() {
|
||||
local case_name="$1"
|
||||
local expected_code="$2"
|
||||
local home="$ROOT/git-identity-$case_name"
|
||||
local agent="coder-git-identity-$case_name"
|
||||
local generated="$home/fleet/agents/$agent.env.generated"
|
||||
write_generated "$home" "$agent"
|
||||
|
||||
case "$case_name" in
|
||||
missing) grep -v '^MOSAIC_GIT_IDENTITY=' "$generated" > "$generated.next" && mv "$generated.next" "$generated" ;;
|
||||
unsafe) sed -i 's|^MOSAIC_GIT_IDENTITY=.*$|MOSAIC_GIT_IDENTITY=bad/identity|' "$generated" ;;
|
||||
mismatch) sed -i 's|^MOSAIC_GIT_IDENTITY=.*$|MOSAIC_GIT_IDENTITY=other-agent|' "$generated" ;;
|
||||
local-shadow)
|
||||
printf 'MOSAIC_GIT_IDENTITY=%s\n' "$agent" > "$home/fleet/agents/$agent.env.local"
|
||||
chmod 600 "$home/fleet/agents/$agent.env.local"
|
||||
;;
|
||||
*) fail "unknown Git identity rejection case: $case_name" ;;
|
||||
esac
|
||||
chmod 600 "$generated"
|
||||
|
||||
: > "$TMUX_CALLS"
|
||||
if output=$(run_start "$home" "$agent" 2>&1); then
|
||||
fail "Git identity case $case_name was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before Git identity $case_name rejection"
|
||||
contains_literal "$output" "code=$expected_code" || \
|
||||
fail "Git identity $case_name diagnostic omitted code $expected_code"
|
||||
}
|
||||
|
||||
assert_git_identity_rejected missing missing-key
|
||||
assert_git_identity_rejected unsafe unsafe-git-identity
|
||||
assert_git_identity_rejected mismatch git-identity-mismatch
|
||||
assert_git_identity_rejected local-shadow generated-key-shadow
|
||||
echo "$valid_args" | grep -qxF '/usr/bin/env' || fail "pane does not use absolute env"
|
||||
echo "$valid_args" | grep -qxF -- '-i' || fail "pane environment is not cleared"
|
||||
|
||||
# The generated-file parent is a security boundary too: even a private regular
|
||||
# file is untrusted if its parent can be replaced or written by another user.
|
||||
@@ -252,7 +125,7 @@ if output=$(run_start "$HOME_UNSAFE_PARENT" coder-parent 2>&1); then
|
||||
fail "generated file under a world-writable parent was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before unsafe parent rejection"
|
||||
contains_literal "$output" 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
|
||||
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_SYMLINK_PARENT="$ROOT/symlink-parent"
|
||||
@@ -263,7 +136,7 @@ if output=$(run_start "$HOME_SYMLINK_PARENT" coder-symlink-parent 2>&1); then
|
||||
fail "generated file under a symlinked parent was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before symlinked parent rejection"
|
||||
contains_literal "$output" 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
||||
|
||||
# Every managed ancestor is a boundary: MOSAIC_HOME, fleet, and agents. A
|
||||
# symlink or group/world-writable ancestor must fail before environment parsing,
|
||||
@@ -301,8 +174,8 @@ assert_managed_ancestor_rejected() {
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before $hazard $ancestor rejection"
|
||||
[ ! -e "$home/work" ] || fail "workdir was created before $hazard $ancestor rejection"
|
||||
contains_literal "$output" 'code=unsafe-' || fail "managed ancestor diagnostic missing"
|
||||
if contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND'; then
|
||||
echo "$output" | grep -qF "code=unsafe-" || fail "managed ancestor diagnostic missing"
|
||||
if echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND'; then
|
||||
fail "environment parsing ran before $hazard $ancestor rejection"
|
||||
fi
|
||||
}
|
||||
@@ -323,9 +196,9 @@ if output=$(run_start "$HOME_SHADOW" coder1 2>&1); then
|
||||
fail "generated-key shadow was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before generated-key shadow rejection"
|
||||
contains_literal "$output" 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
||||
contains_literal "$output" 'sha256=' || fail "shadow diagnostic omitted hash"
|
||||
if contains_literal "$output" codex; then
|
||||
echo "$output" | grep -qF 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
||||
echo "$output" | grep -qF 'sha256=' || fail "shadow diagnostic omitted hash"
|
||||
if echo "$output" | grep -qF 'codex'; then
|
||||
fail "shadow diagnostic leaked value"
|
||||
fi
|
||||
|
||||
@@ -341,9 +214,9 @@ if output=$(run_start "$HOME_COMMAND" coder2 2>&1); then
|
||||
fail "arbitrary command override was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before command rejection"
|
||||
contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
||||
contains_literal "$output" 'sha256=' || fail "command diagnostic omitted hash"
|
||||
if contains_literal "$output" "$COMMAND_VALUE"; then
|
||||
echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
||||
echo "$output" | grep -qF 'sha256=' || fail "command diagnostic omitted hash"
|
||||
if echo "$output" | grep -qF "$COMMAND_VALUE"; then
|
||||
fail "command diagnostic leaked command value"
|
||||
fi
|
||||
|
||||
@@ -357,7 +230,7 @@ if output=$(run_start "$HOME_PERMS" coder3 2>&1); then
|
||||
fail "world-readable local input was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before permissions rejection"
|
||||
contains_literal "$output" 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
||||
|
||||
# A unit/holder-like clean bootstrap must yield a pane with trusted HOME and
|
||||
# computed PATH only. The pane command itself must not carry loader, shell
|
||||
@@ -387,35 +260,25 @@ PATH="$PANE_STALE_PATH" \
|
||||
MOSAIC_TEST_EXECUTE_PANE=1 \
|
||||
"$START" coder-pane-boundary
|
||||
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_line "$pane_args" "HOME=$PANE_TRUSTED_HOME" || \
|
||||
echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||
fail "pane did not restore trusted HOME"
|
||||
contains_literal "$pane_args" "HOME=$PANE_STALE_HOME" && \
|
||||
echo "$pane_args" | grep -qF "HOME=$PANE_STALE_HOME" && \
|
||||
fail "pane inherited stale HOME"
|
||||
contains_literal "$pane_args" "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
|
||||
echo "$pane_args" | grep -qF "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
|
||||
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
||||
contains_literal "$pane_args" "$blocked" && fail "pane inherited $blocked"
|
||||
echo "$pane_args" | grep -qF "$blocked" && fail "pane inherited $blocked"
|
||||
done
|
||||
|
||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
||||
after_pane_env=$(printf '%s\n' "$pane_args" | grep -n -m1 -F '/usr/bin/env' | cut -d: -f1)
|
||||
[ -n "$after_pane_env" ] || fail "pane command did not use absolute env"
|
||||
printf '%s\n' "$pane_args" | tail -n +"$after_pane_env" | grep -qxF -- '-i' || \
|
||||
fail "pane command did not clear its environment"
|
||||
pane_environment=$(tr '\0' '\n' < "$HOME_PANE_BOUNDARY/fleet/pane-environment")
|
||||
# Exercise the repository launcher at $START, not the independently installed
|
||||
# host copy. Set-compare every declared generated projection entry with the
|
||||
# launched process environment so a newly declared identity cannot be omitted
|
||||
# by a hand-maintained per-variable assertion.
|
||||
declared_generated_environment=$(sort "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.generated")
|
||||
missing_or_changed_generated_environment=$(comm -23 \
|
||||
<(printf '%s\n' "$declared_generated_environment") \
|
||||
<(printf '%s\n' "$pane_environment" | sort))
|
||||
if [ -n "$missing_or_changed_generated_environment" ]; then
|
||||
missing_or_changed_keys=$(printf '%s\n' "$missing_or_changed_generated_environment" | cut -d= -f1 | paste -sd, -)
|
||||
fail "runtime pane omitted or changed generated environment keys: $missing_or_changed_keys"
|
||||
fi
|
||||
contains_line "$pane_environment" "HOME=$PANE_TRUSTED_HOME" || \
|
||||
echo "$pane_environment" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||
fail "runtime pane did not receive trusted HOME"
|
||||
contains_literal "$pane_environment" "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
||||
echo "$pane_environment" | grep -qF "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
||||
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
||||
contains_literal "$pane_environment" "$blocked" && fail "runtime pane received $blocked"
|
||||
echo "$pane_environment" | grep -qF "$blocked" && fail "runtime pane received $blocked"
|
||||
done
|
||||
|
||||
write_interaction_generated() {
|
||||
@@ -427,7 +290,6 @@ write_interaction_generated() {
|
||||
chmod 600 "$home/fleet/run/holder-owner"
|
||||
cat > "$home/fleet/agents/$agent.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$agent
|
||||
MOSAIC_GIT_IDENTITY=$agent
|
||||
MOSAIC_AGENT_CLASS=operator-interaction
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=openai/gpt-5.6-sol
|
||||
@@ -490,12 +352,8 @@ write_generated "$HOME_NATIVE_STALE" "coder-native-stale"
|
||||
write_heartbeat_local "$HOME_NATIVE_STALE" "coder-native-stale"
|
||||
STALE_HB="$HOME_NATIVE_STALE/run/coder-native-stale.hb"
|
||||
printf 'ts=native\npid=1\nstatus=busy\nmodel=stale-model\n' > "$STALE_HB"
|
||||
touch -t 200001010000.00 "$STALE_HB.native"
|
||||
# Hold the sidecar's observation epoch constant: assertion runtime must not age
|
||||
# a fresh-marker mutant into the stale state that this fixture must distinguish.
|
||||
STALE_OBSERVATION_EPOCH=$(date +%s)
|
||||
MOSAIC_TEST_FIXED_EPOCH="$STALE_OBSERVATION_EPOCH" \
|
||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
||||
touch -d '10 seconds ago' "$STALE_HB.native"
|
||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
||||
wait_for_sidecar_status "$STALE_HB"
|
||||
|
||||
HOME_NATIVE_ABSENT="$ROOT/native-absent"
|
||||
@@ -516,22 +374,22 @@ if output=$(run_interaction "$HOME_INTERACTION_MALFORMED" interaction-malformed
|
||||
fail "interaction wrapper accepted malformed generated data"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before interaction strict-parser rejection"
|
||||
contains_literal "$output" 'code=unknown-key' || fail "interaction did not use shared strict parser first"
|
||||
echo "$output" | grep -qF 'code=unknown-key' || fail "interaction did not use shared strict parser first"
|
||||
|
||||
# A syntactically valid but policy-incompatible projection reaches the pinned
|
||||
# interaction policy check only after strict parsing and never starts tmux.
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_INTERACTION_POLICY="$ROOT/interaction-policy"
|
||||
write_interaction_generated "$HOME_INTERACTION_POLICY" "interaction-policy"
|
||||
sed -i 's|^MOSAIC_AGENT_RUNTIME=pi$|MOSAIC_AGENT_RUNTIME=codex|' \
|
||||
perl -0pi -e 's/MOSAIC_AGENT_RUNTIME=pi/MOSAIC_AGENT_RUNTIME=codex/' \
|
||||
"$HOME_INTERACTION_POLICY/fleet/agents/interaction-policy.env.generated"
|
||||
if output=$(run_interaction "$HOME_INTERACTION_POLICY" interaction-policy 2>&1); then
|
||||
fail "interaction wrapper accepted a policy-incompatible projection"
|
||||
fi
|
||||
interaction_policy_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_literal "$interaction_policy_args" new-session && \
|
||||
echo "$interaction_policy_args" | grep -qF 'new-session' && \
|
||||
fail "interaction pinned-policy rejection created a tmux session"
|
||||
contains_literal "$output" 'operator interaction service requires runtime pi' || \
|
||||
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
||||
fail "interaction pinned-policy check did not follow strict parsing"
|
||||
|
||||
# Exact stop derives the socket exclusively from the validated generated
|
||||
@@ -544,10 +402,10 @@ HOME="$HOME_STOP" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_HOME="$HOME_STOP" MOSAIC_TMUX_SOCKET=ambient-socket "$START" --stop coder-stop
|
||||
stop_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_line "$stop_args" mosaic-test || fail "exact stop did not use the validated generated socket"
|
||||
contains_line "$stop_args" kill-session || fail "exact stop did not request session termination"
|
||||
contains_line "$stop_args" '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
||||
if contains_literal "$stop_args" ambient-socket; then
|
||||
echo "$stop_args" | grep -qxF 'mosaic-test' || fail "exact stop did not use the validated generated socket"
|
||||
echo "$stop_args" | grep -qxF 'kill-session' || fail "exact stop did not request session termination"
|
||||
echo "$stop_args" | grep -qxF '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
||||
if echo "$stop_args" | grep -qF 'ambient-socket'; then
|
||||
fail "exact stop trusted an ambient socket"
|
||||
fi
|
||||
|
||||
|
||||
@@ -7,9 +7,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
source "$SCRIPT_DIR/detect-platform.sh"
|
||||
|
||||
BRANCH=""
|
||||
TARGET_REPO=""
|
||||
HEAD_SHA=""
|
||||
BRANCH="main"
|
||||
TIMEOUT_SEC=900
|
||||
INTERVAL_SEC=15
|
||||
PURPOSE="merge"
|
||||
@@ -17,12 +15,10 @@ REQUIRE_STATUS=0
|
||||
|
||||
usage() {
|
||||
cat <<EOF
|
||||
Usage: $(basename "$0") [-B branch] [-R owner/repo] [--sha full-40] [-t timeout_sec] [-i interval_sec] [--purpose push|merge] [--require-status]
|
||||
Usage: $(basename "$0") [-B branch] [-t timeout_sec] [-i interval_sec] [--purpose push|merge] [--require-status]
|
||||
|
||||
Options:
|
||||
-B, --branch BRANCH Branch head to inspect (default: current branch)
|
||||
-R, --repo OWNER/REPO Repository containing the branch (default: origin repo)
|
||||
--sha FULL_SHA Inspect this exact 40-character commit instead of resolving the branch
|
||||
-B, --branch BRANCH Branch head to inspect (default: main)
|
||||
-t, --timeout SECONDS Max wait time in seconds (default: 900)
|
||||
-i, --interval SECONDS Poll interval in seconds (default: 15)
|
||||
--purpose VALUE Log context: push|merge (default: merge)
|
||||
@@ -31,65 +27,63 @@ Options:
|
||||
|
||||
Examples:
|
||||
$(basename "$0")
|
||||
$(basename "$0") --purpose push -t 600 -i 10
|
||||
$(basename "$0") --purpose push -B main -t 600 -i 10
|
||||
EOF
|
||||
}
|
||||
|
||||
# get_remote_host and get_gitea_token are provided by detect-platform.sh
|
||||
|
||||
get_state_from_status_json() {
|
||||
# Python source comes from -c so the provider payload remains on stdin.
|
||||
# Never move the payload to argv: commit-status responses can exceed ARG_MAX.
|
||||
python3 -c '
|
||||
python3 - <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
try:
|
||||
payload = json.load(sys.stdin)
|
||||
if not isinstance(payload, dict):
|
||||
raise ValueError("status payload is not an object")
|
||||
except Exception:
|
||||
print("malformed")
|
||||
print("unknown")
|
||||
raise SystemExit(0)
|
||||
|
||||
raw_statuses = payload.get("statuses", [])
|
||||
raw_state = payload.get("state", "")
|
||||
if not isinstance(raw_statuses, list) or not isinstance(raw_state, str):
|
||||
print("malformed")
|
||||
raise SystemExit(0)
|
||||
statuses = raw_statuses
|
||||
state = raw_state.lower()
|
||||
statuses = payload.get("statuses") or []
|
||||
state = (payload.get("state") or "").lower()
|
||||
|
||||
pending_values = {"pending", "queued", "running", "waiting"}
|
||||
failure_values = {"failure", "error", "failed"}
|
||||
success_values = {"success"}
|
||||
|
||||
if state in pending_values:
|
||||
print("pending")
|
||||
raise SystemExit(0)
|
||||
if state in failure_values:
|
||||
print("terminal-failure")
|
||||
raise SystemExit(0)
|
||||
if state in success_values:
|
||||
print("terminal-success")
|
||||
raise SystemExit(0)
|
||||
|
||||
values = []
|
||||
for item in statuses:
|
||||
if not isinstance(item, dict):
|
||||
print("malformed")
|
||||
raise SystemExit(0)
|
||||
raw_value = item.get("status") or item.get("state")
|
||||
if not isinstance(raw_value, str) or not raw_value:
|
||||
print("malformed")
|
||||
raise SystemExit(0)
|
||||
values.append(raw_value.lower())
|
||||
continue
|
||||
value = (item.get("status") or item.get("state") or "").lower()
|
||||
if value:
|
||||
values.append(value)
|
||||
|
||||
if any(value in pending_values for value in values) or state in pending_values:
|
||||
print("pending")
|
||||
elif any(value in failure_values for value in values) or state in failure_values:
|
||||
print("terminal-failure")
|
||||
elif values and all(value in success_values for value in values) and state in {"", "success"}:
|
||||
print("terminal-success")
|
||||
elif not values:
|
||||
if not values and not state:
|
||||
print("no-status")
|
||||
elif any(v in pending_values for v in values):
|
||||
print("pending")
|
||||
elif any(v in failure_values for v in values):
|
||||
print("terminal-failure")
|
||||
elif values and all(v in success_values for v in values):
|
||||
print("terminal-success")
|
||||
else:
|
||||
print("unknown")
|
||||
'
|
||||
PY
|
||||
}
|
||||
|
||||
print_pending_contexts() {
|
||||
python3 -c '
|
||||
python3 - <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
@@ -110,61 +104,17 @@ for item in statuses:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
name = item.get("context") or item.get("name") or "unknown-context"
|
||||
value = str(item.get("status") or item.get("state") or "unknown").lower()
|
||||
value = (item.get("status") or item.get("state") or "unknown").lower()
|
||||
target = item.get("target_url") or item.get("url") or ""
|
||||
if value in pending_values:
|
||||
found = True
|
||||
suffix = f" ({target})" if target else ""
|
||||
print(f"[ci-queue-wait] pending: {name}={value}{suffix}")
|
||||
if target:
|
||||
print(f"[ci-queue-wait] pending: {name}={value} ({target})")
|
||||
else:
|
||||
print(f"[ci-queue-wait] pending: {name}={value}")
|
||||
if not found:
|
||||
print("[ci-queue-wait] no pending contexts")
|
||||
'
|
||||
}
|
||||
|
||||
record_cannot_assert() {
|
||||
local reason="$1"
|
||||
local audit_log="${MOSAIC_CI_QUEUE_AUDIT_LOG:-${XDG_STATE_HOME:-${HOME:-}/.local/state}/mosaic/audit/ci-queue-wait.jsonl}"
|
||||
|
||||
if [[ -z "$audit_log" ]] || ! mkdir -p "$(dirname "$audit_log")"; then
|
||||
echo "Error: CANNOT_ASSERT and audit directory is unavailable; refusing degraded pass." >&2
|
||||
return 70
|
||||
fi
|
||||
|
||||
if ! python3 - "$audit_log" "$reason" "${PLATFORM:-unknown}" "$PURPOSE" "${BRANCH:-unknown}" "${OWNER:-unknown}/${REPO:-unknown}" <<'PY'
|
||||
import datetime
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
path, reason, platform, purpose, branch, repo = sys.argv[1:]
|
||||
record = {
|
||||
"timestamp": datetime.datetime.now(datetime.timezone.utc).isoformat(),
|
||||
"outcome": "CANNOT_ASSERT",
|
||||
"reason": reason,
|
||||
"platform": platform,
|
||||
"purpose": purpose,
|
||||
"disposition": "hold" if purpose == "merge" else "degraded-pass",
|
||||
"branch": branch,
|
||||
"repo": repo,
|
||||
}
|
||||
fd = os.open(path, os.O_WRONLY | os.O_CREAT | os.O_APPEND, 0o600)
|
||||
try:
|
||||
os.write(fd, (json.dumps(record, separators=(",", ":")) + "\n").encode())
|
||||
finally:
|
||||
os.close(fd)
|
||||
PY
|
||||
then
|
||||
echo "Error: CANNOT_ASSERT and audit write failed at ${audit_log}; refusing degraded pass." >&2
|
||||
return 70
|
||||
fi
|
||||
|
||||
if [[ "$PURPOSE" == "merge" ]]; then
|
||||
echo "[ci-queue-wait] CANNOT_ASSERT reason=${reason} purpose=merge branch=${BRANCH:-unknown}; audited=${audit_log}; HOLD (exit 75). Retry after provider recovery; no manual reset is required." >&2
|
||||
return 75
|
||||
fi
|
||||
|
||||
echo "[ci-queue-wait] CANNOT_ASSERT reason=${reason} purpose=push branch=${BRANCH:-unknown}; audited=${audit_log}; push may proceed in degraded mode." >&2
|
||||
return 0
|
||||
}
|
||||
|
||||
github_get_branch_head_sha() {
|
||||
@@ -178,87 +128,7 @@ github_get_commit_status_json() {
|
||||
local owner="$1"
|
||||
local repo="$2"
|
||||
local sha="$3"
|
||||
local work_root status_file checks_file
|
||||
work_root="${AGENT_WORK_ROOT:-${HOME:-}/.cache/mosaic/ci-queue-wait}"
|
||||
mkdir -p "$work_root" || return 1
|
||||
status_file=$(mktemp "$work_root/github-status.XXXXXX") || return 1
|
||||
checks_file=$(mktemp "$work_root/github-checks.XXXXXX") || {
|
||||
rm -f "$status_file"
|
||||
return 1
|
||||
}
|
||||
|
||||
if ! gh api --paginate --slurp "repos/${owner}/${repo}/commits/${sha}/statuses?per_page=100" > "$status_file" ||
|
||||
! gh api --paginate --slurp "repos/${owner}/${repo}/commits/${sha}/check-runs?per_page=100&filter=latest" > "$checks_file"; then
|
||||
rm -f "$status_file" "$checks_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
python3 - "$status_file" "$checks_file" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
||||
status_pages = json.load(handle)
|
||||
with open(sys.argv[2], encoding="utf-8") as handle:
|
||||
check_pages = json.load(handle)
|
||||
|
||||
if not isinstance(status_pages, list) or not isinstance(check_pages, list):
|
||||
raise SystemExit(1)
|
||||
|
||||
# The statuses endpoint is newest-first and can contain retries for one context.
|
||||
# Keep only the newest entry per context after flattening every page.
|
||||
combined = []
|
||||
seen_contexts = set()
|
||||
for page in status_pages:
|
||||
if not isinstance(page, list):
|
||||
raise SystemExit(1)
|
||||
for status in page:
|
||||
if not isinstance(status, dict):
|
||||
raise SystemExit(1)
|
||||
context = status.get("context")
|
||||
if not isinstance(context, str) or not context or context in seen_contexts:
|
||||
continue
|
||||
seen_contexts.add(context)
|
||||
combined.append(status)
|
||||
|
||||
check_runs = []
|
||||
reported_total = 0
|
||||
for page in check_pages:
|
||||
if not isinstance(page, dict):
|
||||
raise SystemExit(1)
|
||||
page_runs = page.get("check_runs") or []
|
||||
total_count = page.get("total_count")
|
||||
if not isinstance(page_runs, list) or not isinstance(total_count, int):
|
||||
raise SystemExit(1)
|
||||
reported_total = max(reported_total, total_count)
|
||||
check_runs.extend(page_runs)
|
||||
if len(check_runs) < reported_total:
|
||||
raise SystemExit(1)
|
||||
|
||||
for run in check_runs:
|
||||
if not isinstance(run, dict):
|
||||
raise SystemExit(1)
|
||||
status = run.get("status")
|
||||
conclusion = run.get("conclusion")
|
||||
if status != "completed":
|
||||
value = "pending"
|
||||
elif conclusion == "success":
|
||||
value = "success"
|
||||
elif conclusion in {"failure", "cancelled", "timed_out", "action_required", "startup_failure", "stale"}:
|
||||
value = "failure"
|
||||
else:
|
||||
value = "unknown"
|
||||
combined.append({
|
||||
"context": run.get("name") or "github-check",
|
||||
"status": value,
|
||||
"target_url": run.get("html_url") or run.get("details_url") or "",
|
||||
})
|
||||
|
||||
json.dump({"state": "", "statuses": combined}, sys.stdout)
|
||||
PY
|
||||
local status=$?
|
||||
rm -f "$status_file" "$checks_file"
|
||||
return "$status"
|
||||
gh api "repos/${owner}/${repo}/commits/${sha}/status"
|
||||
}
|
||||
|
||||
gitea_get_branch_head_sha() {
|
||||
@@ -304,14 +174,6 @@ while [[ $# -gt 0 ]]; do
|
||||
BRANCH="$2"
|
||||
shift 2
|
||||
;;
|
||||
-R|--repo)
|
||||
TARGET_REPO="$2"
|
||||
shift 2
|
||||
;;
|
||||
--sha)
|
||||
HEAD_SHA="$2"
|
||||
shift 2
|
||||
;;
|
||||
-t|--timeout)
|
||||
TIMEOUT_SEC="$2"
|
||||
shift 2
|
||||
@@ -344,89 +206,45 @@ if ! [[ "$TIMEOUT_SEC" =~ ^[0-9]+$ ]] || ! [[ "$INTERVAL_SEC" =~ ^[0-9]+$ ]]; th
|
||||
echo "Error: timeout and interval must be integer seconds." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$HEAD_SHA" && ! "$HEAD_SHA" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
||||
echo "Error: --sha must be a full 40-character hexadecimal commit SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$TARGET_REPO" && ! "$TARGET_REPO" =~ ^[^/[:space:]]+/[^/[:space:]]+$ ]]; then
|
||||
echo "Error: --repo must be OWNER/REPO." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [[ "$PURPOSE" != "push" && "$PURPOSE" != "merge" ]]; then
|
||||
echo "Error: --purpose must be push or merge." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
OWNER="unknown"
|
||||
REPO="unknown"
|
||||
PLATFORM="unknown"
|
||||
if ! OWNER=$(get_repo_owner) || [[ -z "$OWNER" ]]; then
|
||||
record_cannot_assert "repository-owner-unresolvable"
|
||||
exit $?
|
||||
fi
|
||||
if ! REPO=$(get_repo_name) || [[ -z "$REPO" ]]; then
|
||||
record_cannot_assert "repository-name-unresolvable"
|
||||
exit $?
|
||||
fi
|
||||
if ! detect_platform > /dev/null; then
|
||||
PLATFORM="${PLATFORM:-unknown}"
|
||||
record_cannot_assert "unsupported-platform"
|
||||
exit $?
|
||||
fi
|
||||
OWNER=$(get_repo_owner)
|
||||
REPO=$(get_repo_name)
|
||||
detect_platform > /dev/null
|
||||
PLATFORM="${PLATFORM:-unknown}"
|
||||
|
||||
if [[ -n "$TARGET_REPO" ]]; then
|
||||
OWNER="${TARGET_REPO%%/*}"
|
||||
REPO="${TARGET_REPO##*/}"
|
||||
fi
|
||||
|
||||
if [[ -z "$BRANCH" ]]; then
|
||||
if ! BRANCH=$(git symbolic-ref --quiet --short HEAD) || [[ -z "$BRANCH" ]]; then
|
||||
record_cannot_assert "current-branch-unresolvable"
|
||||
exit $?
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ "$PLATFORM" == "github" ]]; then
|
||||
if ! command -v gh >/dev/null 2>&1; then
|
||||
record_cannot_assert "github-cli-unavailable"
|
||||
exit $?
|
||||
echo "Error: gh CLI is required for GitHub CI queue guard." >&2
|
||||
exit 1
|
||||
fi
|
||||
HEAD_SHA=$(github_get_branch_head_sha "$OWNER" "$REPO" "$BRANCH")
|
||||
if [[ -z "$HEAD_SHA" ]]; then
|
||||
if ! HEAD_SHA=$(github_get_branch_head_sha "$OWNER" "$REPO" "$BRANCH") || [[ -z "$HEAD_SHA" ]]; then
|
||||
record_cannot_assert "branch-head-unavailable"
|
||||
exit $?
|
||||
fi
|
||||
echo "Error: Could not resolve ${BRANCH} head SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "[ci-queue-wait] platform=github purpose=${PURPOSE} branch=${BRANCH} sha=${HEAD_SHA}"
|
||||
elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
if ! HOST=$(get_remote_host) || [[ -z "$HOST" ]]; then
|
||||
record_cannot_assert "remote-host-unresolvable"
|
||||
exit $?
|
||||
fi
|
||||
if ! TOKEN=$(get_gitea_token "$HOST") || [[ -z "$TOKEN" ]]; then
|
||||
record_cannot_assert "credential-unresolvable"
|
||||
exit $?
|
||||
HOST=$(get_remote_host) || {
|
||||
echo "Error: Could not determine remote host." >&2
|
||||
exit 1
|
||||
}
|
||||
TOKEN=$(get_gitea_token "$HOST") || {
|
||||
echo "Error: Gitea token not found. Set GITEA_TOKEN or configure ~/.git-credentials." >&2
|
||||
exit 1
|
||||
}
|
||||
HEAD_SHA=$(gitea_get_branch_head_sha "$HOST" "$OWNER/$REPO" "$BRANCH" "$TOKEN")
|
||||
if [[ "$HEAD_SHA" == "__BRANCH_ABSENT__" ]]; then
|
||||
echo "[ci-queue-wait] branch ${BRANCH} not yet on remote — no in-flight pipeline; queue clear."
|
||||
exit 0
|
||||
fi
|
||||
if [[ -z "$HEAD_SHA" ]]; then
|
||||
if ! HEAD_SHA=$(gitea_get_branch_head_sha "$HOST" "$OWNER/$REPO" "$BRANCH" "$TOKEN"); then
|
||||
record_cannot_assert "branch-head-unavailable"
|
||||
exit $?
|
||||
fi
|
||||
if [[ "$HEAD_SHA" == "__BRANCH_ABSENT__" ]]; then
|
||||
echo "[ci-queue-wait] branch ${BRANCH} not yet on remote — no in-flight pipeline; queue clear."
|
||||
exit 0
|
||||
fi
|
||||
if [[ -z "$HEAD_SHA" ]]; then
|
||||
record_cannot_assert "branch-head-unavailable"
|
||||
exit $?
|
||||
fi
|
||||
echo "Error: Could not resolve ${BRANCH} head SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "[ci-queue-wait] platform=gitea purpose=${PURPOSE} branch=${BRANCH} sha=${HEAD_SHA}"
|
||||
else
|
||||
record_cannot_assert "unsupported-platform"
|
||||
exit $?
|
||||
echo "Error: Unsupported platform '${PLATFORM}'." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
START_TS=$(date +%s)
|
||||
@@ -435,20 +253,14 @@ DEADLINE_TS=$((START_TS + TIMEOUT_SEC))
|
||||
while true; do
|
||||
NOW_TS=$(date +%s)
|
||||
if (( NOW_TS > DEADLINE_TS )); then
|
||||
echo "Error: ASSERTED_NOT_READY state=pending; timed out waiting for CI queue to clear on ${BRANCH} after ${TIMEOUT_SEC}s." >&2
|
||||
echo "Error: Timed out waiting for CI queue to clear on ${BRANCH} after ${TIMEOUT_SEC}s." >&2
|
||||
exit 124
|
||||
fi
|
||||
|
||||
if [[ "$PLATFORM" == "github" ]]; then
|
||||
if ! STATUS_JSON=$(github_get_commit_status_json "$OWNER" "$REPO" "$HEAD_SHA"); then
|
||||
record_cannot_assert "status-provider-unreachable"
|
||||
exit $?
|
||||
fi
|
||||
STATUS_JSON=$(github_get_commit_status_json "$OWNER" "$REPO" "$HEAD_SHA")
|
||||
else
|
||||
if ! STATUS_JSON=$(gitea_get_commit_status_json "$HOST" "$OWNER/$REPO" "$HEAD_SHA" "$TOKEN"); then
|
||||
record_cannot_assert "status-provider-unreachable"
|
||||
exit $?
|
||||
fi
|
||||
STATUS_JSON=$(gitea_get_commit_status_json "$HOST" "$OWNER/$REPO" "$HEAD_SHA" "$TOKEN")
|
||||
fi
|
||||
|
||||
STATE=$(printf '%s' "$STATUS_JSON" | get_state_from_status_json)
|
||||
@@ -459,24 +271,21 @@ while true; do
|
||||
printf '%s' "$STATUS_JSON" | print_pending_contexts
|
||||
sleep "$INTERVAL_SEC"
|
||||
;;
|
||||
terminal-success)
|
||||
exit 0
|
||||
;;
|
||||
no-status)
|
||||
if [[ "$REQUIRE_STATUS" -eq 1 ]]; then
|
||||
echo "Error: ASSERTED_NOT_READY state=no-status; --require-status was set for ${BRANCH}." >&2
|
||||
else
|
||||
echo "Error: ASSERTED_NOT_READY state=no-status purpose=${PURPOSE} branch=${BRANCH}." >&2
|
||||
echo "Error: No CI status contexts found for ${BRANCH} while --require-status is set." >&2
|
||||
exit 1
|
||||
fi
|
||||
exit 3
|
||||
echo "[ci-queue-wait] no status contexts present; proceeding."
|
||||
exit 0
|
||||
;;
|
||||
terminal-failure|malformed|unknown)
|
||||
echo "Error: ASSERTED_NOT_READY state=${STATE} purpose=${PURPOSE} branch=${BRANCH}." >&2
|
||||
exit 3
|
||||
terminal-success|terminal-failure|unknown)
|
||||
# Queue guard only blocks on pending/running/queued states.
|
||||
exit 0
|
||||
;;
|
||||
*)
|
||||
echo "Error: ASSERTED_NOT_READY unrecognized-state=${STATE} purpose=${PURPOSE} branch=${BRANCH}." >&2
|
||||
exit 3
|
||||
echo "[ci-queue-wait] unrecognized state '${STATE}', proceeding conservatively."
|
||||
exit 0
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
@@ -5,10 +5,7 @@
|
||||
|
||||
detect_platform() {
|
||||
local remote_url
|
||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
||||
# kills the CALLER before the -z check below can run, so the error message that is
|
||||
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
|
||||
remote_url=$(git remote get-url origin 2>/dev/null) || true
|
||||
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||
|
||||
if [[ -z "$remote_url" ]]; then
|
||||
echo "error: not a git repository or no origin remote" >&2
|
||||
@@ -42,10 +39,7 @@ detect_platform() {
|
||||
|
||||
get_repo_info() {
|
||||
local remote_url
|
||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
||||
# kills the CALLER before the -z check below can run, so the error message that is
|
||||
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
|
||||
remote_url=$(git remote get-url origin 2>/dev/null) || true
|
||||
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||
|
||||
if [[ -z "$remote_url" ]]; then
|
||||
echo "error: not a git repository or no origin remote" >&2
|
||||
@@ -246,21 +240,6 @@ PY
|
||||
} >&2
|
||||
}
|
||||
|
||||
# Explain tea's most misleading failure. `user does not exist [uid: 0, name: ]` reads
|
||||
# as a missing account; it almost always means a REVOKED OR STALE TOKEN. `tea login`
|
||||
# keeps its OWN COPY of the token, so rotating the credential store does not update it.
|
||||
# Diagnostic only -- stderr, no control flow, no exit.
|
||||
explain_tea_user_does_not_exist() {
|
||||
cat >&2 <<'MSG'
|
||||
NOTE: `user does not exist [uid: 0, name: ]` from tea usually means a REVOKED OR STALE TOKEN,
|
||||
not a missing account. A `tea login` stores its OWN COPY of the token; rotating the
|
||||
credential store does NOT update it.
|
||||
CHECK: the login's cached copy (`tea login list` -- read the FULL table, never `| head`),
|
||||
then re-register that login against the current token.
|
||||
DO NOT probe capability with a mutating request; a POST is the action, not a check.
|
||||
MSG
|
||||
}
|
||||
|
||||
get_gitea_login_for_host() {
|
||||
local host="${1:-}"
|
||||
local login
|
||||
|
||||
@@ -91,32 +91,13 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
GITEA_LOGIN_NAME=$(get_gitea_login || true)
|
||||
if [[ -n "$GITEA_LOGIN_NAME" ]]; then
|
||||
if [[ -n "$COMMENT" ]]; then
|
||||
# `tea issue comment` is NOT a subcommand -- tea 0.11.x lists only
|
||||
# list/create/edit/reopen/close under `tea issue`. Comments are the
|
||||
# TOP-LEVEL `tea comment`, which takes the same --repo/--login flags.
|
||||
# The old call therefore always failed, was unchecked, and the script
|
||||
# closed the issue anyway, losing the record of WHY.
|
||||
#
|
||||
# Use `tea comment` rather than the API helper so the comment and the
|
||||
# close are made by the SAME principal ($GITEA_LOGIN_NAME). Routing the
|
||||
# comment through the token-authenticated helper here would attribute the
|
||||
# comment to the token holder and the close to the tea login -- two
|
||||
# principals for one operation.
|
||||
tea comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME" || {
|
||||
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
|
||||
exit 1
|
||||
}
|
||||
tea issue comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||
fi
|
||||
tea issue close "$ISSUE_NUMBER" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||
else
|
||||
echo "No tea login configured for $(get_remote_host); using authenticated Gitea API fallback." >&2
|
||||
if [[ -n "$COMMENT" ]]; then
|
||||
# Fail closed here too: an unchecked comment lets the issue close without its
|
||||
# audit trail, which is the same defect as the tea path above.
|
||||
gitea_issue_comment_api || {
|
||||
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
|
||||
exit 1
|
||||
}
|
||||
gitea_issue_comment_api
|
||||
fi
|
||||
gitea_issue_close_api
|
||||
fi
|
||||
|
||||
@@ -254,32 +254,15 @@ from urllib.parse import urlparse
|
||||
|
||||
|
||||
def _origin_and_path(url):
|
||||
# Normalize a URL to (scheme-class, host, distinguishing-port) + comment path.
|
||||
#
|
||||
# #991: http and https collapse into ONE scheme class ("web"). A Gitea whose
|
||||
# ROOT_URL is configured http:// returns http:// object URLs even when every
|
||||
# client reaches it over https://, so a scheme-strict comparison rejects the
|
||||
# provider's own correct answer about a write that landed — a deterministic
|
||||
# false negative on every comment posted against such a deployment. The
|
||||
# scheme is also not what this check defends: the forgeries it exists to
|
||||
# catch (look-alike host, decoy path prefix, wrong owner/repo/number) all
|
||||
# vary the HOST or the PATH, both of which stay strict below. Any OTHER
|
||||
# scheme (file:, ftp:, javascript:) remains distinguishing and is rejected.
|
||||
#
|
||||
# Port: an implicit port and its own scheme's default compare equal, so
|
||||
# http://h == https://h. An EXPLICIT non-default port still distinguishes,
|
||||
# because a different port is a different service on the same host.
|
||||
# Normalize a URL to (scheme, host, effective-port) + comment path. The port
|
||||
# defaults to the scheme's default (80 http / 443 otherwise) so an implicit
|
||||
# port and its explicit default form compare equal.
|
||||
parsed = urlparse(url or "")
|
||||
scheme = (parsed.scheme or "").lower()
|
||||
host = (parsed.hostname or "").lower()
|
||||
if scheme in ("http", "https"):
|
||||
scheme_class = "web"
|
||||
default_port = 80 if scheme == "http" else 443
|
||||
port = None if parsed.port in (None, default_port) else parsed.port
|
||||
else:
|
||||
scheme_class = scheme
|
||||
port = parsed.port
|
||||
return (scheme_class, host, port), parsed.path.rstrip("/")
|
||||
default_port = 80 if scheme == "http" else 443
|
||||
port = parsed.port if parsed.port is not None else default_port
|
||||
return (scheme, host, port), parsed.path.rstrip("/")
|
||||
|
||||
|
||||
try:
|
||||
|
||||
@@ -156,7 +156,6 @@ case "$PLATFORM" in
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea issue create failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
fi
|
||||
gitea_issue_create_api
|
||||
;;
|
||||
|
||||
@@ -71,7 +71,6 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea issue view failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
fi
|
||||
gitea_issue_view_api
|
||||
else
|
||||
|
||||
@@ -1,306 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# mosaic-worktree.sh — the only supported way to create and dispose of a git
|
||||
# worktree on a fleet host.
|
||||
#
|
||||
# Why this exists as a helper and not as a rule: the rule already existed, in
|
||||
# the framework's own words ("Big work → /var/tmp"), and 255 GB accumulated in
|
||||
# $HOME across 842 directories anyway. Five placement conventions were live on
|
||||
# one fleet host simultaneously. Every one was a decision an agent had to make,
|
||||
# and a decision an agent has to make is a decision that drifts.
|
||||
#
|
||||
# So this script makes NO placement decision available. The caller supplies a
|
||||
# branch name. Every path is DERIVED:
|
||||
#
|
||||
# main worktree <- git worktree list --porcelain (never cwd, which may
|
||||
# itself already be a worktree)
|
||||
# REPO_NAME <- basename of the main worktree
|
||||
# REPO_PARENT <- dirname of the main worktree
|
||||
# WT_ROOT <- $REPO_PARENT/$REPO_NAME-worktrees
|
||||
# SLUG <- branch with '/' replaced by '-'
|
||||
# WT_PATH <- $WT_ROOT/$SLUG
|
||||
#
|
||||
# The derivation puts the worktree on the same filesystem as the object store
|
||||
# it shares, as a sibling of the repo, under one root per repo. Those are the
|
||||
# properties that make the checkout cheap and — via `git worktree list` —
|
||||
# enumerable, which is the only reason automated cleanup can ever be safe.
|
||||
#
|
||||
# Usage:
|
||||
# mosaic-worktree.sh new <branch> [--from <base>] create (branch may exist)
|
||||
# mosaic-worktree.sh path <branch> print derived path, no side effect
|
||||
# mosaic-worktree.sh list this repo's worktrees + state
|
||||
# mosaic-worktree.sh rm <branch> [--force] remove; refuses to lose work
|
||||
# mosaic-worktree.sh gc [--apply] report/remove clean+pushed worktrees
|
||||
#
|
||||
# `rm` and `gc` refuse to delete a worktree with uncommitted changes, with
|
||||
# commits absent from every remote, or holding ignored files that are not of the
|
||||
# well-known regenerable kind (a `.env` is ignored so it is never committed,
|
||||
# which is also why nothing else holds a copy). That check is by EVIDENCE, never
|
||||
# by size or age. --force overrides it and is yours to type deliberately.
|
||||
#
|
||||
# Run from anywhere inside the repo, or pass --repo <path>.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
die() { printf 'mosaic-worktree: %s\n' "$*" >&2; exit 1; }
|
||||
|
||||
REPO_HINT=""
|
||||
ARGS=()
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--repo) REPO_HINT="${2:-}"; shift 2 ;;
|
||||
*) ARGS+=("$1"); shift ;;
|
||||
esac
|
||||
done
|
||||
set -- "${ARGS[@]+"${ARGS[@]}"}"
|
||||
|
||||
CMD="${1:-}"
|
||||
[ -n "$CMD" ] || die "no command. Try: new | path | list | rm | gc"
|
||||
shift || true
|
||||
|
||||
# ---- mechanical derivation -------------------------------------------------
|
||||
# The FIRST entry of `git worktree list --porcelain` is always the main
|
||||
# worktree, regardless of which worktree we are standing in. Deriving from cwd
|
||||
# would nest worktrees inside worktrees.
|
||||
resolve_repo() {
|
||||
local start="${REPO_HINT:-$PWD}"
|
||||
git -C "$start" rev-parse --git-dir >/dev/null 2>&1 \
|
||||
|| die "not inside a git repository: $start"
|
||||
# Take the first entry WITHOUT closing the pipe early. `awk ... exit` on the
|
||||
# first match closes the read end while git is still writing, git takes SIGPIPE,
|
||||
# and under `set -euo pipefail` the command substitution returns 141 and this
|
||||
# function aborts SILENTLY — no message, no worktree, and `new` exits 141 while
|
||||
# printing nothing at all.
|
||||
#
|
||||
# Whether it happens depends on how much git still had to write when awk left,
|
||||
# so the failure is a function of REPO SIZE: fine on a repo with three
|
||||
# worktrees, reliably broken on one with seventy. That is backwards — the repos
|
||||
# this helper exists to serve are exactly the ones that accumulated worktrees,
|
||||
# and it silently did nothing on those while working everywhere it was tried.
|
||||
# Measured on a repo with 73 worktrees (10 KB of porcelain): rc=141, no output.
|
||||
#
|
||||
# The file's own comment block below already names this class for `head -200`
|
||||
# and removed that cap for the same reason. The `exit` here is the same defect
|
||||
# in the same file, so the rule is now uniform: nothing in this script closes a
|
||||
# git pipe early. Dropping `exit` costs one pass over a few KB.
|
||||
MAIN_WT="$(git -C "$start" worktree list --porcelain | awk '/^worktree /&&!seen{print substr($0,10); seen=1}')"
|
||||
[ -n "$MAIN_WT" ] || die "could not resolve the main worktree"
|
||||
REPO_NAME="$(basename -- "$MAIN_WT")"
|
||||
REPO_PARENT="$(dirname -- "$MAIN_WT")"
|
||||
WT_ROOT="$REPO_PARENT/$REPO_NAME-worktrees"
|
||||
}
|
||||
|
||||
slugify() { printf '%s' "$1" | tr '/' '-'; }
|
||||
|
||||
derive_path() {
|
||||
local branch="$1"
|
||||
[ -n "$branch" ] || die "branch name required"
|
||||
printf '%s/%s' "$WT_ROOT" "$(slugify "$branch")"
|
||||
}
|
||||
|
||||
# A worktree root under $HOME defeats the entire point: wrong filesystem, and
|
||||
# $HOME is for configuration and state, not work products. Refuse rather than
|
||||
# silently produce the layout we are trying to eliminate.
|
||||
assert_not_home() {
|
||||
local p="$1" home_real repo_real
|
||||
home_real="$(cd "$HOME" && pwd -P)"
|
||||
repo_real="$(cd "$(dirname -- "$p")" 2>/dev/null && pwd -P || dirname -- "$p")"
|
||||
case "$repo_real/" in
|
||||
"$home_real"/*)
|
||||
die "refusing: derived path is under \$HOME ($p).
|
||||
The repo itself lives under \$HOME, so its worktrees would too. Move the repo
|
||||
to a work filesystem (e.g. /src/$REPO_NAME) and re-run. \$HOME holds
|
||||
configuration, credentials, state and caches — not checkouts." ;;
|
||||
esac
|
||||
}
|
||||
|
||||
# ---- work-loss evidence ----------------------------------------------------
|
||||
# Two independent questions, both answered from git, neither from size or age:
|
||||
# dirty — anything uncommitted in the tree
|
||||
# unpushed — commits reachable from HEAD that no remote ref contains
|
||||
# precious — IGNORED files git will not mention and will not miss
|
||||
#
|
||||
# The third question is not obvious and was missed on the first pass. An
|
||||
# independent reviewer demonstrated it in four commands: a pushed, clean
|
||||
# worktree whose .gitignore covers `*.secret`, holding one `local.secret`.
|
||||
# `git status --porcelain` is empty, `rev-list --count HEAD --not --remotes` is
|
||||
# 0 — the evidence reads SAFE — and `git worktree remove` deletes the file. The
|
||||
# same shape covers `.env`, credentials, scratch notes, downloaded fixtures:
|
||||
# precisely the files that are ignored BECAUSE they must not be committed, which
|
||||
# is also why nothing else is holding a copy.
|
||||
#
|
||||
# So ignored files count as work unless they are the well-known regenerable
|
||||
# kind. Getting that set wrong is asymmetric: an over-broad list preserves a
|
||||
# worktree that could have been reclaimed (cheap, visible, fixable by --force),
|
||||
# an over-narrow one deletes the only copy of a secret (silent, permanent).
|
||||
# The list stays short and conservative for that reason.
|
||||
DISPOSABLE_RE='(^|/)(node_modules|\.venv|venv|__pycache__|\.mypy_cache|\.pytest_cache|\.ruff_cache|\.turbo|\.cache|\.parcel-cache|\.gradle|dist|build|out|target|coverage|\.next|\.nuxt|\.svelte-kit)(/|$)|\.(pyc|pyo|o|class)$'
|
||||
|
||||
# These three run under `set -euo pipefail` inside command substitution, which
|
||||
# makes any nonzero exit ANYWHERE in the pipeline abort the calling function
|
||||
# silently. Two ways that bites, one of which shipped:
|
||||
#
|
||||
# * `grep -v` exits 1 when it filters everything out. A worktree whose only
|
||||
# ignored entry is `node_modules/` is exactly the SAFE case, and it made
|
||||
# `rm` exit 1 with no message and no removal — found by review.
|
||||
# * `head -200` closes the pipe, SIGPIPEs the producer, and turns a worktree
|
||||
# with 201 dirty files into the same silent abort. Not reported; it is the
|
||||
# same defect one step upstream, so the cap is gone. Counting is cheap;
|
||||
# the cap only ever protected output that is now never printed.
|
||||
#
|
||||
# Every one of them therefore ends in a total, and every stage that can
|
||||
# legitimately exit nonzero says so explicitly.
|
||||
wt_dirty() {
|
||||
local out
|
||||
out="$(git -C "$1" status --porcelain 2>/dev/null || true)"
|
||||
if [ -n "$out" ]; then printf '%s\n' "$out" | wc -l; else printf '0'; fi
|
||||
}
|
||||
|
||||
wt_unpushed() { git -C "$1" rev-list --count HEAD --not --remotes 2>/dev/null || printf '?'; }
|
||||
|
||||
# Default --ignored (not =matching) so a 40k-file node_modules collapses to one
|
||||
# directory entry instead of being enumerated and then discarded.
|
||||
wt_precious() {
|
||||
local ignored
|
||||
ignored="$(git -C "$1" status --porcelain --ignored 2>/dev/null \
|
||||
| awk '/^!! /{print substr($0,4)}' || true)"
|
||||
[ -n "$ignored" ] || { printf '0'; return 0; }
|
||||
printf '%s\n' "$ignored" | grep -Ecv "$DISPOSABLE_RE" || true
|
||||
}
|
||||
|
||||
wt_state() {
|
||||
local wt="$1" d u p
|
||||
d="$(wt_dirty "$wt")"; u="$(wt_unpushed "$wt")"; p="$(wt_precious "$wt")"
|
||||
if [ "$d" -eq 0 ] && [ "$u" = "0" ] && [ "$p" -eq 0 ]; then
|
||||
printf 'SAFE\tclean; 0 unpushed; no ignored files worth keeping'
|
||||
else
|
||||
printf 'PRESERVE\t%s uncommitted; %s unpushed; %s ignored-but-not-disposable' "$d" "$u" "$p"
|
||||
fi
|
||||
}
|
||||
|
||||
# ---- commands --------------------------------------------------------------
|
||||
cmd_path() { resolve_repo; derive_path "${1:-}"; echo; }
|
||||
|
||||
cmd_new() {
|
||||
local branch="${1:-}" base=""
|
||||
shift || true
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in --from) base="${2:-}"; shift 2 ;; *) die "unknown flag: $1" ;; esac
|
||||
done
|
||||
[ -n "$branch" ] || die "usage: mosaic-worktree.sh new <branch> [--from <base>]"
|
||||
|
||||
resolve_repo
|
||||
local path; path="$(derive_path "$branch")"
|
||||
assert_not_home "$path"
|
||||
|
||||
if [ -e "$path" ]; then
|
||||
echo "exists: $path"
|
||||
echo "(already checked out — reuse it, or 'rm' it first)"
|
||||
return 0
|
||||
fi
|
||||
|
||||
mkdir -p "$WT_ROOT"
|
||||
|
||||
# Existing branch -> check it out. New branch -> create from base (default:
|
||||
# the remote's default branch if resolvable, else current HEAD).
|
||||
if git -C "$MAIN_WT" show-ref --verify --quiet "refs/heads/$branch" \
|
||||
|| git -C "$MAIN_WT" show-ref --verify --quiet "refs/remotes/origin/$branch"; then
|
||||
git -C "$MAIN_WT" worktree add "$path" "$branch"
|
||||
else
|
||||
if [ -z "$base" ]; then
|
||||
base="$(git -C "$MAIN_WT" symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null || true)"
|
||||
[ -n "$base" ] || base="HEAD"
|
||||
fi
|
||||
git -C "$MAIN_WT" worktree add -b "$branch" "$path" "$base"
|
||||
fi
|
||||
|
||||
cat <<EOF
|
||||
|
||||
worktree: $path
|
||||
branch: $branch
|
||||
|
||||
Removal is part of this task, not a later chore. When the work is pushed:
|
||||
mosaic-worktree.sh rm $branch
|
||||
EOF
|
||||
}
|
||||
|
||||
cmd_list() {
|
||||
resolve_repo
|
||||
printf 'repo: %s\nroot: %s\n\n' "$MAIN_WT" "$WT_ROOT"
|
||||
git -C "$MAIN_WT" worktree list --porcelain \
|
||||
| awk '/^worktree /{print substr($0,10)}' \
|
||||
| while read -r wt; do
|
||||
[ "$wt" = "$MAIN_WT" ] && { printf '%-10s %s (main)\n' "-" "$wt"; continue; }
|
||||
printf '%-10s %s\t%s\n' "$(wt_state "$wt" | cut -f1)" "$wt" "$(wt_state "$wt" | cut -f2)"
|
||||
done
|
||||
}
|
||||
|
||||
cmd_rm() {
|
||||
local branch="${1:-}" force=0
|
||||
shift || true
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in --force) force=1; shift ;; *) die "unknown flag: $1" ;; esac
|
||||
done
|
||||
[ -n "$branch" ] || die "usage: mosaic-worktree.sh rm <branch> [--force]"
|
||||
|
||||
resolve_repo
|
||||
local path; path="$(derive_path "$branch")"
|
||||
[ -d "$path" ] || die "no worktree at $path"
|
||||
|
||||
local d u p
|
||||
d="$(wt_dirty "$path")"; u="$(wt_unpushed "$path")"; p="$(wt_precious "$path")"
|
||||
if [ "$force" -eq 0 ] && { [ "$d" -ne 0 ] || [ "$u" != "0" ] || [ "$p" -ne 0 ]; }; then
|
||||
die "refusing to remove $path
|
||||
uncommitted files: $d
|
||||
unpushed commits: $u
|
||||
ignored, not disposable: $p
|
||||
Commit and push first — that is the contract. Ignored files are counted because
|
||||
git will neither report them nor miss them: a .env or a *.secret is ignored
|
||||
precisely so it is never committed, which is also why nothing else holds a copy.
|
||||
List them with: git -C $path status --porcelain --ignored | grep '^!!'
|
||||
If this work is genuinely disposable, re-run with --force."
|
||||
fi
|
||||
|
||||
# NB: ${force:+--force} would expand for force=0 too ("0" is non-empty).
|
||||
if [ "$force" -eq 1 ]; then
|
||||
git -C "$MAIN_WT" worktree remove --force "$path"
|
||||
else
|
||||
git -C "$MAIN_WT" worktree remove "$path"
|
||||
fi
|
||||
git -C "$MAIN_WT" worktree prune
|
||||
echo "removed: $path"
|
||||
rmdir "$WT_ROOT" 2>/dev/null || true
|
||||
}
|
||||
|
||||
cmd_gc() {
|
||||
local apply=0
|
||||
[ "${1:-}" = "--apply" ] && apply=1
|
||||
resolve_repo
|
||||
git -C "$MAIN_WT" worktree prune
|
||||
git -C "$MAIN_WT" worktree list --porcelain \
|
||||
| awk '/^worktree /{print substr($0,10)}' \
|
||||
| while read -r wt; do
|
||||
[ "$wt" = "$MAIN_WT" ] && continue
|
||||
local_state="$(wt_state "$wt")"
|
||||
case "$local_state" in
|
||||
SAFE*)
|
||||
if [ "$apply" -eq 1 ]; then
|
||||
git -C "$MAIN_WT" worktree remove "$wt" && echo "removed: $wt"
|
||||
else
|
||||
echo "reclaimable (clean + fully pushed): $wt"
|
||||
fi ;;
|
||||
*) echo "preserved: $wt [$(printf '%s' "$local_state" | cut -f2)]" ;;
|
||||
esac
|
||||
done
|
||||
git -C "$MAIN_WT" worktree prune
|
||||
[ "$apply" -eq 1 ] || echo $'\n(report only — re-run with --apply to remove the reclaimable ones)'
|
||||
}
|
||||
|
||||
case "$CMD" in
|
||||
new) cmd_new "$@" ;;
|
||||
path) cmd_path "$@" ;;
|
||||
list) cmd_list "$@" ;;
|
||||
rm) cmd_rm "$@" ;;
|
||||
gc) cmd_gc "$@" ;;
|
||||
-h|--help|help) sed -n '2,40p' "$0" | sed 's/^# \{0,1\}//' ;;
|
||||
*) die "unknown command: $CMD (new | path | list | rm | gc)" ;;
|
||||
esac
|
||||
@@ -84,7 +84,7 @@ cp "$TARGET" "$BAK"
|
||||
export MOSAIC_TEST_WORK_DIR="$WORK/.work"
|
||||
|
||||
# --- where the prose lives: usage() { ... EOF ---------------------------------
|
||||
PROSE_LO="$(grep -n -m1 '^usage() {' "$BAK" | cut -d: -f1)"
|
||||
PROSE_LO="$(grep -n '^usage() {' "$BAK" | head -1 | cut -d: -f1)"
|
||||
PROSE_HI="$(awk -v lo="$PROSE_LO" 'NR > lo && /^EOF$/ { print NR; exit }' "$BAK")"
|
||||
if [[ -z "$PROSE_LO" || -z "$PROSE_HI" ]]; then
|
||||
echo "!! cannot locate the usage() heredoc -- the prose guard would be inert; refusing" >&2
|
||||
|
||||
@@ -219,7 +219,6 @@ case "$PLATFORM" in
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea pr create failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
gitea_pr_create_api
|
||||
;;
|
||||
*)
|
||||
|
||||
@@ -1,185 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# pr-edit.sh - Edit a pull request on GitHub or Gitea
|
||||
# Usage: pr-edit.sh -n <pr_number> [-t <title>] [-b <body>] [-B <base>] [--draft|--ready] [--login <name>] [-r owner/repo] [-H host]
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=detect-platform.sh
|
||||
source "$SCRIPT_DIR/detect-platform.sh"
|
||||
|
||||
PR_NUMBER=""
|
||||
TITLE=""
|
||||
BODY=""
|
||||
BASE_BRANCH=""
|
||||
DRAFT_MODE=""
|
||||
LOGIN_OVERRIDE=""
|
||||
REPO_OVERRIDE=""
|
||||
HOST_OVERRIDE=""
|
||||
AUTH_CONFIG=""
|
||||
|
||||
cleanup() {
|
||||
[[ -z "$AUTH_CONFIG" ]] || rm -f -- "$AUTH_CONFIG"
|
||||
}
|
||||
terminate() {
|
||||
local signal="$1"
|
||||
trap - "$signal"
|
||||
cleanup
|
||||
kill -s "$signal" "$$"
|
||||
}
|
||||
trap cleanup EXIT
|
||||
trap 'terminate HUP' HUP
|
||||
trap 'terminate INT' INT
|
||||
trap 'terminate TERM' TERM
|
||||
|
||||
usage() {
|
||||
cat <<EOF
|
||||
Usage: $(basename "$0") [OPTIONS]
|
||||
|
||||
Edit a pull request on the current repository (Gitea or GitHub).
|
||||
|
||||
Options:
|
||||
-n, --number NUMBER Pull request number (required)
|
||||
-t, --title TITLE New title
|
||||
-b, --body BODY New body/description
|
||||
-B, --base BRANCH New base branch
|
||||
--draft Mark the pull request as draft
|
||||
--ready Mark the pull request ready for review
|
||||
-l, --login NAME Gitea login (must authenticate as MOSAIC_GIT_IDENTITY)
|
||||
-r, --repo OWNER/REPO Explicit target repository
|
||||
-H, --host HOST Explicit Gitea host (required with --repo off-host)
|
||||
-h, --help Show this help message
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
}
|
||||
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
-n|--number) PR_NUMBER="${2:-}"; shift 2 ;;
|
||||
-t|--title) TITLE="${2:-}"; shift 2 ;;
|
||||
-b|--body) BODY="${2:-}"; shift 2 ;;
|
||||
-B|--base) BASE_BRANCH="${2:-}"; shift 2 ;;
|
||||
--draft)
|
||||
[[ "$DRAFT_MODE" != "ready" ]] || { echo "Error: --draft and --ready are mutually exclusive" >&2; exit 1; }
|
||||
DRAFT_MODE="draft"; shift ;;
|
||||
--ready)
|
||||
[[ "$DRAFT_MODE" != "draft" ]] || { echo "Error: --draft and --ready are mutually exclusive" >&2; exit 1; }
|
||||
DRAFT_MODE="ready"; shift ;;
|
||||
-l|--login) LOGIN_OVERRIDE="${2:-}"; shift 2 ;;
|
||||
-r|--repo) REPO_OVERRIDE="${2:-}"; shift 2 ;;
|
||||
-H|--host) HOST_OVERRIDE="${2:-}"; shift 2 ;;
|
||||
-h|--help) usage 0 ;;
|
||||
*) echo "Unknown option: $1" >&2; usage ;;
|
||||
esac
|
||||
done
|
||||
|
||||
[[ -n "$PR_NUMBER" ]] || { echo "Error: Pull request number is required (-n)" >&2; exit 1; }
|
||||
[[ "$PR_NUMBER" =~ ^[1-9][0-9]*$ ]] || { echo "Error: Pull request number must be a positive integer" >&2; exit 1; }
|
||||
if [[ -z "$TITLE" && -z "$BODY" && -z "$BASE_BRANCH" && -z "$DRAFT_MODE" ]]; then
|
||||
echo "Error: At least one edit option is required" >&2
|
||||
exit 1
|
||||
fi
|
||||
[[ -z "$REPO_OVERRIDE" || "$REPO_OVERRIDE" =~ ^[^/[:space:]]+/[^/[:space:]]+$ ]] || {
|
||||
echo "Error: --repo must be OWNER/REPO" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
if [[ -n "$HOST_OVERRIDE" || -n "$REPO_OVERRIDE" ]]; then
|
||||
PLATFORM="gitea"
|
||||
else
|
||||
PLATFORM=$(detect_platform)
|
||||
fi
|
||||
|
||||
case "$PLATFORM" in
|
||||
github)
|
||||
[[ -z "$LOGIN_OVERRIDE" ]] || { echo "Error: --login is only valid for Gitea" >&2; exit 1; }
|
||||
if [[ -n "$TITLE" || -n "$BODY" || -n "$BASE_BRANCH" ]]; then
|
||||
CMD=(gh pr edit "$PR_NUMBER")
|
||||
[[ -n "$TITLE" ]] && CMD+=(--title "$TITLE")
|
||||
[[ -n "$BODY" ]] && CMD+=(--body "$BODY")
|
||||
[[ -n "$BASE_BRANCH" ]] && CMD+=(--base "$BASE_BRANCH")
|
||||
"${CMD[@]}"
|
||||
fi
|
||||
if [[ "$DRAFT_MODE" == "draft" ]]; then
|
||||
gh pr ready "$PR_NUMBER" --undo
|
||||
elif [[ "$DRAFT_MODE" == "ready" ]]; then
|
||||
gh pr ready "$PR_NUMBER"
|
||||
fi
|
||||
;;
|
||||
gitea)
|
||||
IDENTITY="${MOSAIC_GIT_IDENTITY:-}"
|
||||
[[ -n "$IDENTITY" ]] || {
|
||||
echo "Error: MOSAIC_GIT_IDENTITY is required for a mutating Gitea operation" >&2
|
||||
exit 1
|
||||
}
|
||||
HOST="${HOST_OVERRIDE:-}"
|
||||
if [[ -z "$HOST" ]]; then
|
||||
HOST=$(get_remote_host) || {
|
||||
echo "Error: Could not resolve Gitea host; pass --host with --repo" >&2
|
||||
exit 1
|
||||
}
|
||||
fi
|
||||
HOST="${HOST#http://}"; HOST="${HOST#https://}"; HOST="${HOST%%/*}"
|
||||
REPO_SLUG="${REPO_OVERRIDE:-}"
|
||||
if [[ -z "$REPO_SLUG" ]]; then
|
||||
REPO_SLUG=$(get_repo_slug) || { echo "Error: Could not resolve Gitea repo slug from remote" >&2; exit 1; }
|
||||
fi
|
||||
|
||||
if [[ -n "$LOGIN_OVERRIDE" ]]; then
|
||||
GITEA_LOGIN_NAME="$LOGIN_OVERRIDE"
|
||||
elif [[ -n "${GITEA_LOGIN:-}" ]]; then
|
||||
GITEA_LOGIN_NAME="$GITEA_LOGIN"
|
||||
else
|
||||
echo "Error: --login (or GITEA_LOGIN) is required; refusing host-first login selection" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
TOKEN=$(get_gitea_token_for_login "$GITEA_LOGIN_NAME" "$HOST") || {
|
||||
echo "Error: login '$GITEA_LOGIN_NAME' is not configured for target host '$HOST'" >&2
|
||||
exit 1
|
||||
}
|
||||
AUTH_CONFIG=$(gitea_write_auth_config "$TOKEN") || {
|
||||
echo "Error: could not stage private Gitea authentication" >&2
|
||||
exit 1
|
||||
}
|
||||
unset TOKEN
|
||||
|
||||
API_BASE="https://${HOST}/api/v1"
|
||||
# Resolve identity through the SAME private curl config used for the
|
||||
# mutation. Tea login names are globally scoped and can be duplicated
|
||||
# across hosts; a separate `tea api --login NAME` could validate another
|
||||
# credential than this host-bound token.
|
||||
AUTHENTICATED_USER=$(curl -fsS --config "$AUTH_CONFIG" -H "User-Agent: mosaic-pr-edit" "$API_BASE/user" \
|
||||
| python3 -c 'import json,sys; value=json.load(sys.stdin).get("login"); print(value) if isinstance(value,str) and value else sys.exit(1)') || {
|
||||
echo "Error: could not authenticate the host-bound credential for '$GITEA_LOGIN_NAME'" >&2
|
||||
exit 1
|
||||
}
|
||||
[[ "$AUTHENTICATED_USER" == "$IDENTITY" ]] || {
|
||||
echo "Error: host-bound credential authenticates as '$AUTHENTICATED_USER', not MOSAIC_GIT_IDENTITY '$IDENTITY'" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
REPO_API="$API_BASE/repos/${REPO_SLUG}"
|
||||
curl -fsS --config "$AUTH_CONFIG" -H "User-Agent: mosaic-pr-edit" "$REPO_API" >/dev/null || {
|
||||
echo "Error: target repository preflight failed for https://${HOST}/${REPO_SLUG}" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
PAYLOAD=$(TITLE="$TITLE" BODY="$BODY" BASE_BRANCH="$BASE_BRANCH" DRAFT_MODE="$DRAFT_MODE" python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
payload = {}
|
||||
if os.environ["TITLE"]: payload["title"] = os.environ["TITLE"]
|
||||
if os.environ["BODY"]: payload["body"] = os.environ["BODY"]
|
||||
if os.environ["BASE_BRANCH"]: payload["base"] = os.environ["BASE_BRANCH"]
|
||||
if os.environ["DRAFT_MODE"]: payload["draft"] = os.environ["DRAFT_MODE"] == "draft"
|
||||
print(json.dumps(payload))
|
||||
PY
|
||||
)
|
||||
curl -fsS --config "$AUTH_CONFIG" -X PATCH \
|
||||
-H "User-Agent: mosaic-pr-edit" -H "Content-Type: application/json" \
|
||||
-d "$PAYLOAD" "$REPO_API/pulls/${PR_NUMBER}"
|
||||
echo "Updated Gitea pull request #$PR_NUMBER as '$AUTHENTICATED_USER'" >&2
|
||||
;;
|
||||
*) echo "Error: Could not detect git platform" >&2; exit 1 ;;
|
||||
esac
|
||||
@@ -1,6 +1,6 @@
|
||||
#!/bin/bash
|
||||
# pr-merge.sh - Merge pull requests on Gitea or GitHub
|
||||
# Usage: pr-merge.sh -n PR_NUMBER [-m squash] [-d] [--expect-head SHA] [--co-author-trailers --escalate-to PRINCIPAL]
|
||||
# Usage: pr-merge.sh -n PR_NUMBER [-m squash] [-d] [--skip-queue-guard]
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
@@ -12,10 +12,8 @@ source "$SCRIPT_DIR/detect-platform.sh"
|
||||
PR_NUMBER=""
|
||||
MERGE_METHOD="squash"
|
||||
DELETE_BRANCH=false
|
||||
SKIP_QUEUE_GUARD=false
|
||||
DRY_RUN=false
|
||||
EXPECT_HEAD=""
|
||||
CO_AUTHOR_TRAILERS=false
|
||||
ESCALATE_TO=""
|
||||
|
||||
usage() {
|
||||
cat <<EOF
|
||||
@@ -27,18 +25,15 @@ Options:
|
||||
-n, --number NUMBER PR number to merge (required)
|
||||
-m, --method METHOD Merge method: squash only (default: squash)
|
||||
-d, --delete-branch Delete the head branch after merge
|
||||
--skip-queue-guard Skip CI queue guard wait before merge
|
||||
--dry-run Run metadata/login preflight without merging
|
||||
--expect-head SHA Refuse unless the PR head matches this full commit SHA
|
||||
--co-author-trailers Build verified trailers from linked PR commit authors
|
||||
--escalate-to NAME Named principal for an unresolved-author BLOCK
|
||||
-h, --help Show this help message
|
||||
|
||||
Examples:
|
||||
$(basename "$0") -n 42 # Merge PR #42
|
||||
$(basename "$0") -n 42 -m squash # Squash merge
|
||||
$(basename "$0") -n 42 -d # Squash merge and delete branch
|
||||
$(basename "$0") -n 42 --expect-head 0123456789abcdef0123456789abcdef01234567
|
||||
$(basename "$0") -n 42 --co-author-trailers --escalate-to tl-mosaic
|
||||
$(basename "$0") -n 42 --skip-queue-guard # Skip queue guard wait
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
}
|
||||
@@ -58,30 +53,15 @@ while [[ $# -gt 0 ]]; do
|
||||
DELETE_BRANCH=true
|
||||
shift
|
||||
;;
|
||||
--skip-queue-guard)
|
||||
SKIP_QUEUE_GUARD=true
|
||||
shift
|
||||
;;
|
||||
--dry-run)
|
||||
DRY_RUN=true
|
||||
SKIP_QUEUE_GUARD=true
|
||||
shift
|
||||
;;
|
||||
--expect-head)
|
||||
if [[ $# -lt 2 ]]; then
|
||||
echo "Error: --expect-head requires one full commit SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
EXPECT_HEAD="$2"
|
||||
shift 2
|
||||
;;
|
||||
--co-author-trailers)
|
||||
CO_AUTHOR_TRAILERS=true
|
||||
shift
|
||||
;;
|
||||
--escalate-to)
|
||||
if [[ $# -lt 2 ]]; then
|
||||
echo "Error: --escalate-to requires one principal name." >&2
|
||||
exit 1
|
||||
fi
|
||||
ESCALATE_TO="$2"
|
||||
shift 2
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
;;
|
||||
@@ -106,49 +86,18 @@ if [[ "$MERGE_METHOD" != "squash" ]]; then
|
||||
echo "Error: Mosaic policy enforces squash merge only. Received '$MERGE_METHOD'." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$EXPECT_HEAD" && ! "$EXPECT_HEAD" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
||||
echo "Error: --expect-head must be a full 40-character hexadecimal commit SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$CO_AUTHOR_TRAILERS" == true && -z "$ESCALATE_TO" ]]; then
|
||||
echo "Error: --co-author-trailers requires --escalate-to with a named principal." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$ESCALATE_TO" && ! "$ESCALATE_TO" =~ ^[A-Za-z0-9_.-]+$ ]]; then
|
||||
echo "Error: --escalate-to must be one exact principal name." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$CO_AUTHOR_TRAILERS" != true && -n "$ESCALATE_TO" ]]; then
|
||||
echo "Error: --escalate-to is valid only with --co-author-trailers." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
PR_METADATA="$("$SCRIPT_DIR/pr-metadata.sh" -n "$PR_NUMBER")"
|
||||
BASE_BRANCH="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("baseRefName") or "").strip())')"
|
||||
HEAD_BRANCH="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("headRefName") or "").strip())')"
|
||||
HEAD_SHA="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("headRefOid") or "").strip())')"
|
||||
HEAD_REPO="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; value=json.load(sys.stdin).get("headRepository") or ""; print((value.get("nameWithOwner") or value.get("full_name") or "") if isinstance(value, dict) else str(value).strip())')"
|
||||
PR_TITLE="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("title") or "").strip())')"
|
||||
PR_AUTHOR="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; value=json.load(sys.stdin).get("author") or ""; print((value.get("login") or "").strip() if isinstance(value, dict) else str(value).strip())')"
|
||||
if [[ "$BASE_BRANCH" != "main" ]]; then
|
||||
echo "Error: Mosaic policy allows merges only for PRs targeting 'main' (found '$BASE_BRANCH')." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -z "$HEAD_BRANCH" || -z "$HEAD_REPO" || ! "$HEAD_SHA" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
||||
echo "Error: Could not resolve the PR head branch, repository, and full commit SHA for queue inspection." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$EXPECT_HEAD" && "$HEAD_SHA" != "$EXPECT_HEAD" ]]; then
|
||||
echo "Error: PR head moved: expected $EXPECT_HEAD, found $HEAD_SHA." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [[ "$DRY_RUN" != true ]]; then
|
||||
if [[ "$SKIP_QUEUE_GUARD" != true ]]; then
|
||||
"$SCRIPT_DIR/ci-queue-wait.sh" \
|
||||
--purpose merge \
|
||||
-B "$HEAD_BRANCH" \
|
||||
-R "$HEAD_REPO" \
|
||||
--sha "$HEAD_SHA" \
|
||||
-B "$BASE_BRANCH" \
|
||||
-t "${MOSAIC_CI_QUEUE_TIMEOUT_SEC:-900}" \
|
||||
-i "${MOSAIC_CI_QUEUE_POLL_SEC:-15}"
|
||||
fi
|
||||
@@ -157,442 +106,79 @@ PLATFORM=$(detect_platform)
|
||||
OWNER=$(get_repo_owner)
|
||||
REPO=$(get_repo_name)
|
||||
|
||||
write_curl_auth_config() {
|
||||
local mode="$1" credential="$2"
|
||||
printf '%s' "$credential" | python3 -c '
|
||||
import sys
|
||||
mode = sys.argv[1]
|
||||
credential = sys.stdin.read()
|
||||
if not credential or any(char in credential for char in "\r\n"):
|
||||
raise SystemExit(1)
|
||||
escaped = credential.replace("\\", "\\\\").replace("\"", "\\\"")
|
||||
if mode == "token":
|
||||
print(f"header = \"Authorization: token {escaped}\"")
|
||||
elif mode == "basic":
|
||||
print(f"user = \"{escaped}\"")
|
||||
else:
|
||||
raise SystemExit(1)
|
||||
' "$mode"
|
||||
}
|
||||
is_known_tea_empty_identity_failure() {
|
||||
local error_file="$1"
|
||||
|
||||
LAST_GITEA_HTTP_CODE="000"
|
||||
LAST_GITEA_ERROR=""
|
||||
MERGE_TEMP_DIRS=()
|
||||
GITEA_CURL_MAX_BYTES="${MOSAIC_GITEA_CURL_MAX_BYTES:-1048576}"
|
||||
GITEA_CURL_MAX_TIME="${MOSAIC_GITEA_CURL_MAX_TIME_SEC:-30}"
|
||||
GITEA_CURL_CONNECT_TIMEOUT="${MOSAIC_GITEA_CURL_CONNECT_TIMEOUT_SEC:-10}"
|
||||
for bound in "$GITEA_CURL_MAX_BYTES" "$GITEA_CURL_MAX_TIME" "$GITEA_CURL_CONNECT_TIMEOUT"; do
|
||||
if [[ ! "$bound" =~ ^[1-9][0-9]*$ ]]; then
|
||||
echo "Error: Gitea curl bounds must be positive integers; refusing request." >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
GITEA_CURL_BOUNDS=(
|
||||
--max-filesize "$GITEA_CURL_MAX_BYTES"
|
||||
--max-time "$GITEA_CURL_MAX_TIME"
|
||||
--connect-timeout "$GITEA_CURL_CONNECT_TIMEOUT"
|
||||
python3 - "$error_file" <<'PY'
|
||||
import re
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8", errors="replace") as handle:
|
||||
error = handle.read()
|
||||
|
||||
known_empty_identity = re.search(
|
||||
r"user does not exist.*\[.*uid:\s*0,\s*name:\s*\]",
|
||||
error,
|
||||
flags=re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
|
||||
format_gitea_error_response() {
|
||||
local response_file="$1"
|
||||
python3 - "$response_file" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], "rb") as handle:
|
||||
raw = handle.read(65536)
|
||||
try:
|
||||
response = json.loads(raw.decode("utf-8", errors="replace"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
message = "non-JSON response omitted"
|
||||
else:
|
||||
if isinstance(response, dict):
|
||||
message = response.get("message") or response.get("error")
|
||||
if not message and response.get("errors") is not None:
|
||||
message = json.dumps(response["errors"], separators=(",", ":"))
|
||||
else:
|
||||
message = None
|
||||
if not message:
|
||||
message = "JSON response contained no error message"
|
||||
message = str(message)
|
||||
if len(message) > 500:
|
||||
message = message[:500] + "..."
|
||||
print(ascii(message))
|
||||
raise SystemExit(0 if known_empty_identity else 1)
|
||||
PY
|
||||
}
|
||||
|
||||
cleanup_merge_temp_dirs() {
|
||||
local path
|
||||
for path in "${MERGE_TEMP_DIRS[@]}"; do
|
||||
[[ -n "$path" ]] && rm -rf -- "$path"
|
||||
done
|
||||
}
|
||||
trap cleanup_merge_temp_dirs EXIT
|
||||
trap 'exit 130' INT
|
||||
trap 'exit 143' TERM
|
||||
|
||||
fetch_gitea_pr_head() {
|
||||
local host="$1" auth_mode="$2" credential="$3" work_root="$4"
|
||||
local response_file raw_code api_url auth_config curl_rc
|
||||
response_file=$(mktemp "$work_root/pr-merge-pr.XXXXXX")
|
||||
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}"
|
||||
if ! auth_config=$(write_curl_auth_config "$auth_mode" "$credential"); then
|
||||
echo "Error: Could not construct Gitea authentication config; refusing request." >&2
|
||||
rm -f "$response_file"
|
||||
return 1
|
||||
fi
|
||||
raw_code=$(curl -sS -K - "${GITEA_CURL_BOUNDS[@]}" -w '%{http_code}' -o "$response_file" \
|
||||
-H "User-Agent: curl/8" "$api_url" <<<"$auth_config")
|
||||
curl_rc=$?
|
||||
LAST_GITEA_HTTP_CODE="${raw_code:-000}"
|
||||
if [[ "$curl_rc" -ne 0 ]]; then
|
||||
LAST_GITEA_ERROR="curl transport failed (rc=$curl_rc)"
|
||||
rm -f "$response_file"
|
||||
return 1
|
||||
fi
|
||||
if [[ ! "$raw_code" =~ ^2 ]]; then
|
||||
LAST_GITEA_ERROR=$(format_gitea_error_response "$response_file")
|
||||
rm -f "$response_file"
|
||||
return 1
|
||||
fi
|
||||
if ! python3 - "$response_file" <<'PY'
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
||||
pull = json.load(handle)
|
||||
head = pull.get("head") if isinstance(pull, dict) else None
|
||||
sha = str(head.get("sha") or "") if isinstance(head, dict) else ""
|
||||
if not re.fullmatch(r"[0-9a-fA-F]{40}", sha):
|
||||
raise SystemExit(1)
|
||||
print(sha)
|
||||
PY
|
||||
then
|
||||
echo "Error: Gitea PR response has no valid head SHA; refusing merge." >&2
|
||||
rm -f "$response_file"
|
||||
return 1
|
||||
fi
|
||||
rm -f "$response_file"
|
||||
}
|
||||
|
||||
fetch_gitea_pr_commits() {
|
||||
local host="$1" auth_mode="$2" credential="$3" work_root="$4"
|
||||
local page page_file combined_file merged_file raw_code page_count api_url auth_config curl_rc
|
||||
mkdir -p "$work_root"
|
||||
if ! auth_config=$(write_curl_auth_config "$auth_mode" "$credential"); then
|
||||
echo "Error: Could not construct Gitea authentication config; refusing request." >&2
|
||||
return 1
|
||||
fi
|
||||
combined_file=$(mktemp "$work_root/pr-merge-commits.XXXXXX")
|
||||
printf '[]' > "$combined_file"
|
||||
|
||||
page=1
|
||||
while true; do
|
||||
page_file=$(mktemp "$work_root/pr-merge-commits-page.XXXXXX")
|
||||
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/commits?limit=50&page=${page}"
|
||||
raw_code=$(curl -sS -K - "${GITEA_CURL_BOUNDS[@]}" -w '%{http_code}' -o "$page_file" \
|
||||
-H "User-Agent: curl/8" "$api_url" <<<"$auth_config")
|
||||
curl_rc=$?
|
||||
LAST_GITEA_HTTP_CODE="${raw_code:-000}"
|
||||
if [[ "$curl_rc" -ne 0 ]]; then
|
||||
LAST_GITEA_ERROR="curl transport failed (rc=$curl_rc)"
|
||||
rm -f "$page_file" "$combined_file"
|
||||
return 1
|
||||
fi
|
||||
if [[ ! "$raw_code" =~ ^2 ]]; then
|
||||
LAST_GITEA_ERROR=$(format_gitea_error_response "$page_file")
|
||||
rm -f "$page_file" "$combined_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
if ! page_count=$(python3 - "$page_file" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
||||
page = json.load(handle)
|
||||
if not isinstance(page, list):
|
||||
raise SystemExit(1)
|
||||
print(len(page))
|
||||
PY
|
||||
); then
|
||||
echo "Error: Gitea PR commits response is not a JSON array; refusing merge." >&2
|
||||
rm -f "$page_file" "$combined_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
merged_file=$(mktemp "$work_root/pr-merge-commits-merged.XXXXXX")
|
||||
if ! python3 - "$combined_file" "$page_file" > "$merged_file" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
||||
combined = json.load(handle)
|
||||
with open(sys.argv[2], encoding="utf-8") as handle:
|
||||
page = json.load(handle)
|
||||
json.dump(combined + page, sys.stdout, separators=(",", ":"))
|
||||
PY
|
||||
then
|
||||
echo "Error: Could not combine paginated PR commit metadata; refusing merge." >&2
|
||||
rm -f "$page_file" "$combined_file" "$merged_file"
|
||||
return 1
|
||||
fi
|
||||
mv "$merged_file" "$combined_file"
|
||||
rm -f "$page_file"
|
||||
|
||||
if [[ "$page_count" -lt 50 ]]; then
|
||||
break
|
||||
fi
|
||||
page=$((page + 1))
|
||||
if [[ "$page" -gt 1000 ]]; then
|
||||
echo "Error: PR commit pagination exceeded 1000 pages; refusing merge." >&2
|
||||
rm -f "$combined_file"
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
|
||||
cat "$combined_file"
|
||||
rm -f "$combined_file"
|
||||
}
|
||||
|
||||
# LIMITATION: author.login resolution proves the commit address maps to a registered account.
|
||||
# It does NOT prove the named principal authored the commit — git author metadata is self-asserted.
|
||||
# This gate checks ATTRIBUTION LINKAGE, not AUTHORSHIP. Commit signing is out of scope and unadopted.
|
||||
build_coauthor_message_fields() {
|
||||
local commits_file="$1" context_file="$2" head_file="$3"
|
||||
python3 - "$commits_file" "$context_file" "$head_file" <<'PY'
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
|
||||
commits_path, context_path, head_path = sys.argv[1:]
|
||||
with open(commits_path, encoding="utf-8") as handle:
|
||||
commits = json.load(handle)
|
||||
head_sha = open(head_path, encoding="utf-8").read().strip()
|
||||
context_parts = open(context_path, "rb").read().split(b"\0")
|
||||
if len(context_parts) != 4 or context_parts[-1] != b"":
|
||||
raise SystemExit(1)
|
||||
poster, title, principal = (part.decode("utf-8") for part in context_parts[:3])
|
||||
|
||||
if not isinstance(commits, list) or not commits:
|
||||
print(
|
||||
f"BLOCK: provider returned no PR commits; author identity is unmeasurable. "
|
||||
f"Refusing merge; escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
if not poster:
|
||||
print(
|
||||
f"BLOCK: PR poster login is empty; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
|
||||
if not re.fullmatch(r"[0-9a-fA-F]{40}", head_sha):
|
||||
print(
|
||||
f"BLOCK: inspected PR head SHA is invalid; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
|
||||
seen = set()
|
||||
trailers = []
|
||||
head_seen = False
|
||||
for item in commits:
|
||||
if not isinstance(item, dict):
|
||||
print(f"BLOCK: malformed PR commit metadata; escalate to named principal '{principal}'.", file=sys.stderr)
|
||||
raise SystemExit(75)
|
||||
sha = str(item.get("sha") or "<unknown>")
|
||||
if sha == head_sha:
|
||||
head_seen = True
|
||||
commit = item.get("commit") if isinstance(item.get("commit"), dict) else {}
|
||||
commit_author = commit.get("author") if isinstance(commit.get("author"), dict) else {}
|
||||
email = str(commit_author.get("email") or "").strip()
|
||||
provider_author = item.get("author") if isinstance(item.get("author"), dict) else {}
|
||||
login = str(provider_author.get("login") or "").strip()
|
||||
|
||||
if not login:
|
||||
diagnostic_email = email or "<missing>"
|
||||
print(
|
||||
f"BLOCK: commit {sha!r} has author.login=NULL while "
|
||||
f"commit.author.email={diagnostic_email!r}; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
if (
|
||||
not email.isascii()
|
||||
or not email.isprintable()
|
||||
or not re.fullmatch(r"[A-Za-z0-9_.-]+", login)
|
||||
or not re.fullmatch(r"[^<>\s]+@[^<>\s]+", email)
|
||||
):
|
||||
print(
|
||||
f"BLOCK: commit {sha!r} has unusable linked identity "
|
||||
f"author.login={login!r}, commit.author.email={email!r}; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
if login == poster or login in seen:
|
||||
continue
|
||||
seen.add(login)
|
||||
trailers.append(f"Co-authored-by: {login} <{email}>")
|
||||
|
||||
if not head_seen:
|
||||
print(
|
||||
f"BLOCK: inspected PR head is absent from commit enumeration; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
if not trailers:
|
||||
print("{}")
|
||||
raise SystemExit(0)
|
||||
if not title:
|
||||
print(
|
||||
f"BLOCK: PR title is empty; refusing merge; escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
if not title.isprintable() or re.match(r"^[A-Za-z-]+-[Bb]y:", title):
|
||||
print(
|
||||
f"BLOCK: PR title is not one printable, non-trailer line; refusing merge; "
|
||||
f"escalate to named principal '{principal}'.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(75)
|
||||
|
||||
print(json.dumps({
|
||||
"MergeTitleField": title,
|
||||
"MergeMessageField": "\n".join(trailers),
|
||||
}, separators=(",", ":")))
|
||||
PY
|
||||
}
|
||||
|
||||
merge_gitea_api_attempt() {
|
||||
local host="$1" auth_mode="$2" credential="$3"
|
||||
local api_url attempt_dir body_file raw_code commits_file fields_file context_file head_file payload_file work_root attempt_rc auth_config curl_rc
|
||||
LAST_GITEA_HTTP_CODE="000"
|
||||
LAST_GITEA_ERROR=""
|
||||
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
|
||||
work_root="${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
||||
mkdir -p "$work_root"
|
||||
attempt_dir=$(mktemp -d "$work_root/pr-merge-attempt.XXXXXX")
|
||||
chmod 0700 "$attempt_dir"
|
||||
MERGE_TEMP_DIRS+=("$attempt_dir")
|
||||
body_file=$(mktemp "$attempt_dir/api-response.XXXXXX")
|
||||
fields_file=$(mktemp "$attempt_dir/message-fields.XXXXXX")
|
||||
payload_file=$(mktemp "$attempt_dir/payload.XXXXXX")
|
||||
printf '{}' > "$fields_file"
|
||||
|
||||
if [[ "$CO_AUTHOR_TRAILERS" == true ]]; then
|
||||
commits_file=$(mktemp "$attempt_dir/pr-merge-commits-input.XXXXXX")
|
||||
context_file=$(mktemp "$attempt_dir/pr-merge-message-context.XXXXXX")
|
||||
head_file=$(mktemp "$attempt_dir/pr-merge-head-input.XXXXXX")
|
||||
printf '%s\0%s\0%s\0' "$PR_AUTHOR" "$PR_TITLE" "$ESCALATE_TO" > "$context_file"
|
||||
if fetch_gitea_pr_head "$host" "$auth_mode" "$credential" "$attempt_dir" > "$head_file"; then
|
||||
:
|
||||
else
|
||||
attempt_rc=$?
|
||||
rm -f "$body_file" "$fields_file" "$payload_file" "$commits_file" "$context_file" "$head_file"
|
||||
return "$attempt_rc"
|
||||
fi
|
||||
if [[ "$(<"$head_file")" != "$HEAD_SHA" ]]; then
|
||||
echo "BLOCK: authenticated PR head moved from reviewed $HEAD_SHA to $(<"$head_file"); refusing merge; escalate to named principal '$ESCALATE_TO'." >&2
|
||||
rm -f "$body_file" "$fields_file" "$payload_file" "$commits_file" "$context_file" "$head_file"
|
||||
return 75
|
||||
fi
|
||||
if fetch_gitea_pr_commits "$host" "$auth_mode" "$credential" "$attempt_dir" > "$commits_file"; then
|
||||
:
|
||||
else
|
||||
attempt_rc=$?
|
||||
rm -f "$body_file" "$fields_file" "$payload_file" "$commits_file" "$context_file" "$head_file"
|
||||
return "$attempt_rc"
|
||||
fi
|
||||
if build_coauthor_message_fields "$commits_file" "$context_file" "$head_file" > "$fields_file"; then
|
||||
:
|
||||
else
|
||||
attempt_rc=$?
|
||||
rm -f "$body_file" "$fields_file" "$payload_file" "$commits_file" "$context_file" "$head_file"
|
||||
return "$attempt_rc"
|
||||
fi
|
||||
rm -f "$commits_file" "$context_file" "$head_file"
|
||||
fi
|
||||
|
||||
if ! python3 - "$fields_file" "$HEAD_SHA" "$DELETE_BRANCH" > "$payload_file" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
|
||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
||||
fields = json.load(handle)
|
||||
head_sha, delete_branch = sys.argv[2:]
|
||||
payload = {"Do": "squash", "head_commit_id": head_sha}
|
||||
if delete_branch == "true":
|
||||
payload["delete_branch_after_merge"] = True
|
||||
payload.update(fields)
|
||||
allowed = {"Do", "head_commit_id", "delete_branch_after_merge", "MergeTitleField", "MergeMessageField"}
|
||||
if payload.get("Do") != "squash" or set(payload) - allowed:
|
||||
raise SystemExit(1)
|
||||
print(json.dumps(payload, separators=(",", ":")))
|
||||
PY
|
||||
then
|
||||
rm -f "$body_file" "$fields_file" "$payload_file"
|
||||
return 1
|
||||
fi
|
||||
rm -f "$fields_file"
|
||||
|
||||
if ! auth_config=$(write_curl_auth_config "$auth_mode" "$credential"); then
|
||||
echo "Error: Could not construct Gitea authentication config; refusing request." >&2
|
||||
rm -f "$body_file" "$payload_file"
|
||||
return 1
|
||||
fi
|
||||
raw_code=$(curl -sS -K - "${GITEA_CURL_BOUNDS[@]}" -w '%{http_code}' -o "$body_file" \
|
||||
-X POST -H "User-Agent: curl/8" \
|
||||
-H 'Content-Type: application/json' \
|
||||
--data-binary "@$payload_file" "$api_url" <<<"$auth_config")
|
||||
curl_rc=$?
|
||||
LAST_GITEA_HTTP_CODE="${raw_code:-000}"
|
||||
if [[ "$curl_rc" -ne 0 ]]; then
|
||||
LAST_GITEA_ERROR="curl transport failed (rc=$curl_rc)"
|
||||
rm -f "$body_file" "$payload_file"
|
||||
rm -rf -- "$attempt_dir"
|
||||
return 1
|
||||
fi
|
||||
if [[ ! "$raw_code" =~ ^2 ]]; then
|
||||
LAST_GITEA_ERROR=$(format_gitea_error_response "$body_file")
|
||||
fi
|
||||
rm -f "$body_file" "$payload_file"
|
||||
rm -rf -- "$attempt_dir"
|
||||
[[ "$raw_code" =~ ^2 ]]
|
||||
}
|
||||
|
||||
merge_gitea_with_api() {
|
||||
local host="$1" token attempt_rc
|
||||
local host="$1" api_url token basic_auth body_file raw_code payload
|
||||
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
|
||||
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
||||
body_file=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-api-response.XXXXXX")
|
||||
payload='{"Do":"squash"}'
|
||||
|
||||
if ! token=$(get_gitea_token "$host"); then
|
||||
echo "Error: Could not resolve the required Gitea token; refusing merge without changing principals." >&2
|
||||
return 1
|
||||
token=$(get_gitea_token "$host" || true)
|
||||
if [[ -n "$token" ]]; then
|
||||
raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" \
|
||||
-X POST \
|
||||
-H "User-Agent: curl/8" \
|
||||
-H "Authorization: token $token" \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d "$payload" \
|
||||
"$api_url" || true)
|
||||
if [[ "$raw_code" =~ ^2 ]]; then
|
||||
rm -f "$body_file"
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
if [[ -z "$token" ]]; then
|
||||
echo "Error: Required Gitea token resolved empty; refusing merge without changing principals." >&2
|
||||
return 1
|
||||
|
||||
basic_auth=$(get_gitea_basic_auth "$host" || true)
|
||||
if [[ -n "$basic_auth" ]]; then
|
||||
raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" \
|
||||
-X POST \
|
||||
-u "$basic_auth" \
|
||||
-H "User-Agent: curl/8" \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d "$payload" \
|
||||
"$api_url" || true)
|
||||
if [[ "$raw_code" =~ ^2 ]]; then
|
||||
rm -f "$body_file"
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
if merge_gitea_api_attempt "$host" token "$token"; then
|
||||
return 0
|
||||
else
|
||||
attempt_rc=$?
|
||||
fi
|
||||
if [[ "$attempt_rc" -eq 75 ]]; then
|
||||
return 75
|
||||
fi
|
||||
if [[ "$LAST_GITEA_HTTP_CODE" != "401" ]]; then
|
||||
echo "Error: Gitea API merge failed with the identity-bound token (HTTP ${LAST_GITEA_HTTP_CODE:-000}).${LAST_GITEA_ERROR:+ Provider response: $LAST_GITEA_ERROR}" >&2
|
||||
return 1
|
||||
fi
|
||||
echo "Error: Gitea API rejected the identity-bound token with HTTP 401; refusing cross-principal credential fallback." >&2
|
||||
|
||||
python3 - "${raw_code:-000}" "$body_file" <<'PY' >&2
|
||||
import json
|
||||
import sys
|
||||
code, path = sys.argv[1], sys.argv[2]
|
||||
try:
|
||||
with open(path, encoding="utf-8", errors="replace") as handle:
|
||||
raw = handle.read(500)
|
||||
data = json.loads(raw) if raw else {}
|
||||
message = data.get("message") or data.get("error") or raw or "empty response"
|
||||
except Exception:
|
||||
try:
|
||||
message = open(path, encoding="utf-8", errors="replace").read(500) or "empty response"
|
||||
except Exception:
|
||||
message = "unreadable response"
|
||||
print(f"Error: Gitea API merge failed with HTTP {code}: {message}")
|
||||
PY
|
||||
rm -f "$body_file"
|
||||
return 1
|
||||
}
|
||||
|
||||
@@ -602,10 +188,11 @@ if [[ "$DRY_RUN" == true ]]; then
|
||||
echo "Error: Cannot determine host from origin remote URL" >&2
|
||||
exit 1
|
||||
}
|
||||
if [[ "$CO_AUTHOR_TRAILERS" == true ]]; then
|
||||
echo "Dry run: would verify PR commit authors and merge PR #$PR_NUMBER on $HOST with authenticated Gitea API message fields (base=$BASE_BRANCH, method=squash)."
|
||||
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
|
||||
if [[ -n "$TEA_LOGIN" ]]; then
|
||||
echo "Dry run: would merge PR #$PR_NUMBER on $HOST with tea login '$TEA_LOGIN' (base=$BASE_BRANCH, method=squash)."
|
||||
else
|
||||
echo "Dry run: would merge PR #$PR_NUMBER on $HOST with the authenticated exact-head Gitea API path (base=$BASE_BRANCH, method=squash)."
|
||||
echo "Dry run: would merge PR #$PR_NUMBER on $HOST with authenticated Gitea API fallback (base=$BASE_BRANCH, method=squash)."
|
||||
fi
|
||||
else
|
||||
echo "Dry run: would merge PR #$PR_NUMBER on $PLATFORM (base=$BASE_BRANCH, method=squash)."
|
||||
@@ -615,11 +202,7 @@ fi
|
||||
|
||||
case "$PLATFORM" in
|
||||
github)
|
||||
if [[ "$CO_AUTHOR_TRAILERS" == true ]]; then
|
||||
echo "Error: --co-author-trailers currently requires the Gitea REST message-field contract." >&2
|
||||
exit 1
|
||||
fi
|
||||
cmd=(gh pr merge "$PR_NUMBER" --squash --match-head-commit "$HEAD_SHA")
|
||||
cmd=(gh pr merge "$PR_NUMBER" --squash)
|
||||
[[ "$DELETE_BRANCH" == true ]] && cmd+=(--delete-branch)
|
||||
"${cmd[@]}"
|
||||
;;
|
||||
@@ -628,9 +211,32 @@ case "$PLATFORM" in
|
||||
echo "Error: Cannot determine host from origin remote URL" >&2
|
||||
exit 1
|
||||
}
|
||||
# Gitea's API head_commit_id is an atomic compare-and-merge precondition.
|
||||
# tea cannot express it, so every Gitea merge uses the authenticated API path.
|
||||
merge_gitea_with_api "$HOST"
|
||||
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
|
||||
|
||||
if [[ -n "$TEA_LOGIN" ]]; then
|
||||
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
||||
TEA_ERROR_FILE=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-tea-error.XXXXXX")
|
||||
if tea pr merge "$PR_NUMBER" --style squash --repo "$OWNER/$REPO" --login "$TEA_LOGIN" 2> "$TEA_ERROR_FILE"; then
|
||||
rm -f "$TEA_ERROR_FILE"
|
||||
elif is_known_tea_empty_identity_failure "$TEA_ERROR_FILE"; then
|
||||
cat "$TEA_ERROR_FILE" >&2
|
||||
echo "Known tea empty identity failure detected; using authenticated Gitea API merge fallback." >&2
|
||||
rm -f "$TEA_ERROR_FILE"
|
||||
merge_gitea_with_api "$HOST"
|
||||
else
|
||||
cat "$TEA_ERROR_FILE" >&2
|
||||
rm -f "$TEA_ERROR_FILE"
|
||||
exit 1
|
||||
fi
|
||||
else
|
||||
echo "No tea login configured for $HOST; using authenticated Gitea API merge fallback." >&2
|
||||
merge_gitea_with_api "$HOST"
|
||||
fi
|
||||
|
||||
# Delete branch after merge if requested
|
||||
if [[ "$DELETE_BRANCH" == true ]]; then
|
||||
echo "Note: Branch deletion after merge may need to be done separately with tea" >&2
|
||||
fi
|
||||
;;
|
||||
*)
|
||||
echo "Error: Could not detect git platform" >&2
|
||||
|
||||
@@ -109,7 +109,7 @@ PY
|
||||
detect_platform > /dev/null
|
||||
|
||||
if [[ "$PLATFORM" == "github" ]]; then
|
||||
METADATA=$(gh pr view "$PR_NUMBER" --json number,title,body,state,author,headRefName,headRefOid,headRepository,baseRefName,files,labels,assignees,milestone,createdAt,updatedAt,url,isDraft)
|
||||
METADATA=$(gh pr view "$PR_NUMBER" --json number,title,body,state,author,headRefName,baseRefName,files,labels,assignees,milestone,createdAt,updatedAt,url,isDraft)
|
||||
write_metadata "$METADATA"
|
||||
elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
OWNER=$(get_repo_owner)
|
||||
@@ -182,25 +182,6 @@ if isinstance(head_ref, str) and head_ref.startswith('refs/pull/'):
|
||||
data.get('head_ref'),
|
||||
head_ref,
|
||||
)
|
||||
head_sha = first_non_empty(
|
||||
nested(data, 'head', 'sha'),
|
||||
nested(data, 'head', 'id'),
|
||||
data.get('head_sha'),
|
||||
)
|
||||
head_repo = first_non_empty(
|
||||
nested(data, 'head', 'repo', 'full_name'),
|
||||
nested(data, 'head', 'repo', 'name_with_owner'),
|
||||
)
|
||||
if not head_repo:
|
||||
head_repo_owner = first_non_empty(
|
||||
nested(data, 'head', 'repo', 'owner', 'login'),
|
||||
nested(data, 'head', 'repo', 'owner', 'username'),
|
||||
nested(data, 'head', 'repo', 'owner_name'),
|
||||
)
|
||||
head_repo_name = first_non_empty(nested(data, 'head', 'repo', 'name'))
|
||||
if head_repo_owner and head_repo_name:
|
||||
head_repo = f'{head_repo_owner}/{head_repo_name}'
|
||||
|
||||
base_ref = first_non_empty(
|
||||
nested(data, 'base', 'ref'),
|
||||
nested(data, 'base', 'name'),
|
||||
@@ -226,8 +207,6 @@ normalized = {
|
||||
'state': data.get('state'),
|
||||
'author': nested(data, 'user', 'login') or '',
|
||||
'headRefName': head_ref,
|
||||
'headRefOid': head_sha,
|
||||
'headRepository': head_repo,
|
||||
'baseRefName': base_ref,
|
||||
'labels': [l.get('name', '') for l in data.get('labels', []) if isinstance(l, dict)],
|
||||
'assignees': [a.get('login', '') for a in data.get('assignees', []) if isinstance(a, dict)],
|
||||
|
||||
@@ -243,35 +243,15 @@ from urllib.parse import urlparse
|
||||
|
||||
|
||||
def _origin_and_path(url):
|
||||
# Normalize a URL to (scheme-class, host, distinguishing-port) + comment path.
|
||||
#
|
||||
# #991: http and https collapse into ONE scheme class ("web"). A Gitea whose
|
||||
# ROOT_URL is configured http:// returns http:// object URLs even when every
|
||||
# client reaches it over https://, so a scheme-strict comparison rejects the
|
||||
# provider's own correct answer about a comment that landed — a deterministic
|
||||
# false negative on EVERY review comment posted against such a deployment.
|
||||
# That matters more here than anywhere else: on a host where no seat can
|
||||
# create a review OBJECT, the comment-form review record this path produces
|
||||
# is the only gate-16 evidence available, and this check refuses all of it.
|
||||
# The scheme is also not what the check defends: the forgeries it exists to
|
||||
# catch (look-alike host, decoy path prefix, wrong owner/repo/kind/number)
|
||||
# all vary the HOST or the PATH, both of which stay strict below. Any OTHER
|
||||
# scheme (file:, ftp:, javascript:) remains distinguishing and is rejected.
|
||||
#
|
||||
# Port: an implicit port and its own scheme's default compare equal, so
|
||||
# http://h == https://h. An EXPLICIT non-default port still distinguishes,
|
||||
# because a different port is a different service on the same host.
|
||||
# Normalize a URL to (scheme, host, effective-port) + comment path. The port
|
||||
# defaults to the scheme's default (80 http / 443 otherwise) so an implicit
|
||||
# port and its explicit default form compare equal.
|
||||
parsed = urlparse(url or "")
|
||||
scheme = (parsed.scheme or "").lower()
|
||||
host = (parsed.hostname or "").lower()
|
||||
if scheme in ("http", "https"):
|
||||
scheme_class = "web"
|
||||
default_port = 80 if scheme == "http" else 443
|
||||
port = None if parsed.port in (None, default_port) else parsed.port
|
||||
else:
|
||||
scheme_class = scheme
|
||||
port = parsed.port
|
||||
return (scheme_class, host, port), parsed.path.rstrip("/")
|
||||
default_port = 80 if scheme == "http" else 443
|
||||
port = parsed.port if parsed.port is not None else default_port
|
||||
return (scheme, host, port), parsed.path.rstrip("/")
|
||||
|
||||
|
||||
try:
|
||||
|
||||
@@ -13,7 +13,7 @@
|
||||
# Covers:
|
||||
# (a) 404 branch-absent -> exit 0, "queue clear" message.
|
||||
# (b) 200 existing branch + a terminal CI state -> unchanged behavior.
|
||||
# (c) genuine API error (500) -> loud, audited CANNOT_ASSERT; degraded exit 0.
|
||||
# (c) genuine API error (500) -> still fail-closed (nonzero exit).
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
@@ -62,7 +62,7 @@ case "$mode" in
|
||||
200) code=200; body='{"commit":{"id":"deadbeefcafef00d0123456789abcdef01234567"}}' ;;
|
||||
500) code=500; body='{"message":"internal server error"}' ;;
|
||||
no-status) code=200; body='{}' ;;
|
||||
terminal-success) code=200; body='{"state":"success","statuses":[{"status":"success"}]}' ;;
|
||||
terminal-success) code=200; body='{"state":"success"}' ;;
|
||||
*)
|
||||
echo "curl stub: unknown mode=$mode" >&2
|
||||
exit 2
|
||||
@@ -91,7 +91,6 @@ run_ci_queue_wait() {
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
export GITEA_TOKEN="stub-token"
|
||||
export GITEA_URL="https://git.example.test"
|
||||
export MOSAIC_CI_QUEUE_AUDIT_LOG="$WORK_DIR/audit/ci-queue-wait.jsonl"
|
||||
"$SCRIPT_DIR/ci-queue-wait.sh" -B "$branch" --purpose push -t 5 -i 1
|
||||
)
|
||||
}
|
||||
@@ -132,26 +131,19 @@ elif [[ "$out_b" == *"queue clear"* ]]; then
|
||||
fail=1
|
||||
fi
|
||||
|
||||
# (c) genuine API error (500) -> CANNOT_ASSERT is loud and audited, but does not brick delivery.
|
||||
# (c) genuine API error (500) -> still fail-closed, exit nonzero.
|
||||
set +e
|
||||
out_c=$(MOSAIC_STUB_BRANCH_MODE=500 run_ci_queue_wait "feat/some-branch" 2>&1)
|
||||
status_c=$?
|
||||
set -e
|
||||
if [[ "$status_c" -ne 0 ]]; then
|
||||
echo "FAIL(c): expected degraded exit 0 for provider unavailability, got $status_c" >&2
|
||||
echo "$out_c" >&2
|
||||
fail=1
|
||||
elif [[ "$out_c" != *"CANNOT_ASSERT"* ]]; then
|
||||
echo "FAIL(c): expected a loud CANNOT_ASSERT diagnostic" >&2
|
||||
if [[ "$status_c" -eq 0 ]]; then
|
||||
echo "FAIL(c): expected a nonzero exit for a genuine 500 API error, got 0" >&2
|
||||
echo "$out_c" >&2
|
||||
fail=1
|
||||
elif [[ "$out_c" == *"queue clear"* ]]; then
|
||||
echo "FAIL(c): a genuine API error must not be reported as queue-clear" >&2
|
||||
echo "$out_c" >&2
|
||||
fail=1
|
||||
elif [[ ! -s "$WORK_DIR/audit/ci-queue-wait.jsonl" ]]; then
|
||||
echo "FAIL(c): expected a durable CANNOT_ASSERT audit record" >&2
|
||||
fail=1
|
||||
fi
|
||||
|
||||
if [[ "$fail" -eq 0 ]]; then
|
||||
|
||||
@@ -1,95 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# GitHub Actions uses Checks API check-runs, not only legacy commit statuses.
|
||||
|
||||
set -u
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/ci-queue-wait-github-checks}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
STUB_DIR="$WORK_DIR/stubs"
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$STUB_DIR"
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" checkout -q -b fix/github-checks
|
||||
git -C "$REPO_DIR" remote add origin https://github.com/acme/widgets.git
|
||||
|
||||
cat > "$STUB_DIR/gh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
endpoint=""
|
||||
for arg in "$@"; do
|
||||
[[ "$arg" == repos/* ]] && endpoint="$arg"
|
||||
done
|
||||
printf '%s\n' "$*" >> "${MOSAIC_GH_CALL_LOG:?}"
|
||||
case "$endpoint" in
|
||||
repos/acme/widgets/branches/fix/github-checks)
|
||||
printf '%s\n' '0123456789abcdef0123456789abcdef01234567'
|
||||
;;
|
||||
repos/acme/widgets/commits/*/statuses?per_page=100)
|
||||
printf '%s\n' '[[]]'
|
||||
;;
|
||||
repos/acme/widgets/commits/*/check-runs?per_page=100\&filter=latest)
|
||||
case "${MOSAIC_GH_CHECK_MODE:?}" in
|
||||
success) printf '%s\n' '[{"total_count":1,"check_runs":[{"name":"ci","status":"completed","conclusion":"success"}]}]' ;;
|
||||
pending) printf '%s\n' '[{"total_count":1,"check_runs":[{"name":"ci","status":"in_progress","conclusion":null}]}]' ;;
|
||||
failure) printf '%s\n' '[{"total_count":1,"check_runs":[{"name":"ci","status":"completed","conclusion":"failure"}]}]' ;;
|
||||
late-failure) printf '%s\n' '[{"total_count":2,"check_runs":[{"name":"first-page","status":"completed","conclusion":"success"}]},{"total_count":2,"check_runs":[{"name":"later-page","status":"completed","conclusion":"failure"}]}]' ;;
|
||||
*) exit 2 ;;
|
||||
esac
|
||||
;;
|
||||
*) echo "unexpected gh endpoint: $endpoint" >&2; exit 2 ;;
|
||||
esac
|
||||
SH
|
||||
chmod +x "$STUB_DIR/gh"
|
||||
|
||||
run_guard() {
|
||||
local mode="$1"
|
||||
(
|
||||
cd "$REPO_DIR" || exit
|
||||
export PATH="$STUB_DIR:$PATH"
|
||||
export MOSAIC_GH_CHECK_MODE="$mode"
|
||||
export MOSAIC_GH_CALL_LOG="$WORK_DIR/gh-calls.log"
|
||||
export MOSAIC_CI_QUEUE_AUDIT_LOG="$WORK_DIR/audit.jsonl"
|
||||
"$SCRIPT_DIR/ci-queue-wait.sh" --purpose push -t 0 -i 0
|
||||
)
|
||||
}
|
||||
|
||||
failures=0
|
||||
assert_case() {
|
||||
local mode="$1" expected_rc="$2" expected_state="$3" output rc
|
||||
set +e
|
||||
output=$(run_guard "$mode" 2>&1)
|
||||
rc=$?
|
||||
set -e
|
||||
if [[ "$expected_rc" == zero && "$rc" -ne 0 ]]; then
|
||||
echo "FAIL github-$mode: expected rc=0, got $rc" >&2
|
||||
failures=$((failures + 1))
|
||||
elif [[ "$expected_rc" == nonzero && "$rc" -eq 0 ]]; then
|
||||
echo "FAIL github-$mode: expected rc!=0, got 0" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$output" != *"state=$expected_state"* ]]; then
|
||||
echo "FAIL github-$mode: expected state=$expected_state, got:" >&2
|
||||
printf '%s\n' "$output" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
}
|
||||
|
||||
set -e
|
||||
: > "$WORK_DIR/gh-calls.log"
|
||||
assert_case success zero terminal-success
|
||||
assert_case pending nonzero pending
|
||||
assert_case failure nonzero terminal-failure
|
||||
assert_case late-failure nonzero terminal-failure
|
||||
|
||||
if [[ $(grep -c 'check-runs?per_page=100&filter=latest' "$WORK_DIR/gh-calls.log") -lt 4 ]]; then
|
||||
echo "FAIL: expected every case to query all Checks API pages" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
if [[ "$failures" -ne 0 ]]; then
|
||||
echo "GitHub check-runs regression failed ($failures assertions)" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "GitHub check-runs regression passed (4/4 cases, including later-page failure)"
|
||||
@@ -1,364 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Exit-asserting RM-03 regression harness for ci-queue-wait.sh.
|
||||
# Every case is a process-level assertion: a classifier-only green cannot satisfy it.
|
||||
|
||||
set -u
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/ci-queue-wait-tristate}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
STUB_DIR="$WORK_DIR/stubs"
|
||||
AUDIT_LOG="$WORK_DIR/audit/ci-queue-wait.jsonl"
|
||||
STATUS_OBSERVED="$WORK_DIR/status-observed"
|
||||
CLOCK_LOG="$WORK_DIR/clock.log"
|
||||
WATCHDOG_PYTHON="/usr/bin/python3"
|
||||
WATCHDOG_SCRIPT="$WORK_DIR/real-clock-watchdog.py"
|
||||
WATCHDOG_TIMEOUT_SEC=5
|
||||
WATCHDOG_EXIT=90
|
||||
FEATURE_BRANCH="fix/rm-03-fixture"
|
||||
|
||||
if [[ ! -x "$WATCHDOG_PYTHON" ]]; then
|
||||
echo "FAIL setup: required real-clock watchdog runtime is unavailable at $WATCHDOG_PYTHON" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$STUB_DIR"
|
||||
cat > "$WATCHDOG_SCRIPT" <<'PY'
|
||||
import os
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
if len(sys.argv) < 3:
|
||||
raise SystemExit(2)
|
||||
|
||||
timeout_seconds = float(sys.argv[1])
|
||||
process = subprocess.Popen(sys.argv[2:], start_new_session=True)
|
||||
try:
|
||||
return_code = process.wait(timeout=timeout_seconds)
|
||||
except subprocess.TimeoutExpired:
|
||||
try:
|
||||
os.killpg(process.pid, signal.SIGKILL)
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
process.wait()
|
||||
print(
|
||||
f"FAIL HANG watchdog: subject exceeded {timeout_seconds:g}s "
|
||||
"before completing its intended path",
|
||||
file=sys.stderr,
|
||||
)
|
||||
raise SystemExit(90)
|
||||
|
||||
if return_code < 0:
|
||||
raise SystemExit(128 - return_code)
|
||||
raise SystemExit(return_code)
|
||||
PY
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" checkout -q -b "$FEATURE_BRANCH"
|
||||
git -C "$REPO_DIR" remote add origin https://git.example.test/acme/widgets.git
|
||||
|
||||
cat > "$STUB_DIR/curl" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
url=""
|
||||
has_write_out=0
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
-w) has_write_out=1 ;;
|
||||
http://*|https://*) url="$arg" ;;
|
||||
esac
|
||||
done
|
||||
printf '%s\n' "$url" >> "${MOSAIC_STUB_URL_LOG:?}"
|
||||
|
||||
case "$url" in
|
||||
*/branches/*)
|
||||
if [[ "${MOSAIC_STUB_BRANCH_MODE:-ok}" == "hang-before-provider" ]]; then
|
||||
while :; do :; done
|
||||
fi
|
||||
if [[ "${MOSAIC_STUB_BRANCH_MODE:-ok}" == "unreachable" ]]; then
|
||||
exit 7
|
||||
fi
|
||||
body='{"commit":{"id":"deadbeefcafef00d0123456789abcdef01234567"}}'
|
||||
if [[ "$has_write_out" -eq 1 ]]; then
|
||||
printf '%s\n200' "$body"
|
||||
else
|
||||
printf '%s' "$body"
|
||||
fi
|
||||
;;
|
||||
*/status)
|
||||
: > "${MOSAIC_STUB_STATUS_OBSERVED:?}"
|
||||
case "${MOSAIC_STUB_STATUS_MODE:?}" in
|
||||
success) printf '%s' '{"state":"success","statuses":[{"status":"success"}]}' ;;
|
||||
pending) printf '%s' '{"state":"pending","statuses":[{"status":"pending","context":"ci/test"}]}' ;;
|
||||
failure) printf '%s' '{"state":"failure","statuses":[{"status":"failure"}]}' ;;
|
||||
no-status) printf '%s' '{"state":"","statuses":[]}' ;;
|
||||
aggregate-success-no-status) printf '%s' '{"state":"success","statuses":[]}' ;;
|
||||
malformed) printf '%s' 'not-json' ;;
|
||||
malformed-statuses-type) printf '%s' '{"state":"success","statuses":"corrupt"}' ;;
|
||||
malformed-status-entry) printf '%s' '{"state":"success","statuses":[null]}' ;;
|
||||
large-success)
|
||||
python3 -c 'import json; print(json.dumps({"state":"success", "statuses":[{"status":"success"}], "padding":"x" * (160 * 1024)}), end="")'
|
||||
;;
|
||||
unreachable) exit 7 ;;
|
||||
*) echo "unknown status mode" >&2; exit 2 ;;
|
||||
esac
|
||||
;;
|
||||
*) echo "unexpected curl URL: $url" >&2; exit 2 ;;
|
||||
esac
|
||||
SH
|
||||
|
||||
cat > "$STUB_DIR/date" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
if [[ "$#" -ne 1 || "$1" != "+%s" ]]; then
|
||||
echo "unexpected date invocation: $*" >&2
|
||||
exit 2
|
||||
fi
|
||||
|
||||
if [[ -e "${MOSAIC_STUB_STATUS_OBSERVED:?}" ]]; then
|
||||
printf 'date-phase=after-status\n' >> "${MOSAIC_STUB_CLOCK_LOG:?}"
|
||||
printf '1002\n'
|
||||
else
|
||||
printf 'date-phase=before-status\n' >> "${MOSAIC_STUB_CLOCK_LOG:?}"
|
||||
printf '1000\n'
|
||||
fi
|
||||
SH
|
||||
|
||||
cat > "$STUB_DIR/sleep" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
printf 'sleep-after-status=%s\n' "$*" >> "${MOSAIC_STUB_CLOCK_LOG:?}"
|
||||
SH
|
||||
chmod +x "$STUB_DIR/curl" "$STUB_DIR/date" "$STUB_DIR/sleep"
|
||||
|
||||
run_guard() {
|
||||
local status_mode="$1"
|
||||
local audit_log="${2:-$AUDIT_LOG}"
|
||||
shift 2 || true
|
||||
(
|
||||
cd "$REPO_DIR" || exit
|
||||
export PATH="$STUB_DIR:$PATH"
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
if [[ "$status_mode" == "credential-unresolvable" ]]; then
|
||||
export HOME="$WORK_DIR/empty-home"
|
||||
mkdir -p "$HOME"
|
||||
unset GITEA_TOKEN GITEA_URL MOSAIC_GIT_IDENTITY
|
||||
export MOSAIC_STUB_STATUS_MODE=success
|
||||
else
|
||||
export GITEA_TOKEN=stub-token
|
||||
export GITEA_URL=https://git.example.test
|
||||
export MOSAIC_STUB_STATUS_MODE="$status_mode"
|
||||
fi
|
||||
rm -f "$STATUS_OBSERVED" "$CLOCK_LOG"
|
||||
export MOSAIC_STUB_URL_LOG="$WORK_DIR/urls.log"
|
||||
export MOSAIC_STUB_STATUS_OBSERVED="$STATUS_OBSERVED"
|
||||
export MOSAIC_STUB_CLOCK_LOG="$CLOCK_LOG"
|
||||
export MOSAIC_CI_QUEUE_AUDIT_LOG="$audit_log"
|
||||
# Provider observation is the synchronization event. The one-second
|
||||
# timeout is subject semantics under virtual time, never a wall wait.
|
||||
# The absolute Python runtime uses an internal monotonic wait and kills
|
||||
# the subject's isolated process group. Neither operation can resolve
|
||||
# to the virtual date/sleep stubs at the front of PATH.
|
||||
local subject_rc
|
||||
if "$WATCHDOG_PYTHON" "$WATCHDOG_SCRIPT" "$WATCHDOG_TIMEOUT_SEC" \
|
||||
"$SCRIPT_DIR/ci-queue-wait.sh" --purpose "${MOSAIC_TEST_PURPOSE:-push}" -t 1 -i 1 "$@"; then
|
||||
subject_rc=0
|
||||
else
|
||||
subject_rc=$?
|
||||
fi
|
||||
return "$subject_rc"
|
||||
)
|
||||
}
|
||||
|
||||
failures=0
|
||||
assert_provider_observed() {
|
||||
local name="$1" require_expiration="${2:-0}"
|
||||
if [[ ! -e "$STATUS_OBSERVED" ]]; then
|
||||
echo "FAIL $name: status provider was not observed" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ ! -s "$CLOCK_LOG" ]] || ! grep -q '^date-phase=before-status$' "$CLOCK_LOG"; then
|
||||
echo "FAIL $name: virtual clock interception did not run before provider observation" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$require_expiration" -eq 1 ]]; then
|
||||
if ! grep -q '^sleep-after-status=' "$CLOCK_LOG" || ! grep -q '^date-phase=after-status$' "$CLOCK_LOG"; then
|
||||
echo "FAIL $name: pending path did not expire after provider observation" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
run_assertion() {
|
||||
local name="$1" expected_rc="$2" status_mode="$3" required_text="$4"
|
||||
local output rc
|
||||
shift 4
|
||||
set +e
|
||||
output=$(run_guard "$status_mode" "$AUDIT_LOG" "$@" 2>&1)
|
||||
rc=$?
|
||||
set -e
|
||||
|
||||
case "$expected_rc" in
|
||||
zero)
|
||||
if [[ "$rc" -ne 0 ]]; then
|
||||
echo "FAIL $name: expected rc=0, got rc=$rc" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
;;
|
||||
nonzero)
|
||||
if [[ "$rc" -eq 0 ]]; then
|
||||
echo "FAIL $name: expected rc!=0, got rc=0" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
;;
|
||||
not126)
|
||||
if [[ "$rc" -eq 126 ]]; then
|
||||
echo "FAIL $name: payload transport hit ARG_MAX (rc=126)" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
if [[ "$output" != *"$required_text"* ]]; then
|
||||
echo "FAIL $name: output missing '$required_text' (rc=$rc)" >&2
|
||||
printf '%s\n' "$output" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$status_mode" != "credential-unresolvable" ]]; then
|
||||
if [[ "$status_mode" == "pending" ]]; then
|
||||
assert_provider_observed "$name" 1
|
||||
else
|
||||
assert_provider_observed "$name"
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
set -e
|
||||
: > "$WORK_DIR/urls.log"
|
||||
run_assertion success zero success 'state=terminal-success'
|
||||
run_assertion pending nonzero pending 'ASSERTED_NOT_READY'
|
||||
run_assertion failure nonzero failure 'ASSERTED_NOT_READY'
|
||||
run_assertion no-status nonzero no-status 'ASSERTED_NOT_READY'
|
||||
run_assertion aggregate-success-no-status nonzero aggregate-success-no-status 'ASSERTED_NOT_READY'
|
||||
run_assertion malformed nonzero malformed 'ASSERTED_NOT_READY'
|
||||
run_assertion malformed-statuses-type nonzero malformed-statuses-type 'ASSERTED_NOT_READY'
|
||||
run_assertion malformed-status-entry nonzero malformed-status-entry 'ASSERTED_NOT_READY'
|
||||
run_assertion large-payload not126 large-success 'state=terminal-success'
|
||||
run_assertion credential-unresolvable zero credential-unresolvable 'CANNOT_ASSERT'
|
||||
run_assertion provider-unreachable zero unreachable 'CANNOT_ASSERT'
|
||||
|
||||
# Positive liveness control: a subject mutant hangs before the branch lookup
|
||||
# can reach the status provider. Only the independent real-clock watchdog may
|
||||
# terminate it, and its failure must be distinct from subject timeout rc=124.
|
||||
set +e
|
||||
watchdog_output=$(MOSAIC_STUB_BRANCH_MODE=hang-before-provider run_guard success "$AUDIT_LOG" 2>&1)
|
||||
watchdog_rc=$?
|
||||
set -e
|
||||
if [[ "$watchdog_rc" -ne "$WATCHDOG_EXIT" ]]; then
|
||||
echo "FAIL watchdog-control: expected hang-specific rc=$WATCHDOG_EXIT, got rc=$watchdog_rc" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$watchdog_output" != *"FAIL HANG watchdog:"* ]]; then
|
||||
echo "FAIL watchdog-control: expected distinct hang-specific diagnostic" >&2
|
||||
printf '%s\n' "$watchdog_output" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ -e "$STATUS_OBSERVED" ]]; then
|
||||
echo "FAIL watchdog-control: hanging mutant unexpectedly reached the status provider" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
if [[ ! -s "$AUDIT_LOG" ]] || ! grep -q '"outcome":"CANNOT_ASSERT"' "$AUDIT_LOG"; then
|
||||
echo "FAIL provider-unreachable-audit: expected durable CANNOT_ASSERT JSONL record" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
# Merge cannot proceed without exact-head evidence. CANNOT_ASSERT is retryable exit 75,
|
||||
# distinct from ASSERTED_NOT_READY (3/124), and still writes its audit record.
|
||||
merge_audit_lines_before=$(wc -l < "$AUDIT_LOG")
|
||||
set +e
|
||||
merge_unreachable_output=$(MOSAIC_TEST_PURPOSE=merge run_guard unreachable "$AUDIT_LOG" 2>&1)
|
||||
merge_unreachable_rc=$?
|
||||
set -e
|
||||
if [[ "$merge_unreachable_rc" -ne 75 ]]; then
|
||||
echo "FAIL merge-provider-unreachable: expected rc=75, got rc=$merge_unreachable_rc" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$merge_unreachable_output" != *"CANNOT_ASSERT"* ]]; then
|
||||
echo "FAIL merge-provider-unreachable: expected loud CANNOT_ASSERT diagnostic" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
assert_provider_observed merge-provider-unreachable
|
||||
merge_audit_lines_after=$(wc -l < "$AUDIT_LOG")
|
||||
if [[ "$merge_audit_lines_after" -le "$merge_audit_lines_before" ]]; then
|
||||
echo "FAIL merge-provider-unreachable: expected an additional audit record" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
# A feature-branch push with no -B must inspect the checked-out feature branch.
|
||||
if ! grep -q "/branches/$FEATURE_BRANCH" "$WORK_DIR/urls.log"; then
|
||||
echo "FAIL implicit-branch: provider was not queried for $FEATURE_BRANCH" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
# Merge callers can pin both a fork repository and the exact reviewed head SHA.
|
||||
exact_sha=0123456789abcdef0123456789abcdef01234567
|
||||
: > "$WORK_DIR/urls.log"
|
||||
run_assertion exact-fork-head zero success 'state=terminal-success' \
|
||||
-B fix/rm-03-fixture -R contributor/widgets-fork --sha "$exact_sha"
|
||||
if ! grep -q "/repos/contributor/widgets-fork/commits/$exact_sha/status" "$WORK_DIR/urls.log"; then
|
||||
echo "FAIL exact-fork-head: status URL did not bind fork repository and exact SHA" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if grep -q '/branches/' "$WORK_DIR/urls.log"; then
|
||||
echo "FAIL exact-fork-head: explicit SHA must not be re-resolved through a branch" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
# Platform/repository discovery failures use the same audited CANNOT_ASSERT path.
|
||||
audit_lines_before=$(wc -l < "$AUDIT_LOG")
|
||||
git -C "$REPO_DIR" remote set-url origin https://gitlab.com/acme/widgets.git
|
||||
set +e
|
||||
unsupported_output=$(run_guard success "$AUDIT_LOG" 2>&1)
|
||||
unsupported_rc=$?
|
||||
set -e
|
||||
git -C "$REPO_DIR" remote set-url origin https://git.example.test/acme/widgets.git
|
||||
if [[ "$unsupported_rc" -ne 0 ]]; then
|
||||
echo "FAIL unsupported-platform: expected degraded rc=0, got rc=$unsupported_rc" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$unsupported_output" != *"CANNOT_ASSERT"* ]]; then
|
||||
echo "FAIL unsupported-platform: expected loud CANNOT_ASSERT diagnostic" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
audit_lines_after=$(wc -l < "$AUDIT_LOG")
|
||||
if [[ "$audit_lines_after" -le "$audit_lines_before" ]]; then
|
||||
echo "FAIL unsupported-platform: expected an additional audit record" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
|
||||
# A degraded pass is forbidden if the audit receipt cannot be written.
|
||||
mkdir -p "$WORK_DIR/not-a-directory"
|
||||
printf 'file' > "$WORK_DIR/not-a-directory/parent"
|
||||
set +e
|
||||
audit_failure_output=$(run_guard unreachable "$WORK_DIR/not-a-directory/parent/audit.jsonl" 2>&1)
|
||||
audit_failure_rc=$?
|
||||
set -e
|
||||
if [[ "$audit_failure_rc" -eq 0 ]]; then
|
||||
echo "FAIL audit-unavailable: expected rc!=0, got rc=0" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
if [[ "$audit_failure_output" != *"audit"* ]]; then
|
||||
echo "FAIL audit-unavailable: expected loud audit failure diagnostic" >&2
|
||||
failures=$((failures + 1))
|
||||
fi
|
||||
assert_provider_observed audit-unavailable
|
||||
|
||||
if [[ "$failures" -ne 0 ]]; then
|
||||
echo "ci-queue-wait tri-state regression failed ($failures assertions)" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "ci-queue-wait tri-state regression passed (all outcome classes)"
|
||||
@@ -1,58 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Regression: detect_platform / get_repo_info must FAIL LOUDLY outside a git repo,
|
||||
# not kill the caller silently.
|
||||
#
|
||||
# Both functions already contained the right error path:
|
||||
# if [[ -z "$remote_url" ]]; then echo "error: not a git repository..." >&2; return 1; fi
|
||||
# but under `set -e` -- which every wrapper in this directory uses -- the preceding
|
||||
# assignment `remote_url=$(git remote get-url origin 2>/dev/null)` returns git's 128
|
||||
# outside a repo and terminates the CALLER first. The message was unreachable.
|
||||
#
|
||||
# Observed cost: pr-review.sh invoked from a non-repo cwd exits 128 with NO stdout and
|
||||
# NO stderr, even when -r/--repo and -H/--host are supplied -- the flags documented as
|
||||
# "skips git-remote inference". Two reviewer seats hit this and correctly reported
|
||||
# `blocked` with no diagnostic to report.
|
||||
#
|
||||
# The control that matters is the LOUD one: asserting "rc != 0" passes on the broken
|
||||
# build too, because 128 is also non-zero. The test must assert the MESSAGE.
|
||||
set -uo pipefail
|
||||
fail=0
|
||||
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
|
||||
run_outside() { # $1=function name -> "rc:sawmessage"
|
||||
local fn="$1" out rc
|
||||
out=$( cd "$TMP" && bash -c "set -e; source '$HERE/detect-platform.sh'; $fn" 2>&1 ); rc=$?
|
||||
printf '%s:%s' "$rc" "$(grep -qi 'not a git repository' <<<"$out" && echo yes || echo no)"
|
||||
}
|
||||
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
|
||||
|
||||
# $TMP must not be inside a git repo. Do not SKIP on failure: be-coder-07 showed the
|
||||
# original SKIP exited 0, so pointing TMPDIR beneath a git worktree made this test PASS
|
||||
# against unchanged main. A skip that exits 0 is indistinguishable from a pass.
|
||||
# GIT_CEILING_DIRECTORIES stops git walking above $TMP, making the condition hold
|
||||
# regardless of where TMPDIR lives, rather than merely detecting when it does not.
|
||||
# GIT_CEILING_DIRECTORIES is matched against the PHYSICAL path -- a symlinked TMPDIR
|
||||
# (/tmp is commonly one) makes the logical path never match, and the ceiling silently
|
||||
# does nothing. Resolve it before exporting.
|
||||
TMP="$(cd "$TMP" && pwd -P)"
|
||||
export GIT_CEILING_DIRECTORIES="$TMP"
|
||||
if ( cd "$TMP" && git rev-parse --git-dir >/dev/null 2>&1 ); then
|
||||
echo " FAIL scratch dir is inside a git repo even with GIT_CEILING_DIRECTORIES set;"
|
||||
echo " the outside-a-repo precondition cannot be established -- refusing to report a result"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "== outside a git repo: rc=1 AND the diagnostic is emitted =="
|
||||
check "detect_platform" "$(run_outside detect_platform)" "1:yes"
|
||||
check "get_repo_info" "$(run_outside get_repo_info)" "1:yes"
|
||||
|
||||
echo "== inside a git repo the functions still work =="
|
||||
git init -q "$TMP/repo" 2>/dev/null
|
||||
git -C "$TMP/repo" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git 2>/dev/null
|
||||
out=$( cd "$TMP/repo" && bash -c "set -e; source '$HERE/detect-platform.sh'; detect_platform" 2>&1 ); rc=$?
|
||||
if [ "$rc" -eq 0 ] && grep -qi 'gitea' <<<"$out"; then echo " PASS detect_platform in-repo (rc=0, $out)"
|
||||
else echo " FAIL detect_platform in-repo: rc=$rc out=$out"; fail=1; fi
|
||||
|
||||
[ "$fail" -eq 0 ] && echo "OK detect-platform fails loudly outside a repo" || echo "FAILED"
|
||||
exit "$fail"
|
||||
@@ -1,64 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Regression: the tea-failure diagnostic must be STATUS-NEUTRAL.
|
||||
#
|
||||
# Found by be-coder-08 reviewing PR #1086. At all three call sites the diagnostic is emitted
|
||||
# immediately BEFORE the Gitea API fallback. Written as the last command of an && list:
|
||||
# declare -F explain_... >/dev/null && explain_...
|
||||
# under `set -e` a FAILING diagnostic exits and the fallback never runs -- a diagnostic that
|
||||
# suppresses the recovery path it exists to explain. It misbehaves ONLY when the helper is
|
||||
# PRESENT, so the helper-absent path (pre-#1086 behaviour) keeps working and reads as a
|
||||
# passing control.
|
||||
#
|
||||
# TWO DEFECTS IN THE FIRST VERSION OF THIS TEST, both found by be-coder-08:
|
||||
# 1. `out=$( ... ) 2>"$errto"` applies the redirection to the ASSIGNMENT, not to the
|
||||
# command substitution, so the probe's stderr was never actually pointed at /dev/full
|
||||
# and the /dev/full rows proved nothing. Verified: `out=$(echo x >&2) 2>/dev/full`
|
||||
# leaks to the terminal and returns 0; the redirect must be INSIDE the substitution.
|
||||
# 2. `eval "$CONSTRUCT"` changes `set -e` semantics for a bare && list, so the probe did
|
||||
# not exercise the construct as the shipped file executes it. It now writes the line
|
||||
# into a real script and runs it -- same parse, same set -e rules, no eval.
|
||||
# The construct is still LIFTED FROM THE SHIPPED FILE: retyping the fixed form makes the
|
||||
# probe pass on a build whose real call sites still carry the bare && form.
|
||||
set -uo pipefail
|
||||
fail=0
|
||||
GIT_DIR_UNDER_TEST="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
|
||||
probe() { # $1=present|absent $2=stderr target $3=source file -> "rc:fallback"
|
||||
local helper="$1" errto="$2" src="$3" construct script out rc
|
||||
construct=$(grep -m1 'explain_tea_user_does_not_exist' "$GIT_DIR_UNDER_TEST/$src" | sed 's/^[[:space:]]*//')
|
||||
[ -n "$construct" ] || { printf 'no-construct:no'; return; }
|
||||
script="$TMP/probe.sh"
|
||||
{
|
||||
echo '#!/bin/bash'
|
||||
echo 'set -e'
|
||||
echo 'explain_tea_user_does_not_exist() { echo "diagnostic" >&2; }'
|
||||
[ "$helper" = absent ] && echo 'unset -f explain_tea_user_does_not_exist'
|
||||
echo "$construct" # the shipped line, parsed by a real shell
|
||||
echo 'echo FALLBACK_REACHED'
|
||||
} > "$script"
|
||||
# redirect INSIDE the substitution so the subshell's stderr really is $errto
|
||||
out=$( bash "$script" 2>"$errto" ); rc=$?
|
||||
printf '%s:%s' "$rc" "$(grep -q FALLBACK_REACHED <<<"$out" && echo yes || echo no)"
|
||||
}
|
||||
|
||||
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
|
||||
|
||||
echo "== diagnostic must not alter exit status or skip the fallback =="
|
||||
# /dev/full makes every stderr write fail -- the real-world shape is a closed or full fd.
|
||||
for src in pr-create.sh issue-view.sh issue-create.sh; do
|
||||
check "$src stderr OK / helper present" "$(probe present /dev/null "$src")" "0:yes"
|
||||
check "$src stderr OK / helper absent " "$(probe absent /dev/null "$src")" "0:yes"
|
||||
check "$src stderr FAILING / helper present" "$(probe present /dev/full "$src")" "0:yes"
|
||||
check "$src stderr FAILING / helper absent " "$(probe absent /dev/full "$src")" "0:yes"
|
||||
done
|
||||
|
||||
echo "== all three call sites use the status-neutral form =="
|
||||
for f in pr-create.sh issue-view.sh issue-create.sh; do
|
||||
p="$GIT_DIR_UNDER_TEST/$f"
|
||||
grep -q '{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true' "$p" \
|
||||
&& echo " PASS $f guarded" || { echo " FAIL $f: diagnostic is not status-neutral"; fail=1; }
|
||||
done
|
||||
|
||||
[ "$fail" -eq 0 ] && echo "OK diagnostic is status-neutral" || echo "FAILED"
|
||||
exit "$fail"
|
||||
@@ -7,40 +7,14 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/gitea-login-resolution}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
BIN_DIR="$WORK_DIR/bin"
|
||||
HOME_DIR="$WORK_DIR/home"
|
||||
LOG_FILE="$WORK_DIR/calls.log"
|
||||
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR"
|
||||
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/USC/uconnect.git
|
||||
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
|
||||
#
|
||||
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
|
||||
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
|
||||
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
|
||||
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
|
||||
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credentials below are silently
|
||||
# ignored. This suite is the one where the consequence is not subtle: it FAILS
|
||||
# outright on a provisioned seat (rc=1 bare, rc=0 with $HOME sandboxed, one
|
||||
# variable changed) and passes everywhere else, including CI, which has no
|
||||
# per-agent token to leak.
|
||||
#
|
||||
# CONTAINMENT: the sandboxed HOME in the four run helpers below. It only has to
|
||||
# bound a failure that the pin should already have prevented.
|
||||
#
|
||||
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
|
||||
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
|
||||
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
|
||||
# by construction and every suite reads clean however vulnerable it is. To measure,
|
||||
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
|
||||
# per-slot token) so step 0 reaches its fail-loud branch.
|
||||
#
|
||||
# Note the env-var route does NOT work: detect-platform.sh reads
|
||||
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
cat > "$CREDENTIALS_FILE" <<'JSON'
|
||||
{
|
||||
@@ -112,7 +86,6 @@ run_in_repo() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
PATH="$BIN_DIR:$PATH" \
|
||||
HOME="$HOME_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
MOSAIC_TEST_LOG="$LOG_FILE" \
|
||||
"$@"
|
||||
@@ -310,7 +283,6 @@ run_in_repo2() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
PATH="$BIN_DIR2:$PATH" \
|
||||
HOME="$HOME_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
MOSAIC_TEST_LOG="$LOG_FILE" \
|
||||
"$@"
|
||||
@@ -371,7 +343,7 @@ write_fixture() { printf '%s' "$1" > "$FIXTURE_XDG/tea/config.yml"; }
|
||||
token_fallback() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
HOME="$HOME_DIR" XDG_CONFIG_HOME="$FIXTURE_XDG" PYTHONPATH="$NOYAML_DIR" bash -c '
|
||||
XDG_CONFIG_HOME="$FIXTURE_XDG" PYTHONPATH="$NOYAML_DIR" bash -c '
|
||||
source "'"$SCRIPT_DIR"'/detect-platform.sh"
|
||||
get_gitea_token_for_login "$1" "$2"
|
||||
' _ "$1" "$2"
|
||||
@@ -382,7 +354,7 @@ token_fallback() {
|
||||
token_pyyaml() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
HOME="$HOME_DIR" XDG_CONFIG_HOME="$FIXTURE_XDG" bash -c '
|
||||
XDG_CONFIG_HOME="$FIXTURE_XDG" bash -c '
|
||||
source "'"$SCRIPT_DIR"'/detect-platform.sh"
|
||||
get_gitea_token_for_login "$1" "$2"
|
||||
' _ "$1" "$2"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for #701: -h/--help must exit 0, bad args must still exit nonzero.
|
||||
#
|
||||
# Covers wrappers whose usage() previously hard-coded `exit 1`, so every
|
||||
# Covers the 7 wrappers whose usage() previously hard-coded `exit 1`, so every
|
||||
# --help invocation exited nonzero and logged a phantom isError across fleet lanes.
|
||||
# Asserts, per wrapper:
|
||||
# 1. `--help` exits 0 and prints usage.
|
||||
@@ -18,7 +18,6 @@ WRAPPERS=(
|
||||
issue-list.sh
|
||||
milestone-create.sh
|
||||
pr-create.sh
|
||||
pr-edit.sh
|
||||
pr-list.sh
|
||||
pr-merge.sh
|
||||
)
|
||||
@@ -48,7 +47,7 @@ for wrapper in "${WRAPPERS[@]}"; do
|
||||
done
|
||||
|
||||
if [[ "$fail" -eq 0 ]]; then
|
||||
echo "help-exit-code regression passed (8/8 wrappers)"
|
||||
echo "help-exit-code regression passed (7/7 wrappers)"
|
||||
fi
|
||||
|
||||
exit "$fail"
|
||||
|
||||
@@ -1,150 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression: issue-close.sh must NOT close an issue when the closing comment could not
|
||||
# be posted, and comment+close must be made by ONE principal.
|
||||
#
|
||||
# Guards two defects fixed together (see #1081):
|
||||
# 1. `tea issue comment` is not a subcommand -- tea exposes comments as the TOP-LEVEL
|
||||
# `tea comment`. The old call always failed, was unchecked, and the issue closed
|
||||
# anyway, losing the record of WHY it was closed.
|
||||
# 2. Routing the comment through the token-authenticated API helper while the close
|
||||
# used --login would attribute one operation to two principals.
|
||||
#
|
||||
# SAFETY (rev-974, #1085 review 130): this test previously ran under `set -uo pipefail`
|
||||
# with unchecked mkdir/redirect/cd, then prepended a possibly-nonexistent $MOCK_BIN to
|
||||
# PATH -- while `git remote add origin` names the REAL repository. Forcing setup failure
|
||||
# with an unwritable AGENT_WORK_ROOT made it `git init` in its CALLER's directory and
|
||||
# invoke the real, provider-mutating issue-close.sh. Setup now fails closed, and both
|
||||
# `tea` and `curl` are asserted to resolve INSIDE $MOCK_BIN before any target run.
|
||||
set -euo pipefail
|
||||
# NOTE: with `set -e`, `grep -q X && fail "..."` is a trap -- the ABSENT case (grep rc=1,
|
||||
# which is the PASSING case for a must-not-appear assertion) is the last command of an &&
|
||||
# list and silently terminates the script with no message. Every must-not-appear check
|
||||
# below is therefore an if-block. This is the same set -e + &&-list defect be-coder-08
|
||||
# found in #1086, reintroduced here by adding `set -e` for the sandbox-safety fix.
|
||||
|
||||
WORK_ROOT="${AGENT_WORK_ROOT:-${TMPDIR:-/tmp}}"
|
||||
SANDBOX="$WORK_ROOT/issue-close-fail-closed-test-$$"
|
||||
MOCK_BIN="$SANDBOX/bin"; REPO_DIR="$SANDBOX/repo"; CALLS="$SANDBOX/calls.log"
|
||||
cleanup() { rm -rf "$SANDBOX"; }
|
||||
trap cleanup EXIT
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TARGET="$SCRIPT_DIR/issue-close.sh"
|
||||
[ -f "$TARGET" ] || { echo "FAIL: issue-close.sh not found beside this test"; exit 1; }
|
||||
fail() { echo "FAIL: $*"; exit 1; }
|
||||
|
||||
# Every setup step is checked. Under `set -e` these abort; the explicit || fail keeps the
|
||||
# reason legible instead of a bare non-zero exit.
|
||||
mkdir -p "$MOCK_BIN" "$REPO_DIR" || fail "setup: cannot create sandbox under $WORK_ROOT"
|
||||
: > "$CALLS" || fail "setup: cannot write calls log at $CALLS"
|
||||
cd "$REPO_DIR" || fail "setup: cannot cd into $REPO_DIR"
|
||||
git init -q || fail "setup: git init failed"
|
||||
git remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git || fail "setup: git remote add failed"
|
||||
export PATH="$MOCK_BIN:$PATH" CALLS
|
||||
export GITEA_URL="https://git.mosaicstack.dev"
|
||||
export GITEA_TOKEN="redacted-test-token"
|
||||
|
||||
cat > "$MOCK_BIN/curl" <<'EOF'
|
||||
#!/bin/bash
|
||||
method=GET; url=""
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
-X) method="$2"; shift 2 ;;
|
||||
http*|https*) url="$1"; shift ;;
|
||||
*) shift ;;
|
||||
esac
|
||||
done
|
||||
printf 'curl %s %s\n' "$method" "$url" >> "$CALLS"
|
||||
[ "${MOCK_CURL_FAIL:-}" = "1" ] && [ "$method" = "POST" ] && exit 22
|
||||
exit 0
|
||||
EOF
|
||||
chmod +x "$MOCK_BIN/curl"
|
||||
|
||||
mk_tea() { # $1 = exit code for a comment attempt; $2 = login list (empty => no login)
|
||||
local rc="$1" login="${2-}"
|
||||
cat > "$MOCK_BIN/tea" <<EOF
|
||||
#!/bin/bash
|
||||
printf 'tea %s\n' "\$*" >> "$CALLS"
|
||||
if [[ "\$*" == *"login list"* ]]; then
|
||||
printf '%s\n' '${login}'; exit 0
|
||||
fi
|
||||
# Fail ANY comment attempt -- both the correct top-level \`tea comment\` and the broken
|
||||
# \`tea issue comment\` -- so an unfixed script exercises the DEFECT rather than tripping
|
||||
# a setup assertion.
|
||||
if [[ "\$1" == "comment" || ( "\$1" == "issue" && "\$2" == "comment" ) ]]; then exit $rc; fi
|
||||
exit 0
|
||||
EOF
|
||||
chmod +x "$MOCK_BIN/tea"
|
||||
}
|
||||
LOGIN_JSON='[{"name":"git.mosaicstack.dev","url":"https://git.mosaicstack.dev"}]'
|
||||
|
||||
# The mocks must be the ones that run. Without this, a failed setup silently falls through
|
||||
# to the real tea/curl and the "test" mutates the real provider.
|
||||
assert_mocked() {
|
||||
local w
|
||||
for w in tea curl; do
|
||||
p=$(command -v "$w" || true)
|
||||
[ -n "$p" ] || fail "SAFETY: $w does not resolve at all"
|
||||
case "$p" in
|
||||
"$MOCK_BIN"/*) : ;;
|
||||
*) fail "SAFETY: $w resolves to $p, OUTSIDE the sandbox -- refusing to invoke the target" ;;
|
||||
esac
|
||||
done
|
||||
}
|
||||
|
||||
run_target() { # never let a target failure abort the test; we assert on rc
|
||||
# Call sites MUST use `rc=0; run_target ... || rc=$?` -- a bare `run_target ...; rc=$?`
|
||||
# lets the non-zero RETURN trip set -e in the CALLER before rc is ever read.
|
||||
set +e; bash "$TARGET" "$@" >/dev/null 2>&1; local rc=$?; set -e; return $rc
|
||||
}
|
||||
|
||||
# ── tea path ────────────────────────────────────────────────────────────────────────
|
||||
# 1. NEGATIVE (the regression): comment fails => must NOT close, must exit non-zero
|
||||
mk_tea 1 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
grep -qE 'tea (issue )?comment' "$CALLS" || fail "no comment attempt -- setup did not reach the tea branch"
|
||||
if grep -q 'tea issue close' "$CALLS"; then fail "ISSUE CLOSED AFTER THE COMMENT FAILED -- the regression"; fi
|
||||
[ "$rc" -ne 0 ] || fail "comment failed but issue-close exited 0 -- FAIL-OPEN"
|
||||
|
||||
# 2. POSITIVE: comment succeeds => close proceeds, exit 0
|
||||
mk_tea 0 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "comment succeeded but issue-close exited $rc"
|
||||
grep -q 'tea issue close' "$CALLS" || fail "issue not closed even though the comment succeeded"
|
||||
|
||||
# 3. must use top-level `tea comment`, never `tea issue comment`
|
||||
if grep -q 'tea issue comment' "$CALLS"; then fail "used 'tea issue comment' -- not a valid subcommand"; fi
|
||||
|
||||
# 4. ONE PRINCIPAL: comment and close must carry the SAME --login
|
||||
c=$(grep -m1 '^tea comment' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
|
||||
k=$(grep -m1 '^tea issue close' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
|
||||
[ -n "$c" ] || fail "comment carried no --login"
|
||||
[ "$c" = "$k" ] || fail "MIXED PRINCIPALS: comment=$c close=$k"
|
||||
|
||||
# ── no-login / API fallback path ────────────────────────────────────────────────────
|
||||
# rev-974: the delta also adds fail-closed behaviour to this branch, and the suite never
|
||||
# reached it -- replacing the whole fallback contract with an unconditional close still
|
||||
# passed. These assert the POSTCONDITION (which HTTP calls happened, in what order),
|
||||
# not merely that a command ran.
|
||||
# 5. no login + comment FAILS => POST attempted, NO PATCH, non-zero
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; MOCK_CURL_FAIL=1 run_target -i 42 -c "closing note" || rc=$?
|
||||
grep -q 'curl POST' "$CALLS" || fail "API path: no comment POST attempted"
|
||||
if grep -q 'curl PATCH' "$CALLS"; then fail "API path: ISSUE CLOSED (PATCH) AFTER THE COMMENT POST FAILED"; fi
|
||||
[ "$rc" -ne 0 ] || fail "API path: comment failed but exited 0 -- FAIL-OPEN"
|
||||
|
||||
# 6. no login + comment SUCCEEDS => POST strictly BEFORE PATCH, exit 0
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "API path: comment succeeded but exited $rc"
|
||||
order=$(grep -oE 'curl (POST|PATCH)' "$CALLS" | awk '{print $2}' | paste -sd, -)
|
||||
[ "$order" = "POST,PATCH" ] || fail "API path: expected POST,PATCH -- got '${order:-<none>}'"
|
||||
|
||||
# 7. no login + NO comment => PATCH only, never a POST
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "API path: no-comment close exited $rc"
|
||||
if grep -q 'curl POST' "$CALLS"; then fail "API path: posted a comment when none was requested"; fi
|
||||
grep -q 'curl PATCH' "$CALLS" || fail "API path: issue not closed when no comment was requested"
|
||||
|
||||
echo "issue-close.sh fail-closed + single-principal regression passed"
|
||||
@@ -61,54 +61,15 @@ STATE_FILE="$WORK_DIR/comments.json"
|
||||
# A dedicated scratch dir the wrapper is pointed at via TMPDIR, so the leak
|
||||
# check can assert every POST/GET body + metadata temp file is cleaned up.
|
||||
TMP_SCRATCH="$WORK_DIR/scratch"
|
||||
HOME_DIR="$WORK_DIR/home"
|
||||
|
||||
cleanup() {
|
||||
rm -rf "$WORK_DIR"
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR" "$XDG_DIR" "$TMP_SCRATCH" "$HOME_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR" "$XDG_DIR" "$TMP_SCRATCH"
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
|
||||
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
|
||||
#
|
||||
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
|
||||
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
|
||||
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
|
||||
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
|
||||
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credential below is silently
|
||||
# ignored. The stub curl then rejects the unrecognised bearer, and this suite
|
||||
# fails at its FIRST case with `Gitea authenticated-identity read failed with
|
||||
# HTTP 401`. An empty repo-local value shadows the global one and reads back
|
||||
# empty at rc=0. Measured: without this pin the suite is RED on every seat.
|
||||
#
|
||||
# CONTAINMENT: the sandboxed HOME in run_comment(). It only has to bound a
|
||||
# failure that the pin should already have prevented.
|
||||
#
|
||||
# THIS SUITE WAS THE HARDEST OF THE FIVE TO SEE, and the reason is worth stating
|
||||
# because it generalises: run_comment() sends the wrapper's stdout AND stderr to
|
||||
# $OUTPUT_FILE, and the EXIT trap above deletes $WORK_DIR. So the 401 — the only
|
||||
# thing that says what went wrong — exists only inside a directory that is gone
|
||||
# by the time anyone looks. The suite exits 1 with ZERO bytes on stdout and
|
||||
# stderr. A suite that discards or deletes its own evidence turns any post-hoc
|
||||
# assay into a non-measurement: "nothing found" there means "no surviving
|
||||
# trace", never "clean". It was found by intercepting the identity read at its
|
||||
# SOURCE (a PATH shim over `git` logging every `mosaic.gitIdentity` read to a
|
||||
# file outside $WORK_DIR), which is deletion-proof by construction, rather than
|
||||
# by grepping for the symptom.
|
||||
#
|
||||
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
|
||||
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
|
||||
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
|
||||
# by construction and every suite reads clean however vulnerable it is. To
|
||||
# measure, REPLICATE a seat (a decoy HOME whose .gitconfig sets
|
||||
# mosaic.gitIdentity, with no per-slot token) so step 0 reaches its fail-loud
|
||||
# branch — or intercept the read as described above.
|
||||
#
|
||||
# Note the env-var route does NOT work: detect-platform.sh reads
|
||||
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
ISSUE_NUMBER=7
|
||||
REPO_SLUG="mosaicstack/stack"
|
||||
@@ -319,10 +280,7 @@ print("201")
|
||||
print(json.dumps(record))
|
||||
PY
|
||||
)
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
|
||||
result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
|
||||
import json
|
||||
@@ -341,10 +299,7 @@ else:
|
||||
print(json.dumps(match))
|
||||
PY
|
||||
)
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
else
|
||||
echo "Unexpected curl request: $method $url" >&2
|
||||
exit 97
|
||||
@@ -411,7 +366,6 @@ run_comment() {
|
||||
cd "$REPO_DIR"
|
||||
PATH="$BIN_DIR:$PATH" \
|
||||
TMPDIR="$TMP_SCRATCH" \
|
||||
HOME="$HOME_DIR" \
|
||||
XDG_CONFIG_HOME="$XDG_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
ISSUE_COMMENT_TEA_LOG="$TEA_LOG" \
|
||||
|
||||
@@ -7,38 +7,13 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/issue-create-interactive-auth}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
BIN_DIR="$WORK_DIR/bin"
|
||||
HOME_DIR="$WORK_DIR/home"
|
||||
LOG_FILE="$WORK_DIR/calls.log"
|
||||
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR"
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
|
||||
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
|
||||
#
|
||||
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
|
||||
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
|
||||
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
|
||||
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
|
||||
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credential below is silently
|
||||
# ignored and the suite runs against a production credential. An empty repo-local
|
||||
# value shadows the global one and reads back empty at rc=0. Measured: this suite
|
||||
# resolves a per-slot token without it.
|
||||
#
|
||||
# CONTAINMENT: the sandboxed HOME in run_wrapper(). It only has to bound a failure
|
||||
# that the pin should already have prevented.
|
||||
#
|
||||
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
|
||||
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
|
||||
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
|
||||
# by construction and every suite reads clean however vulnerable it is. To measure,
|
||||
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
|
||||
# per-slot token) so step 0 reaches its fail-loud branch.
|
||||
#
|
||||
# Note the env-var route does NOT work: detect-platform.sh reads
|
||||
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
cat > "$CREDENTIALS_FILE" <<'JSON'
|
||||
{"gitea":{"mosaicstack":{"url":"https://git.mosaicstack.dev","token":"test-token"}}}
|
||||
@@ -75,7 +50,6 @@ run_wrapper() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
PATH="$BIN_DIR:$PATH" \
|
||||
HOME="$HOME_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
MOSAIC_TEST_LOG="$LOG_FILE" \
|
||||
"$@"
|
||||
|
||||
@@ -69,7 +69,7 @@ section_nums() { # $1 = output $2 = header-prefix
|
||||
}
|
||||
|
||||
fail() { echo "FAIL: $1" >&2; exit 1; }
|
||||
contains() { grep -qx "$2" <<<"$1"; }
|
||||
contains() { printf '%s\n' "$1" | grep -qx "$2"; }
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Fixed (current) script behavior
|
||||
|
||||
@@ -1,95 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# test-mosaic-worktree-large-repo.sh — the helper must work on the repos it exists for.
|
||||
#
|
||||
# resolve_repo() took the first line of `git worktree list --porcelain` with
|
||||
# `awk '/^worktree /{print substr($0,10); exit}'`. The `exit` closes the read end
|
||||
# of the pipe while git is still writing, git takes SIGPIPE, and under
|
||||
# `set -euo pipefail` the command substitution returns 141 — so the assignment
|
||||
# fails, `set -e` aborts the function, and the script dies printing NOTHING. No
|
||||
# message, no path, no worktree, exit 141.
|
||||
#
|
||||
# What makes it worth a dedicated test rather than a fixture line is WHEN it
|
||||
# fires. If git finishes writing before awk leaves, there is no SIGPIPE and
|
||||
# everything works. So the failure is a function of how much porcelain the repo
|
||||
# produces: invisible on a three-worktree repo, reliable on a seventy-worktree
|
||||
# one. It was measured on a repo with 73 worktrees (10 KB of porcelain) — rc=141,
|
||||
# no output — and it had passed every hand-check before that, on small repos.
|
||||
#
|
||||
# A test that ran `git worktree list` against whatever repo it happens to sit in
|
||||
# would inherit that same size dependence and would have PASSED on the tree that
|
||||
# was broken. So git is stubbed on PATH and made to emit a large porcelain
|
||||
# stream, which turns "depends on the repo you are standing in" into "always".
|
||||
#
|
||||
# Exit: 0 = the helper resolved the repo · 1 = it did not
|
||||
|
||||
set -uo pipefail
|
||||
|
||||
HERE="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TOOL="${1:-$HERE/mosaic-worktree.sh}"
|
||||
[ -x "$TOOL" ] || { printf 'test-mosaic-worktree-large-repo: not executable: %s\n' "$TOOL" >&2; exit 2; }
|
||||
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
mkdir -p "$TMP/bin"
|
||||
|
||||
# The stub answers exactly the two calls resolve_repo makes, and answers the
|
||||
# porcelain one with ~450 KB — comfortably past a 64 KB pipe buffer, so the
|
||||
# writer is still writing when a reader that quits early goes away. Anything
|
||||
# else exits non-zero rather than pretending to be git.
|
||||
cat > "$TMP/bin/git" <<'STUB'
|
||||
#!/bin/sh
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in -C) shift 2 ;; *) break ;; esac
|
||||
done
|
||||
case "$*" in
|
||||
"rev-parse --git-dir")
|
||||
echo .git; exit 0 ;;
|
||||
"worktree list --porcelain")
|
||||
# The first entry is the main worktree. That single line is all the helper
|
||||
# needs, and it is exactly what it stopped receiving.
|
||||
printf 'worktree /src/fakerepo\nHEAD %040d\nbranch refs/heads/main\n\n' 0
|
||||
awk 'BEGIN{ for (i = 0; i < 4000; i++)
|
||||
printf "worktree /src/fakerepo-worktrees/w%d\nHEAD %040d\nbranch refs/heads/topic-%d\n\n", i, 0, i }'
|
||||
# NOT `exit 0`. Real git dies of SIGPIPE here and reports 141, and pipefail
|
||||
# in the caller is what turns that into the silent abort. A stub that exits 0
|
||||
# regardless hands the caller a clean status and the probe passes on the
|
||||
# broken tree — which is how this test failed to be a test on its first run.
|
||||
exit $? ;;
|
||||
esac
|
||||
exit 1
|
||||
STUB
|
||||
chmod +x "$TMP/bin/git"
|
||||
|
||||
fail=0
|
||||
check() {
|
||||
local why="$1" want="$2" got="$3"
|
||||
if [ "$want" = "$got" ]; then
|
||||
printf 'ok %s\n' "$why"
|
||||
else
|
||||
printf 'FAIL %s\n want: %s\n got: %s\n' "$why" "$want" "$got"
|
||||
fail=1
|
||||
fi
|
||||
}
|
||||
|
||||
out="$(PATH="$TMP/bin:$PATH" "$TOOL" path feat/workspace-hygiene 2>&1)"
|
||||
rc=$?
|
||||
|
||||
# Both halves are asserted. rc alone would pass if the helper started printing a
|
||||
# usage error, and output alone would miss a non-zero exit — and the defect's
|
||||
# signature is precisely a non-zero exit with no output, which only the pair
|
||||
# distinguishes from every other way this could go wrong.
|
||||
check 'resolving a repo with a large worktree list exits 0' 0 "$rc"
|
||||
check 'and derives the path from the main worktree' /src/fakerepo-worktrees/feat-workspace-hygiene "$out"
|
||||
|
||||
printf '\n'
|
||||
if [ "$fail" -eq 0 ]; then
|
||||
printf 'mosaic-worktree: resolves against a large porcelain stream.\n'
|
||||
else
|
||||
cat <<'EOF'
|
||||
mosaic-worktree could not resolve the repository.
|
||||
|
||||
An empty output with a non-zero exit is the SIGPIPE signature: a reader that
|
||||
quits early (`awk ... exit`, `head -n`) kills the producer, and pipefail turns
|
||||
that into a silent abort. Nothing in this script may close a git pipe early.
|
||||
EOF
|
||||
fi
|
||||
exit "$fail"
|
||||
@@ -1,160 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for secret-safe, identity-bound PR editing and explicit targets.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-edit}"
|
||||
REPO_DIR="$WORK_DIR/repo"; BIN_DIR="$WORK_DIR/bin"; HOME_DIR="$WORK_DIR/home"
|
||||
XDG_DIR="$WORK_DIR/xdg"; LOG_FILE="$WORK_DIR/calls.log"
|
||||
rm -rf "$WORK_DIR"; mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR" "$XDG_DIR/tea"
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/other/wrong-checkout.git
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
cat > "$XDG_DIR/tea/config.yml" <<'YAML'
|
||||
logins:
|
||||
- name: usc-coder3
|
||||
url: https://git.uscllc.com
|
||||
token: fixture-usc-token
|
||||
- name: same-host-other
|
||||
url: https://git.uscllc.com
|
||||
token: fixture-other-token
|
||||
- name: mosaic-coder3
|
||||
url: https://git.mosaicstack.dev
|
||||
token: fixture-mosaic-token
|
||||
YAML
|
||||
|
||||
cat > "$BIN_DIR/tea" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
# Deliberately misleading duplicate-name response: the wrapper must never use
|
||||
# tea for identity validation because its name lookup is not host-bound.
|
||||
[[ "$*" == "api --login duplicate /user" ]] && { printf '{"login":"coder3"}\n'; exit 0; }
|
||||
exit 1
|
||||
SH
|
||||
cat > "$BIN_DIR/curl" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
printf 'curl' >> "$MOSAIC_TEST_LOG"; printf ' <%s>' "$@" >> "$MOSAIC_TEST_LOG"; printf '\n' >> "$MOSAIC_TEST_LOG"
|
||||
if [[ "${*: -1}" == */user ]]; then
|
||||
printf '{"login":"%s"}\n' "${MOSAIC_STUB_AUTH_USER:-coder3}"
|
||||
elif [[ "${*: -1}" == */repos/* && " $* " != *" -X PATCH "* ]]; then
|
||||
[[ "${MOSAIC_STUB_SIGNAL:-}" == "TERM" ]] && { kill -TERM "$PPID"; sleep 1; }
|
||||
[[ "${MOSAIC_STUB_SIGNAL:-}" == "INT" ]] && { kill -INT "$PPID"; sleep 1; }
|
||||
printf '{"name":"repo"}\n'
|
||||
else
|
||||
printf '{"number":42,"draft":false}\n'
|
||||
fi
|
||||
SH
|
||||
cat > "$BIN_DIR/gh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
printf 'gh' >> "$MOSAIC_TEST_LOG"; printf ' <%s>' "$@" >> "$MOSAIC_TEST_LOG"; printf '\n' >> "$MOSAIC_TEST_LOG"
|
||||
SH
|
||||
chmod +x "$BIN_DIR/tea" "$BIN_DIR/curl" "$BIN_DIR/gh" "$SCRIPT_DIR/pr-edit.sh"
|
||||
|
||||
run_wrapper() {
|
||||
(cd "$REPO_DIR"; PATH="$BIN_DIR:$PATH" HOME="$HOME_DIR" XDG_CONFIG_HOME="$XDG_DIR" \
|
||||
MOSAIC_TEST_LOG="$LOG_FILE" "$SCRIPT_DIR/pr-edit.sh" "$@")
|
||||
}
|
||||
assert_no_secret() {
|
||||
! grep -q 'fixture-.*-token' "$LOG_FILE" || { echo "Credential leaked into curl argv/log" >&2; exit 1; }
|
||||
}
|
||||
|
||||
# The explicit target differs from CWD origin and must govern BOTH host and slug.
|
||||
: > "$LOG_FILE"
|
||||
# shellcheck disable=SC2016 # literal backticks prove argument-array body safety.
|
||||
MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 -r mosaicstack/stack \
|
||||
-H git.mosaicstack.dev --title 'New title' --body 'Body with `literal` bytes' --base develop --draft >/dev/null
|
||||
python3 - "$LOG_FILE" <<'PY'
|
||||
import json, pathlib, sys
|
||||
lines = pathlib.Path(sys.argv[1]).read_text().splitlines()
|
||||
assert len(lines) == 3, lines
|
||||
assert "https://git.mosaicstack.dev/api/v1/user" in lines[0], lines
|
||||
assert "https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack" in lines[1], lines
|
||||
assert "https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack/pulls/42" in lines[2], lines
|
||||
assert all("--config" in line for line in lines), lines
|
||||
assert "Authorization:" not in "\n".join(lines), lines
|
||||
payload = lines[2].split(" <-d> <", 1)[1].split("> <https://", 1)[0]
|
||||
assert json.loads(payload) == {"title":"New title","body":"Body with `literal` bytes","base":"develop","draft":True}
|
||||
PY
|
||||
assert_no_secret
|
||||
|
||||
# Ready maps to false and still preflights before the write.
|
||||
: > "$LOG_FILE"
|
||||
MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login usc-coder3 -r USC/uconnect -H git.uscllc.com --ready >/dev/null
|
||||
grep -q '"draft": false' "$LOG_FILE"; assert_no_secret
|
||||
|
||||
# Identity is mandatory; no ambient/first-host login can write.
|
||||
: > "$LOG_FILE"
|
||||
if run_wrapper -n 42 --login usc-coder3 --draft >/dev/null 2>&1; then echo "Unset identity wrote" >&2; exit 1; fi
|
||||
[[ ! -s "$LOG_FILE" ]] || { echo "Unset identity reached curl" >&2; exit 1; }
|
||||
|
||||
# Explicit and ambient same-host wrong principals both refuse after identity
|
||||
# lookup but before repo preflight/PATCH. The /user read is expected curl #1.
|
||||
for mode in explicit ambient; do
|
||||
: > "$LOG_FILE"
|
||||
if [[ "$mode" == explicit ]]; then
|
||||
cmd=(--login same-host-other)
|
||||
else
|
||||
cmd=(); export GITEA_LOGIN=same-host-other
|
||||
fi
|
||||
if MOSAIC_STUB_AUTH_USER=other MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 "${cmd[@]}" -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
|
||||
echo "$mode wrong identity wrote" >&2; exit 1
|
||||
fi
|
||||
unset GITEA_LOGIN
|
||||
[[ "$(wc -l < "$LOG_FILE")" -eq 1 ]] || { echo "$mode wrong identity passed identity lookup" >&2; exit 1; }
|
||||
! grep -q '/repos/' "$LOG_FILE" || { echo "$mode wrong identity reached repo preflight/PATCH" >&2; exit 1; }
|
||||
done
|
||||
|
||||
# Set identity with no explicit/ambient login refuses rather than selecting first host login.
|
||||
: > "$LOG_FILE"
|
||||
if MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
|
||||
echo "Missing login selected a principal" >&2; exit 1
|
||||
fi
|
||||
[[ ! -s "$LOG_FILE" ]] || { echo "Missing login reached curl" >&2; exit 1; }
|
||||
|
||||
# Split-credential probe for the duplicate-name cross-host seam: tea's
|
||||
# name-only /user would report coder3, while the selected host-bound curl token
|
||||
# reports other. The wrapper must trust only the latter handle used by PATCH.
|
||||
: > "$LOG_FILE"
|
||||
if MOSAIC_STUB_AUTH_USER=other MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 \
|
||||
-r mosaicstack/stack -H git.mosaicstack.dev --draft >/dev/null 2>&1; then
|
||||
echo "Duplicate-name split credential reached PATCH" >&2; exit 1
|
||||
fi
|
||||
[[ "$(wc -l < "$LOG_FILE")" -eq 1 ]] || { echo "Duplicate-name identity mismatch passed /user" >&2; cat "$LOG_FILE" >&2; exit 1; }
|
||||
! grep -q -- '-X> <PATCH' "$LOG_FILE" || { echo "Duplicate-name mismatch mutated" >&2; exit 1; }
|
||||
|
||||
# TERM and INT during repo preflight clean up, do not mutate, and return the
|
||||
# signal status rather than swallowing termination into success.
|
||||
for sig in TERM INT; do
|
||||
: > "$LOG_FILE"
|
||||
set +e
|
||||
MOSAIC_STUB_SIGNAL="$sig" MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login usc-coder3 \
|
||||
-r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1
|
||||
rc=$?
|
||||
set -e
|
||||
[[ "$rc" -ne 0 ]] || { echo "$sig was swallowed into success" >&2; exit 1; }
|
||||
[[ "$rc" -eq 143 || "$rc" -eq 130 ]] || { echo "$sig returned unexpected status $rc" >&2; exit 1; }
|
||||
! grep -q -- '-X> <PATCH' "$LOG_FILE" || { echo "$sig continued into PATCH" >&2; exit 1; }
|
||||
assert_no_secret
|
||||
done
|
||||
|
||||
# Cross-host credential fails before curl; explicit target preflight failure blocks PATCH.
|
||||
: > "$LOG_FILE"
|
||||
if MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
|
||||
echo "Cross-host login wrote" >&2; exit 1
|
||||
fi
|
||||
[[ ! -s "$LOG_FILE" ]] || { echo "Cross-host login reached curl" >&2; exit 1; }
|
||||
|
||||
if run_wrapper -n 42 --draft --ready >/dev/null 2>&1; then echo "Accepted conflicting modes" >&2; exit 1; fi
|
||||
if run_wrapper -n 42 >/dev/null 2>&1; then echo "Accepted no-op edit" >&2; exit 1; fi
|
||||
run_wrapper --help 2>&1 | grep -q '^Usage:'
|
||||
|
||||
# GitHub retains provider-native edit/readiness behavior.
|
||||
git -C "$REPO_DIR" remote set-url origin https://github.com/acme/widgets.git
|
||||
: > "$LOG_FILE"; run_wrapper -n 7 --title 'GitHub title' --draft >/dev/null
|
||||
grep -q 'gh <pr> <edit> <7> <--title> <GitHub title>' "$LOG_FILE"
|
||||
grep -q 'gh <pr> <ready> <7> <--undo>' "$LOG_FILE"
|
||||
echo "PR edit regression harness passed"
|
||||
@@ -1,5 +1,5 @@
|
||||
#!/bin/bash
|
||||
# Regression harness for pr-merge.sh Gitea exact-head API path and input safety.
|
||||
# Regression harness for pr-merge.sh Gitea non-interactive tea empty identity fallback.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
@@ -8,7 +8,6 @@ WORK_ROOT="${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
||||
SANDBOX="$WORK_ROOT/pr-merge-empty-uid-test-$$"
|
||||
MOCK_BIN="$SANDBOX/bin"
|
||||
REPO_DIR="$SANDBOX/repo"
|
||||
HOME_DIR="$SANDBOX/home"
|
||||
LOG_FILE="$SANDBOX/mock.log"
|
||||
|
||||
cleanup() {
|
||||
@@ -16,7 +15,7 @@ cleanup() {
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
mkdir -p "$MOCK_BIN" "$REPO_DIR" "$HOME_DIR"
|
||||
mkdir -p "$MOCK_BIN" "$REPO_DIR"
|
||||
: > "$LOG_FILE"
|
||||
|
||||
cat > "$MOCK_BIN/tea" <<'EOF'
|
||||
@@ -52,23 +51,22 @@ for arg in "$@"; do
|
||||
prev=""
|
||||
continue
|
||||
fi
|
||||
if [[ "$prev" == "data" ]]; then
|
||||
if [[ "$prev" == "-d" ]]; then
|
||||
post_data="$arg"
|
||||
[[ "$post_data" == @* ]] && post_data=$(<"${post_data#@}")
|
||||
prev=""
|
||||
continue
|
||||
fi
|
||||
if [[ "$prev" == "config" ]]; then
|
||||
[[ "$arg" == "-" ]] && cat >/dev/null
|
||||
prev=""
|
||||
if [[ "$arg" == "-o" ]]; then
|
||||
prev="-o"
|
||||
continue
|
||||
fi
|
||||
case "$arg" in
|
||||
-o) prev="-o" ;;
|
||||
-d|--data|--data-binary) prev="data" ;;
|
||||
-K|--config) prev="config" ;;
|
||||
-w) write_code=true ;;
|
||||
esac
|
||||
if [[ "$arg" == "-d" ]]; then
|
||||
prev="-d"
|
||||
continue
|
||||
fi
|
||||
if [[ "$arg" == "-w" ]]; then
|
||||
write_code=true
|
||||
fi
|
||||
done
|
||||
emit_response() {
|
||||
local body="$1"
|
||||
@@ -81,24 +79,15 @@ emit_response() {
|
||||
printf '200'
|
||||
fi
|
||||
}
|
||||
if [[ "$args" == *"/api/v1/repos/mosaicstack/stack/commits/0123456789abcdef0123456789abcdef01234567/status"* ]]; then
|
||||
emit_response '{"state":"success","statuses":[{"context":"ci/test","status":"success"}]}'
|
||||
exit 0
|
||||
fi
|
||||
if [[ "$args" == *"/api/v1/repos/mosaicstack/stack/pulls/123"* && "$args" != *"/api/v1/repos/mosaicstack/stack/pulls/123/merge"* ]]; then
|
||||
emit_response '{"number":123,"title":"mock","state":"open","user":{"login":"tester"},"head":{"ref":"feature/mock","sha":"0123456789abcdef0123456789abcdef01234567","repo":{"full_name":"mosaicstack/stack"}},"base":{"ref":"main"},"labels":[],"assignees":[],"html_url":"https://git.mosaicstack.dev/mosaicstack/stack/pulls/123","mergeable":true}'
|
||||
emit_response '{"number":123,"title":"mock","state":"open","user":{"login":"tester"},"head":{"ref":"feature/mock"},"base":{"ref":"main"},"labels":[],"assignees":[],"html_url":"https://git.mosaicstack.dev/mosaicstack/stack/pulls/123","mergeable":true}'
|
||||
exit 0
|
||||
fi
|
||||
if [[ "$args" == *"-X POST"* && "$args" == *"/api/v1/repos/mosaicstack/stack/pulls/123/merge"* ]]; then
|
||||
POST_DATA="$post_data" python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
payload = json.loads(os.environ["POST_DATA"])
|
||||
assert payload == {
|
||||
"Do": "squash",
|
||||
"head_commit_id": "0123456789abcdef0123456789abcdef01234567",
|
||||
}, payload
|
||||
PY
|
||||
if [[ "$post_data" != '{"Do":"squash"}' ]]; then
|
||||
echo "unexpected merge payload: $post_data" >&2
|
||||
exit 96
|
||||
fi
|
||||
emit_response '{"merged":true,"message":"mock merge complete"}'
|
||||
exit 0
|
||||
fi
|
||||
@@ -110,48 +99,7 @@ chmod +x "$MOCK_BIN/curl"
|
||||
cd "$REPO_DIR"
|
||||
git init -q
|
||||
git remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
|
||||
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
|
||||
#
|
||||
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
|
||||
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
|
||||
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
|
||||
# repo. Step 0 runs BEFORE the credential loader AND before the GITEA_TOKEN env
|
||||
# check, so the `GITEA_TOKEN=redacted-test-token` exported below is silently
|
||||
# overridden and a REAL per-slot token from $HOME is what flows through the
|
||||
# wrapper. Measured on a provisioned seat before this pin: all 5 mock-curl calls
|
||||
# carried the real per-slot token in argv and the fixture token was never used at
|
||||
# ALL. Three consequences specific to this suite:
|
||||
# 1. pr-merge.sh passes the token as `-H "Authorization: token $token"` and the
|
||||
# mock curl logs full argv, so the real credential is written to $LOG_FILE
|
||||
# on disk — transiently: the suite truncates that file between phases and
|
||||
# the EXIT trap removes $SANDBOX, so it leaves NO post-hoc trace. That is
|
||||
# why this suite was the hardest of the three to detect; observing it needs
|
||||
# an instrument that captures argv while the run is live.
|
||||
# 2. Every failure path dumps $OUTPUT/$LOG_FILE to stderr through
|
||||
# `sed 's/redacted-test-token/***REDACTED***/g'` — a redaction pattern that
|
||||
# is the literal fixture string and therefore CANNOT match the token
|
||||
# actually in use.
|
||||
# 3. The leak assertion at "Token leaked to pr-merge.sh output" greps for that
|
||||
# same fixture string, so on a provisioned seat it passes vacuously: it is
|
||||
# searching for a value the run never used.
|
||||
# An empty repo-local value shadows the global one and reads back empty at rc=0.
|
||||
#
|
||||
# CONTAINMENT: the sandboxed HOME exported below. It only has to bound a failure
|
||||
# that the pin should already have prevented.
|
||||
#
|
||||
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
|
||||
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
|
||||
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
|
||||
# by construction and every suite reads clean however vulnerable it is. To measure,
|
||||
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
|
||||
# per-slot token) so step 0 reaches its fail-loud branch.
|
||||
#
|
||||
# Note the env-var route does NOT work: detect-platform.sh reads
|
||||
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
# $SANDBOX/$HOME_DIR were derived from the real $HOME above, before this export.
|
||||
export HOME="$HOME_DIR"
|
||||
export PATH="$MOCK_BIN:$PATH"
|
||||
export PR_MERGE_TEST_LOG="$LOG_FILE"
|
||||
export GITEA_LOGIN="git.mosaicstack.dev"
|
||||
@@ -159,8 +107,8 @@ export GITEA_URL="https://git.mosaicstack.dev"
|
||||
export GITEA_TOKEN="redacted-test-token"
|
||||
|
||||
OUTPUT="$SANDBOX/output.log"
|
||||
if ! "$SCRIPT_DIR/pr-merge.sh" -n 123 -m squash > "$OUTPUT" 2>&1; then
|
||||
echo "Expected pr-merge.sh to use the exact-head Gitea API path." >&2
|
||||
if ! "$SCRIPT_DIR/pr-merge.sh" -n 123 -m squash --skip-queue-guard > "$OUTPUT" 2>&1; then
|
||||
echo "Expected pr-merge.sh to recover via Gitea API fallback." >&2
|
||||
echo "--- output ---" >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$OUTPUT" >&2
|
||||
echo "--- mock log ---" >&2
|
||||
@@ -179,6 +127,38 @@ if grep -q 'redacted-test-token' "$OUTPUT"; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
cat > "$MOCK_BIN/tea" <<'EOF'
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
printf 'tea %q ' "$@" >> "$PR_MERGE_TEST_LOG"
|
||||
printf '\n' >> "$PR_MERGE_TEST_LOG"
|
||||
if [[ "$*" == *"login list"* ]]; then
|
||||
echo '[{"name":"git.mosaicstack.dev","url":"https://git.mosaicstack.dev"}]'
|
||||
exit 0
|
||||
fi
|
||||
if [[ "$*" == *"pr merge"* ]]; then
|
||||
echo 'tea network timeout' >&2
|
||||
exit 2
|
||||
fi
|
||||
exit 0
|
||||
EOF
|
||||
chmod +x "$MOCK_BIN/tea"
|
||||
: > "$LOG_FILE"
|
||||
if "$SCRIPT_DIR/pr-merge.sh" -n 123 -m squash --skip-queue-guard > "$OUTPUT" 2>&1; then
|
||||
echo "Expected arbitrary tea failure to remain blocking." >&2
|
||||
exit 1
|
||||
fi
|
||||
if grep -q '/api/v1/repos/mosaicstack/stack/pulls/123/merge' "$LOG_FILE"; then
|
||||
echo "Arbitrary tea failure unexpectedly used Gitea API merge fallback." >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$LOG_FILE" >&2
|
||||
exit 1
|
||||
fi
|
||||
if ! grep -q 'tea network timeout' "$OUTPUT"; then
|
||||
echo "Expected arbitrary tea error to be preserved in output." >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$OUTPUT" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
cat > "$MOCK_BIN/tea" <<'EOF'
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
@@ -197,8 +177,8 @@ EOF
|
||||
chmod +x "$MOCK_BIN/tea"
|
||||
unset GITEA_LOGIN
|
||||
: > "$LOG_FILE"
|
||||
if ! "$SCRIPT_DIR/pr-merge.sh" -n 123 -m squash > "$OUTPUT" 2>&1; then
|
||||
echo "Expected the exact-head API path not to depend on a tea login." >&2
|
||||
if ! "$SCRIPT_DIR/pr-merge.sh" -n 123 -m squash --skip-queue-guard > "$OUTPUT" 2>&1; then
|
||||
echo "Expected missing tea login to use authenticated Gitea API fallback." >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$OUTPUT" >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$LOG_FILE" >&2
|
||||
exit 1
|
||||
@@ -235,7 +215,7 @@ cd "$REPO_DIR"
|
||||
git remote set-url origin https://github.com/mosaicstack/stack.git
|
||||
: > "$LOG_FILE"
|
||||
rm -f "$SENTINEL"
|
||||
if "$SCRIPT_DIR/pr-merge.sh" -n "$INJECTION" -m squash > "$OUTPUT" 2>&1; then
|
||||
if "$SCRIPT_DIR/pr-merge.sh" -n "$INJECTION" -m squash --skip-queue-guard > "$OUTPUT" 2>&1; then
|
||||
echo "Expected GitHub metacharacter PR number to be rejected." >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$OUTPUT" >&2
|
||||
exit 1
|
||||
@@ -260,7 +240,7 @@ git remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
|
||||
export GITEA_LOGIN="git.mosaicstack.dev"
|
||||
: > "$LOG_FILE"
|
||||
rm -f "$SENTINEL"
|
||||
if "$SCRIPT_DIR/pr-merge.sh" -n "$INJECTION" -m squash > "$OUTPUT" 2>&1; then
|
||||
if "$SCRIPT_DIR/pr-merge.sh" -n "$INJECTION" -m squash --skip-queue-guard > "$OUTPUT" 2>&1; then
|
||||
echo "Expected Gitea metacharacter PR number to be rejected." >&2
|
||||
sed 's/redacted-test-token/***REDACTED***/g' "$OUTPUT" >&2
|
||||
exit 1
|
||||
@@ -280,4 +260,4 @@ if ! grep -q 'Invalid PR number' "$OUTPUT"; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "pr-merge.sh Gitea exact-head API regression passed"
|
||||
echo "pr-merge.sh Gitea fallback regression passed"
|
||||
|
||||
@@ -1,173 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# shellcheck disable=SC2030,SC2031 # Provider arms isolate PATH/credentials in subshells.
|
||||
# The commit whose CI was guarded must be the commit the provider atomically merges.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-merge-head-pin}"
|
||||
SHA=0123456789abcdef0123456789abcdef01234567
|
||||
|
||||
make_fixture() {
|
||||
local name="$1" remote="$2"
|
||||
local root="$WORK_DIR/$name"
|
||||
local tools="$root/tools/git"
|
||||
mkdir -p "$tools" "$root/repo"
|
||||
cp "$SCRIPT_DIR/pr-merge.sh" "$tools/pr-merge.sh"
|
||||
cp "$SCRIPT_DIR/detect-platform.sh" "$tools/detect-platform.sh"
|
||||
git -C "$root/repo" init -q
|
||||
git -C "$root/repo" remote add origin "$remote"
|
||||
cat > "$tools/pr-metadata.sh" <<SH
|
||||
#!/usr/bin/env bash
|
||||
printf '%s\n' '{"baseRefName":"main","headRefName":"fix/pinned","headRefOid":"$SHA","headRepository":"contributor/widgets-fork"}'
|
||||
SH
|
||||
cat > "$tools/ci-queue-wait.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
exit 0
|
||||
SH
|
||||
chmod +x "$tools"/*.sh
|
||||
}
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
make_fixture gitea https://git.example.test/acme/widgets.git
|
||||
make_fixture github https://github.com/acme/widgets.git
|
||||
|
||||
cat > "$WORK_DIR/gitea/curl" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
payload=""
|
||||
out_file=""
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
-d|--data|--data-binary)
|
||||
payload="$2"
|
||||
[[ "$payload" == @* ]] && payload=$(<"${payload#@}")
|
||||
shift 2
|
||||
;;
|
||||
-o)
|
||||
out_file="$2"
|
||||
shift 2
|
||||
;;
|
||||
-K|--config)
|
||||
[[ "$2" == "-" ]] && cat >/dev/null
|
||||
shift 2
|
||||
;;
|
||||
-w|-X|-H)
|
||||
shift 2
|
||||
;;
|
||||
*) shift ;;
|
||||
esac
|
||||
done
|
||||
printf '%s' "$payload" > "${MOSAIC_MERGE_PAYLOAD_LOG:?}"
|
||||
[[ -n "$out_file" ]] && printf '{}' > "$out_file"
|
||||
printf '200'
|
||||
SH
|
||||
chmod +x "$WORK_DIR/gitea/curl"
|
||||
|
||||
set +e
|
||||
(
|
||||
cd "$WORK_DIR/gitea/repo"
|
||||
export PATH="$WORK_DIR/gitea:$PATH"
|
||||
export GITEA_TOKEN=stub-token
|
||||
export GITEA_URL=https://git.example.test
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
export MOSAIC_MERGE_PAYLOAD_LOG="$WORK_DIR/gitea-payload.json"
|
||||
env -u MOSAIC_GIT_IDENTITY "$WORK_DIR/gitea/tools/git/pr-merge.sh" -n 123
|
||||
) >"$WORK_DIR/gitea.out" 2>&1
|
||||
gitea_rc=$?
|
||||
set -e
|
||||
if [[ "$gitea_rc" -ne 0 ]]; then
|
||||
echo "FAIL gitea-pin: merge fixture returned $gitea_rc" >&2
|
||||
cat "$WORK_DIR/gitea.out" >&2
|
||||
exit 1
|
||||
fi
|
||||
python3 - "$WORK_DIR/gitea-payload.json" "$SHA" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
payload = json.load(open(sys.argv[1], encoding="utf-8"))
|
||||
assert set(payload) <= {"Do", "head_commit_id", "delete_branch_after_merge"}, payload
|
||||
assert payload.get("Do") == "squash", payload
|
||||
assert payload.get("head_commit_id") == sys.argv[2], payload
|
||||
PY
|
||||
|
||||
# A merge-gate verdict is commit-bound. A stale expected head must fail before merge.
|
||||
wrong_sha=ffffffffffffffffffffffffffffffffffffffff
|
||||
rm -f "$WORK_DIR/gitea-payload-stale.json"
|
||||
set +e
|
||||
(
|
||||
cd "$WORK_DIR/gitea/repo"
|
||||
export PATH="$WORK_DIR/gitea:$PATH"
|
||||
export GITEA_TOKEN=stub-token
|
||||
export GITEA_URL=https://git.example.test
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
export MOSAIC_MERGE_PAYLOAD_LOG="$WORK_DIR/gitea-payload-stale.json"
|
||||
env -u MOSAIC_GIT_IDENTITY "$WORK_DIR/gitea/tools/git/pr-merge.sh" -n 123 --expect-head "$wrong_sha"
|
||||
) >"$WORK_DIR/gitea-stale.out" 2>&1
|
||||
stale_rc=$?
|
||||
set -e
|
||||
if [[ "$stale_rc" -eq 0 ]] || [[ -e "$WORK_DIR/gitea-payload-stale.json" ]]; then
|
||||
echo "FAIL stale-verdict: moved head was not refused before provider merge" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# A merge-capable path cannot bypass the mandatory queue guard. The legacy
|
||||
# --skip-queue-guard option must be rejected before any provider merge call.
|
||||
cat > "$WORK_DIR/gitea/tools/git/ci-queue-wait.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
exit 99
|
||||
SH
|
||||
chmod +x "$WORK_DIR/gitea/tools/git/ci-queue-wait.sh"
|
||||
rm -f "$WORK_DIR/gitea-payload-bypass.json"
|
||||
set +e
|
||||
(
|
||||
cd "$WORK_DIR/gitea/repo"
|
||||
export PATH="$WORK_DIR/gitea:$PATH"
|
||||
export GITEA_TOKEN=stub-token
|
||||
export GITEA_URL=https://git.example.test
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
export MOSAIC_MERGE_PAYLOAD_LOG="$WORK_DIR/gitea-payload-bypass.json"
|
||||
env -u MOSAIC_GIT_IDENTITY "$WORK_DIR/gitea/tools/git/pr-merge.sh" -n 123 --skip-queue-guard
|
||||
) >"$WORK_DIR/gitea-bypass.out" 2>&1
|
||||
bypass_rc=$?
|
||||
set -e
|
||||
if [[ "$bypass_rc" -eq 0 ]] || [[ -e "$WORK_DIR/gitea-payload-bypass.json" ]]; then
|
||||
echo "FAIL merge-bypass: --skip-queue-guard reached the provider merge path" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Dry-run is the only path that may omit the guard because it exits before the
|
||||
# provider merge dispatch. Prove the exit and absence of a merge payload.
|
||||
rm -f "$WORK_DIR/gitea-payload-dry-run.json"
|
||||
(
|
||||
cd "$WORK_DIR/gitea/repo"
|
||||
export PATH="$WORK_DIR/gitea:$PATH"
|
||||
export GITEA_TOKEN=stub-token
|
||||
export GITEA_URL=https://git.example.test
|
||||
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
|
||||
export MOSAIC_MERGE_PAYLOAD_LOG="$WORK_DIR/gitea-payload-dry-run.json"
|
||||
env -u MOSAIC_GIT_IDENTITY "$WORK_DIR/gitea/tools/git/pr-merge.sh" -n 123 --dry-run
|
||||
) >"$WORK_DIR/gitea-dry-run.out" 2>&1
|
||||
if [[ -e "$WORK_DIR/gitea-payload-dry-run.json" ]]; then
|
||||
echo "FAIL dry-run: non-merging preflight reached the provider merge path" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
cat > "$WORK_DIR/github/gh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
printf '%s\n' "$*" > "${MOSAIC_GH_MERGE_LOG:?}"
|
||||
SH
|
||||
chmod +x "$WORK_DIR/github/gh"
|
||||
(
|
||||
cd "$WORK_DIR/github/repo"
|
||||
export PATH="$WORK_DIR/github:$PATH"
|
||||
export MOSAIC_GH_MERGE_LOG="$WORK_DIR/github-call.log"
|
||||
"$WORK_DIR/github/tools/git/pr-merge.sh" -n 123
|
||||
) >"$WORK_DIR/github.out" 2>&1
|
||||
if ! grep -q -- "--match-head-commit $SHA" "$WORK_DIR/github-call.log"; then
|
||||
echo "FAIL github-pin: merge command omitted --match-head-commit $SHA" >&2
|
||||
cat "$WORK_DIR/github-call.log" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "PR merge exact-head pin regression passed (Gitea + GitHub)"
|
||||
@@ -1,541 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for the optional, identity-checked Gitea squash message.
|
||||
|
||||
set -u
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
SUBJECT="${MOSAIC_TEST_SUBJECT:-$SCRIPT_DIR/pr-merge.sh}"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-merge-message-field}"
|
||||
ORIG_PATH="$PATH"
|
||||
failures=0
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$WORK_DIR"
|
||||
|
||||
fail() {
|
||||
echo "FAIL $1" >&2
|
||||
failures=$((failures + 1))
|
||||
}
|
||||
|
||||
make_case() {
|
||||
local name="$1" case_dir
|
||||
case_dir="$WORK_DIR/$name"
|
||||
mkdir -p "$case_dir/bin" "$case_dir/agent"
|
||||
cp "$SUBJECT" "$case_dir/pr-merge.sh"
|
||||
chmod +x "$case_dir/pr-merge.sh"
|
||||
|
||||
cat > "$case_dir/detect-platform.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
detect_platform() { PLATFORM=gitea; printf 'gitea\n'; }
|
||||
get_repo_owner() { printf 'acme\n'; }
|
||||
get_repo_name() { printf 'widgets\n'; }
|
||||
get_remote_host() { printf 'git.example.test\n'; }
|
||||
get_gitea_token() {
|
||||
printf 'resolved\n' >> "${MOSAIC_TEST_TOKEN_RESOLUTION_LOG:?}"
|
||||
if [[ "${MOSAIC_TEST_TOKEN_AVAILABLE:-true}" != "true" ]]; then
|
||||
return 1
|
||||
fi
|
||||
printf 'fixture-token\n'
|
||||
}
|
||||
get_gitea_basic_auth() {
|
||||
printf 'resolved\n' >> "${MOSAIC_TEST_BASIC_RESOLUTION_LOG:?}"
|
||||
if [[ "${MOSAIC_TEST_BASIC_AVAILABLE:-false}" == "true" ]]; then
|
||||
printf 'fixture-user:fixture-password\n'
|
||||
return "${MOSAIC_TEST_BASIC_RC:-0}"
|
||||
fi
|
||||
return 1
|
||||
}
|
||||
get_gitea_login_for_host() { return 1; }
|
||||
SH
|
||||
|
||||
cat > "$case_dir/pr-metadata.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
if [[ "${MOSAIC_TEST_TITLE_MODE:-safe}" == "injection" ]]; then
|
||||
title='Preserve authors\n\nCo-authored-by: victim <[email protected]>'
|
||||
else
|
||||
title='Preserve both branch authors'
|
||||
fi
|
||||
case "${MOSAIC_TEST_COMMITS_MODE:?}" in
|
||||
verified) head_sha=2222222222222222222222222222222222222222 ;;
|
||||
null-login|unsafe-identity) head_sha=3333333333333333333333333333333333333333 ;;
|
||||
single) head_sha=1111111111111111111111111111111111111111 ;;
|
||||
*) echo "unknown commits mode" >&2; exit 2 ;;
|
||||
esac
|
||||
printf '{"number":42,"title":"%s","author":"poster","baseRefName":"main","headRefName":"feature/fixture","headRefOid":"%s","headRepository":"acme/widgets"}\n' "$title" "$head_sha"
|
||||
SH
|
||||
|
||||
cat > "$case_dir/ci-queue-wait.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
exit 0
|
||||
SH
|
||||
|
||||
cat > "$case_dir/bin/python3" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
*"Preserve both branch authors"*|*"[email protected]"*)
|
||||
: > "${MOSAIC_TEST_METADATA_ARGV_MARKER:?}"
|
||||
;;
|
||||
esac
|
||||
done
|
||||
exec "${MOSAIC_TEST_REAL_PYTHON:?}" "$@"
|
||||
SH
|
||||
|
||||
cat > "$case_dir/bin/curl" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -eu
|
||||
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
*"Preserve both branch authors"*|*"[email protected]"*)
|
||||
: > "${MOSAIC_TEST_METADATA_ARGV_MARKER:?}"
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
url=""
|
||||
method="GET"
|
||||
out_file=""
|
||||
data=""
|
||||
config=""
|
||||
auth_mode="none"
|
||||
has_max_filesize=0
|
||||
has_max_time=0
|
||||
has_connect_timeout=0
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
-o)
|
||||
out_file="$2"
|
||||
shift 2
|
||||
;;
|
||||
-w)
|
||||
shift 2
|
||||
;;
|
||||
-X)
|
||||
method="$2"
|
||||
shift 2
|
||||
;;
|
||||
-d|--data|--data-binary)
|
||||
data="$2"
|
||||
if [[ "$data" == @* ]]; then
|
||||
data=$(<"${data#@}")
|
||||
fi
|
||||
shift 2
|
||||
;;
|
||||
-K|--config)
|
||||
if [[ "$2" == "-" ]]; then
|
||||
config=$(cat)
|
||||
fi
|
||||
shift 2
|
||||
;;
|
||||
--max-filesize)
|
||||
has_max_filesize=1
|
||||
shift 2
|
||||
;;
|
||||
--max-time)
|
||||
has_max_time=1
|
||||
shift 2
|
||||
;;
|
||||
--connect-timeout)
|
||||
has_connect_timeout=1
|
||||
shift 2
|
||||
;;
|
||||
-H|--header|-u|--user)
|
||||
if [[ "$2" == *"fixture-token"* ]]; then
|
||||
: > "${MOSAIC_TEST_TOKEN_ARGV_MARKER:?}"
|
||||
fi
|
||||
if [[ "$2" == *"fixture-password"* ]]; then
|
||||
: > "${MOSAIC_TEST_BASIC_ARGV_MARKER:?}"
|
||||
fi
|
||||
shift 2
|
||||
;;
|
||||
http://*|https://*)
|
||||
url="$1"
|
||||
shift
|
||||
;;
|
||||
*)
|
||||
shift
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [[ "$config" == *"Authorization: token fixture-token"* ]]; then
|
||||
auth_mode="token"
|
||||
: > "${MOSAIC_TEST_AUTH_CONFIG_MARKER:?}"
|
||||
elif [[ "$config" == *"user = \"fixture-user:fixture-password\""* ]]; then
|
||||
auth_mode="basic"
|
||||
: > "${MOSAIC_TEST_BASIC_CONFIG_MARKER:?}"
|
||||
fi
|
||||
printf '%s %s %s\n' "$method" "$auth_mode" "$url" >> "${MOSAIC_TEST_CURL_LOG:?}"
|
||||
printf '%s:%s:%s\n' "$has_max_filesize" "$has_max_time" "$has_connect_timeout" >> "${MOSAIC_TEST_CURL_BOUNDS_LOG:?}"
|
||||
|
||||
case "$url" in
|
||||
*/pulls/42)
|
||||
case "${MOSAIC_TEST_COMMITS_MODE:?}" in
|
||||
verified) head_sha=2222222222222222222222222222222222222222 ;;
|
||||
null-login|unsafe-identity) head_sha=3333333333333333333333333333333333333333 ;;
|
||||
single) head_sha=1111111111111111111111111111111111111111 ;;
|
||||
*) echo "unknown commits mode" >&2; exit 2 ;;
|
||||
esac
|
||||
if [[ "${MOSAIC_TEST_HEAD_MODE:-stable}" == "moved" ]]; then
|
||||
head_sha=4444444444444444444444444444444444444444
|
||||
fi
|
||||
body="{\"head\":{\"sha\":\"$head_sha\"}}"
|
||||
code=200
|
||||
if [[ "${MOSAIC_TEST_FALLBACK_MODE:-none}" == "inspection" && "$auth_mode" == "token" ]]; then
|
||||
body='{"message":"token rejected"}'
|
||||
code=401
|
||||
fi
|
||||
;;
|
||||
*/pulls/42/commits*)
|
||||
case "${MOSAIC_TEST_COMMITS_MODE:?}" in
|
||||
verified)
|
||||
if [[ "${MOSAIC_TEST_EMAIL_MODE:-safe}" == "escape" ]]; then
|
||||
body='[{"sha":"2222222222222222222222222222222222222222","commit":{"author":{"name":"Alice","email":"alice+\u001b[[email protected]"}},"author":{"login":"alice"}},{"sha":"1111111111111111111111111111111111111111","commit":{"author":{"name":"Poster","email":"[email protected]"}},"author":{"login":"poster"}}]'
|
||||
else
|
||||
body='[{"sha":"2222222222222222222222222222222222222222","commit":{"author":{"name":"Alice","email":"[email protected]"}},"author":{"login":"alice"}},{"sha":"1111111111111111111111111111111111111111","commit":{"author":{"name":"Poster","email":"[email protected]"}},"author":{"login":"poster"}}]'
|
||||
fi
|
||||
;;
|
||||
null-login)
|
||||
body='[{"sha":"1111111111111111111111111111111111111111","commit":{"author":{"name":"Poster","email":"[email protected]"}},"author":{"login":"poster"}},{"sha":"3333333333333333333333333333333333333333","commit":{"author":{"name":"Unresolved Author","email":"[email protected]\n\u001b[31m"}},"author":null}]'
|
||||
;;
|
||||
unsafe-identity)
|
||||
body='[{"sha":"unsafe\n\u001b[31m","commit":{"author":{"name":"Unsafe","email":"not-an-email"}},"author":{"login":"unsafe"}},{"sha":"3333333333333333333333333333333333333333","commit":{"author":{"name":"Poster","email":"[email protected]"}},"author":{"login":"poster"}}]'
|
||||
;;
|
||||
single)
|
||||
body='[{"sha":"1111111111111111111111111111111111111111","commit":{"author":{"name":"Poster","email":"[email protected]"}},"author":{"login":"poster"}}]'
|
||||
;;
|
||||
*)
|
||||
echo "unknown commits mode" >&2
|
||||
exit 2
|
||||
;;
|
||||
esac
|
||||
code=200
|
||||
if [[ "${MOSAIC_TEST_FALLBACK_MODE:-none}" == "inspection" && "$auth_mode" == "token" ]]; then
|
||||
body='{"message":"token rejected"}'
|
||||
code=401
|
||||
fi
|
||||
;;
|
||||
*/pulls/42/merge)
|
||||
body='{}'
|
||||
code=200
|
||||
if [[ "${MOSAIC_TEST_FALLBACK_MODE:-none}" == "merge" && "$auth_mode" == "token" ]]; then
|
||||
body='{"message":"token rejected"}'
|
||||
code=401
|
||||
elif [[ "${MOSAIC_TEST_FALLBACK_MODE:-none}" == "provider-error" ]]; then
|
||||
body='{"message":"branch policy rejected\n\u001b[31m"}'
|
||||
code=409
|
||||
elif [[ "${MOSAIC_TEST_FALLBACK_MODE:-none}" == "forbidden" ]]; then
|
||||
body='{"message":"permission denied"}'
|
||||
code=403
|
||||
else
|
||||
printf '%s' "$data" > "${MOSAIC_TEST_MERGE_PAYLOAD:?}"
|
||||
fi
|
||||
;;
|
||||
*/users/*)
|
||||
body='{"message":"not found"}'
|
||||
code=404
|
||||
;;
|
||||
*)
|
||||
body='{"message":"unexpected URL"}'
|
||||
code=500
|
||||
;;
|
||||
esac
|
||||
|
||||
if [[ -n "$out_file" ]]; then
|
||||
printf '%s' "$body" > "$out_file"
|
||||
else
|
||||
printf '%s' "$body"
|
||||
fi
|
||||
printf '%s' "$code"
|
||||
case "${MOSAIC_TEST_CURL_FAILURE:-none}" in
|
||||
oversize) exit 63 ;;
|
||||
stalled) exit 28 ;;
|
||||
esac
|
||||
SH
|
||||
|
||||
chmod +x "$case_dir/detect-platform.sh" "$case_dir/pr-metadata.sh" \
|
||||
"$case_dir/ci-queue-wait.sh" "$case_dir/bin/curl" "$case_dir/bin/python3"
|
||||
printf '%s\n' "$case_dir"
|
||||
}
|
||||
|
||||
run_case() {
|
||||
local case_dir="$1" mode="$2"
|
||||
shift 2
|
||||
MOSAIC_TEST_COMMITS_MODE="$mode" \
|
||||
MOSAIC_TEST_CURL_LOG="$case_dir/curl.log" \
|
||||
MOSAIC_TEST_CURL_BOUNDS_LOG="$case_dir/curl-bounds.log" \
|
||||
MOSAIC_TEST_MERGE_PAYLOAD="$case_dir/merge-payload.json" \
|
||||
MOSAIC_TEST_TOKEN_ARGV_MARKER="$case_dir/token-in-argv" \
|
||||
MOSAIC_TEST_BASIC_ARGV_MARKER="$case_dir/basic-in-argv" \
|
||||
MOSAIC_TEST_AUTH_CONFIG_MARKER="$case_dir/auth-via-config" \
|
||||
MOSAIC_TEST_BASIC_CONFIG_MARKER="$case_dir/basic-via-config" \
|
||||
MOSAIC_TEST_TOKEN_RESOLUTION_LOG="$case_dir/token-resolution.log" \
|
||||
MOSAIC_TEST_BASIC_RESOLUTION_LOG="$case_dir/basic-resolution.log" \
|
||||
MOSAIC_TEST_METADATA_ARGV_MARKER="$case_dir/metadata-in-argv" \
|
||||
MOSAIC_TEST_REAL_PYTHON="$(command -v python3)" \
|
||||
AGENT_WORK_ROOT="$case_dir/agent" \
|
||||
PATH="$case_dir/bin:$ORIG_PATH" \
|
||||
"$case_dir/pr-merge.sh" -n 42 "$@"
|
||||
}
|
||||
|
||||
# Verified multi-author path: the non-poster trailer is built from one commit's
|
||||
# linked author.login and that same commit's author email. No /users lookup.
|
||||
verified_dir=$(make_case verified)
|
||||
set +e
|
||||
verified_output=$(run_case "$verified_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
verified_rc=$?
|
||||
set -e
|
||||
if [[ "$verified_rc" -ne 0 ]]; then
|
||||
fail "verified multi-author merge expected rc=0, got rc=$verified_rc: $verified_output"
|
||||
elif [[ ! -s "$verified_dir/merge-payload.json" ]]; then
|
||||
fail "verified multi-author merge did not reach the API payload"
|
||||
else
|
||||
python3 - "$verified_dir/merge-payload.json" <<'PY' || fail "verified payload did not preserve squash and exact message fields"
|
||||
import json
|
||||
import sys
|
||||
payload = json.load(open(sys.argv[1], encoding="utf-8"))
|
||||
assert payload == {
|
||||
"Do": "squash",
|
||||
"head_commit_id": "2222222222222222222222222222222222222222",
|
||||
"MergeTitleField": "Preserve both branch authors",
|
||||
"MergeMessageField": "Co-authored-by: alice <[email protected]>",
|
||||
}, payload
|
||||
PY
|
||||
fi
|
||||
[[ -e "$verified_dir/auth-via-config" ]] || fail "verified path did not authenticate curl through stdin config"
|
||||
[[ ! -e "$verified_dir/token-in-argv" ]] || fail "verified path placed the Gitea token in curl argv"
|
||||
[[ ! -e "$verified_dir/metadata-in-argv" ]] || fail "verified path placed PR title or contributor email in child argv"
|
||||
[[ "$(wc -l < "$verified_dir/token-resolution.log")" -eq 1 ]] || fail "verified path did not bind inspection and merge to one credential resolution"
|
||||
if grep -q '/users/' "$verified_dir/curl.log" 2>/dev/null; then
|
||||
fail "verified path performed a forbidden second /users lookup"
|
||||
fi
|
||||
if grep -qv '^1:1:1$' "$verified_dir/curl-bounds.log"; then
|
||||
fail "verified path did not apply size/max-time/connect-time bounds to every provider download"
|
||||
fi
|
||||
|
||||
# A linked email containing a terminal escape must block before mutation.
|
||||
escape_email_dir=$(make_case escape-email)
|
||||
set +e
|
||||
escape_email_output=$(MOSAIC_TEST_EMAIL_MODE=escape run_case "$escape_email_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
escape_email_rc=$?
|
||||
set -e
|
||||
[[ "$escape_email_rc" -ne 0 ]] || fail "control-byte email unexpectedly passed"
|
||||
[[ "$escape_email_output" == *"unusable linked identity"* ]] || fail "control-byte email refusal lost its diagnostic"
|
||||
[[ ! -e "$escape_email_dir/merge-payload.json" ]] || fail "control-byte email reached the merge API"
|
||||
|
||||
# Curl transfer and duration failures must remain failures even with HTTP 200.
|
||||
for failure_mode in oversize stalled; do
|
||||
failure_dir=$(make_case "curl-$failure_mode")
|
||||
set +e
|
||||
failure_output=$(MOSAIC_TEST_CURL_FAILURE="$failure_mode" run_case "$failure_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
failure_rc=$?
|
||||
set -e
|
||||
[[ "$failure_rc" -ne 0 ]] || fail "curl $failure_mode failure was discarded: $failure_output"
|
||||
[[ ! -e "$failure_dir/merge-payload.json" ]] || fail "curl $failure_mode failure reached the merge API"
|
||||
done
|
||||
|
||||
# The authenticated head is re-read under the mutation credential but cannot
|
||||
# replace the canonical preflight/review head. A move blocks before enumeration
|
||||
# or mutation even though the provider returned a valid new SHA.
|
||||
moved_dir=$(make_case moved-head)
|
||||
set +e
|
||||
moved_output=$(MOSAIC_TEST_HEAD_MODE=moved \
|
||||
run_case "$moved_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
moved_rc=$?
|
||||
set -e
|
||||
[[ "$moved_rc" -ne 0 ]] || fail "moved authenticated head unexpectedly passed"
|
||||
[[ "$moved_output" == *"authenticated PR head moved from reviewed"* ]] || fail "moved head refusal lost its diagnostic"
|
||||
[[ "$moved_output" == *"tl-mosaic"* ]] || fail "moved head refusal omitted the named escalation principal"
|
||||
[[ ! -e "$moved_dir/merge-payload.json" ]] || fail "moved head refusal reached the merge API"
|
||||
moved_sequence=$(awk '{print $1 ":" $2}' "$moved_dir/curl.log" | paste -sd, -)
|
||||
[[ "$moved_sequence" == "GET:token" ]] || fail "moved head refusal performed post-move inspection/mutation (calls=$moved_sequence)"
|
||||
|
||||
# Token resolution failure is not an authentication response. It must fail
|
||||
# closed instead of borrowing a Basic credential under a different principal.
|
||||
token_missing_dir=$(make_case token-missing)
|
||||
set +e
|
||||
token_missing_output=$(MOSAIC_TEST_TOKEN_AVAILABLE=false MOSAIC_TEST_BASIC_AVAILABLE=true \
|
||||
run_case "$token_missing_dir" single 2>&1)
|
||||
token_missing_rc=$?
|
||||
set -e
|
||||
[[ "$token_missing_rc" -ne 0 ]] || fail "missing token unexpectedly borrowed Basic Auth"
|
||||
[[ "$token_missing_output" == *"required Gitea token"* ]] || fail "missing token refusal lost its diagnostic"
|
||||
[[ ! -e "$token_missing_dir/basic-resolution.log" ]] || fail "missing token resolved Basic Auth after identity failure"
|
||||
[[ ! -e "$token_missing_dir/curl.log" ]] || fail "missing token reached a provider request"
|
||||
|
||||
# A failed Basic resolver must never use its nonempty output or reach mutation.
|
||||
basic_rc_dir=$(make_case basic-resolver-rc)
|
||||
set +e
|
||||
basic_rc_output=$(MOSAIC_TEST_BASIC_AVAILABLE=true MOSAIC_TEST_BASIC_RC=91 MOSAIC_TEST_FALLBACK_MODE=inspection \
|
||||
run_case "$basic_rc_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
basic_rc_rc=$?
|
||||
set -e
|
||||
[[ "$basic_rc_rc" -ne 0 ]] || fail "failed Basic resolver output unexpectedly authorized a merge: $basic_rc_output"
|
||||
[[ ! -e "$basic_rc_dir/merge-payload.json" ]] || fail "failed Basic resolver reached the merge API"
|
||||
|
||||
# HTTP 401 never changes principals: inspection rejection fails closed without
|
||||
# resolving or attempting Basic Auth.
|
||||
fallback_inspect_dir=$(make_case fallback-inspection)
|
||||
set +e
|
||||
fallback_inspect_output=$(MOSAIC_TEST_BASIC_AVAILABLE=true MOSAIC_TEST_FALLBACK_MODE=inspection \
|
||||
run_case "$fallback_inspect_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
fallback_inspect_rc=$?
|
||||
set -e
|
||||
[[ "$fallback_inspect_rc" -ne 0 ]] || fail "inspection token rejection unexpectedly changed principals"
|
||||
[[ "$fallback_inspect_output" == *"refusing cross-principal credential fallback"* ]] || fail "inspection token rejection lost its refusal diagnostic"
|
||||
[[ ! -e "$fallback_inspect_dir/basic-resolution.log" ]] || fail "inspection token rejection resolved Basic Auth"
|
||||
[[ ! -e "$fallback_inspect_dir/merge-payload.json" ]] || fail "inspection token rejection reached merge mutation"
|
||||
inspect_sequence=$(awk '{print $1 ":" $2}' "$fallback_inspect_dir/curl.log" | paste -sd, -)
|
||||
[[ "$inspect_sequence" == "GET:token" ]] || fail "inspection rejection made unexpected provider calls (calls=$inspect_sequence)"
|
||||
|
||||
# Token rejection at merge likewise fails closed without cross-principal retry.
|
||||
fallback_merge_dir=$(make_case fallback-merge)
|
||||
set +e
|
||||
fallback_merge_output=$(MOSAIC_TEST_BASIC_AVAILABLE=true MOSAIC_TEST_FALLBACK_MODE=merge \
|
||||
run_case "$fallback_merge_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
fallback_merge_rc=$?
|
||||
set -e
|
||||
[[ "$fallback_merge_rc" -ne 0 ]] || fail "merge token rejection unexpectedly changed principals"
|
||||
[[ "$fallback_merge_output" == *"refusing cross-principal credential fallback"* ]] || fail "merge token rejection lost its refusal diagnostic"
|
||||
[[ ! -e "$fallback_merge_dir/basic-resolution.log" ]] || fail "merge token rejection resolved Basic Auth"
|
||||
[[ ! -e "$fallback_merge_dir/merge-payload.json" ]] || fail "merge token rejection recorded a successful payload"
|
||||
merge_sequence=$(awk '{print $1 ":" $2}' "$fallback_merge_dir/curl.log" | paste -sd, -)
|
||||
[[ "$merge_sequence" == "GET:token,GET:token,POST:token" ]] || fail "merge rejection made unexpected provider calls (calls=$merge_sequence)"
|
||||
|
||||
# BLOCK path: a commit email exists but author.login is null. It must name both
|
||||
# facts, name the escalation principal, and never reach the merge endpoint.
|
||||
null_dir=$(make_case null-login)
|
||||
set +e
|
||||
null_output=$(run_case "$null_dir" null-login --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
null_rc=$?
|
||||
set -e
|
||||
[[ "$null_rc" -ne 0 ]] || fail "null-login author expected a non-zero BLOCK"
|
||||
[[ "$null_output" == *"BLOCK"* ]] || fail "null-login author omitted BLOCK diagnostic"
|
||||
[[ "$null_output" == *"author.login=NULL"* ]] || fail "null-login author omitted the null provider fact"
|
||||
[[ "$null_output" == *"[email protected]"* ]] || fail "null-login author omitted the commit email fact"
|
||||
[[ "$null_output" == *'\n\x1b[31m'* ]] || fail "null-login author diagnostic did not escape control characters"
|
||||
[[ "$null_output" != *$'\033'* ]] || fail "null-login author diagnostic emitted a raw terminal escape"
|
||||
[[ "$(printf '%s\n' "$null_output" | wc -l)" -eq 1 ]] || fail "null-login author diagnostic permitted newline injection"
|
||||
[[ "$null_output" == *"tl-mosaic"* ]] || fail "null-login author omitted the named escalation principal"
|
||||
[[ ! -e "$null_dir/merge-payload.json" ]] || fail "null-login BLOCK still reached the merge API"
|
||||
|
||||
# Every provider-derived field in alternate BLOCK diagnostics is log-safe too,
|
||||
# including an invalid non-head SHA that contains control characters.
|
||||
unsafe_dir=$(make_case unsafe-identity)
|
||||
set +e
|
||||
unsafe_output=$(run_case "$unsafe_dir" unsafe-identity --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
unsafe_rc=$?
|
||||
set -e
|
||||
[[ "$unsafe_rc" -ne 0 ]] || fail "unsafe identity expected a non-zero BLOCK"
|
||||
[[ "$unsafe_output" == *"unusable linked identity"* ]] || fail "unsafe identity omitted its BLOCK reason"
|
||||
[[ "$unsafe_output" == *'\n\x1b[31m'* ]] || fail "unsafe identity SHA did not escape control characters"
|
||||
[[ "$unsafe_output" != *$'\033'* ]] || fail "unsafe identity diagnostic emitted a raw terminal escape"
|
||||
[[ "$(printf '%s\n' "$unsafe_output" | wc -l)" -eq 1 ]] || fail "unsafe identity diagnostic permitted newline injection"
|
||||
[[ ! -e "$unsafe_dir/merge-payload.json" ]] || fail "unsafe identity BLOCK still reached the merge API"
|
||||
|
||||
# The provider PR title cannot add an unchecked trailer outside the constructed
|
||||
# message field: multi-line and trailer-shaped titles block before mutation.
|
||||
title_dir=$(make_case title-injection)
|
||||
set +e
|
||||
title_output=$(MOSAIC_TEST_TITLE_MODE=injection \
|
||||
run_case "$title_dir" verified --co-author-trailers --escalate-to tl-mosaic 2>&1)
|
||||
title_rc=$?
|
||||
set -e
|
||||
[[ "$title_rc" -ne 0 ]] || fail "title trailer injection unexpectedly passed"
|
||||
[[ "$title_output" == *"not one printable, non-trailer line"* ]] || fail "title injection refusal lost its diagnostic"
|
||||
[[ ! -e "$title_dir/merge-payload.json" ]] || fail "title injection reached the merge API"
|
||||
|
||||
# Provider failures remain diagnosable after their temporary response file is
|
||||
# removed, but provider-controlled control characters stay log-safe.
|
||||
error_dir=$(make_case provider-error)
|
||||
set +e
|
||||
error_output=$(MOSAIC_TEST_BASIC_AVAILABLE=true MOSAIC_TEST_FALLBACK_MODE=provider-error \
|
||||
run_case "$error_dir" single 2>&1)
|
||||
error_rc=$?
|
||||
set -e
|
||||
[[ "$error_rc" -ne 0 ]] || fail "provider error unexpectedly passed"
|
||||
[[ "$error_output" == *"HTTP 409"* ]] || fail "provider error omitted the HTTP status"
|
||||
[[ "$error_output" == *"branch policy rejected"* ]] || fail "provider error response was discarded"
|
||||
[[ "$error_output" == *'\n\x1b[31m'* ]] || fail "provider error response did not escape control characters"
|
||||
[[ "$error_output" != *$'\033'* ]] || fail "provider error response emitted a raw terminal escape"
|
||||
[[ "$error_output" != *"Basic Auth fallback"* ]] || fail "provider error advertised removed Basic Auth fallback"
|
||||
[[ ! -e "$error_dir/basic-resolution.log" ]] || fail "HTTP 409 policy denial incorrectly triggered Basic Auth fallback"
|
||||
|
||||
# Authorization denials likewise fail closed instead of changing principals.
|
||||
forbidden_dir=$(make_case forbidden)
|
||||
set +e
|
||||
forbidden_output=$(MOSAIC_TEST_BASIC_AVAILABLE=true MOSAIC_TEST_FALLBACK_MODE=forbidden \
|
||||
run_case "$forbidden_dir" single 2>&1)
|
||||
forbidden_rc=$?
|
||||
set -e
|
||||
[[ "$forbidden_rc" -ne 0 ]] || fail "HTTP 403 authorization denial unexpectedly passed"
|
||||
[[ "$forbidden_output" == *"HTTP 403"* ]] || fail "authorization denial omitted the HTTP status"
|
||||
[[ "$forbidden_output" != *"Basic Auth fallback"* ]] || fail "authorization denial advertised removed Basic Auth fallback"
|
||||
[[ ! -e "$forbidden_dir/basic-resolution.log" ]] || fail "HTTP 403 authorization denial incorrectly triggered Basic Auth fallback"
|
||||
|
||||
# The BLOCK destination cannot be generic or inferred after failure: opting in
|
||||
# without a named principal is refused before any provider operation.
|
||||
principal_dir=$(make_case missing-principal)
|
||||
set +e
|
||||
principal_output=$(run_case "$principal_dir" verified --co-author-trailers 2>&1)
|
||||
principal_rc=$?
|
||||
set -e
|
||||
[[ "$principal_rc" -ne 0 ]] || fail "co-author mode without a named principal unexpectedly passed"
|
||||
[[ "$principal_output" == *"requires --escalate-to with a named principal"* ]] || fail "missing-principal refusal lost its diagnostic"
|
||||
[[ ! -e "$principal_dir/merge-payload.json" ]] || fail "missing-principal refusal reached the merge API"
|
||||
|
||||
# A trailing value-taking option receives a stable CLI diagnostic instead of a
|
||||
# set -u unbound-variable crash.
|
||||
value_dir=$(make_case missing-principal-value)
|
||||
set +e
|
||||
value_output=$(run_case "$value_dir" verified --co-author-trailers --escalate-to 2>&1)
|
||||
value_rc=$?
|
||||
set -e
|
||||
[[ "$value_rc" -ne 0 ]] || fail "missing --escalate-to value unexpectedly passed"
|
||||
[[ "$value_output" == *"--escalate-to requires one principal name"* ]] || fail "missing --escalate-to value lost its diagnostic"
|
||||
[[ "$value_output" != *"unbound variable"* ]] || fail "missing --escalate-to value crashed under set -u"
|
||||
[[ ! -e "$value_dir/merge-payload.json" ]] || fail "missing --escalate-to value reached the merge API"
|
||||
|
||||
# Negative control: ordinary single-author merge remains byte-for-byte payload
|
||||
# compatible and hardcoded to squash, with no optional message fields.
|
||||
single_dir=$(make_case single)
|
||||
set +e
|
||||
single_output=$(run_case "$single_dir" single 2>&1)
|
||||
single_rc=$?
|
||||
set -e
|
||||
if [[ "$single_rc" -ne 0 ]]; then
|
||||
fail "ordinary single-author merge expected rc=0, got rc=$single_rc: $single_output"
|
||||
elif [[ ! -s "$single_dir/merge-payload.json" ]]; then
|
||||
fail "ordinary single-author merge did not reach the API payload"
|
||||
else
|
||||
python3 - "$single_dir/merge-payload.json" <<'PY' || fail "ordinary single-author payload changed"
|
||||
import json
|
||||
import sys
|
||||
payload = json.load(open(sys.argv[1], encoding="utf-8"))
|
||||
assert payload == {
|
||||
"Do": "squash",
|
||||
"head_commit_id": "1111111111111111111111111111111111111111",
|
||||
}, payload
|
||||
PY
|
||||
fi
|
||||
[[ -e "$single_dir/auth-via-config" ]] || fail "ordinary path did not authenticate curl through stdin config"
|
||||
[[ ! -e "$single_dir/token-in-argv" ]] || fail "ordinary path placed the Gitea token in curl argv"
|
||||
[[ "$(wc -l < "$single_dir/token-resolution.log")" -eq 1 ]] || fail "ordinary path did not use exactly one credential resolution"
|
||||
|
||||
# Squash is not defaultable: an explicit non-squash method must remain refused.
|
||||
method_dir=$(make_case method-refusal)
|
||||
set +e
|
||||
method_output=$(run_case "$method_dir" single -m merge 2>&1)
|
||||
method_rc=$?
|
||||
set -e
|
||||
[[ "$method_rc" -ne 0 ]] || fail "non-squash method unexpectedly passed"
|
||||
[[ "$method_output" == *"enforces squash merge only"* ]] || fail "non-squash refusal lost its policy diagnostic"
|
||||
[[ ! -e "$method_dir/merge-payload.json" ]] || fail "non-squash refusal reached the merge API"
|
||||
|
||||
if [[ "$failures" -ne 0 ]]; then
|
||||
echo "pr-merge message-field regression failed ($failures assertions)" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "pr-merge message-field regression passed (verified, BLOCK, and unchanged squash control)"
|
||||
@@ -1,66 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# RM-03: pr-merge must guard the PR head branch, not its main base branch.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-merge-queue-branch}"
|
||||
FIXTURE_DIR="$WORK_DIR/tools/git"
|
||||
CALL_LOG="$WORK_DIR/queue-call.log"
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$FIXTURE_DIR"
|
||||
cp "$SCRIPT_DIR/pr-merge.sh" "$FIXTURE_DIR/pr-merge.sh"
|
||||
cp "$SCRIPT_DIR/detect-platform.sh" "$FIXTURE_DIR/detect-platform.sh"
|
||||
|
||||
cat > "$FIXTURE_DIR/pr-metadata.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
printf '%s\n' '{"baseRefName":"main","headRefName":"fix/rm-03-fixture","headRefOid":"0123456789abcdef0123456789abcdef01234567","headRepository":"contributor/widgets-fork"}'
|
||||
SH
|
||||
|
||||
cat > "$FIXTURE_DIR/ci-queue-wait.sh" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
printf '%s\n' "$*" > "${MOSAIC_QUEUE_CALL_LOG:?}"
|
||||
exit 42
|
||||
SH
|
||||
chmod +x "$FIXTURE_DIR"/*.sh
|
||||
|
||||
set +e
|
||||
(
|
||||
cd "$WORK_DIR"
|
||||
export MOSAIC_QUEUE_CALL_LOG="$CALL_LOG"
|
||||
"$FIXTURE_DIR/pr-merge.sh" -n 123
|
||||
) >/dev/null 2>&1
|
||||
rc=$?
|
||||
set -e
|
||||
|
||||
if [[ "$rc" -ne 42 ]]; then
|
||||
echo "FAIL: expected queue stub rc=42 to propagate, got $rc" >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -s "$CALL_LOG" ]]; then
|
||||
echo "FAIL: merge wrapper did not invoke the queue guard" >&2
|
||||
exit 1
|
||||
fi
|
||||
if ! grep -q -- '-B fix/rm-03-fixture' "$CALL_LOG"; then
|
||||
echo "FAIL: merge queue guard did not receive PR head branch" >&2
|
||||
cat "$CALL_LOG" >&2
|
||||
exit 1
|
||||
fi
|
||||
if grep -q -- '-B main' "$CALL_LOG"; then
|
||||
echo "FAIL: merge queue guard still received the main base branch" >&2
|
||||
cat "$CALL_LOG" >&2
|
||||
exit 1
|
||||
fi
|
||||
if ! grep -q -- '-R contributor/widgets-fork' "$CALL_LOG"; then
|
||||
echo "FAIL: merge queue guard did not receive the fork head repository" >&2
|
||||
cat "$CALL_LOG" >&2
|
||||
exit 1
|
||||
fi
|
||||
if ! grep -q -- '--sha 0123456789abcdef0123456789abcdef01234567' "$CALL_LOG"; then
|
||||
echo "FAIL: merge queue guard did not receive the exact PR head SHA" >&2
|
||||
cat "$CALL_LOG" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "pr-merge queue branch/repository/SHA regression passed"
|
||||
@@ -8,68 +8,12 @@ WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-metadata-gitea}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
FIXTURE_DIR="$WORK_DIR/fixtures"
|
||||
STUB_DIR="$WORK_DIR/stubs"
|
||||
HOME_DIR="$WORK_DIR/home"
|
||||
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$FIXTURE_DIR" "$STUB_DIR" "$HOME_DIR"
|
||||
mkdir -p "$REPO_DIR" "$FIXTURE_DIR" "$STUB_DIR"
|
||||
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/USC/uconnect.git
|
||||
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
|
||||
#
|
||||
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
|
||||
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
|
||||
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
|
||||
# repo. Step 0 runs BEFORE the credential loader AND before the GITEA_TOKEN env
|
||||
# check, so the `GITEA_TOKEN="stub-token"` set in the run helpers below is
|
||||
# silently overridden and a REAL per-slot token from $HOME is what reaches curl.
|
||||
# Measured on a provisioned seat before this pin: both stub-curl calls carried
|
||||
# the real token in argv. An empty repo-local value shadows the global one and
|
||||
# reads back empty at rc=0.
|
||||
#
|
||||
# CONTAINMENT: the sandboxed HOME in the three run helpers below. It only has to
|
||||
# bound a failure that the pin should already have prevented.
|
||||
#
|
||||
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
|
||||
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
|
||||
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
|
||||
# by construction and every suite reads clean however vulnerable it is. To measure,
|
||||
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
|
||||
# per-slot token) so step 0 reaches its fail-loud branch. See
|
||||
# test-gitea-token-identity.sh for the stronger `env -i HOME=…` form used where a
|
||||
# suite's whole subject IS identity resolution.
|
||||
#
|
||||
# Note the env-var route does NOT work: detect-platform.sh reads
|
||||
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
|
||||
git -C "$REPO_DIR" config mosaic.gitIdentity ""
|
||||
|
||||
# The pin above removes step 0, but this suite has a SECOND, independent
|
||||
# dependency on operator state, and closing only the first would leave the suite
|
||||
# red on any hermetic environment. The `GITEA_TOKEN="stub-token"` /
|
||||
# `GITEA_URL="https://git.example.test"` pair the run helpers set is INERT: step 2
|
||||
# of get_gitea_token accepts GITEA_TOKEN only when GITEA_URL matches the remote
|
||||
# host, and this repo's origin is git.uscllc.com, so that pair can never satisfy
|
||||
# it. Before this fixture the only credential that could reach the authenticated
|
||||
# curl branch was a REAL one — from step 0 on an agent seat, or from step 1
|
||||
# reading the operator's own ~/.config/mosaic/credentials.json. That is why the
|
||||
# "curl success path" case passed: not because the stub credential worked, but
|
||||
# because a production credential was available.
|
||||
#
|
||||
# A fixture is used rather than relying on the sandboxed HOME making step 1 find
|
||||
# nothing: a test that passes because production configuration is ABSENT fails
|
||||
# the moment it is present. Step 1 now resolves deterministically to a value that
|
||||
# is a fixture on every machine.
|
||||
cat > "$CREDENTIALS_FILE" <<'JSON'
|
||||
{
|
||||
"gitea": {
|
||||
"usc": {
|
||||
"url": "https://git.uscllc.com",
|
||||
"token": "stub-token"
|
||||
}
|
||||
}
|
||||
}
|
||||
JSON
|
||||
|
||||
cat > "$FIXTURE_DIR/gitea-standard.json" <<'JSON'
|
||||
{
|
||||
@@ -187,8 +131,6 @@ run_curl_success_case() {
|
||||
set +e
|
||||
output=$(cd "$REPO_DIR" && \
|
||||
PATH="$STUB_DIR:$PATH" \
|
||||
HOME="$HOME_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
TMPDIR="$tmpdir" \
|
||||
GITEA_TOKEN="stub-token" \
|
||||
GITEA_URL="https://git.example.test" \
|
||||
@@ -228,8 +170,6 @@ run_curl_early_exit_cleanup_case() {
|
||||
set +e
|
||||
output=$(cd "$REPO_DIR" && \
|
||||
PATH="$STUB_DIR:$PATH" \
|
||||
HOME="$HOME_DIR" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
TMPDIR="$tmpdir" \
|
||||
GITEA_TOKEN="stub-token" \
|
||||
GITEA_URL="https://git.example.test" \
|
||||
@@ -264,8 +204,7 @@ run_curl_early_exit_cleanup_case() {
|
||||
run_case() {
|
||||
local fixture="$1" expected_number="$2" expected_head="$3"
|
||||
local output
|
||||
output=$(cd "$REPO_DIR" && HOME="$HOME_DIR" MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
MOSAIC_GITEA_PR_METADATA_RAW_FILE="$fixture" "$SCRIPT_DIR/pr-metadata.sh" -n "$expected_number")
|
||||
output=$(cd "$REPO_DIR" && MOSAIC_GITEA_PR_METADATA_RAW_FILE="$fixture" "$SCRIPT_DIR/pr-metadata.sh" -n "$expected_number")
|
||||
PR_METADATA_OUTPUT="$output" python3 - "$expected_number" "$expected_head" <<'PY'
|
||||
import json
|
||||
import os
|
||||
|
||||
@@ -225,10 +225,7 @@ write_response() {
|
||||
emit() {
|
||||
# Split a two-line "status\n<json body>" python result into the response.
|
||||
local result="$1"
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
}
|
||||
|
||||
mode="${PR_REVIEW_TEST_MODE:-}"
|
||||
@@ -439,19 +436,6 @@ elif mode == "comment-url-wrong-repo":
|
||||
elif mode == "comment-url-suffix-injection":
|
||||
# Prefix-injected: a bare endswith("/<slug>/pulls/123") test would ACCEPT it.
|
||||
pr_url = f"{_origin}/deceptive{_slug}/pulls/123"
|
||||
elif mode == "comment-url-wrong-port":
|
||||
# #991 bound: an EXPLICIT non-default port is a different service on the same
|
||||
# host. Relaxing http-vs-https must NOT relax this.
|
||||
pr_url = f"{_p.scheme}://{_p.hostname}:8443{_slug}/pulls/123"
|
||||
elif mode == "comment-url-non-web-scheme":
|
||||
# #991 bound: ONLY http/https collapse; any other scheme stays distinguishing.
|
||||
pr_url = f"ftp://{_p.netloc}{_slug}/pulls/123"
|
||||
elif mode == "comment-url-scheme-downgrade":
|
||||
# #991, and the only URL mode here that must be ACCEPTED. A Gitea whose
|
||||
# ROOT_URL is http:// returns http:// object URLs for a repo reached over
|
||||
# https://. Same host, same path, correct record — a truthful provider
|
||||
# answer about a comment that landed, not a forgery.
|
||||
pr_url = f"http://{_p.netloc}{_slug}/pulls/123"
|
||||
elif mode == "comment-mixed-case-slug":
|
||||
# #875: EXPECTED_REPO_SLUG is taken verbatim from GITEA_API_BASE and can be
|
||||
# mixed-case (e.g. "USC/uconnect"), but Gitea canonicalizes the returned
|
||||
@@ -906,16 +890,11 @@ fi
|
||||
assert_no_temp_leak "review-body-reuse"
|
||||
|
||||
# Cases 12-15 (#865 Blocker 3): a PR comment whose id/author/body are all correct
|
||||
# but whose provider-returned pull_request_url does not belong to this PR must
|
||||
# FAIL CLOSED. Verification pins the URL's ORIGIN (scheme-class + host + explicit
|
||||
# non-default port) and FULL path (deployment prefix + exact owner/repo + kind +
|
||||
# number); a bare endswith/suffix test would wrongly accept the look-alike-host
|
||||
# and prefix-injection variants. comment-url-wrong-port and
|
||||
# comment-url-non-web-scheme (#991) bound the scheme relaxation from the other
|
||||
# side: collapsing http/https must not also collapse a different port or a
|
||||
# different scheme family.
|
||||
for bad_mode in comment-url-wrong-host comment-url-wrong-owner comment-url-wrong-repo \
|
||||
comment-url-suffix-injection comment-url-wrong-port comment-url-non-web-scheme; do
|
||||
# but whose provider-returned pull_request_url is forged must FAIL CLOSED.
|
||||
# Verification pins the URL's ORIGIN (scheme+host+effective-port) and FULL path
|
||||
# (deployment prefix + exact owner/repo + kind + number); a bare endswith/suffix
|
||||
# test would wrongly accept the look-alike-host and prefix-injection variants.
|
||||
for bad_mode in comment-url-wrong-host comment-url-wrong-owner comment-url-wrong-repo comment-url-suffix-injection; do
|
||||
if run_review "$bad_mode" comment durable-body; then
|
||||
echo "FAIL: forged comment URL ($bad_mode) was accepted" >&2
|
||||
cat "$OUTPUT_FILE" >&2
|
||||
@@ -941,19 +920,6 @@ run_review comment-mixed-case-slug comment durable-body https://git.mosaicstack.
|
||||
grep -q 'Added and verified comment on Gitea PR #123' "$OUTPUT_FILE"
|
||||
assert_no_temp_leak "comment-mixed-case-slug"
|
||||
|
||||
# Case 15c (#991): the deployment's Gitea ROOT_URL is http:// while every client
|
||||
# reaches it over https://, so the provider returns an http:// pull_request_url
|
||||
# for a comment that is otherwise entirely correct. Same class as 15b — a
|
||||
# legitimate provider response, not a spoof — and a scheme-strict compare
|
||||
# rejects it on EVERY comment, deterministically. That is not a cosmetic false
|
||||
# negative here: on a host where no seat can create a review OBJECT, this
|
||||
# comment-form record is the only gate-16 evidence obtainable, and the wrapper
|
||||
# refuses all of it while the comment sits durably on the PR. Host, path, owner,
|
||||
# repo, kind and number stay strict; only http-vs-https is relaxed.
|
||||
run_review comment-url-scheme-downgrade comment durable-body
|
||||
grep -q 'Added and verified comment on Gitea PR #123' "$OUTPUT_FILE"
|
||||
assert_no_temp_leak "comment-url-scheme-downgrade"
|
||||
|
||||
# Case 16 (#865 ITEM 1, current-head TOCTOU): the PR head advances between the
|
||||
# pre-submit head read (which pins the review) and the post-verify re-read. The
|
||||
# review is genuinely created and verified as pinned to the OLD head, but the
|
||||
|
||||
@@ -222,8 +222,8 @@ grep -q 'Unknown action: bogus-action' "$OUTPUT_FILE"
|
||||
|
||||
# --- Case 2: -h/--help documents both overrides.
|
||||
HELP_TEXT="$("$SCRIPT_DIR/pr-review.sh" -h)"
|
||||
grep -q -- '-r, --repo' <<<"$HELP_TEXT"
|
||||
grep -q -- '-H, --host' <<<"$HELP_TEXT"
|
||||
echo "$HELP_TEXT" | grep -q -- '-r, --repo'
|
||||
echo "$HELP_TEXT" | grep -q -- '-H, --host'
|
||||
|
||||
# --- Case 3 (comment): a TRUE no-git-origin dir + -r/-H must not silently die
|
||||
# and must not fail with "not a git repository or no origin remote" either.
|
||||
|
||||
@@ -1,703 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# test-wrapper-guard.sh — hermetic behavioural regression for wrapper-guard.sh.
|
||||
#
|
||||
# Resolves no credentials, touches no network, and creates no repository: the
|
||||
# guard reads a hook payload on stdin and answers with an exit code, so the whole
|
||||
# contract is testable from fixtures.
|
||||
#
|
||||
# The fixtures are written to a temp file rather than passed inline, and this is
|
||||
# not stylistic. The guard inspects the literal text of the Bash command it is
|
||||
# handed. A test that embeds `git clone ... $HOME` inside its own command line
|
||||
# trips the guard on the harness instead of on the fixture — which is exactly
|
||||
# what happened the first time this was checked by hand. Substring matching over
|
||||
# whole command text is the guard's deliberate fail-closed posture; a test that
|
||||
# does not account for it silently measures the wrong thing.
|
||||
#
|
||||
# Exit: 0 = every fixture behaved as specified · 1 = at least one did not
|
||||
|
||||
set -uo pipefail
|
||||
|
||||
HERE="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
GUARD="${1:-$HERE/wrapper-guard.sh}"
|
||||
[ -x "$GUARD" ] || { printf 'test-wrapper-guard: not executable: %s\n' "$GUARD" >&2; exit 2; }
|
||||
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
FIXTURES="$TMP/fixtures.tsv"
|
||||
|
||||
# Each line: <expected-exit> TAB <hook payload> TAB <what it proves>
|
||||
# [ TAB <substring the block message must contain> ]
|
||||
# 0 = allowed, 2 = blocked. The optional fourth field is how the remediation
|
||||
# itself gets checked; without it a block is only asserted to have happened,
|
||||
# not to have been useful.
|
||||
{
|
||||
printf '2\t{"tool_input":{"command":"git clone https://example.invalid/x ~/wt"}}\tcheckout into $HOME is refused\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add ~/wt topic"}}\tworktree into $HOME is refused\n'
|
||||
printf '2\t{"tool_input":{"command":"g\\"it\\" clone https://example.invalid/x $HOME/wt"}}\ta double quote inside git does not hide a checkout\n'
|
||||
printf '2\t{"tool_input":{"command":"g'"'"'it'"'"' clone https://example.invalid/x $HOME/wt"}}\ta single quote inside git does not hide a checkout\n'
|
||||
printf '2\t{"tool_input":{"command":"g\\\\it clone https://example.invalid/x $HOME/wt"}}\tan unquoted escape inside git does not hide a checkout\n'
|
||||
# Path words use the same quote/escape state machine as names, but preserve
|
||||
# substitutions so HOME remains visible. Quotes do not split the path word.
|
||||
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\"/wt"}}\ta closing quote between HOME and slash does not hide the path\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x ${HOME}/wt"}}\tthe braced HOME spelling is the same home path\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x \\"${HOME}\\"/wt"}}\tbraced HOME may also end a quoted span before the slash\n'
|
||||
# Lexically equivalent absolute paths must be compared after shell-known HOME
|
||||
# expansion and dot-segment normalization, without resolving filesystem links.
|
||||
printf '2\t{"tool_input":{"command":"git clone x /var/../$HOME/wt"}}\tHOME expansion after parent traversal is normalized before comparison\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add /var/../${HOME}/wt"}}\tworktree placement also normalizes embedded HOME expansion\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir=/var/../$HOME/gd x /src/wt"}}\tseparate Git state cannot hide behind parent traversal\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME/../outside-home/wt"}}\ta parent segment that leaves HOME is not over-blocked\n'
|
||||
# The target may be HOME itself. End-of-command and whitespace terminate the
|
||||
# token just as a slash does; punctuation that can extend a path does not.
|
||||
printf '2\t{"tool_input":{"command":"git clone x $HOME"}}\tthe unbraced variable may name HOME exactly\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\""}}\tquotes do not change the exact HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x ${HOME}"}}\tthe braced variable may name HOME exactly\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x ~"}}\ttilde may name HOME exactly\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add $HOME topic"}}\twhitespace terminates an exact HOME target before another argument\n'
|
||||
# Unquoted POSIX metacharacters terminate the target word even without spaces.
|
||||
printf '2\t{"tool_input":{"command":"git clone x $HOME;echo x"}}\tsemicolon terminates an exact HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\"&& echo x"}}\tand-if terminates a quoted exact HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x ${HOME}| cat"}}\ta pipe terminates a braced exact HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x ~&"}}\tbackground operator terminates a tilde HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x $HOME</dev/null"}}\tinput redirection terminates the target word\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x $HOME>out"}}\toutput redirection terminates the target word\n'
|
||||
printf '2\t{"tool_input":{"command":"( git clone x $HOME)"}}\ta subshell close terminates the exact HOME target\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone x $HOME\\necho x"}}\ta literal newline terminates the target word\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME_BACKUP/wt"}}\ta longer HOME-prefixed variable is a different path\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOMEBREW/wt"}}\tHOMEBREW is not HOME either\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME.bak/wt"}}\ta dot continues the path token into a sibling name\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME+bak/wt"}}\tplus is ordinary sibling filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME@bak/wt"}}\tat-sign is ordinary sibling filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME,bak/wt"}}\tcomma is ordinary sibling filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME:bak/wt"}}\tcolon is ordinary sibling filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME=bak/wt"}}\tequals is ordinary sibling filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x ${HOME}+bak/wt"}}\tbraced HOME plus suffix is still a sibling\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x /home/tester+bak/wt"}}\ta literal plus-suffixed home path is a sibling\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x /home/tester@bak/wt"}}\ta literal at-suffixed home path is a sibling\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME+bak/wt;echo x"}}\ta later terminator does not turn a sibling into HOME\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME@bak/wt&& echo x"}}\tand-if after a sibling preserves the allow\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x \\"$HOME;bak/wt\\""}}\ta quoted semicolon is filename content, not a boundary\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME\\\\;bak/wt"}}\tan escaped semicolon is filename content, not a boundary\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME\\u001b/wt"}}\ta raw internal-marker byte is encoded as filename content\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x /home/tester.bak/wt"}}\ta literal sibling path is not beneath HOME\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x /home/testerx/wt"}}\ta longer literal basename is not HOME\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x ~root/wt"}}\tanother account tilde is not this account HOME\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x $HOME}/wt"}}\ta closing brace without an opening brace is a literal suffix\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x ${HOME/wt"}}\tan opening brace without a close is not a HOME expansion\n'
|
||||
# Quote removal must not create an expansion the shell never performs.
|
||||
printf '0\t{"tool_input":{"command":"git clone x '"'"'$HOME'"'"'/wt"}}\tsingle-quoted HOME is a literal directory name\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x \\\\$HOME/wt"}}\tan escaped dollar makes HOME literal outside quotes\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x \\"\\\\$HOME\\"/wt"}}\tan escaped dollar makes HOME literal inside double quotes\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x \\"~/wt\\""}}\ttilde does not expand inside double quotes\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x '"'"'~/wt'"'"'"}}\ttilde does not expand inside single quotes\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone x \\\\~/wt"}}\tan escaped tilde is literal too\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone https://example.invalid/x /src/wt"}}\tcheckout onto a work filesystem is fine\n'
|
||||
# Round ten: placement is decided by the destination and the one clone option
|
||||
# that creates repository state elsewhere, not by every HOME-valued word in
|
||||
# the command. Sources, templates, references, and environment are not targets.
|
||||
printf '0\t{"tool_input":{"command":"NOTE=$HOME git clone https://example.invalid/x /src/wt"}}\tan unrelated assignment carrying HOME is not checkout placement\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --reference=$HOME https://example.invalid/x /src/wt"}}\ta HOME reference is an object source, not checkout placement\n'
|
||||
printf '0\t{"tool_input":{"command":"GIT_DIR=$HOME/x git clone https://example.invalid/x /src/wt"}}\tclone does not place its destination from ambient GIT_DIR\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --template=$HOME/t https://example.invalid/x /src/wt"}}\ta HOME template source is not checkout placement\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir=$HOME/gd https://example.invalid/x /src/wt"}}\tseparate-git-dir explicitly places repository state under HOME\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir $HOME/gd https://example.invalid/x /src/wt"}}\tthe space-separated placement option is equivalent\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --reason=$HOME/note /src/wt"}}\ta worktree reason is metadata, not its path\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone $HOME/source /src/wt"}}\ta HOME source with an explicit safe destination is not placement\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --reference $HOME https://example.invalid/x /src/wt"}}\ta space-separated HOME reference remains a source\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --template $HOME/t https://example.invalid/x /src/wt"}}\ta space-separated HOME template remains a source\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone 2>/dev/null https://example.invalid/x $HOME/wt"}}\ta redirection before clone arguments does not become the destination\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --reference $HOME https://example.invalid/x $HOME/wt"}}\ta source option does not hide a later HOME destination\n'
|
||||
# Round eleven: Git accepts boolean options as a rule-generated family,
|
||||
# including --no-* negations. Each command below was checked with Git itself:
|
||||
# `git clone <option> /nonexistent-src /nonexistent-dst` reaches the missing
|
||||
# source instead of reporting an unknown option. The HOME word is the source,
|
||||
# not the explicit /src destination, so Bash expansion is allowed here.
|
||||
printf '0\t{"tool_input":{"command":"git clone --bare $HOME/source /src/wt"}}\tbare clone keeps its HOME source distinct from the safe destination\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --mirror $HOME/source /src/wt"}}\tmirror is an accepted flag and does not consume the HOME source\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --ipv4 $HOME/source /src/wt"}}\tipv4 is an accepted flag and does not consume the HOME source\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --ipv6 $HOME/source /src/wt"}}\tipv6 is an accepted flag and does not consume the HOME source\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-local $HOME/source /src/wt"}}\tgenerated no-local remains a flag rather than a placement option\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-reject-shallow $HOME/source /src/wt"}}\tgenerated no-reject-shallow remains a flag rather than placement\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone -4 $HOME/source /src/wt"}}\tthe short IPv4 flag leaves the HOME word in source position\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone -6 $HOME/source /src/wt"}}\tthe short IPv6 flag leaves the HOME word in source position\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-bare $HOME/source /src/wt"}}\tan unusual generated negation is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-sparse $HOME/source /src/wt"}}\tgenerated no-sparse is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-dissociate $HOME/source /src/wt"}}\tgenerated no-dissociate is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-shallow-submodules $HOME/source /src/wt"}}\ta long generated negation is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-quiet $HOME/source /src/wt"}}\tgenerated no-quiet is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-progress $HOME/source /src/wt"}}\tgenerated no-progress is accepted without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone --no-recurse-submodules $HOME/source /src/wt"}}\tgenerated no-recurse-submodules is accepted without enumeration\n'
|
||||
# Git also generates accepted long abbreviations and short-option bundles.
|
||||
# The closed value-taking option grammar must consume their values correctly.
|
||||
printf '0\t{"tool_input":{"command":"git clone --templ $HOME/t $HOME/source /src/wt"}}\tan accepted template abbreviation consumes metadata rather than the source\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone -qj 1 $HOME/source /src/wt"}}\ta short flag bundle ending in jobs consumes its separate value\n'
|
||||
printf '0\t{"tool_input":{"command":"git clone -qb topic $HOME/source /src/wt"}}\ta short flag bundle ending in branch consumes its separate value\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --separate-git-d=$HOME/gd https://example.invalid/x /src/wt"}}\tan accepted placement-option abbreviation remains blocked in attached form\n'
|
||||
printf '2\t{"tool_input":{"command":"git clone --separate-git-d $HOME/gd https://example.invalid/x /src/wt"}}\tan accepted placement-option abbreviation remains blocked in separate form\n'
|
||||
# Worktree boolean options have the same generated-negation grammar. The next
|
||||
# positional is its real path, so safe paths allow and HOME paths still block.
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --no-force /src/wt"}}\tgenerated worktree no-force accepts a safe path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --no-detach /src/wt"}}\tgenerated worktree no-detach accepts a safe path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --no-lock /src/wt"}}\tgenerated worktree no-lock accepts a safe path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --no-guess-remote /src/wt"}}\ta long worktree negation accepts a safe path without enumeration\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add -d /src/wt"}}\tthe documented short detach flag accepts a safe path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add -q /src/wt"}}\tthe documented short quiet flag accepts a safe path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --lock --rea $HOME/note /src/wt"}}\tan accepted reason abbreviation consumes metadata rather than the path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add -fb $HOME/topic /src/wt"}}\ta short branch bundle consumes its HOME-valued branch before the safe path\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add -fb topic $HOME/wt"}}\ta short branch bundle does not hide the later HOME path\n'
|
||||
# Upstream Git defines --orphan as a boolean flag; -b still carries the branch.
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --orphan /src/wt"}}\torphan mode accepts a safe path without consuming it as a value\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add --orphan $HOME/wt"}}\torphan mode does not hide its HOME path\n'
|
||||
printf '0\t{"tool_input":{"command":"git worktree add --orphan -b $HOME/topic /src/wt"}}\torphan mode leaves HOME branch metadata to the branch option\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add --orphan -b topic $HOME/wt"}}\torphan mode plus a branch option preserves HOME path blocking\n'
|
||||
# The optional second positional is commit-ish metadata, never placement.
|
||||
# HOME expands here, but the explicit worktree path remains safely under /src.
|
||||
printf '0\t{"tool_input":{"command":"git worktree add /src/wt $HOME/topic"}}\ta HOME-shaped commit-ish is not the worktree path\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add --no-force $HOME/wt"}}\ta generated worktree negation does not hide the HOME path\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add --no-guess-remote $HOME/wt"}}\ta long worktree negation preserves HOME placement blocking\n'
|
||||
# Explicit placement options and later simple commands remain traps.
|
||||
printf '2\t{"tool_input":{"command":"git clone --bare $HOME/source /src/wt && git clone x $HOME/wt"}}\ta boolean flag in one command does not hide a later HOME destination\n'
|
||||
printf '2\t{"tool_input":{"command":"git worktree add --no-force /src/wt; git clone x $HOME/wt"}}\ta worktree flag before a boundary does not hide later HOME placement\n'
|
||||
# Routing this arm through the shared name site also repaired an over-block it
|
||||
# had carried from the start: the old whole-command regex found `git` INSIDE a
|
||||
# longer word, so these two were refused at every head before this commit.
|
||||
# Same class as mycurl and curl-wrapper, and refusing them is how a guard gets
|
||||
# routed around instead of repaired.
|
||||
printf '0\t{"tool_input":{"command":"mygit clone https://example.invalid/x $HOME/wt"}}\tmygit is a different program and its checkout is not ours\n'
|
||||
printf '0\t{"tool_input":{"command":"gitfoo clone https://example.invalid/x $HOME/wt"}}\tthe name has to end where git ends\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -s -X GET https://git.example.invalid/api/v1/repos/a/b/pulls/1"}}\treads are never blocked\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\treview write has a wrapper\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\tmerge write has a wrapper\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://api.github.com/repos/a/b/issues"}}\tGitHub host is covered too\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/releases"}}\tan endpoint with no wrapper passes\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d {\\"event\\":\\"APPROVE\\"} https://example.invalid/x"}}\tthe APPROVE token is caught anywhere\n'
|
||||
printf '0\t{"tool_input":{"command":"ls -la /src"}}\tordinary commands are untouched\n'
|
||||
printf '0\t{"tool_input":{"command":"MOSAIC_WRAPPER_OVERRIDE=1 curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls"}}\tbreak-glass works\n'
|
||||
printf '0\t{"tool_input":{}}\tan empty payload does not block the session\n'
|
||||
# --- bypasses an independent reviewer demonstrated against the first version.
|
||||
# Each of these returned 0 (allowed) and each is a real write. They are pinned
|
||||
# as fixtures rather than fixed-and-forgotten because the class is recurring:
|
||||
# the guard reads text, so every spelling it does not know is a hole.
|
||||
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t-d@body with no space is still a body\n'
|
||||
printf '2\t{"tool_input":{"command":"curl --request=POST -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t--request=POST equals-form is still a method\n'
|
||||
printf '2\t{"tool_input":{"command":"p=/api/v1/repo; q=s/a/b/pulls/1/reviews; curl -d@b https://git.example.invalid${p}${q}"}}\ta path split across variables is still that path\n'
|
||||
printf '2\t{"tool_input":{"command":"curl --data-binary @b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\t--data-binary is a body\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -F f=@b https://git.example.invalid/api/v1/repos/a/b/issues"}}\t-F multipart is a body\n'
|
||||
# Reads must survive every one of those broadenings, or the guard gets disabled.
|
||||
printf '0\t{"tool_input":{"command":"curl -s https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tno body and no verb is a read\n'
|
||||
printf '0\t{"tool_input":{"command":"grep -rn /pulls/ src/ | head -20"}}\ta path fragment in a grep is not an API call\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://registry.example.invalid/v2/x/manifests/latest"}}\tan unwrapped API is not this guard'"'"'s business\n'
|
||||
# --- round two of the same review. Splitting the ENDPOINT TOKEN defeats any
|
||||
# amount of fragment matching, because the endpoint does not exist until the
|
||||
# shell expands it. The guard now refuses to clear a write whose URL it cannot
|
||||
# read, rather than pretending it read one.
|
||||
printf '2\t{"tool_input":{"command":"a=/api/v1/repos/a/b/iss; b=ues/1/comments; curl -d@body https://git.example.invalid${a}${b}"}}\tan endpoint token split across variables is unreadable, not absent\n'
|
||||
printf '2\t{"tool_input":{"command":"a=/api/v1/repos/a/b/pu; b=lls/1/reviews; curl -d@body https://git.example.invalid${a}${b}"}}\tsame split, review endpoint\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d @payload https://hooks.example.invalid/services/${WEBHOOK_ID}"}}\tan opaque URL that is not forge-shaped stays allowed\n'
|
||||
# --- round six changed the contract in this direction, and these fixtures are
|
||||
# where it shows. They used to assert that discussing a call is not making one.
|
||||
# Five rounds proved there is no textual way to tell a quoted example from a
|
||||
# quoted command, so the guard stopped trying: it judges the payload, and a
|
||||
# payload inside quotes is still a payload. Quoting one of these on a Bash
|
||||
# command line is now refused, and the way to write the example is a
|
||||
# file-writing tool. This is the deliberate cost of the mechanism change.
|
||||
printf '2\t{"tool_input":{"command":"grep -R \\"curl -d https://git.example.invalid/api/v1/repos/a/b/issues\\" docs/"}}\tquoting a wrapped write is refused even in a grep\n'
|
||||
printf '2\t{"tool_input":{"command":"echo \\"curl -d https://git.example.invalid/api/v1/repos/a/b/pulls\\" > note.txt"}}\t...and when written into a file\n'
|
||||
printf '2\t{"tool_input":{"command":"python3 -c '"'"'print(\\"curl -d https://git.example.invalid/api/v1/repos/a/b/issues\\")'"'"'"}}\t...and when printed from another language\n'
|
||||
# The boundary that keeps this from being "block everything": what is refused
|
||||
# is a WRITE to a WRAPPED endpoint. Mentioning either alone still passes, and
|
||||
# these are asserted as hard as the blocks above.
|
||||
printf '0\t{"tool_input":{"command":"grep -R \\"curl -s https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" docs/"}}\tquoting a READ example is untouched\n'
|
||||
printf '0\t{"tool_input":{"command":"echo \\"the wrapped endpoint is https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" >> notes.md"}}\tnaming the endpoint without a body flag is untouched\n'
|
||||
printf '0\t{"tool_input":{"command":"grep -R \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/releases\\" docs/"}}\tquoting a write to an UNWRAPPED endpoint is untouched\n'
|
||||
printf '0\t{"tool_input":{"command":"issue-comment.sh --repo a/b --issue 1 --body @msg.md"}}\tthe wrapper itself carries a body flag and must never trip its own guard\n'
|
||||
# Command position must still catch the real thing behind operators and env.
|
||||
printf '2\t{"tool_input":{"command":"cd /tmp && GITEA_TOKEN=$T curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\ta real call behind && and an assignment is still a call\n'
|
||||
# --- the case the AUTHOR hit twice while chasing the above: sending a message
|
||||
# that QUOTED one of these fixtures. Under the old contract that was a defect
|
||||
# to be parsed away; under this one it is the documented cost, and the message
|
||||
# gets composed with a file-writing tool instead.
|
||||
printf '2\t{"tool_input":{"command":"send.sh -m \\"repro was: cd /tmp && curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tquoting the repro in a message is refused too\n'
|
||||
printf '2\t{"tool_input":{"command":"cat >> notes.md <<EOF\\nwe ran: curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues\\nEOF"}}\ta heredoc body carrying the payload is refused with it\n'
|
||||
# ...but quotes stop being data the moment something executes them.
|
||||
printf '2\t{"tool_input":{"command":"bash -c \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tbash -c makes the quoted text code again\n'
|
||||
# --- round three. Each of these four is a real write that a bare-name match
|
||||
# for the client could not see, because an ordinary word sat in front of it.
|
||||
# They are kept as fixtures after the mechanism change even though the guard no
|
||||
# longer looks for a client at all: they are the evidence for WHY it stopped,
|
||||
# and a future re-narrowing that reintroduced position would fail here first.
|
||||
printf '2\t{"tool_input":{"command":"env GITEA_TOKEN=$T curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tenv VAR=... in front of the client is still the client\n'
|
||||
printf '2\t{"tool_input":{"command":"command curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tcommand in front of the client is still the client\n'
|
||||
printf '2\t{"tool_input":{"command":"timeout 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\ttimeout N in front of the client is still the client\n'
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan absolute path to the client is still the client\n'
|
||||
printf '2\t{"tool_input":{"command":"echo timeout 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments >> notes.md"}}\tnaming the call after echo carries the payload, so it is refused\n'
|
||||
# A shell standing between quoted data and execution makes that data code,
|
||||
# and the pipe is the form agents actually use. Filing it as data allowed the
|
||||
# call to vanish from the skeleton while still running.
|
||||
printf '2\t{"tool_input":{"command":"printf '"'"'%%s\\\\n'"'"' '"'"'curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments'"'"' | sh"}}\tquoted code piped to a shell is code\n'
|
||||
printf '2\t{"tool_input":{"command":"cat <<EOF | sh\\ncurl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\nEOF"}}\ta heredoc piped to a shell is code\n'
|
||||
printf '2\t{"tool_input":{"command":"sh -s <<EOF\\ncurl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\nEOF"}}\tsh -s reads its script from the heredoc\n'
|
||||
# ...and the questions that used to follow — is the pipe target a shell, does a
|
||||
# shell on one line execute a string on another — no longer have to be answered
|
||||
# at all. Both of these carry the payload, both are refused, and neither
|
||||
# outcome depends on parsing what the pipe or the other line does.
|
||||
printf '2\t{"tool_input":{"command":"grep -R \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" docs/ | wc -l"}}\tpiping the payload to wc is refused without asking what wc is\n'
|
||||
printf '2\t{"tool_input":{"command":"docker run --rm alpine sh -c '"'"'echo hi'"'"'\\necho \\"example: curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" >> notes.md"}}\tan unrelated shell on another line no longer changes the answer either way\n'
|
||||
# --- round four. The guard was still reading the command as typed rather than
|
||||
# as the shell will run it: a backslash before a newline is removed before
|
||||
# anything else happens, so the endpoint token can be split across the join.
|
||||
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/iss\\\\\\nues/1/comments"}}\ta line continuation inside the endpoint token is still that endpoint\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pu\\\\\\nlls/1/reviews"}}\tsame join, review endpoint\n'
|
||||
printf '2\t{"tool_input":{"command":"cat >> notes.md <<EOF\\nwe ran: curl -d@b https://git.example.invalid/api/v1/repos/a/b/iss\\\\\\nues/1/comments\\nEOF"}}\tthe join still runs first, and the joined payload is refused in a document too\n'
|
||||
# Transparent prefixes take option VALUES, and the value was a word the list
|
||||
# did not know — so the client went missing again behind an ordinary `sudo -u`.
|
||||
printf '2\t{"tool_input":{"command":"sudo -u root curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan option value after a prefix does not hide the client\n'
|
||||
printf '2\t{"tool_input":{"command":"timeout --signal TERM 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan option pair plus a duration does not hide the client\n'
|
||||
printf '2\t{"tool_input":{"command":"xargs echo curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tthe payload behind xargs echo is refused rather than adjudicated\n'
|
||||
printf '0\t{"tool_input":{"command":"sudo apt-get install curl"}}\tinstalling the client is not calling it\n'
|
||||
# Execution through another command needed its own case under the old design.
|
||||
printf '2\t{"tool_input":{"command":"find . -maxdepth 0 -exec curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments ;"}}\tfind -exec runs the client\n'
|
||||
# --- round five, and the finding that ended the parser. Command substitution
|
||||
# inside a double-quoted span EXECUTES, while the skeleton was discarding that
|
||||
# span as inert prose. The unquoted and process-substitution forms already
|
||||
# blocked, which is what made it a classification defect rather than a spelling
|
||||
# one: the same call was refused or allowed depending on a quote character.
|
||||
printf '2\t{"tool_input":{"command":"echo \\"$(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)\\""}}\tcommand substitution inside double quotes executes\n'
|
||||
printf '2\t{"tool_input":{"command":"echo \\"`curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments`\\""}}\tso does the backtick form\n'
|
||||
printf '2\t{"tool_input":{"command":"msg=\\"$(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)\\""}}\tand an assignment RHS is not data either\n'
|
||||
printf '2\t{"tool_input":{"command":"echo $(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)"}}\tthe unquoted form, which blocked before and must keep blocking\n'
|
||||
printf '2\t{"tool_input":{"command":"cat <(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)"}}\tprocess substitution, same\n'
|
||||
printf '2\t{"tool_input":{"command":"bash --command \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\""}}\tthe long-option spelling of bash -c needs no entry in any list now\n'
|
||||
# A client the guard was never taught is the point of dropping client
|
||||
# detection: neither of these names curl at all.
|
||||
printf '2\t{"tool_input":{"command":"python3 -c '"'"'import requests; requests.post(\\"https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\", json={})'"'"'"}}\ta library call is a write with no flag and no curl\n'
|
||||
printf '2\t{"tool_input":{"command":"wget --post-data=x https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\twget spells its body differently and is still a write\n'
|
||||
|
||||
# Round six scoped the guard on `https?://`, and review found the absence shape
|
||||
# had simply moved to that new boundary: a raw provider CLI carries no scheme,
|
||||
# so the guard never reached the write question. These are the reported repros.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues -f title=x -f body=y"}}\tgh api is a raw write with no URL scheme at all\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/pulls/1/reviews -f event=APPROVE"}}\tand it reaches the endpoint the review wrapper owns\n'
|
||||
printf '2\t{"tool_input":{"command":"tea api -X POST repos/a/b/issues/1/comments -f body=x"}}\ttea api, same shape, different CLI\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d x git.example.invalid/api/v1/repos/a/b/issues"}}\ta scheme-less host path is still an API write\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api repos/a/b/issues -f title=x"}}\tgh POSTs implicitly when handed a field, exactly as curl does with -d\n'
|
||||
# ...and the boundary that stops a broader scope gate becoming block-everything.
|
||||
printf '0\t{"tool_input":{"command":"gh api repos/a/b/pulls/1"}}\treading through a provider CLI stays untouched\n'
|
||||
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/releases -f tag_name=v1"}}\tno wrapper owns releases, whoever calls it\n'
|
||||
printf '0\t{"tool_input":{"command":"tea pulls create --title x --repo a/b"}}\tprovider PORCELAIN is out of scope by decision, not by accident\n'
|
||||
printf '0\t{"tool_input":{"command":"rm -f /var/tmp/api/v1-issues-notes.txt"}}\t-f is only a body when it carries key=value\n'
|
||||
printf '0\t{"tool_input":{"command":"grep -f patterns.txt /src/api/v1/repos/a/b/issues.log"}}\tsame, on the flag agents actually collide with\n'
|
||||
|
||||
# Wrong remediation is its own defect: /issues/1/labels used to block with
|
||||
# "use issue-create.sh", which is not the wrapper for that call. Round seven
|
||||
# answered that by letting EVERY path under a numbered issue or PR through,
|
||||
# and review showed the reasoning ("no wrapper owns these") was false in this
|
||||
# tree. These are the reported repros, all rc 0 before round eight, and each
|
||||
# asserts the wrapper the advice must name — not merely that a block happened.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f title=x"}}\tan issue edit is issue-edit.sh, not a wrapper gap\tissue-edit.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1"}}\tsame call through curl, same wrapper\tissue-edit.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1/labels -f labels[]=bug"}}\tlabels are wrapped, and the advice says by which\tissue-edit.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/assignees -f assignees[]=u"}}\tassignees are issue-assign.sh\tissue-assign.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api repos/a/b/issues/1/assignees -f assignees[]=u"}}\tthe array field spelling is a body with no -X at all\tissue-assign.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/labels"}}\ta PR is an issue where labels live, so the issue wrapper owns them\tissue-edit.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1"}}\tPR state is pr-close.sh, and the gap in that arm is stated\tpr-close.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/milestones/4"}}\ta milestone state change is milestone-close.sh, not the create wrapper\tmilestone-close.sh\n'
|
||||
# SPAN. A wrapper that owns a slice of an endpoint must not be advertised as
|
||||
# owning the endpoint. milestone-close.sh takes only -t <title> and sends
|
||||
# state=closed, so a title/description/due-date edit is a gap and the message
|
||||
# has to say so — round eight named the wrapper and stopped there.
|
||||
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/milestones/1"}}\ta milestone edit blocks, but the advice states the close-only span\towns the CLOSE only\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f assignee=u"}}\tissue-edit.sh cannot set an assignee, so the message names the one that can\tissue-assign.sh owns the assignee\n'
|
||||
# The residue: still genuinely owned by nothing, and still flowing through.
|
||||
# Requesting a reviewer is not submitting one; pr-review.sh files verdicts and
|
||||
# nothing in the tree adds a requested reviewer.
|
||||
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/pulls/1/requested_reviewers -f reviewers[]=u"}}\tno wrapper requests a reviewer, so it is not refused with pr-review.sh\n'
|
||||
# SPAN, applied to the guard's OWN fail-closed rule rather than to a wrapper.
|
||||
# The scope gate admits three shapes; the unreadable-endpoint rule asked only
|
||||
# for `https?://`, so a split endpoint in the other two was in scope to block,
|
||||
# produced no readable endpoint, and fell through to allow. Same defect class
|
||||
# as the milestone arm, one layer up. Each shape gets its own fixture, because
|
||||
# a single one would have passed on the arm that already worked.
|
||||
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; gh api -X POST ${p}${q} -f title=x"}}\ta split endpoint in a provider-CLI api call is unreadable, not absent\n'
|
||||
printf '2\t{"tool_input":{"command":"p=repos/a/b/issues/1/comm; q=ents; gh api -X POST ${p}${q} -f body=x"}}\tsame, comments\n'
|
||||
printf '2\t{"tool_input":{"command":"p=repos/a/b/pulls/1/rev; q=iews; gh api -X POST ${p}${q} -f event=APPROVED"}}\tsame, and a verdict is the costliest one to lose\n'
|
||||
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; tea api -X POST ${p}${q} -f title=x"}}\tevery CLI the scope gate admits, not just gh\n'
|
||||
printf '2\t{"tool_input":{"command":"p=/api/v1/repos/a/b/iss; q=ues; curl -X POST -d x git.example.invalid${p}${q}"}}\ta schemeless forge host with a split path is unreadable too\n'
|
||||
printf '2\t{"tool_input":{"command":"h=git.example.invalid; q=ues; curl -X POST -d x ${h}/api/v1/repos/a/b/iss${q}"}}\tthe expansion may come first; the token is what matters\n'
|
||||
# And the reason this is not "any variable blocks a write": a payload in a
|
||||
# variable is the SAFE way to pass one and leaves the endpoint fully legible.
|
||||
printf '0\t{"tool_input":{"command":"gh api repos/a/b/git/refs -f sha=$SHA"}}\tan expansion in a body value leaves the endpoint readable\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d \\"$BODY\\" https://git.example.invalid/api/v1/repos/a/b/git/refs"}}\tsame for a quoted body on an unwrapped endpoint\n'
|
||||
printf '0\t{"tool_input":{"command":"gh api repos/${OWNER}/${REPO}/git/refs"}}\ta read with a split endpoint is still a read\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/issues/comments/5"}}\tediting a comment has no wrapper; only creating one does\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1/stopwatch/start"}}\tno wrapper owns a stopwatch, and none is invented for it\n'
|
||||
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/times -f time=60"}}\tnor time tracking\n'
|
||||
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/reactions -f content=+1"}}\tnor reactions\n'
|
||||
# ...and the residue must be decided by the SEGMENT, never by a stray slash.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=see-/docs/x"}}\ta slash inside the body is not a subresource\tissue-edit.sh\n'
|
||||
# The arms above the numbered ones must keep blocking, with their own wrappers.
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tthe wrapped subresource must not fall through\tissue-comment.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues"}}\tnor may issue creation\tissue-create.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls"}}\tPR creation is wrapped and must not fall through with them\tpr-create.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tand a review still names the review wrapper\tpr-review.sh\n'
|
||||
|
||||
# SPAN a third time, now in the scope gate itself: it asked for `/api/v[0-9]`,
|
||||
# which is Gitea's spelling. GitHub's API carries no version segment at all
|
||||
# (`api.github.com/repos/...`), so the schemeless Gitea write was in scope and
|
||||
# the schemeless GitHub one was not — a gate calibrated to one dialect rather
|
||||
# than to what identifies a provider API. `/repos/` is the marker both share.
|
||||
# These endpoints are READABLE, so each asserts the wrapper it must name; a
|
||||
# rc-only fixture here would pass on the unreadable arm and prove nothing.
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/issues"}}\ta schemeless GitHub host is a provider API even with no version segment\tissue-create.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/issues/1/comments"}}\tsame, and the subresource still names its own wrapper\tissue-comment.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"host=api.github.com; curl -X POST -d x ${host}/repos/a/b/issues"}}\tthe host may be a variable; the path is what the guard reads\tissue-create.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/pulls/1/reviews"}}\ta verdict is the costliest call to lose to a spelling\tpr-review.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"p=/repos/a/b/iss; q=ues; curl -X POST -d x api.github.com${p}${q}"}}\tand the split form of it is unreadable, not absent\n'
|
||||
# The end-of-options marker, which is the one option not spelled like one.
|
||||
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; gh api -X POST -- ${p}${q} -f title=x"}}\ta bare -- must not walk the endpoint past the scanner\n'
|
||||
# Widening a scope gate may not create a block. Reads and unwrapped endpoints
|
||||
# in the newly admitted shape have to stay allowed, or this is a regression
|
||||
# wearing a fix'"'"'s clothes.
|
||||
printf '0\t{"tool_input":{"command":"curl api.github.com/repos/a/b/issues"}}\tadmitting a shape to the gate does not make a read a write\n'
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/git/refs"}}\tno wrapper owns git refs, on GitHub'"'"'s spelling either\n'
|
||||
printf '0\t{"tool_input":{"command":"gh api -- repos/a/b/issues"}}\tthe marker in a read is still a read\n'
|
||||
|
||||
# The APPROVE trap, in the spelling a provider CLI uses, and the value that
|
||||
# must never trip it.
|
||||
printf '0\t{"tool_input":{"command":"curl -X POST -d {\\"event\\":\\"APPROVED\\"} https://git.example.invalid/api/v1/repos/a/b/releases"}}\tAPPROVED is the correct value and is never the trap\n'
|
||||
# Documented over-block, pinned so it is a known boundary and not a surprise.
|
||||
printf '2\t{"tool_input":{"command":"python3 -c '"'"'print(\\"https://git.example.invalid/api/v1/repos/a/b/issues/1/comments .post(\\")'"'"'"}}\tprose carrying .post( near a wrapped URL is refused, by the same payload rule\n'
|
||||
|
||||
# --- round nine, all four from one adversarial pass, and three of them are
|
||||
# the same shape: a test written over the WHOLE command text deciding an
|
||||
# ALLOW. That is the fail-open form this file keeps rediscovering, and it had
|
||||
# reached the break-glass itself.
|
||||
#
|
||||
# BREAK-GLASS. `case "$CMD" in *MOSAIC_WRAPPER_OVERRIDE=1*)` cleared the entire
|
||||
# command if that string appeared anywhere in it — so quoting the override in a
|
||||
# note, or naming a variable after it, disabled the guard for the call sitting
|
||||
# beside it. The override is now read POSITIONALLY: leading `NAME=value`
|
||||
# assignments only, exactly where the shell would honour one.
|
||||
printf '2\t{"tool_input":{"command":"echo \\"MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews\\" >> notes.md"}}\tquoting the override in a document does not arm it\n'
|
||||
printf '2\t{"tool_input":{"command":"NOTES=MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tan assignment whose VALUE is the override is not the override\n'
|
||||
printf '2\t{"tool_input":{"command":"MOSAIC_WRAPPER_OVERRIDE=10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t=10 matched the old substring test and is not the value 1\n'
|
||||
printf '0\t{"tool_input":{"command":"GITEA_TOKEN=$T MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tthe override still works behind other assignments, as the shell reads it\n'
|
||||
# The cost, pinned rather than discovered later: positional means positional.
|
||||
printf '2\t{"tool_input":{"command":"cd /tmp && MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\tan override after && is not in command position and does not arm\n'
|
||||
|
||||
# SUBRESOURCE REFINEMENT, same defect one arm lower. It asked whether a
|
||||
# subresource appears ANYWHERE in the command, so a numbered-object write was
|
||||
# cleared on the strength of text in its own BODY. Inverted: clear only when
|
||||
# EVERY numbered-object occurrence carries a subresource.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=cf-/pulls/2/files"}}\ta subresource in the body does not clear a write to the numbered issue\tissue-edit.sh\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=cf-/issues/3/reactions"}}\tsame, quoting a subresource of the same object type\tissue-edit.sh\n'
|
||||
# ...and its documented cost, in the safe direction.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/reactions -f content=cf-/issues/2"}}\tan unwrapped subresource write that quotes a bare issue is refused\n'
|
||||
|
||||
# -K/--config. curl reads the method, the body, the headers AND the URL from
|
||||
# that file, so none of them are in the command: every write test above read 0
|
||||
# and the call went through. An unreadable request is not a cleared one.
|
||||
printf '2\t{"tool_input":{"command":"curl --config /tmp/req https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tthe request in a config file is unreadable, so it is refused\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -K /tmp/req https://git.example.invalid/api/v1/repos/a/b/issues"}}\tthe short spelling, same answer\t--config/-K\n'
|
||||
# Cost, stated: this refuses a --config read against a host that has nothing
|
||||
# to do with a forge. The alternative is to require a forge marker in a
|
||||
# command whose URL may itself be in the file, which is the hole again.
|
||||
printf '2\t{"tool_input":{"command":"curl --config /tmp/req https://example.invalid/anything"}}\tan unrelated https URL with --config is refused too, by decision\t--config/-K\n'
|
||||
printf '0\t{"tool_input":{"command":"eslint --config .eslintrc.json src/"}}\t--config on a command that is not curl is nobody'"'"'s business\n'
|
||||
|
||||
# ROUND TEN. The --config check above was first written INSIDE the API-shape
|
||||
# gate, so it was guarded by a condition that the capability it guards against
|
||||
# removes. A config file can carry the URL; delete the URL from the command and
|
||||
# nothing is API-shaped, the branch is never entered, and the guard reports
|
||||
# clean on precisely the call it exists to refuse. It is now asked of any curl.
|
||||
printf '2\t{"tool_input":{"command":"curl --config /tmp/provider-write.cfg"}}\ta config file can own the URL, so there is nothing API-shaped left to gate on\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -K/tmp/provider-write.cfg"}}\tcurl accepts the value attached to the short flag\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -sK /tmp/provider-write.cfg"}}\tand inside a bundle, which a space-separated test does not see\t--config/-K\n'
|
||||
printf '0\t{"tool_input":{"command":"tar -K /tmp/archive.tar"}}\t-K on a command that is not curl is not this hook'"'"'s business\n'
|
||||
# curl by any ordinary path spelling. The first version of the config check
|
||||
# matched the bare word only, so these three executed the same wrapped write
|
||||
# while the guard reported clean. Recognizing only the unqualified name is
|
||||
# caller-name parsing, and that is the class this file exists to refuse.
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/curl --config /tmp/provider-write.cfg"}}\tan absolute path is the same invocation, not a different one\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"env /usr/bin/curl -K/tmp/provider-write.cfg"}}\tand it is still curl behind env, with the value attached\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"./curl --config /tmp/provider-write.cfg"}}\ta relative path costs two characters and used to be enough\t--config/-K\n'
|
||||
# The prefix must end at a slash: a basename that merely ENDS in curl is a
|
||||
# different program, and blocking it would be the over-block that gets a guard
|
||||
# routed around rather than fixed.
|
||||
printf '0\t{"tool_input":{"command":"mycurl --config /tmp/provider-write.cfg"}}\tmycurl is not curl, and over-blocking is its own failure\n'
|
||||
printf '0\t{"tool_input":{"command":"/opt/x/curl-wrapper --config /tmp/provider-write.cfg"}}\tnor is curl-wrapper, whose name only starts the same way\n'
|
||||
|
||||
# And the same name once it is punctuated. The basename repair above fixed the
|
||||
# UNQUOTED path spelling and nothing else, so two quote characters restored the
|
||||
# bypass it had just closed: the check was still modelling one presentation of
|
||||
# a shell word instead of the word. Every one of these executes the real curl.
|
||||
printf '2\t{"tool_input":{"command":"\\"/usr/bin/curl\\" --config /tmp/provider-write.cfg"}}\tquoting a path does not make it a different program\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"'"'"'./curl'"'"' --config /tmp/provider-write.cfg"}}\tnor does quoting a relative one\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"$(which curl) --config /tmp/provider-write.cfg"}}\tthe name is in the text even when a substitution supplies the path\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"`which curl` --config /tmp/provider-write.cfg"}}\tand in the older spelling of the same substitution\t--config/-K\n'
|
||||
|
||||
# The provider-CLI SCOPE gate had the identical defect, untouched while the
|
||||
# curl arm was repaired twice. It decides whether write detection runs at all,
|
||||
# so failing to admit these is indistinguishable from allowing them — and no
|
||||
# URL marker rescues them, because provider CLI paths carry no leading slash.
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/gh api -X POST repos/a/b/issues -f title=x"}}\tan absolute path to a provider CLI is still a provider CLI\n'
|
||||
printf '2\t{"tool_input":{"command":"./gh api -X POST repos/a/b/issues -f title=x"}}\tand a relative one still is too\n'
|
||||
printf '2\t{"tool_input":{"command":"/usr/local/bin/tea api -X POST repos/a/b/issues -f title=x"}}\tthe same is true of every CLI the gate names, not just the first\n'
|
||||
printf '0\t{"tool_input":{"command":"mygh api -X POST repos/a/b/issues -f title=x"}}\tmygh is not gh, and the scope gate must not over-admit either\n'
|
||||
printf '0\t{"tool_input":{"command":"/usr/bin/gh api repos/a/b/issues"}}\ta read through an absolute path is still a read\n'
|
||||
|
||||
# Quotes and backslashes INSIDE the word. The previous repair replaced quote
|
||||
# characters with whitespace, which is token separation and not quote removal:
|
||||
# a shell removes a quote without splitting the word around it, so `cu"rl"` is
|
||||
# one word naming curl while whitespace made it two words naming neither.
|
||||
# `"/usr/bin/curl"` passed under that version only because the inserted space
|
||||
# happened to land after a slash, which established nothing.
|
||||
printf '2\t{"tool_input":{"command":"cu\\"rl\\" --config /tmp/provider-write.cfg"}}\ta quote inside the word does not make it another program\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"cu'"'"'rl'"'"' --config /tmp/provider-write.cfg"}}\tand a single quote inside it is the same word again\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/cu\\\\rl --config /tmp/provider-write.cfg"}}\tescaping is ordinary word formation, not a disguise\t--config/-K\n'
|
||||
# A backslash is NOT uniformly removed. It is literal inside single quotes,
|
||||
# and inside double quotes when it precedes anything other than $, `, ",
|
||||
# backslash, or newline. These spell a different program and must stay allowed.
|
||||
printf '0\t{"tool_input":{"command":"'"'"'cu\\\\rl'"'"' --config /tmp/provider-write.cfg"}}\ta backslash inside single quotes remains literal\n'
|
||||
printf '0\t{"tool_input":{"command":"\\"cu\\\\rl\\" --config /tmp/provider-write.cfg"}}\ta backslash before r inside double quotes remains literal\n'
|
||||
printf '0\t{"tool_input":{"command":"'"'"'g\\\\it'"'"' clone https://example.invalid/x $HOME/wt"}}\ta literal backslash in a single-quoted non-git name is not a checkout\n'
|
||||
printf '0\t{"tool_input":{"command":"\\"g\\\\it\\" clone https://example.invalid/x $HOME/wt"}}\ta literal backslash in a double-quoted non-git name is not a checkout\n'
|
||||
# The other branch of the same rule: OUTSIDE quotes a backslash escapes the
|
||||
# next character, so an escaped quote is a literal quote IN the name and the
|
||||
# program is not curl. Held separately from the cases above because it is a
|
||||
# different arm of the state machine, and an arm without a fixture is a rule
|
||||
# that is not held.
|
||||
printf '0\t{"tool_input":{"command":"cu\\\\\\"rl\\\\\\" --config /tmp/provider-write.cfg"}}\tan escaped quote is a literal quote in the name\n'
|
||||
# Three quoted segments concatenate into ONE word. This is the shape that
|
||||
# distinguishes quote removal from token separation, so it is worth its own line.
|
||||
printf '2\t{"tool_input":{"command":"\\"cu\\"'"'"'r'"'"'\\"l\\" --config /tmp/provider-write.cfg"}}\tadjacent quoted segments are one word, and that word is curl\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST repos/a/b/issues -f title=x"}}\tthe CLI name is a word on the same terms\n'
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/g\\\\h api -X POST repos/a/b/issues -f title=x"}}\tincluding when it is escaped behind a path\n'
|
||||
# The FLAG is the same recognition problem as the name, and is read the same
|
||||
# way. No review raised this one; the name was simply the easier half to reach.
|
||||
printf '2\t{"tool_input":{"command":"curl --con\\"fig\\" /tmp/provider-write.cfg"}}\tone word spelling --config is still --config\t--config/-K\n'
|
||||
|
||||
# The unreadable-endpoint arm is the THIRD name consumer. It kept a private
|
||||
# bare-name copy of the scope gate's regex, so a caller could be admitted by
|
||||
# the repaired gate and then go unrecognized by the fail-closed refinement —
|
||||
# a gate and its own refinement disagreeing about who the caller is.
|
||||
printf '2\t{"tool_input":{"command":"/usr/bin/gh api -X POST repos/a/b/$EP -f title=x"}}\ta path-qualified CLI with an assembled endpoint is still unreadable\n'
|
||||
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST repos/a/b/$EP -f title=x"}}\tand so is a quoted one, which is where the two halves disagreed\n'
|
||||
printf '0\t{"tool_input":{"command":"mygh api -X POST repos/a/b/$EP -f title=x"}}\tmygh is still not gh, in the refinement as well as the gate\n'
|
||||
|
||||
# Shapes nobody raised. Written down because reasoning that they were already
|
||||
# covered is precisely what produced two of the rounds above; each one below
|
||||
# was measured, and the three that fail at df83a9ee are here on that evidence.
|
||||
# `\curl` is the ordinary way to bypass a shell alias and is a thing people
|
||||
# actually type, which makes it the least hypothetical entry in the file.
|
||||
printf '2\t{"tool_input":{"command":"\\\\curl --config /tmp/provider-write.cfg"}}\tescaping the leading character to dodge an alias still names curl\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"cur\\"l\\" --config /tmp/provider-write.cfg"}}\tthe quote may sit at any offset in the word\t--config/-K\n'
|
||||
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST \\"repos/a/b/$EP\\" -f title=x"}}\tboth halves dressed at once, which is where they last disagreed\n'
|
||||
|
||||
# Over-blocking is a real failure and not a safe direction: a guard that
|
||||
# refuses legitimate work gets routed around instead of repaired. These four
|
||||
# pass at both heads, which is what a regression guard is for.
|
||||
printf '0\t{"tool_input":{"command":"gh api \\"repos/a/b/issues\\""}}\ta quoted read is still a read\n'
|
||||
printf '0\t{"tool_input":{"command":"curl https://example.com/file.txt -o /tmp/f"}}\tan ordinary download is not a provider write\n'
|
||||
printf '0\t{"tool_input":{"command":"echo \\"$EP\\" && gh --version"}}\tno api subcommand, so nothing to refuse\n'
|
||||
printf '0\t{"tool_input":{"command":"echo \\"not a curl call\\""}}\tthe word inside a string, with no flag, is prose\n'
|
||||
|
||||
# Percent-encoded endpoints. Not hypothetical: /issues/1174 and /iss%%75es/1174
|
||||
# both returned HTTP 200 with the same object from the live forge, so the
|
||||
# encoded spelling IS the wrapped endpoint and the literal comparison below it
|
||||
# sees a segment matching nothing. Refused rather than decoded — a decoder has
|
||||
# to be exactly right about depth and normalization, which is the parser
|
||||
# mistake this file declines everywhere else.
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/iss%%75es/1/comments -f body=x"}}\tan encoded path segment reaches the wrapped endpoint\tpercent-escape\n'
|
||||
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/revi%%65ws"}}\tsame for the review endpoint, which is the one that matters most\tpercent-escape\n'
|
||||
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/iss%%2575es/1/comments -f body=x"}}\tdouble-encoded too, which is why this refuses instead of decoding\tpercent-escape\n'
|
||||
# Scoped to writes, deliberately. Reads are never blocked by this guard and a
|
||||
# query string carrying %%20 is an ordinary URL, not a hazard.
|
||||
printf '0\t{"tool_input":{"command":"curl -s https://git.example.invalid/api/v1/repos/a/b/issues?q=a%%20b"}}\ta percent-escape in a READ is not this hook'"'"'s business\n'
|
||||
} > "$FIXTURES"
|
||||
|
||||
fail=0 n=0
|
||||
while IFS=$'\t' read -r want payload why remedy; do
|
||||
[ -n "${want:-}" ] || continue
|
||||
n=$((n + 1))
|
||||
out="$(printf '%s' "$payload" | "$GUARD" 2>&1)"
|
||||
got=$?
|
||||
if [ "$got" != "$want" ]; then
|
||||
printf 'FAIL %s (want exit %s, got %s)\n' "$why" "$want" "$got"
|
||||
fail=1
|
||||
continue
|
||||
fi
|
||||
# A block that names the wrong wrapper is a defect in its own right, and until
|
||||
# now it was invisible here: the harness read the exit code and nothing else,
|
||||
# so /issues/1/labels blocking with "use issue-create.sh" passed every run for
|
||||
# six rounds. Where a fixture states the remediation it expects, assert it.
|
||||
if [ -n "${remedy:-}" ] && ! printf '%s' "$out" | grep -Fq -- "$remedy"; then
|
||||
printf 'FAIL %s (blocked, but the advice does not name %s)\n' "$why" "$remedy"
|
||||
fail=1
|
||||
continue
|
||||
fi
|
||||
printf 'ok %s\n' "$why"
|
||||
done < "$FIXTURES"
|
||||
|
||||
# ---- $HOME resolution ------------------------------------------------------
|
||||
# These cannot be fixtures. Every case above varies the COMMAND; this defect
|
||||
# varies the ENVIRONMENT, and the loop has no way to express that.
|
||||
#
|
||||
# The checkout arm built its pattern from "$HOME" without asking whether $HOME
|
||||
# was a usable value. Three values it is not: unset (which is a crash under
|
||||
# `set -u`, not a decision), empty (the pattern collapses to `/`, so `~|\$HOME|`
|
||||
# matches whatever the empty alternative touches), and "/" (every absolute path
|
||||
# is under it, so the comparison stops discriminating). An agent seat running
|
||||
# with no HOME — a systemd unit without one, a container, `env -i` — got the
|
||||
# checkout question answered by accident rather than on the merits.
|
||||
#
|
||||
# The fix resolves $HOME once, rejects all three, and BLOCKS the checkout it
|
||||
# cannot adjudicate. A guard may not clear a question it was unable to ask. The
|
||||
# blast radius of that fail-closed arm is asserted below to be one command shape
|
||||
# and not the session: with no HOME at all, ordinary commands still pass and the
|
||||
# API arms still block.
|
||||
home_case() {
|
||||
local why="$1" want="$2" homeval="$3" cmd="$4" needle="${5:-}"
|
||||
local out got
|
||||
n=$((n + 1))
|
||||
local payload
|
||||
payload="$(jq -nc --arg command "$cmd" '{tool_input:{command:$command}}')"
|
||||
if [ "$homeval" = "@unset" ]; then
|
||||
out="$(printf '%s' "$payload" | env -u HOME "$GUARD" 2>&1)"
|
||||
else
|
||||
out="$(printf '%s' "$payload" | env HOME="$homeval" "$GUARD" 2>&1)"
|
||||
fi
|
||||
got=$?
|
||||
if [ "$got" != "$want" ]; then
|
||||
printf 'FAIL %s (want exit %s, got %s)\n' "$why" "$want" "$got"
|
||||
fail=1
|
||||
return
|
||||
fi
|
||||
if [ -n "$needle" ] && ! printf '%s' "$out" | grep -Fq -- "$needle"; then
|
||||
printf 'FAIL %s (exit %s, but the message does not say %s)\n' "$why" "$got" "$needle"
|
||||
fail=1
|
||||
return
|
||||
fi
|
||||
printf 'ok %s\n' "$why"
|
||||
}
|
||||
|
||||
home_case 'HOME unset: a checkout is refused, not adjudicated' \
|
||||
2 '@unset' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
|
||||
home_case 'HOME empty: same, and it is not the same thing as unset' \
|
||||
2 '' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
|
||||
home_case 'HOME=/ : every path is under it, so it discriminates nothing' \
|
||||
2 '/' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
|
||||
home_case 'a usable HOME still allows a checkout onto a work filesystem' \
|
||||
0 '/home/tester' 'git clone https://example.invalid/x /src/wt'
|
||||
home_case 'a usable HOME still catches the literal path' \
|
||||
2 '/home/tester' 'git clone https://example.invalid/x /home/tester/wt' 'checks a repository out under'
|
||||
home_case 'a usable HOME catches the exact literal path without a trailing slash' \
|
||||
2 '/home/tester' 'git clone https://example.invalid/x /home/tester' 'checks a repository out under'
|
||||
home_case 'quotes around the exact literal HOME path do not change the target' \
|
||||
2 '/home/tester' 'git clone https://example.invalid/x "/home/tester"' 'checks a repository out under'
|
||||
home_case 'a quoted literal HOME segment remains contiguous with the suffix' \
|
||||
2 '/home/tester' 'git clone https://example.invalid/x "/home/tester"/wt' 'checks a repository out under'
|
||||
home_case 'a repeated leading slash is the same absolute HOME path' \
|
||||
2 '/home/tester' 'git clone https://example.invalid/x //home/tester/wt' 'checks a repository out under'
|
||||
home_case 'dot segments cannot disguise the literal HOME path' \
|
||||
2 '/home/tester' 'git worktree add /var/../home/tester/./wt' 'checks a repository out under'
|
||||
home_case 'parent traversal into HOME is normalized for separate Git state' \
|
||||
2 '/home/tester' 'git clone --separate-git-dir=/home/other/../tester/gd x /src/wt' 'checks a repository out under'
|
||||
home_case 'normalization still permits a literal HOME sibling' \
|
||||
0 '/home/tester' 'git clone x /home/tester/../tester-sibling/wt'
|
||||
home_case 'and the unexpanded $HOME spelling, which needs no resolution at all' \
|
||||
2 '/home/tester' 'git worktree add $HOME/wt topic' 'checks a repository out under'
|
||||
|
||||
# Resolve the longest existing parent physically before appending a nonexistent
|
||||
# destination. Lexical normalization alone cannot see a symlink into HOME, and
|
||||
# it applies `..` in the wrong order when the preceding component is a symlink.
|
||||
SYMLINK_HOME="$TMP/symlink-home"
|
||||
SYMLINK_SAFE="$TMP/symlink-safe"
|
||||
mkdir -p "$SYMLINK_HOME/nested" "$SYMLINK_SAFE"
|
||||
ln -s "$SYMLINK_HOME" "$TMP/home-link"
|
||||
ln -s "$SYMLINK_HOME/nested" "$TMP/home-nested-link"
|
||||
ln -s "$SYMLINK_SAFE" "$TMP/safe-link"
|
||||
home_case 'a clone path through a symlink into HOME is refused' \
|
||||
2 "$SYMLINK_HOME" "git clone x $TMP/home-link/wt" 'checks a repository out under'
|
||||
home_case 'a worktree path through a symlink into HOME is refused' \
|
||||
2 "$SYMLINK_HOME" "git worktree add $TMP/home-link/wt" 'checks a repository out under'
|
||||
home_case 'symlink resolution occurs before a following parent segment' \
|
||||
2 "$SYMLINK_HOME" "git clone x $TMP/home-nested-link/../wt" 'checks a repository out under'
|
||||
home_case 'a symlink to a physical path outside HOME remains allowed' \
|
||||
0 "$SYMLINK_HOME" "git clone x $TMP/safe-link/wt"
|
||||
# The fail-closed arm is scoped to checkouts. If it were not, a seat with no
|
||||
# HOME would have every command it runs refused, which is how a guard gets
|
||||
# disabled rather than fixed.
|
||||
home_case 'HOME unset does not block an ordinary command' \
|
||||
0 '@unset' 'ls -la /src'
|
||||
home_case 'HOME unset does not stop the API arms doing their job' \
|
||||
2 '@unset' 'curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews' 'pr-review.sh'
|
||||
|
||||
# ---- the guard standing on its own -----------------------------------------
|
||||
# Every case above runs the guard from the directory holding its siblings, so
|
||||
# `[ -x "$W/pr-review.sh" ]` succeeds and the $HOME fallback beside it never
|
||||
# evaluates. That is a property of the HARNESS, not of the guard, and it hid a
|
||||
# live fail-open: with the guard copied somewhere alone AND no HOME, the
|
||||
# fallback expanded an unset variable under `set -u` and the script died at
|
||||
# rc=1 — on EVERY arm, before any adjudication. A PreToolUse hook exiting
|
||||
# nonzero-but-not-2 is a non-blocking error, so that seat ran with no guard and
|
||||
# nothing reported it.
|
||||
#
|
||||
# The first remediation moved that expansion four lines earlier and called it
|
||||
# closed. It was not closed, because the test could not reach it. So the guard
|
||||
# is copied ALONE here — no siblings, no installed mosaic home — which is the
|
||||
# deployment this file already claims to support ("still works from a repo
|
||||
# checkout with no installed mosaic home").
|
||||
LONE="$TMP/lone"; mkdir -p "$LONE"
|
||||
cp "$GUARD" "$LONE/wrapper-guard.sh"; chmod +x "$LONE/wrapper-guard.sh"
|
||||
|
||||
lone_case() {
|
||||
local why="$1" want="$2" homeval="$3" cmd="$4" needle="${5:-}"
|
||||
local out got
|
||||
n=$((n + 1))
|
||||
if [ "$homeval" = "@unset" ]; then
|
||||
out="$(printf '%s' "{\"tool_input\":{\"command\":\"$cmd\"}}" | env -u HOME "$LONE/wrapper-guard.sh" 2>&1)"
|
||||
else
|
||||
out="$(printf '%s' "{\"tool_input\":{\"command\":\"$cmd\"}}" | env HOME="$homeval" "$LONE/wrapper-guard.sh" 2>&1)"
|
||||
fi
|
||||
got=$?
|
||||
if [ "$got" != "$want" ]; then
|
||||
printf 'FAIL %s [standalone] (want exit %s, got %s)\n' "$why" "$want" "$got"
|
||||
fail=1
|
||||
return
|
||||
fi
|
||||
if [ -n "$needle" ] && ! printf '%s' "$out" | grep -Fq -- "$needle"; then
|
||||
printf 'FAIL %s [standalone] (exit %s, but the message does not say %s)\n' "$why" "$got" "$needle"
|
||||
fail=1
|
||||
return
|
||||
fi
|
||||
printf 'ok %s [standalone]\n' "$why"
|
||||
}
|
||||
|
||||
lone_case 'no siblings and no HOME: an ordinary command still passes, not rc=1' \
|
||||
0 '@unset' 'ls -la /src'
|
||||
lone_case 'no siblings and no HOME: a wrapped write is still refused' \
|
||||
2 '@unset' 'curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews' 'pr-review.sh'
|
||||
lone_case 'no siblings and no HOME: a checkout is refused, not adjudicated' \
|
||||
2 '@unset' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
|
||||
# Spelled without quotes on purpose. The payload is interpolated into a JSON
|
||||
# string by the helper, so a fixture carrying bare double quotes produces
|
||||
# malformed JSON, jq returns empty, and the guard exits 0 on an empty command —
|
||||
# a PASS that measures nothing. That is what the first version of this case did.
|
||||
lone_case 'no siblings and no HOME: the APPROVE trap still fires' \
|
||||
2 '@unset' 'gh api -X POST repos/a/b/pulls/1/reviews -f event=APPROVE'
|
||||
lone_case 'no siblings, usable HOME: ordinary commands unaffected' \
|
||||
0 '/home/tester' 'ls -la /src'
|
||||
|
||||
printf '\n'
|
||||
if [ "$fail" -eq 0 ]; then
|
||||
printf 'wrapper-guard: %d/%d fixtures behaved as specified.\n' "$n" "$n"
|
||||
else
|
||||
cat <<'EOF'
|
||||
wrapper-guard drifted from its contract.
|
||||
|
||||
A guard that blocks too much gets routed around, and a guard that blocks too
|
||||
little is decoration. Both directions are failures here, which is why the
|
||||
allowed cases are asserted as hard as the blocked ones.
|
||||
EOF
|
||||
fi
|
||||
exit "$fail"
|
||||
File diff suppressed because it is too large
Load Diff
@@ -91,12 +91,10 @@ fi
|
||||
|
||||
if [[ -n "$dirty_files" ]]; then
|
||||
echo " Modified files:"
|
||||
mapfile -t dirty_lines <<<"$dirty_files"
|
||||
file_count="${#dirty_lines[@]}"
|
||||
display_count=$((file_count < 20 ? file_count : 20))
|
||||
for ((i = 0; i < display_count; i++)); do
|
||||
echo " ${dirty_lines[$i]}"
|
||||
echo "$dirty_files" | head -20 | while IFS= read -r line; do
|
||||
echo " $line"
|
||||
done
|
||||
file_count="$(echo "$dirty_files" | wc -l)"
|
||||
if (( file_count > 20 )); then
|
||||
echo " ... and $(( file_count - 20 )) more"
|
||||
fi
|
||||
|
||||
@@ -64,12 +64,12 @@ if jq -e '.next_task == "T-001"' "$capsule_file" >/dev/null 2>&1; then pass_case
|
||||
if grep -Fq 'Target runtime:** codex' <<< "$codex_continue_output"; then pass_case "continue prompt contains target runtime codex"; else fail_case "continue prompt contains target runtime codex"; fi
|
||||
|
||||
codex_run_prompt="$(MOSAIC_COORD_RUNTIME=codex bash "$SCRIPT_DIR/session-run.sh" --project "$tmp_project" --print)"
|
||||
if [[ "${codex_run_prompt%%$'\n'*}" == "Now initiating Orchestrator mode..." ]]; then pass_case "codex run prompt first line is mode declaration"; else fail_case "codex run prompt first line is mode declaration"; fi
|
||||
if [[ "$(printf '%s\n' "$codex_run_prompt" | head -n1)" == "Now initiating Orchestrator mode..." ]]; then pass_case "codex run prompt first line is mode declaration"; else fail_case "codex run prompt first line is mode declaration"; fi
|
||||
if grep -Fq 'Do NOT ask clarifying questions before your first tool actions' <<< "$codex_run_prompt"; then pass_case "codex run prompt includes no-questions hard gate"; else fail_case "codex run prompt includes no-questions hard gate"; fi
|
||||
if grep -Fq '"next_task": "T-001"' <<< "$codex_run_prompt"; then pass_case "codex run prompt embeds capsule json"; else fail_case "codex run prompt embeds capsule json"; fi
|
||||
|
||||
claude_run_prompt="$(MOSAIC_COORD_RUNTIME=claude bash "$SCRIPT_DIR/session-run.sh" --project "$tmp_project" --print)"
|
||||
if [[ "${claude_run_prompt%%$'\n'*}" == "## Continuation Mission" ]]; then pass_case "claude run prompt remains continuation prompt format"; else fail_case "claude run prompt remains continuation prompt format"; fi
|
||||
if [[ "$(printf '%s\n' "$claude_run_prompt" | head -n1)" == "## Continuation Mission" ]]; then pass_case "claude run prompt remains continuation prompt format"; else fail_case "claude run prompt remains continuation prompt format"; fi
|
||||
|
||||
echo ""
|
||||
echo "Smoke test summary: pass=$PASS fail=$FAIL"
|
||||
|
||||
@@ -96,8 +96,8 @@ L="$WORK/live5.md"; G="$WORK/ledger5.md"; echo "# LEDGER" > "$G"
|
||||
make_board "$L" 6 1 400
|
||||
before_l=$(cat "$L"); before_g=$(cat "$G")
|
||||
out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 2000 --dry-run 2>&1) || note "dry-run exited nonzero: $out"
|
||||
grep -qi "dry run" <<<"$out" || note "dry-run did not announce itself"
|
||||
grep -q "would roll" <<<"$out" || note "dry-run did not report a plan"
|
||||
echo "$out" | grep -qi "dry run" || note "dry-run did not announce itself"
|
||||
echo "$out" | grep -q "would roll" || note "dry-run did not report a plan"
|
||||
[[ "$(cat "$L")" == "$before_l" ]] || note "dry-run modified LIVE"
|
||||
[[ "$(cat "$G")" == "$before_g" ]] || note "dry-run modified LEDGER"
|
||||
|
||||
|
||||
@@ -66,7 +66,7 @@ present=0
|
||||
|
||||
for entry in "${PRDY_REQUIRED_SECTIONS[@]}"; do
|
||||
pattern="${entry#*|}"
|
||||
if grep -qiE "$pattern" <<<"$PRD_CONTENT"; then
|
||||
if echo "$PRD_CONTENT" | grep -qiE "$pattern"; then
|
||||
present=$((present + 1))
|
||||
fi
|
||||
done
|
||||
|
||||
@@ -169,13 +169,13 @@ main() {
|
||||
# classify_surface PATH → surface name (highest-risk match wins, mirrors TS)
|
||||
classify_surface() {
|
||||
local p="$1"
|
||||
if grep -qiE 'auth|login|session|token|permission|rbac|credential|secret' <<<"$p"; then echo auth; return; fi
|
||||
if grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed' <<<"$p"; then echo data; return; fi
|
||||
if grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform' <<<"$p"; then echo infra; return; fi
|
||||
if grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite' <<<"$p"; then echo build; return; fi
|
||||
if grep -qE '\.tsx|\.css|components/|apps/web/' <<<"$p"; then echo ui; return; fi
|
||||
if grep -qE '\.spec\.|\.test\.|__tests__/' <<<"$p"; then echo test; return; fi
|
||||
if grep -qE '\.md$|docs/' <<<"$p"; then echo docs; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'auth|login|session|token|permission|rbac|credential|secret'; then echo auth; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed'; then echo data; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform'; then echo infra; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite'; then echo build; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.tsx|\.css|components/|apps/web/'; then echo ui; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.spec\.|\.test\.|__tests__/'; then echo test; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.md$|docs/'; then echo docs; return; fi
|
||||
echo none
|
||||
}
|
||||
|
||||
|
||||
@@ -13,12 +13,7 @@ JSON_INPUT=$(cat)
|
||||
if command -v jq &>/dev/null; then
|
||||
FILE_PATH=$(echo "$JSON_INPUT" | jq -r '.tool_input.file_path // .tool_response.filePath // .file_path // empty' 2>/dev/null || echo "")
|
||||
else
|
||||
file_path_pattern='"file_path"[[:space:]]*:[[:space:]]*"([^"]*)"'
|
||||
if [[ "$JSON_INPUT" =~ $file_path_pattern ]]; then
|
||||
FILE_PATH="${BASH_REMATCH[1]}"
|
||||
else
|
||||
FILE_PATH=""
|
||||
fi
|
||||
FILE_PATH=$(echo "$JSON_INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"\([^"]*\)"$/\1/' | head -1)
|
||||
fi
|
||||
|
||||
# Only check TypeScript files
|
||||
@@ -58,7 +53,7 @@ OUTPUT=$(npx tsc --noEmit --pretty --maxNodeModuleJsDepth 0 2>&1) || STATUS=$?
|
||||
if [ "${STATUS:-0}" -ne 0 ]; then
|
||||
# Filter output to only show errors related to the edited file (if possible)
|
||||
BASENAME=$(basename "$FILE_PATH")
|
||||
RELEVANT=$(grep -A2 "$BASENAME" <<<"$OUTPUT" 2>/dev/null || sed -n '1,20p' <<<"$OUTPUT")
|
||||
RELEVANT=$(echo "$OUTPUT" | grep -A2 "$BASENAME" 2>/dev/null || echo "$OUTPUT" | head -20)
|
||||
|
||||
echo "TypeScript type errors detected after editing $FILE_PATH:"
|
||||
echo "$RELEVANT"
|
||||
|
||||
@@ -1,293 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# check-tools-index.sh — assert every shipped tool is discoverable from the
|
||||
# resident documentation an agent actually has in context.
|
||||
#
|
||||
# WHY THIS GATE EXISTS
|
||||
# --------------------
|
||||
# The framework ships 26 git wrappers. Before this gate, 20 of them were named
|
||||
# in neither `defaults/TOOLS.md` nor `guides/TOOLS-REFERENCE.md`. One of the
|
||||
# undocumented ones was `pr-review.sh` — the wrapper that carries the
|
||||
# APPROVED/APPROVE provider-dialect split.
|
||||
#
|
||||
# The observable consequence, on a live fleet host: an agent needing to place a
|
||||
# review verdict reached for raw `curl`, sent GitHub's `APPROVE` to a Gitea
|
||||
# host, and got HTTP 200 with the review silently filed PENDING — three times,
|
||||
# because nothing about the failure pointed at the wrapper that already handled
|
||||
# it correctly. The agent was not ignoring Constitution gate 7. It was obeying
|
||||
# an index that said the tool did not exist.
|
||||
#
|
||||
# That is not a discipline problem and no amount of prose fixes it. A wrapper
|
||||
# that is not in the resident index is, from inside a session, indistinguishable
|
||||
# from a wrapper that was never written. So the invariant is mechanical:
|
||||
#
|
||||
# shipping a tool and documenting it are the same commit, or CI fails.
|
||||
#
|
||||
# WHAT IT CHECKS
|
||||
# --------------
|
||||
# forward every non-excluded tool in an ENFORCED suite is named in at least
|
||||
# one index document (missing tool -> undiscoverable -> FAIL)
|
||||
# reverse every `<name>.sh` an index document attributes to an enforced
|
||||
# suite exists on disk (stale reference -> agent runs a ghost -> FAIL)
|
||||
#
|
||||
# Suites outside the enforced set are reported with a coverage percentage but do
|
||||
# not fail the build, so the ratchet can be tightened one suite per PR instead of
|
||||
# landing as one unreviewable sweep. `--strict` fails on those too.
|
||||
#
|
||||
# WHY THE ENFORCED LIST LIVES HERE AND NOT IN A MARKER INSIDE THE DOC
|
||||
# -------------------------------------------------------------------
|
||||
# `TOOLS.md` is operator-owned (see framework-manifest.txt). A marker inside it
|
||||
# would let an operator silence this gate by editing their own copy — the gate
|
||||
# would then be strongest exactly where it is least needed and absent where it
|
||||
# is needed most. The list is framework-owned and changes only through a
|
||||
# reviewed PR.
|
||||
#
|
||||
# Usage:
|
||||
# check-tools-index.sh [--tools-dir DIR] [--doc FILE]... [--strict] [--self-test]
|
||||
#
|
||||
# Exit: 0 = every enforced suite fully discoverable · 1 = drift · 2 = bad usage
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
# Suites whose coverage is a HARD requirement. Add a suite here only together
|
||||
# with the doc changes that make it pass.
|
||||
#
|
||||
# `git` is first because it is the suite Constitution gates 6-8 make mandatory:
|
||||
# an undiscoverable git wrapper converts a hard gate into a coin flip.
|
||||
ENFORCED_SUITES=(git)
|
||||
|
||||
# Files that are not agent-callable tools and must not be required in an index.
|
||||
EXCLUDE_GLOBS=(
|
||||
'test-*' # hermetic regression scripts, invoked by CI not by agents
|
||||
'_*' # private helpers (_lib, _scripts internals)
|
||||
'*.bak' # editor/installer debris
|
||||
'*.pre-*' # pre-change backups (e.g. ci-queue-wait.sh.pre-404fix-bak)
|
||||
'README.md'
|
||||
)
|
||||
|
||||
STRICT=0
|
||||
SELF_TEST=0
|
||||
TOOLS_DIR=""
|
||||
DOCS=()
|
||||
|
||||
die() { printf 'check-tools-index: %s\n' "$*" >&2; exit 2; }
|
||||
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--tools-dir) TOOLS_DIR="${2:-}"; shift 2 ;;
|
||||
--doc) DOCS+=("${2:-}"); shift 2 ;;
|
||||
--strict) STRICT=1; shift ;;
|
||||
--self-test) SELF_TEST=1; shift ;;
|
||||
-h|--help) sed -n '2,48p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
|
||||
*) die "unknown argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# ---- location resolution ---------------------------------------------------
|
||||
# Runs from two places with different layouts, and must not silently check the
|
||||
# wrong tree: a CI checkout (repo-relative) and an installed host ($MOSAIC_HOME).
|
||||
resolve_locations() {
|
||||
local here framework
|
||||
here="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# .../framework/tools/quality/scripts -> .../framework
|
||||
framework="$(cd -- "$here/../../.." && pwd)"
|
||||
|
||||
if [ -z "$TOOLS_DIR" ]; then
|
||||
if [ -d "$framework/tools" ]; then
|
||||
TOOLS_DIR="$framework/tools"
|
||||
else
|
||||
TOOLS_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}/tools"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ ${#DOCS[@]} -eq 0 ]; then
|
||||
# The two layouts are mutually exclusive on purpose. Unioning them would let
|
||||
# a well-maintained operator TOOLS.md on the developer's own machine mask a
|
||||
# gap in the shipped defaults — the check would pass locally and the defect
|
||||
# would still install on every other host. Repo layout wins when present.
|
||||
if [ -f "$framework/defaults/TOOLS.md" ]; then
|
||||
DOCS+=("$framework/defaults/TOOLS.md")
|
||||
[ -f "$framework/guides/TOOLS-REFERENCE.md" ] && DOCS+=("$framework/guides/TOOLS-REFERENCE.md")
|
||||
else
|
||||
local mosaic_home="${MOSAIC_HOME:-$HOME/.config/mosaic}"
|
||||
[ -f "$mosaic_home/TOOLS.md" ] && DOCS+=("$mosaic_home/TOOLS.md")
|
||||
[ -f "$mosaic_home/guides/TOOLS-REFERENCE.md" ] && DOCS+=("$mosaic_home/guides/TOOLS-REFERENCE.md")
|
||||
fi
|
||||
fi
|
||||
|
||||
[ -d "$TOOLS_DIR" ] || die "tools dir not found: $TOOLS_DIR"
|
||||
[ ${#DOCS[@]} -gt 0 ] || die "no index documents found (pass --doc FILE)"
|
||||
}
|
||||
|
||||
is_excluded() {
|
||||
local name="$1" glob
|
||||
for glob in "${EXCLUDE_GLOBS[@]}"; do
|
||||
# shellcheck disable=SC2254 # glob is intentionally a pattern
|
||||
case "$name" in $glob) return 0 ;; esac
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
# A tool counts as documented when its basename appears anywhere in the corpus.
|
||||
# Deliberately permissive about *form* (table cell, code fence, prose) and strict
|
||||
# about *presence*: the gate's job is "an agent can find it", not house style.
|
||||
documented() { grep -qF -- "$1" "$CORPUS"; }
|
||||
|
||||
# ---- the check -------------------------------------------------------------
|
||||
run_check() {
|
||||
local rc=0 suite dir tool base enforced
|
||||
|
||||
CORPUS="$(mktemp)"; trap 'rm -f "$CORPUS"' RETURN
|
||||
cat "${DOCS[@]}" > "$CORPUS"
|
||||
|
||||
printf 'tools: %s\n' "$TOOLS_DIR"
|
||||
for d in "${DOCS[@]}"; do printf 'index: %s\n' "$d"; done
|
||||
printf '\n'
|
||||
|
||||
for dir in "$TOOLS_DIR"/*/; do
|
||||
[ -d "$dir" ] || continue
|
||||
suite="$(basename -- "$dir")"
|
||||
case " ${ENFORCED_SUITES[*]} " in *" $suite "*) enforced=1 ;; *) enforced=0 ;; esac
|
||||
[ "$STRICT" -eq 1 ] && enforced=1
|
||||
case "$suite" in _*) continue ;; esac
|
||||
|
||||
local total=0 found=0
|
||||
local -a suite_missing=() suite_noexec=()
|
||||
for tool in "$dir"*.sh; do
|
||||
[ -e "$tool" ] || continue
|
||||
base="$(basename -- "$tool")"
|
||||
is_excluded "$base" && continue
|
||||
total=$((total + 1))
|
||||
if documented "$base"; then
|
||||
found=$((found + 1))
|
||||
# Documented AND present is not enough. The index presents these as
|
||||
# commands to run, and every caller — the wrapper guard included —
|
||||
# decides "is this tool here?" with `[ -x ]`. A 0644 wrapper is
|
||||
# documented, present, and dead: it reads as absent to every check that
|
||||
# matters while scoring 100% here. That is a false green, which is worse
|
||||
# than a red, so it fails rather than warns.
|
||||
[ -x "$tool" ] || suite_noexec+=("$base")
|
||||
else
|
||||
suite_missing+=("$base")
|
||||
fi
|
||||
done
|
||||
[ "$total" -eq 0 ] && continue
|
||||
|
||||
local pct=$(( found * 100 / total ))
|
||||
if [ "$enforced" -eq 1 ] && [ ${#suite_noexec[@]} -gt 0 ]; then
|
||||
printf 'FAIL %-12s %3d%% (%d/%d) documented but not executable: %s\n' \
|
||||
"$suite" "$pct" "$found" "$total" "${suite_noexec[*]}"
|
||||
rc=1
|
||||
fi
|
||||
if [ "$enforced" -eq 1 ] && [ ${#suite_missing[@]} -gt 0 ]; then
|
||||
printf 'FAIL %-12s %3d%% (%d/%d) undocumented: %s\n' \
|
||||
"$suite" "$pct" "$found" "$total" "${suite_missing[*]}"
|
||||
rc=1
|
||||
elif [ "$enforced" -eq 1 ] && [ ${#suite_noexec[@]} -eq 0 ]; then
|
||||
printf 'ok %-12s %3d%% (%d/%d) [enforced]\n' "$suite" "$pct" "$found" "$total"
|
||||
else
|
||||
printf 'info %-12s %3d%% (%d/%d) not yet enforced\n' "$suite" "$pct" "$found" "$total"
|
||||
fi
|
||||
|
||||
# Reverse: an index that names a tool this suite does not have sends agents
|
||||
# after something that cannot run. Only checked for enforced suites, where
|
||||
# the naming is unambiguous enough to attribute.
|
||||
if [ "$enforced" -eq 1 ]; then
|
||||
local -a stale=()
|
||||
local ref
|
||||
while read -r ref; do
|
||||
[ -n "$ref" ] || continue
|
||||
is_excluded "$ref" && continue
|
||||
[ -e "$dir$ref" ] || stale+=("$ref")
|
||||
done < <(grep -oE "$suite/[a-z0-9][a-z0-9._-]*\.sh" "$CORPUS" \
|
||||
| sed "s|^$suite/||" | sort -u)
|
||||
if [ ${#stale[@]} -gt 0 ]; then
|
||||
printf 'FAIL %-12s stale index references (no such file): %s\n' \
|
||||
"$suite" "${stale[*]}"
|
||||
rc=1
|
||||
fi
|
||||
fi
|
||||
done
|
||||
|
||||
printf '\n'
|
||||
if [ "$rc" -ne 0 ]; then
|
||||
cat <<EOF
|
||||
Undocumented tools are undiscoverable. An agent cannot obey a hard gate that
|
||||
tells it to use a wrapper it has no way to learn exists — it will reach for raw
|
||||
curl/gh/tea instead, and the wrapper's provider-dialect handling will be lost.
|
||||
|
||||
Fix by naming each tool above in one of the index documents listed at the top,
|
||||
in the same commit that ships it.
|
||||
EOF
|
||||
else
|
||||
printf 'every enforced suite is fully discoverable.\n'
|
||||
fi
|
||||
return "$rc"
|
||||
}
|
||||
|
||||
# ---- self-test -------------------------------------------------------------
|
||||
# Proves the gate can actually fail. A checker that only ever passes is
|
||||
# indistinguishable from one that is not running, which is the failure mode this
|
||||
# whole file exists to prevent — so it must demonstrate a red on demand.
|
||||
self_test() {
|
||||
local tmp rc
|
||||
tmp="$(mktemp -d)"; trap 'rm -rf "$tmp"' RETURN
|
||||
mkdir -p "$tmp/tools/git"
|
||||
printf '#!/bin/sh\n' > "$tmp/tools/git/documented-tool.sh"
|
||||
printf '#!/bin/sh\n' > "$tmp/tools/git/test-ignored.sh"
|
||||
chmod +x "$tmp/tools/git/documented-tool.sh" "$tmp/tools/git/test-ignored.sh"
|
||||
|
||||
# run_check reads the TOOLS_DIR / DOCS globals; an array cannot ride in a
|
||||
# command-prefix assignment, so point the globals at the fixture directly.
|
||||
TOOLS_DIR="$tmp/tools"
|
||||
DOCS=("$tmp/doc.md")
|
||||
|
||||
# Case 1: fully documented -> pass.
|
||||
printf 'see tools/git/documented-tool.sh for details\n' > "$tmp/doc.md"
|
||||
if run_check >/dev/null; then
|
||||
printf 'self-test 1/4 ok (complete index passes)\n'
|
||||
else
|
||||
printf 'self-test 1/4 FAIL (complete index should pass)\n'; return 1
|
||||
fi
|
||||
|
||||
# Case 2: an undocumented tool -> fail.
|
||||
printf '#!/bin/sh\n' > "$tmp/tools/git/undocumented-tool.sh"
|
||||
rc=0; run_check >/dev/null || rc=$?
|
||||
if [ "$rc" -eq 1 ]; then
|
||||
printf 'self-test 2/4 ok (undocumented tool fails the gate)\n'
|
||||
else
|
||||
printf 'self-test 2/4 FAIL (undocumented tool should fail, got rc=%s)\n' "$rc"; return 1
|
||||
fi
|
||||
|
||||
# Case 3: a stale index reference -> fail.
|
||||
rm "$tmp/tools/git/undocumented-tool.sh"
|
||||
printf 'also tools/git/deleted-tool.sh\n' >> "$tmp/doc.md"
|
||||
rc=0; run_check >/dev/null || rc=$?
|
||||
if [ "$rc" -eq 1 ]; then
|
||||
printf 'self-test 3/4 ok (stale index reference fails the gate)\n'
|
||||
else
|
||||
printf 'self-test 3/4 FAIL (stale reference should fail, got rc=%s)\n' "$rc"; return 1
|
||||
fi
|
||||
|
||||
# Case 4: documented, present, and NOT executable -> fail. Found by an
|
||||
# independent reviewer: a 0644 wrapper scored 100% here while reading as
|
||||
# absent to every `[ -x ]` in the fleet, including the wrapper guard's.
|
||||
sed -i '/deleted-tool/d' "$tmp/doc.md"
|
||||
printf '#!/bin/sh\n' > "$tmp/tools/git/noexec-tool.sh"
|
||||
chmod 0644 "$tmp/tools/git/noexec-tool.sh"
|
||||
printf 'and tools/git/noexec-tool.sh\n' >> "$tmp/doc.md"
|
||||
rc=0; run_check >/dev/null || rc=$?
|
||||
if [ "$rc" -eq 1 ]; then
|
||||
printf 'self-test 4/4 ok (documented but non-executable tool fails the gate)\n'
|
||||
else
|
||||
printf 'self-test 4/4 FAIL (non-executable tool should fail, got rc=%s)\n' "$rc"; return 1
|
||||
fi
|
||||
|
||||
printf '\nself-test passed: the gate demonstrably reds on every drift direction.\n'
|
||||
}
|
||||
|
||||
if [ "$SELF_TEST" -eq 1 ]; then
|
||||
self_test
|
||||
else
|
||||
resolve_locations
|
||||
run_check
|
||||
fi
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user