Compare commits
3
Commits
main
..
aafc155563
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
aafc155563 | ||
|
|
e0c00e4209 | ||
|
|
ab360d443c |
@@ -46,10 +46,6 @@ steps:
|
|||||||
# [0] of the pnpm chain, so severing that chain would silence it together
|
# [0] of the pnpm chain, so severing that chain would silence it together
|
||||||
# with everything it guards; this direct line keeps one instrument running.
|
# with everything it guards; this direct line keeps one instrument running.
|
||||||
- bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh
|
- bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.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
|
|
||||||
|
|
||||||
# Blocking gate (#791): a framework upgrade must never write or delete an
|
# Blocking gate (#791): a framework upgrade must never write or delete an
|
||||||
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
|
# 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.
|
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
|
### TUI & Gateway
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
|
|||||||
@@ -245,21 +245,9 @@ describe('EnrollmentService.createToken', () => {
|
|||||||
const after = Date.now();
|
const after = Date.now();
|
||||||
|
|
||||||
const expiresMs = new Date(result.expiresAt).getTime();
|
const expiresMs = new Date(result.expiresAt).getTime();
|
||||||
|
// Should be at most 900s from now
|
||||||
// The property under test is CLAMPING: a 9999s request must come back as 900s.
|
expect(expiresMs - before).toBeLessThanOrEqual(900_000 + 100);
|
||||||
// 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);
|
|
||||||
expect(expiresMs - after).toBeGreaterThanOrEqual(0);
|
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);
|
|
||||||
});
|
});
|
||||||
});
|
});
|
||||||
|
|
||||||
|
|||||||
-154
@@ -102,128 +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)
|
## Fleet Declarative Configuration Management Workstream (FCM, #758)
|
||||||
|
|
||||||
### Problem and objective
|
### Problem and objective
|
||||||
@@ -298,38 +176,6 @@ roster-derived part of the generated launch projection and prove it reaches the
|
|||||||
3. `AC-FGI-03`: Focused launcher and generated-environment tests, repository quality gates,
|
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.
|
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)
|
## Exact Cross-Harness Fleet Communications Contract (#766)
|
||||||
|
|||||||
@@ -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 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.
|
- [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 management
|
||||||
|
|
||||||
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
|
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
|
||||||
|
|||||||
@@ -7,8 +7,7 @@
|
|||||||
3. [Provider Configuration](#provider-configuration)
|
3. [Provider Configuration](#provider-configuration)
|
||||||
4. [MCP Server Configuration](#mcp-server-configuration)
|
4. [MCP Server Configuration](#mcp-server-configuration)
|
||||||
5. [Environment Variables Reference](#environment-variables-reference)
|
5. [Environment Variables Reference](#environment-variables-reference)
|
||||||
6. [Pi Goal Loop Operations](#pi-goal-loop-operations)
|
6. [Local Fleet Canary](./fleet-local-canary.md)
|
||||||
7. [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_SYSTEM_PROMPT` | — | Platform-level system prompt injected into all sessions |
|
||||||
| `AGENT_USER_TOOLS` | all tools | Comma-separated allowlist of tools for non-admin users |
|
| `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
|
### Providers
|
||||||
|
|
||||||
| Variable | Default | Description |
|
| Variable | Default | Description |
|
||||||
@@ -385,29 +374,3 @@ Session cleanup is scoped to one session identifier and only removes that sessio
|
|||||||
| Variable | Default | Description |
|
| Variable | Default | Description |
|
||||||
| ----------------------- | ----------------------------- | ------------------------------------------ |
|
| ----------------------- | ----------------------------- | ------------------------------------------ |
|
||||||
| `MOSAIC_WORKSPACE_ROOT` | monorepo root (auto-detected) | Root path for mission workspace operations |
|
| `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)
|
5. [Adding New MCP Tools](#adding-new-mcp-tools)
|
||||||
6. [Database Schema and Migrations](#database-schema-and-migrations)
|
6. [Database Schema and Migrations](#database-schema-and-migrations)
|
||||||
7. [Claude Code Skill Bridge](#claude-code-skill-bridge)
|
7. [Claude Code Skill Bridge](#claude-code-skill-bridge)
|
||||||
8. [Pi Persistent Goal Extension](#pi-persistent-goal-extension)
|
8. [API Endpoint Reference](#api-endpoint-reference)
|
||||||
9. [API Endpoint Reference](#api-endpoint-reference)
|
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||||
10. [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
|
canonical root directly. Codex still relies on the existing full skill-sync
|
||||||
linker and needs separate parity analysis before this lifecycle API is extended.
|
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
|
## API Endpoint Reference
|
||||||
|
|
||||||
All endpoints are served by the gateway at `http://localhost:14242` by default.
|
All endpoints are served by the gateway at `http://localhost:14242` by default.
|
||||||
|
|||||||
@@ -8,10 +8,9 @@
|
|||||||
4. [Tasks](#tasks)
|
4. [Tasks](#tasks)
|
||||||
5. [Settings](#settings)
|
5. [Settings](#settings)
|
||||||
6. [CLI Usage](#cli-usage)
|
6. [CLI Usage](#cli-usage)
|
||||||
7. [Pi Persistent Goals](#pi-persistent-goals)
|
7. [Sub-package Commands](#sub-package-commands)
|
||||||
8. [Sub-package Commands](#sub-package-commands)
|
8. [Telemetry](#telemetry)
|
||||||
9. [Telemetry](#telemetry)
|
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||||
10. [Local Fleet Canary](./fleet-local-canary.md)
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -308,57 +307,6 @@ mosaic prdy
|
|||||||
mosaic quality-rails
|
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
|
### Claude Code Skill Registration
|
||||||
|
|||||||
@@ -1,72 +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 |
|
|
||||||
|
|
||||||
Remaining wake-validation sites are intentionally deferred to the final review-sized tranche and are not yet assigned a safety verdict here.
|
|
||||||
@@ -192,37 +192,6 @@ This is the third GNU-host/Alpine-CI portability defect in the lane: GNU `grep`
|
|||||||
- Workflow definition population: **1/3 pull-request-eligible** (`ci.yml` of `ci.yml`, `ci-image.yml`, `publish.yml`).
|
- 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.
|
- 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
|
## 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.
|
- Landing on `main` does not update the currently installed host launcher. Host framework installation/reseed and Jarvis live-seat validation are separate downstream events.
|
||||||
|
|||||||
@@ -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.
|
|
||||||
@@ -1,37 +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.
|
|
||||||
|
|
||||||
## 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 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.
|
|
||||||
@@ -1,99 +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.
|
|
||||||
@@ -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`
|
1. Injects the full runtime contract via `--append-system-prompt`
|
||||||
2. Loads Mosaic skills via `--skill` flags
|
2. Loads Mosaic skills via `--skill` flags
|
||||||
3. Loads framework-owned `mosaic-extension.ts` and `goal-extension.ts` from
|
3. Loads the Mosaic extension via `--extension` for lifecycle hooks
|
||||||
`~/.config/mosaic/runtime/pi/` via ordered `--extension` flags
|
|
||||||
4. Detects active missions and injects initial prompts
|
4. Detects active missions and injects initial prompts
|
||||||
|
|
||||||
## Capabilities vs Other Runtimes
|
## 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 thinking levels replace sequential-thinking MCP
|
||||||
- Native skill discovery compatible with Mosaic SKILL.md format
|
- Native skill discovery compatible with Mosaic SKILL.md format
|
||||||
- Native extension system for lifecycle hooks (TypeScript, not bash shims)
|
- 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
|
- Native session persistence and resume
|
||||||
- Model-agnostic (Anthropic, OpenAI, Google, Ollama, custom providers)
|
- Model-agnostic (Anthropic, OpenAI, Google, Ollama, custom providers)
|
||||||
|
|
||||||
|
|||||||
@@ -94,14 +94,7 @@ The launcher:
|
|||||||
1. Verifies `~/.config/mosaic` exists
|
1. Verifies `~/.config/mosaic` exists
|
||||||
2. Verifies `SOUL.md` exists (auto-runs `mosaic init` if missing)
|
2. Verifies `SOUL.md` exists (auto-runs `mosaic init` if missing)
|
||||||
3. Injects `AGENTS.md` into the runtime
|
3. Injects `AGENTS.md` into the runtime
|
||||||
4. For Pi, loads the framework-owned core and persistent-goal extensions from
|
4. Forwards all arguments to the runtime CLI
|
||||||
`~/.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.
|
|
||||||
|
|
||||||
You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtime adapters will tell the agent to read `~/.config/mosaic/AGENTS.md`.
|
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
|
│ ├── claude/ ← CLAUDE.md, RUNTIME.md, settings.json, hooks
|
||||||
│ ├── codex/ ← instructions.md, RUNTIME.md
|
│ ├── codex/ ← instructions.md, RUNTIME.md
|
||||||
│ ├── opencode/ ← AGENTS.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
|
│ └── mcp/ ← MCP server configs
|
||||||
├── skills/ ← Universal skills (synced from mosaic/agent-skills)
|
├── skills/ ← Universal skills (synced from mosaic/agent-skills)
|
||||||
├── skills-local/ ← Local cross-runtime 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 |
|
| 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 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 codex` | Writes composed runtime contract to `~/.codex/instructions.md` before launch |
|
||||||
| `mosaic opencode` | Writes composed runtime contract to `~/.config/opencode/AGENTS.md` before launch |
|
| `mosaic opencode` | Writes composed runtime contract to `~/.config/opencode/AGENTS.md` before launch |
|
||||||
|
|||||||
@@ -51,26 +51,12 @@ Skills are discovered from:
|
|||||||
|
|
||||||
### Extensions
|
### Extensions
|
||||||
|
|
||||||
`mosaic pi` loads framework-owned extensions directly from `~/.config/mosaic/runtime/pi/` in this
|
The Mosaic Pi extension (`~/.config/mosaic/runtime/pi/mosaic-extension.ts`) handles:
|
||||||
order:
|
|
||||||
|
|
||||||
1. `mosaic-extension.ts` — session lifecycle, mission context, memory routing, lease/mutator gates,
|
- Session start/end lifecycle hooks
|
||||||
and fleet heartbeat reporting.
|
- Active mission detection and context injection
|
||||||
2. `goal-extension.ts` — optional persistent `/goal` controller with per-turn and post-compaction
|
- Memory routing to `~/.config/mosaic/memory/`
|
||||||
checks.
|
- MACP queue status reporting
|
||||||
|
|
||||||
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`.
|
|
||||||
|
|
||||||
### Sessions
|
### 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 "$TEST_ROOT"' EXIT
|
trap 'tmux -L "$TEST_SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$TEST_ROOT"' EXIT
|
||||||
MARKER="$TEST_ROOT/loader-marker"
|
MARKER="$TEST_ROOT/loader-marker"
|
||||||
LIBRARY="$TEST_ROOT/marker.so"
|
LIBRARY="$TEST_ROOT/marker.so"
|
||||||
FIXTURE_READY="$TEST_ROOT/loader-ready"
|
|
||||||
FIXTURE_FIFO="$TEST_ROOT/loader-block"
|
|
||||||
HOLDER_HOME="$TEST_ROOT/holder-home"
|
HOLDER_HOME="$TEST_ROOT/holder-home"
|
||||||
mkfifo "$FIXTURE_FIFO"
|
|
||||||
mkdir -p "$HOLDER_HOME/.config/mosaic/fleet/run"
|
mkdir -p "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||||
chmod 700 "$HOLDER_HOME/.config" "$HOLDER_HOME/.config/mosaic" \
|
chmod 700 "$HOLDER_HOME/.config" "$HOLDER_HOME/.config/mosaic" \
|
||||||
"$HOLDER_HOME/.config/mosaic/fleet" "$HOLDER_HOME/.config/mosaic/fleet/run"
|
"$HOLDER_HOME/.config/mosaic/fleet" "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||||
@@ -90,17 +87,7 @@ __attribute__((constructor)) static void mark_loader(void) {
|
|||||||
EOF
|
EOF
|
||||||
cc -shared -fPIC -o "$LIBRARY" "$TEST_ROOT/marker.c"
|
cc -shared -fPIC -o "$LIBRARY" "$TEST_ROOT/marker.c"
|
||||||
MOSAIC_LOADER_MARKER="$MARKER" LD_PRELOAD="$LIBRARY" \
|
MOSAIC_LOADER_MARKER="$MARKER" LD_PRELOAD="$LIBRARY" \
|
||||||
tmux -L "$TEST_SOCKET" new-session -d -s _holder \
|
tmux -L "$TEST_SOCKET" new-session -d -s _holder 'sleep 60'
|
||||||
"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"
|
|
||||||
[ -s "$MARKER" ] || fail "contaminated fixture did not execute loader constructor"
|
[ -s "$MARKER" ] || fail "contaminated fixture did not execute loader constructor"
|
||||||
server_pid=$(tmux -L "$TEST_SOCKET" display-message -p '#{pid}')
|
server_pid=$(tmux -L "$TEST_SOCKET" display-message -p '#{pid}')
|
||||||
: > "$MARKER"
|
: > "$MARKER"
|
||||||
@@ -158,8 +145,7 @@ EOF
|
|||||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin \
|
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin \
|
||||||
MOSAIC_TMUX_SOCKET="$TEST_SOCKET" MOSAIC_TMUX_HOLDER=_holder "$HOLDER_START"
|
MOSAIC_TMUX_SOCKET="$TEST_SOCKET" MOSAIC_TMUX_HOLDER=_holder "$HOLDER_START"
|
||||||
tmux -L "$TEST_SOCKET" has-session -t '=_holder:0.0' || fail "fresh holder was not created"
|
tmux -L "$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 tmux -L "$TEST_SOCKET" show-environment -g LD_PRELOAD 2>/dev/null | grep -q '^LD_PRELOAD='; then
|
||||||
if grep -q '^LD_PRELOAD=' <<<"$ld_preload_env"; then
|
|
||||||
fail "fresh holder retained LD_PRELOAD"
|
fail "fresh holder retained LD_PRELOAD"
|
||||||
fi
|
fi
|
||||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
||||||
|
|||||||
@@ -69,7 +69,7 @@ if [[ -n "$GROUP" ]]; then
|
|||||||
group_response=$(curl -sk \
|
group_response=$(curl -sk \
|
||||||
-H "Authorization: Bearer $TOKEN" \
|
-H "Authorization: Bearer $TOKEN" \
|
||||||
"${AUTHENTIK_URL}/api/v3/core/groups/?search=${GROUP}")
|
"${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
|
if [[ -n "$group_pk" ]]; then
|
||||||
payload=$(echo "$payload" | jq --arg gk "$group_pk" '. + {groups: [$gk]}')
|
payload=$(echo "$payload" | jq --arg gk "$group_pk" '. + {groups: [$gk]}')
|
||||||
else
|
else
|
||||||
|
|||||||
@@ -14,82 +14,6 @@ fail() {
|
|||||||
exit 1
|
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'
|
cat > "$FAKE_BIN/tmux" <<'SHIM'
|
||||||
#!/usr/bin/env bash
|
#!/usr/bin/env bash
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
@@ -138,19 +62,6 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
|
|||||||
SHIM
|
SHIM
|
||||||
chmod +x "$FAKE_BIN/mosaic"
|
chmod +x "$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() {
|
write_generated() {
|
||||||
local home="$1"
|
local home="$1"
|
||||||
local agent="$2"
|
local agent="$2"
|
||||||
@@ -178,7 +89,6 @@ run_start() {
|
|||||||
local agent="$2"
|
local agent="$2"
|
||||||
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||||
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
||||||
MOSAIC_TEST_FIXED_EPOCH="${MOSAIC_TEST_FIXED_EPOCH:-}" \
|
|
||||||
MOSAIC_TEST_HOME="$home" \
|
MOSAIC_TEST_HOME="$home" \
|
||||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||||
MOSAIC_HOME="$home" "$START" "$agent"
|
MOSAIC_HOME="$home" "$START" "$agent"
|
||||||
@@ -191,19 +101,19 @@ AGENT_VALID="coder0"
|
|||||||
write_generated "$HOME_VALID" "$AGENT_VALID"
|
write_generated "$HOME_VALID" "$AGENT_VALID"
|
||||||
run_start "$HOME_VALID" "$AGENT_VALID"
|
run_start "$HOME_VALID" "$AGENT_VALID"
|
||||||
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||||
contains_literal "$valid_args" new-session || fail "valid generated projection did not reach tmux"
|
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
||||||
contains_literal "$valid_args" mosaic || fail "fixed mosaic launcher command missing"
|
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
||||||
contains_literal "$valid_args" yolo || fail "fixed yolo launcher command missing"
|
echo "$valid_args" | grep -qF 'yolo' || fail "fixed yolo launcher command missing"
|
||||||
contains_literal "$valid_args" pi || fail "roster runtime missing"
|
echo "$valid_args" | grep -qF 'pi' || fail "roster runtime missing"
|
||||||
if contains_literal "$valid_args" 'bash -c'; then
|
if echo "$valid_args" | grep -qF 'bash -c'; then
|
||||||
fail "launcher constructed a shell command payload"
|
fail "launcher constructed a shell command payload"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# The pane must start through an absolute clean-environment boundary. Its
|
# The pane must start through an absolute clean-environment boundary. Its
|
||||||
# runtime command remains an argv vector, but no holder/session environment
|
# runtime command remains an argv vector, but no holder/session environment
|
||||||
# control variable can pass through the pane command.
|
# control variable can pass through the pane command.
|
||||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
echo "$valid_args" | grep -qxF '/usr/bin/env' || fail "pane does not use absolute env"
|
||||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
echo "$valid_args" | grep -qxF -- '-i' || fail "pane environment is not cleared"
|
||||||
|
|
||||||
# Git identity is generated authority, not an optional or independently mutable
|
# Git identity is generated authority, not an optional or independently mutable
|
||||||
# local value. Each invalid form must fail before fake tmux receives a call.
|
# local value. Each invalid form must fail before fake tmux receives a call.
|
||||||
@@ -232,7 +142,7 @@ assert_git_identity_rejected() {
|
|||||||
fail "Git identity case $case_name was accepted"
|
fail "Git identity case $case_name was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before Git identity $case_name rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before Git identity $case_name rejection"
|
||||||
contains_literal "$output" "code=$expected_code" || \
|
echo "$output" | grep -qF "code=$expected_code" || \
|
||||||
fail "Git identity $case_name diagnostic omitted code $expected_code"
|
fail "Git identity $case_name diagnostic omitted code $expected_code"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -252,7 +162,7 @@ if output=$(run_start "$HOME_UNSAFE_PARENT" coder-parent 2>&1); then
|
|||||||
fail "generated file under a world-writable parent was accepted"
|
fail "generated file under a world-writable parent was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before unsafe parent rejection"
|
[ ! -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"
|
: > "$TMUX_CALLS"
|
||||||
HOME_SYMLINK_PARENT="$ROOT/symlink-parent"
|
HOME_SYMLINK_PARENT="$ROOT/symlink-parent"
|
||||||
@@ -263,7 +173,7 @@ if output=$(run_start "$HOME_SYMLINK_PARENT" coder-symlink-parent 2>&1); then
|
|||||||
fail "generated file under a symlinked parent was accepted"
|
fail "generated file under a symlinked parent was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before symlinked parent rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before symlinked parent rejection"
|
||||||
contains_literal "$output" 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
echo "$output" | grep -qF 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
||||||
|
|
||||||
# Every managed ancestor is a boundary: MOSAIC_HOME, fleet, and agents. A
|
# Every managed ancestor is a boundary: MOSAIC_HOME, fleet, and agents. A
|
||||||
# symlink or group/world-writable ancestor must fail before environment parsing,
|
# symlink or group/world-writable ancestor must fail before environment parsing,
|
||||||
@@ -301,8 +211,8 @@ assert_managed_ancestor_rejected() {
|
|||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before $hazard $ancestor rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before $hazard $ancestor rejection"
|
||||||
[ ! -e "$home/work" ] || fail "workdir was created 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"
|
echo "$output" | grep -qF "code=unsafe-" || fail "managed ancestor diagnostic missing"
|
||||||
if contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND'; then
|
if echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND'; then
|
||||||
fail "environment parsing ran before $hazard $ancestor rejection"
|
fail "environment parsing ran before $hazard $ancestor rejection"
|
||||||
fi
|
fi
|
||||||
}
|
}
|
||||||
@@ -323,9 +233,9 @@ if output=$(run_start "$HOME_SHADOW" coder1 2>&1); then
|
|||||||
fail "generated-key shadow was accepted"
|
fail "generated-key shadow was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before generated-key shadow rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before generated-key shadow rejection"
|
||||||
contains_literal "$output" 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
echo "$output" | grep -qF 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
||||||
contains_literal "$output" 'sha256=' || fail "shadow diagnostic omitted hash"
|
echo "$output" | grep -qF 'sha256=' || fail "shadow diagnostic omitted hash"
|
||||||
if contains_literal "$output" codex; then
|
if echo "$output" | grep -qF 'codex'; then
|
||||||
fail "shadow diagnostic leaked value"
|
fail "shadow diagnostic leaked value"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@@ -341,9 +251,9 @@ if output=$(run_start "$HOME_COMMAND" coder2 2>&1); then
|
|||||||
fail "arbitrary command override was accepted"
|
fail "arbitrary command override was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before command rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before command rejection"
|
||||||
contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
||||||
contains_literal "$output" 'sha256=' || fail "command diagnostic omitted hash"
|
echo "$output" | grep -qF 'sha256=' || fail "command diagnostic omitted hash"
|
||||||
if contains_literal "$output" "$COMMAND_VALUE"; then
|
if echo "$output" | grep -qF "$COMMAND_VALUE"; then
|
||||||
fail "command diagnostic leaked command value"
|
fail "command diagnostic leaked command value"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@@ -357,7 +267,7 @@ if output=$(run_start "$HOME_PERMS" coder3 2>&1); then
|
|||||||
fail "world-readable local input was accepted"
|
fail "world-readable local input was accepted"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before permissions rejection"
|
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before permissions rejection"
|
||||||
contains_literal "$output" 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
echo "$output" | grep -qF 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
||||||
|
|
||||||
# A unit/holder-like clean bootstrap must yield a pane with trusted HOME and
|
# A unit/holder-like clean bootstrap must yield a pane with trusted HOME and
|
||||||
# computed PATH only. The pane command itself must not carry loader, shell
|
# computed PATH only. The pane command itself must not carry loader, shell
|
||||||
@@ -387,17 +297,19 @@ PATH="$PANE_STALE_PATH" \
|
|||||||
MOSAIC_TEST_EXECUTE_PANE=1 \
|
MOSAIC_TEST_EXECUTE_PANE=1 \
|
||||||
"$START" coder-pane-boundary
|
"$START" coder-pane-boundary
|
||||||
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
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"
|
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"
|
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
|
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 $blocked"
|
||||||
done
|
done
|
||||||
|
|
||||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
after_pane_env=$(printf '%s\n' "$pane_args" | grep -n -m1 -F '/usr/bin/env' | cut -d: -f1)
|
||||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
[ -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' < "$HOME_PANE_BOUNDARY/fleet/pane-environment")
|
pane_environment=$(tr '\0' '\n' < "$HOME_PANE_BOUNDARY/fleet/pane-environment")
|
||||||
# Exercise the repository launcher at $START, not the independently installed
|
# Exercise the repository launcher at $START, not the independently installed
|
||||||
# host copy. Set-compare every declared generated projection entry with the
|
# host copy. Set-compare every declared generated projection entry with the
|
||||||
@@ -411,11 +323,11 @@ if [ -n "$missing_or_changed_generated_environment" ]; then
|
|||||||
missing_or_changed_keys=$(printf '%s\n' "$missing_or_changed_generated_environment" | cut -d= -f1 | paste -sd, -)
|
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"
|
fail "runtime pane omitted or changed generated environment keys: $missing_or_changed_keys"
|
||||||
fi
|
fi
|
||||||
contains_line "$pane_environment" "HOME=$PANE_TRUSTED_HOME" || \
|
echo "$pane_environment" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||||
fail "runtime pane did not receive trusted HOME"
|
fail "runtime pane did not receive trusted HOME"
|
||||||
contains_literal "$pane_environment" "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
echo "$pane_environment" | grep -qF "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
||||||
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
||||||
contains_literal "$pane_environment" "$blocked" && fail "runtime pane received $blocked"
|
echo "$pane_environment" | grep -qF "$blocked" && fail "runtime pane received $blocked"
|
||||||
done
|
done
|
||||||
|
|
||||||
write_interaction_generated() {
|
write_interaction_generated() {
|
||||||
@@ -491,11 +403,7 @@ write_heartbeat_local "$HOME_NATIVE_STALE" "coder-native-stale"
|
|||||||
STALE_HB="$HOME_NATIVE_STALE/run/coder-native-stale.hb"
|
STALE_HB="$HOME_NATIVE_STALE/run/coder-native-stale.hb"
|
||||||
printf 'ts=native\npid=1\nstatus=busy\nmodel=stale-model\n' > "$STALE_HB"
|
printf 'ts=native\npid=1\nstatus=busy\nmodel=stale-model\n' > "$STALE_HB"
|
||||||
touch -t 200001010000.00 "$STALE_HB.native"
|
touch -t 200001010000.00 "$STALE_HB.native"
|
||||||
# Hold the sidecar's observation epoch constant: assertion runtime must not age
|
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
||||||
# a fresh-marker mutant into the stale state that this fixture must distinguish.
|
|
||||||
STALE_OBSERVATION_EPOCH=$(date +%s)
|
|
||||||
MOSAIC_TEST_FIXED_EPOCH="$STALE_OBSERVATION_EPOCH" \
|
|
||||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
|
||||||
wait_for_sidecar_status "$STALE_HB"
|
wait_for_sidecar_status "$STALE_HB"
|
||||||
|
|
||||||
HOME_NATIVE_ABSENT="$ROOT/native-absent"
|
HOME_NATIVE_ABSENT="$ROOT/native-absent"
|
||||||
@@ -516,7 +424,7 @@ if output=$(run_interaction "$HOME_INTERACTION_MALFORMED" interaction-malformed
|
|||||||
fail "interaction wrapper accepted malformed generated data"
|
fail "interaction wrapper accepted malformed generated data"
|
||||||
fi
|
fi
|
||||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before interaction strict-parser rejection"
|
[ ! -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 "$output" | grep -qF 'code=unknown-key' || fail "interaction did not use shared strict parser first"
|
||||||
|
|
||||||
# A syntactically valid but policy-incompatible projection reaches the pinned
|
# A syntactically valid but policy-incompatible projection reaches the pinned
|
||||||
# interaction policy check only after strict parsing and never starts tmux.
|
# interaction policy check only after strict parsing and never starts tmux.
|
||||||
@@ -529,9 +437,9 @@ if output=$(run_interaction "$HOME_INTERACTION_POLICY" interaction-policy 2>&1);
|
|||||||
fail "interaction wrapper accepted a policy-incompatible projection"
|
fail "interaction wrapper accepted a policy-incompatible projection"
|
||||||
fi
|
fi
|
||||||
interaction_policy_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
interaction_policy_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||||
contains_literal "$interaction_policy_args" new-session && \
|
echo "$interaction_policy_args" | grep -qF 'new-session' && \
|
||||||
fail "interaction pinned-policy rejection created a tmux session"
|
fail "interaction pinned-policy rejection created a tmux session"
|
||||||
contains_literal "$output" 'operator interaction service requires runtime pi' || \
|
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
||||||
fail "interaction pinned-policy check did not follow strict parsing"
|
fail "interaction pinned-policy check did not follow strict parsing"
|
||||||
|
|
||||||
# Exact stop derives the socket exclusively from the validated generated
|
# Exact stop derives the socket exclusively from the validated generated
|
||||||
@@ -544,10 +452,10 @@ HOME="$HOME_STOP" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
|||||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||||
MOSAIC_HOME="$HOME_STOP" MOSAIC_TMUX_SOCKET=ambient-socket "$START" --stop coder-stop
|
MOSAIC_HOME="$HOME_STOP" MOSAIC_TMUX_SOCKET=ambient-socket "$START" --stop coder-stop
|
||||||
stop_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
stop_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||||
contains_line "$stop_args" mosaic-test || fail "exact stop did not use the validated generated socket"
|
echo "$stop_args" | grep -qxF 'mosaic-test' || fail "exact stop did not use the validated generated socket"
|
||||||
contains_line "$stop_args" kill-session || fail "exact stop did not request session termination"
|
echo "$stop_args" | grep -qxF 'kill-session' || fail "exact stop did not request session termination"
|
||||||
contains_line "$stop_args" '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
echo "$stop_args" | grep -qxF '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
||||||
if contains_literal "$stop_args" ambient-socket; then
|
if echo "$stop_args" | grep -qF 'ambient-socket'; then
|
||||||
fail "exact stop trusted an ambient socket"
|
fail "exact stop trusted an ambient socket"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
|||||||
@@ -5,10 +5,7 @@
|
|||||||
|
|
||||||
detect_platform() {
|
detect_platform() {
|
||||||
local remote_url
|
local remote_url
|
||||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||||
# 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=$(git remote get-url origin 2>/dev/null) || true
|
|
||||||
|
|
||||||
if [[ -z "$remote_url" ]]; then
|
if [[ -z "$remote_url" ]]; then
|
||||||
echo "error: not a git repository or no origin remote" >&2
|
echo "error: not a git repository or no origin remote" >&2
|
||||||
@@ -42,10 +39,7 @@ detect_platform() {
|
|||||||
|
|
||||||
get_repo_info() {
|
get_repo_info() {
|
||||||
local remote_url
|
local remote_url
|
||||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||||
# 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=$(git remote get-url origin 2>/dev/null) || true
|
|
||||||
|
|
||||||
if [[ -z "$remote_url" ]]; then
|
if [[ -z "$remote_url" ]]; then
|
||||||
echo "error: not a git repository or no origin remote" >&2
|
echo "error: not a git repository or no origin remote" >&2
|
||||||
@@ -246,21 +240,6 @@ PY
|
|||||||
} >&2
|
} >&2
|
||||||
}
|
}
|
||||||
|
|
||||||
# Explain tea's most misleading failure. `user does not exist [uid: 0, name: ]` reads
|
|
||||||
# as a missing account; it almost always means a REVOKED OR STALE TOKEN. `tea login`
|
|
||||||
# keeps its OWN COPY of the token, so rotating the credential store does not update it.
|
|
||||||
# Diagnostic only -- stderr, no control flow, no exit.
|
|
||||||
explain_tea_user_does_not_exist() {
|
|
||||||
cat >&2 <<'MSG'
|
|
||||||
NOTE: `user does not exist [uid: 0, name: ]` from tea usually means a REVOKED OR STALE TOKEN,
|
|
||||||
not a missing account. A `tea login` stores its OWN COPY of the token; rotating the
|
|
||||||
credential store does NOT update it.
|
|
||||||
CHECK: the login's cached copy (`tea login list` -- read the FULL table, never `| head`),
|
|
||||||
then re-register that login against the current token.
|
|
||||||
DO NOT probe capability with a mutating request; a POST is the action, not a check.
|
|
||||||
MSG
|
|
||||||
}
|
|
||||||
|
|
||||||
get_gitea_login_for_host() {
|
get_gitea_login_for_host() {
|
||||||
local host="${1:-}"
|
local host="${1:-}"
|
||||||
local login
|
local login
|
||||||
|
|||||||
@@ -91,32 +91,13 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
|||||||
GITEA_LOGIN_NAME=$(get_gitea_login || true)
|
GITEA_LOGIN_NAME=$(get_gitea_login || true)
|
||||||
if [[ -n "$GITEA_LOGIN_NAME" ]]; then
|
if [[ -n "$GITEA_LOGIN_NAME" ]]; then
|
||||||
if [[ -n "$COMMENT" ]]; then
|
if [[ -n "$COMMENT" ]]; then
|
||||||
# `tea issue comment` is NOT a subcommand -- tea 0.11.x lists only
|
tea issue comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||||
# list/create/edit/reopen/close under `tea issue`. Comments are the
|
|
||||||
# TOP-LEVEL `tea comment`, which takes the same --repo/--login flags.
|
|
||||||
# The old call therefore always failed, was unchecked, and the script
|
|
||||||
# closed the issue anyway, losing the record of WHY.
|
|
||||||
#
|
|
||||||
# Use `tea comment` rather than the API helper so the comment and the
|
|
||||||
# close are made by the SAME principal ($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
|
|
||||||
}
|
|
||||||
fi
|
fi
|
||||||
tea issue close "$ISSUE_NUMBER" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
tea issue close "$ISSUE_NUMBER" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||||
else
|
else
|
||||||
echo "No tea login configured for $(get_remote_host); using authenticated Gitea API fallback." >&2
|
echo "No tea login configured for $(get_remote_host); using authenticated Gitea API fallback." >&2
|
||||||
if [[ -n "$COMMENT" ]]; then
|
if [[ -n "$COMMENT" ]]; then
|
||||||
# Fail closed here too: an unchecked comment lets the issue close without its
|
gitea_issue_comment_api
|
||||||
# audit trail, which is the same defect as the tea path above.
|
|
||||||
gitea_issue_comment_api || {
|
|
||||||
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
|
|
||||||
exit 1
|
|
||||||
}
|
|
||||||
fi
|
fi
|
||||||
gitea_issue_close_api
|
gitea_issue_close_api
|
||||||
fi
|
fi
|
||||||
|
|||||||
@@ -156,7 +156,6 @@ case "$PLATFORM" in
|
|||||||
exit 0
|
exit 0
|
||||||
fi
|
fi
|
||||||
echo "Warning: tea issue create failed, trying Gitea API fallback..." >&2
|
echo "Warning: tea issue create failed, trying Gitea API fallback..." >&2
|
||||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
|
||||||
fi
|
fi
|
||||||
gitea_issue_create_api
|
gitea_issue_create_api
|
||||||
;;
|
;;
|
||||||
|
|||||||
@@ -71,7 +71,6 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
|||||||
exit 0
|
exit 0
|
||||||
fi
|
fi
|
||||||
echo "Warning: tea issue view failed, trying Gitea API fallback..." >&2
|
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
|
fi
|
||||||
gitea_issue_view_api
|
gitea_issue_view_api
|
||||||
else
|
else
|
||||||
|
|||||||
@@ -84,7 +84,7 @@ cp "$TARGET" "$BAK"
|
|||||||
export MOSAIC_TEST_WORK_DIR="$WORK/.work"
|
export MOSAIC_TEST_WORK_DIR="$WORK/.work"
|
||||||
|
|
||||||
# --- where the prose lives: usage() { ... EOF ---------------------------------
|
# --- 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")"
|
PROSE_HI="$(awk -v lo="$PROSE_LO" 'NR > lo && /^EOF$/ { print NR; exit }' "$BAK")"
|
||||||
if [[ -z "$PROSE_LO" || -z "$PROSE_HI" ]]; then
|
if [[ -z "$PROSE_LO" || -z "$PROSE_HI" ]]; then
|
||||||
echo "!! cannot locate the usage() heredoc -- the prose guard would be inert; refusing" >&2
|
echo "!! cannot locate the usage() heredoc -- the prose guard would be inert; refusing" >&2
|
||||||
|
|||||||
@@ -219,7 +219,6 @@ case "$PLATFORM" in
|
|||||||
exit 0
|
exit 0
|
||||||
fi
|
fi
|
||||||
echo "Warning: tea pr create failed, trying Gitea API fallback..." >&2
|
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
|
gitea_pr_create_api
|
||||||
;;
|
;;
|
||||||
*)
|
*)
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
#!/bin/bash
|
#!/bin/bash
|
||||||
# pr-merge.sh - Merge pull requests on Gitea or GitHub
|
# 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]
|
||||||
|
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
|
||||||
@@ -14,8 +14,6 @@ MERGE_METHOD="squash"
|
|||||||
DELETE_BRANCH=false
|
DELETE_BRANCH=false
|
||||||
DRY_RUN=false
|
DRY_RUN=false
|
||||||
EXPECT_HEAD=""
|
EXPECT_HEAD=""
|
||||||
CO_AUTHOR_TRAILERS=false
|
|
||||||
ESCALATE_TO=""
|
|
||||||
|
|
||||||
usage() {
|
usage() {
|
||||||
cat <<EOF
|
cat <<EOF
|
||||||
@@ -29,16 +27,12 @@ Options:
|
|||||||
-d, --delete-branch Delete the head branch after merge
|
-d, --delete-branch Delete the head branch after merge
|
||||||
--dry-run Run metadata/login preflight without merging
|
--dry-run Run metadata/login preflight without merging
|
||||||
--expect-head SHA Refuse unless the PR head matches this full commit SHA
|
--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
|
-h, --help Show this help message
|
||||||
|
|
||||||
Examples:
|
Examples:
|
||||||
$(basename "$0") -n 42 # Merge PR #42
|
$(basename "$0") -n 42 # Merge PR #42
|
||||||
$(basename "$0") -n 42 -m squash # Squash merge
|
$(basename "$0") -n 42 -m squash # Squash merge
|
||||||
$(basename "$0") -n 42 -d # Squash merge and delete branch
|
$(basename "$0") -n 42 -d # Squash merge and delete branch
|
||||||
$(basename "$0") -n 42 --expect-head 0123456789abcdef0123456789abcdef01234567
|
|
||||||
$(basename "$0") -n 42 --co-author-trailers --escalate-to tl-mosaic
|
|
||||||
EOF
|
EOF
|
||||||
exit "${1:-1}"
|
exit "${1:-1}"
|
||||||
}
|
}
|
||||||
@@ -63,25 +57,9 @@ while [[ $# -gt 0 ]]; do
|
|||||||
shift
|
shift
|
||||||
;;
|
;;
|
||||||
--expect-head)
|
--expect-head)
|
||||||
if [[ $# -lt 2 ]]; then
|
|
||||||
echo "Error: --expect-head requires one full commit SHA." >&2
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
EXPECT_HEAD="$2"
|
EXPECT_HEAD="$2"
|
||||||
shift 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="$2"
|
|
||||||
shift 2
|
|
||||||
;;
|
|
||||||
-h|--help)
|
-h|--help)
|
||||||
usage 0
|
usage 0
|
||||||
;;
|
;;
|
||||||
@@ -110,30 +88,17 @@ if [[ -n "$EXPECT_HEAD" && ! "$EXPECT_HEAD" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
|||||||
echo "Error: --expect-head must be a full 40-character hexadecimal commit SHA." >&2
|
echo "Error: --expect-head must be a full 40-character hexadecimal commit SHA." >&2
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
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 "$PR_NUMBER")"
|
PR_METADATA="$("$SCRIPT_DIR/pr-metadata.sh" -n "$PR_NUMBER")"
|
||||||
BASE_BRANCH="$(printf '%s' "$PR_METADATA" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("baseRefName") or "").strip())')"
|
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_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_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())')"
|
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 [[ "$BASE_BRANCH" != "main" ]]; then
|
if [[ "$BASE_BRANCH" != "main" ]]; then
|
||||||
echo "Error: Mosaic policy allows merges only for PRs targeting 'main' (found '$BASE_BRANCH')." >&2
|
echo "Error: Mosaic policy allows merges only for PRs targeting 'main' (found '$BASE_BRANCH')." >&2
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
if [[ -z "$HEAD_BRANCH" || -z "$HEAD_REPO" || ! "$HEAD_SHA" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
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
|
echo "Error: Could not resolve the PR head branch, repository, and full commit SHA for queue inspection." >&2
|
||||||
exit 1
|
exit 1
|
||||||
@@ -157,442 +122,70 @@ PLATFORM=$(detect_platform)
|
|||||||
OWNER=$(get_repo_owner)
|
OWNER=$(get_repo_owner)
|
||||||
REPO=$(get_repo_name)
|
REPO=$(get_repo_name)
|
||||||
|
|
||||||
write_curl_auth_config() {
|
merge_gitea_with_api() {
|
||||||
local mode="$1" credential="$2"
|
local host="$1" api_url token basic_auth body_file raw_code payload
|
||||||
printf '%s' "$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)
|
|
||||||
' "$mode"
|
|
||||||
}
|
|
||||||
|
|
||||||
LAST_GITEA_HTTP_CODE="000"
|
|
||||||
LAST_GITEA_ERROR=""
|
|
||||||
MERGE_TEMP_DIRS=()
|
|
||||||
GITEA_CURL_MAX_BYTES="${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"
|
|
||||||
)
|
|
||||||
|
|
||||||
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))
|
|
||||||
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/${PR_NUMBER}/merge"
|
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
|
||||||
work_root="${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
||||||
mkdir -p "$work_root"
|
body_file=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-api-response.XXXXXX")
|
||||||
attempt_dir=$(mktemp -d "$work_root/pr-merge-attempt.XXXXXX")
|
payload=$(python3 - "$HEAD_SHA" "$DELETE_BRANCH" <<'PY'
|
||||||
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" > "$payload_file" <<'PY'
|
|
||||||
import json
|
import json
|
||||||
import sys
|
import sys
|
||||||
|
|
||||||
with open(sys.argv[1], encoding="utf-8") as handle:
|
head_sha, delete_branch = sys.argv[1:]
|
||||||
fields = json.load(handle)
|
|
||||||
head_sha, delete_branch = sys.argv[2:]
|
|
||||||
payload = {"Do": "squash", "head_commit_id": head_sha}
|
payload = {"Do": "squash", "head_commit_id": head_sha}
|
||||||
if delete_branch == "true":
|
if delete_branch == "true":
|
||||||
payload["delete_branch_after_merge"] = True
|
payload["delete_branch_after_merge"] = True
|
||||||
payload.update(fields)
|
|
||||||
allowed = {"Do", "head_commit_id", "delete_branch_after_merge", "MergeTitleField", "MergeMessageField"}
|
|
||||||
if payload.get("Do") != "squash" or set(payload) - allowed:
|
|
||||||
raise SystemExit(1)
|
|
||||||
print(json.dumps(payload, separators=(",", ":")))
|
print(json.dumps(payload, separators=(",", ":")))
|
||||||
PY
|
PY
|
||||||
then
|
)
|
||||||
rm -f "$body_file" "$fields_file" "$payload_file"
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
rm -f "$fields_file"
|
|
||||||
|
|
||||||
if ! auth_config=$(write_curl_auth_config "$auth_mode" "$credential"); then
|
token=$(get_gitea_token "$host" || true)
|
||||||
echo "Error: Could not construct Gitea authentication config; refusing request." >&2
|
if [[ -n "$token" ]]; then
|
||||||
rm -f "$body_file" "$payload_file"
|
raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" \
|
||||||
return 1
|
-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 "$body_file"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
fi
|
fi
|
||||||
raw_code=$(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"
|
|
||||||
[[ "$raw_code" =~ ^2 ]]
|
|
||||||
}
|
|
||||||
|
|
||||||
merge_gitea_with_api() {
|
basic_auth=$(get_gitea_basic_auth "$host" || true)
|
||||||
local host="$1" token attempt_rc
|
if [[ -n "$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 "$body_file"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
if ! token=$(get_gitea_token "$host"); then
|
python3 - "${raw_code:-000}" "$body_file" <<'PY' >&2
|
||||||
echo "Error: Could not resolve the required Gitea token; refusing merge without changing principals." >&2
|
import json
|
||||||
return 1
|
import sys
|
||||||
fi
|
code, path = sys.argv[1], sys.argv[2]
|
||||||
if [[ -z "$token" ]]; then
|
try:
|
||||||
echo "Error: Required Gitea token resolved empty; refusing merge without changing principals." >&2
|
with open(path, encoding="utf-8", errors="replace") as handle:
|
||||||
return 1
|
raw = handle.read(500)
|
||||||
fi
|
data = json.loads(raw) if raw else {}
|
||||||
if merge_gitea_api_attempt "$host" token "$token"; then
|
message = data.get("message") or data.get("error") or raw or "empty response"
|
||||||
return 0
|
except Exception:
|
||||||
else
|
try:
|
||||||
attempt_rc=$?
|
message = open(path, encoding="utf-8", errors="replace").read(500) or "empty response"
|
||||||
fi
|
except Exception:
|
||||||
if [[ "$attempt_rc" -eq 75 ]]; then
|
message = "unreadable response"
|
||||||
return 75
|
print(f"Error: Gitea API merge failed with HTTP {code}: {message}")
|
||||||
fi
|
PY
|
||||||
if [[ "$LAST_GITEA_HTTP_CODE" != "401" ]]; then
|
rm -f "$body_file"
|
||||||
echo "Error: Gitea API merge failed with the identity-bound token (HTTP ${LAST_GITEA_HTTP_CODE:-000}).${LAST_GITEA_ERROR:+ Provider response: $LAST_GITEA_ERROR}" >&2
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
echo "Error: Gitea API rejected the identity-bound token with HTTP 401; refusing cross-principal credential fallback." >&2
|
|
||||||
return 1
|
return 1
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -602,10 +195,11 @@ if [[ "$DRY_RUN" == true ]]; then
|
|||||||
echo "Error: Cannot determine host from origin remote URL" >&2
|
echo "Error: Cannot determine host from origin remote URL" >&2
|
||||||
exit 1
|
exit 1
|
||||||
}
|
}
|
||||||
if [[ "$CO_AUTHOR_TRAILERS" == true ]]; then
|
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
|
||||||
echo "Dry run: would verify PR commit authors and merge PR #$PR_NUMBER on $HOST with authenticated Gitea API message fields (base=$BASE_BRANCH, method=squash)."
|
if [[ -n "$TEA_LOGIN" ]]; then
|
||||||
|
echo "Dry run: would merge PR #$PR_NUMBER on $HOST with tea login '$TEA_LOGIN' (base=$BASE_BRANCH, method=squash)."
|
||||||
else
|
else
|
||||||
echo "Dry run: would merge PR #$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
|
fi
|
||||||
else
|
else
|
||||||
echo "Dry run: would merge PR #$PR_NUMBER on $PLATFORM (base=$BASE_BRANCH, method=squash)."
|
echo "Dry run: would merge PR #$PR_NUMBER on $PLATFORM (base=$BASE_BRANCH, method=squash)."
|
||||||
@@ -615,10 +209,6 @@ fi
|
|||||||
|
|
||||||
case "$PLATFORM" in
|
case "$PLATFORM" in
|
||||||
github)
|
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 --match-head-commit "$HEAD_SHA")
|
||||||
[[ "$DELETE_BRANCH" == true ]] && cmd+=(--delete-branch)
|
[[ "$DELETE_BRANCH" == true ]] && cmd+=(--delete-branch)
|
||||||
"${cmd[@]}"
|
"${cmd[@]}"
|
||||||
@@ -629,7 +219,7 @@ case "$PLATFORM" in
|
|||||||
exit 1
|
exit 1
|
||||||
}
|
}
|
||||||
# Gitea's API head_commit_id is an atomic compare-and-merge precondition.
|
# 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.
|
# tea cannot express it, so exact-head merges use the authenticated API path.
|
||||||
merge_gitea_with_api "$HOST"
|
merge_gitea_with_api "$HOST"
|
||||||
;;
|
;;
|
||||||
*)
|
*)
|
||||||
|
|||||||
@@ -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"
|
|
||||||
@@ -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' "$CALLS" || fail "API path: issue not closed when no comment was requested"
|
|
||||||
|
|
||||||
echo "issue-close.sh fail-closed + single-principal regression passed"
|
|
||||||
@@ -280,10 +280,7 @@ print("201")
|
|||||||
print(json.dumps(record))
|
print(json.dumps(record))
|
||||||
PY
|
PY
|
||||||
)
|
)
|
||||||
response_status="${result%%$'\n'*}"
|
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||||
response_body=""
|
|
||||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
|
||||||
write_response "$response_status" "$response_body"
|
|
||||||
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
|
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
|
||||||
result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
|
result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
|
||||||
import json
|
import json
|
||||||
@@ -302,10 +299,7 @@ else:
|
|||||||
print(json.dumps(match))
|
print(json.dumps(match))
|
||||||
PY
|
PY
|
||||||
)
|
)
|
||||||
response_status="${result%%$'\n'*}"
|
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||||
response_body=""
|
|
||||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
|
||||||
write_response "$response_status" "$response_body"
|
|
||||||
else
|
else
|
||||||
echo "Unexpected curl request: $method $url" >&2
|
echo "Unexpected curl request: $method $url" >&2
|
||||||
exit 97
|
exit 97
|
||||||
|
|||||||
@@ -69,7 +69,7 @@ section_nums() { # $1 = output $2 = header-prefix
|
|||||||
}
|
}
|
||||||
|
|
||||||
fail() { echo "FAIL: $1" >&2; exit 1; }
|
fail() { echo "FAIL: $1" >&2; exit 1; }
|
||||||
contains() { grep -qx "$2" <<<"$1"; }
|
contains() { printf '%s\n' "$1" | grep -qx "$2"; }
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
# ---------------------------------------------------------------------------
|
||||||
# Fixed (current) script behavior
|
# Fixed (current) script behavior
|
||||||
|
|||||||
@@ -51,23 +51,22 @@ for arg in "$@"; do
|
|||||||
prev=""
|
prev=""
|
||||||
continue
|
continue
|
||||||
fi
|
fi
|
||||||
if [[ "$prev" == "data" ]]; then
|
if [[ "$prev" == "-d" ]]; then
|
||||||
post_data="$arg"
|
post_data="$arg"
|
||||||
[[ "$post_data" == @* ]] && post_data=$(<"${post_data#@}")
|
|
||||||
prev=""
|
prev=""
|
||||||
continue
|
continue
|
||||||
fi
|
fi
|
||||||
if [[ "$prev" == "config" ]]; then
|
if [[ "$arg" == "-o" ]]; then
|
||||||
[[ "$arg" == "-" ]] && cat >/dev/null
|
prev="-o"
|
||||||
prev=""
|
|
||||||
continue
|
continue
|
||||||
fi
|
fi
|
||||||
case "$arg" in
|
if [[ "$arg" == "-d" ]]; then
|
||||||
-o) prev="-o" ;;
|
prev="-d"
|
||||||
-d|--data|--data-binary) prev="data" ;;
|
continue
|
||||||
-K|--config) prev="config" ;;
|
fi
|
||||||
-w) write_code=true ;;
|
if [[ "$arg" == "-w" ]]; then
|
||||||
esac
|
write_code=true
|
||||||
|
fi
|
||||||
done
|
done
|
||||||
emit_response() {
|
emit_response() {
|
||||||
local body="$1"
|
local body="$1"
|
||||||
|
|||||||
@@ -36,30 +36,13 @@ cat > "$WORK_DIR/gitea/curl" <<'SH'
|
|||||||
#!/usr/bin/env bash
|
#!/usr/bin/env bash
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
payload=""
|
payload=""
|
||||||
out_file=""
|
for ((i=1; i<=$#; i++)); do
|
||||||
while [[ $# -gt 0 ]]; do
|
if [[ "${!i}" == "-d" ]]; then
|
||||||
case "$1" in
|
j=$((i + 1))
|
||||||
-d|--data|--data-binary)
|
payload="${!j}"
|
||||||
payload="$2"
|
fi
|
||||||
[[ "$payload" == @* ]] && payload=$(<"${payload#@}")
|
|
||||||
shift 2
|
|
||||||
;;
|
|
||||||
-o)
|
|
||||||
out_file="$2"
|
|
||||||
shift 2
|
|
||||||
;;
|
|
||||||
-K|--config)
|
|
||||||
[[ "$2" == "-" ]] && cat >/dev/null
|
|
||||||
shift 2
|
|
||||||
;;
|
|
||||||
-w|-X|-H)
|
|
||||||
shift 2
|
|
||||||
;;
|
|
||||||
*) shift ;;
|
|
||||||
esac
|
|
||||||
done
|
done
|
||||||
printf '%s' "$payload" > "${MOSAIC_MERGE_PAYLOAD_LOG:?}"
|
printf '%s' "$payload" > "${MOSAIC_MERGE_PAYLOAD_LOG:?}"
|
||||||
[[ -n "$out_file" ]] && printf '{}' > "$out_file"
|
|
||||||
printf '200'
|
printf '200'
|
||||||
SH
|
SH
|
||||||
chmod +x "$WORK_DIR/gitea/curl"
|
chmod +x "$WORK_DIR/gitea/curl"
|
||||||
|
|||||||
@@ -1,541 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# Regression harness for the optional, identity-checked Gitea squash message.
|
|
||||||
|
|
||||||
set -u
|
|
||||||
|
|
||||||
SCRIPT_DIR="$(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)"
|
|
||||||
@@ -225,10 +225,7 @@ write_response() {
|
|||||||
emit() {
|
emit() {
|
||||||
# Split a two-line "status\n<json body>" python result into the response.
|
# Split a two-line "status\n<json body>" python result into the response.
|
||||||
local result="$1"
|
local result="$1"
|
||||||
response_status="${result%%$'\n'*}"
|
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||||
response_body=""
|
|
||||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
|
||||||
write_response "$response_status" "$response_body"
|
|
||||||
}
|
}
|
||||||
|
|
||||||
mode="${PR_REVIEW_TEST_MODE:-}"
|
mode="${PR_REVIEW_TEST_MODE:-}"
|
||||||
|
|||||||
@@ -222,8 +222,8 @@ grep -q 'Unknown action: bogus-action' "$OUTPUT_FILE"
|
|||||||
|
|
||||||
# --- Case 2: -h/--help documents both overrides.
|
# --- Case 2: -h/--help documents both overrides.
|
||||||
HELP_TEXT="$("$SCRIPT_DIR/pr-review.sh" -h)"
|
HELP_TEXT="$("$SCRIPT_DIR/pr-review.sh" -h)"
|
||||||
grep -q -- '-r, --repo' <<<"$HELP_TEXT"
|
echo "$HELP_TEXT" | grep -q -- '-r, --repo'
|
||||||
grep -q -- '-H, --host' <<<"$HELP_TEXT"
|
echo "$HELP_TEXT" | grep -q -- '-H, --host'
|
||||||
|
|
||||||
# --- Case 3 (comment): a TRUE no-git-origin dir + -r/-H must not silently die
|
# --- 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.
|
# and must not fail with "not a git repository or no origin remote" either.
|
||||||
|
|||||||
@@ -91,12 +91,10 @@ fi
|
|||||||
|
|
||||||
if [[ -n "$dirty_files" ]]; then
|
if [[ -n "$dirty_files" ]]; then
|
||||||
echo " Modified files:"
|
echo " Modified files:"
|
||||||
mapfile -t dirty_lines <<<"$dirty_files"
|
echo "$dirty_files" | head -20 | while IFS= read -r line; do
|
||||||
file_count="${#dirty_lines[@]}"
|
echo " $line"
|
||||||
display_count=$((file_count < 20 ? file_count : 20))
|
|
||||||
for ((i = 0; i < display_count; i++)); do
|
|
||||||
echo " ${dirty_lines[$i]}"
|
|
||||||
done
|
done
|
||||||
|
file_count="$(echo "$dirty_files" | wc -l)"
|
||||||
if (( file_count > 20 )); then
|
if (( file_count > 20 )); then
|
||||||
echo " ... and $(( file_count - 20 )) more"
|
echo " ... and $(( file_count - 20 )) more"
|
||||||
fi
|
fi
|
||||||
|
|||||||
@@ -64,12 +64,12 @@ if jq -e '.next_task == "T-001"' "$capsule_file" >/dev/null 2>&1; then pass_case
|
|||||||
if grep -Fq 'Target runtime:** codex' <<< "$codex_continue_output"; then pass_case "continue prompt contains target runtime codex"; else fail_case "continue prompt contains target runtime codex"; fi
|
if grep -Fq 'Target runtime:** codex' <<< "$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 "$tmp_project" --print)"
|
codex_run_prompt="$(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' <<< "$codex_run_prompt"; then pass_case "codex run prompt includes no-questions hard gate"; else fail_case "codex run prompt includes no-questions hard gate"; fi
|
if grep -Fq 'Do NOT ask clarifying questions before your first tool actions' <<< "$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"' <<< "$codex_run_prompt"; then pass_case "codex run prompt embeds capsule json"; else fail_case "codex run prompt embeds capsule json"; fi
|
if grep -Fq '"next_task": "T-001"' <<< "$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 "$tmp_project" --print)"
|
claude_run_prompt="$(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 ""
|
||||||
echo "Smoke test summary: pass=$PASS fail=$FAIL"
|
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
|
make_board "$L" 6 1 400
|
||||||
before_l=$(cat "$L"); before_g=$(cat "$G")
|
before_l=$(cat "$L"); before_g=$(cat "$G")
|
||||||
out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 2000 --dry-run 2>&1) || note "dry-run exited nonzero: $out"
|
out=$(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"
|
echo "$out" | grep -qi "dry run" || note "dry-run did not announce itself"
|
||||||
grep -q "would roll" <<<"$out" || note "dry-run did not report a plan"
|
echo "$out" | grep -q "would roll" || note "dry-run did not report a plan"
|
||||||
[[ "$(cat "$L")" == "$before_l" ]] || note "dry-run modified LIVE"
|
[[ "$(cat "$L")" == "$before_l" ]] || note "dry-run modified LIVE"
|
||||||
[[ "$(cat "$G")" == "$before_g" ]] || note "dry-run modified LEDGER"
|
[[ "$(cat "$G")" == "$before_g" ]] || note "dry-run modified LEDGER"
|
||||||
|
|
||||||
|
|||||||
@@ -66,7 +66,7 @@ present=0
|
|||||||
|
|
||||||
for entry in "${PRDY_REQUIRED_SECTIONS[@]}"; do
|
for entry in "${PRDY_REQUIRED_SECTIONS[@]}"; do
|
||||||
pattern="${entry#*|}"
|
pattern="${entry#*|}"
|
||||||
if grep -qiE "$pattern" <<<"$PRD_CONTENT"; then
|
if echo "$PRD_CONTENT" | grep -qiE "$pattern"; then
|
||||||
present=$((present + 1))
|
present=$((present + 1))
|
||||||
fi
|
fi
|
||||||
done
|
done
|
||||||
|
|||||||
@@ -169,13 +169,13 @@ main() {
|
|||||||
# classify_surface PATH → surface name (highest-risk match wins, mirrors TS)
|
# classify_surface PATH → surface name (highest-risk match wins, mirrors TS)
|
||||||
classify_surface() {
|
classify_surface() {
|
||||||
local p="$1"
|
local p="$1"
|
||||||
if grep -qiE 'auth|login|session|token|permission|rbac|credential|secret' <<<"$p"; then echo auth; return; fi
|
if printf '%s' "$p" | grep -qiE 'auth|login|session|token|permission|rbac|credential|secret'; then echo auth; return; fi
|
||||||
if grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed' <<<"$p"; then echo data; return; fi
|
if printf '%s' "$p" | grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed'; then echo data; return; fi
|
||||||
if grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform' <<<"$p"; then echo infra; return; fi
|
if printf '%s' "$p" | grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform'; then echo infra; return; fi
|
||||||
if grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite' <<<"$p"; then echo build; return; fi
|
if printf '%s' "$p" | grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite'; then echo build; return; fi
|
||||||
if grep -qE '\.tsx|\.css|components/|apps/web/' <<<"$p"; then echo ui; return; fi
|
if printf '%s' "$p" | grep -qE '\.tsx|\.css|components/|apps/web/'; then echo ui; return; fi
|
||||||
if grep -qE '\.spec\.|\.test\.|__tests__/' <<<"$p"; then echo test; return; fi
|
if printf '%s' "$p" | grep -qE '\.spec\.|\.test\.|__tests__/'; then echo test; return; fi
|
||||||
if grep -qE '\.md$|docs/' <<<"$p"; then echo docs; return; fi
|
if printf '%s' "$p" | grep -qE '\.md$|docs/'; then echo docs; return; fi
|
||||||
echo none
|
echo none
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -13,12 +13,7 @@ JSON_INPUT=$(cat)
|
|||||||
if command -v jq &>/dev/null; then
|
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 "")
|
FILE_PATH=$(echo "$JSON_INPUT" | jq -r '.tool_input.file_path // .tool_response.filePath // .file_path // empty' 2>/dev/null || echo "")
|
||||||
else
|
else
|
||||||
file_path_pattern='"file_path"[[:space:]]*:[[:space:]]*"([^"]*)"'
|
FILE_PATH=$(echo "$JSON_INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"\([^"]*\)"$/\1/' | head -1)
|
||||||
if [[ "$JSON_INPUT" =~ $file_path_pattern ]]; then
|
|
||||||
FILE_PATH="${BASH_REMATCH[1]}"
|
|
||||||
else
|
|
||||||
FILE_PATH=""
|
|
||||||
fi
|
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Only check TypeScript files
|
# Only check TypeScript files
|
||||||
@@ -58,7 +53,7 @@ OUTPUT=$(npx tsc --noEmit --pretty --maxNodeModuleJsDepth 0 2>&1) || STATUS=$?
|
|||||||
if [ "${STATUS:-0}" -ne 0 ]; then
|
if [ "${STATUS:-0}" -ne 0 ]; then
|
||||||
# Filter output to only show errors related to the edited file (if possible)
|
# Filter output to only show errors related to the edited file (if possible)
|
||||||
BASENAME=$(basename "$FILE_PATH")
|
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 "TypeScript type errors detected after editing $FILE_PATH:"
|
||||||
echo "$RELEVANT"
|
echo "$RELEVANT"
|
||||||
|
|||||||
@@ -26,9 +26,6 @@ chk "F1 fresh: CONSTITUTION/AGENTS/STANDARDS/TOOLS seeded" \
|
|||||||
"[ -f '$T1/CONSTITUTION.md' ] && [ -f '$T1/AGENTS.md' ] && [ -f '$T1/STANDARDS.md' ] && [ -f '$T1/TOOLS.md' ]"
|
"[ -f '$T1/CONSTITUTION.md' ] && [ -f '$T1/AGENTS.md' ] && [ -f '$T1/STANDARDS.md' ] && [ -f '$T1/TOOLS.md' ]"
|
||||||
chk "F1 fresh: AGENTS == shipped default" "cmp -s '$T1/AGENTS.md' '$DEFA/AGENTS.md'"
|
chk "F1 fresh: AGENTS == shipped default" "cmp -s '$T1/AGENTS.md' '$DEFA/AGENTS.md'"
|
||||||
chk "F1 fresh: framework-version stamped 3" "[ \"\$(cat '$T1/.framework-version' 2>/dev/null)\" = 3 ]"
|
chk "F1 fresh: framework-version stamped 3" "[ \"\$(cat '$T1/.framework-version' 2>/dev/null)\" = 3 ]"
|
||||||
chk "F1 fresh: Pi goal extension deploys under Mosaic runtime" \
|
|
||||||
"cmp -s '$T1/runtime/pi/goal-extension.ts' '$FW/runtime/pi/goal-extension.ts'"
|
|
||||||
chk "F1 fresh: installer creates no nested main Pi config" "[ ! -e '$T1/.pi' ]"
|
|
||||||
|
|
||||||
# F2 — legacy install with a user-edited AGENTS.md (the sanctioned pre-constitution customization)
|
# F2 — legacy install with a user-edited AGENTS.md (the sanctioned pre-constitution customization)
|
||||||
T2=$(mktemp -d); mkdir -p "$T2/credentials"
|
T2=$(mktemp -d); mkdir -p "$T2/credentials"
|
||||||
@@ -92,8 +89,6 @@ chk "F6 reseed: per-agent env bytes survive" "cmp -s '$T6/fleet/agents/coder0.en
|
|||||||
chk "F6 reseed: heartbeat bytes survive" "cmp -s '$T6/fleet/run/coder0.hb' '$E6/run.expected'"
|
chk "F6 reseed: heartbeat bytes survive" "cmp -s '$T6/fleet/run/coder0.hb' '$E6/run.expected'"
|
||||||
chk "F6 reseed: framework examples are refreshed" "grep -q orchestrator '$T6/fleet/examples/general.yaml'"
|
chk "F6 reseed: framework examples are refreshed" "grep -q orchestrator '$T6/fleet/examples/general.yaml'"
|
||||||
chk "F6 reseed: framework roster schema is refreshed" "cmp -s '$T6/fleet/roster.schema.json' '$FW/fleet/roster.schema.json'"
|
chk "F6 reseed: framework roster schema is refreshed" "cmp -s '$T6/fleet/roster.schema.json' '$FW/fleet/roster.schema.json'"
|
||||||
chk "F6 reseed: Pi goal extension is refreshed from framework source" \
|
|
||||||
"cmp -s '$T6/runtime/pi/goal-extension.ts' '$FW/runtime/pi/goal-extension.ts'"
|
|
||||||
|
|
||||||
rm -rf "$T1" "$T2" "$T3" "$T4" "$T5" "$T6" "$E6"
|
rm -rf "$T1" "$T2" "$T3" "$T4" "$T5" "$T6" "$E6"
|
||||||
echo
|
echo
|
||||||
|
|||||||
@@ -176,12 +176,8 @@ run_snap() {
|
|||||||
|
|
||||||
# Resolve the single pre-update-* snapshot dir under a state dir (newest if many).
|
# Resolve the single pre-update-* snapshot dir under a state dir (newest if many).
|
||||||
snap_dir() {
|
snap_dir() {
|
||||||
local -a snapshots=()
|
find "$1/mosaic/backups" -maxdepth 1 -type d -name 'pre-update-*' 2>/dev/null \
|
||||||
mapfile -t snapshots < <(
|
| LC_ALL=C sort -r | head -1
|
||||||
find "$1/mosaic/backups" -maxdepth 1 -type d -name 'pre-update-*' 2>/dev/null \
|
|
||||||
| LC_ALL=C sort -r
|
|
||||||
)
|
|
||||||
printf '%s\n' "${snapshots[0]:-}"
|
|
||||||
}
|
}
|
||||||
|
|
||||||
echo "── Part 1/2/3: durable snapshot scope, perms, no-leak ──────────────────"
|
echo "── Part 1/2/3: durable snapshot scope, perms, no-leak ──────────────────"
|
||||||
|
|||||||
@@ -336,7 +336,7 @@ chk "[reset-fail] the manual-recovery pointer is emitted (not a silent set -e ex
|
|||||||
"grep -q 'Snapshot restore could not reset' '$OUTG'"
|
"grep -q 'Snapshot restore could not reset' '$OUTG'"
|
||||||
chk "[reset-fail] the recovery message points at a preserved snapshot dir" \
|
chk "[reset-fail] the recovery message points at a preserved snapshot dir" \
|
||||||
"grep -q 'preserved at: .*mosaic-snapshot' '$OUTG'"
|
"grep -q 'preserved at: .*mosaic-snapshot' '$OUTG'"
|
||||||
SNAP_E="$(grep -m1 -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTG")"
|
SNAP_E="$(grep -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTG" | head -1)"
|
||||||
chk "[reset-fail] the named snapshot directory actually survives for recovery" \
|
chk "[reset-fail] the named snapshot directory actually survives for recovery" \
|
||||||
"[ -n '$SNAP_E' ] && [ -d '$SNAP_E' ]"
|
"[ -n '$SNAP_E' ] && [ -d '$SNAP_E' ]"
|
||||||
chk "[reset-fail] operator secret value never appears in installer output" \
|
chk "[reset-fail] operator secret value never appears in installer output" \
|
||||||
@@ -353,8 +353,7 @@ chk "[control] without the D2 recovery line the operator gets no snapshot pointe
|
|||||||
"! grep -q 'Snapshot restore could not reset' '$OUTH'"
|
"! grep -q 'Snapshot restore could not reset' '$OUTH'"
|
||||||
[ -n "${SNAP_E:-}" ] && rm -rf "$SNAP_E"
|
[ -n "${SNAP_E:-}" ] && rm -rf "$SNAP_E"
|
||||||
# Reap any snapshot the reset-fail runs left in /tmp (reset failed → never cleaned).
|
# Reap any snapshot the reset-fail runs left in /tmp (reset failed → never cleaned).
|
||||||
orphan_snapshot="$(grep -m1 -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTH" 2>/dev/null || true)"
|
grep -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTH" 2>/dev/null | head -1 | while read -r s; do rm -rf "$s"; done
|
||||||
[ -n "$orphan_snapshot" ] && rm -rf "$orphan_snapshot"
|
|
||||||
|
|
||||||
# Cleanup (generated installer controls are also removed by the EXIT trap).
|
# Cleanup (generated installer controls are also removed by the EXIT trap).
|
||||||
for d in "$HA" "$REFA" "$HB" "$REFB" "$HC" "$HD" "$HE" "$REFE" "$HF" "$REFF" "$HG" "$HH"; do rm -rf "$d"; done
|
for d in "$HA" "$REFA" "$HB" "$REFB" "$HC" "$HD" "$HE" "$REFE" "$HF" "$REFF" "$HG" "$HH"; do rm -rf "$d"; done
|
||||||
|
|||||||
@@ -110,7 +110,7 @@ for attempt in $(seq 1 $((RETRIES + 1))); do
|
|||||||
sleep 1.2
|
sleep 1.2
|
||||||
pane=$("${tmux_cmd[@]}" capture-pane -t "$EFFECTIVE_TARGET" -p 2>/dev/null)
|
pane=$("${tmux_cmd[@]}" capture-pane -t "$EFFECTIVE_TARGET" -p 2>/dev/null)
|
||||||
|
|
||||||
if grep -qF "$QUEUED_RE" <<<"$pane"; then
|
if printf '%s' "$pane" | grep -qF "$QUEUED_RE"; then
|
||||||
status="queued"; break
|
status="queued"; break
|
||||||
fi
|
fi
|
||||||
# Locate the REPL input box (prompt glyph). If we cannot see it, we have NO
|
# Locate the REPL input box (prompt glyph). If we cannot see it, we have NO
|
||||||
@@ -121,7 +121,7 @@ for attempt in $(seq 1 $((RETRIES + 1))); do
|
|||||||
fi
|
fi
|
||||||
# Input box located AND still carrying our tail => unsubmitted draft. Flush + retry.
|
# Input box located AND still carrying our tail => unsubmitted draft. Flush + retry.
|
||||||
# (Submitted messages scroll up into history; a draft stays on the ❯ line.)
|
# (Submitted messages scroll up into history; a draft stays on the ❯ line.)
|
||||||
if [ -n "$snippet" ] && grep -qF "$snippet" <<<"$promptline"; then
|
if [ -n "$snippet" ] && printf '%s' "$promptline" | grep -qF "$snippet"; then
|
||||||
status="draft"; continue
|
status="draft"; continue
|
||||||
fi
|
fi
|
||||||
# Input box located AND clear of our tail => positively submitted. This is the
|
# Input box located AND clear of our tail => positively submitted. This is the
|
||||||
|
|||||||
@@ -34,20 +34,16 @@ tmux new-session -d -s "$DEFAULT_TARGET" -c "$TMPDIR" 'PS1="❯ " exec bash --no
|
|||||||
|
|
||||||
"$SEND_MESSAGE" -L "$SOCKET" -t "=$TARGET" -m "named socket hello" >/tmp/send-message-named.out
|
"$SEND_MESSAGE" -L "$SOCKET" -t "=$TARGET" -m "named socket hello" >/tmp/send-message-named.out
|
||||||
sleep 0.2
|
sleep 0.2
|
||||||
named_pane="$(capture_named)" || fail "could not capture named socket pane"
|
capture_named | grep -qF "named socket hello" || fail "send-message.sh did not deliver to named socket"
|
||||||
grep -qF "named socket hello" <<<"$named_pane" || fail "send-message.sh did not deliver to named socket"
|
if capture_default | grep -qF "named socket hello"; then
|
||||||
default_pane="$(capture_default)" || fail "could not capture default socket pane"
|
|
||||||
if grep -qF "named socket hello" <<<"$default_pane"; then
|
|
||||||
fail "send-message.sh leaked named-socket message to default tmux server"
|
fail "send-message.sh leaked named-socket message to default tmux server"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
"$AGENT_SEND" -L "$SOCKET" -S "tester:source" -s "=$TARGET" -m "agent socket hello" >/tmp/agent-send-named.out
|
"$AGENT_SEND" -L "$SOCKET" -S "tester:source" -s "=$TARGET" -m "agent socket hello" >/tmp/agent-send-named.out
|
||||||
sleep 0.2
|
sleep 0.2
|
||||||
named_pane="$(capture_named)" || fail "could not capture named socket pane"
|
capture_named | grep -qF "[tester:source ->" || fail "agent-send.sh did not include preamble"
|
||||||
grep -qF "[tester:source ->" <<<"$named_pane" || fail "agent-send.sh did not include preamble"
|
capture_named | grep -qF "agent socket hello" || fail "agent-send.sh did not deliver to named socket"
|
||||||
grep -qF "agent socket hello" <<<"$named_pane" || fail "agent-send.sh did not deliver to named socket"
|
if capture_default | grep -qF "agent socket hello"; then
|
||||||
default_pane="$(capture_default)" || fail "could not capture default socket pane"
|
|
||||||
if grep -qF "agent socket hello" <<<"$default_pane"; then
|
|
||||||
fail "agent-send.sh leaked named-socket message to default tmux server"
|
fail "agent-send.sh leaked named-socket message to default tmux server"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@@ -69,11 +65,11 @@ done
|
|||||||
sleep 0.2
|
sleep 0.2
|
||||||
for i in $(seq 1 "$CONC_N"); do
|
for i in $(seq 1 "$CONC_N"); do
|
||||||
pane=$(tmux -L "$SOCKET" capture-pane -t "=conc-$i:0.0" -p)
|
pane=$(tmux -L "$SOCKET" capture-pane -t "=conc-$i:0.0" -p)
|
||||||
grep -qF "CONCPAYLOAD-${i}-END" <<<"$pane" \
|
printf '%s' "$pane" | grep -qF "CONCPAYLOAD-${i}-END" \
|
||||||
|| fail "concurrent send dropped payload for pane conc-$i"
|
|| fail "concurrent send dropped payload for pane conc-$i"
|
||||||
for j in $(seq 1 "$CONC_N"); do
|
for j in $(seq 1 "$CONC_N"); do
|
||||||
[ "$j" = "$i" ] && continue
|
[ "$j" = "$i" ] && continue
|
||||||
if grep -qF "CONCPAYLOAD-${j}-END" <<<"$pane"; then
|
if printf '%s' "$pane" | grep -qF "CONCPAYLOAD-${j}-END"; then
|
||||||
fail "concurrent send cross-delivered payload $j to pane conc-$i"
|
fail "concurrent send cross-delivered payload $j to pane conc-$i"
|
||||||
fi
|
fi
|
||||||
done
|
done
|
||||||
|
|||||||
@@ -31,7 +31,7 @@ tmux -L "$SOCKET" new-session -d -s repl -c "$TMP" \
|
|||||||
'PS1="❯ " exec bash --noprofile --norc -i'
|
'PS1="❯ " exec bash --noprofile --norc -i'
|
||||||
sleep 0.3
|
sleep 0.3
|
||||||
out=$("$SEND" -L "$SOCKET" -t "=repl" -m "verdict fixture one delivered ok" 2>"$TMP/e1"); rc=$?
|
out=$("$SEND" -L "$SOCKET" -t "=repl" -m "verdict fixture one delivered ok" 2>"$TMP/e1"); rc=$?
|
||||||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
if [ "$rc" -eq 0 ] && printf '%s' "$out" | grep -qF "✓ delivered"; then
|
||||||
ok "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered"
|
ok "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered"
|
||||||
else
|
else
|
||||||
no "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e1")]"
|
no "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e1")]"
|
||||||
|
|||||||
@@ -123,7 +123,7 @@ _manifest_val() {
|
|||||||
# _manifest_val KEY — echo VALUE for KEY=VALUE in the manifest (blank if none).
|
# _manifest_val KEY — echo VALUE for KEY=VALUE in the manifest (blank if none).
|
||||||
local key="$1"
|
local key="$1"
|
||||||
[ -f "$MANIFEST" ] || return 0
|
[ -f "$MANIFEST" ] || return 0
|
||||||
awk -v key="$key" 'index($0, key "=") == 1 { sub(/^[^=]*=/, ""); gsub(/[[:space:]]/, ""); print; exit }' "$MANIFEST"
|
sed -n "s/^${key}=//p" "$MANIFEST" | head -n1 | tr -d '[:space:]'
|
||||||
}
|
}
|
||||||
|
|
||||||
# _load_watchlist — validate the watch-list path + JSON + schema_version range.
|
# _load_watchlist — validate the watch-list path + JSON + schema_version range.
|
||||||
@@ -267,7 +267,7 @@ _poll_source() {
|
|||||||
if snap_json="$(jq -ce '.' <<<"$rawmeta" 2>/dev/null)"; then
|
if snap_json="$(jq -ce '.' <<<"$rawmeta" 2>/dev/null)"; then
|
||||||
snap_sha="$(jq -r 'if (.snapshot_sha|type) == "string" then .snapshot_sha else "" end' <<<"$snap_json")"
|
snap_sha="$(jq -r 'if (.snapshot_sha|type) == "string" then .snapshot_sha else "" end' <<<"$snap_json")"
|
||||||
snap_ts="$(jq -r 'if (.snapshot_ts|type) == "number" then (.snapshot_ts|floor|tostring) else "" end' <<<"$snap_json")"
|
snap_ts="$(jq -r 'if (.snapshot_ts|type) == "number" then (.snapshot_ts|floor|tostring) else "" end' <<<"$snap_json")"
|
||||||
if [ -n "$snap_sha" ] && ! grep -Eq '^[0-9a-f]{7,64}$' <<<"$snap_sha"; then
|
if [ -n "$snap_sha" ] && ! printf '%s' "$snap_sha" | grep -Eq '^[0-9a-f]{7,64}$'; then
|
||||||
echo "detector.sh: source '$kind/$id' snapshot_sha rejected (not a 7-64 char lowercase-hex git sha) — snapshot metadata DROPPED, poll continues (#940)." >&2
|
echo "detector.sh: source '$kind/$id' snapshot_sha rejected (not a 7-64 char lowercase-hex git sha) — snapshot metadata DROPPED, poll continues (#940)." >&2
|
||||||
snap_sha=""
|
snap_sha=""
|
||||||
snap_ts=""
|
snap_ts=""
|
||||||
@@ -275,7 +275,7 @@ _poll_source() {
|
|||||||
# A ts must be a sane positive epoch BEFORE any arithmetic touches it: a
|
# A ts must be a sane positive epoch BEFORE any arithmetic touches it: a
|
||||||
# negative or absurdly large value would make the shell integer comparison
|
# negative or absurdly large value would make the shell integer comparison
|
||||||
# below error out and silently KEEP the bad ts — validate first, compare after.
|
# below error out and silently KEEP the bad ts — validate first, compare after.
|
||||||
if [ -n "$snap_ts" ] && ! grep -Eq '^[0-9]{1,12}$' <<<"$snap_ts"; then
|
if [ -n "$snap_ts" ] && ! printf '%s' "$snap_ts" | grep -Eq '^[0-9]{1,12}$'; then
|
||||||
echo "detector.sh: source '$kind/$id' snapshot_ts rejected (not a sane positive epoch) — snapshot_ts DROPPED, poll continues (#940)." >&2
|
echo "detector.sh: source '$kind/$id' snapshot_ts rejected (not a sane positive epoch) — snapshot_ts DROPPED, poll continues (#940)." >&2
|
||||||
snap_ts=""
|
snap_ts=""
|
||||||
fi
|
fi
|
||||||
|
|||||||
@@ -644,8 +644,7 @@ cmd_render() {
|
|||||||
oseq="$(jq -r '.observed_seq // "?"' <<<"$line")"
|
oseq="$(jq -r '.observed_seq // "?"' <<<"$line")"
|
||||||
oclass="$(jq -r '.class // "actionable"' <<<"$line")"
|
oclass="$(jq -r '.class // "actionable"' <<<"$line")"
|
||||||
oloc="$(jq -c '.locators // {}' <<<"$line")"
|
oloc="$(jq -c '.locators // {}' <<<"$line")"
|
||||||
olabel="$(_locator_line "$oloc")"
|
olabel="$(_locator_line "$oloc" | head -n1)"
|
||||||
olabel="${olabel%%$'\n'*}"
|
|
||||||
printf ' * seq %s [%s] %s\n' "$oseq" "$(_scrub_inline "$oclass")" "$olabel"
|
printf ' * seq %s [%s] %s\n' "$oseq" "$(_scrub_inline "$oclass")" "$olabel"
|
||||||
done <<<"$pending"
|
done <<<"$pending"
|
||||||
fi
|
fi
|
||||||
|
|||||||
@@ -146,7 +146,7 @@ EOF
|
|||||||
_manifest_val() {
|
_manifest_val() {
|
||||||
local key="$1"
|
local key="$1"
|
||||||
[ -f "$MANIFEST" ] || return 0
|
[ -f "$MANIFEST" ] || return 0
|
||||||
awk -v key="$key" 'index($0, key "=") == 1 { sub(/^[^=]*=/, ""); gsub(/[[:space:]]/, ""); print; exit }' "$MANIFEST"
|
sed -n "s/^${key}=//p" "$MANIFEST" | head -n1 | tr -d '[:space:]'
|
||||||
}
|
}
|
||||||
|
|
||||||
# _load_watchlist — validate path + JSON + shape + Gate B schema range (mirrors
|
# _load_watchlist — validate path + JSON + shape + Gate B schema range (mirrors
|
||||||
|
|||||||
@@ -25,7 +25,7 @@
|
|||||||
"lint": "eslint src",
|
"lint": "eslint src",
|
||||||
"typecheck": "tsc --noEmit",
|
"typecheck": "tsc --noEmit",
|
||||||
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
|
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
|
||||||
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && bash framework/tools/fleet/test-start-agent-session.sh && bash framework/systemd/user/test-fleet-units.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/git/test-explain-diagnostic-status-neutral.sh && bash framework/tools/git/test-detect-platform-outside-repo.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
|
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && bash framework/tools/fleet/test-start-agent-session.sh && bash framework/systemd/user/test-fleet-units.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
|
||||||
},
|
},
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@mosaicstack/brain": "workspace:*",
|
"@mosaicstack/brain": "workspace:*",
|
||||||
|
|||||||
@@ -5,7 +5,6 @@ import { tmpdir } from 'node:os';
|
|||||||
import { join } from 'node:path';
|
import { join } from 'node:path';
|
||||||
import {
|
import {
|
||||||
buildPiSkillArgs,
|
buildPiSkillArgs,
|
||||||
discoverPiExtensionArgs,
|
|
||||||
enumerateSkillDirs,
|
enumerateSkillDirs,
|
||||||
piForceSkillNames,
|
piForceSkillNames,
|
||||||
registerRuntimeLaunchers,
|
registerRuntimeLaunchers,
|
||||||
@@ -179,52 +178,6 @@ describe('buildPiSkillArgs', () => {
|
|||||||
});
|
});
|
||||||
});
|
});
|
||||||
|
|
||||||
describe('discoverPiExtensionArgs', () => {
|
|
||||||
it('loads the core and goal extensions in deterministic order from Mosaic home', () => {
|
|
||||||
const root = mkdtempSync(join(tmpdir(), 'mosaic-pi-extensions-'));
|
|
||||||
const runtimeDir = join(root, 'runtime', 'pi');
|
|
||||||
mkdirSync(runtimeDir, { recursive: true });
|
|
||||||
writeFileSync(join(runtimeDir, 'goal-extension.ts'), '// goal\n');
|
|
||||||
writeFileSync(join(runtimeDir, 'mosaic-extension.ts'), '// core\n');
|
|
||||||
|
|
||||||
try {
|
|
||||||
expect(discoverPiExtensionArgs(root)).toEqual([
|
|
||||||
'--extension',
|
|
||||||
join(runtimeDir, 'mosaic-extension.ts'),
|
|
||||||
'--extension',
|
|
||||||
join(runtimeDir, 'goal-extension.ts'),
|
|
||||||
]);
|
|
||||||
} finally {
|
|
||||||
rmSync(root, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('remains backward-compatible when the optional goal extension is absent', () => {
|
|
||||||
const root = mkdtempSync(join(tmpdir(), 'mosaic-pi-extensions-'));
|
|
||||||
const runtimeDir = join(root, 'runtime', 'pi');
|
|
||||||
mkdirSync(runtimeDir, { recursive: true });
|
|
||||||
writeFileSync(join(runtimeDir, 'mosaic-extension.ts'), '// core\n');
|
|
||||||
|
|
||||||
try {
|
|
||||||
expect(discoverPiExtensionArgs(root)).toEqual([
|
|
||||||
'--extension',
|
|
||||||
join(runtimeDir, 'mosaic-extension.ts'),
|
|
||||||
]);
|
|
||||||
} finally {
|
|
||||||
rmSync(root, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('emits no extension arguments when Mosaic runtime assets are absent', () => {
|
|
||||||
const root = mkdtempSync(join(tmpdir(), 'mosaic-pi-extensions-'));
|
|
||||||
try {
|
|
||||||
expect(discoverPiExtensionArgs(root)).toEqual([]);
|
|
||||||
} finally {
|
|
||||||
rmSync(root, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('enumerateSkillDirs (real FS)', () => {
|
describe('enumerateSkillDirs (real FS)', () => {
|
||||||
let root: string;
|
let root: string;
|
||||||
|
|
||||||
|
|||||||
@@ -715,15 +715,9 @@ export function buildPiSkillArgs(
|
|||||||
return ['--no-skills', ...forcedSkillArgs];
|
return ['--no-skills', ...forcedSkillArgs];
|
||||||
}
|
}
|
||||||
|
|
||||||
const PI_EXTENSION_FILES = ['mosaic-extension.ts', 'goal-extension.ts'] as const;
|
function discoverPiExtension(): string[] {
|
||||||
|
const ext = join(MOSAIC_HOME, 'runtime', 'pi', 'mosaic-extension.ts');
|
||||||
export function discoverPiExtensionArgs(mosaicHome: string = MOSAIC_HOME): string[] {
|
return existsSync(ext) ? ['--extension', ext] : [];
|
||||||
const args: string[] = [];
|
|
||||||
for (const fileName of PI_EXTENSION_FILES) {
|
|
||||||
const extensionPath = join(mosaicHome, 'runtime', 'pi', fileName);
|
|
||||||
if (existsSync(extensionPath)) args.push('--extension', extensionPath);
|
|
||||||
}
|
|
||||||
return args;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// ─── Launch functions ────────────────────────────────────────────────────────
|
// ─── Launch functions ────────────────────────────────────────────────────────
|
||||||
@@ -798,7 +792,7 @@ function launchRuntime(runtime: RuntimeName, args: string[], yolo: boolean): nev
|
|||||||
const prompt = buildRuntimePrompt('pi');
|
const prompt = buildRuntimePrompt('pi');
|
||||||
const cliArgs = ['--append-system-prompt', prompt];
|
const cliArgs = ['--append-system-prompt', prompt];
|
||||||
cliArgs.push(...buildPiSkillArgs(args));
|
cliArgs.push(...buildPiSkillArgs(args));
|
||||||
cliArgs.push(...discoverPiExtensionArgs());
|
cliArgs.push(...discoverPiExtension());
|
||||||
if (hasMissionNoArgs) {
|
if (hasMissionNoArgs) {
|
||||||
cliArgs.push(missionPrompt);
|
cliArgs.push(missionPrompt);
|
||||||
} else {
|
} else {
|
||||||
|
|||||||
@@ -209,20 +209,6 @@ describe('FileConfigAdapter.syncFramework — defaults seeding', () => {
|
|||||||
);
|
);
|
||||||
});
|
});
|
||||||
|
|
||||||
it('deploys the Mosaic-owned Pi goal extension only inside the Mosaic runtime tree', async () => {
|
|
||||||
const sourceRuntime = join(fixture.sourceDir, 'runtime', 'pi');
|
|
||||||
mkdirSync(sourceRuntime, { recursive: true });
|
|
||||||
writeFileSync(join(sourceRuntime, 'goal-extension.ts'), '// persistent goal extension\n');
|
|
||||||
|
|
||||||
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
|
|
||||||
await adapter.syncFramework('fresh');
|
|
||||||
|
|
||||||
expect(
|
|
||||||
readFileSync(join(fixture.mosaicHome, 'runtime', 'pi', 'goal-extension.ts'), 'utf-8'),
|
|
||||||
).toBe('// persistent goal extension\n');
|
|
||||||
expect(existsSync(join(fixture.mosaicHome, '.pi'))).toBe(false);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('is a no-op for seeding when defaults/ dir does not exist', async () => {
|
it('is a no-op for seeding when defaults/ dir does not exist', async () => {
|
||||||
rmSync(fixture.defaultsDir, { recursive: true });
|
rmSync(fixture.defaultsDir, { recursive: true });
|
||||||
|
|
||||||
|
|||||||
@@ -1,796 +0,0 @@
|
|||||||
import { afterEach, describe, expect, it, vi } from 'vitest';
|
|
||||||
|
|
||||||
interface FakeEntry {
|
|
||||||
type: string;
|
|
||||||
customType?: string;
|
|
||||||
data?: unknown;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface SentMessage {
|
|
||||||
message: {
|
|
||||||
customType: string;
|
|
||||||
content: string;
|
|
||||||
display: boolean;
|
|
||||||
};
|
|
||||||
options?: {
|
|
||||||
triggerTurn?: boolean;
|
|
||||||
deliverAs?: 'steer' | 'followUp' | 'nextTurn';
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
interface FakeContext {
|
|
||||||
cwd: string;
|
|
||||||
ui: {
|
|
||||||
notifications: Array<{ message: string; level?: string }>;
|
|
||||||
statuses: Map<string, string | undefined>;
|
|
||||||
notify(message: string, level?: string): void;
|
|
||||||
setStatus(key: string, value: string | undefined): void;
|
|
||||||
};
|
|
||||||
sessionManager: {
|
|
||||||
getBranch(): FakeEntry[];
|
|
||||||
};
|
|
||||||
isIdle(): boolean;
|
|
||||||
hasPendingMessages(): boolean;
|
|
||||||
abort(): void;
|
|
||||||
}
|
|
||||||
|
|
||||||
type EventHandler = (
|
|
||||||
event: Record<string, unknown>,
|
|
||||||
context: FakeContext,
|
|
||||||
) => unknown | Promise<unknown>;
|
|
||||||
|
|
||||||
type CommandHandler = (args: string, context: FakeContext) => unknown | Promise<unknown>;
|
|
||||||
|
|
||||||
interface FakeToolResult {
|
|
||||||
content: Array<{ type: string; text: string }>;
|
|
||||||
details?: unknown;
|
|
||||||
terminate?: boolean;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface FakeTool {
|
|
||||||
name: string;
|
|
||||||
execute(
|
|
||||||
toolCallId: string,
|
|
||||||
params: Record<string, unknown>,
|
|
||||||
signal: AbortSignal | undefined,
|
|
||||||
onUpdate: undefined,
|
|
||||||
context: FakeContext,
|
|
||||||
): Promise<FakeToolResult>;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface GoalExtensionFactory {
|
|
||||||
(api: FakePiApi): void;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface GoalExtensionModule {
|
|
||||||
default: GoalExtensionFactory;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface FakePiApi {
|
|
||||||
on(event: string, handler: EventHandler): void;
|
|
||||||
registerCommand(name: string, options: { description: string; handler: CommandHandler }): void;
|
|
||||||
registerTool(tool: FakeTool): void;
|
|
||||||
appendEntry(customType: string, data?: unknown): void;
|
|
||||||
sendMessage(message: SentMessage['message'], options?: SentMessage['options']): void;
|
|
||||||
}
|
|
||||||
|
|
||||||
function isGoalExtensionModule(value: unknown): value is GoalExtensionModule {
|
|
||||||
if (typeof value !== 'object' || value === null) return false;
|
|
||||||
return typeof Reflect.get(value, 'default') === 'function';
|
|
||||||
}
|
|
||||||
|
|
||||||
const goalExtensionUrl = new URL('../../framework/runtime/pi/goal-extension.ts', import.meta.url)
|
|
||||||
.href;
|
|
||||||
const importedGoalExtension: unknown = await import(goalExtensionUrl);
|
|
||||||
if (!isGoalExtensionModule(importedGoalExtension)) {
|
|
||||||
throw new Error('Pi goal extension must export a default registration function');
|
|
||||||
}
|
|
||||||
const registerGoalExtension = importedGoalExtension.default;
|
|
||||||
|
|
||||||
function isRecord(value: unknown): value is Record<string, unknown> {
|
|
||||||
return typeof value === 'object' && value !== null && !Array.isArray(value);
|
|
||||||
}
|
|
||||||
|
|
||||||
class FakePi {
|
|
||||||
readonly handlers = new Map<string, EventHandler[]>();
|
|
||||||
readonly commands = new Map<string, CommandHandler>();
|
|
||||||
readonly tools = new Map<string, FakeTool>();
|
|
||||||
readonly entries: FakeEntry[] = [];
|
|
||||||
readonly sentMessages: SentMessage[] = [];
|
|
||||||
readonly notifications: Array<{ message: string; level?: string }> = [];
|
|
||||||
readonly statuses = new Map<string, string | undefined>();
|
|
||||||
branch: FakeEntry[] = [];
|
|
||||||
idle = true;
|
|
||||||
pending = false;
|
|
||||||
abortCount = 0;
|
|
||||||
|
|
||||||
readonly context: FakeContext = {
|
|
||||||
cwd: '/tmp/project',
|
|
||||||
ui: {
|
|
||||||
notifications: this.notifications,
|
|
||||||
statuses: this.statuses,
|
|
||||||
notify: (message: string, level?: string): void => {
|
|
||||||
this.notifications.push({ message, level });
|
|
||||||
},
|
|
||||||
setStatus: (key: string, value: string | undefined): void => {
|
|
||||||
this.statuses.set(key, value);
|
|
||||||
},
|
|
||||||
},
|
|
||||||
sessionManager: {
|
|
||||||
getBranch: (): FakeEntry[] => [...this.branch],
|
|
||||||
},
|
|
||||||
isIdle: (): boolean => this.idle,
|
|
||||||
hasPendingMessages: (): boolean => this.pending,
|
|
||||||
abort: (): void => {
|
|
||||||
this.abortCount += 1;
|
|
||||||
},
|
|
||||||
};
|
|
||||||
|
|
||||||
readonly api: FakePiApi = {
|
|
||||||
on: (event: string, handler: EventHandler): void => {
|
|
||||||
this.handlers.set(event, [...(this.handlers.get(event) ?? []), handler]);
|
|
||||||
},
|
|
||||||
registerCommand: (
|
|
||||||
name: string,
|
|
||||||
options: { description: string; handler: CommandHandler },
|
|
||||||
): void => {
|
|
||||||
this.commands.set(name, options.handler);
|
|
||||||
},
|
|
||||||
registerTool: (tool: FakeTool): void => {
|
|
||||||
this.tools.set(tool.name, tool);
|
|
||||||
},
|
|
||||||
appendEntry: (customType: string, data?: unknown): void => {
|
|
||||||
const entry: FakeEntry = { type: 'custom', customType, data };
|
|
||||||
this.entries.push(entry);
|
|
||||||
this.branch.push(entry);
|
|
||||||
},
|
|
||||||
sendMessage: (message: SentMessage['message'], options?: SentMessage['options']): void => {
|
|
||||||
this.sentMessages.push({ message, options });
|
|
||||||
},
|
|
||||||
};
|
|
||||||
|
|
||||||
constructor(initialBranch: FakeEntry[] = []) {
|
|
||||||
this.branch = [...initialBranch];
|
|
||||||
registerGoalExtension(this.api);
|
|
||||||
}
|
|
||||||
|
|
||||||
async emit(event: string, value: Record<string, unknown> = {}): Promise<unknown[]> {
|
|
||||||
const results: unknown[] = [];
|
|
||||||
for (const handler of this.handlers.get(event) ?? []) {
|
|
||||||
results.push(await handler(value, this.context));
|
|
||||||
}
|
|
||||||
return results;
|
|
||||||
}
|
|
||||||
|
|
||||||
async goal(args: string): Promise<void> {
|
|
||||||
const handler = this.commands.get('goal');
|
|
||||||
if (handler === undefined) throw new Error('/goal was not registered');
|
|
||||||
await handler(args, this.context);
|
|
||||||
}
|
|
||||||
|
|
||||||
async report(params: Record<string, unknown>): Promise<FakeToolResult> {
|
|
||||||
const tool = this.tools.get('mosaic_goal_report');
|
|
||||||
if (tool === undefined) throw new Error('mosaic_goal_report was not registered');
|
|
||||||
return await tool.execute('goal-report-1', params, undefined, undefined, this.context);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
function latestGoalStateData(pi: FakePi): Record<string, unknown> {
|
|
||||||
for (let index = pi.entries.length - 1; index >= 0; index -= 1) {
|
|
||||||
const entry = pi.entries[index];
|
|
||||||
if (entry?.customType === 'mosaic-goal-state' && isRecord(entry.data)) return entry.data;
|
|
||||||
}
|
|
||||||
throw new Error('No persisted Mosaic goal state found');
|
|
||||||
}
|
|
||||||
|
|
||||||
function stateField(pi: FakePi, field: string): unknown {
|
|
||||||
return latestGoalStateData(pi)[field];
|
|
||||||
}
|
|
||||||
|
|
||||||
function activeGoalStatementFromContext(result: unknown): string {
|
|
||||||
if (!isRecord(result)) throw new Error('Context handler did not return an object');
|
|
||||||
const messages = result['messages'];
|
|
||||||
if (!Array.isArray(messages)) throw new Error('Context result did not include messages');
|
|
||||||
const goalMessage = messages.find(
|
|
||||||
(message: unknown): boolean =>
|
|
||||||
isRecord(message) && message['customType'] === 'mosaic-goal-context',
|
|
||||||
);
|
|
||||||
if (!isRecord(goalMessage) || typeof goalMessage['content'] !== 'string') {
|
|
||||||
throw new Error('Goal context message was not injected');
|
|
||||||
}
|
|
||||||
return goalMessage['content'];
|
|
||||||
}
|
|
||||||
|
|
||||||
afterEach(() => {
|
|
||||||
vi.useRealTimers();
|
|
||||||
vi.unstubAllEnvs();
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('Mosaic Pi goal extension commands', () => {
|
|
||||||
it('shows help and handles controls safely when no goal exists', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal('');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('/goal set');
|
|
||||||
await pi.goal('status');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('No Mosaic goal is set');
|
|
||||||
|
|
||||||
for (const command of ['pause', 'resume', 'cancel']) {
|
|
||||||
await pi.goal(command);
|
|
||||||
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
||||||
}
|
|
||||||
expect(pi.entries).toHaveLength(0);
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('sets, reports, pauses, resumes, and cancels a bounded goal', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal('set Deliver the local goal extension with tests');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(stateField(pi, 'statement')).toBe('Deliver the local goal extension with tests');
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
expect(pi.sentMessages[0]?.options?.triggerTurn).toBe(true);
|
|
||||||
|
|
||||||
await pi.goal('status');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('Deliver the local goal extension');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('active');
|
|
||||||
|
|
||||||
await pi.goal('pause');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('paused');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
|
|
||||||
await pi.goal('resume');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
|
|
||||||
await pi.goal('cancel');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('cancelled');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('accepts /goal <statement> shorthand but refuses to replace an active goal', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal('First goal');
|
|
||||||
const firstGoalId = stateField(pi, 'goalId');
|
|
||||||
await pi.goal('set Second goal');
|
|
||||||
|
|
||||||
expect(stateField(pi, 'goalId')).toBe(firstGoalId);
|
|
||||||
expect(stateField(pi, 'statement')).toBe('First goal');
|
|
||||||
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('/goal cancel');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('rejects invalid phase transitions, aborts busy work, and supports clear as cancel', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Preserve transition safety');
|
|
||||||
|
|
||||||
await pi.goal('resume');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('cannot be resumed');
|
|
||||||
pi.idle = false;
|
|
||||||
await pi.goal('pause maintenance window');
|
|
||||||
expect(stateField(pi, 'stopReason')).toBe('maintenance window');
|
|
||||||
expect(pi.abortCount).toBe(1);
|
|
||||||
await pi.goal('pause');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('cannot be paused');
|
|
||||||
await pi.goal('clear');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('cancelled');
|
|
||||||
expect(pi.abortCount).toBe(2);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('rejects empty and oversized goal statements without starting a run', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal('set');
|
|
||||||
await pi.goal(`set ${'x'.repeat(8_001)}`);
|
|
||||||
|
|
||||||
expect(pi.entries).toHaveLength(0);
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('Mosaic Pi goal lifecycle', () => {
|
|
||||||
it('injects one fresh active contract before every model context', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Keep the agent oriented');
|
|
||||||
|
|
||||||
const existingGoalContext = {
|
|
||||||
role: 'custom',
|
|
||||||
customType: 'mosaic-goal-context',
|
|
||||||
content: 'stale',
|
|
||||||
};
|
|
||||||
const existingContinuation = {
|
|
||||||
role: 'custom',
|
|
||||||
customType: 'mosaic-goal-continuation',
|
|
||||||
content: 'stale continuation',
|
|
||||||
};
|
|
||||||
const first = await pi.emit('context', {
|
|
||||||
messages: [existingGoalContext, existingContinuation],
|
|
||||||
});
|
|
||||||
const second = await pi.emit('context', { messages: [] });
|
|
||||||
|
|
||||||
expect(activeGoalStatementFromContext(first[0])).toContain('Keep the agent oriented');
|
|
||||||
expect(activeGoalStatementFromContext(first[0])).toContain('mosaic_goal_report');
|
|
||||||
expect(activeGoalStatementFromContext(first[0])).not.toContain('stale');
|
|
||||||
if (!isRecord(first[0]) || !Array.isArray(first[0]['messages'])) {
|
|
||||||
throw new Error('Expected filtered context messages');
|
|
||||||
}
|
|
||||||
expect(first[0]['messages']).toHaveLength(1);
|
|
||||||
expect(activeGoalStatementFromContext(second[0])).toContain('Keep the agent oriented');
|
|
||||||
|
|
||||||
await pi.goal('cancel');
|
|
||||||
expect(
|
|
||||||
await pi.emit('context', {
|
|
||||||
messages: [existingGoalContext, existingContinuation],
|
|
||||||
}),
|
|
||||||
).toEqual([{ messages: [] }]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('lets an existing busy run adopt the goal and waits behind a pending message', async () => {
|
|
||||||
const busy = new FakePi();
|
|
||||||
busy.idle = false;
|
|
||||||
await busy.goal('set Join the current run safely');
|
|
||||||
expect(busy.sentMessages).toHaveLength(0);
|
|
||||||
|
|
||||||
busy.pending = true;
|
|
||||||
await busy.emit('agent_settled');
|
|
||||||
expect(busy.sentMessages).toHaveLength(0);
|
|
||||||
busy.pending = false;
|
|
||||||
busy.idle = true;
|
|
||||||
await busy.emit('agent_settled');
|
|
||||||
expect(busy.sentMessages).toHaveLength(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('records every turn and continues once when an active run settles', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Finish all acceptance criteria');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
|
|
||||||
await pi.emit('turn_end', { turnIndex: 0, message: {}, toolResults: [] });
|
|
||||||
expect(stateField(pi, 'turnCount')).toBe(1);
|
|
||||||
expect(stateField(pi, 'lastCheckSource')).toBe('turn');
|
|
||||||
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
expect(pi.sentMessages[0]?.message.content).toContain('Goal remains active');
|
|
||||||
|
|
||||||
await pi.emit('agent_start');
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(2);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('requires two consecutive evidence-bearing achievement reports', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Prove the feature works');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
|
|
||||||
const first = await pi.report({
|
|
||||||
status: 'achieved',
|
|
||||||
summary: 'Focused tests pass',
|
|
||||||
evidence: ['pnpm test: 12 passed'],
|
|
||||||
});
|
|
||||||
expect(first.terminate).toBe(true);
|
|
||||||
expect(stateField(pi, 'phase')).toBe('verifying');
|
|
||||||
expect(stateField(pi, 'verificationPasses')).toBe(1);
|
|
||||||
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
expect(pi.sentMessages[0]?.message.content).toContain('verification pass');
|
|
||||||
|
|
||||||
await pi.emit('agent_start');
|
|
||||||
const second = await pi.report({
|
|
||||||
status: 'achieved',
|
|
||||||
summary: 'Independent recheck confirms completion',
|
|
||||||
evidence: ['rerun: 12 passed', 'framework path verified'],
|
|
||||||
});
|
|
||||||
expect(second.terminate).toBe(true);
|
|
||||||
expect(stateField(pi, 'phase')).toBe('achieved');
|
|
||||||
expect(stateField(pi, 'verificationPasses')).toBe(2);
|
|
||||||
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('rejects malformed progress reports and reports submitted without an active goal', async () => {
|
|
||||||
const noGoal = new FakePi();
|
|
||||||
await expect(
|
|
||||||
noGoal.report({ status: 'continue', summary: 'work', evidence: [] }),
|
|
||||||
).rejects.toThrow(/No active Mosaic goal/);
|
|
||||||
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Validate report boundaries');
|
|
||||||
const invalidReports: Record<string, unknown>[] = [
|
|
||||||
{},
|
|
||||||
{ status: 'invalid', summary: 'work', evidence: [] },
|
|
||||||
{ status: 'continue', evidence: [] },
|
|
||||||
{ status: 'continue', summary: ' ', evidence: [] },
|
|
||||||
{ status: 'continue', summary: 'x'.repeat(2_001), evidence: [] },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: 'not-an-array' },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: Array.from({ length: 21 }, () => 'x') },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: [4] },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: [''] },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: ['x'.repeat(1_001)] },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: [], nextStep: 4 },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: [], nextStep: ' ' },
|
|
||||||
{ status: 'continue', summary: 'work', evidence: [], nextStep: 'x'.repeat(2_001) },
|
|
||||||
];
|
|
||||||
for (const report of invalidReports) {
|
|
||||||
await expect(pi.report(report)).rejects.toThrow();
|
|
||||||
}
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('rejects an achievement claim without evidence', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Require evidence');
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
pi.report({ status: 'achieved', summary: 'Trust me', evidence: [] }),
|
|
||||||
).rejects.toThrow(/evidence/i);
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('redacts credential-shaped goal and report text before persistence or display', async () => {
|
|
||||||
const githubToken = `ghp_${'a'.repeat(32)}`;
|
|
||||||
const anthropicKey = `sk-ant-api03-${'b'.repeat(40)}`;
|
|
||||||
const bearerToken = 'header.payload.signature-canary';
|
|
||||||
const databaseUrl = 'postgresql://mosaic:[email protected]/mosaic';
|
|
||||||
const password = 'password-canary';
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal(`set Rotate ${githubToken} without retaining it`);
|
|
||||||
const context = await pi.emit('context', { messages: [] });
|
|
||||||
expect(activeGoalStatementFromContext(context[0])).not.toContain(githubToken);
|
|
||||||
|
|
||||||
const result = await pi.report({
|
|
||||||
status: 'achieved',
|
|
||||||
summary: `Validated ${anthropicKey}`,
|
|
||||||
evidence: [`Authorization: Bearer ${bearerToken}`, `DATABASE_URL=${databaseUrl}`],
|
|
||||||
nextStep: `password=${password}`,
|
|
||||||
});
|
|
||||||
await pi.goal('status');
|
|
||||||
|
|
||||||
const persisted = JSON.stringify(latestGoalStateData(pi));
|
|
||||||
const displayed = pi.notifications.at(-1)?.message ?? '';
|
|
||||||
const toolOutput = JSON.stringify(result);
|
|
||||||
for (const secret of [githubToken, anthropicKey, bearerToken, databaseUrl, password]) {
|
|
||||||
expect(persisted).not.toContain(secret);
|
|
||||||
expect(displayed).not.toContain(secret);
|
|
||||||
expect(toolOutput).not.toContain(secret);
|
|
||||||
}
|
|
||||||
expect(persisted).toContain('[REDACTED-SECRET]');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('preserves ordinary typed fields that resemble sensitive assignment names', async () => {
|
|
||||||
const typedFields = 'token: string, password: boolean, secret: false';
|
|
||||||
const pi = new FakePi();
|
|
||||||
|
|
||||||
await pi.goal(`set Preserve TypeScript fields: ${typedFields}`);
|
|
||||||
await pi.report({
|
|
||||||
status: 'continue',
|
|
||||||
summary: `Schema still contains ${typedFields}`,
|
|
||||||
evidence: [`interface Config { ${typedFields} }`],
|
|
||||||
nextStep: `Keep ${typedFields} unchanged`,
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(stateField(pi, 'statement')).toContain(typedFields);
|
|
||||||
expect(JSON.stringify(stateField(pi, 'lastReport'))).toContain(typedFields);
|
|
||||||
expect(JSON.stringify(latestGoalStateData(pi))).not.toContain('[REDACTED-SECRET]');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('stops autonomous continuation when the max-turn limit is reached', async () => {
|
|
||||||
vi.stubEnv('MOSAIC_GOAL_MAX_TURNS', '2');
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Bound this run');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
|
|
||||||
await pi.emit('turn_end', { turnIndex: 0, message: {}, toolResults: [] });
|
|
||||||
await pi.emit('turn_end', { turnIndex: 1, message: {}, toolResults: [] });
|
|
||||||
|
|
||||||
expect(stateField(pi, 'phase')).toBe('exhausted');
|
|
||||||
expect(pi.abortCount).toBe(1);
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('resets the no-progress sequence when a continuation report changes', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Track changing progress');
|
|
||||||
|
|
||||||
await pi.report({
|
|
||||||
status: 'continue',
|
|
||||||
summary: 'First checkpoint',
|
|
||||||
evidence: ['file A changed'],
|
|
||||||
nextStep: 'Run focused tests',
|
|
||||||
});
|
|
||||||
await pi.report({
|
|
||||||
status: 'continue',
|
|
||||||
summary: 'Second checkpoint',
|
|
||||||
evidence: ['focused tests passed'],
|
|
||||||
nextStep: 'Review the diff',
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(stateField(pi, 'noProgressReports')).toBe(1);
|
|
||||||
await pi.goal('status');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('Next step: Review the diff');
|
|
||||||
expect(pi.notifications.at(-1)?.message).toContain('focused tests passed');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('stops after a bounded number of identical no-progress reports', async () => {
|
|
||||||
vi.stubEnv('MOSAIC_GOAL_MAX_NO_PROGRESS', '2');
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Detect stalled work');
|
|
||||||
|
|
||||||
const report = {
|
|
||||||
status: 'continue',
|
|
||||||
summary: 'No change yet',
|
|
||||||
evidence: ['same observation'],
|
|
||||||
nextStep: 'Try again',
|
|
||||||
};
|
|
||||||
await pi.report(report);
|
|
||||||
await pi.report(report);
|
|
||||||
|
|
||||||
expect(stateField(pi, 'phase')).toBe('exhausted');
|
|
||||||
expect(stateField(pi, 'noProgressReports')).toBe(2);
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('rejects a goal report mixed with another tool result in the same turn', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Require a sole final report');
|
|
||||||
await pi.report({
|
|
||||||
status: 'achieved',
|
|
||||||
summary: 'Premature mixed claim',
|
|
||||||
evidence: ['one observation'],
|
|
||||||
});
|
|
||||||
|
|
||||||
await pi.emit('turn_end', {
|
|
||||||
turnIndex: 0,
|
|
||||||
message: {},
|
|
||||||
toolResults: [{ toolName: 'mosaic_goal_report' }, { toolName: 'read' }],
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(stateField(pi, 'verificationPasses')).toBe(0);
|
|
||||||
expect(stateField(pi, 'lastCheckOutcome')).toBe('mixed-goal-report-rejected');
|
|
||||||
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('marks blocked reports terminal until the operator resumes', async () => {
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Stop on a real blocker');
|
|
||||||
|
|
||||||
await pi.report({
|
|
||||||
status: 'blocked',
|
|
||||||
summary: 'Missing required access',
|
|
||||||
evidence: ['provider returned 403'],
|
|
||||||
});
|
|
||||||
expect(stateField(pi, 'phase')).toBe('blocked');
|
|
||||||
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
|
|
||||||
await pi.goal('resume');
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(stateField(pi, 'turnCount')).toBe(0);
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('Mosaic Pi goal compaction and restoration', () => {
|
|
||||||
it('resets provisional verification and defers manual-compaction continuation until idle', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Survive compaction');
|
|
||||||
await pi.report({
|
|
||||||
status: 'achieved',
|
|
||||||
summary: 'Initial claim',
|
|
||||||
evidence: ['focused test passed'],
|
|
||||||
});
|
|
||||||
expect(stateField(pi, 'phase')).toBe('verifying');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
|
|
||||||
await pi.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
||||||
expect(stateField(pi, 'phase')).toBe('active');
|
|
||||||
expect(stateField(pi, 'verificationPasses')).toBe(0);
|
|
||||||
expect(stateField(pi, 'compactionCount')).toBe(1);
|
|
||||||
expect(stateField(pi, 'lastCheckSource')).toBe('compact');
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
|
|
||||||
await vi.runAllTimersAsync();
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
expect(pi.sentMessages[0]?.message.content).toContain('compaction');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('does not re-enter an active automatic compaction and relies on the settled backstop', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Avoid compaction races');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
pi.idle = false;
|
|
||||||
|
|
||||||
await pi.emit('session_compact', { reason: 'threshold', willRetry: false });
|
|
||||||
await vi.runAllTimersAsync();
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
|
|
||||||
pi.idle = true;
|
|
||||||
await pi.emit('agent_settled');
|
|
||||||
expect(pi.sentMessages).toHaveLength(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('restores branch-specific state on session start and tree navigation', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const source = new FakePi();
|
|
||||||
await source.goal('set Restore this exact branch goal');
|
|
||||||
const activeState = latestGoalStateData(source);
|
|
||||||
|
|
||||||
const restored = new FakePi([
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: activeState },
|
|
||||||
]);
|
|
||||||
await restored.emit('session_start', { reason: 'resume' });
|
|
||||||
expect(restored.statuses.get('mosaic-goal')).toContain('active');
|
|
||||||
const context = await restored.emit('context', { messages: [] });
|
|
||||||
expect(activeGoalStatementFromContext(context[0])).toContain('Restore this exact branch goal');
|
|
||||||
|
|
||||||
await restored.goal('pause');
|
|
||||||
const pausedState = latestGoalStateData(restored);
|
|
||||||
restored.branch = [{ type: 'custom', customType: 'mosaic-goal-state', data: pausedState }];
|
|
||||||
await restored.emit('session_tree', {});
|
|
||||||
await vi.runAllTimersAsync();
|
|
||||||
expect(stateField(restored, 'phase')).toBe('paused');
|
|
||||||
expect(restored.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('restores only fully valid persisted states and ignores malformed entries', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const source = new FakePi();
|
|
||||||
await source.goal('set Validate persisted branch state');
|
|
||||||
await source.report({
|
|
||||||
status: 'continue',
|
|
||||||
summary: 'Valid report',
|
|
||||||
evidence: ['valid evidence'],
|
|
||||||
nextStep: 'Continue validation',
|
|
||||||
});
|
|
||||||
const valid = latestGoalStateData(source);
|
|
||||||
|
|
||||||
const validRestore = new FakePi([
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: valid },
|
|
||||||
]);
|
|
||||||
await validRestore.emit('session_start', { reason: 'resume' });
|
|
||||||
expect(stateField(validRestore, 'statement')).toBe('Validate persisted branch state');
|
|
||||||
await validRestore.emit('session_shutdown', { reason: 'reload' });
|
|
||||||
|
|
||||||
const validReport = latestGoalStateData(source)['lastReport'];
|
|
||||||
if (!isRecord(validReport)) throw new Error('Expected a valid persisted report fixture');
|
|
||||||
const integerFields = [
|
|
||||||
'turnCount',
|
|
||||||
'reportCount',
|
|
||||||
'verificationPasses',
|
|
||||||
'requiredVerificationPasses',
|
|
||||||
'noProgressReports',
|
|
||||||
'maxTurns',
|
|
||||||
'maxNoProgressReports',
|
|
||||||
'compactionCount',
|
|
||||||
];
|
|
||||||
const corruptions: Array<(state: Record<string, unknown>) => unknown> = [
|
|
||||||
(): unknown => null,
|
|
||||||
(state): unknown => ({ ...state, version: 99 }),
|
|
||||||
(state): unknown => ({ ...state, goalId: '' }),
|
|
||||||
(state): unknown => ({ ...state, statement: '' }),
|
|
||||||
(state): unknown => ({ ...state, statement: 'x'.repeat(8_001) }),
|
|
||||||
(state): unknown => ({ ...state, phase: 'unknown' }),
|
|
||||||
(state): unknown => ({ ...state, lastCheckSource: 'unknown' }),
|
|
||||||
(state): unknown => ({ ...state, startedAt: 4 }),
|
|
||||||
(state): unknown => ({ ...state, lastCheckAt: 4 }),
|
|
||||||
(state): unknown => ({ ...state, lastReport: null }),
|
|
||||||
(state): unknown => ({ ...state, lastProgressFingerprint: 4 }),
|
|
||||||
(state): unknown => ({ ...state, stopReason: 4 }),
|
|
||||||
...integerFields.map((field: string) => (state: Record<string, unknown>): unknown => ({
|
|
||||||
...state,
|
|
||||||
[field]: -1,
|
|
||||||
})),
|
|
||||||
];
|
|
||||||
|
|
||||||
corruptions.push(
|
|
||||||
(state: Record<string, unknown>): unknown => ({ ...state, maxTurns: 501 }),
|
|
||||||
(state: Record<string, unknown>): unknown => ({ ...state, maxNoProgressReports: 101 }),
|
|
||||||
(state: Record<string, unknown>): unknown => ({ ...state, requiredVerificationPasses: 3 }),
|
|
||||||
);
|
|
||||||
const reportCorruptions: Array<Record<string, unknown>> = [
|
|
||||||
{ ...validReport, status: 'bad' },
|
|
||||||
{ ...validReport, summary: '' },
|
|
||||||
{ ...validReport, evidence: 'bad' },
|
|
||||||
{ ...validReport, evidence: [4] },
|
|
||||||
{ ...validReport, fingerprint: '' },
|
|
||||||
{ ...validReport, reportedAt: '' },
|
|
||||||
{ ...validReport, nextStep: 4 },
|
|
||||||
];
|
|
||||||
for (const corruptReport of reportCorruptions) {
|
|
||||||
corruptions.push((state: Record<string, unknown>): unknown => ({
|
|
||||||
...state,
|
|
||||||
lastReport: corruptReport,
|
|
||||||
}));
|
|
||||||
}
|
|
||||||
|
|
||||||
for (const corrupt of corruptions) {
|
|
||||||
const candidate = corrupt(structuredClone(valid));
|
|
||||||
const restored = new FakePi([
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: candidate },
|
|
||||||
]);
|
|
||||||
await restored.emit('session_start', { reason: 'resume' });
|
|
||||||
expect(restored.statuses.get('mosaic-goal')).toBeUndefined();
|
|
||||||
expect(await restored.emit('context', { messages: [] })).toEqual([undefined]);
|
|
||||||
}
|
|
||||||
|
|
||||||
const failClosed = new FakePi([
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: valid },
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: { ...valid, version: 99 } },
|
|
||||||
]);
|
|
||||||
await failClosed.emit('session_start', { reason: 'resume' });
|
|
||||||
expect(failClosed.statuses.get('mosaic-goal')).toBeUndefined();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fails closed instead of reusing credential-bearing legacy branch state', async () => {
|
|
||||||
const source = new FakePi();
|
|
||||||
await source.goal('set Build a valid restore fixture');
|
|
||||||
const cleanState = latestGoalStateData(source);
|
|
||||||
const legacyState = structuredClone(cleanState);
|
|
||||||
legacyState['statement'] = `Legacy secret ghp_${'z'.repeat(32)}`;
|
|
||||||
|
|
||||||
const restored = new FakePi([
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: legacyState },
|
|
||||||
{ type: 'custom', customType: 'mosaic-goal-state', data: cleanState },
|
|
||||||
]);
|
|
||||||
await restored.emit('session_start', { reason: 'resume' });
|
|
||||||
|
|
||||||
expect(restored.statuses.get('mosaic-goal')).toBeUndefined();
|
|
||||||
expect(await restored.emit('context', { messages: [] })).toEqual([undefined]);
|
|
||||||
expect(restored.notifications.at(-1)?.level).toBe('warning');
|
|
||||||
expect(restored.notifications.at(-1)?.message).toContain('was not restored');
|
|
||||||
expect(restored.entries).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('schedules an active tree-restored goal and preserves terminal state through compaction', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const source = new FakePi();
|
|
||||||
await source.goal('set Restore active tree work');
|
|
||||||
const active = latestGoalStateData(source);
|
|
||||||
|
|
||||||
const restored = new FakePi();
|
|
||||||
restored.branch = [{ type: 'custom', customType: 'mosaic-goal-state', data: active }];
|
|
||||||
await restored.emit('session_tree', {});
|
|
||||||
await vi.runAllTimersAsync();
|
|
||||||
expect(restored.sentMessages).toHaveLength(1);
|
|
||||||
expect(restored.sentMessages[0]?.message.content).toContain('tree navigation');
|
|
||||||
|
|
||||||
await restored.goal('cancel');
|
|
||||||
await restored.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
||||||
expect(stateField(restored, 'phase')).toBe('cancelled');
|
|
||||||
expect(stateField(restored, 'compactionCount')).toBe(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('cancels deferred continuation when the session shuts down', async () => {
|
|
||||||
vi.useFakeTimers();
|
|
||||||
const pi = new FakePi();
|
|
||||||
await pi.goal('set Do not leak a stale timer');
|
|
||||||
pi.sentMessages.length = 0;
|
|
||||||
|
|
||||||
await pi.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
||||||
await pi.emit('session_shutdown', { reason: 'reload' });
|
|
||||||
await vi.runAllTimersAsync();
|
|
||||||
|
|
||||||
expect(pi.sentMessages).toHaveLength(0);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -72,9 +72,8 @@ elif [[ -n "$DATA_DIR" ]]; then
|
|||||||
while IFS= read -r file; do
|
while IFS= read -r file; do
|
||||||
[[ -z "$file" ]] && continue
|
[[ -z "$file" ]] && continue
|
||||||
done_total=$((done_total + 1))
|
done_total=$((done_total + 1))
|
||||||
history_rc=0
|
if git -C "$DATA_DIR" log --since="${WINDOW_DAYS} days ago" --pretty='%s' -- "$file" 2>/dev/null \
|
||||||
history="$(git -C "$DATA_DIR" log --since="${WINDOW_DAYS} days ago" --pretty='%s' -- "$file" 2>/dev/null)" || history_rc=$?
|
| grep -qiE 'reopen|revert|fix|regression|wrong|incorrect|redo'; then
|
||||||
if [[ "$history_rc" -eq 0 ]] && grep -qiE 'reopen|revert|fix|regression|wrong|incorrect|redo' <<<"$history"; then
|
|
||||||
detectable=$((detectable + 1))
|
detectable=$((detectable + 1))
|
||||||
fi
|
fi
|
||||||
done < <(find "$DATA_DIR" -type f -name '*.json' 2>/dev/null)
|
done < <(find "$DATA_DIR" -type f -name '*.json' 2>/dev/null)
|
||||||
|
|||||||
@@ -64,9 +64,9 @@ for line in "${LINES[@]}"; do
|
|||||||
# - build/test/lint/type/ci signals → CI would have caught it
|
# - build/test/lint/type/ci signals → CI would have caught it
|
||||||
# - security/auth/permission/data/migration → human review would flag it
|
# - security/auth/permission/data/migration → human review would flag it
|
||||||
# - everything else (logic/UX/assumption/edge) → only-self-reflection bucket
|
# - everything else (logic/UX/assumption/edge) → only-self-reflection bucket
|
||||||
if grep -qiE 'test|lint|type|build|ci|compile|typo' <<<"$subj"; then
|
if printf '%s' "$subj" | grep -qiE 'test|lint|type|build|ci|compile|typo'; then
|
||||||
ci=$((ci + 1))
|
ci=$((ci + 1))
|
||||||
elif grep -qiE 'security|auth|permission|rbac|secret|migration|data|sql|injection' <<<"$subj"; then
|
elif printf '%s' "$subj" | grep -qiE 'security|auth|permission|rbac|secret|migration|data|sql|injection'; then
|
||||||
human=$((human + 1))
|
human=$((human + 1))
|
||||||
else
|
else
|
||||||
selfonly=$((selfonly + 1))
|
selfonly=$((selfonly + 1))
|
||||||
|
|||||||
@@ -1,28 +0,0 @@
|
|||||||
[
|
|
||||||
"tools/matrix-presence-harness/run.sh:TSX_CLI=\"$(ls -d \"${REPO}\"/node_modules/.pnpm/tsx@*/node_modules/tsx/dist/cli.mjs 2>/dev/null | head -1)\"",
|
|
||||||
"tools/e2e-install-test.sh:if ! mosaic gateway --help 2>&1 | grep -q 'verify'; then",
|
|
||||||
"tools/install.sh:EXTRACTED_DIR=\"$(find \"$WORK_DIR\" -maxdepth 1 -mindepth 1 -type d | head -1)\"",
|
|
||||||
"scripts/analysis/reflect-board-history.sh:if git -C \"$DATA_DIR\" log --since=\"${WINDOW_DAYS} days ago\" --pretty='%s' -- \"$file\" 2>/dev/null | grep -qiE 'reopen|revert|fix|regression|wrong|incorrect|redo'; then",
|
|
||||||
"scripts/analysis/reflect-git-history.sh:if printf '%s' \"$subj\" | grep -qiE 'test|lint|type|build|ci|compile|typo'; then",
|
|
||||||
"scripts/analysis/reflect-git-history.sh:elif printf '%s' \"$subj\" | grep -qiE 'security|auth|permission|rbac|secret|migration|data|sql|injection'; then",
|
|
||||||
"packages/mosaic/framework/tools/authentik/user-create.sh:group_pk=$(echo \"$group_response\" | jq -r \".results[] | select(.name == \\\"$GROUP\\\") | .pk\" | head -1)",
|
|
||||||
"packages/mosaic/framework/tools/git/mutate-push-guard.sh:PROSE_LO=\"$(grep -n '^usage() {' \"$BAK\" | head -1 | cut -d: -f1)\"",
|
|
||||||
"packages/mosaic/framework/tools/orchestrator/session-resume.sh:echo \"$dirty_files\" | head -20 | while IFS= read -r line; do",
|
|
||||||
"packages/mosaic/framework/tools/prdy/prdy-status.sh:if echo \"$PRD_CONTENT\" | grep -qiE \"$pattern\"; then",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qiE 'auth|login|session|token|permission|rbac|credential|secret'; then echo auth; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qiE 'migration|prisma|schema|\\.sql|entity|repository|seed'; then echo data; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qiE 'docker|\\.woodpecker|compose|traefik|deploy|helm|k8s|terraform'; then echo infra; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qiE 'package\\.json|tsconfig|turbo\\.json|pnpm-|\\.config\\.|eslint|vite'; then echo build; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qE '\\.tsx|\\.css|components/|apps/web/'; then echo ui; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qE '\\.spec\\.|\\.test\\.|__tests__/'; then echo test; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:if printf '%s' \"$p\" | grep -qE '\\.md$|docs/'; then echo docs; return; fi",
|
|
||||||
"packages/mosaic/framework/tools/qa/typecheck-hook.sh:FILE_PATH=$(echo \"$JSON_INPUT\" | grep -o '\"file_path\"[[:space:]]*:[[:space:]]*\"[^\"]*\"' | sed 's/.*\"\\([^\"]*\\)\"$/\\1/' | head -1)",
|
|
||||||
"packages/mosaic/framework/tools/qa/typecheck-hook.sh:RELEVANT=$(echo \"$OUTPUT\" | grep -A2 \"$BASENAME\" 2>/dev/null || echo \"$OUTPUT\" | head -20)",
|
|
||||||
"packages/mosaic/framework/tools/tmux/send-message.sh:if printf '%s' \"$pane\" | grep -qF \"$QUEUED_RE\"; then",
|
|
||||||
"packages/mosaic/framework/tools/tmux/send-message.sh:if [ -n \"$snippet\" ] && printf '%s' \"$promptline\" | grep -qF \"$snippet\"; then",
|
|
||||||
"packages/mosaic/framework/tools/wake/detector.sh:sed -n \"s/^${key}=//p\" \"$MANIFEST\" | head -n1 | tr -d '[:space:]'",
|
|
||||||
"packages/mosaic/framework/tools/wake/detector.sh:if [ -n \"$snap_sha\" ] && ! printf '%s' \"$snap_sha\" | grep -Eq '^[0-9a-f]{7,64}$'; then",
|
|
||||||
"packages/mosaic/framework/tools/wake/detector.sh:if [ -n \"$snap_ts\" ] && ! printf '%s' \"$snap_ts\" | grep -Eq '^[0-9]{1,12}$'; then",
|
|
||||||
"packages/mosaic/framework/tools/wake/digest.sh:olabel=\"$(_locator_line \"$oloc\" | head -n1)\"",
|
|
||||||
"packages/mosaic/framework/tools/wake/reconcile.sh:sed -n \"s/^${key}=//p\" \"$MANIFEST\" | head -n1 | tr -d '[:space:]'"
|
|
||||||
]
|
|
||||||
@@ -1,24 +0,0 @@
|
|||||||
[
|
|
||||||
"packages/mosaic/framework/systemd/user/test-fleet-units.sh:if tmux -L \"$TEST_SOCKET\" show-environment -g LD_PRELOAD 2>/dev/null | grep -q '^LD_PRELOAD='; then",
|
|
||||||
"packages/mosaic/framework/tools/git/test-issue-comment-readback.sh:write_response \"$(printf '%s' \"$result\" | head -n1)\" \"$(printf '%s' \"$result\" | tail -n +2)\"",
|
|
||||||
"packages/mosaic/framework/tools/git/test-issue-comment-readback.sh:write_response \"$(printf '%s' \"$result\" | head -n1)\" \"$(printf '%s' \"$result\" | tail -n +2)\"",
|
|
||||||
"packages/mosaic/framework/tools/git/test-lane-brief-pr-linkage.sh:contains() { printf '%s\\n' \"$1\" | grep -qx \"$2\"; }",
|
|
||||||
"packages/mosaic/framework/tools/git/test-pr-review-gitea-comment.sh:write_response \"$(printf '%s' \"$result\" | head -n1)\" \"$(printf '%s' \"$result\" | tail -n +2)\"",
|
|
||||||
"packages/mosaic/framework/tools/git/test-pr-review-repo-host-override.sh:echo \"$HELP_TEXT\" | grep -q -- '-r, --repo'",
|
|
||||||
"packages/mosaic/framework/tools/git/test-pr-review-repo-host-override.sh:echo \"$HELP_TEXT\" | grep -q -- '-H, --host'",
|
|
||||||
"packages/mosaic/framework/tools/orchestrator/smoke-test.sh:if [[ \"$(printf '%s\\n' \"$codex_run_prompt\" | head -n1)\" == \"Now initiating Orchestrator mode...\" ]]; then pass_case \"codex run prompt first line is mode declaration\"; else fail_case \"codex run prompt first line is mode declaration\"; fi",
|
|
||||||
"packages/mosaic/framework/tools/orchestrator/smoke-test.sh:if [[ \"$(printf '%s\\n' \"$claude_run_prompt\" | head -n1)\" == \"## Continuation Mission\" ]]; then pass_case \"claude run prompt remains continuation prompt format\"; else fail_case \"claude run prompt remains continuation prompt format\"; fi",
|
|
||||||
"packages/mosaic/framework/tools/orchestrator/test-board-roll.sh:echo \"$out\" | grep -qi \"dry run\" || note \"dry-run did not announce itself\"",
|
|
||||||
"packages/mosaic/framework/tools/orchestrator/test-board-roll.sh:echo \"$out\" | grep -q \"would roll\" || note \"dry-run did not report a plan\"",
|
|
||||||
"packages/mosaic/framework/tools/quality/scripts/test-upgrade-durable-snapshot.sh:find \"$1/mosaic/backups\" -maxdepth 1 -type d -name 'pre-update-*' 2>/dev/null | LC_ALL=C sort -r | head -1",
|
|
||||||
"packages/mosaic/framework/tools/quality/scripts/test-upgrade-rollback.sh:SNAP_E=\"$(grep -o '/[^ ]*mosaic-snapshot[^ ]*' \"$OUTG\" | head -1)\"",
|
|
||||||
"packages/mosaic/framework/tools/quality/scripts/test-upgrade-rollback.sh:grep -o '/[^ ]*mosaic-snapshot[^ ]*' \"$OUTH\" 2>/dev/null | head -1 | while read -r s; do rm -rf \"$s\"; done",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:capture_named | grep -qF \"named socket hello\" || fail \"send-message.sh did not deliver to named socket\"",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:if capture_default | grep -qF \"named socket hello\"; then",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:capture_named | grep -qF \"[tester:source ->\" || fail \"agent-send.sh did not include preamble\"",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:capture_named | grep -qF \"agent socket hello\" || fail \"agent-send.sh did not deliver to named socket\"",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:if capture_default | grep -qF \"agent socket hello\"; then",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:printf '%s' \"$pane\" | grep -qF \"CONCPAYLOAD-${i}-END\" || fail \"concurrent send dropped payload for pane conc-$i\"",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-socket.sh:if printf '%s' \"$pane\" | grep -qF \"CONCPAYLOAD-${j}-END\"; then",
|
|
||||||
"packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh:if [ \"$rc\" -eq 0 ] && printf '%s' \"$out\" | grep -qF \"✓ delivered\"; then"
|
|
||||||
]
|
|
||||||
@@ -1,160 +0,0 @@
|
|||||||
import assert from 'node:assert/strict';
|
|
||||||
import { spawnSync } from 'node:child_process';
|
|
||||||
import { chmod, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
|
|
||||||
import { tmpdir } from 'node:os';
|
|
||||||
import path from 'node:path';
|
|
||||||
import test from 'node:test';
|
|
||||||
|
|
||||||
const ROOT = new URL('../', import.meta.url);
|
|
||||||
const EXPECTED_BASELINE_SITES = 26;
|
|
||||||
const EXPECTED_TEST_BASELINE_SITES = 22;
|
|
||||||
const TARGETS = [
|
|
||||||
'tools/matrix-presence-harness/run.sh',
|
|
||||||
'tools/e2e-install-test.sh',
|
|
||||||
'tools/install.sh',
|
|
||||||
'scripts/agent/session-start.sh',
|
|
||||||
'scripts/analysis/reflect-board-history.sh',
|
|
||||||
'scripts/analysis/reflect-git-history.sh',
|
|
||||||
'packages/mosaic/framework/templates/repo/scripts/agent/session-start.sh',
|
|
||||||
'packages/mosaic/framework/tools/authentik/user-create.sh',
|
|
||||||
'packages/mosaic/framework/tools/git/mutate-push-guard.sh',
|
|
||||||
'packages/mosaic/framework/tools/orchestrator/session-resume.sh',
|
|
||||||
'packages/mosaic/framework/tools/prdy/prdy-status.sh',
|
|
||||||
'packages/mosaic/framework/tools/qa/reflect-stop-hook.sh',
|
|
||||||
'packages/mosaic/framework/tools/qa/typecheck-hook.sh',
|
|
||||||
'packages/mosaic/framework/tools/tmux/send-message.sh',
|
|
||||||
'packages/mosaic/framework/tools/wake/detector.sh',
|
|
||||||
'packages/mosaic/framework/tools/wake/digest.sh',
|
|
||||||
'packages/mosaic/framework/tools/wake/reconcile.sh',
|
|
||||||
'packages/mosaic/framework/systemd/user/test-fleet-units.sh',
|
|
||||||
'packages/mosaic/framework/tools/git/test-issue-comment-readback.sh',
|
|
||||||
'packages/mosaic/framework/tools/git/test-lane-brief-pr-linkage.sh',
|
|
||||||
'packages/mosaic/framework/tools/git/test-pr-review-gitea-comment.sh',
|
|
||||||
'packages/mosaic/framework/tools/git/test-pr-review-repo-host-override.sh',
|
|
||||||
'packages/mosaic/framework/tools/orchestrator/smoke-test.sh',
|
|
||||||
'packages/mosaic/framework/tools/orchestrator/test-board-roll.sh',
|
|
||||||
'packages/mosaic/framework/tools/quality/scripts/test-upgrade-durable-snapshot.sh',
|
|
||||||
'packages/mosaic/framework/tools/quality/scripts/test-upgrade-rollback.sh',
|
|
||||||
'packages/mosaic/framework/tools/tmux/test-send-message-socket.sh',
|
|
||||||
'packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh',
|
|
||||||
];
|
|
||||||
|
|
||||||
// These statuses are explicitly non-load-bearing or unreachable at designed input.
|
|
||||||
// They remain inventoried until the final #1099 tranche records every verdict.
|
|
||||||
const ACCEPTED = [
|
|
||||||
['tools/install.sh', 'mosaic-bak-', '|| true'],
|
|
||||||
['tools/install.sh', 'mosaicstack-mosaic-*.tgz', 'head -1'],
|
|
||||||
['tools/install.sh', 'mosaicstack-gateway-*.tgz', 'head -1'],
|
|
||||||
['scripts/agent/session-start.sh', 'docs/scratchpads/*.md', '|| true'],
|
|
||||||
[
|
|
||||||
'packages/mosaic/framework/templates/repo/scripts/agent/session-start.sh',
|
|
||||||
'docs/scratchpads/*.md',
|
|
||||||
'|| true',
|
|
||||||
],
|
|
||||||
];
|
|
||||||
|
|
||||||
const earlyExit =
|
|
||||||
/(?<!\|)\|(?!\|)[^;\n]*(?:grep\b[^;\n]*(?:-[A-Za-z]*q|--quiet|-m\s*1)|head\b(?:\s|$))/;
|
|
||||||
|
|
||||||
function scan(sources) {
|
|
||||||
const found = [];
|
|
||||||
for (const [file, rawSource] of sources) {
|
|
||||||
const source = rawSource.replace(/\\\n\s*/g, ' ');
|
|
||||||
for (const rawLine of source.split('\n')) {
|
|
||||||
const line = rawLine.trim();
|
|
||||||
if (!earlyExit.test(line)) continue;
|
|
||||||
const accepted = ACCEPTED.some(
|
|
||||||
([acceptedFile, ...fragments]) =>
|
|
||||||
acceptedFile === file && fragments.every((item) => line.includes(item)),
|
|
||||||
);
|
|
||||||
if (!accepted) found.push(`${file}:${line}`);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return found;
|
|
||||||
}
|
|
||||||
|
|
||||||
async function currentSources() {
|
|
||||||
return Promise.all(
|
|
||||||
TARGETS.map(async (file) => [file, await readFile(new URL(file, ROOT), 'utf8')]),
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
async function assertBaselineFixture(file, expectedCount, expectedUnique = expectedCount) {
|
|
||||||
const baseline = JSON.parse(await readFile(new URL(file, ROOT), 'utf8'));
|
|
||||||
assert.equal(baseline.length, expectedCount);
|
|
||||||
assert.equal(new Set(baseline).size, expectedUnique);
|
|
||||||
const fixtureSources = baseline.map((site) => {
|
|
||||||
const separator = site.indexOf(':');
|
|
||||||
assert.ok(separator > 0, `invalid baseline site: ${site}`);
|
|
||||||
return [site.slice(0, separator), site.slice(separator + 1)];
|
|
||||||
});
|
|
||||||
assert.deepEqual(scan(fixtureSources), baseline);
|
|
||||||
}
|
|
||||||
|
|
||||||
test('the registered runtime baseline denominator is exactly 26 unsafe sites', async () => {
|
|
||||||
await assertBaselineFixture(
|
|
||||||
'scripts/fixtures/pipefail-early-exit-baseline.json',
|
|
||||||
EXPECTED_BASELINE_SITES,
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
test('the registered test baseline denominator is exactly 22 unsafe sites', async () => {
|
|
||||||
await assertBaselineFixture(
|
|
||||||
'scripts/fixtures/pipefail-early-exit-test-baseline.json',
|
|
||||||
EXPECTED_TEST_BASELINE_SITES,
|
|
||||||
21,
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
test('load-bearing pipefail paths do not pipe into early-exiting consumers', async () => {
|
|
||||||
assert.deepEqual(scan(await currentSources()), []);
|
|
||||||
});
|
|
||||||
|
|
||||||
test('gateway verify capability preserves the complete help-probe truth table', async () => {
|
|
||||||
const directory = await mkdtemp(path.join(tmpdir(), 'gateway-help-probe-'));
|
|
||||||
const mosaic = path.join(directory, 'mosaic');
|
|
||||||
const probe = new URL('tools/e2e-gateway-verify-supported.sh', ROOT).pathname;
|
|
||||||
try {
|
|
||||||
await writeFile(
|
|
||||||
mosaic,
|
|
||||||
'#!/usr/bin/env bash\nprintf \'%s\\n\' "${MOCK_HELP_OUTPUT:-}"\nexit "${MOCK_HELP_RC:-0}"\n',
|
|
||||||
);
|
|
||||||
await chmod(mosaic, 0o755);
|
|
||||||
const run = (rc, output) =>
|
|
||||||
spawnSync('bash', [probe], {
|
|
||||||
env: {
|
|
||||||
...process.env,
|
|
||||||
PATH: `${directory}:${process.env.PATH}`,
|
|
||||||
MOCK_HELP_RC: String(rc),
|
|
||||||
MOCK_HELP_OUTPUT: output,
|
|
||||||
},
|
|
||||||
}).status;
|
|
||||||
|
|
||||||
assert.equal(run(0, 'commands: verify'), 0);
|
|
||||||
assert.equal(run(0, 'commands: install'), 1);
|
|
||||||
assert.equal(run(1, 'commands: verify'), 1);
|
|
||||||
} finally {
|
|
||||||
await rm(directory, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
test('board-history preserves non-git data-dir as a non-detectable result', async () => {
|
|
||||||
const directory = await mkdtemp(path.join(tmpdir(), 'reflect-board-non-git-'));
|
|
||||||
try {
|
|
||||||
await writeFile(path.join(directory, 'task.json'), '{}\n');
|
|
||||||
const result = spawnSync(
|
|
||||||
'bash',
|
|
||||||
[
|
|
||||||
new URL('scripts/analysis/reflect-board-history.sh', ROOT).pathname,
|
|
||||||
'--data-dir',
|
|
||||||
directory,
|
|
||||||
],
|
|
||||||
{ encoding: 'utf8' },
|
|
||||||
);
|
|
||||||
assert.equal(result.status, 0, result.stderr);
|
|
||||||
assert.match(result.stdout, /"done_tasks": 1/);
|
|
||||||
assert.match(result.stdout, /"detectable_outcomes": 0/);
|
|
||||||
} finally {
|
|
||||||
await rm(directory, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
@@ -1,10 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# Exit 0 only when the capability probe itself succeeds and advertises verify.
|
|
||||||
# A failed help command and a successful response without verify are both
|
|
||||||
# unsupported, matching the historical e2e-install-test.sh conditional.
|
|
||||||
set -uo pipefail
|
|
||||||
|
|
||||||
gateway_help_rc=0
|
|
||||||
gateway_help="$(mosaic gateway --help 2>&1)" || gateway_help_rc=$?
|
|
||||||
[[ "$gateway_help_rc" -eq 0 ]] || exit 1
|
|
||||||
grep -q 'verify' <<<"$gateway_help"
|
|
||||||
@@ -136,7 +136,7 @@ fi
|
|||||||
echo "=== [inner] Running mosaic gateway verify ==="
|
echo "=== [inner] Running mosaic gateway verify ==="
|
||||||
# `gateway verify` was added in feat/mosaic-first-run-ux.
|
# `gateway verify` was added in feat/mosaic-first-run-ux.
|
||||||
# If the installed version pre-dates this, skip gracefully.
|
# If the installed version pre-dates this, skip gracefully.
|
||||||
if ! bash /repo/tools/e2e-gateway-verify-supported.sh; then
|
if ! mosaic gateway --help 2>&1 | grep -q 'verify'; then
|
||||||
echo "[SKIP] 'mosaic gateway verify' not available in installed version ${INSTALLED_VERSION}."
|
echo "[SKIP] 'mosaic gateway verify' not available in installed version ${INSTALLED_VERSION}."
|
||||||
echo "[SKIP] This command was added in the feat/mosaic-first-run-ux release."
|
echo "[SKIP] This command was added in the feat/mosaic-first-run-ux release."
|
||||||
echo "[SKIP] Re-run after the new version is published to validate this step."
|
echo "[SKIP] Re-run after the new version is published to validate this step."
|
||||||
|
|||||||
+4
-8
@@ -308,17 +308,13 @@ ensure_monorepo() {
|
|||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Gitea archives extract to exactly one <repo-name>/ inside the work dir.
|
# Gitea archives extract to <repo-name>/ inside the work dir
|
||||||
# Read the complete population so a malformed multi-root archive reaches the
|
EXTRACTED_DIR="$(find "$WORK_DIR" -maxdepth 1 -mindepth 1 -type d | head -1)"
|
||||||
# named diagnostic instead of aborting on an upstream SIGPIPE under pipefail.
|
if [[ -z "$EXTRACTED_DIR" ]] || [[ ! -d "$EXTRACTED_DIR" ]]; then
|
||||||
local -a extracted_dirs=()
|
fail "Could not locate extracted source in archive."
|
||||||
mapfile -d '' -t extracted_dirs < <(find "$WORK_DIR" -maxdepth 1 -mindepth 1 -type d -print0)
|
|
||||||
if [[ "${#extracted_dirs[@]}" -ne 1 ]] || [[ ! -d "${extracted_dirs[0]:-}" ]]; then
|
|
||||||
fail "Could not locate exactly one extracted source directory in archive."
|
|
||||||
ls -la "$WORK_DIR" >&2
|
ls -la "$WORK_DIR" >&2
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
EXTRACTED_DIR="${extracted_dirs[0]}"
|
|
||||||
}
|
}
|
||||||
|
|
||||||
# Build @mosaicstack/mosaic + @mosaicstack/gateway from source and install both
|
# Build @mosaicstack/mosaic + @mosaicstack/gateway from source and install both
|
||||||
|
|||||||
@@ -35,10 +35,7 @@ export DARK_THRESHOLD_MS="${DARK_THRESHOLD_MS:-6000}"
|
|||||||
export AGENT_SLUGS="${AGENT_SLUGS:-alpha,bravo,charlie}"
|
export AGENT_SLUGS="${AGENT_SLUGS:-alpha,bravo,charlie}"
|
||||||
export VICTIM_SLUG="${VICTIM_SLUG:-charlie}"
|
export VICTIM_SLUG="${VICTIM_SLUG:-charlie}"
|
||||||
|
|
||||||
shopt -s nullglob
|
TSX_CLI="$(ls -d "${REPO}"/node_modules/.pnpm/tsx@*/node_modules/tsx/dist/cli.mjs 2>/dev/null | head -1)"
|
||||||
TSX_CANDIDATES=("${REPO}"/node_modules/.pnpm/tsx@*/node_modules/tsx/dist/cli.mjs)
|
|
||||||
shopt -u nullglob
|
|
||||||
TSX_CLI="${TSX_CANDIDATES[0]:-}"
|
|
||||||
if [[ -z "${TSX_CLI}" ]]; then
|
if [[ -z "${TSX_CLI}" ]]; then
|
||||||
echo "run.sh: tsx not found under node_modules — run pnpm install first" >&2
|
echo "run.sh: tsx not found under node_modules — run pnpm install first" >&2
|
||||||
exit 1
|
exit 1
|
||||||
|
|||||||
Reference in New Issue
Block a user