Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
dde5b84964 | ||
|
|
b6c3129d2e | ||
|
|
c25f5b8dae | ||
|
|
e25ef0373c |
No files matched your search
@@ -5411,3 +5411,9 @@ Row 299 (573, #1806, Gander, Filbert): before, the P10 band test timed a fault r
|
||||
2026-10-23T17:29:46Z | Gyro Vikunja571 sage-3542 Connections amendment | Branch gyro/editor-connections-design cut exactly from landed PRD1.17 30e6bb680; read REQ-LIB-5 in that PRD. Replaced stale J-b waits in parent and W4. Proposed W8 owns current authorized Markdown/DOCX links/backlinks list, labels, versioned refresh, leakage refusals and fixture tests. Build order under mos-1470/comment961 is W7 closed routing candidate, W8 landing, then W7 human first-real-import opening. No REQ-LIB-8 condition or acceptance change. Q234/mos-1363/S0 M1-M14 and post-10-27/MVP priority fixed. Static diff, twelve brief sections and append-only checks pass. No repo Node, tests, build, browser, queue mutation or live action. Fenton reviews after authorized docs branch push; Sage lands on approval.
|
||||
|
||||
2026-10-23T17:32:37Z | Gyro sage-3544 fenton-0016 N1/N2 delta | Before: W7 Gate/final real-conversion list omit the W8 build-order cross-reference and W8 human-view filtering cites agent settings. After: both locations explicitly put W8 landing before human opening as mos-1470 build order, not acceptance; comment/tracked-deletion links are not current story links and never appear in the human Connections view regardless of agent settings. New commit atop approved 5af060fb5, no amend. Static diff and append-only checks pass. Docs only, no repo Node/tests/live action. Fenton checks only this delta.
|
||||
|
||||
2026-10-23 | Beakley (88b97f65) | Row 217 #1718 takeover, before implementation | Clean base 45dca69f6 on beakley/row217. Recovering Launchpad handoff for citation guard, live settings, page store and runner retry. Acceptance is C2-06/design 5.2 plus sage-3595/3599/3602. Tracking agents/beakley/work/queue-217/BUILD.md; no product changes or Node/tests; Sage CLEAR required.
|
||||
|
||||
2026-10-23 | Beakley (88b97f65) | Row 217 #1718 untested draft checkpoint | Continued Launchpad e25ef0373; added runner retry/text/note implementation, pure protocol constants and sage-3640 approved single read-only mount, CLI documentation and new acceptance test files. Static checks caught missing projects compatibility, async request mutation and Git pathspec matching; bounded fixes and regression tests authored. git diff --check clean. No Node/test/mutant executed; Sage holds CLEAR. 283/216/285 dependency checks and all acceptance execution remain open. Packet agents/beakley/work/queue-217/MANIFEST.md.
|
||||
|
||||
2026-10-23 | Beakley (88b97f65) | Row 217 early-look follow-up, Untested | Webby 0939c0682 E1 adds ordinary mallory human-swap test; E2 adds stored trailer-derived agent/file event evidence; E6 creative-sender matrix and E7 runtime readRaw tests authored. Sage-3668/3670 accepts direct writer substitution because setter keys exclude replyLimits (organization.set exists, correcting review premise), and requires distinct availability refusal for E4. Real held-lock/socket and runner-reason regressions plus M5 authored before that production fix; expected RED awaits Sage CLEAR. No Node/tests/mutants, no old-test edits, no green claim.
|
||||
@@ -0,0 +1,157 @@
|
||||
# Row 217 — C2-06 citation guard, page store and runner retry
|
||||
|
||||
Owner: Beakley (88b97f65-97db-4f05-8c6e-081f92bc3501), assigned by Mos Q245.
|
||||
Issue: #1718. Reviewer: Webby. Branch: `beakley/row217`.
|
||||
Brief: `docs/plans/2026-10-20_case2-rows.md`, C2-06.
|
||||
Status: Untested draft on Launchpad handoff `e25ef0373`; targeted execution awaits Sage CLEAR.
|
||||
|
||||
## Plan and boundaries
|
||||
|
||||
Continue Launchpad's implementation from its handed-off ref. Complete the guard,
|
||||
live reply limits and M11 writer fence, broker page store and check evidence,
|
||||
CLI setter and runner retry/note behavior against the brief and design 5.2.
|
||||
Supply acceptance tests and mutants, then request Sage's test slot and Webby's
|
||||
review. Sage owns queue movement, gate and landing. Push only `beakley/*`, add
|
||||
commits without amend/force or attribution lines. No credential reads.
|
||||
|
||||
## Standing rulings received from Sage (sage-3610)
|
||||
|
||||
- sage-3595: stub supporting scope until row 283 lands, then rebase onto it and
|
||||
add real-fixture tests. Landing follows 283. `runtime.mjs` wiring approved.
|
||||
- Check evidence belongs in an `action.allowed` event in the same transaction
|
||||
as message insertion; no new event kind. Read the library at the cited commit.
|
||||
- In library businesses only, JSON over 32,768 characters gets the
|
||||
`request-too-large` retry. `role.claim` adds `library` only for a library business.
|
||||
- Store `check.citations` entries with `scope`, `agent`, and `file` (the file's
|
||||
last commit at the cited commit). On `thread.messages`, add `last` at the served
|
||||
tip, one git call per distinct path per read. Scope/agent are broker evidence.
|
||||
- sage-3599: optional `BusError.reason`, guard refusals only, capped at 300
|
||||
characters. Add bus server/client to manifest. Reasonless envelopes stay
|
||||
byte-identical.
|
||||
- `render.mjs` obsolete notice hits belong to row 225.
|
||||
- Node and tests require Sage CLEAR (sage-3610 supersedes the initial permission
|
||||
for targeted new tests). Full suites, webui builds and gate require shared slot.
|
||||
- Existing test edits require Mos GO through Sage; list every file and numstat
|
||||
below before seeking that approval.
|
||||
|
||||
## Recovery and coordination
|
||||
|
||||
Initial base `45dca69f6`, clean. `scripts/mosaic queue next beakley` refused:
|
||||
linked worktrees cannot run the queue. Reported to Sage/Mos in beakley-0001;
|
||||
Sage will change ownership at a queue gap. No queue files changed.
|
||||
Read AGENTS.md, agents/README.md, C2-06 brief, design 5.2 and the row 225 BUILD
|
||||
contract. Requested Launchpad handoff in beakley-0002. Its header timestamp was
|
||||
mistakenly typed ahead of the actual clock; sequence key identifies the message.
|
||||
|
||||
## Existing test changes
|
||||
|
||||
None yet. No tests or Node commands run.
|
||||
|
||||
|
||||
## Handoff adopted and independent work (2026-10-23)
|
||||
|
||||
Fast-forwarded `beakley/row217` to Launchpad `e25ef0373` on `45dca69f6`.
|
||||
The full original handoff/rulings remain at
|
||||
`agents/launchpad/work/queue-217/BUILD.md`. No handoff code was rebuilt from scratch.
|
||||
|
||||
Implemented the runner path: role.claim library switch; exact fixed texts; note
|
||||
inside JSON text with citations retained and no JSON clip; fixed texts defer
|
||||
notes; one same-session retry for guard codes and both existing size caps;
|
||||
retry fallback chosen from the second refusal; separate usage turn id for retry.
|
||||
Outside library businesses the existing send path remains intact.
|
||||
|
||||
Added the CLI README usage paragraph. New acceptance tests cover library parsing,
|
||||
real Git reachability/quotes/scope/origin, settings fallback, M11 direct writer
|
||||
and serialization, CLI dispatch, broker insert/check atomicity, live settings,
|
||||
page bounds/lifecycle, socket reasons, per-path last reads, request snapshots,
|
||||
and runner RESULT/typed send_message, fixed texts, long JSON and unslop behavior.
|
||||
These are authored evidence only: none has executed.
|
||||
|
||||
Static defects corrected locally: a missing projects object now means no library;
|
||||
the guard sends its captured request arguments after the asynchronous check;
|
||||
origin/last Git logs use literal pathspecs; a web quote can match any retained
|
||||
fetch of the cited URL. Each has new-file regression coverage.
|
||||
|
||||
## Scope additions and cross-row contract
|
||||
|
||||
- `packages/library/src/reply-protocol.mjs`: shared GUARD_CODES/FIXED_TEXTS,
|
||||
import-free, so runner imports do not reach host Git modules. guard.mjs
|
||||
reexports them to preserve Launchpad's API. Fethry confirmed no renderer import
|
||||
is needed when the renderer simply displays fixed texts as ordinary text.
|
||||
- `packages/seat/src/sandbox.mjs`: one RUNNER_FILES entry for that pure file,
|
||||
approved by sage-3640. No other mount change. The existing sandbox.test.mjs
|
||||
import-closure test must pass unchanged; seat joins the gate list.
|
||||
- Runtime hunks remain exactly Launchpad's import and library guard/limits/last
|
||||
adapters, plus library.limits.set dispatch. Drift checks wait on 216 and 285.
|
||||
- Status contract confirmed with Fethry (beakley-0004, fethry-0009): nested
|
||||
`replyLimits: {requireCitation, citationsPerReply, fallback: [keys],
|
||||
problem: "reply-limits-unreadable" | null}`. Check entries remain ordered
|
||||
`scope/agent/file`, plus `last` on reads; no changed boolean.
|
||||
|
||||
## Verification and remaining acceptance
|
||||
|
||||
- Static `git diff --check`: clean so far. No Node, suite, test or mutant run.
|
||||
- Existing test file edits: none (numstat 0/0 for every pre-existing test).
|
||||
All new test files are listed in manifest.r1.sha256; no Mos approval requested.
|
||||
- `mutants.py` is authored for isolated HEAD archives with green controls:
|
||||
M1 remove both writer fences; M2 compare incoming human; M3 split evidence
|
||||
from insert; M4 drop client reason. Not executed.
|
||||
- Still required: Sage CLEAR for targeted runs; fix first-run failures; supporting
|
||||
scope acceptance against row 283; 216 index/readLibrary fixture comparison;
|
||||
285/runtime drift check; full library/business/bus/cli/harness/seat suites and
|
||||
every scripts/test-*.sh on Sage's gate; mutant execution; Webby approval.
|
||||
- Before in-review, perform brief's obsolete-code/key search and report outside
|
||||
ownership hits to Sage. render.mjs/render.test.mjs hits belong to 225.
|
||||
- No queue changes, protected branch pushes, gate claims or acceptance claims.
|
||||
|
||||
Static obsolete-code/key search completed: only packages/library/src/render.mjs:6 and packages/library/tests/render.test.mjs:58 match no-cited-answer; both belong to row 225 per standing ruling. No owned-path hit. Repeat before in-review after dependency changes.
|
||||
|
||||
|
||||
## Webby early look 0939c0682 / webby-0249 and sage-3668/3670
|
||||
|
||||
This remains an untested draft. The follow-up adds tests only; production E4
|
||||
changes wait for the held-lock regression's first RED under Sage CLEAR.
|
||||
|
||||
- E1: added an ordinary actor `mallory` that sets both `human` to itself and
|
||||
`replyLimits`. The existing role/tester actors did not distinguish M2 because
|
||||
the actor-shape exclusions rejected them independently of the human comparison.
|
||||
M2 is still unrun; no kill claimed.
|
||||
- E2: added a real bus event assertion for `agent: "acme/scribe"` from a file's
|
||||
Mosaic-Agent trailer. The cited tip includes a later unrelated commit, so the
|
||||
event must store the file commit rather than the library tip. thread.messages
|
||||
must show `last === file` for that unchanged path. Supporting scope still waits
|
||||
for row 283's real fixture, as ruled.
|
||||
- E3: sage-3668 accepts direct writer.write tests under chief and tester actors
|
||||
as substitutes for the brief's setter cases (brief lines 483-491 at base
|
||||
45dca69f6). Correction to the early-look premise: organization.set DOES exist,
|
||||
broker.mjs:4701/4709, but ORGANIZATION_KEYS excludes replyLimits; instances.set
|
||||
also cannot carry it. Direct writes exercise the shared M11 boundary those
|
||||
setters cannot reach with that input. Sage confirmed the accurate reason in
|
||||
sage-3670; the unrelated actor case remains required.
|
||||
- E4: traced readSyncState -> withLibraryLock -> library-sync-busy after five
|
||||
seconds -> servedMirror catch-all -> null served -> misleading citation-invalid.
|
||||
New real-flock/socket test first proves the cite valid, holds the lock, asserts
|
||||
the exact citation-unavailable reason the agent receives, verifies no insert,
|
||||
and checks fixed fallback delivery and recovery after unlock. Additional tests
|
||||
distinguish malformed sync state from absent/new mirrors, and assert that the
|
||||
actual runner retry request contains that reason. These tests are expected RED
|
||||
until the fix. Planned production change: only an absent mirror or legitimate
|
||||
empty state yields null; other failures become GuardError citation-unavailable;
|
||||
bodies without path cites do not require the mirror lock. Add the code to
|
||||
GUARD_CODES so the runner sends the agent that reason on its one retry. Per
|
||||
sage-3670, existing four fallback bodies can remain only if that delivery is
|
||||
verified. M5 restores catch-all behavior; authored, not run.
|
||||
- E5: first-library-project selection is a Launchpad handoff implementation
|
||||
choice, not a validated rule that a business can only have one library.
|
||||
Cites into another library remain a limitation. No mapping/schema rule added.
|
||||
- E6: the broker's full guard table now runs as both coder and research.
|
||||
- E7: new citation-runtime.test.mjs starts the real runtime, reads limits from
|
||||
the real organization file, then changes, corrupts and removes that fixture
|
||||
file and checks library.status without replacing the library adapter.
|
||||
|
||||
No Node, tests or mutants ran. No test that predated row 217 changed.
|
||||
|
||||
|
||||
## Webby follow-up 192049c98 / webby-0258
|
||||
|
||||
E1, E2, E6 and E7 closed statically; no executed acceptance claimed. E3 correction and E5 limitation accepted. E4 tests accepted statically; real RED then production fix/green remain on hold for Sage CLEAR, with supporting scope waiting on 283. F1: citation-helpers status now uses its mutable served value, matching guard/last after setServed instead of reporting the original fixture commit. Test-only fixture correction, unrun. manifest.r3.sha256 records the updated helper; no production or old-test changes.
|
||||
@@ -0,0 +1,68 @@
|
||||
# Row 217 draft manifest — Untested
|
||||
|
||||
Issue #1718, Case 2 C2-06. Base `45dca69f6`, continued from Launchpad
|
||||
`e25ef0373`. This is a checkpoint for static review, not an in-review or
|
||||
acceptance claim. `manifest.r1.sha256` freezes the product and test files.
|
||||
|
||||
## Product scope
|
||||
|
||||
| Path | Change |
|
||||
| --- | --- |
|
||||
| packages/library/src/guard.mjs | Schema and seven checks, real cited-commit reads, origins and latest path commits |
|
||||
| packages/library/src/limits.mjs | Pure defaults, validation and conservative unreadable-file fallback |
|
||||
| packages/library/src/reply-protocol.mjs | Import-free guard codes and four runner fixed texts |
|
||||
| packages/library/src/index.mjs | Guard and limits exports |
|
||||
| packages/business/src/business.mjs | Permit any replyLimits value without widening another schema |
|
||||
| packages/business/src/organization.mjs | M11 fence on input and serialized output, human setter, raw live reader |
|
||||
| packages/bus/src/broker.mjs | Async pre-insert guard, atomic existing-kind check event, per-session pages, settings verb/status, optional library claim flag and read-time last evidence |
|
||||
| packages/bus/src/runtime.mjs | Inject guard/live limits/last and dispatch human setter (sage-3595) |
|
||||
| packages/bus/src/server.mjs | Await guarded sends and thread reads; optional guard reason (sage-3599) |
|
||||
| packages/bus/src/client.mjs | Preserve optional capped reason (sage-3599) |
|
||||
| packages/harness/src/runner.mjs | Library texts, one retry, JSON note/clip behavior and retry usage tracking |
|
||||
| packages/seat/src/sandbox.mjs | Exactly one read-only RUNNER_FILES addition for the pure protocol (sage-3640) |
|
||||
| packages/cli/src/limits.mjs | Human limits replies file command |
|
||||
| packages/cli/README.md | Reply settings usage |
|
||||
|
||||
No dependency, SQL schema, event kind, role authority or credential changes.
|
||||
The additional sandbox file carries only constants and has no imports.
|
||||
|
||||
## New tests and fixtures
|
||||
|
||||
| Path | Acceptance focus |
|
||||
| --- | --- |
|
||||
| packages/library/tests/guard.test.mjs | Seven table checks, cap boundaries, real Git origins/reachability/literal names, web quotes and limits fallback |
|
||||
| packages/business/tests/reply-limits.test.mjs | Human-only M11, old-human comparison, dotted agent identity, serialization, invalid values and raw reads |
|
||||
| packages/bus/tests/citation-helpers.mjs | Shared made-up repository and real broker fixture |
|
||||
| packages/bus/tests/citation-guard.test.mjs | Refusal insertion counts, transaction failure, live settings/status, page bounds, socket envelopes, file/last and async snapshot |
|
||||
| packages/cli/tests/reply-limits.test.mjs | Revision read, exact setter args and usage refusals |
|
||||
| packages/harness/tests/fixtures/citation-adapter.mjs | Scripted local harness, typed calls and unslop events |
|
||||
| packages/harness/tests/citation-runner.test.mjs | Every RESULT refusal and typed send_message, one retry, both size caps, plain multibyte answers, fixed texts and notes, old non-library behavior |
|
||||
|
||||
No existing test changed. Existing role.claim pins and the seat import-closure
|
||||
test stay untouched. Existing test numstat: none.
|
||||
|
||||
## Review focus and outstanding evidence
|
||||
|
||||
The check event and message insert must roll back together. Scope/agent/file
|
||||
come from Git; `last` is read once per distinct path per read. Guard refusals
|
||||
alone have a reason, bounded at 300 characters without quote or URL content.
|
||||
Captured arguments must be the ones inserted after async validation. Every
|
||||
plain or JSON length refusal shares the same single retry budget.
|
||||
|
||||
All tests and four isolated mutants are unrun pending Sage CLEAR. The supporting
|
||||
scope tests require row 283; the index-set comparison requires row 216; runtime
|
||||
drift must be checked against 216/285 before in-review. Landing follows 283.
|
||||
Full gate: library, business, bus, cli, harness and seat, plus every
|
||||
scripts/test-*.sh. Webby reviews the final tested manifest; Sage owns the gate,
|
||||
queue and landing. No push to a protected branch is authorized.
|
||||
|
||||
|
||||
## Early-look follow-up packet (manifest.r2.sha256)
|
||||
|
||||
Tests-only follow-up to Webby 0939c0682. Adds ordinary-actor M2 discrimination,
|
||||
stored agent/file evidence at an unrelated tip, creative-sender table coverage,
|
||||
and real runtime readRaw coverage. New citation-availability.test.mjs and runner
|
||||
availability case are intentionally unrun regressions for E4/sage-3668/3670.
|
||||
Production availability handling is not implemented yet: run that targeted RED
|
||||
on CLEAR before applying its fix, then rerun the same cases. M5 restores the
|
||||
catch-all. This packet is not ready for a green gate or manifest approval.
|
||||
@@ -0,0 +1,21 @@
|
||||
68c05644d29188b897e2d4695d8e7025e143d424d69a91bc07bc950f589d34bf packages/bus/src/broker.mjs
|
||||
ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8 packages/bus/src/client.mjs
|
||||
49e01e5e73cc3e830ad48a1b6b13fe4d06a38950f17847dc049b75209d6d3f0a packages/bus/src/runtime.mjs
|
||||
66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc packages/bus/src/server.mjs
|
||||
29114051a9bc5271e48978a9552d64b51b0ac4810f94a1f98940bf617b148df8 packages/bus/tests/citation-guard.test.mjs
|
||||
dc2d5836f10f591fc174aaf9587a3bff793b24ac29efe9ab68c6a9243d1d1c2c packages/bus/tests/citation-helpers.mjs
|
||||
825da818ba3cf45a4837f0f15a9c2cdba55a3d0bbb4479d55236f35799427c6f packages/business/src/business.mjs
|
||||
dbd79a4dfc926620d034b540f98f39336d81e4c79f214424c3cf19250c1d1f8d packages/business/src/organization.mjs
|
||||
bec04a894bc2af000548283ed7719e4de1c6d56688f42238a113390e9b2d3fbe packages/business/tests/reply-limits.test.mjs
|
||||
1f1bea250f694a2aae9b9dc856b3c3424ceca153ccf826c99ccb98e6ea9cd394 packages/cli/README.md
|
||||
2f291a71f490f2741edada7a3e3788500f8976a08eb8ab1411f6c5982f778260 packages/cli/src/limits.mjs
|
||||
f38af2d46d5f5f6388f599912507b94b87a0bf9dcc2104bb2187c38ee35118d5 packages/cli/tests/reply-limits.test.mjs
|
||||
6ad72b4245e0a66e32725941900c1ece64c2e5de2fb73d65c8e042b4f3a691a6 packages/harness/src/runner.mjs
|
||||
ec7ef0cbf493217eb9229895cae2fe7ef603f41913840e59a73220df387c81ca packages/harness/tests/citation-runner.test.mjs
|
||||
330bc71bf6c7e64d3ddb70440903d2d9acf7878d44a49d7e30c2352ee4c807ec packages/harness/tests/fixtures/citation-adapter.mjs
|
||||
0365114cf5773cbaa9fba196fbd1e773b2ec5ad2300c40231c357ca58884b9e3 packages/library/src/guard.mjs
|
||||
aaa8f7ba60a729a88a6ef57b3d5ff5a69bcf0e17b60e7db51a8dc5a697627b6c packages/library/src/index.mjs
|
||||
3e04fa25a64334d33ffbec704205b32cd01992f2d341e908f933a345199beee0 packages/library/src/limits.mjs
|
||||
c9e682eff87e822647921288d7fce0ebdc7b09f0a6dfdd6528f10249ae26e81b packages/library/src/reply-protocol.mjs
|
||||
dd056409712113eb9c1b70e29b21022f5b30df6ffbfb2658e293edd6ec7195c7 packages/library/tests/guard.test.mjs
|
||||
2f3ec99129d16394d4458e252b9cba4e38ff66cd9393e3889f8afc3140e15a8e packages/seat/src/sandbox.mjs
|
||||
@@ -0,0 +1,23 @@
|
||||
68c05644d29188b897e2d4695d8e7025e143d424d69a91bc07bc950f589d34bf packages/bus/src/broker.mjs
|
||||
ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8 packages/bus/src/client.mjs
|
||||
49e01e5e73cc3e830ad48a1b6b13fe4d06a38950f17847dc049b75209d6d3f0a packages/bus/src/runtime.mjs
|
||||
66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc packages/bus/src/server.mjs
|
||||
cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9 packages/bus/tests/citation-availability.test.mjs
|
||||
8dc344b8a905c58d544b031ca84adb7eb869d9de88eb8e6b0fc1d9190702a38a packages/bus/tests/citation-guard.test.mjs
|
||||
62d8a55945d4b700e22c8c49b6420a5e25719d266901a2ad20c72514735e65e9 packages/bus/tests/citation-helpers.mjs
|
||||
168dcac99d9bfdfdf5ff0eaa2c0fff91595b351b4d0092dc299532c9c32869f0 packages/bus/tests/citation-runtime.test.mjs
|
||||
825da818ba3cf45a4837f0f15a9c2cdba55a3d0bbb4479d55236f35799427c6f packages/business/src/business.mjs
|
||||
dbd79a4dfc926620d034b540f98f39336d81e4c79f214424c3cf19250c1d1f8d packages/business/src/organization.mjs
|
||||
4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f packages/business/tests/reply-limits.test.mjs
|
||||
1f1bea250f694a2aae9b9dc856b3c3424ceca153ccf826c99ccb98e6ea9cd394 packages/cli/README.md
|
||||
2f291a71f490f2741edada7a3e3788500f8976a08eb8ab1411f6c5982f778260 packages/cli/src/limits.mjs
|
||||
f38af2d46d5f5f6388f599912507b94b87a0bf9dcc2104bb2187c38ee35118d5 packages/cli/tests/reply-limits.test.mjs
|
||||
6ad72b4245e0a66e32725941900c1ece64c2e5de2fb73d65c8e042b4f3a691a6 packages/harness/src/runner.mjs
|
||||
a5ef1b65230239a7baf6d0e8f2b8a51c0516348c7c4339a55b3f0a1a6ff531ba packages/harness/tests/citation-runner.test.mjs
|
||||
330bc71bf6c7e64d3ddb70440903d2d9acf7878d44a49d7e30c2352ee4c807ec packages/harness/tests/fixtures/citation-adapter.mjs
|
||||
0365114cf5773cbaa9fba196fbd1e773b2ec5ad2300c40231c357ca58884b9e3 packages/library/src/guard.mjs
|
||||
aaa8f7ba60a729a88a6ef57b3d5ff5a69bcf0e17b60e7db51a8dc5a697627b6c packages/library/src/index.mjs
|
||||
3e04fa25a64334d33ffbec704205b32cd01992f2d341e908f933a345199beee0 packages/library/src/limits.mjs
|
||||
c9e682eff87e822647921288d7fce0ebdc7b09f0a6dfdd6528f10249ae26e81b packages/library/src/reply-protocol.mjs
|
||||
dd056409712113eb9c1b70e29b21022f5b30df6ffbfb2658e293edd6ec7195c7 packages/library/tests/guard.test.mjs
|
||||
2f3ec99129d16394d4458e252b9cba4e38ff66cd9393e3889f8afc3140e15a8e packages/seat/src/sandbox.mjs
|
||||
@@ -0,0 +1,23 @@
|
||||
68c05644d29188b897e2d4695d8e7025e143d424d69a91bc07bc950f589d34bf packages/bus/src/broker.mjs
|
||||
ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8 packages/bus/src/client.mjs
|
||||
49e01e5e73cc3e830ad48a1b6b13fe4d06a38950f17847dc049b75209d6d3f0a packages/bus/src/runtime.mjs
|
||||
66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc packages/bus/src/server.mjs
|
||||
cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9 packages/bus/tests/citation-availability.test.mjs
|
||||
8dc344b8a905c58d544b031ca84adb7eb869d9de88eb8e6b0fc1d9190702a38a packages/bus/tests/citation-guard.test.mjs
|
||||
8a2d4b636f8d4f926c484254c33ecf7b7e4722acef3250d2730593984d5ac06b packages/bus/tests/citation-helpers.mjs
|
||||
168dcac99d9bfdfdf5ff0eaa2c0fff91595b351b4d0092dc299532c9c32869f0 packages/bus/tests/citation-runtime.test.mjs
|
||||
825da818ba3cf45a4837f0f15a9c2cdba55a3d0bbb4479d55236f35799427c6f packages/business/src/business.mjs
|
||||
dbd79a4dfc926620d034b540f98f39336d81e4c79f214424c3cf19250c1d1f8d packages/business/src/organization.mjs
|
||||
4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f packages/business/tests/reply-limits.test.mjs
|
||||
1f1bea250f694a2aae9b9dc856b3c3424ceca153ccf826c99ccb98e6ea9cd394 packages/cli/README.md
|
||||
2f291a71f490f2741edada7a3e3788500f8976a08eb8ab1411f6c5982f778260 packages/cli/src/limits.mjs
|
||||
f38af2d46d5f5f6388f599912507b94b87a0bf9dcc2104bb2187c38ee35118d5 packages/cli/tests/reply-limits.test.mjs
|
||||
6ad72b4245e0a66e32725941900c1ece64c2e5de2fb73d65c8e042b4f3a691a6 packages/harness/src/runner.mjs
|
||||
a5ef1b65230239a7baf6d0e8f2b8a51c0516348c7c4339a55b3f0a1a6ff531ba packages/harness/tests/citation-runner.test.mjs
|
||||
330bc71bf6c7e64d3ddb70440903d2d9acf7878d44a49d7e30c2352ee4c807ec packages/harness/tests/fixtures/citation-adapter.mjs
|
||||
0365114cf5773cbaa9fba196fbd1e773b2ec5ad2300c40231c357ca58884b9e3 packages/library/src/guard.mjs
|
||||
aaa8f7ba60a729a88a6ef57b3d5ff5a69bcf0e17b60e7db51a8dc5a697627b6c packages/library/src/index.mjs
|
||||
3e04fa25a64334d33ffbec704205b32cd01992f2d341e908f933a345199beee0 packages/library/src/limits.mjs
|
||||
c9e682eff87e822647921288d7fce0ebdc7b09f0a6dfdd6528f10249ae26e81b packages/library/src/reply-protocol.mjs
|
||||
dd056409712113eb9c1b70e29b21022f5b30df6ffbfb2658e293edd6ec7195c7 packages/library/tests/guard.test.mjs
|
||||
2f3ec99129d16394d4458e252b9cba4e38ff66cd9393e3889f8afc3140e15a8e packages/seat/src/sandbox.mjs
|
||||
@@ -0,0 +1,68 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Run only on Sage CLEAR. Mutate isolated HEAD archives; never edit the checkout.
|
||||
|
||||
A green control run is required before each negative result counts as a kill.
|
||||
Usage: python3 agents/beakley/work/queue-217/mutants.py OUTPUT_DIRECTORY
|
||||
"""
|
||||
from pathlib import Path
|
||||
import io
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import tarfile
|
||||
import tempfile
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[4]
|
||||
OUT = Path(sys.argv[1]).resolve()
|
||||
OUT.mkdir(parents=True, exist_ok=True)
|
||||
WRITER = "packages/business/src/organization.mjs"
|
||||
BROKER = "packages/bus/src/broker.mjs"
|
||||
CLIENT = "packages/bus/src/client.mjs"
|
||||
ATOMIC = "if (check) this.#event(s, 'action.allowed', { action: 'message.checked', message: mid, check }, mid, checkEventId(mid));"
|
||||
REENTER = "return this.#reenter(cap, s, { verb: 'message.send', args }, check);"
|
||||
SPLIT = """const result = this.#reenter(cap, s, { verb: 'message.send', args }, check);
|
||||
if (check) this.#store.transaction(() => this.#event(s, 'action.allowed', { action: 'message.checked', message: result.id, check }, result.id, checkEventId(result.id)));
|
||||
return result;"""
|
||||
MUTANTS = [
|
||||
("M1-writer-fence", [(WRITER, " replyLimitsFence(old, document, actor);", ""),
|
||||
(WRITER, " replyLimitsFence(old, written, actor);", "")],
|
||||
["packages/business/tests/reply-limits.test.mjs"]),
|
||||
("M2-incoming-human", [(WRITER, "actor === old.human", "actor === document.human")],
|
||||
["packages/business/tests/reply-limits.test.mjs"]),
|
||||
("M3-split-check-transaction", [(BROKER, ATOMIC, ""), (BROKER, REENTER, SPLIT)],
|
||||
["packages/bus/tests/citation-guard.test.mjs"]),
|
||||
("M5-hide-library-unavailable", [("packages/library/src/guard.mjs",
|
||||
"refuse('citation-unavailable', 'The library is busy or unavailable. Retry the answer when the library is available.');",
|
||||
"served = null;")], ["packages/bus/tests/citation-availability.test.mjs"]),
|
||||
("M4-drop-client-reason", [(CLIENT, "new BusError(r.error, typeof r.reason === 'string' ? r.reason.slice(0, 300) : undefined)", "new BusError(r.error)")],
|
||||
["packages/bus/tests/citation-guard.test.mjs"]),
|
||||
]
|
||||
|
||||
archive = subprocess.check_output(["git", "archive", "HEAD", "packages", "roles", "scripts", "tools", "docs", "package.json", "RELEASE"], cwd=ROOT)
|
||||
summary = []
|
||||
for name, changes, tests in MUTANTS:
|
||||
with tempfile.TemporaryDirectory(prefix="row217-mutant-") as directory:
|
||||
work = Path(directory)
|
||||
with tarfile.open(fileobj=io.BytesIO(archive)) as source:
|
||||
source.extractall(work, filter="data")
|
||||
modules = ROOT / "node_modules"
|
||||
if modules.exists():
|
||||
os.symlink(modules.resolve(), work / "node_modules", target_is_directory=True)
|
||||
cmd = ["node", "--test", *tests]
|
||||
with (OUT / f"{name}-control.log").open("w") as log:
|
||||
control = subprocess.run(cmd, cwd=work, stdout=log, stderr=subprocess.STDOUT, timeout=120)
|
||||
if control.returncode:
|
||||
raise SystemExit(f"{name}: control RED, no mutant result claimed")
|
||||
for file, before, after in changes:
|
||||
path = work / file
|
||||
text = path.read_text()
|
||||
if text.count(before) != 1:
|
||||
raise SystemExit(f"{name}: expected exactly one mutation anchor in {file}")
|
||||
path.write_text(text.replace(before, after))
|
||||
with (OUT / f"{name}.log").open("w") as log:
|
||||
mutant = subprocess.run(cmd, cwd=work, stdout=log, stderr=subprocess.STDOUT, timeout=120)
|
||||
if mutant.returncode == 0:
|
||||
raise SystemExit(f"{name}: SURVIVED")
|
||||
summary.append(f"{name}: killed (control green, mutant exit {mutant.returncode})")
|
||||
(OUT / "summary.txt").write_text("\n".join(summary) + "\n")
|
||||
print(summary[-1], flush=True)
|
||||
@@ -0,0 +1,124 @@
|
||||
# Row 217 (Case 2 C2-06): build notes
|
||||
|
||||
Brief: docs/plans/2026-10-20_case2-rows.md, section C2-06, at base 45dca69f6.
|
||||
Builder: Launchpad until 2026-10-23 19:09Z. Then Mos moved coding to Codex seats (mos-1500, Q245) and
|
||||
the row went to Beakley on beakley/row217.
|
||||
|
||||
## State at handoff
|
||||
|
||||
All code in this commit is UNTESTED. No node, no test and no mutant has run on it. No test file is written.
|
||||
`packages/harness/src/runner.mjs` is not started.
|
||||
|
||||
Done, untested:
|
||||
- `packages/library/src/limits.mjs` (new, pure): `REPLY_LIMITS`, `resolveReplyLimits(read)` gives
|
||||
`{requireCitation, citationsPerReply, fallback, unreadable}`, `checkReplyLimits(value)` gives a clone or null.
|
||||
An unreadable business file forces `requireCitation` true. A key falls back to its default when
|
||||
`replyLimits` is not an object or the key holds an invalid value.
|
||||
- `packages/library/src/guard.mjs` (new): `GUARD_CODES` in design 5.2's table order, `FIXED_TEXTS`,
|
||||
`WEB_CITE_DEFINITIONS`, `REASON_MAX` (300), `GuardError`, `parseReply`, `checkReply`, `libraryReader`,
|
||||
`lastCommits`, `guardReply`.
|
||||
- `packages/library/src/index.mjs`: exports for both.
|
||||
- `packages/business/src/business.mjs`: `replyLimits` is a known top key. The validated output doesn't carry it.
|
||||
- `packages/business/src/organization.mjs`: the M11 fence `replyLimitsFence(old, document, actor)` compares
|
||||
against `old.human`, refuses the tester and any `<definition>.<instance>` of `old.roles`, and is called for
|
||||
both `document` and `written`. `setReplyLimits` and `readRaw` are exported.
|
||||
- `packages/bus/src/broker.mjs`: the guard call, the page store, the check event, `library.limits.set`,
|
||||
`library.status` gains `replyLimits`, `role.claim` gains `library`, `thread.messages` gains `check` and `last`.
|
||||
- `packages/bus/src/server.mjs`, `client.mjs`: `BusError.reason` (sage-3599).
|
||||
- `packages/bus/src/runtime.mjs`: guard deps and the `library.limits.set` dispatch.
|
||||
- `packages/cli/src/limits.mjs`: `limits replies --file LIMITS`.
|
||||
|
||||
Left:
|
||||
- `packages/harness/src/runner.mjs`: the C2-07 runner work (see "Runner plan" below).
|
||||
- `packages/cli/README.md`: a line for `limits replies`.
|
||||
- Every test in the brief and the rulings below, then the mutants.
|
||||
- The rebases onto rows 283, 216 and 285, with the drift checks below.
|
||||
- This file's gate results and the manifest.
|
||||
|
||||
## Rulings in force
|
||||
|
||||
sage-3595:
|
||||
1. Supporting scope: a stub classify test now. Before in-review, rebase onto row 283's landing
|
||||
(honker/row283-build bd2c1c4ea when ruled) and add two real-fixture tests: a supporting cite with
|
||||
`as: "canon"` refuses `playground-cited-as-canon`, and the stored check result names `supporting`.
|
||||
2. runtime.mjs is approved for the guard wiring and the one `library.limits.set` branch. List its hunks here,
|
||||
name it in the manifest, and drift-check it after the 216 and 285 rebases.
|
||||
3. The check result is an `action.allowed` event with `action: "message.checked"`. The events kind CHECK at
|
||||
`packages/bus/src/migrations/3b.sql:9` has no `message.checked`, so a new kind would be a schema step.
|
||||
The event and the message INSERT share one transaction: a mutant that splits them must fail.
|
||||
4. readLibrary at the cited commit stands in for the C2-05a index. On the 216 rebase, compare 216's index
|
||||
set with readLibrary's for the fixture and record the result here.
|
||||
5. The retry is for a library business only. Tests: a JSON body between 32,768 characters and 64 KiB gets
|
||||
the retry; outside a library business nothing changes.
|
||||
6. Old `role.claim` pins stay as they are.
|
||||
7. `render.mjs:6` and `render.test.mjs:58` belong to row 225. Leave them.
|
||||
8. `thread.messages` rows that carry `check` get `last` per path cite: the file's last commit at the served
|
||||
tip, one git call per distinct path per read. Test with a fixture file committed after the cite.
|
||||
|
||||
sage-3599: `BusError` gets an optional `reason`. Only the citation guard's refusals set it. The envelope
|
||||
carries `reason` only when it is set. It is the guard's own text, never a quote, file text, url or a path
|
||||
other than the cited one, at most 300 characters. Tests: a guard refusal reaches the runner with code and
|
||||
reason; a refusal without a reason has an envelope byte-identical to today's, checked against an existing
|
||||
pin; a mutant that drops the client.mjs pass-through fails.
|
||||
|
||||
sage-3602: store `file` per path cite from the same git log call as the trailer. Test with a cited commit
|
||||
that didn't touch the file, so `file` differs from the cited commit, and `last` equals `file`.
|
||||
|
||||
## The check-result contract with row 225 (launchpad-0118, launchpad-0120, morgana-0200, sage-3596)
|
||||
|
||||
- Stored on the `message.checked` event: `{citations: [...]}` in body order.
|
||||
- A path cite: `{scope, agent, file}`. `scope` is the classify scope. `agent` is the cite's file's last
|
||||
commit's `Mosaic-Agent` trailer at the cited commit, or null. `file` is that commit's 40-hex id, or null.
|
||||
- A url cite: `{scope: "web", agent: null}`.
|
||||
- On `thread.messages`, each path cite gains `last`: the file's last commit at the served tip (40-hex or null).
|
||||
The Console compares `last` with `file`.
|
||||
- Rows without `check` are unchanged. No `changed` boolean. The webui passes rows through unchanged.
|
||||
|
||||
## Hunks outside the brief's file list
|
||||
|
||||
- `packages/bus/src/runtime.mjs`: imports `setReplyLimits`; the library deps gain `guard`, `replyLimits`
|
||||
(organizationWriter `readRaw`, or `{readable: false}` with no organization), `last` and `GuardError`;
|
||||
the organization dispatch gains `library.limits.set`.
|
||||
- `packages/bus/src/server.mjs`: a `refusal(e, other)` helper above serve's doc comment builds every
|
||||
BusError envelope and adds `reason` only when set. The synchronous request path accepts a Promise result
|
||||
(the guard is async), with a 120 s timeout, and releases `own` when it settles.
|
||||
- `packages/bus/src/client.mjs`: `new BusError(r.error, reason)` with `reason` a string cut at 300.
|
||||
|
||||
## Decisions and their tradeoffs
|
||||
|
||||
- The guard runs async outside the SQL transaction, then re-enters request() through `#guardPass`, so
|
||||
message.send's insert and the check event stay one synchronous transaction.
|
||||
- The guard runs before message.send's own checks, so a guard code can come before an authority code.
|
||||
- The check event id is derived from the message id (a UUID-shaped sha256), so `thread.messages` finds it
|
||||
through the unique index on `events.id`.
|
||||
- With no organization configured, `replyLimits` reads as unreadable, so it fails closed.
|
||||
- With more than one library project, the guard uses the first in the business file's order.
|
||||
- A library business without guard deps refuses guarded sends with `project-not-configured`.
|
||||
- The page store is per cap: 20 pages of 200 KB, kept only in a library business, dropped at session
|
||||
delete or disconnect and at run end.
|
||||
- The CLI `replies` verb reads the revision itself from `limits`.
|
||||
- Guard reasons never carry a url or a quote (sage-3599).
|
||||
|
||||
## Runner plan (not built)
|
||||
|
||||
`role.claim`'s reply is discarded at `runner.mjs:462`; keep it and read `library === true`. In a library
|
||||
business, at the reply site (`runner.mjs:582-587`):
|
||||
- Fixed texts `(the session gave no answer)` and `(the turn failed)`; the reason stays in the run log.
|
||||
A fixed text goes with no note, and `unslop.sent()` is not called, so the note waits.
|
||||
- A body that parses as a JSON object with a string `text` gets `unslop.note()` appended to `text`, is
|
||||
serialized again and is never clipped. A plain body keeps `clip(body) + unslop.note()`.
|
||||
- On a refusal whose code is in `GUARD_CODES`, or `request-too-large` from the client, or the broker's
|
||||
`invalid-request` from `string(a.body, 32768)` for a body over 32,768 characters (ruling 5; the runner
|
||||
can tell it by the body length it sent), run one new turn in the same
|
||||
session naming the code and `err.reason`, or the 64 KiB limit. Bracket it with usage like other turns.
|
||||
- After the retry: a table code sends `(no answer passed the citation check)`, too large sends
|
||||
`(the answer was too long to send)`. One retry per answer, whatever the cause.
|
||||
- `runTurn`'s output buffer holds up to 4 * BODY_MAX characters, so a reply over 64 KiB can reach the send.
|
||||
- Outside a library business nothing changes.
|
||||
|
||||
## Mutants planned
|
||||
|
||||
- The M11 writer check removed.
|
||||
- `document.human` compared instead of `old.human`.
|
||||
- The check event split from the insert transaction.
|
||||
- The client.mjs reason pass-through dropped.
|
||||
@@ -1593,3 +1593,5 @@ are never rewritten or removed; corrections are new entries.
|
||||
2026-10-23T17:48:43Z | Scrooge (629b6cd3) | Row 252 Console inbox Approve and Deny (#1753) | Rebased onto 306 landing as 580037105 (range-diff all =), slot run bus 907/0 webui 410/0 cli 943/0, in-review revs 3608/3609, Webby r1 APPROVE, J1-J19 specs to Sage; Sage landed 45ea3fa0d (done rev 3616). Part 1 mutant results were never in BUILD.md; they went to Sage by T3 (scrooge-0252-mutant-specs).
|
||||
2026-10-23 | Sage (1ef1e4f8) | Rows 308 and 252 landings, 571 Connections design amendment, Vikunja 597 | 308 (PRD 1.17, #1815) landed 30e6bb680 and 252 (#1753) landed 45ea3fa0d (replay of 580037105 onto 30e6bb680, range-diff all =), each after a full gate on the landed tree (252 also J1-J19, J11c and J18 equivalent); Gyro's 571 amendment (Fenton APPROVE) landed e8bb13df8; Vikunja 570, 435 and 597 done, canonical webui esbuild 0.28.2; queue revs 3589-3616 committed 59f013247
|
||||
2026-10-23 | Sage (1ef1e4f8) | Vikunja 571 W build rows; rows 13, 42, 257 and 289 check | Filed the design's ten W rows as queue rows 309-318 (revs 3617-3626, owners set to unassigned 3627-3636, queue commit 293b42fee pushed); Vikunja 571 done (comment 994). Row 13's candidate fd72d2689 is on refactor, gate is Monday's row 7 ledger run; 42 paused under mos-1184; 257 post-v1; 289 waits on 214 and 288. Slot released 17:56Z.
|
||||
|
||||
2026-10-23 | Beakley (88b97f65, Codex gpt-6.1-sol) | Row 217 #1718 takeover under Q245 | Registered beakley/row217; read brief/design and standing Sage rulings; awaiting Launchpad ref before implementation. Queue next refused linked worktree; reported to Sage. Untested, no Node/test run pending CLEAR.
|
||||
+134
-7
@@ -203,15 +203,26 @@ const canonical = (x) =>
|
||||
Number.isFinite(Date.parse(x)) &&
|
||||
new Date(x).toISOString() === x;
|
||||
export class BusError extends Error {
|
||||
constructor(code) {
|
||||
// C2-06 (sage-3599): only the citation guard's refusals carry a reason, and the envelope passes it on.
|
||||
constructor(code, reason) {
|
||||
super(code);
|
||||
this.code = code;
|
||||
if (reason !== undefined) this.reason = reason;
|
||||
}
|
||||
}
|
||||
const fail = (code) => {
|
||||
throw new BusError(code);
|
||||
};
|
||||
const object = (x) => x !== null && typeof x === 'object' && !Array.isArray(x);
|
||||
// C2-06 (design 5.2, B7): the page store keeps a session's last 20 broker fetches, 200 KB of text each.
|
||||
const PAGE_COUNT = 20;
|
||||
const PAGE_BYTES = 200 * 1024;
|
||||
// C2-06: the guard's check event takes an id derived from the message's, so a thread read finds it
|
||||
// through the unique index on events.id (there is none on subject).
|
||||
const checkEventId = (mid) => {
|
||||
const h = createHash('sha256').update('message.checked:' + mid).digest('hex');
|
||||
return `${h.slice(0, 8)}-${h.slice(8, 12)}-${h.slice(12, 16)}-${h.slice(16, 20)}-${h.slice(20, 32)}`;
|
||||
};
|
||||
const text = (x, max = 4096) => typeof x === 'string' && x.length > 0 && x.length <= max && !x.includes('\0');
|
||||
const id = (x) => text(x, 160) && /^[a-zA-Z0-9][a-zA-Z0-9_.:/-]*$/.test(x);
|
||||
function keys(x, allowed, required = []) {
|
||||
@@ -389,6 +400,11 @@ export class Broker {
|
||||
#credentialVerbs;
|
||||
#project;
|
||||
#library;
|
||||
// C2-06 (design 5.2, B7): cap -> the session's kept web.fetch pages, in a library business only.
|
||||
// In memory, dropped with the session.
|
||||
#pages = new Map();
|
||||
// C2-06: { s, check } while a guarded message.send or a thread.messages re-enters request().
|
||||
#guardPass = null;
|
||||
#usage;
|
||||
#limits;
|
||||
#harnessOn;
|
||||
@@ -1403,7 +1419,10 @@ export class Broker {
|
||||
this.#launcherReleased.delete(key);
|
||||
this.#accessRevoked.delete(key);
|
||||
for (const [cap, s] of this.#sessions)
|
||||
if (!s.human && !s.reader && s.business === record.business && s.run === record.run) this.#sessions.delete(cap);
|
||||
if (!s.human && !s.reader && s.business === record.business && s.run === record.run) {
|
||||
this.#sessions.delete(cap);
|
||||
this.#pages.delete(cap);
|
||||
}
|
||||
return this.#store.transaction(() => {
|
||||
const h = this.#own(session);
|
||||
const released = h?.op === 'claim' && h.holder_run === session.run;
|
||||
@@ -1485,6 +1504,7 @@ export class Broker {
|
||||
}
|
||||
disconnect(cap) {
|
||||
this.#sessions.delete(cap);
|
||||
this.#pages.delete(cap);
|
||||
}
|
||||
identity(cap) {
|
||||
const s = this.#session(cap);
|
||||
@@ -4666,10 +4686,19 @@ export class Broker {
|
||||
return this.#requestProjectFile(s, { verb: request.verb, args: structuredClone(args) });
|
||||
if (LIBRARY_VERBS.includes(request.verb))
|
||||
return this.#requestLibrary(s, { verb: request.verb, args: structuredClone(args) });
|
||||
// C2-06 (design 5.2): an agent's message to the human in a library business passes the citation
|
||||
// guard first, outside any transaction, and thread.messages adds each path cite's `last`. Both
|
||||
// then re-enter request() for the synchronous path below.
|
||||
if (this.#guardPass?.s !== s) {
|
||||
if (request.verb === 'message.send' && this.#guarded(s, args.to))
|
||||
return this.#guardedSend(cap, s, request, structuredClone(args));
|
||||
if (request.verb === 'thread.messages' && this.#libraryProject(s.business) && this.#library?.last)
|
||||
return this.#withLast(cap, s, request);
|
||||
}
|
||||
if (CREDENTIAL_VERBS.includes(request.verb)) return this.#requestCredential(s, request.verb, structuredClone(args));
|
||||
if (request.verb === 'instance.hire' || request.verb === 'instance.fire')
|
||||
return this.#chiefLifecycle(s, request.verb, structuredClone(args));
|
||||
if (["limits", "limits.set", "organization.set", "organization.revision", "plugins", "plugins.set", "instances", "instances.set", "routes", "routes.set", "veto.set"].includes(request.verb)) {
|
||||
if (["limits", "limits.set", "organization.set", "organization.revision", "plugins", "plugins.set", "instances", "instances.set", "routes", "routes.set", "veto.set", "library.limits.set"].includes(request.verb)) {
|
||||
// Row 123 (#1617, REQ-COS-1, REQ-LIMIT-1): organization.set is limits.set for a role whose
|
||||
// file lists organization.change. It takes the same keys, runs the same write path and
|
||||
// logs the same receipt; only the actor differs: the role definition and instance.
|
||||
@@ -4715,6 +4744,12 @@ export class Broker {
|
||||
keys(args, VETO_KEYS, VETO_KEYS);
|
||||
this.#human(s);
|
||||
this.#mayHuman(s, "veto.set", args.name);
|
||||
}
|
||||
// C2-06 M11: the human's replyLimits verb. The tester is refused by the gate above and an agent
|
||||
// session by human-required; the writer's fence refuses any other actor.
|
||||
else if (request.verb === "library.limits.set") {
|
||||
keys(args, ["revision", "replyLimits"], ["revision", "replyLimits"]);
|
||||
this.#human(s);
|
||||
} else {
|
||||
keys(args, ORGANIZATION_KEYS, ["revision"]);
|
||||
// Row 194 (D2.4, B7): the chief can't change a kept instance's model, as that replaces it at
|
||||
@@ -5138,7 +5173,14 @@ export class Broker {
|
||||
const context = { business: this.#business(s.business), project: args.project };
|
||||
let result;
|
||||
if (verb === 'library.file') result = await this.#library.readFile({ ...context, path: args.path });
|
||||
else if (verb === 'library.status') result = await this.#library.status(context);
|
||||
else if (verb === 'library.status') {
|
||||
result = await this.#library.status(context);
|
||||
// C2-06: the reply limits in force, read from the file now, and the keys that fell back.
|
||||
if (this.#library.replyLimits) {
|
||||
const { requireCitation, citationsPerReply, fallback, unreadable } = this.#library.replyLimits(s.business);
|
||||
result = { ...result, replyLimits: { requireCitation, citationsPerReply, fallback, problem: unreadable ? 'reply-limits-unreadable' : null } };
|
||||
}
|
||||
}
|
||||
else {
|
||||
// A fetch that did not move served still answers with the code, so the refusal is recorded.
|
||||
const { state, code } = await this.#library.sync(context, { accept: args.accept ?? null });
|
||||
@@ -5152,6 +5194,78 @@ export class Broker {
|
||||
throw this.#refused(s, Failure && error instanceof Failure ? new BusError(error.code) : error, request);
|
||||
}
|
||||
}
|
||||
// C2-06: the business's library project, the first in file order, or null.
|
||||
#libraryProject(business) {
|
||||
return Object.entries(this.#business(business).projects ?? {}).find(([, p]) => p.kind === 'library')?.[0] ?? null;
|
||||
}
|
||||
// C2-06 (design 5.2): every agent session's message to the human in a business with a library project
|
||||
// is guarded, whatever the sender's definition.
|
||||
#guarded(s, to) {
|
||||
return to === 'human' && !s.human && !s.tester && !s.user && !s.reader && !s.console && this.#libraryProject(s.business) !== null;
|
||||
}
|
||||
#reenter(cap, s, request, check) {
|
||||
this.#guardPass = { s, check };
|
||||
try {
|
||||
return this.request(cap, request);
|
||||
} finally {
|
||||
this.#guardPass = null;
|
||||
}
|
||||
}
|
||||
// As #requestProject: the git reads run outside any SQL transaction. A guard refusal is recorded with
|
||||
// its code and reaches the caller with the guard's reason; the send then runs, and stores the check
|
||||
// result in its own transaction.
|
||||
async #guardedSend(cap, s, request, args) {
|
||||
let check;
|
||||
try {
|
||||
this.#store.transaction(() => this.#agent(s));
|
||||
if (!this.#library?.guard || !this.#library?.replyLimits) fail('project-not-configured');
|
||||
if (typeof args.body !== 'string') fail('invalid-request');
|
||||
const business = this.#business(s.business);
|
||||
check = await this.#library.guard({ business, project: this.#libraryProject(s.business) }, args.body, {
|
||||
limits: this.#library.replyLimits(s.business),
|
||||
definition: business.roles[s.role]?.definition ?? null,
|
||||
pages: this.#pages.get(cap) ?? [],
|
||||
});
|
||||
} catch (e) {
|
||||
const Guard = this.#library?.GuardError;
|
||||
throw this.#refused(s, Guard && e instanceof Guard ? new BusError(e.code, e.reason) : e, request);
|
||||
}
|
||||
return this.#reenter(cap, s, { verb: 'message.send', args }, check);
|
||||
}
|
||||
// C2-06 (sage-3595, morgana-0200): each path cite of a checked row gains `last`, the file's last commit
|
||||
// at the served tip, one git call per distinct path. Rows without `check` are unchanged.
|
||||
async #withLast(cap, s, request) {
|
||||
const rows = this.#reenter(cap, s, request, null);
|
||||
if (!rows.some((m) => m.check)) return rows;
|
||||
const cites = (m) => {
|
||||
try {
|
||||
const c = JSON.parse(m.body).citations;
|
||||
return Array.isArray(c) ? c : [];
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
};
|
||||
let last = new Map();
|
||||
try {
|
||||
const paths = rows.filter((m) => m.check).flatMap((m) => cites(m).filter((c) => typeof c?.path === 'string').map((c) => c.path));
|
||||
last = await this.#library.last({ business: this.#business(s.business), project: this.#libraryProject(s.business) }, paths);
|
||||
} catch {
|
||||
last = new Map();
|
||||
}
|
||||
return rows.map((m) => {
|
||||
if (!m.check) return m;
|
||||
const body = cites(m);
|
||||
return { ...m, check: { ...m.check, citations: m.check.citations.map((c, i) =>
|
||||
c.scope === 'web' ? c : { ...c, last: last.get(body[i]?.path) ?? null }) } };
|
||||
});
|
||||
}
|
||||
// C2-06 (B7): a fetch's text, kept for url cites in a library business only.
|
||||
#keepPage(cap, s, url, page) {
|
||||
if (!this.#sessions.has(cap) || !this.#libraryProject(s.business) || typeof page?.text !== 'string') return;
|
||||
const text = Buffer.from(page.text).subarray(0, PAGE_BYTES).toString();
|
||||
const kept = { url, finalUrl: typeof page.finalUrl === 'string' ? page.finalUrl : null, text };
|
||||
this.#pages.set(cap, [...(this.#pages.get(cap) ?? []), kept].slice(-PAGE_COUNT));
|
||||
}
|
||||
// The eight task verbs reach the trusted S3 handler here. It runs outside any transaction, gets the
|
||||
// cap to authorize and record through authorize() and recordTask(); refusals are recorded as in request().
|
||||
async requestTask(cap, request, handler) {
|
||||
@@ -5235,6 +5349,7 @@ export class Broker {
|
||||
throw refuse(new BusError('web-failed'));
|
||||
}
|
||||
complete(out.summary);
|
||||
if (verb === 'web.fetch') this.#keepPage(cap, s, args.url, out.result);
|
||||
return { ...out.result, untrusted: true, notice: WEB_UNTRUSTED, source: verb };
|
||||
}
|
||||
// Row 210 (#1707, design D5): host.run, one sudo command on a registered host over ssh, for a
|
||||
@@ -5361,7 +5476,7 @@ export class Broker {
|
||||
by,
|
||||
);
|
||||
this.#routeSession(s.session);
|
||||
return { role: s.role, run: s.run, thread: s.thread };
|
||||
return { role: s.role, run: s.run, thread: s.thread, ...(this.#libraryProject(s.business) ? { library: true } : {}) };
|
||||
}
|
||||
if (
|
||||
this.#store.get(
|
||||
@@ -5385,7 +5500,8 @@ export class Broker {
|
||||
by,
|
||||
);
|
||||
this.#routeWaiting(s.business, s.role);
|
||||
return { role: s.role, run: s.run };
|
||||
// C2-06 (C2-07): the runner's switch to the library texts and retry. Absent elsewhere.
|
||||
return { role: s.role, run: s.run, ...(this.#libraryProject(s.business) ? { library: true } : {}) };
|
||||
}
|
||||
case 'role.release': {
|
||||
keys(a, []);
|
||||
@@ -5749,6 +5865,10 @@ export class Broker {
|
||||
if (this.#userThread(s) && to === 'human') fail('user-thread-human');
|
||||
this.#checkMessaging(s.business, this.#sender(s), testerThread && to === 'tester' ? 'human' : to);
|
||||
string(a.body, 32768);
|
||||
// C2-06: a guarded send is stored only through #guardedSend's pass, with its check result.
|
||||
const guarded = this.#guarded(s, to);
|
||||
if (guarded && this.#guardPass?.s !== s) fail('storage-refused');
|
||||
const check = guarded ? this.#guardPass.check : null;
|
||||
if (
|
||||
a.class !== undefined &&
|
||||
![
|
||||
@@ -5795,6 +5915,9 @@ export class Broker {
|
||||
a.corrects ?? null,
|
||||
a.body,
|
||||
);
|
||||
// C2-06: the stored check result shares the message's transaction (sage-3595 item 3). No new
|
||||
// event kind, which would be a schema step: the events kind CHECK is migrations/3b.sql:9.
|
||||
if (check) this.#event(s, 'action.allowed', { action: 'message.checked', message: mid, check }, mid, checkEventId(mid));
|
||||
const cancelled = this.#route(s.business, mid, to, thread);
|
||||
const request = s.human
|
||||
? this.#event(s, 'human.input', { kind: 'instruction', message: mid }, mid)
|
||||
@@ -6414,11 +6537,15 @@ export class Broker {
|
||||
)?.seq;
|
||||
if (after === undefined) fail('message-not-found');
|
||||
}
|
||||
// C2-06 (row 225, morgana-0198): a row the citation guard checked carries the stored result.
|
||||
return this.#store.all(
|
||||
`SELECT m.* FROM messages m JOIN message_threads mt ON mt.message=m.id WHERE mt.session=? AND m.seq>? ORDER BY m.seq LIMIT ${limit}`,
|
||||
session,
|
||||
after,
|
||||
);
|
||||
).map((m) => {
|
||||
const e = this.#store.get("SELECT body FROM events WHERE id=? AND kind='action.allowed' AND subject=?", checkEventId(m.id), m.id);
|
||||
return e ? { ...m, check: JSON.parse(e.body).check } : m;
|
||||
});
|
||||
}
|
||||
// Row 206 (193b2, #1704, design 5.3): the owner of a thread shares it read-only, or ends a share.
|
||||
// A user's collaborator grant must still cover the thread, and a user target needs a live grant
|
||||
|
||||
@@ -41,7 +41,8 @@ export class Client {
|
||||
const r = JSON.parse(input.toString('utf8'));
|
||||
if (r.ok === true) end(null, r.result);
|
||||
else if (r.ok === false && typeof r.error === 'string' && /^[a-z-]{1,64}$/.test(r.error))
|
||||
end(new BusError(r.error));
|
||||
// C2-06 (sage-3599): the citation guard's reason, when the envelope has one.
|
||||
end(new BusError(r.error, typeof r.reason === 'string' ? r.reason.slice(0, 300) : undefined));
|
||||
else end(new BusError('invalid-response'));
|
||||
} catch {
|
||||
end(new BusError('invalid-response'));
|
||||
|
||||
@@ -14,7 +14,7 @@ import { publishRemote, workingRepo, WorkingError } from '../../seat/src/working
|
||||
import { createLoader, hasModule } from '../../plugins/src/loader.mjs';
|
||||
import { pluginSettings } from '../../business/src/plugin-settings.mjs';
|
||||
import { instanceSettings } from '../../business/src/instance-settings.mjs';
|
||||
import { organizationWriter, OrganizationError } from '../../business/src/organization.mjs';
|
||||
import { organizationWriter, OrganizationError, setReplyLimits } from '../../business/src/organization.mjs';
|
||||
import { credentialVerbs } from './credential-verbs.mjs';
|
||||
import { loadBusiness } from '../../business/src/business.mjs';
|
||||
import { loadRole } from '../../business/src/role.mjs';
|
||||
@@ -305,6 +305,13 @@ export async function startBroker({
|
||||
status: context => libraryModule.libraryStatus({ ...context, dataRoot }),
|
||||
sync: (context, { accept }) => processing.work(() => libraryModule.sync({ ...context, dataRoot }, { ...syncOptions(context.business), accept })),
|
||||
LibraryError: libraryModule.LibraryError,
|
||||
// C2-06: the citation guard, the reply limits read from the business file at each check (none
|
||||
// configured reads as unreadable, so requireCitation is true), and thread.messages' `last`.
|
||||
guard: (context, body, options) => libraryModule.guardReply({ ...context, dataRoot }, body, options),
|
||||
replyLimits: id => libraryModule.resolveReplyLimits(organization
|
||||
? organizationWriter({ dir: organization.dir, rolesDir: organization.rolesDir }).readRaw(id) : { readable: false }),
|
||||
last: (context, paths) => libraryModule.lastCommits({ ...context, dataRoot }, paths),
|
||||
GuardError: libraryModule.GuardError,
|
||||
},
|
||||
project: {
|
||||
readSpec: context => projectModule.readSpec({ ...context, dataRoot }),
|
||||
@@ -334,6 +341,8 @@ export async function startBroker({
|
||||
else if(verb==='plugins.set')result=plugins.set(id,args,actor);
|
||||
// Row 194 (#1692, V6): the human's keep and noHire lists, through the instance writer.
|
||||
else if(verb==='veto.set')result=instances.veto(id,args,actor);
|
||||
// C2-06 M11: the human's replyLimits, through the organization writer's fence.
|
||||
else if(verb==='library.limits.set')result=setReplyLimits(organizationWriter({dir:organization.dir,rolesDir:organization.rolesDir}),id,args,actor);
|
||||
// Row 194 (D2.1, D2.2): the chief's hire and fire, with the reason in the change context.
|
||||
else if(verb==='instance.hire')result=instances.hire(id,args,{actor,context});
|
||||
else if(verb==='instance.fire')result=instances.fire(id,{name:args.name},{actor,context});
|
||||
|
||||
@@ -7,6 +7,11 @@ const LIMIT = 65536;
|
||||
// Row 148: a document save may carry up to 1 MiB of text. Only a request that names that verb near
|
||||
// its start (the proof object comes first) may pass LIMIT; the parsed verb is checked again below.
|
||||
const SAVE_VERB_AT_START = new RegExp(`"verb":"${PROJECT_SAVE_VERB.replaceAll('.', '\\.')}"`);
|
||||
// The refusal envelope. C2-06 (sage-3599): `reason` is added only when the error carries one, which
|
||||
// only the citation guard's refusals do, so every other envelope is byte-identical to before.
|
||||
const refusal = (e, other) => e instanceof BusError
|
||||
? { ok: false, error: e.code, ...(typeof e.reason === 'string' ? { reason: e.reason } : {}) }
|
||||
: { ok: false, error: other };
|
||||
// One request per connection. There is deliberately no reconnect/retry or SQL verb.
|
||||
// `tasks` ({handle, timeout}) is the trusted S3 adapter; only the eight task verbs reach it.
|
||||
// `web` is the trusted web service (web.mjs), or a function from a business id to one (or null); only
|
||||
@@ -15,6 +20,7 @@ const SAVE_VERB_AT_START = new RegExp(`"verb":"${PROJECT_SAVE_VERB.replaceAll('.
|
||||
// host-not-configured.
|
||||
// A request carries exactly one of cap, human (row S4), tester (row 110), user (FED R3) and console
|
||||
// (row 252) proof.
|
||||
|
||||
export async function serve({ broker, path, authenticateHuman = null, authenticateTester = null, authenticateUser = null, authenticateConsole = null, peerReader = null, timeout = 5000, tasks = null, web = null, host = null }) {
|
||||
try {
|
||||
lstatSync(path);
|
||||
@@ -96,7 +102,7 @@ export async function serve({ broker, path, authenticateHuman = null, authentica
|
||||
.requestTask(cap, { verb: r.verb, args: r.args ?? {} }, tasks.handle)
|
||||
.then(
|
||||
(result) => finish({ ok: true, result }),
|
||||
(e) => finish({ ok: false, error: e instanceof BusError ? e.code : 'adapter-failed' }),
|
||||
(e) => finish(refusal(e, 'adapter-failed')),
|
||||
)
|
||||
.finally(() => {
|
||||
if (own) release();
|
||||
@@ -114,7 +120,7 @@ export async function serve({ broker, path, authenticateHuman = null, authentica
|
||||
.requestWeb(cap, { verb: r.verb, args: r.args ?? {} }, service, { onAdmit: () => socket.setTimeout(service.timeout) })
|
||||
.then(
|
||||
(result) => finish({ ok: true, result }),
|
||||
(e) => finish({ ok: false, error: e instanceof BusError ? e.code : 'web-failed' }),
|
||||
(e) => finish(refusal(e, 'web-failed')),
|
||||
)
|
||||
.finally(() => {
|
||||
if (own) release();
|
||||
@@ -130,7 +136,7 @@ export async function serve({ broker, path, authenticateHuman = null, authentica
|
||||
.requestHost(cap, { verb: r.verb, args: r.args ?? {} }, host, { onAdmit: (ms) => socket.setTimeout(ms + 10000) })
|
||||
.then(
|
||||
(result) => finish({ ok: true, result }),
|
||||
(e) => finish({ ok: false, error: e instanceof BusError ? e.code : 'host-failed' }),
|
||||
(e) => finish(refusal(e, 'host-failed')),
|
||||
)
|
||||
.finally(() => {
|
||||
if (own) release();
|
||||
@@ -153,14 +159,26 @@ export async function serve({ broker, path, authenticateHuman = null, authentica
|
||||
socket.setTimeout(120_000);
|
||||
Promise.resolve().then(() => broker.request(cap, { verb: r.verb, args: r.args ?? {} })).then(
|
||||
result => { if (!socket.destroyed) finish({ ok: true, result }); },
|
||||
e => { if (!socket.destroyed) finish({ ok: false, error: e instanceof BusError ? e.code : 'invalid-envelope' }); },
|
||||
e => { if (!socket.destroyed) finish(refusal(e, 'invalid-envelope')); },
|
||||
).finally(() => { if (own) release(); });
|
||||
return;
|
||||
}
|
||||
const result = broker.request(cap, { verb: r.verb, args: r.args ?? {} });
|
||||
// C2-06: a guarded message.send and a library business's thread.messages read Git first, so
|
||||
// the broker answers them with a promise. Every other verb stays synchronous.
|
||||
if (result instanceof Promise) {
|
||||
const own = transient;
|
||||
transient = null;
|
||||
socket.setTimeout(120_000);
|
||||
result.then(
|
||||
value => { if (!socket.destroyed) finish({ ok: true, result: value }); },
|
||||
e => { if (!socket.destroyed) finish(refusal(e, 'invalid-envelope')); },
|
||||
).finally(() => { if (own) release(); });
|
||||
return;
|
||||
}
|
||||
finish({ ok: true, result });
|
||||
} catch (e) {
|
||||
finish({ ok: false, error: e instanceof BusError ? e.code : 'invalid-envelope' });
|
||||
finish(refusal(e, 'invalid-envelope'));
|
||||
} finally {
|
||||
if (transient) release();
|
||||
}
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
// E4/sage-3668: real flock contention must not turn a valid cite into an invalid-cite refusal.
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { mkdirSync, writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { ensureMirror, mirrorPath, SYNC_STATE_FILE, withLibraryLock } from '../../library/src/mirror.mjs';
|
||||
import { guardReply } from '../../library/src/guard.mjs';
|
||||
import { git } from '../../library/tests/helpers.mjs';
|
||||
import { Client } from '../src/client.mjs';
|
||||
import { serve } from '../src/server.mjs';
|
||||
import { citationWorld, citedBody, fixtureCite } from './citation-helpers.mjs';
|
||||
|
||||
test('C2-06 held library lock gives the agent citation-unavailable and its retry reason', { timeout: 25000 }, async t => {
|
||||
const f = citationWorld(t), dataRoot = join(f.root, 'data'); mkdirSync(dataRoot, { mode: 0o700 });
|
||||
const context = { business: f.business, project: 'books', dataRoot };
|
||||
await ensureMirror(context); const mirror = mirrorPath(context);
|
||||
git(f.repo, '-c', 'protocol.file.allow=always', 'push', '-q', mirror, 'HEAD:refs/heads/served');
|
||||
writeFileSync(join(mirror, SYNC_STATE_FILE), JSON.stringify({ version: 1, branch: 'main', served: f.commit,
|
||||
lastFetch: null, lastError: null, diverged: null, problems: [] }), { mode: 0o600 });
|
||||
f.adapter.guard = (ctx, body, opts) => guardReply({ ...ctx, dataRoot }, body, opts);
|
||||
f.call(f.agent, 'role.claim');
|
||||
const socket = join(f.root, 'availability.sock'), server = await serve({ broker: f.broker, path: socket });
|
||||
t.after(() => server.close()); const client = new Client({ path: socket, cap: f.agent, timeout: 15000 });
|
||||
const args = { to: 'human', body: citedBody([fixtureCite(f.commit)]) };
|
||||
await client.call('message.send', args); // Establish that the cite and real mirror are valid.
|
||||
const before = f.store.get('SELECT count(*) n FROM messages').n;
|
||||
await withLibraryLock(mirror, async () => {
|
||||
await assert.rejects(client.call('message.send', args), e => {
|
||||
assert.equal(e.code, 'citation-unavailable');
|
||||
assert.equal(e.reason, 'The library is busy or unavailable. Retry the answer when the library is available.');
|
||||
return true;
|
||||
});
|
||||
assert.equal(f.store.get('SELECT count(*) n FROM messages').n, before);
|
||||
// A fixed fallback carries no library cite and must not need the contested lock.
|
||||
await client.call('message.send', { to: 'human', body: '(no answer passed the citation check)' });
|
||||
});
|
||||
await client.call('message.send', args); // No lock mutation or lost valid cite after release.
|
||||
});
|
||||
|
||||
test('C2-06 malformed sync state is availability failure, never a fabricated invalid cite', async t => {
|
||||
const f = citationWorld(t), dataRoot = join(f.root, 'data'); mkdirSync(dataRoot, { mode: 0o700 });
|
||||
const context = { business: f.business, project: 'books', dataRoot };
|
||||
await ensureMirror(context); const mirror = mirrorPath(context);
|
||||
writeFileSync(join(mirror, SYNC_STATE_FILE), '{broken', { mode: 0o600 });
|
||||
await assert.rejects(guardReply(context, citedBody([fixtureCite(f.commit)]), {
|
||||
limits: f.limits(), definition: 'coder', pages: [],
|
||||
}), { code: 'citation-unavailable' });
|
||||
});
|
||||
|
||||
test('C2-06 no mirror or freshly initialized empty mirror still means no served citation', async t => {
|
||||
const f = citationWorld(t), dataRoot = join(f.root, 'data'); mkdirSync(dataRoot, { mode: 0o700 });
|
||||
const context = { business: f.business, project: 'books', dataRoot };
|
||||
const check = () => guardReply(context, citedBody([fixtureCite(f.commit)]), { limits: f.limits(), definition: 'coder', pages: [] });
|
||||
await assert.rejects(check(), { code: 'citation-invalid' });
|
||||
await ensureMirror(context); await assert.rejects(check(), { code: 'citation-invalid' });
|
||||
});
|
||||
@@ -0,0 +1,153 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { connect } from 'node:net';
|
||||
import { readFileSync, rmSync, writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { Client } from '../src/client.mjs';
|
||||
import { serve } from '../src/server.mjs';
|
||||
import { FIXED_TEXTS, GuardError } from '../../library/src/guard.mjs';
|
||||
import { git } from '../../library/tests/helpers.mjs';
|
||||
import { organizationWriter, setReplyLimits } from '../../business/src/organization.mjs';
|
||||
import { businessDoc, rolesCopy, writeJson } from '../../business/tests/helpers.mjs';
|
||||
import { resolveReplyLimits } from '../../library/src/limits.mjs';
|
||||
import { citationWorld, citedBody, fixtureCite, guardCases } from './citation-helpers.mjs';
|
||||
|
||||
for (const definition of ['coder', 'research']) test(`C2-06 ${definition} send_message guard covers every table refusal; inserts nothing`, async t => {
|
||||
const f = citationWorld(t, { definition }); f.call(f.agent, 'role.claim');
|
||||
writeFileSync(f.settings, JSON.stringify({ replyLimits: { requireCitation: true } }));
|
||||
for (const [code, body] of guardCases(f.commit)) {
|
||||
const count = f.store.get('SELECT count(*) n FROM messages').n;
|
||||
await assert.rejects(f.call(f.agent, 'message.send', { to: 'human', body }), e => e.code === code && e.reason.length <= 300);
|
||||
assert.equal(f.store.get('SELECT count(*) n FROM messages').n, count, code);
|
||||
assert.equal(f.store.all("SELECT * FROM events WHERE json_extract(body,'$.action')='message.checked'").length, 0);
|
||||
}
|
||||
const sent = await f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(f.commit)]) });
|
||||
const row = f.store.get("SELECT body,subject FROM events WHERE json_extract(body,'$.action')='message.checked'");
|
||||
assert.equal(row.subject, sent.id);
|
||||
assert.deepEqual(JSON.parse(row.body).check, { citations: [{ scope: 'canon', agent: null, file: f.commit }] });
|
||||
});
|
||||
|
||||
test('C2-06 stored check carries the file author trailer at an unrelated cited tip', async t => {
|
||||
const f = citationWorld(t, { definition: 'research' }); f.call(f.agent, 'role.claim');
|
||||
const path = 'Book One/Characters/Mara Vell.md';
|
||||
writeFileSync(join(f.repo, path), readFileSync(join(f.repo, path), 'utf8') + 'A fixture note.\n');
|
||||
git(f.repo, 'add', '-A'); git(f.repo, 'commit', '-qm', 'Fixture note\n\nMosaic-Agent: acme/scribe');
|
||||
const file = git(f.repo, 'rev-parse', 'HEAD');
|
||||
writeFileSync(join(f.repo, 'Inbox Note.md'), 'Unrelated fixture.\n'); git(f.repo, 'add', '-A'); git(f.repo, 'commit', '-qm', 'unrelated');
|
||||
const cited = git(f.repo, 'rev-parse', 'HEAD'); f.setServed(cited);
|
||||
assert.notEqual(cited, file);
|
||||
const sent = await f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(cited)]) });
|
||||
const event = f.store.get("SELECT body FROM events WHERE subject=? AND json_extract(body,'$.action')='message.checked'", sent.id);
|
||||
assert.deepEqual(JSON.parse(event.body).check, { citations: [{ scope: 'canon', agent: 'acme/scribe', file }] });
|
||||
const [row] = await f.call(f.human, 'thread.messages', { thread: f.thread.id });
|
||||
assert.deepEqual(row.check.citations, [{ scope: 'canon', agent: 'acme/scribe', file, last: file }]);
|
||||
});
|
||||
|
||||
test('C2-06 check evidence and insert are atomic when storing evidence fails', async t => {
|
||||
const f = citationWorld(t); f.call(f.agent, 'role.claim');
|
||||
f.store.run(`CREATE TRIGGER fixture_check_refused BEFORE INSERT ON events
|
||||
WHEN json_extract(NEW.body,'$.action')='message.checked' BEGIN SELECT RAISE(ABORT,'fixture check failure'); END`);
|
||||
await assert.rejects(f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(f.commit)]) }));
|
||||
assert.equal(f.store.get('SELECT count(*) n FROM messages').n, 0);
|
||||
});
|
||||
|
||||
test('C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts', async t => {
|
||||
const f = citationWorld(t); f.call(f.agent, 'role.claim');
|
||||
const send = body => f.call(f.agent, 'message.send', { to: 'human', body });
|
||||
await send('free');
|
||||
writeFileSync(f.settings, JSON.stringify({ replyLimits: { requireCitation: true } }));
|
||||
await assert.rejects(send('free'), { code: 'citation-missing' });
|
||||
writeFileSync(f.settings, JSON.stringify({ replyLimits: { requireCitation: false } })); await send('free');
|
||||
for (const invalid of ['{broken', 'null', '[]']) {
|
||||
writeFileSync(f.settings, invalid);
|
||||
const before = f.store.get('SELECT count(*) n FROM messages').n;
|
||||
await assert.rejects(send('free'), { code: 'citation-missing' });
|
||||
await assert.rejects(send(citedBody(Array(21).fill(fixtureCite(f.commit)))), { code: 'citations-over-limit' });
|
||||
assert.equal(f.store.get('SELECT count(*) n FROM messages').n, before);
|
||||
for (const text of Object.values(FIXED_TEXTS)) await send(text);
|
||||
assert.equal((await f.call(f.human, 'library.status', { project: 'books' })).replyLimits.problem, 'reply-limits-unreadable');
|
||||
}
|
||||
rmSync(f.settings);
|
||||
await assert.rejects(send('free'), { code: 'citation-missing' });
|
||||
});
|
||||
|
||||
test('C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect', async t => {
|
||||
const f = citationWorld(t, { definition: 'research' }); f.call(f.agent, 'role.claim');
|
||||
const fetch = async (n, text = `page ${n}`) => f.broker.requestWeb(f.agent, { verb: 'web.fetch', args: { url: `https://fixture.invalid/${n}` } },
|
||||
{ handle: async () => ({ result: { text }, summary: { outcome: 'ok' } }) });
|
||||
const send = (n, quote) => f.call(f.agent, 'message.send', { to: 'human', body: citedBody([{ url: `https://fixture.invalid/${n}`, quote }]) });
|
||||
await fetch(0); await send(0, 'page 0');
|
||||
for (let n = 1; n <= 20; n++) await fetch(n);
|
||||
await assert.rejects(send(0, 'page 0'), { code: 'citation-unfetched' }); await send(1, 'page 1');
|
||||
await fetch(21, 'x'.repeat(200 * 1024) + 'AFTER_CAP');
|
||||
await send(21, 'xxxx'); await assert.rejects(send(21, 'AFTER_CAP'), { code: 'citation-unfetched' });
|
||||
f.broker.disconnect(f.agent);
|
||||
f.broker.endLaunch({ business: 'acme', run: 'coder-run', reason: 'fixture', exitCode: 0 });
|
||||
const replacement = f.broker.bindLaunch({ ...f.launch, run: 'next-run' });
|
||||
f.call(replacement, 'role.claim');
|
||||
await assert.rejects(f.call(replacement, 'message.send', { to: 'human', body: citedBody([{ url: 'https://fixture.invalid/21', quote: 'xxxx' }]) }), { code: 'citation-unfetched' });
|
||||
});
|
||||
|
||||
test('C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical', async t => {
|
||||
const f = citationWorld(t, { guard: async () => { throw new GuardError('citation-invalid', 'guard reason '.repeat(50)); } });
|
||||
f.call(f.agent, 'role.claim'); const path = join(f.root, 'socket');
|
||||
const server = await serve({ broker: f.broker, path }); t.after(() => server.close());
|
||||
const client = new Client({ path, cap: f.agent });
|
||||
await assert.rejects(client.call('message.send', { to: 'human', body: 'fixture' }), e => e.code === 'citation-invalid' && e.reason === ('guard reason '.repeat(50)).slice(0, 300));
|
||||
const raw = await new Promise((resolve, reject) => {
|
||||
const socket = connect(path); let text = ''; socket.on('error', reject); socket.on('data', b => { text += b; }); socket.on('end', () => resolve(text));
|
||||
socket.on('connect', () => socket.write(JSON.stringify({ cap: f.agent, verb: 'unknown-fixture' }) + '\n'));
|
||||
});
|
||||
assert.equal(raw, '{"ok":false,"error":"unknown-verb"}\n');
|
||||
});
|
||||
|
||||
test('C2-06 non-library businesses retain role.claim shape and unguarded free sends', async t => {
|
||||
const f = citationWorld(t, { library: false });
|
||||
assert.deepEqual(f.call(f.agent, 'role.claim'), { role: 'coder', run: 'coder-run' });
|
||||
assert.ok(f.call(f.agent, 'message.send', { to: 'human', body: 'free' }).id);
|
||||
});
|
||||
|
||||
test('C2-06 thread messages carry file/last evidence with one read per distinct path', async t => {
|
||||
const f = citationWorld(t, { definition: 'research' }); f.call(f.agent, 'role.claim');
|
||||
const path = 'Book One/Characters/Mara Vell.md';
|
||||
await f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(f.commit), fixtureCite(f.commit)]) });
|
||||
await f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(f.commit)]) });
|
||||
const rows = await f.call(f.human, 'thread.messages', { thread: f.thread.id });
|
||||
assert.equal(rows.length, 2); assert.deepEqual(f.reads, [path]);
|
||||
for (const row of rows) for (const c of row.check.citations) {
|
||||
assert.equal(c.file, f.commit); assert.equal(c.last, f.commit); assert.equal(c.agent, null);
|
||||
}
|
||||
writeFileSync(join(f.repo, path), 'A changed fixture.\n'); git(f.repo, 'add', '-A'); git(f.repo, 'commit', '-qm', 'changed fixture');
|
||||
const changed = git(f.repo, 'rev-parse', 'HEAD'); f.setServed(changed); f.reads.length = 0;
|
||||
const newer = await f.call(f.human, 'thread.messages', { thread: f.thread.id });
|
||||
assert.deepEqual(f.reads, [path]); assert.equal(newer[0].check.citations[0].file, f.commit); assert.equal(newer[0].check.citations[0].last, changed);
|
||||
});
|
||||
|
||||
test('C2-06 guarded request snapshot cannot change between check and insert', async t => {
|
||||
let finish;
|
||||
const f = citationWorld(t, { guard: () => new Promise(r => { finish = r; }) }); f.call(f.agent, 'role.claim');
|
||||
const request = { verb: 'message.send', args: { to: 'human', body: 'checked fixture' } };
|
||||
const sent = f.broker.request(f.agent, request); request.args.body = 'unchecked replacement';
|
||||
finish(null); await sent;
|
||||
assert.equal(f.store.get("SELECT body FROM messages WHERE from_role='coder'").body, 'checked fixture');
|
||||
});
|
||||
|
||||
test('C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged', async t => {
|
||||
let writer;
|
||||
const f = citationWorld(t, { organization: (id, verb, args, actor) => {
|
||||
assert.equal(verb, 'library.limits.set'); return setReplyLimits(writer, id, args, actor);
|
||||
} });
|
||||
const dir = join(f.root, 'config'), file = writeJson(join(dir, 'businesses/acme.json'), businessDoc(f.root));
|
||||
writer = organizationWriter({ dir, rolesDir: rolesCopy(f.root) });
|
||||
f.adapter.replyLimits = () => resolveReplyLimits(writer.readRaw('acme'));
|
||||
f.call(f.agent, 'role.claim');
|
||||
await f.call(f.human, 'library.limits.set', { revision: writer.read('acme').revision, replyLimits: { requireCitation: true } });
|
||||
await assert.rejects(f.call(f.agent, 'message.send', { to: 'human', body: 'free' }), { code: 'citation-missing' });
|
||||
const before = readFileSync(file), log = readFileSync(writer.logFile('acme'));
|
||||
const args = { revision: writer.read('acme').revision, replyLimits: { citationsPerReply: 0 } };
|
||||
for (const [cap, code] of [[f.human, 'invalid-request'], [f.agent, 'human-required'], [f.tester, 'tester-refused']]) {
|
||||
assert.throws(() => f.call(cap, 'library.limits.set', args), { code });
|
||||
assert.deepEqual(readFileSync(file), before); assert.deepEqual(readFileSync(writer.logFile('acme')), log);
|
||||
}
|
||||
assert.throws(() => f.call(f.human, 'library.limits.set', { ...args, replyLimits: { invented: true } }), { code: 'invalid-request' });
|
||||
});
|
||||
@@ -0,0 +1,65 @@
|
||||
// C2-06: real broker, real Git reads and fixture-only library. Reused by runner acceptance tests.
|
||||
import { mkdirSync, readFileSync, writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { Store } from '../src/store.mjs';
|
||||
import { Broker } from '../src/broker.mjs';
|
||||
import { checkReply, GuardError, libraryReader } from '../../library/src/guard.mjs';
|
||||
import { THREAD_DEFINITIONS } from '../../business/src/vocabulary.mjs';
|
||||
import { resolveReplyLimits } from '../../library/src/limits.mjs';
|
||||
import { mapping, repo, MARKER } from '../../library/tests/helpers.mjs';
|
||||
|
||||
export const citedBody = citations => JSON.stringify({ text: 'A fixture answer.', citations });
|
||||
export const fixtureCite = (commit, extra = {}) => ({ path: 'Book One/Characters/Mara Vell.md', commit, lines: [9, 9], quote: 'Grey eyes.', ...extra });
|
||||
|
||||
export function citationWorld(t, { definition = 'coder', library = true, guard: overrideGuard, organization = null, sendAuthority = true } = {}) {
|
||||
const r = repo(t), root = r.root, state = join(root, 'bus'); mkdirSync(state, { mode: 0o700 });
|
||||
const store = new Store(state); t.after(() => store.close());
|
||||
const map = mapping(), settings = join(root, 'business.json');
|
||||
writeFileSync(settings, JSON.stringify({ replyLimits: { requireCitation: false, citationsPerReply: 20 } }));
|
||||
const business = { id: 'acme', human: 'jason', vars: { 'bus.tester': true },
|
||||
...(library ? { projects: { books: map } } : {}),
|
||||
arbiters: { technical: 'coder', delivery: 'coder' },
|
||||
roles: { coder: { definition, web: true, authority: { withinRole: sendAuthority ? ['message.send'] : [], crossRole: [] } } } };
|
||||
const limits = () => {
|
||||
try { return resolveReplyLimits({ readable: true, document: JSON.parse(readFileSync(settings, 'utf8')) }); }
|
||||
catch { return resolveReplyLimits({ readable: false }); }
|
||||
};
|
||||
let served = r.commit;
|
||||
const reads = [];
|
||||
const adapter = {
|
||||
GuardError,
|
||||
replyLimits: limits,
|
||||
guard: overrideGuard ?? ((context, body, opts) => checkReply(body, {
|
||||
limits: opts.limits, mapping: map, library: libraryReader(r.repo, served, map),
|
||||
web: { allowed: ['companion', 'research'].includes(opts.definition), pages: opts.pages },
|
||||
})),
|
||||
last: async (context, paths) => {
|
||||
const out = new Map(); for (const path of new Set(paths)) { reads.push(path); out.set(path, await libraryReader(r.repo, served, map).last(path)); } return out;
|
||||
},
|
||||
readFile: async () => ({}), status: async () => ({ project: 'books', served }),
|
||||
};
|
||||
const broker = new Broker({ store, businesses: { acme: business }, library: adapter, organization });
|
||||
const human = broker.bindHuman({ business: 'acme', human: 'jason', via: 'cli', outsideAgent: true });
|
||||
const project = THREAD_DEFINITIONS.includes(definition)
|
||||
? broker.request(human, { verb: 'project.create', args: { name: 'Citation fixture' } }) : null;
|
||||
const thread = project
|
||||
? broker.request(human, { verb: 'thread.create', args: { project: project.id, name: 'Fixture thread', instance: 'coder' } }) : null;
|
||||
const launch = { business: 'acme', role: 'coder', run: 'coder-run', harness: 'pi', ...(thread ? { thread: thread.thread ?? thread.id } : {}) };
|
||||
const agent = broker.bindLaunch(launch);
|
||||
const tester = broker.bindTester({ business: 'acme' });
|
||||
const call = (cap, verb, args = {}) => broker.request(cap, { verb, args });
|
||||
return { ...r, root, store, business, broker, agent, human, tester, settings, limits, call, adapter, reads, launch, thread, setServed: commit => { served = commit; } };
|
||||
}
|
||||
|
||||
export function guardCases(commit) {
|
||||
const good = fixtureCite(commit);
|
||||
return [
|
||||
['reply-invalid', JSON.stringify({ text: 'x', citations: [], invented: true })],
|
||||
['citation-missing', 'Uncited fixture answer.'],
|
||||
['citations-over-limit', citedBody(Array(21).fill(good))],
|
||||
['citation-invalid', citedBody([{ ...good, quote: 'wrong fixture quote' }])],
|
||||
['playground-cited-as-canon', citedBody([{ ...good, path: 'Book One/Playground/What If.md', lines: [4, 4], quote: MARKER, as: 'canon' }])],
|
||||
['citation-cross-universe', citedBody([good, { ...good, path: 'Second World/Chapters/01.md', lines: [1, 1], quote: MARKER }])],
|
||||
['citation-unfetched', citedBody([{ url: 'https://fixture.invalid/page', quote: 'no fetch' }])],
|
||||
];
|
||||
}
|
||||
@@ -0,0 +1,29 @@
|
||||
// E7: exercise startBroker's real live readRaw adapter, rather than replacing the library adapter.
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
import { startBroker } from '../src/runtime.mjs';
|
||||
import { validateBusinessDocument } from '../../business/src/business.mjs';
|
||||
import { businessDoc, rolesCopy, writeJson } from '../../business/tests/helpers.mjs';
|
||||
import { mappingEntry } from '../../library/tests/helpers.mjs';
|
||||
|
||||
test('C2-06 runtime reads changed and unreadable reply limits without restarting', async t => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'citation-runtime-')); t.after(() => rmSync(root, { recursive: true, force: true }));
|
||||
const doc = businessDoc(root), rolesDir = rolesCopy(root), dir = join(root, 'config'), dataRoot = join(root, 'data');
|
||||
doc.projects.books = mappingEntry(); doc.replyLimits = { requireCitation: false, citationsPerReply: 3 };
|
||||
const file = writeJson(join(dir, 'businesses/acme.json'), doc);
|
||||
const business = validateBusinessDocument(doc, file, { rolesDir }); mkdirSync(dataRoot, { mode: 0o700 });
|
||||
const runtime = await startBroker({ dataRoot, businesses: { acme: business }, organization: { dir, rolesDir } });
|
||||
t.after(() => runtime.close());
|
||||
const human = runtime.broker.bindHuman({ business: 'acme', human: 'jason', via: 'cli', outsideAgent: true });
|
||||
const status = () => runtime.broker.request(human, { verb: 'library.status', args: { project: 'books' } });
|
||||
assert.deepEqual((await status()).replyLimits, { requireCitation: false, citationsPerReply: 3, fallback: [], problem: null });
|
||||
doc.replyLimits = { requireCitation: true, citationsPerReply: 7 }; writeJson(file, doc);
|
||||
assert.deepEqual((await status()).replyLimits, { requireCitation: true, citationsPerReply: 7, fallback: [], problem: null });
|
||||
writeFileSync(file, '{broken');
|
||||
assert.deepEqual((await status()).replyLimits, { requireCitation: true, citationsPerReply: 20, fallback: [], problem: 'reply-limits-unreadable' });
|
||||
rmSync(file);
|
||||
assert.equal((await status()).replyLimits.problem, 'reply-limits-unreadable');
|
||||
});
|
||||
@@ -21,7 +21,7 @@ const BOT_NAME = /^bot-[a-z0-9][a-z0-9._-]{0,60}$/;
|
||||
// How long a thread's session stays up with no turn before the launcher stops
|
||||
// it, when launch.threadIdleSeconds is absent (REQ-THREAD-2, row 121).
|
||||
export const THREAD_IDLE_SECONDS = 900;
|
||||
const TOP_KEYS = ["businessVersion", "id", "human", "arbiters", "projects", "vars", "tracker", "roles", "launch", "plugins", "hosts", "retired"];
|
||||
const TOP_KEYS = ["businessVersion", "id", "human", "arbiters", "projects", "vars", "tracker", "roles", "launch", "plugins", "hosts", "retired", "replyLimits"];
|
||||
|
||||
// The config directory: next to the system config, $MOSAIC_CONFIG or
|
||||
// ~/.config/mosaic-dev/config.json, the same rule mosaic-config.mjs uses.
|
||||
|
||||
@@ -8,6 +8,7 @@ import { join, dirname } from "node:path";
|
||||
import { randomUUID } from "node:crypto";
|
||||
import { businessFilePath, validateBusinessDocument } from "./business.mjs";
|
||||
import { requireId, sha256, canonicalJson } from "./util.mjs";
|
||||
import { checkReplyLimits } from "../../library/src/limits.mjs";
|
||||
|
||||
export class OrganizationError extends Error {
|
||||
constructor(code, message = code) {
|
||||
@@ -80,6 +81,33 @@ function changes(old, next, path = "") {
|
||||
}];
|
||||
}
|
||||
|
||||
// C2-06 M11: replyLimits is the human's alone. Any setter that changes it refuses unless the actor is
|
||||
// the business's human as the file stood before the write, and no agent or the tester under that
|
||||
// name. Compared as M9 compares projects, on the document and again on what lands on disk.
|
||||
function replyLimitsFence(old, document, actor) {
|
||||
if (canonicalJson(document?.replyLimits) === canonicalJson(old.replyLimits)) return;
|
||||
const agents = Object.entries(old.roles ?? {}).map(([instance, entry]) => `${entry?.definition}.${instance}`);
|
||||
if (actor === old.human && actor !== "tester" && !agents.includes(actor)) return;
|
||||
// The reason names each changed key and its value in force (the brief's M11).
|
||||
const plain = v => v !== null && typeof v === "object" && !Array.isArray(v);
|
||||
const before = old.replyLimits, after = document?.replyLimits;
|
||||
const named = plain(before) && plain(after)
|
||||
? [...new Set([...Object.keys(before), ...Object.keys(after)])].filter(k => canonicalJson(before[k]) !== canonicalJson(after[k]))
|
||||
.map(k => `replyLimits.${k} is ${canonicalJson(before[k]) ?? "unset"}`)
|
||||
: [`replyLimits is ${canonicalJson(before) ?? "unset"}`];
|
||||
fail("organization-reply-limits-human-only", `${named.join(", ").slice(0, 240)}; only the human changes it`);
|
||||
}
|
||||
|
||||
// C2-06: library.limits.set, the human's verb. It replaces the whole replyLimits object; a key left out
|
||||
// is its default. An unknown key or a value outside the table refuses invalid-request, and the write's
|
||||
// M11 fence refuses any actor but the human.
|
||||
export function setReplyLimits(writer, id, args, actor) {
|
||||
const replyLimits = checkReplyLimits(args?.replyLimits);
|
||||
if (replyLimits === null || typeof args?.revision !== "string") fail("invalid-request", "replyLimits takes requireCitation and citationsPerReply only");
|
||||
const { document } = writer.read(id);
|
||||
return writer.write(id, { ...document, replyLimits }, { revision: args.revision, actor });
|
||||
}
|
||||
|
||||
export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
|
||||
const evidence = join(dir, "businesses", ".history");
|
||||
const logFile = id => join(evidence, id, "changes.jsonl");
|
||||
@@ -93,6 +121,19 @@ export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
|
||||
return { document, revision: sha256(bytes) };
|
||||
}
|
||||
|
||||
// C2-06: the citation guard reads replyLimits fresh on every check, from the raw file, so a business
|
||||
// file that fails validation still yields its limits. { readable: false } when the file is missing,
|
||||
// unreadable, not JSON or not an object.
|
||||
function readRaw(id) {
|
||||
try {
|
||||
const document = JSON.parse(regular(businessFilePath(id, dir)));
|
||||
return document !== null && typeof document === "object" && !Array.isArray(document)
|
||||
? { readable: true, document } : { readable: false };
|
||||
} catch {
|
||||
return { readable: false };
|
||||
}
|
||||
}
|
||||
|
||||
function withLock(id, fn) {
|
||||
const parent = join(dir, "businesses");
|
||||
directory(evidence);
|
||||
@@ -191,6 +232,7 @@ export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
|
||||
// mapping, including library playgrounds and hybrid universes.
|
||||
if (canonicalJson(document?.projects) !== canonicalJson(old.projects))
|
||||
fail('organization-projects-protected');
|
||||
replyLimitsFence(old, document, actor);
|
||||
validateBusinessDocument(document, file, { rolesDir });
|
||||
const bytes = JSON.stringify(document, null, 2) + "\n";
|
||||
// Check and log exactly what lands on disk, for every setter: a value JSON
|
||||
@@ -198,6 +240,7 @@ export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
|
||||
const written = JSON.parse(bytes);
|
||||
if (canonicalJson(written.projects) !== canonicalJson(old.projects))
|
||||
fail('organization-projects-protected');
|
||||
replyLimitsFence(old, written, actor);
|
||||
validateBusinessDocument(written, file, { rolesDir });
|
||||
const after = sha256(bytes);
|
||||
const transaction = randomUUID();
|
||||
@@ -245,5 +288,5 @@ export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
|
||||
});
|
||||
}
|
||||
|
||||
return { logFile, read, write, record, recover: id => withLock(id, () => recover(id)) };
|
||||
return { logFile, read, readRaw, write, record, recover: id => withLock(id, () => recover(id)) };
|
||||
}
|
||||
@@ -0,0 +1,76 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { readFileSync, rmSync, writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { organizationWriter, setReplyLimits } from '../src/organization.mjs';
|
||||
import { validateBusinessDocument } from '../src/business.mjs';
|
||||
import { businessDoc, rolesCopy, tmp, writeJson } from './helpers.mjs';
|
||||
|
||||
function fixture(t, human = 'jason') {
|
||||
const root = tmp(); t.after(() => rmSync(root, { recursive: true, force: true }));
|
||||
const doc = businessDoc(root); doc.human = human; doc.replyLimits = { requireCitation: false, citationsPerReply: 20 };
|
||||
const dir = join(root, 'config'), file = writeJson(join(dir, 'businesses/acme.json'), doc), rolesDir = rolesCopy(root);
|
||||
const writer = organizationWriter({ dir, rolesDir });
|
||||
const next = structuredClone(doc); next.vars['tracker.pollSeconds'] = 61;
|
||||
writer.write('acme', next, { revision: writer.read('acme').revision, actor: human });
|
||||
return { root, file, writer, rolesDir, log: writer.logFile('acme') };
|
||||
}
|
||||
|
||||
function refused(f, actor, change) {
|
||||
const before = readFileSync(f.file), log = readFileSync(f.log), { document, revision } = f.writer.read('acme');
|
||||
change(document);
|
||||
assert.throws(() => f.writer.write('acme', document, { revision, actor }), { code: 'organization-reply-limits-human-only' });
|
||||
assert.deepEqual(readFileSync(f.file), before); assert.deepEqual(readFileSync(f.log), log);
|
||||
}
|
||||
|
||||
test('C2-06 M11 human replacement works; omitted settings return to defaults', t => {
|
||||
const f = fixture(t);
|
||||
setReplyLimits(f.writer, 'acme', { revision: f.writer.read('acme').revision, replyLimits: { requireCitation: true } }, 'jason');
|
||||
assert.deepEqual(f.writer.read('acme').document.replyLimits, { requireCitation: true });
|
||||
setReplyLimits(f.writer, 'acme', { revision: f.writer.read('acme').revision, replyLimits: {} }, 'jason');
|
||||
assert.deepEqual(f.writer.read('acme').document.replyLimits, {});
|
||||
});
|
||||
|
||||
test('C2-06 M11 agents and tester cannot change settings, including by changing human', t => {
|
||||
const f = fixture(t);
|
||||
for (const actor of ['chief-of-staff.chief', 'tester', 'coder.coder'])
|
||||
refused(f, actor, d => { d.replyLimits.requireCitation = true; });
|
||||
refused(f, 'chief-of-staff.chief', d => { d.human = 'chief-of-staff.chief'; d.replyLimits.requireCitation = true; });
|
||||
const dotted = fixture(t, 'coder.coder');
|
||||
refused(dotted, 'coder.coder', d => { d.replyLimits.citationsPerReply = 1; });
|
||||
});
|
||||
|
||||
test('C2-06 M11 serialization cannot replace settings after the first fence', t => {
|
||||
const f = fixture(t);
|
||||
refused(f, 'chief-of-staff.chief', d => {
|
||||
Object.defineProperty(d.replyLimits, 'toJSON', { value: () => ({ requireCitation: true }) });
|
||||
});
|
||||
});
|
||||
|
||||
// E1: unlike tester/role actors, mallory passes the other actor-shape exclusions.
|
||||
// Comparing document.human instead of old.human must fail this case.
|
||||
test('C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits', t => {
|
||||
const f = fixture(t);
|
||||
refused(f, 'mallory', d => { d.human = 'mallory'; d.replyLimits.requireCitation = true; });
|
||||
});
|
||||
|
||||
test('C2-06 invalid setter values preserve the business and changes.jsonl', t => {
|
||||
const f = fixture(t), before = readFileSync(f.file), log = readFileSync(f.log);
|
||||
for (const replyLimits of [{ citationsPerReply: 0 }, { citationsPerReply: 1001 }, { requireCitation: 'true' }, { invented: true }, []]) {
|
||||
assert.throws(() => setReplyLimits(f.writer, 'acme', { revision: f.writer.read('acme').revision, replyLimits }, 'jason'), { code: 'invalid-request' });
|
||||
assert.deepEqual(readFileSync(f.file), before); assert.deepEqual(readFileSync(f.log), log);
|
||||
}
|
||||
});
|
||||
|
||||
test('C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files', t => {
|
||||
const f = fixture(t), doc = f.writer.read('acme').document;
|
||||
for (const replyLimits of ['true', 1, null, [true], {}, { requireCitation: 'true' }, { citationsPerReply: 0 }]) {
|
||||
const next = { ...doc, replyLimits };
|
||||
assert.doesNotThrow(() => validateBusinessDocument(next, f.file, { rolesDir: f.rolesDir }));
|
||||
writeJson(f.file, next); assert.deepEqual(f.writer.readRaw('acme').document.replyLimits, replyLimits);
|
||||
}
|
||||
for (const bad of ['{broken', 'null', '[]', '1']) {
|
||||
writeFileSync(f.file, bad); assert.deepEqual(f.writer.readRaw('acme'), { readable: false });
|
||||
}
|
||||
rmSync(f.file); assert.deepEqual(f.writer.readRaw('acme'), { readable: false });
|
||||
});
|
||||
@@ -959,6 +959,12 @@ writer adds `since`, the time the limit was set, and keeps it on later saves.
|
||||
A patch that sends a different `since` is refused. Only these paths are token
|
||||
limits; the agent limits above are never read as one, whatever their names.
|
||||
|
||||
`mosaic limits replies --file LIMITS [--business ID]` replaces the citation settings
|
||||
through the human-only `library.limits.set` verb. LIMITS is a JSON object with optional
|
||||
`requireCitation` (boolean, default false) and `citationsPerReply` (integer 1–1000,
|
||||
default 20). Omitted keys use their defaults; unknown keys and invalid values refuse.
|
||||
The next library reply uses the new settings without restarting the bus.
|
||||
|
||||
`mosaic limits reset WORD... [--business ID]` moves one token limit's `since`
|
||||
to now, so its count restarts. The path is one word per level, as the plain
|
||||
output prints it: `mosaic limits reset tokens models anthropic claude-opus-5-5`.
|
||||
|
||||
@@ -7,9 +7,10 @@ import { CliError } from "./errors.mjs";
|
||||
import { migrateLaunch } from "../../business/src/migrate-launch.mjs";
|
||||
|
||||
// Row 155 (#1649, Q169): a PATCH may carry `assistants`, the assistant's vars, tracker and definition.
|
||||
// C2-06 M11: `replies --file LIMITS` replaces replyLimits with the file's object, at the current revision.
|
||||
export const LIMITS_USAGE = "mosaic limits [--business ID] [--json] [--tester] | set --file PATCH [--business ID] | " +
|
||||
"reset PATH... [--business ID] | migrate --file ORGANIZATION --models MAPPING [--roles-dir DIR]; " +
|
||||
"PATCH keys: revision, limits, models, instances, reset, assistants";
|
||||
"reset PATH... [--business ID] | replies --file LIMITS [--business ID] | migrate --file ORGANIZATION --models MAPPING [--roles-dir DIR]; " +
|
||||
"PATCH keys: revision, limits, models, instances, reset, assistants; LIMITS keys: requireCitation, citationsPerReply";
|
||||
|
||||
export const DAILY_NOTE = "Daily quotas count only this stack's own use of the account, not its use anywhere else.";
|
||||
|
||||
@@ -67,8 +68,9 @@ export async function limitsCommand(args, io, callFor) {
|
||||
io.stdout.write(JSON.stringify(converted, null, 2) + "\n");
|
||||
return;
|
||||
}
|
||||
if (!["view", "set", "reset"].includes(verb) || values["--models"] || values["--roles-dir"] ||
|
||||
(verb !== "set" && values["--file"]) || (verb === "set" && !values["--file"]) ||
|
||||
const fileVerb = verb === "set" || verb === "replies";
|
||||
if (!["view", "set", "reset", "replies"].includes(verb) || values["--models"] || values["--roles-dir"] ||
|
||||
(!fileVerb && values["--file"]) || (fileVerb && !values["--file"]) ||
|
||||
(verb === "reset" && parsed.positional.length < 2)) {
|
||||
throw new CliError(LIMITS_USAGE, 4);
|
||||
}
|
||||
@@ -78,6 +80,11 @@ export async function limitsCommand(args, io, callFor) {
|
||||
// result's `tokens` lists each token limit: counted, not-enforced or check-failed.
|
||||
let result;
|
||||
if (verb === "set") result = await call("limits.set", JSON.parse(readFileSync(values["--file"], "utf8")));
|
||||
else if (verb === "replies") {
|
||||
const replyLimits = JSON.parse(readFileSync(values["--file"], "utf8"));
|
||||
const { revision } = await call("limits", {});
|
||||
result = await call("library.limits.set", { revision, replyLimits });
|
||||
}
|
||||
else if (verb === "reset") {
|
||||
const { revision } = await call("limits", {});
|
||||
result = await call("limits.set", { revision, reset: [parsed.positional.slice(1)] });
|
||||
|
||||
@@ -0,0 +1,23 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { mkdtempSync, rmSync, writeFileSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
import { limitsCommand } from '../src/limits.mjs';
|
||||
|
||||
test('C2-06 CLI replies reads revision and sends only the JSON settings to the human verb', async t => {
|
||||
const dir = mkdtempSync(join(tmpdir(), 'reply-cli-')); t.after(() => rmSync(dir, { recursive: true, force: true }));
|
||||
const file = join(dir, 'settings.json'); writeFileSync(file, JSON.stringify({ requireCitation: true, citationsPerReply: 7 }));
|
||||
const calls = [], output = [];
|
||||
await limitsCommand(['replies', '--file', file, '--business', 'acme'], { stdout: { write: s => output.push(s) } }, parsed => {
|
||||
assert.equal(parsed.values['--business'], 'acme');
|
||||
return async (verb, args) => { calls.push([verb, args]); return verb === 'limits' ? { revision: 'r1' } : { revision: 'r2' }; };
|
||||
});
|
||||
assert.deepEqual(calls, [['limits', {}], ['library.limits.set', { revision: 'r1', replyLimits: { requireCitation: true, citationsPerReply: 7 } }]]);
|
||||
assert.match(output.join(''), /r2/);
|
||||
});
|
||||
|
||||
test('C2-06 CLI replies requires a file and refuses tester writes before a bus call', async () => {
|
||||
for (const args of [['replies'], ['replies', '--tester', '--file', 'unused'], ['replies', '--file', 'unused', '--models', 'unused']])
|
||||
await assert.rejects(limitsCommand(args, { stdout: { write() {} } }, () => { throw Error('bus touched'); }), { exitCode: 4 });
|
||||
});
|
||||
@@ -38,6 +38,7 @@ import { createServer, connect } from "node:net";
|
||||
import { join } from "node:path";
|
||||
import { pathToFileURL } from "node:url";
|
||||
import { Client } from "../../bus/src/client.mjs";
|
||||
import { GUARD_CODES, FIXED_TEXTS } from "../../library/src/reply-protocol.mjs";
|
||||
import { fetchReview, landWork, pushWorking } from "./git-tools.mjs";
|
||||
|
||||
export const EXIT = Object.freeze({ stopped: 0, founder: 20, claim: 21, session: 22, broker: 23, usage: 2 });
|
||||
@@ -458,8 +459,9 @@ export async function main(runDir, { stdin = process.stdin, env = process.env, l
|
||||
return EXIT.founder;
|
||||
}
|
||||
const client = new Client({ path: session.brokerSocket, cap, timeout: 30_000 });
|
||||
let library = false;
|
||||
try {
|
||||
await client.call("role.claim");
|
||||
library = (await client.call("role.claim"))?.library === true;
|
||||
} catch (e) {
|
||||
// No answer is not a refusal: the broker is down or the outcome is unknown.
|
||||
if (e.code === "outcome-unknown") {
|
||||
@@ -582,9 +584,60 @@ export async function main(runDir, { stdin = process.stdin, env = process.env, l
|
||||
if (!turn.ok) log(`runner: turn ${n} for message ${m.id} failed: ${turn.reason}`);
|
||||
try {
|
||||
if (m.class !== "RESULT") {
|
||||
const body = turn.ok ? turn.text || "(the session gave no answer)" : `The turn failed: ${turn.reason}`;
|
||||
await client.call("message.send", { to: m.from_role, body: clip(body) + unslop.note(), class: "RESULT", in_reply_to: m.id });
|
||||
unslop.sent();
|
||||
if (!library) {
|
||||
const body = turn.ok ? turn.text || "(the session gave no answer)" : `The turn failed: ${turn.reason}`;
|
||||
await client.call("message.send", { to: m.from_role, body: clip(body) + unslop.note(), class: "RESULT", in_reply_to: m.id });
|
||||
unslop.sent();
|
||||
} else {
|
||||
const send = async (answer) => {
|
||||
const raw = answer.ok ? answer.text || FIXED_TEXTS.empty : FIXED_TEXTS.failed;
|
||||
const fixed = Object.values(FIXED_TEXTS).includes(raw);
|
||||
let body = raw;
|
||||
if (!fixed) {
|
||||
let value;
|
||||
try { value = JSON.parse(raw); } catch {}
|
||||
if (value !== null && typeof value === "object" && !Array.isArray(value)) {
|
||||
// Malformed objects still reach the guard and its reply-invalid refusal.
|
||||
if (typeof value.text === "string") value.text += unslop.note();
|
||||
body = JSON.stringify(value);
|
||||
} else body = clip(raw) + unslop.note();
|
||||
}
|
||||
try {
|
||||
await client.call("message.send", { to: m.from_role, body, class: "RESULT", in_reply_to: m.id });
|
||||
if (!fixed) unslop.sent();
|
||||
} catch (error) {
|
||||
// The existing broker body cap is smaller than the socket's 64 KiB cap.
|
||||
// Both follow the one-retry rule, without changing non-library sends.
|
||||
if (error.code === "invalid-request" && body.length > 32768) {
|
||||
error = Object.assign(new Error("request-too-large"), { code: "request-too-large" });
|
||||
}
|
||||
throw error;
|
||||
}
|
||||
};
|
||||
try { await send(turn); }
|
||||
catch (error) {
|
||||
if (!GUARD_CODES.includes(error.code) && error.code !== "request-too-large") throw error;
|
||||
log(`runner: reply to ${m.id} refused: ${error.code}${error.reason ? `: ${error.reason}` : ""}`);
|
||||
const reason = error.code === "request-too-large"
|
||||
? "The message exceeds the 64 KiB request limit or the 32768-character body limit. Send a shorter answer."
|
||||
: error.reason ?? "The reply did not pass the citation check.";
|
||||
++n;
|
||||
try { await client.call("usage.begin", { turn: `${m.id}:retry` }); }
|
||||
catch (e) { log(`runner: usage baseline unavailable: ${e.code ?? "failed"}`); }
|
||||
const retry = await runTurn({ session, request: `${block ?? ""}\n${turnRequest(m)}\n\nYour answer was refused with ${error.code}: ${reason}\nReply again in this same session.`, n, env: turnEnv, onChild: (c) => (child = c) });
|
||||
unslop.read();
|
||||
try { await client.call("usage.end", { turn: `${m.id}:retry` }); }
|
||||
catch (e) { log(`runner: usage outcome unavailable: ${e.code ?? "failed"}`); }
|
||||
if (stopping) break loop;
|
||||
if (!retry.ok) log(`runner: retry turn ${n} for message ${m.id} failed: ${retry.reason}`);
|
||||
try { await send(retry); }
|
||||
catch (again) {
|
||||
if (!GUARD_CODES.includes(again.code) && again.code !== "request-too-large") throw again;
|
||||
log(`runner: retry to ${m.id} refused: ${again.code}`);
|
||||
await send({ ok: true, text: again.code === "request-too-large" ? FIXED_TEXTS.tooLong : FIXED_TEXTS.uncited });
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
await client.call("message.read", { id: m.id });
|
||||
} catch (e) {
|
||||
|
||||
@@ -0,0 +1,144 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { spawn } from 'node:child_process';
|
||||
import { once } from 'node:events';
|
||||
import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { serve } from '../../bus/src/server.mjs';
|
||||
import { FIXED_TEXTS } from '../../library/src/reply-protocol.mjs';
|
||||
import { GuardError } from '../../library/src/guard.mjs';
|
||||
import { citationWorld, citedBody, fixtureCite, guardCases } from '../../bus/tests/citation-helpers.mjs';
|
||||
|
||||
const RUNNER = new URL('../src/runner.mjs', import.meta.url).pathname;
|
||||
const ADAPTER = new URL('./fixtures/citation-adapter.mjs', import.meta.url).pathname;
|
||||
async function until(fn) {
|
||||
const stop = Date.now() + 15000;
|
||||
while (Date.now() < stop) { const value = fn(); if (value) return value; await new Promise(r => setTimeout(r, 15)); }
|
||||
throw Error('fixture timed out');
|
||||
}
|
||||
|
||||
async function setup(t, stepsFor, { library = true, requireCitation = true, sendAuthority = true, guard } = {}) {
|
||||
const f = citationWorld(t, { library, sendAuthority, guard }), runDir = join(f.root, 'run'), bundle = join(runDir, 'bundle');
|
||||
mkdirSync(bundle, { recursive: true }); mkdirSync(join(f.root, 'ws'));
|
||||
const steps = stepsFor(f.commit), brokerSocket = join(f.root, 'broker.sock');
|
||||
writeFileSync(f.settings, JSON.stringify({ replyLimits: { requireCitation } }));
|
||||
const server = await serve({ broker: f.broker, path: brokerSocket });
|
||||
writeFileSync(join(runDir, 'fixture-steps.json'), JSON.stringify(steps));
|
||||
const adapter = join(runDir, 'adapter.sh'); writeFileSync(adapter, `exec '${process.execPath}' '${ADAPTER}'\n`);
|
||||
writeFileSync(join(bundle, 'prompt.md'), 'Fixture only.\n');
|
||||
writeFileSync(join(bundle, 'tools.json'), JSON.stringify([{ name: 'send_message', verb: 'message.send', action: 'message.send' }]));
|
||||
writeFileSync(join(bundle, 'policy.json'), JSON.stringify({ needs: [], credentials: [] }));
|
||||
writeFileSync(join(runDir, 'session.json'), JSON.stringify({ business: 'acme', instance: 'coder', run: 'coder-run', harness: 'pi',
|
||||
provider: 'fixture', model: 'fixture', brokerSocket, workspace: join(f.root, 'ws'), sessionDir: join(runDir, 'session'), adapter,
|
||||
bundle: { prompt: join(bundle, 'prompt.md'), tools: join(bundle, 'tools.json'), policy: join(bundle, 'policy.json') },
|
||||
toolSocket: join(runDir, 'tools.sock'), turnMarker: join(runDir, 'turn.done'), turnEnd: 'marker', harnessEnv: {}, pollInterval: 20, turnTimeout: 10 }));
|
||||
const child = spawn(process.execPath, [RUNNER, runDir], { stdio: ['pipe', 'ignore', 'pipe'], env: { PATH: process.env.PATH } });
|
||||
let log = ''; child.stderr.on('data', b => { log += b; }); child.stdin.on('error', () => {}); child.stdin.end(JSON.stringify({ cap: f.agent }) + '\n');
|
||||
const exited = once(child, 'exit');
|
||||
t.after(async () => { child.kill('SIGTERM'); await exited; await server.close(); });
|
||||
await until(() => f.store.get("SELECT 1 FROM role_claims WHERE role='coder' AND op='claim'"));
|
||||
const ask = async () => {
|
||||
const sent = await f.call(f.human, 'message.send', { to: 'coder', body: 'Fixture question.', class: 'REQUEST' });
|
||||
const reply = await until(() => f.store.get('SELECT * FROM messages WHERE in_reply_to=?', sent.id));
|
||||
await until(() => f.store.get("SELECT 1 FROM deliveries WHERE message=? AND op='read'", sent.id));
|
||||
return reply;
|
||||
};
|
||||
return { ...f, runDir, ask, log: () => log, count: () => Number(readFileSync(join(runDir, 'fixture-count'), 'utf8')) };
|
||||
}
|
||||
|
||||
for (const code of ['reply-invalid', 'citation-missing', 'citations-over-limit', 'citation-invalid', 'playground-cited-as-canon', 'citation-cross-universe', 'citation-unfetched']) {
|
||||
test(`C2-06 RESULT ${code} retries once, delivers only the valid answer and names reason`, async t => {
|
||||
const f = await setup(t, commit => [{ text: guardCases(commit).find(c => c[0] === code)[1] }, { text: citedBody([fixtureCite(commit)]) }]);
|
||||
const reply = await f.ask(); assert.equal(reply.body, citedBody([fixtureCite(f.commit)])); assert.equal(f.count(), 2);
|
||||
assert.equal(f.store.get("SELECT count(*) n FROM messages WHERE from_role='coder'").n, 1);
|
||||
const requests = readFileSync(join(f.runDir, 'fixture-requests.jsonl'), 'utf8').trim().split('\n').map(JSON.parse);
|
||||
assert.match(requests[1], new RegExp(code)); assert.match(requests[1], /refused with/);
|
||||
assert.match(f.log(), new RegExp(code));
|
||||
});
|
||||
}
|
||||
|
||||
test('C2-06 RESULT two guard refusals use the citation fixed text and exactly one retry', async t => {
|
||||
const f = await setup(t, () => [{ text: 'uncited' }, { text: 'uncited again' }]);
|
||||
assert.equal((await f.ask()).body, FIXED_TEXTS.uncited); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
for (const size of [34000, 70000]) {
|
||||
test(`C2-06 RESULT JSON ${size} characters retries with a shorter valid answer`, async t => {
|
||||
const f = await setup(t, commit => [{ text: JSON.stringify({ text: 'x'.repeat(size), citations: [fixtureCite(commit)] }) }, { text: citedBody([fixtureCite(commit)]) }]);
|
||||
assert.equal((await f.ask()).body, citedBody([fixtureCite(f.commit)])); assert.equal(f.count(), 2);
|
||||
assert.match(readFileSync(join(f.runDir, 'fixture-requests.jsonl'), 'utf8'), /64 KiB/);
|
||||
});
|
||||
}
|
||||
|
||||
test('C2-06 RESULT two oversized JSON bodies use the length fixed text with citations required', async t => {
|
||||
const f = await setup(t, commit => Array(2).fill({ text: JSON.stringify({ text: 'x'.repeat(70000), citations: [fixtureCite(commit)] }) }));
|
||||
assert.equal((await f.ask()).body, FIXED_TEXTS.tooLong); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
test('C2-06 multibyte plain bodies also receive the one request-size retry', async t => {
|
||||
const f = await setup(t, commit => [{ text: '界'.repeat(32000) }, { text: citedBody([fixtureCite(commit)]) }]);
|
||||
assert.equal((await f.ask()).body, citedBody([fixtureCite(f.commit)])); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
test('C2-06 two multibyte plain bodies use the length fallback', async t => {
|
||||
const f = await setup(t, () => Array(2).fill({ text: '界'.repeat(32000) }));
|
||||
assert.equal((await f.ask()).body, FIXED_TEXTS.tooLong); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
test('C2-06 RESULT a length refusal then citation refusal shares one retry and citation fallback', async t => {
|
||||
const f = await setup(t, commit => [{ text: JSON.stringify({ text: 'x'.repeat(70000), citations: [fixtureCite(commit)] }) }, { text: 'uncited' }]);
|
||||
assert.equal((await f.ask()).body, FIXED_TEXTS.uncited); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
test('C2-06 fixed empty/failed replies defer unslop note until the next cited reply', async t => {
|
||||
const f = await setup(t, commit => [{ text: '', unslop: true }, { fail: true }, { text: citedBody([fixtureCite(commit)]) }]);
|
||||
assert.equal((await f.ask()).body, FIXED_TEXTS.empty); assert.equal((await f.ask()).body, FIXED_TEXTS.failed);
|
||||
const reply = JSON.parse((await f.ask()).body);
|
||||
assert.deepEqual(reply.citations, [fixtureCite(f.commit)]); assert.match(reply.text, /unslop/i); assert.equal(f.count(), 3);
|
||||
});
|
||||
|
||||
test('C2-06 cited JSON above the old 32000 clip retains its citations and text', async t => {
|
||||
const f = await setup(t, commit => [{ text: JSON.stringify({ text: 'x'.repeat(32200), citations: [fixtureCite(commit)] }) }]);
|
||||
const reply = JSON.parse((await f.ask()).body); assert.equal(reply.text.length, 32200); assert.deepEqual(reply.citations, [fixtureCite(f.commit)]); assert.equal(f.count(), 1);
|
||||
});
|
||||
|
||||
test('C2-06 a flagged cited answer keeps the note inside text and citations whole', async t => {
|
||||
const f = await setup(t, commit => [{ text: citedBody([fixtureCite(commit)]), unslop: true }]);
|
||||
const reply = JSON.parse((await f.ask()).body);
|
||||
assert.deepEqual(reply.citations, [fixtureCite(f.commit)]); assert.match(reply.text, /unslop/i); assert.equal(f.count(), 1);
|
||||
});
|
||||
|
||||
test('C2-06 send_message typed tool runs every guard code before the valid RESULT', async t => {
|
||||
const f = await setup(t, commit => [{ text: citedBody([fixtureCite(commit)]), tools: guardCases(commit).map(([, body]) => ({ to: 'human', body })) }]);
|
||||
await f.ask(); const results = readFileSync(join(f.runDir, 'fixture-tools.jsonl'), 'utf8').trim().split('\n').map(JSON.parse);
|
||||
assert.equal(results.length, 7); results.forEach((r, i) => { assert.equal(r.ok, false); assert.match(r.error, new RegExp(guardCases(f.commit)[i][0])); });
|
||||
assert.equal(f.store.get("SELECT count(*) n FROM messages WHERE from_role='coder'").n, 1);
|
||||
});
|
||||
|
||||
test('C2-06 outside library the old failed text, clip and unslop behavior hold', async t => {
|
||||
const f = await setup(t, () => [{ fail: true }, { text: 'x'.repeat(40000), unslop: true }], { library: false });
|
||||
assert.match((await f.ask()).body, /^The turn failed:/);
|
||||
const reply = (await f.ask()).body; assert.match(reply, /answer cut at 32000 characters/); assert.match(reply, /unslop/i); assert.equal(f.count(), 2);
|
||||
});
|
||||
|
||||
test('C2-06 outside library a refused send keeps the existing no-retry behavior', async t => {
|
||||
const f = await setup(t, () => [{ text: 'answer without send authority' }], { library: false, sendAuthority: false });
|
||||
await f.call(f.human, 'message.send', { to: 'coder', body: 'Fixture question.', class: 'REQUEST' });
|
||||
await until(() => /runner: reply to .* failed:/.test(f.log()));
|
||||
assert.equal(f.count(), 1); assert.equal(f.store.get("SELECT count(*) n FROM messages WHERE from_role='coder'").n, 0);
|
||||
assert.equal(existsSync(join(f.runDir, 'fixture-requests.jsonl')), true);
|
||||
});
|
||||
|
||||
|
||||
// E4: the agent must receive the availability reason in its actual retry turn,
|
||||
// rather than being told only that the source citation was invalid.
|
||||
test('C2-06 the retry turn delivers citation-unavailable reason to the agent', async t => {
|
||||
let sends = 0;
|
||||
const reason = 'The library is busy or unavailable. Retry the answer when the library is available.';
|
||||
const f = await setup(t, commit => [{ text: citedBody([fixtureCite(commit)]) }, { text: citedBody([fixtureCite(commit)]) }], {
|
||||
guard: async () => { if (sends++ === 0) throw new GuardError('citation-unavailable', reason); return null; },
|
||||
});
|
||||
await f.ask(); assert.equal(f.count(), 2);
|
||||
const requests = readFileSync(join(f.runDir, 'fixture-requests.jsonl'), 'utf8').trim().split('\n').map(JSON.parse);
|
||||
assert.equal(requests[1].includes(`citation-unavailable: ${reason}`), true);
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
// A fixture-only scripted harness. No provider or real credential is used.
|
||||
import { appendFileSync, existsSync, readFileSync, writeFileSync } from 'node:fs';
|
||||
import { dirname, join } from 'node:path';
|
||||
import { callTool } from '../../src/tools.mjs';
|
||||
|
||||
const root = dirname(process.env.MOSAIC_TURN_MARKER), countFile = join(root, 'fixture-count');
|
||||
const n = existsSync(countFile) ? Number(readFileSync(countFile, 'utf8')) : 0;
|
||||
const steps = JSON.parse(readFileSync(join(root, 'fixture-steps.json'), 'utf8'));
|
||||
const step = steps[n] ?? { fail: true };
|
||||
writeFileSync(countFile, String(n + 1));
|
||||
appendFileSync(join(root, 'fixture-requests.jsonl'), JSON.stringify(process.env.MOSAIC_REQUEST) + '\n');
|
||||
if (step.unslop) appendFileSync(process.env.MOSAIC_UNSLOP_LOG, JSON.stringify({ ev: 'flagged', findings: [{ source: 'fixture', id: 'fixture' }] }) + '\n');
|
||||
for (const args of step.tools ?? []) {
|
||||
let result;
|
||||
try { result = { ok: true, result: await callTool(process.env.MOSAIC_TOOL_SOCKET, 'send_message', args) }; }
|
||||
catch (e) { result = { ok: false, error: e.message }; }
|
||||
appendFileSync(join(root, 'fixture-tools.jsonl'), JSON.stringify(result) + '\n');
|
||||
}
|
||||
if (step.fail) process.exit(3);
|
||||
process.stdout.write(step.text ?? '');
|
||||
writeFileSync(process.env.MOSAIC_TURN_MARKER, 'done\n');
|
||||
@@ -0,0 +1,188 @@
|
||||
// C2-06 (design 5.2, rulings after r11 Q222, Q223 and Q226): the citation guard. The broker runs it
|
||||
// before it stores an agent's message to the human in a business with a library project. It reads
|
||||
// only the citations, never what the text says. Codes are design 5.2's table.
|
||||
import { git } from '../../project/src/git.mjs';
|
||||
import { classify } from './scope.mjs';
|
||||
import { listTree, readLibrary, readTexts, splitLines } from './reader.mjs';
|
||||
import { LibraryError } from './problems.mjs';
|
||||
import { mirrorPath, readSyncState } from './mirror.mjs';
|
||||
import { plain } from './limits.mjs';
|
||||
|
||||
import { FIXED_TEXTS } from './reply-protocol.mjs';
|
||||
export { GUARD_CODES, FIXED_TEXTS } from './reply-protocol.mjs';
|
||||
|
||||
// Web cites are for these definitions only (design 5.2).
|
||||
export const WEB_CITE_DEFINITIONS = Object.freeze(['research', 'companion']);
|
||||
|
||||
// The reason reaches the runner (sage-3599): the guard's own text naming the check, the cite and the
|
||||
// limit, never a quote or file text, and at most REASON_MAX characters.
|
||||
export const REASON_MAX = 300;
|
||||
export class GuardError extends LibraryError {
|
||||
constructor(code, reason) { reason = reason.slice(0, REASON_MAX); super(code, reason); this.reason = reason; }
|
||||
}
|
||||
const refuse = (code, reason) => { throw new GuardError(code, reason); };
|
||||
|
||||
const SHA = /^[a-f0-9]{40}$/;
|
||||
|
||||
const LIBRARY_CITE = ['path', 'commit', 'lines', 'quote'];
|
||||
const WEB_CITE = ['url', 'quote'];
|
||||
const only = (value, required, optional = []) => plain(value)
|
||||
&& required.every(k => Object.hasOwn(value, k)) && Object.keys(value).every(k => required.includes(k) || optional.includes(k));
|
||||
const text = value => typeof value === 'string' && value.length > 0 && !value.includes('\0');
|
||||
|
||||
function libraryCite(c) {
|
||||
return only(c, LIBRARY_CITE, ['as']) && text(c.path) && c.path.length <= 4096 && typeof c.commit === 'string' && SHA.test(c.commit)
|
||||
&& Array.isArray(c.lines) && c.lines.length === 2 && c.lines.every(n => Number.isSafeInteger(n) && n >= 1) && c.lines[0] <= c.lines[1]
|
||||
&& text(c.quote) && (!Object.hasOwn(c, 'as') || c.as === 'canon');
|
||||
}
|
||||
const webCite = c => only(c, WEB_CITE) && text(c.url) && c.url.length <= 4096 && text(c.quote);
|
||||
|
||||
// A body is free text, or a JSON object {text, citations} that must fit the schema. Returns
|
||||
// { text, citations, cited } where `cited` says the body was the JSON form.
|
||||
export function parseReply(body) {
|
||||
let value;
|
||||
try { value = JSON.parse(body); } catch { return { text: body, citations: [], cited: false }; }
|
||||
if (!plain(value)) return { text: body, citations: [], cited: false };
|
||||
if (!only(value, ['text', 'citations']) || typeof value.text !== 'string' || !Array.isArray(value.citations))
|
||||
refuse('reply-invalid', 'a JSON object reply holds exactly "text", a string, and "citations", a list');
|
||||
value.citations.forEach((c, i) => {
|
||||
if (!libraryCite(c) && !webCite(c))
|
||||
refuse('reply-invalid', `citation ${i + 1} is neither {path, commit, lines, quote, as?} nor {url, quote}`);
|
||||
});
|
||||
return { text: value.text, citations: value.citations, cited: true };
|
||||
}
|
||||
|
||||
const squash = value => value.replace(/\s+/g, ' ').trim();
|
||||
|
||||
// Design 5.2's checks, in the table's order. `limits` comes from resolveReplyLimits. `library` reads
|
||||
// git for a library cite (libraryReader below). `web` is { allowed, pages } for this sender: whether
|
||||
// its definition may cite a url, and the session's kept fetches. Returns the stored check result,
|
||||
// { citations: [{ scope, agent, file }] } in body order (agreed with row 225, morgana-0198 and
|
||||
// morgana-0200; a url cite is { scope: 'web', agent: null }), or null for a
|
||||
// plain body. Throws GuardError.
|
||||
export async function checkReply(body, { limits, mapping, library, web }) {
|
||||
if (Object.values(FIXED_TEXTS).includes(body)) return null;
|
||||
const reply = parseReply(body);
|
||||
const { citations } = reply;
|
||||
if (limits.requireCitation && citations.length === 0)
|
||||
refuse('citation-missing', 'replyLimits.requireCitation is true, so a reply carries at least one citation');
|
||||
if (citations.length > limits.citationsPerReply)
|
||||
refuse('citations-over-limit', `replyLimits.citationsPerReply is ${limits.citationsPerReply}; the reply carries ${citations.length}`);
|
||||
if (!reply.cited) return null;
|
||||
const found = [];
|
||||
for (const [i, c] of citations.entries()) {
|
||||
if (!Object.hasOwn(c, 'path')) { found.push(null); continue; }
|
||||
const at = `citation ${i + 1} (${c.path})`;
|
||||
const where = classify(mapping, c.path);
|
||||
if (where.scope === 'unmapped') refuse('citation-invalid', `${at} names a path that isn't mapped`);
|
||||
const lines = await library.lines(c.commit, c.path);
|
||||
if (lines === null) refuse('citation-invalid', `${at} isn't an indexed file at a commit reachable from the served commit`);
|
||||
if (c.lines[1] > lines.length) refuse('citation-invalid', `${at} cites lines past the file's ${lines.length}`);
|
||||
const quote = squash(c.quote);
|
||||
if (!quote || !squash(lines.slice(c.lines[0] - 1, c.lines[1]).join('\n')).includes(quote))
|
||||
refuse('citation-invalid', `${at} quote isn't in lines ${c.lines[0]}-${c.lines[1]}`);
|
||||
found.push(where);
|
||||
}
|
||||
citations.forEach((c, i) => {
|
||||
if (c.as === 'canon' && found[i].scope !== 'canon')
|
||||
refuse('playground-cited-as-canon', `citation ${i + 1} (${c.path}) is ${found[i].scope}, not canon`);
|
||||
});
|
||||
const universes = [...new Set(found.filter(Boolean).map(w => w.universe))];
|
||||
if (universes.length > 1) {
|
||||
const hybrid = universes.find(u => mapping.universes[u]?.kind === 'hybrid');
|
||||
const sources = hybrid ? mapping.universes[hybrid].sources : [];
|
||||
if (!hybrid || !universes.every(u => u === hybrid || sources.includes(u)))
|
||||
refuse('citation-cross-universe', `the citations span universes ${universes.join(', ')}`);
|
||||
}
|
||||
citations.forEach((c, i) => {
|
||||
if (!Object.hasOwn(c, 'url')) return;
|
||||
if (!web.allowed) refuse('citation-unfetched', `citation ${i + 1}: only research and companion cite a url`);
|
||||
const quote = squash(c.quote);
|
||||
const pages = web.pages.filter(p => p.url === c.url || p.finalUrl === c.url);
|
||||
if (!pages.length) refuse('citation-unfetched', `citation ${i + 1}: this session fetched no such url through the bus`);
|
||||
if (!quote || !pages.some(page => squash(page.text).includes(quote))) refuse('citation-unfetched', `citation ${i + 1}: the quote isn't in the url's kept text`);
|
||||
});
|
||||
const out = [];
|
||||
for (const [i, c] of citations.entries())
|
||||
out.push(found[i] ? { scope: found[i].scope, ...await library.origin(c.commit, c.path) } : { scope: 'web', agent: null });
|
||||
return { citations: out };
|
||||
}
|
||||
|
||||
// Git reads for one check against the bare mirror. `lines` is the file's lines at `commit` when the
|
||||
// commit is reachable from the served commit and readLibrary indexes the path there (sage-3595 item 4:
|
||||
// readLibrary at the cited commit stands in for the C2-05a index), else null. Reads are cached per
|
||||
// commit for the one check.
|
||||
export function libraryReader(mirror, served, mapping) {
|
||||
const indexed = new Map(), reach = new Map();
|
||||
const once = (cache, key, read) => {
|
||||
if (!cache.has(key)) cache.set(key, read().catch(() => null));
|
||||
return cache.get(key);
|
||||
};
|
||||
const reachable = commit => once(reach, commit, async () => {
|
||||
if (!mirror || !served) return false;
|
||||
if (await git(mirror, ['cat-file', '-t', commit]) !== 'commit') return false;
|
||||
await git(mirror, ['merge-base', '--is-ancestor', commit, served]);
|
||||
return true;
|
||||
});
|
||||
const index = commit => once(indexed, commit, async () => {
|
||||
const [read, entries] = await Promise.all([readLibrary({ repo: mirror, commit, mapping }), listTree(mirror, commit)]);
|
||||
return { files: new Set(read.files.map(file => file.path)), entries };
|
||||
});
|
||||
return {
|
||||
async lines(commit, path) {
|
||||
if (!await reachable(commit)) return null;
|
||||
const at = await index(commit);
|
||||
if (!at?.files.has(path)) return null;
|
||||
const texts = await readTexts(mirror, [at.entries.find(entry => entry.path === path)]).catch(() => new Map());
|
||||
return texts.has(path) ? splitLines(texts.get(path)) : null;
|
||||
},
|
||||
// One git call: the file's last commit at `commit` (morgana-0200: the Console compares it with the
|
||||
// served tip's, as the cited library commit needn't touch the file) and that commit's trailer.
|
||||
async origin(commit, path) {
|
||||
if (!mirror) return { agent: null, file: null };
|
||||
try {
|
||||
const [file, trailer = ''] = (await git(mirror, ['--literal-pathspecs', 'log', '-1', '--format=%H%x00%(trailers:key=Mosaic-Agent,valueonly)', commit, '--', path])).split('\0');
|
||||
return { agent: trailer.trim() || null, file: SHA.test(file) ? file : null };
|
||||
} catch { return { agent: null, file: null }; }
|
||||
},
|
||||
// The file's last commit at the served tip, for thread.messages (sage-3595), or null.
|
||||
async last(path) {
|
||||
if (!mirror || !served) return null;
|
||||
try {
|
||||
const value = await git(mirror, ['--literal-pathspecs', 'log', '-1', '--format=%H', served, '--', path]);
|
||||
return SHA.test(value) ? value : null;
|
||||
} catch { return null; }
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
// thread.messages' `last` (sage-3595): each path's last commit at the served tip, one git call per
|
||||
// distinct path. A path maps to null when there is no served commit or the read fails.
|
||||
export async function lastCommits(context, paths) {
|
||||
const { mirror, served } = await servedMirror(context);
|
||||
const reader = libraryReader(mirror, served, null);
|
||||
const out = new Map();
|
||||
for (const path of new Set(paths)) out.set(path, await reader.last(path));
|
||||
return out;
|
||||
}
|
||||
|
||||
// The library project's bare mirror and its served commit. Either is null when there is none yet, so
|
||||
// a plain reply still passes and any library cite refuses citation-invalid.
|
||||
async function servedMirror(context) {
|
||||
const mapping = context.business.projects[context.project];
|
||||
let mirror = null, served = null;
|
||||
try {
|
||||
mirror = mirrorPath(context);
|
||||
served = (await readSyncState(mirror, { branch: mapping.branch })).served ?? null;
|
||||
} catch { served = null; }
|
||||
return { mapping, mirror, served };
|
||||
}
|
||||
|
||||
// The broker's entry: the library project's mirror at its served commit, then checkReply. `context`
|
||||
// is { business, project, dataRoot }. `definition` is the sender's role definition, which decides only
|
||||
// whether a url cite may pass; `pages` is the broker's page store for the sender's session.
|
||||
export async function guardReply(context, body, { limits, definition, pages }) {
|
||||
const { mapping, mirror, served } = await servedMirror(context);
|
||||
const web = { allowed: WEB_CITE_DEFINITIONS.includes(definition), pages };
|
||||
return checkReply(body, { limits, mapping, library: libraryReader(mirror, served, mapping), web });
|
||||
}
|
||||
@@ -8,3 +8,5 @@ export { renderItems, KINDS, NOTICES, UNREADABLE } from './render.mjs';
|
||||
export { survey, formatSurvey, surveyMain } from './survey.mjs';
|
||||
export { SYNC_STATE_FILE, mirrorPath, ensureMirror, withLibraryLock, servedCommit, readSyncState, libraryStatus, readLibraryFile } from './mirror.mjs';
|
||||
export { syncCommand, sync, ASKPASS, SLOT, SYNC_INTERVAL_MS } from './sync.mjs';
|
||||
export { REPLY_LIMITS, resolveReplyLimits, checkReplyLimits } from './limits.mjs';
|
||||
export { GUARD_CODES, FIXED_TEXTS, WEB_CITE_DEFINITIONS, REASON_MAX, GuardError, parseReply, checkReply, libraryReader, guardReply, lastCommits } from './guard.mjs';
|
||||
@@ -0,0 +1,41 @@
|
||||
// C2-06 (design 5.2): the business file's replyLimits, read by the citation guard and written only
|
||||
// by the human's library.limits.set. Pure, so the business package's organization writer imports it.
|
||||
|
||||
export const plain = value => value !== null && typeof value === 'object' && !Array.isArray(value);
|
||||
|
||||
// The replyLimits keys, their defaults and their valid values. A key is read only when Object.hasOwn
|
||||
// finds it and its value passes `valid`; anything else is the default (webby-0144 R3).
|
||||
export const REPLY_LIMITS = Object.freeze({
|
||||
requireCitation: { default: false, valid: v => typeof v === 'boolean' },
|
||||
citationsPerReply: { default: 20, valid: v => Number.isInteger(v) && v >= 1 && v <= 1000 },
|
||||
});
|
||||
|
||||
// `read` is { readable: false } when the business file is missing, unreadable, not JSON or not an
|
||||
// object at check time, else { readable: true, document }. An unreadable file checks at the defaults
|
||||
// except requireCitation, which is true so a setting she turned on doesn't fail open (webby-0151 R2).
|
||||
export function resolveReplyLimits(read) {
|
||||
const limits = {}, fallback = [];
|
||||
const unreadable = !read?.readable || !plain(read.document);
|
||||
const raw = unreadable ? undefined : read.document.replyLimits;
|
||||
for (const [key, { default: value, valid }] of Object.entries(REPLY_LIMITS)) {
|
||||
if (plain(raw) && Object.hasOwn(raw, key) && valid(raw[key])) limits[key] = raw[key];
|
||||
else {
|
||||
limits[key] = value;
|
||||
// A key fell back when replyLimits is there but isn't an object, or holds the key with a value
|
||||
// outside the table. A key left out is simply its default.
|
||||
if (raw !== undefined && (!plain(raw) || Object.hasOwn(raw, key))) fallback.push(key);
|
||||
}
|
||||
}
|
||||
if (unreadable) limits.requireCitation = true;
|
||||
return { ...limits, fallback, unreadable };
|
||||
}
|
||||
|
||||
// library.limits.set's check: the whole object is replaced, a key left out means its default, and an
|
||||
// unknown key or a value outside the table refuses. Returns the object to write.
|
||||
export function checkReplyLimits(value) {
|
||||
if (!plain(value)) return null;
|
||||
for (const [key, v] of Object.entries(value))
|
||||
if (!Object.hasOwn(REPLY_LIMITS, key) || !REPLY_LIMITS[key].valid(v)) return null;
|
||||
return structuredClone(value);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
// C2-06: shared pure protocol constants for the host guard and sandboxed runner.
|
||||
export const GUARD_CODES = Object.freeze(['reply-invalid', 'citation-missing', 'citations-over-limit', 'citation-invalid',
|
||||
'playground-cited-as-canon', 'citation-cross-universe', 'citation-unfetched']);
|
||||
|
||||
// The runner's four fixed texts in a library business. The guard accepts exactly these bodies when
|
||||
// requireCitation is true; an agent that sends one gains nothing it couldn't say anyway.
|
||||
export const FIXED_TEXTS = Object.freeze({
|
||||
empty: '(the session gave no answer)',
|
||||
failed: '(the turn failed)',
|
||||
uncited: '(no answer passed the citation check)',
|
||||
tooLong: '(the answer was too long to send)',
|
||||
});
|
||||
@@ -0,0 +1,129 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { checkReply, GuardError, libraryReader, parseReply, FIXED_TEXTS } from '../src/guard.mjs';
|
||||
import { resolveReplyLimits, checkReplyLimits } from '../src/limits.mjs';
|
||||
import { BASE, MARKER, mapping, repo, git } from './helpers.mjs';
|
||||
|
||||
const defaults = resolveReplyLimits({ readable: true, document: {} });
|
||||
const body = citations => JSON.stringify({ text: 'A fixture answer.', citations });
|
||||
const cite = (commit, extra = {}) => ({ path: 'Book One/Characters/Mara Vell.md', commit, lines: [9, 9], quote: 'Grey eyes.', ...extra });
|
||||
const context = r => ({ limits: defaults, mapping: mapping(), library: libraryReader(r.repo, r.commit, mapping()), web: { allowed: true, pages: [] } });
|
||||
const refusal = code => e => e instanceof GuardError && e.code === code && typeof e.reason === 'string' && e.reason.length <= 300;
|
||||
|
||||
test('C2-06 reply schema: free bodies, exact objects and safe refusal reasons', async t => {
|
||||
const c = context(repo(t));
|
||||
for (const text of ['plain', 'null', '42', '[]', '"text"', '{broken']) {
|
||||
assert.equal(parseReply(text).cited, false);
|
||||
assert.equal(await checkReply(text, c), null);
|
||||
}
|
||||
assert.deepEqual(await checkReply(body([]), c), { citations: [] });
|
||||
for (const value of [{}, { text: 'x', citations: [], scope: 'canon' }, { text: 1, citations: [] },
|
||||
{ text: 'x', citations: {} }, { text: 'x', citations: [{ url: 'https://invalid.test', quote: 'x', agent: 'forged' }] },
|
||||
{ text: 'x', citations: [cite('a'.repeat(40), { as: 'supporting' })] }])
|
||||
await assert.rejects(checkReply(JSON.stringify(value), c), refusal('reply-invalid'));
|
||||
});
|
||||
|
||||
test('C2-06 citation setting and all four exact fixed texts', async t => {
|
||||
const c = context(repo(t)); c.limits = { ...defaults, requireCitation: true };
|
||||
await assert.rejects(checkReply('plain', c), refusal('citation-missing'));
|
||||
await assert.rejects(checkReply(body([]), c), refusal('citation-missing'));
|
||||
for (const text of Object.values(FIXED_TEXTS)) {
|
||||
assert.equal(await checkReply(text, c), null);
|
||||
await assert.rejects(checkReply(text + ' ', c), refusal('citation-missing'));
|
||||
}
|
||||
});
|
||||
|
||||
test('C2-06 default citation cap passes 20 and refuses 21, even with optional citations', async t => {
|
||||
const r = repo(t), c = context(r);
|
||||
assert.equal((await checkReply(body(Array(20).fill(cite(r.commit))), c)).citations.length, 20);
|
||||
await assert.rejects(checkReply(body(Array(21).fill(cite(r.commit))), c), refusal('citations-over-limit'));
|
||||
});
|
||||
|
||||
test('C2-06 real Git citation scope, reachability, lines and normalized quotes', async t => {
|
||||
const r = repo(t), c = context(r);
|
||||
assert.equal((await checkReply(body([cite(r.commit, { quote: 'Grey\n eyes.' })]), c)).citations[0].scope, 'canon');
|
||||
for (const extra of [{ path: 'Inbox Note.md', lines: [1, 1], quote: MARKER },
|
||||
{ path: 'Book One/Board.canvas' }, { path: 'Book One/Characters/Missing.md' },
|
||||
{ commit: '0'.repeat(40) }, { commit: git(r.repo, 'rev-parse', 'HEAD^{tree}') },
|
||||
{ lines: [999, 999] }, { quote: 'not in her fixture' }])
|
||||
await assert.rejects(checkReply(body([cite(r.commit, extra)]), c), refusal('citation-invalid'));
|
||||
// A future commit exists locally but is not reachable from the served commit.
|
||||
writeFileSync(join(r.repo, 'Inbox Note.md'), 'new\n'); git(r.repo, 'add', '-A'); git(r.repo, 'commit', '-qm', 'future');
|
||||
await assert.rejects(checkReply(body([cite(git(r.repo, 'rev-parse', 'HEAD'))]), c), refusal('citation-invalid'));
|
||||
assert.equal((await checkReply(body([cite(r.commit)]), c)).citations[0].scope, 'canon');
|
||||
});
|
||||
|
||||
test('C2-06 playground cites pass but cannot state canon', async t => {
|
||||
const r = repo(t), c = context(r), p = cite(r.commit, { path: 'Book One/Playground/What If.md', lines: [4, 4], quote: MARKER });
|
||||
assert.equal((await checkReply(body([p]), c)).citations[0].scope, 'playground');
|
||||
await assert.rejects(checkReply(body([{ ...p, as: 'canon' }]), c), refusal('playground-cited-as-canon'));
|
||||
});
|
||||
|
||||
test('C2-06 independent universes refuse; a hybrid and only its sources pass', async t => {
|
||||
const r = repo(t, { ...BASE, 'Crossover/Chapters/01.md': 'A hybrid fixture.\n' }), c = context(r);
|
||||
const other = cite(r.commit, { path: 'Second World/Chapters/01.md', lines: [1, 1], quote: MARKER });
|
||||
await assert.rejects(checkReply(body([cite(r.commit), other]), c), refusal('citation-cross-universe'));
|
||||
c.mapping = mapping(e => { e.universes.cross = { kind: 'hybrid', name: 'Cross', sources: ['harbor', 'second'], books: ['Crossover'] }; return e; });
|
||||
c.library = libraryReader(r.repo, r.commit, c.mapping);
|
||||
const hybrid = cite(r.commit, { path: 'Crossover/Chapters/01.md', lines: [1, 1], quote: 'hybrid fixture' });
|
||||
assert.equal((await checkReply(body([hybrid, cite(r.commit), other]), c)).citations.length, 3);
|
||||
});
|
||||
|
||||
test('C2-06 web cites require allowed definition, this session fetch and kept quote', async t => {
|
||||
const c = context(repo(t)), web = { url: 'https://fixture.invalid/page', quote: 'kept text' };
|
||||
await assert.rejects(checkReply(body([web]), c), refusal('citation-unfetched'));
|
||||
c.web.pages = [{ url: web.url, finalUrl: 'https://fixture.invalid/final', text: 'The kept\n text is here.' }];
|
||||
assert.deepEqual(await checkReply(body([web]), c), { citations: [{ scope: 'web', agent: null }] });
|
||||
assert.equal((await checkReply(body([{ ...web, url: c.web.pages[0].finalUrl }]), c)).citations.length, 1);
|
||||
c.web.pages.push({ url: web.url, text: 'A later fetch.' });
|
||||
assert.equal((await checkReply(body([{ ...web, quote: 'later fetch' }]), c)).citations.length, 1);
|
||||
await assert.rejects(checkReply(body([{ ...web, quote: 'discarded bytes' }]), c), refusal('citation-unfetched'));
|
||||
c.web.allowed = false;
|
||||
await assert.rejects(checkReply(body([web]), c), refusal('citation-unfetched'));
|
||||
});
|
||||
|
||||
test('C2-06 file origin is the path commit and trailer, while last follows served changes', async t => {
|
||||
const r = repo(t), path = 'Book One/Characters/Mara Vell.md';
|
||||
writeFileSync(join(r.repo, path), 'Agent fixture.\n'); git(r.repo, 'add', '-A');
|
||||
git(r.repo, 'commit', '-qm', 'Note\n\nMosaic-Agent: acme/scribe');
|
||||
const file = git(r.repo, 'rev-parse', 'HEAD');
|
||||
writeFileSync(join(r.repo, 'Inbox Note.md'), 'Unrelated.\n'); git(r.repo, 'add', '-A'); git(r.repo, 'commit', '-qm', 'unrelated');
|
||||
const cited = git(r.repo, 'rev-parse', 'HEAD'), reader = libraryReader(r.repo, cited, mapping());
|
||||
assert.notEqual(cited, file);
|
||||
assert.deepEqual(await reader.origin(cited, path), { agent: 'acme/scribe', file });
|
||||
assert.equal(await reader.last(path), file);
|
||||
writeFileSync(join(r.repo, path), 'Human fixture.\n'); git(r.repo, 'add', '-A'); git(r.repo, 'commit', '-qm', 'human');
|
||||
assert.notEqual(await libraryReader(r.repo, git(r.repo, 'rev-parse', 'HEAD'), mapping()).last(path), file);
|
||||
});
|
||||
|
||||
test('C2-06 origin uses literal paths even when a filename contains a glob', async t => {
|
||||
const path = 'Book One/Characters/Mara*.md';
|
||||
const r = repo(t, { ...BASE, [path]: 'Literal fixture.\n' }), original = r.commit;
|
||||
writeFileSync(join(r.repo, 'Book One/Characters/Mara Vell.md'), 'Other fixture.\n'); git(r.repo, 'add', '-A');
|
||||
git(r.repo, 'commit', '-qm', 'Other path\n\nMosaic-Agent: acme/other');
|
||||
const reader = libraryReader(r.repo, git(r.repo, 'rev-parse', 'HEAD'), mapping());
|
||||
assert.deepEqual(await reader.origin(git(r.repo, 'rev-parse', 'HEAD'), path), { agent: null, file: original });
|
||||
assert.equal(await reader.last(path), original);
|
||||
});
|
||||
|
||||
test('C2-06 reply limits fall back independently without coercion or inherited keys', () => {
|
||||
for (const value of ['true', 1, null, [true], {}]) {
|
||||
const r = resolveReplyLimits({ readable: true, document: { replyLimits: { requireCitation: value, citationsPerReply: 5 } } });
|
||||
assert.equal(r.requireCitation, false); assert.equal(r.citationsPerReply, 5); assert.deepEqual(r.fallback, ['requireCitation']);
|
||||
}
|
||||
for (const value of [0, 1001, 2.5, true, '5']) {
|
||||
const r = resolveReplyLimits({ readable: true, document: { replyLimits: { requireCitation: true, citationsPerReply: value } } });
|
||||
assert.equal(r.requireCitation, true); assert.equal(r.citationsPerReply, 20); assert.deepEqual(r.fallback, ['citationsPerReply']);
|
||||
}
|
||||
for (const value of [null, [], 1, 'settings', undefined]) {
|
||||
const r = resolveReplyLimits({ readable: true, document: { replyLimits: value } });
|
||||
assert.equal(r.requireCitation, false); assert.equal(r.citationsPerReply, 20);
|
||||
}
|
||||
assert.equal(resolveReplyLimits({ readable: true, document: { replyLimits: Object.create({ requireCitation: true }) } }).requireCitation, false);
|
||||
for (const document of [undefined, null, [], 'invalid']) assert.equal(resolveReplyLimits({ readable: true, document }).requireCitation, true);
|
||||
assert.equal(resolveReplyLimits({ readable: false }).requireCitation, true);
|
||||
assert.deepEqual(checkReplyLimits({ requireCitation: true, citationsPerReply: 1000 }), { requireCitation: true, citationsPerReply: 1000 });
|
||||
for (const value of [{ unknown: 1 }, { requireCitation: 'true' }, { citationsPerReply: 0 }, null, []]) assert.equal(checkReplyLimits(value), null);
|
||||
});
|
||||
@@ -60,6 +60,7 @@ export const RUNNER_FILES = Object.freeze([
|
||||
"packages/bus/src/landing.mjs",
|
||||
"packages/business/src/vocabulary.mjs",
|
||||
"packages/plugins/src/kinds.mjs",
|
||||
"packages/library/src/reply-protocol.mjs",
|
||||
"packages/processing-control/src/state.mjs",
|
||||
"packages/tasks/src/requirements.mjs",
|
||||
].map((p) => join(REPO, p)));
|
||||
|
||||
Reference in new issue
Block a user