row 217: record six green suites and five killed mutants for review

row 217: correct new runtime fixture and record first-run evidence
row 217: trim inherited limits whitespace and refresh hashes (Untested)
2026-10-24 05:24:36 -05:00 · 2026-10-24 05:06:00 -05:00 · 2026-10-24 04:56:24 -05:00 · 2026-10-24 04:55:55 -05:00 · 2026-10-24 04:55:38 -05:00 · 2026-10-24 04:52:18 -05:00
81 changed files with 6295 additions and 24 deletions
@@ -5476,3 +5476,12 @@ remain; no live state, schema or bus policy change.

 2026-10-24 | Goldie | Row265 / #1770 verified (mos-1567, sage-3942) | Approved correction adds solely address import pin + Row265 comment to project-runtime.test and one pure-source RUNNER_FILES mount; new block checks parser has no imports. Serialized fresh-short-TMP timeout-k10: unchanged sandbox10/10, parser15/15, rooms18/18, full bus957/957, twelve named refusal mutants killed (each Node1, driver0), restored parser15/15 + rooms18/18. All positives zero fail/skip/cancel; every mutation restored full broker SHA71b32ee4. Old first-red evidence retained, no other old-test change. Slot returned goldie-0034; Boyd packet explicitly includes mount-list review, candidate push next.
 2026-10-24T07:18:53Z | Sage | Row 327 (#1825, Bradford, Poe and Dewey) LANDED 68c08b4e7. Before: refactor at 94d9e90a6; the push guard was a scratch script with no reviewed-binary check. After: scripts/push-check.sh and scripts/test-push-check.sh on refactor, 3 commits cherry-picked onto 6a5e12511 with blobs equal to the round 3 tip d858c9f8b, plus doc commits 76f84465f and 68c08b4e7. Binaries are found by numstat or a NUL in the first 8000 committed bytes, regardless of attributes; each needs its sha256 and path in an approved latest-round candidate; an unconfirmed queue tail exits 2. Reviews: Poe c31525 rev 3882, Dewey c31526 rev 3883. Gate: 1st run 06:57Z RED, not the candidate: canonical node_modules was empty from 05:45:15Z (sage-4023). Rerun with its own root npm ci GREEN 07:15:49Z: 17 package suites 0 failures (cli 986, plugins 119, webui 418), 11 scripts exit 0, push-check 6 mutants KILLED; skips are the queue canonical-root check and the row 244 live provider cases. The landed push-check.sh passed its own push (NO_BINARY, NO_ATTRIBUTION, PUSH_READY). mos-1575: gates install their own node_modules; canonical restored with npm ci (128 packages).
+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.
+
+2026-10-24 | Beakley (88b97f65) | Row 217 round 2, sage-4037 | Rebased published dde5b8496 onto e0c6142f3 on new beakley/row217-r2; both append-log histories retained. Conflicts preserve landed grant dispatch, revocation hook and lookup exports. Added E4 citation-unavailable product path and real supporting-scope/index comparison tests after row283 8d2856ee3. Untested: no Node/npm/tests/mutants/build; ready for Sage CLEAR after Lena296. Full range-diff and honest discarded local rebase correction in agents/beakley/work/queue-217/BUILD.md.
+
+2026-10-24T10:21Z | Beakley (88b97f65) | Row 217 round2 slot verified, sage-4042/4043 | Source 2d274a5b6: touched57/57, whole library142/142 business270/270 bus974/974 cli988/988 harness172/172 seat218/218, all zero fail/skip/cancel. M1-M5 killed, controls/restored controls green, product hashes restored after each; E4 RED stand-in observed. Only first-red was new runtime fixture invalid-authority, corrected and retained in receipts; no old test failed/edited. Local root/webui npm ci, short TMPDIR, timeout-k10; no canonical npm/rm or module link. Full evidence agents/beakley/work/queue-217/run-r2; Sage owns scripts landing gate and formal review.
@@ -0,0 +1,314 @@
+# 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. Current branch: `beakley/row217-r2` (original `beakley/row217` preserved).
+Brief: `docs/plans/2026-10-20_case2-rows.md`, C2-06.
+Status: six whole suites green and M1–M5 killed under sage-4042/4043; ready for formal review. Landing scripts and integration remain Sage's.
+
+## 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.
+
+
+## Round 2 / sage-4037 — 2026-10-24, Untested
+
+New branch `beakley/row217-r2` from published `dde5b8496`, rebased exactly onto
+`origin/refactor` at `e0c6142f3` (109 upstream commits since `45dca69f6`). The
+published original branch is unchanged; no amend or force-push. The replayed
+four commits are b9ef816ff, 7400509ba, a447880cb, 2655ec010. Full range-diff:
+`rebase-r2.range-diff.txt`. Last commit is `=`, the first three are `!` from
+conflict context/indentation and append-log placement described below.
+
+Conflict resolutions:
+- broker.mjs: retained landed grants.scope/grants.scope.set dispatch and added
+  library.limits.set to the organization verb dispatch; neither path removed.
+- runtime.mjs: retained grants.scope.set and added library.limits.set alongside
+  it; retained query/sync wiring and all new base lifecycle behavior.
+- organization.mjs: retained row 239's beforeWrite/revoked wrapper, placing both
+  M11 fences before validations/revocation as on the old candidate. A refused
+  reply-limit write cannot invoke beforeWrite.
+- library/index.mjs: retained C2-05a buildIndex/query exports and added the guard
+  and reply-limits exports.
+- BUILD-LOG.md and docs/SESSIONS.md: retained upstream appends followed by all
+  Beakley appends. Static byte-prefix checks prove the entire e0c6142f3 log
+  histories survive; all original Beakley entries also survive.
+- business.mjs, cli README and sandbox.mjs auto-merged. Static diff against the
+  target confirms only this row's TOP_KEYS addition, README paragraph and one
+  import-free protocol mount; landed supporting scope and room-address mount
+  remain intact. runtime diff contains only the approved import, injected
+  guard/limits/last adapters and setter dispatch, now beside grants.scope.set.
+
+Correction recorded honestly: the first unpublished rebase attempt used an
+unbounded marker regex that removed code after a conflict. The diff stat caught
+it immediately; aborted the rebase and repeated with bounded markers. No result
+from that discarded attempt was pushed. The successful first replay matches the
+original 589 insertions/20 deletions; no broad deletions remain.
+
+Implemented E4 under sage-4037's explicit direction to make the product fix
+while keeping all tests unrun. This supersedes the earlier planned RED-first
+execution order; no RED or green has been observed. The existing regression
+cases predate the fix. GUARD_CODES now includes citation-unavailable. Only a
+mirror confirmed absent by lstat, or readSyncState's legitimate empty state,
+yields no served commit. Other read/lock/metadata errors give the fixed safe
+reason: "The library is busy or unavailable. Retry the answer when the library
+is available." The runner receives it through BusError.reason and includes it
+in its one retry request. The existing four fallback bodies remain. Plain,
+web-only and fixed replies require no mirror read, so a busy mirror cannot
+block the runner's fixed fallback. M5's real production anchor now exists.
+
+Supporting scope after row 283 (`8d2856ee3`): added two broker tests using real
+mapping/reader classification, not a scope stub. A path in both supporting and
+playground refuses as canon; an agent-committed supporting path stores
+scope=supporting, agent=acme/scribe and its file commit in message.checked.
+
+C2-05a comparison: index-build.mjs builds its file map directly from readLibrary
+files; indexFor calls that same reader at the requested commit. Added a real
+fixture test comparing the index set, readLibrary set and libraryReader.lines
+admission, including supporting, unmapped Markdown and .canvas. This comparison
+is authored and statically traced, not executed; numerical results wait on CLEAR.
+
+Current packet: manifest.r4.sha256, relative to e0c6142f3. No test file already
+present at that base was edited. No Node, npm, tests, mutants or webui build run.
+Ready for CLEAR after Lena's row 296. On CLEAR, install with npm ci
+--ignore-scripts --no-audit --no-fund in THIS worktree root and packages/webui;
+never link to canonical node_modules or run npm/rm in the canonical checkout.
+Use short mktemp TMPDIR and timeout -k 10. Any old-test red goes to Sage before
+an edit. Full green gate, mutants and Webby verdict remain outstanding.
+
+Range-diff receipt rendering trims trailing whitespace on diff separator lines; no substantive range-diff content changed. This removes whitespace warnings caused by embedding raw diff output in a tracked text file.
+
+Final base-to-candidate whitespace check found a trailing blank line inherited from Launchpad in limits.mjs; removed it without behavior changes. manifest.r5.sha256 supersedes r4 for the exact candidate file hashes.
+
+
+## CLEAR sage-4042/4043 — execution started 2026-10-24
+
+Queue beakley-217-start initially refused Lena's review-outcome lock twice;
+same-op retry succeeded at rev3894 (briefed→in-progress). No queue bypass.
+Short TMPDIR /mnt/storage/scratch/tmp/tNoueZ. Worktree-local npm ci at root
+(128 packages) and packages/webui (2) completed; neither path was a symlink.
+No npm/rm command ran in canonical. All test commands use timeout -k 10.
+
+E4 current file: 3 pass/0 fail/0 skip. M5 isolated pre-fix stand-in: 1 pass,
+2 expected assertion failures (citation-invalid instead of citation-unavailable),
+exit1. Restored product bytes and checkout product hashes, then E4 restored
+control 3/3. Receipts under run-r2/m5-red. M1 six-space anchors both match
+exactly once on the eight-space lines.
+
+Touched test files first run: 56 pass/1 fail, zero skip/cancel. The sole first-red
+was NEW citation-runtime.test.mjs invalid-authority at Broker.checkBusiness:
+validator output has unresolved roles and is not the host's broker projection.
+Adjusted that new fixture only, following limits-runtime.test.mjs: minimal
+empty-authority coder, validated real project mappings, real organization adapter
+and systemFor(root). Single rerun 1/1, then all touched files 57/57. No base test
+failure or edit. First log retained as run-r2/touched-first.log and reported to
+Sage in beakley-0014. No production change was required.
+
+The isolated mutant driver now wraps each node run in timeout -k 10, refuses a
+symlinked root node_modules, restores mutated files in finally, verifies original
+checkout product hashes after every mutant and reruns the restored control.
+Optional name filters allow the E4 M5 RED before the full mutant pass. No
+canonical dependency link is used; isolated copies link only this worktree's
+own dependency install.
+
+
+## Final slot results / 2026-10-24 10:21Z
+
+All requested runs completed serially under sage-4042/4043 on source revision
+`2d274a5b6`. Final receipt commits change only tracking and logs, not packages.
+
+| Whole suite | Pass | Fail / skip / cancel |
+| --- | ---: | --- |
+| library | 142 | 0 / 0 / 0 |
+| business | 270 | 0 / 0 / 0 |
+| bus | 974 | 0 / 0 / 0 |
+| cli | 988 | 0 / 0 / 0 |
+| harness | 172 | 0 / 0 / 0 |
+| seat | 218 | 0 / 0 / 0 |
+
+Total 2,764 whole-suite tests. Touched files rerun 57/57. The unchanged
+RUNNER_FILES import-closure test passed in seat (seat-suite.log:153). The only
+first-run failure was the NEW runtime fixture already recorded above; no old
+test failed and no test present at e0c6142f3 was edited.
+
+M1–M5 all killed by the intended assertion, each with Node exit1, a green
+control and green restored control. Driver exit0. M1 catches missing writer
+refusals; M2 is killed by mallory's human swap; M3 detects one message left
+behind after evidence failure; M4 detects the missing reason; M5 detects
+citation-invalid in place of citation-unavailable on contention and bad state.
+Every mutation was in a disposable HEAD archive. Each changed file was restored,
+checkout product hashes checked after every mutant, and the restored control
+rerun. All five final restored.sha256 certificates match current product files.
+M5 also ran separately before the whole suites as the authorized pre-fix RED
+stand-in; its held-lock and malformed-state assertions failed, then restored
+E4 passed 3/3. Full raw controls/negatives/restores are retained.
+
+Receipts: run-r2/summary.json and summary.txt; *-suite.log; touched-first.log,
+touched-rerun.log; availability-green.log; runtime-fixture-retry.log; npm-root.log
+and npm-webui.log; m1-anchors.txt; m5-red/ and mutants/. All are text, no binary
+artifact added. All Node/mutant/npm runs used the short TMPDIR and timeout -k 10.
+Both node_modules trees are local npm ci installs. No canonical npm/rm or
+canonical dependency link. No further runtime/source changes after the tests.
+
+Acceptance formerly waiting on dependencies is executed: real row283 supporting
+canon refusal and supporting/agent event pass; the C2-05a readLibrary/index set
+comparison passes; runtime readRaw live/corrupt/missing-file test passes; runner
+retry request carries the E4 availability reason. The repeat obsolete-name
+search finds only render.mjs:6 and render.test.mjs:58, owned by row225; no owned
+hit. First-library selection remains the accepted E5 limitation. Webby-0274 N1
+is a nonblocking wording limitation: configuration faults share the safe
+busy-or-unavailable retry text. No policy/schema restriction was invented.
+
+Current complete changed-file manifest over e0c6142f3..candidate is
+candidate-manifest.sha256, excluding itself to avoid a circular hash. It includes
+source, tests, records and evidence. Earlier numbered manifests are historical.
+Formal Webby verdict and all scripts/test-*.sh at landing remain Sage's steps;
+this is verified for review, not an integration/deployment claim.
+
+Exact negative-test logs retain Node's whitespace-only diagnostic lines. Whole diff --check reports those 12 blank-line padding warnings in run-r2 logs; source/docs diff --check excluding captured run-r2 evidence is clean. No source whitespace problem or test failure is hidden by that exclusion.
@@ -0,0 +1,61 @@
+# Row 217 round 2 — verified for review
+
+Issue #1718, C2-06. Base e0c6142f3; branch beakley/row217-r2. Continued
+Launchpad e25ef0373 through the preserved original dde5b8496 branch. Range-diff,
+conflict resolutions and acceptance receipts are in BUILD.md. Tested source
+revision: 2d274a5b6; the final commits add records/evidence only.
+
+The broker checks agent-to-human citations before insertion, stores trusted
+scope/agent/file evidence atomically with the message, and supplies per-path last
+on thread reads. It keeps session-local fetched pages and reads reply settings
+live through the M11 human-only writer. The runner preserves cited JSON, defers
+notes on fixed replies, and retries once with the refusal code and safe reason.
+E4 adds citation-unavailable for mirror/state/lock faults; uncited/web-only/fixed
+bodies do not need the mirror lock. Supporting scope uses landed row283 code.
+
+## Product and test scope
+
+The package paths listed in candidate-manifest.sha256 are exactly this row's
+base-to-candidate changes. Fourteen product paths cover library guard/limits/
+protocol/exports; business validation/writer; bus broker/runtime/server/client;
+CLI command/README; runner; and the single approved pure-protocol sandbox mount.
+Nine test/helper/fixture paths are additions. No existing test is modified.
+The mounted protocol stays import-free. Runtime retains the landed grant/query/
+sync behavior; the writer retains beforeWrite/revoked handling and fences before
+revocation. No SQL schema, event kind, role authority or credential change.
+
+## Executed evidence
+
+| Whole suite | Pass | Fail / skip / cancel |
+| --- | ---: | --- |
+| library | 142 | 0 / 0 / 0 |
+| business | 270 | 0 / 0 / 0 |
+| bus | 974 | 0 / 0 / 0 |
+| cli | 988 | 0 / 0 / 0 |
+| harness | 172 | 0 / 0 / 0 |
+| seat | 218 | 0 / 0 / 0 |
+
+Touched files 57/57; total whole suites 2,764. First run was 56/57 due solely
+to a new runtime fixture missing the broker's resolved authority shape. Only
+that new fixture changed; single and full touched reruns passed. No old test
+failed. First-red evidence remains in run-r2/touched-first.log.
+
+M1–M5 killed: missing M11 fences, incoming-human trust, split check transaction,
+dropped client reason, and hidden library availability. Every negative run has
+green control/restored runs and matching restored product certificates. M5 is
+also the authorized E4 pre-fix RED stand-in. Supporting canon refusal, stored
+supporting/agent evidence, the C2-05a index comparison, runtime raw settings and
+agent-visible E4 retry reason all pass. The unchanged sandbox closure test passes.
+
+Commands ran serially under Sage CLEAR with short TMPDIR and timeout -k 10.
+Root/webui dependencies came from local npm ci, never canonical links. Full logs,
+summary.json and mutant certificates are in run-r2/. The complete changed-file
+manifest candidate-manifest.sha256 covers e0c6142f3..candidate, excluding itself;
+its SHA256 is supplied with the pushed tip. Historical manifests stay untouched.
+
+## Remaining boundaries
+
+Sage runs every scripts/test-*.sh at landing and posts the formal Webby review
+request. No merge/deployment performed. First-library selection remains the
+accepted limitation; configuration faults share the safe unavailable reason
+(Webby N1, nonblocking). Obsolete-name search hits only row225's render files.
@@ -0,0 +1,80 @@
+74398edcedf16a3d856ab9e7ea900eb61a4df7f726f04b74b2ff123e7536e9c1  BUILD-LOG.md
+87880c30c2be0180e6eec4dbe203f86e93ae2b1b4be44031b6a4903c6245a0ec  agents/beakley/work/queue-217/BUILD.md
+e7ecf624ccb2b918efb08001ae9da36380fe918f8c27db704860809b6792e6f2  agents/beakley/work/queue-217/MANIFEST.md
+f4a042b5d6d393d2be62b107d7157ae51dd8fbf36f4360f5cd8cf07c03c74251  agents/beakley/work/queue-217/manifest.r1.sha256
+53f051a4e416a34181ad9bcc7687f0d686274542b06d9758e2db7eb81e848811  agents/beakley/work/queue-217/manifest.r2.sha256
+f96fccc566d01d70db32188574d0b5331ef3c90bce66558449a51b3f21da1b29  agents/beakley/work/queue-217/manifest.r3.sha256
+faf8ec3e0ab458fe95120345ec93e077b0dcad9458c0f2683a20effb6ce3ed93  agents/beakley/work/queue-217/manifest.r4.sha256
+a58f0e273b60508b95c833cbace26799d7aa935117fd1f9a27812fba65b93d54  agents/beakley/work/queue-217/manifest.r5.sha256
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/manifest.r6.sha256
+04a9d0585b5ae4818d87d67ac27f838355f1a6f586625a16cf01d91d7bb6d4a0  agents/beakley/work/queue-217/mutants.py
+4a5f7b3373fd3ff46e2d6a5f7ee7106ad76a71c9034ca5a44b9e7340f0cc4cff  agents/beakley/work/queue-217/rebase-r2.range-diff.txt
+630070b0d682120ba64b382ab3b47b3fa3e8f0bcfc695ca09432d01d705fbcb3  agents/beakley/work/queue-217/run-r2/README.md
+c4245272d5fc89c5fd3a9ea979e7d65727ea76e24364190af57556c59ad2fe34  agents/beakley/work/queue-217/run-r2/availability-green.log
+700fff38b0a99ffdb44863f13015673cb459e5e645c5df46580eafbc407c95c8  agents/beakley/work/queue-217/run-r2/bus-suite.log
+ef216d0af325c2b6647eb8405e5de70ebb5a0e7a28bb3d8fe3abc6a289a8d3d2  agents/beakley/work/queue-217/run-r2/business-suite.log
+af173117f83359ebba62c5c00eadc749bb179551a8e290bcf55bbe39b1e7272c  agents/beakley/work/queue-217/run-r2/cli-suite.log
+a615f69ba60859e9d7817f3353b0d7c71e6c12eecc3ecf0f630d473be21e5fef  agents/beakley/work/queue-217/run-r2/harness-suite.log
+acaa08001101fd69a12cae377984e0d469c2cedc2affb5ccf9af426a72549dcc  agents/beakley/work/queue-217/run-r2/library-suite.log
+5414ce5b94e7ac7918ed64f62e5fd2b921d49c7e93cf73042b9187d014069934  agents/beakley/work/queue-217/run-r2/m1-anchors.txt
+7d7138b25568adb98932bbe180a337fe6798c3eddcd7134ce7278c24fea48818  agents/beakley/work/queue-217/run-r2/m5-driver.log
+de7dd716d3981fd9fa1d114882e60f9a83736cdb8f8e2096c3913c9f8620238a  agents/beakley/work/queue-217/run-r2/m5-red/M5-hide-library-unavailable-control.log
+6b98d3943d04d99f3ef212f11901d2257422410c477abec27ed3100a0d20dad9  agents/beakley/work/queue-217/run-r2/m5-red/M5-hide-library-unavailable-restored-green.log
+a58f0e273b60508b95c833cbace26799d7aa935117fd1f9a27812fba65b93d54  agents/beakley/work/queue-217/run-r2/m5-red/M5-hide-library-unavailable-restored.sha256
+d852a464fd624ce12d8d6bdc9800402639bb500a6d40c628cb836ca1bcf1e326  agents/beakley/work/queue-217/run-r2/m5-red/M5-hide-library-unavailable.log
+7d7138b25568adb98932bbe180a337fe6798c3eddcd7134ce7278c24fea48818  agents/beakley/work/queue-217/run-r2/m5-red/summary.txt
+1c405f1f15d2ce2db37b5809cdf5eaff68f18c99c5621e1c43262a289c5e35c4  agents/beakley/work/queue-217/run-r2/mutants-driver.log
+c96487e87c1ae9e34a7222b04701c5efcce25fe201f03a0213b989f7cde2c376  agents/beakley/work/queue-217/run-r2/mutants/M1-writer-fence-control.log
+8b294ecc057ad64ace7f520a1785b54df7df5a9eddf962813c3e5f8fa723ffd4  agents/beakley/work/queue-217/run-r2/mutants/M1-writer-fence-restored-green.log
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/run-r2/mutants/M1-writer-fence-restored.sha256
+be749486956e85a71f08107139613e09b62c53b58e8cc10e0fbe807e95d079a6  agents/beakley/work/queue-217/run-r2/mutants/M1-writer-fence.log
+525da1cc780dfea1a66f95739d444516bd16271c7ec539d615012ec9c8e7c139  agents/beakley/work/queue-217/run-r2/mutants/M2-incoming-human-control.log
+3546705980bb4a73295f16e42ab55f38c6adca9a5c53252264ae4ef66c595dfc  agents/beakley/work/queue-217/run-r2/mutants/M2-incoming-human-restored-green.log
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/run-r2/mutants/M2-incoming-human-restored.sha256
+77352c22c459c516ff47ff1caa42fe9763fe201a04079646b0ccc0da6a145804  agents/beakley/work/queue-217/run-r2/mutants/M2-incoming-human.log
+58de145ec0384de4f560b28dcfa76e98c384be5c771d6561fb1054f07ea8166b  agents/beakley/work/queue-217/run-r2/mutants/M3-split-check-transaction-control.log
+6a4cd0ef36b0d2318ef71c941ce300d215b6d2f87d0b4328c461ba53d812434c  agents/beakley/work/queue-217/run-r2/mutants/M3-split-check-transaction-restored-green.log
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/run-r2/mutants/M3-split-check-transaction-restored.sha256
+2deb72f2d442f413fd06e205093f6fa3f955ec6ef707b7ca65b86be8c8883f9b  agents/beakley/work/queue-217/run-r2/mutants/M3-split-check-transaction.log
+31cac91f43c8b7ebe0431f27a038b0fcd554a12b232592747f3972213cfa192b  agents/beakley/work/queue-217/run-r2/mutants/M4-drop-client-reason-control.log
+e06c1da8dcd9e7eb013a4597b14369e296e21b812476bd6d88c7a7aa040d4065  agents/beakley/work/queue-217/run-r2/mutants/M4-drop-client-reason-restored-green.log
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/run-r2/mutants/M4-drop-client-reason-restored.sha256
+66d8f72df3bc0428624dab437cb04923ecab42055d29c6ffde43af98d47f32ae  agents/beakley/work/queue-217/run-r2/mutants/M4-drop-client-reason.log
+3f74fbd3b4297868b9bb637a7924739363470964873a4bd3dc2f5daf2d0e9c8a  agents/beakley/work/queue-217/run-r2/mutants/M5-hide-library-unavailable-control.log
+96d95a45d5326e614328531a7dadebce5d3ce70e40ec23dd49a66c1a676b45be  agents/beakley/work/queue-217/run-r2/mutants/M5-hide-library-unavailable-restored-green.log
+120b15db5eb75897095fe3d0759553e482365d58061d763beba7754a6e0d0734  agents/beakley/work/queue-217/run-r2/mutants/M5-hide-library-unavailable-restored.sha256
+fa57189e9de99c4a76be27da3b857c07fc76706f7d0ee7409ba4efd43c3642b7  agents/beakley/work/queue-217/run-r2/mutants/M5-hide-library-unavailable.log
+1c405f1f15d2ce2db37b5809cdf5eaff68f18c99c5621e1c43262a289c5e35c4  agents/beakley/work/queue-217/run-r2/mutants/summary.txt
+862418d3d4124871ca5fcaf35e16c318a04e2888da83836751ddfea110efeb06  agents/beakley/work/queue-217/run-r2/npm-root.log
+38b75d8bddacf8d227883a29dd8a10f87a7f02d8a95f3f8809cb966fc9c8cf7a  agents/beakley/work/queue-217/run-r2/npm-webui.log
+7f29b5a328fd6be61ebc4110a048305b50856810ab97a7798cd427924d74e8c9  agents/beakley/work/queue-217/run-r2/runtime-fixture-retry.log
+3bd51fe222a61412e8285eb522a2f7b5c1b0b035f7dca0e9ff66190bd53e6706  agents/beakley/work/queue-217/run-r2/seat-suite.log
+8b98c6ba76de46ddd858b4b95bae7bce2d1bf969edb85901ad8819e1280869a1  agents/beakley/work/queue-217/run-r2/summary.json
+e374cb7ab28a46dd560b267b0fe6691b11c0c2fabd00087c4e49a02ab1bf8086  agents/beakley/work/queue-217/run-r2/summary.txt
+ad2022c7ccdfa151e029eed92cd309369a97f197d9304775f6d2be3dc5f11080  agents/beakley/work/queue-217/run-r2/touched-first.log
+e1fe5ebae1a36f196470848bf27b99c21d316c9236a1d1328d7bcaca0ee4d3e9  agents/beakley/work/queue-217/run-r2/touched-rerun.log
+0c1b1f079b4b993e8d1aeb730d743e28696413eae8be6dd79731d749d1d45d0b  agents/launchpad/work/queue-217/BUILD.md
+76b0a5785f134c09cda677e8f5fb3e7454b39883c4a6f55360d9d277476fcd2c  docs/SESSIONS.md
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -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 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+168dcac99d9bfdfdf5ff0eaa2c0fff91595b351b4d0092dc299532c9c32869f0  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+3e04fa25a64334d33ffbec704205b32cd01992f2d341e908f933a345199beee0  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+168dcac99d9bfdfdf5ff0eaa2c0fff91595b351b4d0092dc299532c9c32869f0  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,90 @@
+#!/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 hashlib
+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 = []
+selected = set(sys.argv[2:])
+product_files = [line.split('  ', 1)[1] for line in (ROOT / 'agents/beakley/work/queue-217/manifest.r5.sha256').read_text().splitlines()]
+def hashes(base, files):
+    return {file: hashlib.sha256((base / file).read_bytes()).hexdigest() for file in files}
+original_products = hashes(ROOT, product_files)
+for name, changes, tests in MUTANTS:
+    if selected and name not in selected:
+        continue
+    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.is_symlink():
+            raise SystemExit('root node_modules must be a local install, never a canonical link')
+        if modules.exists():
+            os.symlink(modules.resolve(), work / "node_modules", target_is_directory=True)
+        cmd = ["timeout", "-k", "10", "120", "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")
+        originals = {file: (work / file).read_bytes() for file, _, _ in changes}
+        try:
+            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=140)
+            if mutant.returncode != 1:
+                raise SystemExit(f"{name}: expected assertion failure exit 1, got {mutant.returncode}")
+        finally:
+            for file, content in originals.items():
+                (work / file).write_bytes(content)
+            assert all((work / file).read_bytes() == content for file, content in originals.items())
+            assert hashes(ROOT, product_files) == original_products, 'checkout product hashes changed'
+            (OUT / f"{name}-restored.sha256").write_text(''.join(f'{digest}  {file}\n' for file, digest in sorted(original_products.items())))
+        with (OUT / f"{name}-restored-green.log").open("w") as log:
+            restored = subprocess.run(cmd, cwd=work, stdout=log, stderr=subprocess.STDOUT, timeout=140)
+        if restored.returncode:
+            raise SystemExit(f"{name}: restored control RED")
+        summary.append(f"{name}: killed (control green, mutant exit {mutant.returncode}, hashes restored, restored green)")
+        (OUT / "summary.txt").write_text("\n".join(summary) + "\n")
+        print(summary[-1], flush=True)
@@ -0,0 +1,112 @@
+1:  e25ef0373 ! 1:  b9ef816ff launchpad: row 217 C2-06 work in progress, UNTESTED, handed to Beakley (mos-1500)
+    @@ packages/bus/src/broker.mjs: export class Broker {
+            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 (request.verb === 'grants.scope' || request.verb === 'grants.scope.set')
+    +         return this.#grantScopeVerb(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
+    @@ packages/bus/src/runtime.mjs: export async function startBroker({
+            project: {
+              readSpec: context => projectModule.readSpec({ ...context, dataRoot }),
+     @@ packages/bus/src/runtime.mjs: 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);
+    +         // Row 298: the human's grant scope, through the instance writer.
+    +         else if(verb==='grants.scope.set')result=instances.grantScope(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.
+    @@ packages/business/src/organization.mjs: export function organizationWriter({ dir
+          const parent = join(dir, "businesses");
+          directory(evidence);
+     @@ packages/business/src/organization.mjs: 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
+    +         // 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
+     @@ packages/business/src/organization.mjs: 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();
+    +         const written = JSON.parse(bytes);
+    +         if (canonicalJson(written.projects) !== canonicalJson(old.projects))
+    +           fail('organization-projects-protected');
+    ++        replyLimitsFence(old, written, actor);
+    +         validateBusinessDocument(written, file, { rolesDir });
+    +         if (beforeWrite) {
+    +           beforeWrite();
+     @@ packages/business/src/organization.mjs: export function organizationWriter({ dir, rolesDir, barrier = () => {} }) {
+          });
+        }
+    @@ packages/library/src/guard.mjs (new)
+     +}
+
+      ## packages/library/src/index.mjs ##
+    -@@ packages/library/src/index.mjs: 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';
+    +@@ packages/library/src/index.mjs: export { SYNC_STATE_FILE, mirrorPath, ensureMirror, withLibraryLock, servedCommi
+      export { syncCommand, sync, ASKPASS, SLOT, SYNC_INTERVAL_MS } from './sync.mjs';
+    + export { buildIndex, indexFor, clearIndexCache, indexCacheSize } from './index-build.mjs';
+    + export { sees, find, get, search, manuscript, universeInfo, QUERY_REPLY_CAP, LOOKUP_LIMIT, MANUSCRIPT_LINES } from './query.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';
+
+2:  c25f5b8da ! 2:  7400509ba row 217: citation runner retry and acceptance draft (Untested)
+    @@ Commit message
+         row 217: citation runner retry and acceptance draft (Untested)
+
+      ## BUILD-LOG.md ##
+    -@@ BUILD-LOG.md: 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.
+    +@@ BUILD-LOG.md: remain; no live state, schema or bus policy change.
+
+    - 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.
+    -+
+    + 2026-10-24 | Goldie | Row265 / #1770 verified (mos-1567, sage-3942) | Approved correction adds solely address import pin + Row265 comment to project-runtime.test and one pure-source RUNNER_FILES mount; new block checks parser has no imports. Serialized fresh-short-TMP timeout-k10: unchanged sandbox10/10, parser15/15, rooms18/18, full bus957/957, twelve named refusal mutants killed (each Node1, driver0), restored parser15/15 + rooms18/18. All positives zero fail/skip/cancel; every mutation restored full broker SHA71b32ee4. Old first-red evidence retained, no other old-test change. Slot returned goldie-0034; Boyd packet explicitly includes mount-list review, candidate push next.
+    + 2026-10-24T07:18:53Z | Sage | Row 327 (#1825, Bradford, Poe and Dewey) LANDED 68c08b4e7. Before: refactor at 94d9e90a6; the push guard was a scratch script with no reviewed-binary check. After: scripts/push-check.sh and scripts/test-push-check.sh on refactor, 3 commits cherry-picked onto 6a5e12511 with blobs equal to the round 3 tip d858c9f8b, plus doc commits 76f84465f and 68c08b4e7. Binaries are found by numstat or a NUL in the first 8000 committed bytes, regardless of attributes; each needs its sha256 and path in an approved latest-round candidate; an unconfirmed queue tail exits 2. Reviews: Poe c31525 rev 3882, Dewey c31526 rev 3883. Gate: 1st run 06:57Z RED, not the candidate: canonical node_modules was empty from 05:45:15Z (sage-4023). Rerun with its own root npm ci GREEN 07:15:49Z: 17 package suites 0 failures (cli 986, plugins 119, webui 418), 11 scripts exit 0, push-check 6 mutants KILLED; skips are the queue canonical-root check and the row 244 live provider cases. The landed push-check.sh passed its own push (NO_BINARY, NO_ATTRIBUTION, PUSH_READY). mos-1575: gates install their own node_modules; canonical restored with npm ci (128 packages).
+     +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.
+    @@ agents/beakley/work/queue-217/mutants.py (new)
+
+      ## docs/SESSIONS.md ##
+     @@ docs/SESSIONS.md: 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.
+    + 2026-10-24T04:27Z | Goldie (a13dd6d5-5e73-4b7d-8318-02abeff24940) | Row265 / #1770 C2-09b rooms | Goldie owns build, Boyd reviews under sage-3915. New goldie/row265 worktree at ec86f2c84, claim rev3814; room verbs/parser/new tests prepared, no old tests changed. Sage-3932 slot: new parser14/14 and rooms18/18 passed; whole bus in progress before refusal mutants, stop rule active.
+    + 2026-10-24T04:35Z | Goldie (a13dd6d5-5e73-4b7d-8318-02abeff24940) | Row265 / #1770 verified | First slot stopped at project-runtime import pin. mos-1567 narrowly authorizes pin and pure-source mount correction. sage-3942 rerun: sandbox10/10, parser15/15, rooms18/18, bus957/957, twelve refusal mutants killed/restored SHA71b32ee4, parser15/15 + rooms18/18 again. Slot returned goldie-0034; no further test runs. Boyd reviews RUNNER_FILES alongside rooms; own-branch push/claimant in-review next.
+    + 2026-10-24T07:18:53Z | Sage (1ef1e4f8) | Row 327 / #1825 push guard landed (mos-1572 option A, mos-1575) | Gate went red 06:57Z on an empty canonical node_modules (Glomgold's webui npm ci through a link to canonical, glomgold-0011); rerun with its own npm ci GREEN 07:15:49Z on 1bd214e38; pushed 68c08b4e7 07:18:03Z; #1825 closed c31530; canonical restored (128 packages); brief template rule 4db23a51f | landed
+     +
+     +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.
+
+3:  b6c3129d2 ! 3:  a447880cb row 217: early-review coverage and availability RED cases (Untested)
+    @@ Commit message
+         row 217: early-review coverage and availability RED cases (Untested)
+
+      ## BUILD-LOG.md ##
+    -@@ BUILD-LOG.md: Row 299 (573, #1806, Gander, Filbert): before, the P10 band test timed a fault r
+    +@@ BUILD-LOG.md: remain; no live state, schema or bus policy change.
+      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.
+4:  dde5b8496 = 4:  2655ec010 row 217: keep fixture status on its current served tip (Untested)
@@ -0,0 +1,30 @@
+# Row217 round2 test receipts
+
+Sage CLEAR sage-4042/4043, 2026-10-24. Source revision 2d274a5b6. All runs
+serialized; source files stayed unchanged through the whole-suite and mutant pass.
+Commands used TMPDIR=/mnt/storage/scratch/tmp/tNoueZ and timeout -k 10.
+
+- npm ci --ignore-scripts --no-audit --no-fund at the worktree root (300s bound),
+  then packages/webui (300s). Actual directories, no canonical links.
+- node --test packages/bus/tests/citation-availability.test.mjs (180s).
+- python3 agents/beakley/work/queue-217/mutants.py <m5-red> M5-hide-library-unavailable
+  (420s). Green control, the authorized pre-fix RED stand-in, restore+green.
+- node --test --test-concurrency=1 with the seven new test files (900s):
+  library/guard, business/reply-limits, cli/reply-limits, bus/citation-availability,
+  bus/citation-guard, bus/citation-runtime and harness/citation-runner. Whole files.
+- First attempt 56/57: new runtime fixture invalid-authority. Only that fixture
+  was corrected to the established broker projection. runtime-fixture-retry.log
+  is its 1/1 rerun (180s); touched-rerun.log is the whole-file 57/57 rerun.
+- npm test in packages/library, then business (900s each), bus and cli (1200s
+  each), harness and seat (900s each). Never overlapped package runs.
+- python3 agents/beakley/work/queue-217/mutants.py <mutants> (900s).
+  The driver wraps each Node run in timeout -k 10 120. Each negative exits1,
+  is preceded by a green control, restores its product bytes/hashes and then
+  reruns the restored control green. No checkout product file is mutated.
+
+summary.json holds complete counts; summary.txt is the short version. M1 anchors
+are recorded in m1-anchors.txt. The five *-restored.sha256 files match current
+product files. Full outputs are retained, including the first new-test failure.
+Negative logs intentionally keep Node's whitespace-only diagnostic padding;
+standard git diff --check flags that padding, not source code. No binary logs.
+No old test failed or was edited. Sage runs scripts/test-*.sh at landing.
@@ -0,0 +1,11 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5142.976705ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (33.874404ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (33.746516ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 3
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5307.376982
@@ -0,0 +1,280 @@
+npm notice run @mosaic/[email protected] test
+npm notice run node --test tests/
+✔ a grant's level is collaborator or viewer (2.351697ms)
+✔ any other level refuses with the key path named (1.505284ms)
+✔ covers tells a viewer grant from a collaborator grant (0.605812ms)
+✔ covers refuses a call with no level, so a viewer grant can't slip past a collaborator check (0.247487ms)
+✔ a viewer grant still needs its business, project, instance and expiry to cover (0.247397ms)
+✔ a valid document passes and comes back frozen (4.146183ms)
+✔ checkAccess does not freeze or alias the caller's document (0.552481ms)
+✔ LEVELS is the single allowed level set, collaborator and viewer (row 193a) (0.259109ms)
+✔ accessFilePath is access.json in the config directory (0.495701ms)
+✔ top level: object, unknown keys, accessVersion, revision, arrays (2.131141ms)
+✔ users: unknown keys and the id rule (0.609866ms)
+✔ users: human, tester and any business's human are refused (0.455944ms)
+✔ users: home is a given peer or local (0.372673ms)
+✔ users: subjects, provider, sub, uniqueness and owner subjects (2.126611ms)
+✔ grants: unknown keys, id, user and business (0.897075ms)
+✔ grants: projects is ["*"] or distinct lowercase UUIDs (1.199677ms)
+✔ grants: instances is ["*"] or distinct declared instances of that business (0.889396ms)
+✔ grants: any level other than collaborator or viewer refuses, naming grants[i].level (1.13158ms)
+✔ grants: expires is optional ISO time, and a past expiry is not refused (0.979808ms)
+✔ the context is required and checked (1.713394ms)
+✔ loadAccess reads a valid file and checks it (0.755936ms)
+✔ loadAccess refuses a missing file, a symlink and a directory with exit 4 (0.519376ms)
+✔ loadAccess refuses another owner and group or other write (0.581157ms)
+✔ loadAccess refuses bad JSON and a bad document with exit 2 (1.841309ms)
+✔ covers: * and listed ids match (0.340508ms)
+✔ covers: an unlisted project, instance or business doesn't match (0.20254ms)
+✔ covers: an expired grant doesn't match, at and after the instant (0.698261ms)
+✔ covers: level is the least level asked for (row 193a) (0.213107ms)
+✔ covers: a missing or unknown level throws (row 193a, N1) (0.385188ms)
+✔ covers: a grant with an unknown level covers nothing (row 193a) (0.191435ms)
+✔ covers: now must be a valid Date (0.21008ms)
+✔ today's files load unchanged: identity, publish and remote are optional (11.61814ms)
+✔ a granted agent loads with its identity, grant and the project's upstream (4.906248ms)
+✔ N10: publish needs identity and a gitea definition, and the error names the grant (9.522958ms)
+✔ publish names declared projects that have a remote, each once (7.911234ms)
+✔ identity fields are checked (14.073433ms)
+✔ D9c: the upstream must be its own normalized form, exactly /OWNER/REPO (29.451403ms)
+✔ D9c: one .git is stripped, and the fork is built from the stripped name (1.733511ms)
+✔ D9c: gitea.url names the instance only (10.698646ms)
+✔ the upstream's host and port must be the agent's Gitea's (4.064711ms)
+✔ remote-not-fork: an upstream the agent's own user owns, compared without case (10.115713ms)
+✔ store references: own path only (design D1, D3a) (0.50611ms)
+✔ the role file loads and resolves through loadBusiness (18.165733ms)
+✔ the shipped file is exactly the approved list (1.392044ms)
+✔ the assistant's authority is message.send and record.write within role (4.312182ms)
+✔ the assistant talks to the user and the chief of staff only, and no other shipped role is limited (0.978023ms)
+✔ a business grant through limits does not widen the role (6.715605ms)
+✔ a launch block whose by is the assistant is refused (3.553443ms)
+✔ the instance takes no credential references and no tracker (9.975785ms)
+✔ an arbiter whose role definition declares messaging lists is refused, for each kind (8.992963ms)
+✔ an arbiter without messaging lists is accepted beside the limited assistant (3.104416ms)
+✔ the contract passes work to the chief of staff and directs no one (0.788753ms)
+✔ REQ-HARN-2: the assistant, companion and research hold the web grant, and no other role file does (1.683056ms)
+✔ C2-04: library mappings load without roots, remain frozen, and retain mapping refusals (31.538067ms)
+✔ C2-04: an otherwise valid publish grant cannot name a library repo (4.356759ms)
+✔ config directory and file path follow MOSAIC_CONFIG (0.467526ms)
+✔ the fixture business validates and comes back frozen (4.106001ms)
+✔ two instances may share a definition (2.097865ms)
+✔ top-level refusals (6.537312ms)
+✔ arbiters and projects (24.968268ms)
+✔ role instances (9.057417ms)
+✔ Vikunja bots (29.820456ms)
+✔ a role without Vikunja takes no tracker block (9.629575ms)
+✔ credential references match the definition's services (11.680645ms)
+✔ launch (31.945766ms)
+✔ REQ-THREAD-2 REQ-LAUNCH-1 launch.threadIdleSeconds: absent is the default, a positive integer is used, anything else refuses (34.141496ms)
+✔ loadBusiness: file checks (12.995702ms)
+✔ loadBusiness: not a regular file (111.510997ms)
+✔ loading writes nothing (1.787307ms)
+✔ names that are Object.prototype properties don't count as declared (5.786433ms)
+✔ the shipped example refuses as written and validates once filled in (2.551686ms)
+✔ persona vars: agent layer, creative definition only, both or neither (26.121282ms)
+✔ row 194 keep, noHire and retired validate, and a file without them loads as before (4.607715ms)
+✔ row 194 each bad keep, noHire or retired entry refuses (19.966409ms)
+✔ row 323: committed Case 1 document loads unchanged through the business loader (10.685638ms)
+✔ row 323: real business validate accepts the Case 1 fixture without tracker credentials (226.106251ms)
+✔ row 323: real factory install accepts the document's scratch input and writes it unchanged (294.937207ms)
+✔ row 323: the Case 1 business boots without a tracker or @sync credential (60.850375ms)
+✔ row 323: factory install refuses bus.tester false before writing (39.485453ms)
+✔ row 323: literal library key refuses through final business validation (176.986326ms)
+✔ row 323: a library project refuses through the factory profile plan (36.685902ms)
+✔ row 325: the Case 1 project's sole key matches the repository project id (7.063988ms)
+✔ row 325: real business validate reports the copied repository project valid (203.591785ms)
+✔ row 325: the old mosaic-stack project key refuses against those same project bytes (227.47487ms)
+✔ the role file loads and resolves through loadBusiness (22.21166ms)
+✔ the shipped file is exactly the approved list (0.355811ms)
+✔ the resolved record matches the approved list, so a widened file fails (4.433743ms)
+✔ the chief of staff holds role.launch, message.send, role.end, organization.change, record.write, instance.name, role.hire and role.fire; every other action is gated (6.025087ms)
+✔ the pm does not hold role.launch (7.814194ms)
+✔ a business grant of a gated action through limits does not widen the role (5.309288ms)
+✔ a limit that drops role.launch leaves the chief of staff with no launch block (5.488981ms)
+✔ a launch block whose by is the pm instance is refused (4.031539ms)
+✔ the contract names no duty to talk to the human and the pm contract no launch (1.077581ms)
+✔ the instance takes no credential references and no tracker (7.111256ms)
+✔ C2-04: business validate and resolve skip a library before code projects and credential checks (581.819531ms)
+✔ usage errors exit 4 (330.347677ms)
+✔ validate: a good business exits 0 and prints instance digests (80.712835ms)
+✔ validate: project files (358.68705ms)
+✔ validate: missing files and a broken system config (272.747082ms)
+✔ validate: credential reference problems exit 2 and name each one (75.47514ms)
+✔ validate: a not-issued store agent dated today passes, and an issued one with a past expiry fails (152.378642ms)
+✔ validate: a token file inside the repository is refused (76.459487ms)
+✔ validate: role definitions come from MOSAIC_ROLES_DIR (210.323656ms)
+✔ resolve: prints one instance's record (260.543734ms)
+✔ resolve: refusals (375.881441ms)
+✔ parse: exactly one of file or env, plus the service's date (3.551882ms)
+✔ check: a good file has no problems (1.2198ms)
+✔ check never opens the file: a write-only token passes (0.477268ms)
+✔ check: file problems (1.60977ms)
+✔ check: token files can't live in the repository or dataRoot, even through a linked directory (1.508979ms)
+✔ check: dates and environment references (0.686041ms)
+✔ each definition loads, with a contract file, and is exactly the approved list (4.83466ms)
+✔ an organization file that declares them passes, and each resolves to least privilege (10.307081ms)
+✔ the chief of staff launches each one; no other role does (11.082937ms)
+✔ a C-suite role can't be made the launcher: launch.by must hold role.launch (5.052598ms)
+✔ limits can narrow a C-suite role but never widen it (4.524289ms)
+✔ any unknown key, tool, action or version in a role file is refused (4.904699ms)
+✔ row 298: checkGrantScope takes the D2 shape and refuses anything else (2.752624ms)
+✔ row 298: a missing scope is empty and a bad one falls back to empty, which covers nothing (0.482721ms)
+✔ row 298: a Gitea grant is in scope only when its agent and every project are listed (0.341447ms)
+✔ row 298 (sage-3594 Q2): host commands match whole argv tokens, and enrollment is never in scope (0.467524ms)
+✔ row 298: a bad grantScope in the file still loads, and the read shows the fallback (18.355754ms)
+✔ row 298: the writer checks the scope, logs the change and removes the key for {} (142.313501ms)
+✔ row 298 (sage-3594 Q1): the general writers can't write grantScope (25.353249ms)
+✔ REQ-WAIT-1: GATED_ONLY is exactly the hard waits; the new actions are in the vocabulary (1.86466ms)
+✔ REQ-ROLE-2: END_PROTECTED includes the assistant's thread definition (0.234237ms)
+✔ REQ-COS-3: role.hire and role.fire are routed, not hard waits (0.300439ms)
+✔ REQ-WAIT-3: every action is routed or a hard wait, never both, and the routed list names only actions (0.967731ms)
+✔ REQ-WAIT-3: instance.name is routed under REQ-MSG-2 (1.5), not a hard wait (row 141, sage-0589) (1.313696ms)
+✔ REQ-WAIT-2: a role listing a hard wait at either class is refused; the actions that left can be granted (5.343386ms)
+✔ S1: the business file refuses hosts at the top level and in a role, and host.<id> references (56.500208ms)
+✔ T1: address, user and host key checks, which the enrollment raise uses (11.374442ms)
+✔ T26: no wildcard and no shell, runner or interpreter as a prefix (2.722004ms)
+✔ D6: argv shape and the literal prefix match (0.922698ms)
+✔ C2-04: instance settings skip a library while checking a later code project (98.596648ms)
+✔ row 165 read lists each instance and the definitions add accepts (16.615936ms)
+✔ row 165 add: two instances join, validate exits 0, the log names the human, and the writer asks for no restart (row 194, D3) (308.207149ms)
+✔ row 165 change: definition, vars and launch membership log before and after; none asks for a restart, the bus reloads (row 194, D3) (180.35178ms)
+✔ row 165 refuses each validation failure and leaves the file's bytes alone (44.040709ms)
+✔ T19 add of a credentialed definition writes store references dated today, names its bot, and validate exits 0 (101.60641ms)
+✔ T19 add of a definition that declares host writes references for its token services only (12.273146ms)
+✔ row 165 refuses a definition change to or from one that declares credentials (6.011439ms)
+✔ row 165 a vars or launch change on an instance with its binding succeeds and keeps the binding (87.081633ms)
+✔ row 165 refuses an END_PROTECTED definition and every change to a protected instance (9.425714ms)
+✔ row 165 refuses while a project file doesn't resolve, as validate would (21.508015ms)
+✔ row 165 refuses a stale revision and leaves the file's bytes alone (13.794117ms)
+✔ row 65 an instance write refuses harness-off, thinking-unsupported, an unknown model and a partial fallback (38.79158ms)
+✔ row 213 a creative instance is the human's: add, vars and definition changes, persona digest only (105.47603ms)
+✔ row 256 T1-T3, T5 the human deletes a creative instance, no other actor does, and the assistant stays (106.119319ms)
+✔ row 256 T4 the human's delete of the only listed instance, a creative one, is the last-listed refusal (3.635722ms)
+✔ REQ-LIMIT-1 schema: every scope unset or zero, adjustable above four, bad values and unknown models refuse (27.767213ms)
+✔ REQ-LIMIT-1 counts each exact scope at/over limit, unlimited and old tuple after model reassignment (1.218782ms)
+✔ REQ-ROLE-3 writer: atomic validated revision, immutable previous bytes and authenticated actor/old/new receipt (65.935591ms)
+✔ REQ-ROLE-3 writer: pre-rename fault leaves old file, post-rename recovery records commit, conflicting recovery refuses (42.79247ms)
+✔ REQ-LIMIT-1 / decision145 migration prints only, preserves values, rejects ambiguity, and is idempotent (20.740471ms)
+✔ REQ-LIMIT-1 shared settings validates the complete proposed selection and logs exact actor (73.013224ms)
+✔ REQ-LIMIT-1 provider is table data: another provider routes separately and aliases share exact counts (5.530215ms)
+✔ REQ-ROLE-3 refuses live writer locks, symlink targets and uncertain recovery without changing bytes (31.489428ms)
+✔ Q169 assistants: vars and definition change and log the actor; tracker null leaves no tracker (74.510885ms)
+✔ Q169 assistants: refuses other instances, other definitions, holder and credentials, empty entries, a tracker the definition has no credential for and a stale revision (46.648048ms)
+✔ Q169 assistants: a definition with a vikunja credential takes a tracker change and refuses its removal or a used bot (28.59175ms)
+✔ row 65 routes lists every instance with harness, model, thinking and fallback, the switched-on harnesses, the model keys and each harness's levels (4.496203ms)
+✔ row 65 setRoutes saves a harness, model, thinking and whole fallback, reads each back from the file, logs the actor, and a null fallback clears all three (28.880486ms)
+✔ row 65 setRoutes refuses a partial fallback, a switched-off harness, a level the harness doesn't apply, an unloaded module, an unknown model or instance, a malformed route, no change and a stale revision, with the file unchanged (33.617502ms)
+✔ row 65 a file with harness vars and no plugins.harness loads and its views read; a model change still saves, and a route change refuses harness-off (15.471063ms)
+✔ B7 kept instance: the models keys it names and the instances key are the human's (32.512862ms)
+✔ B7 kept instance: its route is the human's (13.733689ms)
+✔ M10 creative instance: models keys it names, the instances key and its route are the human's (41.972839ms)
+✔ C2-04 M9: changed playground and hybrid entries leave business and changes.jsonl byte-identical (75.744651ms)
+✔ C2-04 M9: code projects, additions, deletions and array changes are protected too (73.935851ms)
+✔ C2-04 M9: canonical key order is allowed and a non-project setter still records its change (53.997154ms)
+✔ C2-04 M9: a serialization hook cannot change projects after the canonical comparison (29.857522ms)
+✔ M7/M8: library seats come from library businesses, creative seats from their creative definitions (20.881147ms)
+✔ M8: a business with no library project puts no seat in either set (19.190367ms)
+✔ M7/M8: a business file that is not valid JSON throws; no empty set (7.135915ms)
+✔ M7/M8: an absent businesses directory gives empty sets (1.688414ms)
+✔ M7/M8: a businesses path that is not a directory throws; no empty set (4.583153ms)
+✔ M7/M8: a businesses symlink to a missing target throws; no empty set (2.208552ms)
+✔ M7/M8: a config directory under a regular file throws (lstat fails with ENOTDIR); no empty set (0.601986ms)
+✔ M7/M8: a business file that can't be read throws; no empty set (12.318486ms)
+✔ T6 delete refuses in the design's order and leaves the file's bytes alone (104.896221ms)
+✔ T6 delete refuses the last listed instance (7.490182ms)
+✔ T6 a clean delete removes the entry and its own references, adds retired, and the name can't come back (213.690055ms)
+✔ T7 veto: keep, unkeep, nohire and hire each write once, a repeat is no change, and the log names the human (171.894178ms)
+✔ T7 veto refuses an unknown or END_PROTECTED keep, a bad request, a stale revision and a business without launch (26.238526ms)
+✔ D2.2 hire adds and lists a new instance, logs the chief's context, and sets only model and limits (92.062371ms)
+✔ D2.2 hire refuses noHire, a kept name and a listed name, and re-lists a fired one only as it was (29.586421ms)
+✔ D2.2 fire delists and keeps the entry, a repeat is done with no write, and each refusal holds (88.451593ms)
+✔ row 256 checkDelete passes the human's creative delete and refuses another actor's; fire still refuses (5.294872ms)
+✔ row 239 T1 a fire on a revision that goes stale before the writer's lock refuses there and revokes nothing (5.756058ms)
+✔ row 239 T2 a write after the revoke refused before publication carries revoked, and the file keeps the edit (7.753057ms)
+✔ row 239 T3 any error after the revoke carries revoked, for a fire and a delete; a revoke that throws carries nothing (32.403692ms)
+✔ Q247: omitting tracker loads as null and preserves independent role bots (10.793015ms)
+✔ Q247: real business validate passes without a sync credential reference or file (168.186763ms)
+✔ Q247: present tracker retains its values and validation without mutating the input (9.372029ms)
+✔ Q247: present null, undefined and malformed trackers still refuse (18.314895ms)
+✔ Q247: absent business tracker does not waive a role's Vikunja bot requirement (2.859494ms)
+✔ REQ-PLUG-1 schema: plugins is optional, names known kinds and checked module names (40.546579ms)
+✔ REQ-PLUG-1 REQ-ROLE-3 the setter writes plugins through the organization writer and logs old and new names (92.751615ms)
+✔ vikunja:19/309 a patch changes only the kinds it names; null removes one kind, explicitly and in the trail (100.494327ms)
+✔ vikunja:19/309 an unknown kind (set or removed), a bad module, an empty patch and null on the wrong shape are refused, nothing written (9.927988ms)
+✔ REQ-PLUG-1 REQ-ROLE-3 the writer checks the bytes it writes: a Date in plugins is refused there too (19.985103ms)
+✔ REQ-PLUG-1 REQ-ROLE-3 a refused setter write throws a code, changes nothing and logs nothing (4.143331ms)
+✔ vikunja:19/305 with an exists check, the setter refuses a module no tree file answers to, before anything is written (18.273494ms)
+✔ optional project repo is preserved and must be a normalized absolute path (32.895793ms)
+✔ loaded business project repo cannot be nested in any declared code checkout (6.807091ms)
+✔ path and load (3.706713ms)
+✔ refusals (1.897981ms)
+✔ record.write is within-role for the eleven approved v2 agents, never gated-only (3.85853ms)
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (98.331729ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (55.766765ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (17.47904ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (16.039248ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (17.259974ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (19.048524ms)
+✔ C2-04: a library first in projects does not hide a later project layer (21.880181ms)
+✔ systemVars flattens the validated config (1.820728ms)
+✔ precedence: system, business, project, project role, agent (10.989776ms)
+✔ limits narrow the definition and never widen it (8.400306ms)
+✔ role.launch stays within-role only for the instance the launch block names (18.468852ms)
+✔ limits.authority without role.launch leaves the launcher with no launch block (13.185333ms)
+✔ limits.authority narrows cross-role actions too (2.699689ms)
+✔ classify (6.249491ms)
+✔ the record carries what the broker and launcher need (4.7922ms)
+✔ digest: key order doesn't matter, any value change does (12.395981ms)
+✔ refusals (3.790542ms)
+✔ the four shipped version 2 roles load (5.229965ms)
+✔ shipped role scopes match addendum B section 2 and the SR runbook (2.178782ms)
+✔ shipped authority follows the note's table (13.291498ms)
+✔ every role file in roles/ loads through the validator, and a v2 contract exists (2.100731ms)
+✔ version 1 files keep loading with no authority (1.521097ms)
+✔ the conductor policy isn't a role (0.302424ms)
+✔ a missing role file is exit 4, a symbolic link too (0.564721ms)
+✔ version 2 refusals (3.788273ms)
+✔ authority: closed vocabulary, no gated-only action, no overlap (3.881951ms)
+✔ messaging: optional, role definitions and human, never the tester (1.949889ms)
+✔ row 64 skills: optional, distinct skill directory names, none on version 1 (2.255987ms)
+✔ credentials: Gitea scopes (1.343013ms)
+✔ credentials: Vikunja scopes are a group-to-verbs map from the grantable list (1.709889ms)
+✔ credentials: services (0.759517ms)
+✔ contract: a non-empty regular Markdown file beside the role file (0.838905ms)
+✔ the six creative roles load: read tools, message.send only, messaging with the human only (0.693212ms)
+✔ M1: a creative role file wider than read and answer is refused (1.897832ms)
+✔ hireable: HIRE_ALLOWED is exactly the six plain work actions, and every one is routed (0.173708ms)
+✔ hireable: a list naming a definition that holds any refused action refuses at load, one case per action (18.133668ms)
+✔ hireable: a mixed definition refuses, a clean list loads, and the named file's own hireable isn't read (1.146869ms)
+✔ hireable: a missing, version 1, duplicate or badly named entry refuses, and the key is optional (3.734122ms)
+✔ the pm and the cto check a saved spec against settled decisions and work in flight, and answer with a BLOCK or an accept (11.616694ms)
+✔ the chief of staff relays a BLOCK or an accept to the assistant as a reply to the message that carried it (1.277302ms)
+✔ the assistant summarizes a spec review in its own words and doesn't repeat the chief of staff's text (0.70976ms)
+✔ REQ-LIMIT-3 schema: each subject kind, limit 0 and no ceiling are accepted; bad limits, times, keys and undeclared instances refuse (49.216064ms)
+✔ REQ-LIMIT-3 the writer stamps since: a new limit gets now, a changed one keeps its time, a different time is refused (85.0223ms)
+✔ REQ-LIMIT-3 only tokens.* at schema depth holds token limits: agent limits named `limit` save as sent, and a token limit named `limit` is stamped and reset (67.775561ms)
+✔ REQ-LIMIT-3 a reset moves since to now, is logged with its actor, and refuses a path that is not a limit (34.296428ms)
+✔ REQ-LIMIT-2 schema: launch.account names a credential set; a daily quota needs a reset and an IANA zone and names the account (33.871693ms)
+✔ REQ-LIMIT-2 the writer stamps a daily quota's since, keeps its reset and zone, and a reset moves since (33.845575ms)
+✔ every key names known layers and a merge rule (1.726458ms)
+✔ unknown keys and wrong layers refuse (1.084085ms)
+✔ types (3.275461ms)
+✔ merge: defaults, then the most specific layer wins (0.419589ms)
+✔ merge: limits only narrow, and provenance lists each source (0.757115ms)
+✔ merge doesn't change its inputs (0.206627ms)
+✔ web.searxng takes https anywhere and http on loopback, so Jason's 127.0.0.1:8888 passes (0.262745ms)
+✔ both definitions load, with a contract file, and are exactly the approved lists (5.013658ms)
+✔ security-reviewer has no write or shell tool and classifies only the verdict as its own (9.066819ms)
+✔ merge-gate's only grant is git.merge.protected cross-role, and it has no write tool (3.470869ms)
+✔ neither role can be an arbiter: its messaging lists refuse the business file (row 133) (8.498658ms)
+✔ every role contract carries the proactive line in its Authority section (1.099286ms)
+✔ pm and chief-of-staff say where a raise goes under REQ-DEC-2 (0.851681ms)
+✔ the merge landing takes two runs: merge-gate, cto and chief-of-staff each say their part (0.660442ms)
+ℹ tests 270
+ℹ suites 0
+ℹ pass 270
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 2873.146579
@@ -0,0 +1,182 @@
+npm notice run test
+npm notice run node --test tests/*.test.mjs
+✔ sessionModel: the route is the instance's own vars, and a missing one refuses no-route by name (37.340888ms)
+✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (10.573131ms)
+✔ a chief-of-staff bundle lists launch among the bus tools and the manifest's typed tools (4.412373ms)
+✔ a chief-of-staff bundle lists end_run, change_organization and set_name as typed and nothing untyped, for either harness (8.193363ms)
+✔ the stop line names end_run for a role.end holder, and every other role keeps today's text (13.648406ms)
+✔ a claude-code bundle adds the wrapped gate hook and the MCP config (7.875641ms)
+✔ the prompt's built-in tools line is the harness's own names, as the manifest lists them (22.548582ms)
+✔ the prompt names the project clones in the workspace, and none when there are none (13.290253ms)
+✔ the prompt explains the review loop to a role with push_working, and reviews to one with fetch_review (15.420914ms)
+✔ the prompt explains landing to a role with land_work, and to no other (9.918107ms)
+✔ the prompt tells the pm to ask the chief of staff for sessions, and no other role (18.356673ms)
+✔ a bundle is written once: an existing file refuses (3.135889ms)
+✔ a path with a single quote can't go into the hook command (3.86973ms)
+✔ web grant on pi: the bundle has web_search and web_fetch, and no built-in web tool (4.927453ms)
+✔ no web grant on pi: no web tool in the bundle, and the gate blocks a web call (4.535472ms)
+✔ web grant on claude-code: the bundle has web_search and web_fetch, and no built-in web tool (4.409455ms)
+✔ no web grant on claude-code: no web tool in the bundle, and the gate blocks a web call (7.034483ms)
+✔ a granted session's gate lets the typed web tools through and still blocks the built-ins (6.471178ms)
+✔ search-source searxng-url: a granted role gets the typed broker tools and no harness web tool; an ungranted role gets nothing (12.185523ms)
+✔ search-source searxng-bundled: a granted role gets the typed broker tools and no harness web tool; an ungranted role gets nothing (11.958441ms)
+✔ search-source harness-builtin: claude-code gets WebSearch and WebFetch and no typed web tool, only when granted (12.933659ms)
+✔ search-source harness-builtin is refused for a granted pi role, which has no built-in web tool (4.064682ms)
+✔ C2-06 RESULT reply-invalid retries once, delivers only the valid answer and names reason (351.396996ms)
+✔ C2-06 RESULT citation-missing retries once, delivers only the valid answer and names reason (256.673143ms)
+✔ C2-06 RESULT citations-over-limit retries once, delivers only the valid answer and names reason (222.852677ms)
+✔ C2-06 RESULT citation-invalid retries once, delivers only the valid answer and names reason (261.389143ms)
+✔ C2-06 RESULT playground-cited-as-canon retries once, delivers only the valid answer and names reason (268.849657ms)
+✔ C2-06 RESULT citation-cross-universe retries once, delivers only the valid answer and names reason (231.674929ms)
+✔ C2-06 RESULT citation-unfetched retries once, delivers only the valid answer and names reason (216.064282ms)
+✔ C2-06 RESULT two guard refusals use the citation fixed text and exactly one retry (188.874138ms)
+✔ C2-06 RESULT JSON 34000 characters retries with a shorter valid answer (236.68605ms)
+✔ C2-06 RESULT JSON 70000 characters retries with a shorter valid answer (234.722358ms)
+✔ C2-06 RESULT two oversized JSON bodies use the length fixed text with citations required (193.029509ms)
+✔ C2-06 multibyte plain bodies also receive the one request-size retry (223.988818ms)
+✔ C2-06 two multibyte plain bodies use the length fallback (205.649902ms)
+✔ C2-06 RESULT a length refusal then citation refusal shares one retry and citation fallback (206.128944ms)
+✔ C2-06 fixed empty/failed replies defer unslop note until the next cited reply (295.722008ms)
+✔ C2-06 cited JSON above the old 32000 clip retains its citations and text (189.724785ms)
+✔ C2-06 a flagged cited answer keeps the note inside text and citations whole (192.59344ms)
+✔ C2-06 send_message typed tool runs every guard code before the valid RESULT (262.703841ms)
+✔ C2-06 outside library the old failed text, clip and unslop behavior hold (208.584382ms)
+✔ C2-06 outside library a refused send keeps the existing no-retry behavior (159.048751ms)
+✔ C2-06 the retry turn delivers citation-unavailable reason to the agent (190.203749ms)
+✔ allow exits 0, a deny exits 2 with the reason on stderr (211.158287ms)
+✔ a missing or wrong policy, or a bad event, exits 2 (113.877105ms)
+✔ the bundle's wrapped command: a missing gate or node still blocks (1104.288151ms)
+✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (1070.940549ms)
+✔ claude: the hook alone blocks a path outside the workspace (568.174554ms)
+✔ claude: a second turn resumes the first turn's session (940.097062ms)
+✔ claude adapter: --restricted is always passed (6.108878ms)
+✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (19.555633ms)
+✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (6.450898ms)
+✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (912.426727ms)
+✔ claude: a missing hook or MCP file refuses before claude starts (8.255308ms)
+✔ claude: row 66 a reply with a tell gets the correction notice on the next turn, a clean reply gets none, and the counts read after (1813.719749ms)
+✔ claude: row 66 a broken lists.json gives no clean verdict, the operator is told once, and the session still answers (861.243377ms)
+✔ M2: the gate refuses write, edit and bash to every creative role on pi and claude-code (58.57362ms)
+✔ M6: no creative session gets raise_decision; the assistant and the chief of staff keep it (27.01682ms)
+✔ web: research and companion get the broker's typed web tools, and a harness-builtin source refuses web-source-not-allowed (34.87358ms)
+✔ persona: the block sits between the contract and ## This session, fenced, with the name and digest (10.05189ms)
+✔ persona: each unsafe or unpinned file refuses before the bundle directory is made (30.976676ms)
+✔ adapters pass the prompt file's absolute path; the persona and the prompt text never sit in argv (48.053085ms)
+✔ the pi adapter refuses a missing, unreadable or directory prompt file before pi starts (13.20329ms)
+✔ pi: policy tools and typed tools pass, anything else is blocked (4.524582ms)
+✔ claude: builtins map from pi names, typed tools need the mcp prefix (1.1263ms)
+✔ file tool paths must resolve inside the workspace (4.02957ms)
+✔ pi's own path normalisation can't be used to step out (1.586245ms)
+✔ a symlink inside the workspace that points out is outside (1.300474ms)
+✔ a dangling symlink is refused at any depth, in both harnesses (5.091178ms)
+✔ read is checked under every spelling pi's read would open, in both harnesses (29.6566ms)
+✔ other spellings cover directories, dangling links and pi's cwd (2.651598ms)
+✔ a relative path climbs from the workspace's real path, in both harnesses (9.557314ms)
+✔ claude path fields per tool (1.146391ms)
+✔ glob patterns stay inside the workspace (1.220629ms)
+✔ a path that can't be checked is blocked (0.713439ms)
+✔ fetch_review's have lists the working refs before origin's, and no more than HAVE_MAX (358.466429ms)
+✔ fetch_review's have orders the working refs newest first within each clone, one clone after another (177.220281ms)
+✔ a runner git past its time: SIGTERM reaches its process group, and SIGKILL follows after the grace period (1810.093816ms)
+✔ once a signalled runner git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (303.717292ms)
+✔ land_work sends one land line and resolves the host's started answer (3.694332ms)
+✔ initialize, ping and tools/list (73.055562ms)
+✔ tools/call goes through the tool socket; a refusal is an isError result (66.566638ms)
+✔ replies are compact JSON; over the cap a tool error names the size and the cap (60.558157ms)
+✔ unknown tools and methods are JSON-RPC errors and never reach the socket (52.967178ms)
+✔ a missing argument is a usage error (35.244954ms)
+✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (676.072372ms)
+✔ pi: a reply over the cap is a tool error naming the size and the cap; list_tasks asks for open tasks (532.762084ms)
+✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (479.264215ms)
+✔ pi: a read is refused when pi would open another spelling outside (479.008336ms)
+✔ pi: a relative path climbs from the real path of a workspace behind a symlink (495.496517ms)
+✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (458.873867ms)
+✔ pi: a missing extension refuses before any model call (6.358156ms)
+✔ pi: an extension without its configuration fails pi's start (380.653357ms)
+✔ pi: row 66 a reply with a tell gets the correction notice on the next turn, a clean reply gets none, and the counts read after (1353.463628ms)
+✔ pi: row 66 a broken lists.json gives no clean verdict, the operator is told once, and the session still answers (748.010347ms)
+✔ raise_decision offers domain as technical or delivery only, optional, and says where a raise goes (23.00088ms)
+✔ raise_decision forwards domain to decision.raise, and a call without it sends none (100.23044ms)
+✔ founderCheck: founder variables, then a needed service without a usable token (3.039179ms)
+✔ turnRequest names the sender, class, reply and decision (0.355597ms)
+✔ turnRequest says a tester's message is a test and never Jason's instruction (0.317095ms)
+✔ turnRequest says a user's message is a granted user's and never the owner's instruction (0.277911ms)
+✔ turnRequest shows the message's own sent time, a day old as well as new (0.227187ms)
+✔ stateBlock names the launch state with its time and event, and the open tasks with the cap (0.334368ms)
+✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (257.255462ms)
+✔ launches revoked and then restored: the turn's block reads allowed and gives the restore time (272.592717ms)
+✔ a task closed on the tracker is missing from the next turn's open list (239.571073ms)
+✔ a message read a day after it was sent shows the time it was sent (148.998515ms)
+✔ a decision the human resolves becomes a turn citing the decision and the answer (196.043584ms)
+✔ a failed state read fails the turn: no adapter runs, the sender hears why, the message is read (103.372577ms)
+✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (91.622163ms)
+✔ typed tools carry the runner's capability; launch goes to the host's launch socket (336.226718ms)
+✔ end_run, organization_revision and change_organization reach the broker with the tool's arguments, and refusals keep their codes (429.635331ms)
+✔ set_name reaches the broker's name.set with the tool's arguments, and refusals keep their codes (182.337097ms)
+✔ a RESULT gets no automatic reply; failed turns reply with the reason (1269.003752ms)
+✔ the bus's launch notice is one turn with no reply, and is not taken again (269.091562ms)
+✔ SIGTERM during a turn kills the turn's process group and still exits 0 (122.399792ms)
+✔ founder credentials stop before the claim (20) (162.909348ms)
+✔ a refused claim exits 21; an ended run's capability exits 22 (165.231771ms)
+✔ the launch ending under a running session exits 22 (134.851141ms)
+✔ a broker that stays unreachable exits 23 after brokerRetries polls (234.508622ms)
+✔ a broker that is down at the claim exits 23, not 21 (78.168597ms)
+✔ no capability, or a malformed one, on stdin exits 2 (194.303544ms)
+✔ a missing or malformed policy exits 2 before the claim (120.576748ms)
+✔ REQ-LIMIT-4 runner brackets its actual harness turn before the reply and read receipt (194.53726ms)
+✔ REQ-LIMIT-4 a runner at its limit stops at the end of its turn: RESULT and read first, then exit 22 and a limit-check revoke (168.261307ms)
+✔ landingRequest is the fixed template, with the decision and task ref and nothing else (0.147237ms)
+✔ each landing entry is one turn before any message, with the state block and the fixed request; it sends nothing and reads nothing (226.715761ms)
+✔ an empty landing takes no landing turn: the message is turn 1 (195.475495ms)
+✔ a run in a landing turn isn't released for a second held decision until its landing turns end and it has read its messages (596.516739ms)
+✔ a malformed landing exits 2 before the claim, with no turn (568.856934ms)
+✔ row 65 a session.json without a turnEnd of marker or exit, or a harnessEnv of strings, exits 2 before the claim (269.597797ms)
+✔ row 65 harnessEnv reaches the adapter, and an exit harness needs no turn marker (141.169295ms)
+✔ row 66 the adapter gets the run's unslop log, and a flagged reply's note rides that reply's RESULT, once (300.426996ms)
+✔ row 66 a turn with no reply holds its note for the next reply; a broken check is told once (345.164969ms)
+✔ row 66 unslopNotes keeps a note until sent(), reads only whole lines, and unslopCounts reads a log after the session (1.68702ms)
+✔ row 66 a clipped answer with both note parts stays under the bus's body limit, and the note under 600 (161.518813ms)
+✔ row 66 a refused send keeps the note: it rides the next RESULT the session sends (264.81696ms)
+✔ each repo role's prompt carries exactly its listed skills, each file as the bundle copy and the source (69.791416ms)
+✔ a skill's files go into the prompt in sorted path order, sub-directories included (9.238961ms)
+✔ a role with no skills gets no Skills section, no skills directory and an empty manifest list (11.39746ms)
+✔ an enabled skill the role doesn't list stays out of the prompt (8.706347ms)
+✔ the bundle copy outlives the source: deactivating a skill after the build leaves the run's copy (4.473957ms)
+✔ a listed skill that isn't enabled refuses skill-not-enabled, naming the activate command (9.541232ms)
+✔ a skill directory that isn't plain refuses: a symlinked skill, SKILL.md or sub-file, or a non-file entry (2.643822ms)
+✔ a skill file that can't go into the prompt refuses: a bad name, non-UTF-8 bytes, or the end marker (3.518581ms)
+✔ a role's skills over SKILL_BYTES together refuse, naming the skill that crossed it (10.193929ms)
+✔ each adapter passes the skills only in the prompt file, with skill discovery off (59.00799ms)
+✔ every role sees read_spec, record writer follows its grant, citation schemas stay strict (25.138022ms)
+✔ typed socket forwards read content/history and agent record writes, and cannot write a spec (172.529974ms)
+✔ the PM gets its task verbs and the reads, and no launch (11.972118ms)
+✔ send_message offers the BLOCK class, beside the classes it already had (3.837774ms)
+✔ the chief of staff gets launch, send_message, end_run, hire, fire, change_organization and set_name, and no task verbs (4.871494ms)
+✔ hire and fire send instance.hire and instance.fire under role.hire and role.fire, only for a holder of the grant (22.751702ms)
+✔ request_staff is the pm's alone: staff.request over message.send, roles and counts bounded (15.291362ms)
+✔ end_run sends role and reason, no decision; change_organization sends revision and the organization keys (2.689052ms)
+✔ set_name sends instance and name to name.set under instance.name, only for a holder of that grant (12.695737ms)
+✔ the organization keys change_organization takes are the broker's ORGANIZATION_KEYS and the settings' SETTINGS_KEYS (0.178758ms)
+✔ a role without role.end or organization.change gets none of the three tools, and each follows its own grant (12.115972ms)
+✔ no role's tools send instances or instances.set, and change_organization takes no instance write keys (10.7825ms)
+✔ the assistant gets send_message, the reads and the web tools (it holds the web grant), no launch (2.17462ms)
+✔ list_requirements reads the requirement ids, for a task.create holder with a tracker (3.939398ms)
+✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (3.125698ms)
+✔ a coder with a tracker gets its own task tools and no task_reassign (2.258296ms)
+✔ launch only when the business's launch block names the instance as launcher (3.280204ms)
+✔ an action outside the instance's authority has no tool (1.994949ms)
+✔ the review loop: push_working and request_review for the coder, fetch_review and review_verdict for the reviewer, none for the PM (7.387015ms)
+✔ land_work is there only with land, after push_working, with the task and the decision (4.431191ms)
+✔ callTool: one JSON line out, the result back, a refusal rejects (16.610729ms)
+✔ list_tasks takes the broker's filters and pages; get_task takes a task_ref (4.144909ms)
+✔ callTool sends list_tasks done false unless the session names done; other tools as given (3.985977ms)
+✔ replyText: compact JSON up to the cap, an error naming the size and the cap over it (1.008682ms)
+✔ web_search's query maxLength is the web layer's SEARCH_MAX_QUERY_CHARS (4.810935ms)
+ℹ tests 172
+ℹ suites 0
+ℹ pass 172
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 12131.328093
@@ -0,0 +1,153 @@
+npm notice run @mosaic/[email protected] test
+npm notice run node --test tests/*.test.mjs
+✔ C2-06 reply schema: free bodies, exact objects and safe refusal reasons (31.081491ms)
+✔ C2-06 citation setting and all four exact fixed texts (27.31137ms)
+✔ C2-06 default citation cap passes 20 and refuses 21, even with optional citations (144.940253ms)
+✔ C2-06 real Git citation scope, reachability, lines and normalized quotes (71.988432ms)
+✔ C2-06 playground cites pass but cannot state canon (42.141068ms)
+✔ C2-06 independent universes refuse; a hybrid and only its sources pass (69.134397ms)
+✔ C2-06 web cites require allowed definition, this session fetch and kept quote (17.090852ms)
+✔ C2-06 file origin is the path commit and trailer, while last follows served changes (51.160201ms)
+✔ C2-06 origin uses literal paths even when a filename contains a glob (35.841257ms)
+✔ C2-06 cited-commit guard reads exactly the C2-05a indexed file set with supporting scope (79.711572ms)
+✔ C2-06 reply limits fall back independently without coercion or inherited keys (0.78046ms)
+✔ the same commit, repo path and mapping return the same index, and only mapped files are in it (53.330474ms)
+✔ a different repo path, mapping or commit gets its own index (73.465944ms)
+✔ the cache holds at most eight indexes and evicts the least recently used (93.355098ms)
+✔ a failed read is not kept in the cache (19.15839ms)
+✔ a missing or unchecked mapping is refused before any read (18.591276ms)
+✔ a 3,000-file rebuild completes and its time is reported (3339.384537ms)
+ℹ 3,000-file index rebuild: 3093 ms
+✔ resolver step 1: a path from the repo root, with or without .md (2.003164ms)
+✔ resolver step 2: the same path with vaultPrefix/ stripped (0.323373ms)
+✔ resolver step 3: a path relative to the linking file, never above the repo root (0.278534ms)
+✔ resolver step 4: a base name that matches exactly one indexed file (0.322938ms)
+✔ a link into another of her repos resolves to nothing (0.213594ms)
+✔ wikilink forms, embeds, and links skipped inside code (1.24016ms)
+✔ only a body embed whose target has an extension other than .md, in any case, is an attachment (0.455416ms)
+✔ the fixture mapping checks and comes back frozen (2.830981ms)
+✔ C2-01c: a prefix inside or holding another entry's book refuses library-playground-other-universe (1.34922ms)
+✔ C2-01c: a prefix equal to a book folder, or holding its own, refuses library-mapping-invalid (0.74756ms)
+✔ C2-01c: universe-level prefixes lie outside every book, in a plain universe and in a hybrid with no books (1.203696ms)
+✔ C2-01c: a draft takes kind, name and playground only, and comes back frozen with books [] (1.782129ms)
+✔ C2-01d: supporting prefixes at book level, universe level, in a hybrid and in a draft, [] when absent (0.643444ms)
+✔ C2-01d: each supporting prefix rule refuses with its code (2.880363ms)
+✔ C2-01d: between the lists, a supporting prefix may equal its own playground, and a playground may hold its own supporting (0.978814ms)
+✔ C2-01d: editor is optional, kept when given, and refuses anything but a plain name and email (5.417269ms)
+✔ C2-01d: an accepted editor round-trips through a real git commit unchanged (22.81842ms)
+✔ no playground prefix holds another, and no book folder holds another (1.309845ms)
+✔ shape refusals: kind, remote, branch, unknown keys, types, manuscript, folder names (1.68793ms)
+✔ C2-03a sage-2021: user is optional, kept when given, and must be a plain account name (0.986251ms)
+✔ a hybrid universe is a shape the query code can take (1.4), with sources that must exist (1.600445ms)
+✔ a caller-supplied fail receives the code, as business file loading will pass it (C2-04) (0.396233ms)
+✔ scope comes from the path alone (design 1.2) (2.453311ms)
+✔ C2-04 mirror: exact default path, bare without checkout or remote, and idempotent initialization (82.599485ms)
+✔ C2-04 mirror: simultaneous creators publish one intact mirror and leave no staging paths (49.399699ms)
+✔ C2-04 mirror: skipped publication accepts both coreutils statuses without removing the winner (174.577156ms)
+✔ C2-04 mirror: preserve occupied directories and reject symlink ancestors and code overlaps (20.556264ms)
+✔ C2-04 mirror: existing metadata accepts only bare Git plus state and the precreated lock (34.414614ms)
+✔ C2-04 state: missing state is empty only while the served ref is absent (54.101069ms)
+✔ C2-04 state: valid problems and sync metadata return no content and change no state bytes (57.832223ms)
+✔ C2-04 state: strict keys, types, times, branch, commit and fixed R messages fail closed (158.515834ms)
+✔ C2-04 state: symlink, hardlink, non-private state and missing lock refuse without replacement (57.609887ms)
+✔ C2-04 file: served commit, not HEAD or a caller commit, owns the exact returned text (113.829438ms)
+✔ C2-04 file: R1, R2 and R7 exclusions and never-synced mirrors cannot return file bodies (124.255784ms)
+✔ C2-04 lock: a first-sync and fast-forward reader wait for a consistent pair across processes (314.221744ms)
+✔ C2-04 lock: same-process waits, timeout code, callback expiry and throw release (5038.833094ms)
+✔ C2-04 lock: owner death releases the kernel lock without replacing its file (54.543028ms)
+✔ C2-04 lock: a missing flock binary becomes a handled refusal (49.73045ms)
+✔ C2-04 lock: an unawaited scoped read drains before the lock is released (20.869629ms)
+✔ the query reply cap equals the harness reply cap (1.544541ms)
+✔ find is bound to its universe and refuses a call without one (70.281377ms)
+✔ every result carries its scope, and playground appears only when asked for (39.878964ms)
+✔ unmapped files never appear in any reply (35.123505ms)
+✔ a hybrid sees its sources canon, minus exclusions, and no playground (39.679182ms)
+✔ a hybrid gets a source file it can see, and not an excluded or foreign one (54.602693ms)
+✔ get lists visible links both ways and drops a target another universe cannot see (50.638492ms)
+✔ a long list pages by position, never cuts an item, and returns 50 per page (193.227492ms)
+✔ a page stays under the reply cap when items are large (91.885035ms)
+✔ a search line too long to fit alone comes back marked, with no excerpt, and the other hits still return (33.20163ms)
+✔ a find item that cannot fit alone is refused, not cut (46.447292ms)
+✔ get pages its lines, and the next line picks up where the page stopped (39.12526ms)
+✔ get refuses a file whose front matter alone is over the cap, and a line alone is over the cap (36.804238ms)
+✔ get pages the links of a hub note, every page carries the front matter, and the pages add up (1107.995321ms)
+✔ get rejects a bad links_from (34.377162ms)
+✔ search returns scoped line hits, case-insensitively, and refuses empty text (30.729667ms)
+✔ a manuscript call returns one chapter, at most 400 lines, and names its next line (47.791378ms)
+✔ a manuscript call without a chapter returns the first chapter in path order and names the next (26.366902ms)
+✔ a chapter name that matches two visible files is refused (25.448584ms)
+✔ a hybrid reads a source chapter through its declared sources only (39.969561ms)
+✔ universe info reports a hybrid sources, constraints and notes, and refuses an unknown universe (15.657923ms)
+✔ an exclusion hides what it names from a hybrid and from nothing else (39.404555ms)
+✔ PRD 1.14: a lookup that names a book leaves book-null files out (34.647951ms)
+✔ PRD 1.14: library_manuscript never reads a book-null file (32.637362ms)
+✔ PRD 1.14: a draft universe has no canon, so its lookups return files only with scope playground (32.338176ms)
+✔ PRD 1.14: library_universe on a draft returns its kind, name and prefixes (15.442774ms)
+✔ a hybrid gets a source playground file as null, while the source gets it with scope playground (42.674554ms)
+✔ the fixture reads clean: every resolver step, appears_in and relationships wikilinks indexed (63.033383ms)
+✔ R1: executables, symlinks, gitlinks, blobs over 1 MiB and non-UTF-8 text are not indexed (95.339567ms)
+✔ R2: unmapped paths are reported and not indexed (31.564751ms)
+✔ R3: front matter not fully parsed stays raw, with the line where parsing stopped (36.896696ms)
+✔ front matter forms the reader accepts and refuses (1.596508ms)
+✔ R4: a link to no file, to more than one, or into another repo is reported and not followed (35.504393ms)
+✔ a block list link carries its item line, a scalar or flow link its key line, and problems follow (37.229678ms)
+✔ an unresolved attachment embed gives no problem; a link or front matter value to one is R4; a note embed resolves (33.783255ms)
+✔ an indexed Dr.Quinn.md resolves as a body link, a block list link and an embed (33.230236ms)
+✔ R5: a canon file that refers into the playground is reported, and the link still goes by path (29.709099ms)
+✔ R6: a canon file that refers into another universe is reported; a hybrid may refer into its sources (30.970646ms)
+✔ R7: two paths that differ only in case are both left out (41.126208ms)
+✔ the reader reads the commit, never the working tree, and refuses a bad commit id (41.98282ms)
+✔ a bare mirror reads the same as the clone (53.445984ms)
+✔ renderItems snapshot: fact (1.786386ms)
+✔ renderItems snapshot: finding (0.299155ms)
+✔ renderItems snapshot: correction (0.259329ms)
+✔ renderItems snapshot: question (0.218182ms)
+✔ renderItems snapshot: idea (0.223821ms)
+✔ renderItems numbers several items and takes a parsed body as well as a string (1.090019ms)
+✔ without options a path cite has no badge and is never marked changed (0.280013ms)
+✔ renderItems snapshot: notice no-cited-answer (0.237711ms)
+✔ renderItems snapshot: notice no-answer (0.198705ms)
+✔ renderItems snapshot: notice turn-failed (0.337126ms)
+✔ a body without the reply shape shows a fixed line and none of its text (0.613863ms)
+✔ C2-01c: each level gives its universe, and its book or null (4.092943ms)
+✔ C2-01c: prefixes come first: in a book that holds a prefix, a file outside it is canon and one under it playground (0.607188ms)
+✔ C2-01c: a canon file linking into a draft gives R6, and into its own universe-level prefix gives R5 (65.023589ms)
+✔ C2-01d: each supporting level gives its universe, and its book or null (0.8244ms)
+✔ C2-01d: supporting comes before playground; a folder in both lists is supporting, one in the playground only stays playground (0.633065ms)
+✔ C2-01d: only .md files are supporting; a .canvas or .base under a supporting prefix is unmapped (0.517375ms)
+✔ C2-01d: a path passes at book level, universe level, in a draft and in a folder in both lists (2.312377ms)
+✔ C2-01d: a path of exactly 1024 bytes passes, and 1025 bytes made of multi-byte characters refuses (0.98988ms)
+✔ C2-01d: a path outside the universe's supporting folders refuses (0.763326ms)
+✔ C2-01d: malformed paths refuse by class, in order (0.710036ms)
+✔ C2-01d: a symlink or gitlink on the way, or at the path itself, refuses (0.383033ms)
+✔ C2-01d: a name that differs from a tree name only in case or Unicode form refuses, at the file or any folder (0.99427ms)
+✔ the survey prints folder names, counts, key sets and link-form counts, and never text (65.469359ms)
+✔ folder names print DEL, C1 and bidi controls, U+061C among them, as escapes (37.571162ms)
+✔ an embed of an attachment counts as an embed and as an attachment; a plain link to one does not (24.053267ms)
+✔ with --mapping the survey adds scope, resolver step and problem counts (51.551822ms)
+✔ C2-01d: with --mapping the survey counts supporting files (49.232972ms)
+✔ survey exit codes: usage 4, bad mapping 3, unreadable repo 2 (19.679523ms)
+✔ scripts/mosaic library survey reaches the survey (97.237921ms)
+✔ C2-03a argv: the fixed sequence, one https allow, no other protocol key (2.539459ms)
+✔ C2-03a argv: only an https URL with a plain host, no userinfo, and a plain user (1.147619ms)
+✔ C2-03a helper: answers only the exact prompts for the configured host and user (dewey-0765) (43.662638ms)
+✔ C2-03a first sync: served is the fetched tip, HEAD is served, the survey reads it, and the token stays in the slot (199.624214ms)
+✔ C2-03a fast-forward: served moves, problems are rebuilt, and a repeat changes only lastFetch (272.12795ms)
+✔ C2-03a Filbert N2: a read that took served before a sync still finds its objects after served moves (255.892244ms)
+✔ C2-03a overlap: a reader during a sync sees the old pair or the new one, never a mix (220.077465ms)
+✔ C2-03a diverged: a non-fast-forward keeps serving and holds until a human accepts the tip (511.485441ms)
+✔ C2-03a accept starts the record over, so a changed branch gets a fresh state (204.895458ms)
+✔ C2-03a fetch failure: a wrong token keeps serving and records the error, lastFetch unchanged (210.171392ms)
+✔ C2-03a a failed first fetch records the error with nothing served (57.52009ms)
+✔ C2-03a a 302 to another host fails the fetch and the other host sees nothing (68.211135ms)
+✔ C2-03a the slot: missing or unsafe refuses before git, and sync never opens it (65.636096ms)
+✔ C2-03a sage-2021: an entry with no user refuses library-remote-invalid and runs no git (34.004871ms)
+✔ C2-03a one sync per mirror: an overlapping call refuses library-sync-busy (129.134012ms)
+ℹ tests 142
+ℹ suites 0
+ℹ pass 142
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 6490.060843
@@ -0,0 +1,2 @@
+1 match: replyLimitsFence(old, document, actor);
+1 match: replyLimitsFence(old, written, actor);
@@ -0,0 +1 @@
+M5-hide-library-unavailable: killed (control green, mutant exit 1, hashes restored, restored green)
@@ -0,0 +1,11 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5151.319291ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (37.53806ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (35.257703ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 3
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5310.30031
@@ -0,0 +1,11 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5147.642347ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (32.256875ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.701926ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 3
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5295.499085
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+168dcac99d9bfdfdf5ff0eaa2c0fff91595b351b4d0092dc299532c9c32869f0  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,68 @@
+✖ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5108.905478ms)
+✖ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (40.518617ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (37.68422ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 1
+ℹ fail 2
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5261.169843
+
+✖ failing tests:
+
+test at packages/bus/tests/citation-availability.test.mjs:13:1
+✖ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5108.905478ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  + actual - expected
+  
+  + 'citation-invalid'
+  - 'citation-unavailable'
+              ^
+  
+      at Object.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/bus/tests/citation-availability.test.mjs:29:14)
+      at expectedException (node:assert:547:17)
+      at expectsError (node:assert:672:21)
+      at strict.rejects (node:assert:738:3)
+      at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+      at async file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/bus/tests/citation-availability.test.mjs:28:5
+      at async withLibraryLock (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/library/src/mirror.mjs:171:18)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/bus/tests/citation-availability.test.mjs:27:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 'citation-invalid',
+    expected: 'citation-unavailable',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+
+test at packages/bus/tests/citation-availability.test.mjs:40:1
+✖ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (40.518617ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+  + actual - expected
+  
+    Comparison {
+  +   code: 'citation-invalid'
+  -   code: 'citation-unavailable'
+    }
+  
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/bus/tests/citation-availability.test.mjs:45:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: Error: citation-invalid: citation 1 (Book One/Characters/Mara Vell.md) isn't an indexed file at a commit reachable from the served commit
+        at refuse (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/library/src/guard.mjs:24:42)
+        at checkReply (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/library/src/guard.mjs:80:25)
+        at async waitForActual (node:assert:615:5)
+        at async strict.rejects (node:assert:738:25)
+        at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-pd3x2htc/packages/bus/tests/citation-availability.test.mjs:45:3)
+        at async Test.run (node:internal/test_runner/test:1409:7)
+        at async Test.processPendingSubtests (node:internal/test_runner/test:974:7),
+    expected: { code: 'citation-unavailable' },
+    operator: 'rejects',
+    diff: 'simple'
+  }
@@ -0,0 +1 @@
+M5-hide-library-unavailable: killed (control green, mutant exit 1, hashes restored, restored green)
@@ -0,0 +1,5 @@
+M1-writer-fence: killed (control green, mutant exit 1, hashes restored, restored green)
+M2-incoming-human: killed (control green, mutant exit 1, hashes restored, restored green)
+M3-split-check-transaction: killed (control green, mutant exit 1, hashes restored, restored green)
+M5-hide-library-unavailable: killed (control green, mutant exit 1, hashes restored, restored green)
+M4-drop-client-reason: killed (control green, mutant exit 1, hashes restored, restored green)
@@ -0,0 +1,14 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (29.278355ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (22.040025ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (8.805323ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (8.829275ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (9.171416ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (10.423621ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 6
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 139.016448
@@ -0,0 +1,14 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (27.397407ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (23.565905ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (8.312613ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (8.050944ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (8.746752ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (11.061782ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 6
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 137.787038
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,73 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (26.703775ms)
+✖ C2-06 M11 agents and tester cannot change settings, including by changing human (12.156717ms)
+✖ C2-06 M11 serialization cannot replace settings after the first fence (11.431272ms)
+✖ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (14.308135ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (9.043165ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (9.576698ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 3
+ℹ fail 3
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 131.91294
+
+✖ failing tests:
+
+test at packages/business/tests/reply-limits.test.mjs:34:1
+✖ C2-06 M11 agents and tester cannot change settings, including by changing human (12.156717ms)
+  AssertionError [ERR_ASSERTION]: Missing expected exception.
+      at refused (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:22:10)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:37:5)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
+      at Test.postRun (node:internal/test_runner/test:1542:19)
+      at Test.run (node:internal/test_runner/test:1467:12)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
+    generatedMessage: false,
+    code: 'ERR_ASSERTION',
+    actual: undefined,
+    expected: { code: 'organization-reply-limits-human-only' },
+    operator: 'throws',
+    diff: 'simple'
+  }
+
+test at packages/business/tests/reply-limits.test.mjs:43:1
+✖ C2-06 M11 serialization cannot replace settings after the first fence (11.431272ms)
+  AssertionError [ERR_ASSERTION]: Missing expected exception.
+      at refused (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:22:10)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:45:3)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
+      at Test.postRun (node:internal/test_runner/test:1542:19)
+      at Test.run (node:internal/test_runner/test:1467:12)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: false,
+    code: 'ERR_ASSERTION',
+    actual: undefined,
+    expected: { code: 'organization-reply-limits-human-only' },
+    operator: 'throws',
+    diff: 'simple'
+  }
+
+test at packages/business/tests/reply-limits.test.mjs:52:1
+✖ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (14.308135ms)
+  AssertionError [ERR_ASSERTION]: Missing expected exception.
+      at refused (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:22:10)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-m6rnq3wd/packages/business/tests/reply-limits.test.mjs:54:3)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
+      at Test.postRun (node:internal/test_runner/test:1542:19)
+      at Test.run (node:internal/test_runner/test:1467:12)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: false,
+    code: 'ERR_ASSERTION',
+    actual: undefined,
+    expected: { code: 'organization-reply-limits-human-only' },
+    operator: 'throws',
+    diff: 'simple'
+  }
@@ -0,0 +1,14 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (31.955623ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (22.832309ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (9.274775ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (8.69039ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (8.733202ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (10.441869ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 6
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 143.570268
@@ -0,0 +1,14 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (29.948602ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (22.139351ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (9.054641ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (8.381635ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (9.081946ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (10.33004ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 6
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 141.370383
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,35 @@
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (28.334896ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (22.541196ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (8.304131ms)
+✖ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (11.712463ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (8.875517ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (9.882976ms)
+ℹ tests 6
+ℹ suites 0
+ℹ pass 5
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 140.418146
+
+✖ failing tests:
+
+test at packages/business/tests/reply-limits.test.mjs:52:1
+✖ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (11.712463ms)
+  AssertionError [ERR_ASSERTION]: Missing expected exception.
+      at refused (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-_aqjby1c/packages/business/tests/reply-limits.test.mjs:22:10)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-_aqjby1c/packages/business/tests/reply-limits.test.mjs:54:3)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
+      at Test.postRun (node:internal/test_runner/test:1542:19)
+      at Test.run (node:internal/test_runner/test:1467:12)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: false,
+    code: 'ERR_ASSERTION',
+    actual: undefined,
+    expected: { code: 'organization-reply-limits-human-only' },
+    operator: 'throws',
+    diff: 'simple'
+  }
@@ -0,0 +1,21 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (118.943843ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (94.790271ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (65.901789ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (41.908138ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (48.179621ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (41.94764ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (56.521104ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (88.283371ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (55.47311ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.321347ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (77.5591ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (24.639839ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (42.159103ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 13
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 866.146033
@@ -0,0 +1,21 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (162.15169ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (151.110586ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (100.984805ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (81.389166ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (92.148118ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (78.197117ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (168.055107ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (271.850306ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (92.491602ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (61.315017ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (126.633466ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (61.436932ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (118.486786ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 13
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 1649.634687
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,41 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (121.738375ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (94.199334ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (59.307121ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (41.252933ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (48.700382ms)
+✖ C2-06 check evidence and insert are atomic when storing evidence fails (42.434516ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (56.552861ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (88.426285ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (54.352185ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.064514ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (81.176348ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (25.324993ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (42.147552ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 12
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 872.02572
+
+✖ failing tests:
+
+test at packages/bus/tests/citation-guard.test.mjs:71:1
+✖ C2-06 check evidence and insert are atomic when storing evidence fails (42.434516ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  
+  1 !== 0
+  
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-etkv3bqf/packages/bus/tests/citation-guard.test.mjs:76:10)
+      at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 1,
+    expected: 0,
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
@@ -0,0 +1,21 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (107.311079ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (92.235404ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (59.017311ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (41.107066ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (47.696908ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (41.214066ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (54.665908ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (86.001777ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (55.168942ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.744539ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (79.212003ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (24.722314ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (41.933148ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 13
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 841.716764
@@ -0,0 +1,21 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (110.781773ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (91.548051ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (57.119223ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (40.819326ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (47.776616ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (41.268825ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (53.375873ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (82.822565ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (54.131458ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.350984ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (80.819295ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (26.401011ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (41.116925ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 13
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 839.688386
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,47 @@
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (109.280676ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (94.019544ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (58.84355ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (42.275234ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (48.954969ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (41.628985ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (54.367118ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (85.049228ms)
+✖ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (53.346085ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.218776ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (78.373306ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (24.622347ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (41.8227ms)
+ℹ tests 13
+ℹ suites 0
+ℹ pass 12
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 840.560306
+
+✖ failing tests:
+
+test at packages/bus/tests/citation-guard.test.mjs:116:1
+✖ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (53.346085ms)
+  AssertionError [ERR_ASSERTION]: The validation function is expected to return "true". Received false
+  
+  Caught error:
+  
+  Error: citation-invalid
+      at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-db3vgbd1/packages/bus/tests/citation-guard.test.mjs:121:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: Error: citation-invalid
+        at Socket.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-db3vgbd1/packages/bus/src/client.mjs:45:17)
+        at Socket.emit (node:events:514:20)
+        at addChunk (node:internal/streams/readable:575:12)
+        at readableAddChunkPushByteMode (node:internal/streams/readable:526:3)
+        at Readable.push (node:internal/streams/readable:406:5)
+        at Pipe.onStreamRead (node:internal/stream_base_commons:189:23),
+    operator: 'rejects',
+    diff: 'simple'
+  }
@@ -0,0 +1,11 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5143.590096ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (33.560438ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.849587ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 3
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5290.343804
@@ -0,0 +1,11 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5131.56715ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (32.560014ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.756895ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 3
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5271.350019
@@ -0,0 +1,23 @@
+eeca81ab965f9e94f930ee5f51d16f019af6368bc6c3994895e204f7a54ec8d2  packages/bus/src/broker.mjs
+ad3c686a089f67f3c89610937c6fc9b32367cea5d9735125d89bef042082d4e8  packages/bus/src/client.mjs
+36b05dd3119e5929211aa1cc5d45c5043f5a1c34567ddc7cac8f002835d44abe  packages/bus/src/runtime.mjs
+66b26d131a19f4f411686427274936850c1ff0aed11e9b281ae4aadcf4b289fc  packages/bus/src/server.mjs
+cdd0304ec25ef1ad3e31c52502fa46f2c80bd77c8d3c2e13f8ed4b5328f342c9  packages/bus/tests/citation-availability.test.mjs
+2e05074cd9d15d810103658af3858161cee2af78b0a2e1ba910222fab3e84401  packages/bus/tests/citation-guard.test.mjs
+2c7a2102e2e0244876e41b664f4f706baefe3375100b956655551db1230f5da3  packages/bus/tests/citation-helpers.mjs
+9768b6dc5ae078c5cc4f76473097287b74c5bc5853d39e1f57f153e646f861af  packages/bus/tests/citation-runtime.test.mjs
+abaeac64f2c3bf8ba83c9a4488edd9105c4707a6564560c5333d5421445653af  packages/business/src/business.mjs
+3a6044de5d1ca2cc35c5285b460c3e402b4274837e5d88b97f489797f6004903  packages/business/src/organization.mjs
+4d2eb11beaa80175e524af1b95c81e7164990fba1d3e1754f5ba06eee390a14f  packages/business/tests/reply-limits.test.mjs
+a2bb98734bcc2556f8b2168f0faf8a89f7064c3f0aa49feb7d1975d596192f09  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
+f710d9600a17f6e2989a289cfe84e58f161d86c7306605946ce05fa71b364eb2  packages/library/src/guard.mjs
+c0d630798914e300e461c247340533328e97119e54909c6a9406340e61fed8b7  packages/library/src/index.mjs
+98ef45ed61144aaea44d8aea1ac43082b6d340297e46846d01772da38728e530  packages/library/src/limits.mjs
+7b46f47b5e9d6b554b5d39bce2cd95c4610f5f35b8ab8fdc5a2864b3214be809  packages/library/src/reply-protocol.mjs
+406146ebbce3710f308243b684a1c17e7626c1b65a4468489364317e31537a48  packages/library/tests/guard.test.mjs
+39c8e6c8250a13fa43015fb2c407195e30ee642f729a9f6a644c38b4ea758a72  packages/seat/src/sandbox.mjs
@@ -0,0 +1,70 @@
+✖ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5104.72293ms)
+✖ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (35.117198ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.286656ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 1
+ℹ fail 2
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 5250.151124
+
+✖ failing tests:
+
+test at packages/bus/tests/citation-availability.test.mjs:13:1
+✖ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5104.72293ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  + actual - expected
+  
+  + 'citation-invalid'
+  - 'citation-unavailable'
+              ^
+  
+      at Object.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/bus/tests/citation-availability.test.mjs:29:14)
+      at expectedException (node:assert:547:17)
+      at expectsError (node:assert:672:21)
+      at strict.rejects (node:assert:738:3)
+      at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+      at async file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/bus/tests/citation-availability.test.mjs:28:5
+      at async withLibraryLock (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/library/src/mirror.mjs:171:18)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/bus/tests/citation-availability.test.mjs:27:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 'citation-invalid',
+    expected: 'citation-unavailable',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+
+test at packages/bus/tests/citation-availability.test.mjs:40:1
+✖ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (35.117198ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+  + actual - expected
+  
+    Comparison {
+  +   code: 'citation-invalid'
+  -   code: 'citation-unavailable'
+    }
+  
+      at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/bus/tests/citation-availability.test.mjs:45:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: Error: citation-invalid: citation 1 (Book One/Characters/Mara Vell.md) isn't an indexed file at a commit reachable from the served commit
+        at refuse (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/library/src/guard.mjs:24:42)
+        at checkReply (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/library/src/guard.mjs:80:25)
+        at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
+        at async waitForActual (node:assert:615:5)
+        at async strict.rejects (node:assert:738:25)
+        at async TestContext.<anonymous> (file:///mnt/storage/scratch/tmp/tNoueZ/row217-mutant-xglaeqeb/packages/bus/tests/citation-availability.test.mjs:45:3)
+        at async Test.run (node:internal/test_runner/test:1409:7)
+        at async Test.processPendingSubtests (node:internal/test_runner/test:974:7),
+    expected: { code: 'citation-unavailable' },
+    operator: 'rejects',
+    diff: 'simple'
+  }
@@ -0,0 +1,5 @@
+M1-writer-fence: killed (control green, mutant exit 1, hashes restored, restored green)
+M2-incoming-human: killed (control green, mutant exit 1, hashes restored, restored green)
+M3-split-check-transaction: killed (control green, mutant exit 1, hashes restored, restored green)
+M5-hide-library-unavailable: killed (control green, mutant exit 1, hashes restored, restored green)
+M4-drop-client-reason: killed (control green, mutant exit 1, hashes restored, restored green)
@@ -0,0 +1,3 @@
+npm warn deprecated [email protected]: Use your platform's native DOMException instead
+
+added 128 packages in 2s
@@ -0,0 +1,2 @@
+
+added 2 packages in 205ms
@@ -0,0 +1,9 @@
+✔ C2-06 runtime reads changed and unreadable reply limits without restarting (118.083931ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 1
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 227.817729
@@ -0,0 +1,234 @@
+npm notice run @mosaic/[email protected] test
+npm notice run node --test tests/
+✔ C2-04: ensureCheckouts skips a library before a real clone and leaves no books path (66.766764ms)
+✔ a first launch clones the root at its branch, with the root's path as origin (47.521672ms)
+✔ the clone is not at its place until git clone has finished (31.999361ms)
+✔ a later launch fast-forwards a clean clone after a commit to the root, then finds it current (87.563022ms)
+✔ a clone ahead of the root keeps its commits and counts as current (53.447311ms)
+▶ a dirty clone and one on another branch are fetched, and nothing but refs/remotes moves
+  ✔ a modified file (53.258759ms)
+  ✔ an untracked file (52.286642ms)
+  ✔ a staged file (55.132154ms)
+  ✔ another branch (53.48074ms)
+  ✔ a detached HEAD (54.504119ms)
+✔ a dirty clone and one on another branch are fetched, and nothing but refs/remotes moves (269.989404ms)
+✔ a diverged clone gets the fetch into refs/remotes and is kept, not-fast-forward (53.461206ms)
+▶ a clone kept before the branch check, or for a failed status, gets no fetch
+  ✔ not-a-clone (27.485728ms)
+  ✔ hooks-present (31.094616ms)
+  ✔ submodule (38.060187ms)
+  ✔ config-changed (36.195255ms)
+  ✔ root-unreadable (36.385271ms)
+  ✔ root-detached (39.627905ms)
+  ✔ status-failed, on the root's branch and clean (42.704327ms)
+  ✔ status-failed, dirty (44.881211ms)
+✔ a clone kept before the branch check, or for a failed status, gets no fetch (297.899967ms)
+✔ a dirty clone whose fetch fails is kept, fetch-failed, exactly as it was (47.755395ms)
+✔ every git call the host makes, for a new clone and an existing one, carries maintenance.auto=false and gc.auto=0 (57.603139ms)
+✔ a clone with loose objects enough for gc --auto gets no maintenance or gc from the fetch and the merge (89.466874ms)
+▶ a clone with user.name or user.email in its config is kept, and git runs nothing in it
+  ✔ user.name (28.628791ms)
+  ✔ user.email (30.423895ms)
+✔ a clone with user.name or user.email in its config is kept, and git runs nothing in it (59.627127ms)
+✔ a commit git can't read after the fast-forward is null (57.084762ms)
+✔ a new clone whose commit can't be read refuses the launch and leaves nothing behind (21.081119ms)
+▶ a clone the session rigged is kept, and git runs nothing and writes nothing outside it
+  ✔ core.fsmonitor (39.453854ms)
+  ✔ core.hooksPath (34.616469ms)
+  ✔ a hook file (35.090442ms)
+  ✔ include.path (34.527401ms)
+  ✔ includeIf (35.13899ms)
+  ✔ a filter driver (34.195382ms)
+  ✔ origin moved (37.391948ms)
+  ✔ a second origin url (35.731817ms)
+  ✔ the origin url twice, both the root (33.999145ms)
+  ✔ an ext:: origin (31.652835ms)
+  ✔ a branch tracking another remote (33.3147ms)
+  ✔ a branch merging a tag (33.72502ms)
+  ✔ a fetch line onto local branches (34.126505ms)
+  ✔ no origin (32.973963ms)
+  ✔ a config file over the size cap (30.967833ms)
+  ✔ config a symlink to /dev/zero (31.51332ms)
+  ✔ the clone a symlink to the bait (32.976685ms)
+  ✔ the clone a file (39.528201ms)
+  ✔ the clone a plain directory (32.193931ms)
+  ✔ .git a gitdir: file (31.732811ms)
+  ✔ .git a symlink (36.499471ms)
+  ✔ .git/logs a symlink (34.327705ms)
+  ✔ .git/refs/heads a symlink (30.308688ms)
+  ✔ .git/objects a symlink (28.895664ms)
+  ✔ a reflog hard-linked to a file outside (28.33422ms)
+  ✔ HEAD a fifo (29.791372ms)
+  ✔ a commondir file (30.182546ms)
+  ✔ an alternates file (30.414863ms)
+  ✔ a gitlink staged, no .gitmodules (42.003032ms)
+  ✔ a gitlink and .gitmodules staged (47.484582ms)
+  ✔ a gitlink to a repository with its own gitlink (53.625899ms)
+  ✔ a gitlink and .gitmodules committed (45.90129ms)
+  ✔ a gitlink and submodule.active in config (43.005636ms)
+  ✔ a .git/modules with no gitlink (31.240083ms)
+✔ a clone the session rigged is kept, and git runs nothing and writes nothing outside it (1201.693467ms)
+▶ a root that can't be cloned refuses with the project id and leaves nothing behind
+  ✔ missing (9.543898ms)
+  ✔ not a repository (9.15995ms)
+  ✔ a plain directory inside another repository (13.291966ms)
+  ✔ unreadable (10.409599ms)
+  ✔ on no branch (11.130486ms)
+  ✔ missing an object (14.936384ms)
+✔ a root that can't be cloned refuses with the project id and leaves nothing behind (69.273079ms)
+✔ a clone whose root is on no branch, or gone, is kept and named (28.705151ms)
+✔ no credential or forge remote of the root reaches a clone (46.990023ms)
+✔ every project in the business file gets its own clone at its own branch (32.655381ms)
+✔ a clone past its time gets SIGTERM and refuses the launch, with nothing left in the workspace (514.003804ms)
+✔ a clone that ignores SIGTERM gets SIGKILL once the grace period is over (1016.843724ms)
+✔ a timeout signals git's process group, so a process git started dies with it (515.051887ms)
+✔ once a signalled git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (514.556145ms)
+✔ the budget is the setting's whole number of bytes from 1 MiB to 1 GiB, and the default for anything else (1.567727ms)
+✔ a stream past the default budget is not-collected with a lower bound, and a later collection catches up (65.101994ms)
+✔ a budget smaller than the streams counts over several collections, once each, and is known when it catches up (2.599724ms)
+✔ a line split across reads counts once (9.33078ms)
+✔ Claude history from before the ledger makes the first Pi collection harness-unsupported, for good (1.440992ms)
+✔ an empty claude-projects/ is no Claude history, and one filled after the ledger exists isn't checked (1.428192ms)
+✔ a claude-projects/ that can't be read records nothing, and the next collection checks again (1.330216ms)
+✔ the stream cap is the setting's whole number from 32 to 65536, and the default for anything else (0.16791ms)
+✔ more streams than the cap is not-collected, with cursors only for the streams opened, and a larger cap catches up (2.344595ms)
+✔ the default cap opens STREAMS streams and writes no more cursor lines than that (52.65919ms)
+✔ row 307 the known ledger row 270 wrote reads the same count (4.720302ms)
+✔ row 307 after the known ledger, one collection through pi's module answers the next count (3.122956ms)
+✔ row 307 the store-incomplete ledger row 270 wrote reads the same count (1.172174ms)
+✔ row 307 after the store-incomplete ledger, one collection through pi's module answers the next count (1.473641ms)
+✔ row 307 the store-unreadable ledger row 270 wrote reads the same count (1.233218ms)
+✔ row 307 after the store-unreadable ledger, one collection through pi's module answers the next count (1.478165ms)
+✔ row 307 the not-collected ledger row 270 wrote reads the same count (1.059533ms)
+✔ row 307 after the not-collected ledger, one collection through pi's module answers the next count (2.381792ms)
+✔ row 307 the claude-code ledger row 270 wrote reads the same count (1.16785ms)
+✔ row 307 after the claude-code ledger, one collection through pi's module answers the next count (1.422304ms)
+✔ row 307 the claude-history ledger row 270 wrote reads the same count (2.943093ms)
+✔ row 307 after the claude-history ledger, one collection through pi's module answers the next count (1.5333ms)
+✔ row 307 the torn ledger row 270 wrote reads the same count (1.006203ms)
+✔ row 307 after the torn ledger, one collection through pi's module answers the next count (2.284545ms)
+✔ row 307 core refuses an answer outside the contract and appends nothing (8.468181ms)
+✔ row 307 the module gets the store's two native directories, a copy of the cursors, the budget, the cap and first (2.320411ms)
+✔ an empty store, a store with no compaction and a failed start count 0, known (7.138038ms)
+✔ one and three completed compactions (2.441636ms)
+✔ a compaction copied into a branched stream counts once, under the stream it was first seen in (3.056ms)
+✔ one collection over two streams holding the same copy counts it once and writes it once (1.831681ms)
+✔ the same entry id at another time in another stream is another compaction (1.582065ms)
+✔ resume: each collection reads past its cursor and writes a key once (2.114301ms)
+✔ a partial trailing line waits for its newline (1.624959ms)
+✔ a missing ledger is not-collected and an unreadable one store-unreadable, never 0 (1.322325ms)
+✔ a symlinked ledger is store-unreadable and is not written through (1.293154ms)
+✔ a torn last ledger line makes the count unknown, a lower bound, and stays so (2.167108ms)
+✔ a bad ledger line in the middle makes the count unknown (3.331232ms)
+▶ a stream that shrank, changed under its cursor or went away is store-incomplete for good
+  ✔ shrink (2.038847ms)
+  ✔ rewrite (1.477185ms)
+  ✔ remove (1.974024ms)
+✔ a stream that shrank, changed under its cursor or went away is store-incomplete for good (6.254361ms)
+✔ a stream that isn't a regular file or a Pi session is store-unreadable, and that passes (1.252704ms)
+✔ a first line that isn't a session header is store-unreadable (1.120253ms)
+✔ a Claude run is harness-unsupported, and stays so after a Pi run (1.273691ms)
+✔ storeDir is the store sessionStore makes, without making it (1.538256ms)
+✔ the ledger is under no sandbox mount (5.456112ms)
+✔ rootHits: a top-level file, a new top-level directory, src/ and v1/ are the root; paths under known directories aren't (1.861197ms)
+✔ gateEnv keeps the named variables that are strings and drops everything else (0.310846ms)
+✔ isMosaicStack: a checkout whose HEAD descends from the root commit and has node_modules; nothing else (76.743834ms)
+✔ gateSteps: each package with tests but queue in name order, then each scripts/test-*.sh (2.377262ms)
+✔ runGate: every step passes, each with its own log and a summary line, under the environment it was given (211.160741ms)
+✔ runGate: the first failing step stops the gate and names its log (269.569796ms)
+✔ runGate: an abort stops the running step and everything in its group, and runs nothing after it (185.986993ms)
+✔ the CLI: root-file prints the hits and exits 2, or exits 0; gate exits 0, or 2 with the step and its log; anything else is usage (661.443234ms)
+✔ T3: publish pushes the work commit by oid to <user>/<branch> on the fork, with the token only through the helper (318.365034ms)
+✔ T3: the token is never in git's argv, the fork URL included; it reaches git on fd 3 only (157.63501ms)
+✔ T3: a moved fork branch refuses non-fast-forward; no + and no force (173.077055ms)
+✔ T3: D9a: an empty fork and an unrelated fork refuse remote-unrelated; a missing fork refuses fork-unavailable (379.595919ms)
+✔ T3: a fork past main refuses remote-unrelated until root catches up (152.254688ms)
+✔ T3: a wrong token refuses fork-unavailable; git's stderr isn't in the refusal (102.972548ms)
+✔ T3: a 302 is not followed: fork-unavailable, and the target sees no request (113.352932ms)
+✔ T3: the helper answers only the fork's host and port: a fork on another port gets no token (95.099891ms)
+✔ T3: a fork that echoes the token refuses credential-leak (131.28193ms)
+✔ T3: no tls parameter, no trust: the scratch CA reaches git only through it (91.935601ms)
+✔ D9 steps 3 and 4: ref-moved and identity-mismatch refuse before any request (143.070058ms)
+✔ publishRemote refuses a fork, user or destination that isn't shell- and ref-safe before any git (88.646013ms)
+✔ RUNNER_FILES is exactly what the runner and the harness sources it starts import (7.032234ms)
+✔ sandboxProblem names a missing bwrap and a bwrap that fails (15.78888ms)
+✔ every bind says why; the bundle and session file stay read-only over the run directory (2.196421ms)
+✔ row 65 a harness module's mounts bind read-only after the adapter, each with the module's reason (2.143393ms)
+✔ REQ-THREAD-2 a thread store binds its session directory and Claude transcripts, and nothing more (1.644658ms)
+✔ the host's git socket is bound only when given, read-only and before the writable binds (1.090126ms)
+✔ the git identity is the instance's, at <instance>@<business>.mosaic.invalid, and sandboxArgv refuses without it (1.690862ms)
+✔ a confined session's shell reaches its own workspace and run directory and nothing of the founder's or another session's (2106.854649ms)
+✔ a bind that exposes a stand-in, or a missing workspace bind, fails the matching check (2924.249794ms)
+✔ a confined session that runs tester-cli.mjs is refused as tester, and the same shim outside the sandbox binds (300.518853ms)
+✔ resolveSeat: by name under --repo resolves the repo layout (2.419588ms)
+✔ resolveSeat: by path resolves the fleet layout (0.765582ms)
+✔ resolveSeat: refusals for missing dir, missing launch.sh, non-executable launch.sh, invalid name, and unknown layout (1.626754ms)
+✔ tmuxContext: outside tmux, default socket, custom socket, and exec failure (1.236572ms)
+✔ makeRegistration produces a record that validates; each shape violation throws SeatError (1.593741ms)
+✔ writeRegistration/readRegistration: round trip, permissions, absence, and malformed records (2.34318ms)
+✔ updateTask: changes task, taskSetBy and updatedAt only, and refuses appropriately (2.203796ms)
+✔ CLI launch: registers, execs the fake launch script, and passes args through (66.404825ms)
+✔ CLI launch: --harness lands in the record (50.392752ms)
+✔ CLI launch: the launch script's own exit code passes through (46.659659ms)
+✔ CLI launch: relaunching a seat rewrites the one registration record (89.26575ms)
+✔ CLI launch: omitting --task records an empty string, not null (39.318048ms)
+✔ CLI seat task: updates only the task after a launch, and refuses on an unlaunched seat (96.331713ms)
+✔ CLI refusals: no args, unknown flag, missing config, already-registered env, and exec failure (164.27632ms)
+✔ samePath: equal paths, symlinked dirs, distinct dirs, and non-strings (0.422092ms)
+✔ resolveSetBy: explicit --by wins over the environment; absent or empty environment gives unknown; invalid explicit or environment values refuse with exit 4 (0.590318ms)
+✔ validateRegistration/readRegistration: taskSetBy is optional; a record without it (written before #1511) still loads unchanged; an invalid one is refused; the version does not change (0.734057ms)
+✔ updateTask: records setBy, preserves startedAt and every unrelated field, upgrades an old record in place only when the task is set, and replaces a previous attribution (0.906133ms)
+✔ CLI seat task: --by beats MOSAIC_AGENT_NAME, the environment beats nothing, empty environment is unknown, invalid --by or environment refuses with exit 4 and leaves the record byte for byte (330.90649ms)
+✔ REQ-THREAD-2 sessionStore: a legacy session keeps the thread's store, any other gets sessions/<s>/, each segment checked first (5.360486ms)
+✔ REQ-THREAD-2 sessionStore refuses legacy-store-unmapped for a thread whose old store no legacy session maps (1.608175ms)
+✔ REQ-THREAD-2 sessionWorkspace: private directories per session, unsafe segments and overlaps refused (3.523108ms)
+✔ REQ-THREAD-2 lockSessionWorkspace: one writer; a live host or run holds it, a stale lock is taken over, an unreadable one holds (15.189866ms)
+✔ REQ-THREAD-2 sessions.json v2: entries carry session and workspace, running() keys on the session, a v1 file still reads (1.889362ms)
+✔ REQ-LIMIT-1: family substring matching is no longer exported (1.378459ms)
+✔ sessionEnv passes only the allowlist, the repo's bin on PATH, and the run id (1.063207ms)
+✔ ZAI_API_KEY passes the session allowlist, and ZAI_TOKEN does not (0.239826ms)
+✔ sessionExit gives a runner's signal death back as the signal; a session credential is one whole set of nonempty variables (0.405172ms)
+✔ newRun: short ids, 0700 directories, and a refusal when the socket path won't fit (2.727102ms)
+✔ session file and launch log: 0600, the session file written once (2.111664ms)
+✔ endReason maps the runner's exit codes; a signal is killed (0.220582ms)
+✔ Registry mirrors to sessions.json; readSessions marks live entries; bad files refuse (2.216711ms)
+✔ a read-only Registry never writes sessions.json, refuses add() and leaves the file on remove() (2.154331ms)
+✔ REQ-THREAD-1 Registry.running keys a thread run by business, instance and thread (1.027065ms)
+✔ REQ-THREAD-2 REQ-LAUNCH-1 threadStore checks both segments before the join and refuses an unsafe directory (2.628544ms)
+✔ stopSession refuses an unknown run, reports a stale one, and won't signal a pid that isn't a runner (1.552738ms)
+✔ a session runs in its sandbox as pid 1 of its namespace, claims, answers, and stops on mosaic stop (293.088316ms)
+✔ workRef and validBranch take only what a ref name can hold (2.280976ms)
+✔ a push lands as the task's work ref, a fast-forward lands after it, and main is the root's (187.443563ms)
+✔ a rewritten branch refuses non-fast-forward and the work ref stays (124.192671ms)
+✔ a branch with no history in common with main refuses unrelated-history (60.579235ms)
+✔ a bundle that needs commits the working repository lacks refuses missing-prerequisite (51.079109ms)
+✔ the root is fetched again before each push and main follows it, so a clone of a newer root pushes (129.47937ms)
+✔ a root moved back after the clone leaves the push's base unknown: missing-prerequisite (78.854404ms)
+✔ a commit with a broken object refuses invalid-bundle, and only because fsck is on (86.468293ms)
+✔ only a v2 bundle with the named branch is read (64.914471ms)
+✔ a branch named main, or named for another task, moves only this task's work ref (102.371349ms)
+✔ a record that throws moves the work ref back, or removes a new one (141.771502ms)
+✔ a work ref that can't go back refuses rollback-failed, naming the ref and the commit (362.776758ms)
+✔ a root that can't be read refuses root-unreadable (28.853641ms)
+✔ a git past its time gets SIGTERM, leaves no ref lock, and the next push lands (2132.860162ms)
+✔ a git that ignores SIGTERM gets SIGKILL once the grace period is over (1025.936026ms)
+✔ a working repository path that isn't a directory refuses (23.030329ms)
+✔ review bundles a pushed commit as refs/mosaic/review, leaving out what the reviewer has (120.899663ms)
+✔ review of a project with no working repository refuses unknown-commit (14.031146ms)
+✔ the runner's git tools hold the host's limits and branch rule (1.219295ms)
+✔ a reseed moves root but leaves a landed main, and main forwards once root contains it (184.469774ms)
+✔ after a landing, a push built on the root still lands and main stays where the landing put it (126.530409ms)
+✔ once the root shares no history with a landed main, a push is checked against main, not the root (179.004093ms)
+✔ a landing squashes the reviewed diff onto main as the bus host and moves main only at finish (105.224989ms)
+✔ a landing refuses ref-moved, base-conflict and root-file before it makes a commit (308.132399ms)
+✔ a landing whose applied diff isn't the reviewed one refuses patch-drift and leaves no worktree (121.415385ms)
+✔ finish refuses base-moved when main moved, and a record that throws moves main back (242.643351ms)
+✔ halted push receipt rolls back only its unrecorded ref and cleans temporary refs (198.696687ms)
+ℹ tests 218
+ℹ suites 0
+ℹ pass 218
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 6318.071226
@@ -0,0 +1,202 @@
+{
+  "base": "e0c6142f3",
+  "testedRevision": "2d274a5b6c35c3e74b07206ffd724a6579bb149d",
+  "tmpdir": "/mnt/storage/scratch/tmp/tNoueZ",
+  "wholeSuites": {
+    "library": {
+      "tests": 142,
+      "pass": 142,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "business": {
+      "tests": 270,
+      "pass": 270,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "bus": {
+      "tests": 974,
+      "pass": 974,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "cli": {
+      "tests": 988,
+      "pass": 988,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "harness": {
+      "tests": 172,
+      "pass": 172,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "seat": {
+      "tests": 218,
+      "pass": 218,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    }
+  },
+  "touched": {
+    "touched-first": {
+      "tests": 57,
+      "pass": 56,
+      "fail": 1,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "touched-rerun": {
+      "tests": 57,
+      "pass": 57,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "availability-green": {
+      "tests": 3,
+      "pass": 3,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    },
+    "runtime-fixture-retry": {
+      "tests": 1,
+      "pass": 1,
+      "fail": 0,
+      "cancelled": 0,
+      "skipped": 0
+    }
+  },
+  "mutants": {
+    "M1-writer-fence": {
+      "control": {
+        "tests": 6,
+        "pass": 6,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "negative": {
+        "tests": 6,
+        "pass": 3,
+        "fail": 3,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "restored": {
+        "tests": 6,
+        "pass": 6,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "productHashesRestored": true
+    },
+    "M2-incoming-human": {
+      "control": {
+        "tests": 6,
+        "pass": 6,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "negative": {
+        "tests": 6,
+        "pass": 5,
+        "fail": 1,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "restored": {
+        "tests": 6,
+        "pass": 6,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "productHashesRestored": true
+    },
+    "M3-split-check-transaction": {
+      "control": {
+        "tests": 13,
+        "pass": 13,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "negative": {
+        "tests": 13,
+        "pass": 12,
+        "fail": 1,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "restored": {
+        "tests": 13,
+        "pass": 13,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "productHashesRestored": true
+    },
+    "M4-drop-client-reason": {
+      "control": {
+        "tests": 13,
+        "pass": 13,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "negative": {
+        "tests": 13,
+        "pass": 12,
+        "fail": 1,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "restored": {
+        "tests": 13,
+        "pass": 13,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "productHashesRestored": true
+    },
+    "M5-hide-library-unavailable": {
+      "control": {
+        "tests": 3,
+        "pass": 3,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "negative": {
+        "tests": 3,
+        "pass": 1,
+        "fail": 2,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "restored": {
+        "tests": 3,
+        "pass": 3,
+        "fail": 0,
+        "cancelled": 0,
+        "skipped": 0
+      },
+      "productHashesRestored": true
+    }
+  },
+  "totalWholeSuiteTests": 2764
+}
@@ -0,0 +1,9 @@
+library: 142/142 pass; fail=0 skipped=0 cancelled=0
+business: 270/270 pass; fail=0 skipped=0 cancelled=0
+bus: 974/974 pass; fail=0 skipped=0 cancelled=0
+cli: 988/988 pass; fail=0 skipped=0 cancelled=0
+harness: 172/172 pass; fail=0 skipped=0 cancelled=0
+seat: 218/218 pass; fail=0 skipped=0 cancelled=0
+Touched rerun 57/57; first run 56/57, new runtime fixture corrected.
+M1-M5 killed; each control/restored run green, hashes restored.
+No old test failed or was edited. scripts/test-*.sh left to Sage at landing.
@@ -0,0 +1,80 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5129.213097ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (32.312603ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.769445ms)
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (104.132156ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (90.030314ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (57.202238ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (41.82067ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (47.52786ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (45.049883ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (54.4217ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (86.893454ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (55.019525ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.383322ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (76.778515ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (24.114008ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (47.161109ms)
+✖ C2-06 runtime reads changed and unreadable reply limits without restarting (78.402278ms)
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (26.436831ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (21.452407ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (8.669666ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (8.204041ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (9.079346ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (10.338142ms)
+✔ C2-06 CLI replies reads revision and sends only the JSON settings to the human verb (1.898838ms)
+✔ C2-06 CLI replies requires a file and refuses tester writes before a bus call (0.465972ms)
+✔ C2-06 RESULT reply-invalid retries once, delivers only the valid answer and names reason (222.089187ms)
+✔ C2-06 RESULT citation-missing retries once, delivers only the valid answer and names reason (200.104611ms)
+✔ C2-06 RESULT citations-over-limit retries once, delivers only the valid answer and names reason (197.834891ms)
+✔ C2-06 RESULT citation-invalid retries once, delivers only the valid answer and names reason (210.156515ms)
+✔ C2-06 RESULT playground-cited-as-canon retries once, delivers only the valid answer and names reason (213.835593ms)
+✔ C2-06 RESULT citation-cross-universe retries once, delivers only the valid answer and names reason (209.912186ms)
+✔ C2-06 RESULT citation-unfetched retries once, delivers only the valid answer and names reason (198.705684ms)
+✔ C2-06 RESULT two guard refusals use the citation fixed text and exactly one retry (182.386586ms)
+✔ C2-06 RESULT JSON 34000 characters retries with a shorter valid answer (213.370025ms)
+✔ C2-06 RESULT JSON 70000 characters retries with a shorter valid answer (199.782915ms)
+✔ C2-06 RESULT two oversized JSON bodies use the length fixed text with citations required (184.820165ms)
+✔ C2-06 multibyte plain bodies also receive the one request-size retry (201.829013ms)
+✔ C2-06 two multibyte plain bodies use the length fallback (182.03426ms)
+✔ C2-06 RESULT a length refusal then citation refusal shares one retry and citation fallback (183.540139ms)
+✔ C2-06 fixed empty/failed replies defer unslop note until the next cited reply (274.786836ms)
+✔ C2-06 cited JSON above the old 32000 clip retains its citations and text (167.141798ms)
+✔ C2-06 a flagged cited answer keeps the note inside text and citations whole (168.83631ms)
+✔ C2-06 send_message typed tool runs every guard code before the valid RESULT (230.565935ms)
+✔ C2-06 outside library the old failed text, clip and unslop behavior hold (197.472747ms)
+✔ C2-06 outside library a refused send keeps the existing no-retry behavior (151.296315ms)
+✔ C2-06 the retry turn delivers citation-unavailable reason to the agent (184.635398ms)
+✔ C2-06 reply schema: free bodies, exact objects and safe refusal reasons (14.759264ms)
+✔ C2-06 citation setting and all four exact fixed texts (9.899391ms)
+✔ C2-06 default citation cap passes 20 and refuses 21, even with optional citations (76.751112ms)
+✔ C2-06 real Git citation scope, reachability, lines and normalized quotes (41.360225ms)
+✔ C2-06 playground cites pass but cannot state canon (23.671961ms)
+✔ C2-06 independent universes refuse; a hybrid and only its sources pass (41.572641ms)
+✔ C2-06 web cites require allowed definition, this session fetch and kept quote (10.468249ms)
+✔ C2-06 file origin is the path commit and trailer, while last follows served changes (31.989388ms)
+✔ C2-06 origin uses literal paths even when a filename contains a glob (20.084358ms)
+✔ C2-06 cited-commit guard reads exactly the C2-05a indexed file set with supporting scope (44.687642ms)
+✔ C2-06 reply limits fall back independently without coercion or inherited keys (0.462948ms)
+ℹ tests 57
+ℹ suites 0
+ℹ pass 56
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 11101.06711
+
+✖ failing tests:
+
+test at packages/bus/tests/citation-runtime.test.mjs:12:1
+✖ C2-06 runtime reads changed and unreadable reply limits without restarting (78.402278ms)
+  Error: invalid-authority
+      at fail (file:///home/jwoltje/.t3/worktrees/mosaic-stack/beakley-row217/packages/bus/src/broker.mjs:215:9)
+      at checkBusiness (file:///home/jwoltje/.t3/worktrees/mosaic-stack/beakley-row217/packages/bus/src/broker.mjs:366:7)
+      at new Broker (file:///home/jwoltje/.t3/worktrees/mosaic-stack/beakley-row217/packages/bus/src/broker.mjs:537:63)
+      at startBroker (file:///home/jwoltje/.t3/worktrees/mosaic-stack/beakley-row217/packages/bus/src/runtime.mjs:274:14)
+      at async TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/beakley-row217/packages/bus/tests/citation-runtime.test.mjs:18:19)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
+    code: 'invalid-authority'
+  }
@@ -0,0 +1,65 @@
+✔ C2-06 held library lock gives the agent citation-unavailable and its retry reason (5131.834326ms)
+✔ C2-06 malformed sync state is availability failure, never a fabricated invalid cite (31.609704ms)
+✔ C2-06 no mirror or freshly initialized empty mirror still means no served citation (31.510292ms)
+✔ C2-06 coder send_message guard covers every table refusal; inserts nothing (102.606635ms)
+✔ C2-06 research send_message guard covers every table refusal; inserts nothing (91.30209ms)
+✔ C2-06 stored check carries the file author trailer at an unrelated cited tip (55.686451ms)
+✔ C2-06 supporting cite cannot state canon, including a folder also marked playground (42.44166ms)
+✔ C2-06 supporting file stores supporting scope and its real agent trailer (48.386414ms)
+✔ C2-06 check evidence and insert are atomic when storing evidence fails (39.194827ms)
+✔ C2-06 live limits change both directions; unreadable file keeps checks and exact fixed texts (54.284625ms)
+✔ C2-06 page store is session-local, caps 20 fetches and 200 KiB, drops at disconnect (85.004961ms)
+✔ C2-06 transport passes safe capped guard reason; ordinary refusal envelope is byte-identical (54.117068ms)
+✔ C2-06 non-library businesses retain role.claim shape and unguarded free sends (26.131034ms)
+✔ C2-06 thread messages carry file/last evidence with one read per distinct path (76.437567ms)
+✔ C2-06 guarded request snapshot cannot change between check and insert (23.908928ms)
+✔ C2-06 library.limits.set is human-only and invalid settings leave file and receipts unchanged (39.656735ms)
+✔ C2-06 runtime reads changed and unreadable reply limits without restarting (113.293022ms)
+✔ C2-06 M11 human replacement works; omitted settings return to defaults (36.305063ms)
+✔ C2-06 M11 agents and tester cannot change settings, including by changing human (21.839826ms)
+✔ C2-06 M11 serialization cannot replace settings after the first fence (8.253422ms)
+✔ C2-06 M11 an unrelated actor cannot appoint itself human and change reply limits (7.674495ms)
+✔ C2-06 invalid setter values preserve the business and changes.jsonl (8.65299ms)
+✔ C2-06 validator accepts hand-edited settings; raw reader fails closed on invalid files (9.800617ms)
+✔ C2-06 CLI replies reads revision and sends only the JSON settings to the human verb (1.78485ms)
+✔ C2-06 CLI replies requires a file and refuses tester writes before a bus call (0.520156ms)
+✔ C2-06 RESULT reply-invalid retries once, delivers only the valid answer and names reason (220.792912ms)
+✔ C2-06 RESULT citation-missing retries once, delivers only the valid answer and names reason (195.400791ms)
+✔ C2-06 RESULT citations-over-limit retries once, delivers only the valid answer and names reason (196.181772ms)
+✔ C2-06 RESULT citation-invalid retries once, delivers only the valid answer and names reason (211.797981ms)
+✔ C2-06 RESULT playground-cited-as-canon retries once, delivers only the valid answer and names reason (212.360651ms)
+✔ C2-06 RESULT citation-cross-universe retries once, delivers only the valid answer and names reason (212.667005ms)
+✔ C2-06 RESULT citation-unfetched retries once, delivers only the valid answer and names reason (184.261348ms)
+✔ C2-06 RESULT two guard refusals use the citation fixed text and exactly one retry (184.957084ms)
+✔ C2-06 RESULT JSON 34000 characters retries with a shorter valid answer (216.343048ms)
+✔ C2-06 RESULT JSON 70000 characters retries with a shorter valid answer (198.338992ms)
+✔ C2-06 RESULT two oversized JSON bodies use the length fixed text with citations required (183.309434ms)
+✔ C2-06 multibyte plain bodies also receive the one request-size retry (198.411283ms)
+✔ C2-06 two multibyte plain bodies use the length fallback (182.244769ms)
+✔ C2-06 RESULT a length refusal then citation refusal shares one retry and citation fallback (184.948978ms)
+✔ C2-06 fixed empty/failed replies defer unslop note until the next cited reply (294.575418ms)
+✔ C2-06 cited JSON above the old 32000 clip retains its citations and text (169.454956ms)
+✔ C2-06 a flagged cited answer keeps the note inside text and citations whole (164.824669ms)
+✔ C2-06 send_message typed tool runs every guard code before the valid RESULT (213.365137ms)
+✔ C2-06 outside library the old failed text, clip and unslop behavior hold (198.225522ms)
+✔ C2-06 outside library a refused send keeps the existing no-retry behavior (155.955999ms)
+✔ C2-06 the retry turn delivers citation-unavailable reason to the agent (188.198987ms)
+✔ C2-06 reply schema: free bodies, exact objects and safe refusal reasons (17.723832ms)
+✔ C2-06 citation setting and all four exact fixed texts (11.590649ms)
+✔ C2-06 default citation cap passes 20 and refuses 21, even with optional citations (79.713842ms)
+✔ C2-06 real Git citation scope, reachability, lines and normalized quotes (41.208361ms)
+✔ C2-06 playground cites pass but cannot state canon (24.250695ms)
+✔ C2-06 independent universes refuse; a hybrid and only its sources pass (42.707909ms)
+✔ C2-06 web cites require allowed definition, this session fetch and kept quote (10.901286ms)
+✔ C2-06 file origin is the path commit and trailer, while last follows served changes (37.369269ms)
+✔ C2-06 origin uses literal paths even when a filename contains a glob (20.592546ms)
+✔ C2-06 cited-commit guard reads exactly the C2-05a indexed file set with supporting scope (51.682837ms)
+✔ C2-06 reply limits fall back independently without coercion or inherited keys (0.499884ms)
+ℹ tests 57
+ℹ suites 0
+ℹ pass 57
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 11134.473726
@@ -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.
@@ -1626,3 +1626,9 @@ are never rewritten or removed; corrections are new entries.
 2026-10-24T04:27Z | Goldie (a13dd6d5-5e73-4b7d-8318-02abeff24940) | Row265 / #1770 C2-09b rooms | Goldie owns build, Boyd reviews under sage-3915. New goldie/row265 worktree at ec86f2c84, claim rev3814; room verbs/parser/new tests prepared, no old tests changed. Sage-3932 slot: new parser14/14 and rooms18/18 passed; whole bus in progress before refusal mutants, stop rule active.
 2026-10-24T04:35Z | Goldie (a13dd6d5-5e73-4b7d-8318-02abeff24940) | Row265 / #1770 verified | First slot stopped at project-runtime import pin. mos-1567 narrowly authorizes pin and pure-source mount correction. sage-3942 rerun: sandbox10/10, parser15/15, rooms18/18, bus957/957, twelve refusal mutants killed/restored SHA71b32ee4, parser15/15 + rooms18/18 again. Slot returned goldie-0034; no further test runs. Boyd reviews RUNNER_FILES alongside rooms; own-branch push/claimant in-review next.
 2026-10-24T07:18:53Z | Sage (1ef1e4f8) | Row 327 / #1825 push guard landed (mos-1572 option A, mos-1575) | Gate went red 06:57Z on an empty canonical node_modules (Glomgold's webui npm ci through a link to canonical, glomgold-0011); rerun with its own npm ci GREEN 07:15:49Z on 1bd214e38; pushed 68c08b4e7 07:18:03Z; #1825 closed c31530; canonical restored (128 packages); brief template rule 4db23a51f | landed
+
+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.
+
+2026-10-24 | Beakley (88b97f65) | Row 217 round 2 under sage-4037 | New beakley/row217-r2 rebased onto e0c6142f3, retained both log histories, E4 product fix and supporting/index tests drafted. No Node/npm/tests/mutants run; ready for CLEAR; local-only dependency installs required on CLEAR, old-test red goes to Sage.
+
+2026-10-24T10:21Z | Beakley (88b97f65) | Row217 #1718 round2 slot | All touched57 and six whole suites2764 pass, zero skips/cancels; M1-M5 killed/restored, E4 RED stand-in observed. First-new runtime fixture red recorded and corrected; no old-test change/failure. Evidence in agents/beakley/work/queue-217/run-r2. Verified for review on beakley/row217-r2; Sage landing scripts/review remain.
@@ -204,15 +204,26 @@ 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 = []) {
@@ -393,6 +404,11 @@ 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;
@@ -1412,7 +1428,10 @@ 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;
@@ -1494,6 +1513,7 @@ export class Broker {
  }
  disconnect(cap) {
    this.#sessions.delete(cap);
+    this.#pages.delete(cap);
  }
  identity(cap) {
    const s = this.#session(cap);
@@ -4758,12 +4778,21 @@ 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 (request.verb === 'grants.scope' || request.verb === 'grants.scope.set')
        return this.#grantScopeVerb(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.
@@ -4809,6 +4838,12 @@ 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
@@ -5263,7 +5298,14 @@ 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 });
@@ -5277,6 +5319,78 @@ 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) {
@@ -5360,6 +5474,7 @@ 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
@@ -5486,7 +5601,7 @@ 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(
@@ -5510,7 +5625,8 @@ 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, []);
@@ -5874,6 +5990,10 @@ 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 &&
          ![
@@ -5920,6 +6040,9 @@ 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)
@@ -6632,11 +6755,15 @@ 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 }),
@@ -338,6 +345,8 @@ export async function startBroker({
        else if(verb==='veto.set')result=instances.veto(id,args,actor);
        // Row 298: the human's grant scope, through the instance writer.
        else if(verb==='grants.scope.set')result=instances.grantScope(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 +1,178 @@
+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 }]);
+});
+
+const supportingMapping = entry => {
+  entry.universes.harbor.supporting = ['Book One/Playground/'];
+  return entry;
+};
+
+test('C2-06 supporting cite cannot state canon, including a folder also marked playground', async t => {
+  const f = citationWorld(t, { definition: 'research', mapChange: supportingMapping }); f.call(f.agent, 'role.claim');
+  const count = f.store.get('SELECT count(*) n FROM messages').n;
+  await assert.rejects(f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(f.commit, {
+    path: 'Book One/Playground/What If.md', lines: [4, 4], quote: 'Mara Vell', as: 'canon',
+  })]) }), { code: 'playground-cited-as-canon' });
+  assert.equal(f.store.get('SELECT count(*) n FROM messages').n, count);
+});
+
+test('C2-06 supporting file stores supporting scope and its real agent trailer', async t => {
+  const f = citationWorld(t, { definition: 'research', mapChange: supportingMapping }); f.call(f.agent, 'role.claim');
+  const path = 'Book One/Playground/What If.md';
+  writeFileSync(join(f.repo, path), readFileSync(join(f.repo, path), 'utf8') + 'Agent fixture note.\n');
+  git(f.repo, 'add', '-A'); git(f.repo, 'commit', '-qm', 'Supporting note\n\nMosaic-Agent: acme/scribe');
+  const file = git(f.repo, 'rev-parse', 'HEAD'); f.setServed(file);
+  const sent = await f.call(f.agent, 'message.send', { to: 'human', body: citedBody([fixtureCite(file, { path, lines: [4, 4], quote: 'Mara Vell' })]) });
+  const event = f.store.get("SELECT body FROM events WHERE subject=? AND json_extract(body,'$.action')='message.checked'", sent.id);
+  assert.deepEqual(JSON.parse(event.body).check, { citations: [{ scope: 'supporting', agent: 'acme/scribe', file }] });
+});
+
+test('C2-06 check evidence and insert are atomic when storing evidence fails', async t => {
+  const f = citationWorld(t); f.call(f.agent, 'role.claim');
+  f.store.run(`CREATE TRIGGER fixture_check_refused BEFORE INSERT ON events
+    WHEN json_extract(NEW.body,'$.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, mapChange } = {}) {
+  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(mapChange), 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 +1,34 @@
+// 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, systemFor, 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 checked = validateBusinessDocument(doc, file, { rolesDir }); mkdirSync(dataRoot, { mode: 0o700 });
+  // Runtime takes the host's broker projection, not the business validator's unresolved role entries.
+  // No agent action is needed here: use the same empty-authority shape as limits-runtime.test.mjs.
+  const business = { id: 'acme', human: 'jason', projects: checked.projects,
+    arbiters: { technical: 'coder', delivery: 'coder' },
+    roles: { coder: { definition: 'coder', authority: { withinRole: [], crossRole: [] } } } };
+  const runtime = await startBroker({ dataRoot, businesses: { acme: business }, organization: { dir, rolesDir, system: systemFor(root) } });
+  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);
@@ -198,6 +239,7 @@ 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
@@ -205,6 +247,7 @@ 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 });
        if (beforeWrite) {
          beforeWrite();
@@ -260,5 +303,5 @@ 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 +1,201 @@
+// 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 { lstatSync } from 'node:fs';
+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;
+}
+
+// Only an absent mirror or a legitimate empty sync state means there is no served commit.
+// A lock timeout or unsafe/unreadable state is availability failure, not evidence of an invalid cite.
+async function servedMirror(context) {
+  const mapping = context.business.projects[context.project];
+  let mirror = null, served = null;
+  try {
+    mirror = mirrorPath(context);
+    try { lstatSync(mirror); }
+    catch (error) {
+      if (error.code === 'ENOENT') return { mapping, mirror: null, served: null };
+      throw error;
+    }
+    served = (await readSyncState(mirror, { branch: mapping.branch })).served ?? null;
+  } catch {
+    refuse('citation-unavailable', 'The library is busy or unavailable. Retry the answer when the library is available.');
+  }
+  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 web = { allowed: WEB_CITE_DEFINITIONS.includes(definition), pages };
+  // Plain replies, web-only replies and the runner's exact fallback texts don't read Git.
+  // In particular, a busy mirror must not prevent the fixed fallback from being delivered.
+  const reply = parseReply(body);
+  if (!reply.citations.some(c => Object.hasOwn(c, 'path')))
+    return checkReply(body, { limits, mapping: context.business.projects[context.project], library: null, web });
+  const { mapping, mirror, served } = await servedMirror(context);
+  return checkReply(body, { limits, mapping, library: libraryReader(mirror, served, mapping), web });
+}
@@ -11,3 +11,5 @@ export { SYNC_STATE_FILE, mirrorPath, ensureMirror, withLibraryLock, servedCommi
 export { syncCommand, sync, ASKPASS, SLOT, SYNC_INTERVAL_MS } from './sync.mjs';
 export { buildIndex, indexFor, clearIndexCache, indexCacheSize } from './index-build.mjs';
 export { sees, find, get, search, manuscript, universeInfo, QUERY_REPLY_CAP, LOOKUP_LIMIT, MANUSCRIPT_LINES } from './query.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 +1,40 @@
+// 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', 'citation-unavailable']);
+
+// 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 +1,150 @@
+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 { readLibrary, listTree } from '../src/reader.mjs';
+import { indexFor } from '../src/index-build.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);
+});
+
+// C2-05a landed: compare the real lookup index with the guard's cited-commit reader.
+// A guard that admits unmapped files, or excludes a supporting file, breaks this fixture.
+test('C2-06 cited-commit guard reads exactly the C2-05a indexed file set with supporting scope', async t => {
+  const r = repo(t), map = mapping(entry => {
+    entry.universes.harbor.supporting = ['Book One/Playground/']; return entry;
+  });
+  const read = await readLibrary({ repo: r.repo, commit: r.commit, mapping: map });
+  const index = await indexFor({ repo: r.repo, commit: r.commit, mapping: map });
+  const reader = libraryReader(r.repo, r.commit, map), admitted = [];
+  for (const entry of await listTree(r.repo, r.commit)) {
+    if (await reader.lines(r.commit, entry.path) !== null) admitted.push(entry.path);
+  }
+  assert.deepEqual(admitted.sort(), [...index.files.keys()].sort());
+  assert.deepEqual(admitted, read.files.map(f => f.path).sort());
+  assert.equal(index.files.get('Book One/Playground/What If.md').scope, 'supporting');
+  assert.equal(index.files.has('Inbox Note.md'), false);
+  assert.equal(index.files.has('Book One/Board.canvas'), false);
+});
+
+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);
+});
@@ -61,6 +61,7 @@ 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)));
Author	SHA1	Message	Date
jason.woltje	96659ccf43	row 217: record six green suites and five killed mutants for review	2026-10-24 05:24:36 -05:00
jason.woltje	2d274a5b6c	row 217: correct new runtime fixture and record first-run evidence	2026-10-24 05:06:00 -05:00
jason.woltje	6558c7bf53	row 217: trim inherited limits whitespace and refresh hashes (Untested)	2026-10-24 04:56:24 -05:00
jason.woltje	11a9ca1cff	row 217: normalize range-diff receipt whitespace (Untested)	2026-10-24 04:55:55 -05:00
jason.woltje	fc7110f0a7	row 217: availability refusal and landed supporting scope (Untested)	2026-10-24 04:55:38 -05:00
jason.woltje	2655ec010f	row 217: keep fixture status on its current served tip (Untested)	2026-10-24 04:52:18 -05:00
jason.woltje	a447880cb4	row 217: early-review coverage and availability RED cases (Untested)	2026-10-24 04:52:17 -05:00
jason.woltje	7400509ba3	row 217: citation runner retry and acceptance draft (Untested)	2026-10-24 04:52:17 -05:00
jason.woltje	b9ef816ff7	launchpad: row 217 C2-06 work in progress, UNTESTED, handed to Beakley (mos-1500) Guard, limits, M11 fence, broker guard/page store/check event, BusError reason, runtime wiring and the CLI replies verb. No runner work, no tests, nothing run. BUILD.md lists the rulings, the row 225 contract and what is left.	2026-10-24 04:52:08 -05:00
				`@@ -0,0 +1 @@`
				`M5-hide-library-unavailable: killed (control green, mutant exit 1, hashes restored, restored green)`