row224: record whole-suite passes and killed retry mutant

row224: supply required reference in creative tool fixture
row224: record CLI and bus passes and harness fixture red
2026-10-24 13:43:47 -05:00 · 2026-10-24 13:41:58 -05:00 · 2026-10-24 13:40:57 -05:00 · 2026-10-24 13:39:55 -05:00 · 2026-10-24 13:37:44 -05:00 · 2026-10-24 13:31:19 -05:00
21 changed files with 2759 additions and 5 deletions
@@ -0,0 +1,742 @@
+# Row 224 — C2-05b broker lookups and typed tools (#1725)
+
+Owner: Della; reviewer: Dewey. Assignment sage-2795; scope extension sage-2804.
+Base: `4f3fbc25a` (Researcher C2-05a). Branch: `della/row224`.
+Brief: C2-05b in `docs/plans/2026-10-20_case2-rows.md` at `aca16404c`
+and `51cc0445c`; design section 3, 5.3 M3 and 7.2; C2-05a BUILD rulings.
+
+## Execution boundary and progress
+
+Code/docs and local Git only while row 253 holds the gate. No Node (including
+syntax checks), HTTPS Git, queue claim, test or push until Sage's CLEAR.
+Tests are written first; their RED/GREEN runs are deferred, not claimed.
+Queue next is deferred too: its executable uses Node. Sage assigned this row
+explicitly. After 253 and 216 land, rebase under a new branch name.
+
+- Pre-flight: query.mjs consumes `{repo,commit,mapping}`; broker cannot import
+  Git/filesystem library code because it is in the sandbox import closure.
+  Runtime injects the host lookup adapter; existing human file/status/sync stay.
+- Pre-flight: resolved has no project list and a library is never a checkout.
+  Bundle needs an explicit library flag from launcher business configuration.
+- M3 reading: exact creative base is five lookups plus send_message; retain
+  explicitly granted broker web_search/web_fetch for research/companion under
+  landed C2-08 and sage-2804. No generic spec, task, evidence or decision tools. Residual (mos-1308): those
+  reads lack broker action checks; their typed-tool absence is the only fence
+  for creative roles. M1/M2 deny bash; broker-side refusal is outside this row.
+  Mos confirmed this interpretation in mos-1308; design wording fix belongs to Gosalyn. Other definitions retain their current tools.
+- Multi-library businesses use an optional project ID; omit it only with one
+  configured library. Universe is required for all five tools, including get.
+- Missing library uses the brief's `library-not-configured`; argument errors
+  reuse `invalid-request` and C2-05a query codes. No new action or authority.
+
+## Manifest (draft code, unrun)
+
+- bus/src/broker.mjs: five lookup verbs, strict args, holder/business rechecks.
+- bus/src/runtime.mjs: host lookup adapter, stale-before-read sync, served pin.
+- harness/src/tools.mjs: five schemas; creative exact-set filtering.
+- harness/src/bundle.mjs: library flag forwarded to typedTools.
+- cli/src/launcher.mjs: one flag derived from trusted business projects.
+- bus/tests/library-lookups.test.mjs: real query/broker/socket/runtime cases.
+- harness/tests/library-tools.test.mjs: schemas, role snapshots, bundle parity.
+- cli/tests/thread-launch.test.mjs: flag reaches a real launched bundle with no library checkout.
+- agents/della/work/queue-224/BUILD.md: manifest, rulings and deferred verification ledger.
+
+## Verification ledger
+
+No test or syntax-check run yet. Acceptance requires full bus/cli/harness suites
+and every scripts/test-*.sh on Sage's gate; focused files and affected CLI/
+seat import-closure tests precede that only in an authorized CLEAR.
+
+## Coordination
+
+Huey272 reports no runtime/bundle/launcher overlap. Rocko219 changes launcher
+THREAD_DEFINITIONS checks only, separate from our buildBundle flag argument.
+The launcher argument is required: bundle cannot derive library presence from
+checkout IDs (a library has no agent clone). No role, authority or config schema
+changes; library project entries are already validated and protected by M9.
+
+## Mount and pin impact (inspection only)
+
+No new imports in broker.mjs or tools.mjs; no RUNNER_FILES or sandbox mount
+addition. runtime.mjs is host-only and already imports library index.mjs.
+Bundle forwards only a boolean, never a root/mapping/slot/credential. The
+existing import-closure tests are bus/tests/project-runtime.test.mjs and
+seat/tests/sandbox.test.mjs. Grep found no literal sha256 pin for runtime.mjs
+or bundle.mjs; bundle tests derive current source digests through SOURCES.
+Library sources remain in the existing whole-directory release copy.
+
+## Runs to schedule only after CLEAR
+
+Set TMPDIR=/mnt/storage/scratch/tmp. Focused new bus/harness files first,
+then existing library.test.mjs, library-sync.test.mjs, project-runtime.test.mjs,
+harness creative/tools/spec-tools/bundle files and affected CLI launch tests.
+Follow with the required whole bus/cli/harness suites and Sage's full shell gate.
+No timing claim yet: use the repository/Sage per-file limits and record every
+command, outcome, elapsed time and timeout before acceptance. No focused skip
+or pattern run substitutes for whole-file gate evidence.
+
+## Read-through findings and residuals
+
+- Library get requires universe although the older design table omitted it;
+  section 3 isolation rule and C2-05a's accepted API are binding.
+- Query type enum matches mapping.TYPES (five values); manuscript is a distinct
+  lookup and not a find type. Unknown host-path/commit/business/accept fields
+  are refused; explicit project is restricted to this business's library list.
+- Async reads recheck the live holder and current project revision. A stale
+  read attempts sync, then takes the new served snapshot; a returned fetch
+  failure/divergence keeps serving the old pin. Busy sync uses the current pin.
+  Unreadable state, no served commit or unsafe configuration refuse. Query
+  and sync never hold a SQLite transaction over await.
+- Processing halt refuses new agent lookup work and rechecks before returning
+  async results. Existing human library file/status/sync behavior is unchanged.
+- Timer sync and reads still use C2-03a's 60-second contract. No timer tuning or
+  resource-limit schema is introduced by this row. Q222 creative reply settings
+  are in C2-06; no reply guard or writing capability is implemented here.
+- The generic tool socket's existing 60-second client timeout can precede the
+  server's 120-second Git timeout. This row does not change the generic timeout;
+  a timed-out lookup is read-only and retryable, never a write/outcome claim.
+- All tests are authored but unrun. No RED, GREEN, syntax, runtime performance,
+  sandbox, broker/harness suite, shell gate, claim or push evidence exists yet.
+
+## Candidate review checklist (read-through only)
+
+- [x] Five verbs mapped to real C2-05a methods, all require universe.
+- [x] Default sole library or explicit owned project; no caller repo/commit.
+- [x] Human-only file/status/sync gates kept; lookup holder rechecked.
+- [x] Async socket dispatch includes lookup verbs through LIBRARY_VERBS.
+- [x] Stale/unknown fetch syncs first; results use current immutable served pin.
+- [x] Six/eight creative names per mos-1308; other roles retain their tools.
+- [x] Launcher -> bundle -> typedTools passes presence without a library clone.
+- [x] No imports added to sandbox source closure; no mount change.
+- [ ] Execute new tests, RED characterization, full files/suites after CLEAR.
+- [ ] Rebase after rows 253/216 land, under a new branch name.
+- [ ] Claim/push only in Sage-authorized gap; Dewey review and Sage gate.
+
+Candidate preservation commits are explicitly unrun under sage-2795; they are
+not completion, green-suite or landing claims. No dependencies installed.
+
+Correction: the first committed-range diff --check found a blank line at EOF
+in the new library-tools test, missed while it was untracked. Removed in a
+follow-up local commit; the complete range must be checked again. No tests ran.
+
+## Shared-log receipts for Sage (sage-2815)
+
+The shared logs are unchanged from the base in this row. Sage appends these
+receipts in the landing sweep; they are preserved here, not in the manifest.
+
+For `BUILD-LOG.md`:
+
+```text
+2026-10-22T16:36:30Z | Della row224 C2-05b #1725 preparation | Before: C2-05a queries exist at 4f3fbc25a but no broker lookup verbs or typed tools. Scope: broker/tools plus Sage-authorized runtime/bundle integration, tests and docs. Existing human-only library reads retained; five agent queries require a live holder and trusted configured source. Code/docs only under row253 gate; no Node/test/push/claim. Runtime ownership coordinated with Rocko219/Huey272.
+```
+
+For `docs/SESSIONS.md`:
+
+```text
+2026-10-22T16:36:30Z | Della (sage-2795 / sage-2804, Q220) | Row 224 C2-05b #1725, della/row224 base 4f3fbc25a | Read both pinned briefs and C2-05a source; preparing broker/typed tools and authorized host runtime/bundle seams. No queue command, Node, HTTPS Git, claim, test or push during Gander gate. Dewey reviewer; Rocko/Huey runtime coordination sent. Tests and integration verification deferred to CLEAR.
+```
+
+Local-only draft pins 19c0a7adf/7cf39c390 are superseded by the
+log-free candidate. Saved as local branch della/row224-draft-with-logs before
+rebuilding the unpublished candidate commit; no remote history changed.
+
+## Dewey dewey-0852 and Sage sage-2819 — focused corrections
+
+B1: inline freshness uses max(lastFetch, lastError.at), not lastFetch alone.
+An error within 60 seconds counts as a recent attempt, so later lookups serve
+the old served pin without another fetch. Keep inline sync: the brief requires
+it and businesses without timed libraries have no sync timer. The extended
+failed-fetch test makes reads at +1, +59,999 and +60,000 ms (one attempt total),
+then +60,001 ms (second attempt). All reads must return the old commit.
+
+Required mutant M-B1: remove lastError.at from recentAttempt. The repeated
+reads must fail the attempted-count assertion. This mutant has NOT been run.
+
+Residual (Sage will defer): the first inline fetch in each outage window can
+still exceed the tool timeout (60 seconds, or the runner broker client’s
+30 seconds). Bounding that fetch is out of scope for 224. Subsequent reads
+are paced by persisted lastError.at. No claim of first-read outage latency.
+
+N1: whole bus, cli and harness suites are required, plus the shell gate.
+If the new thread-launch integration test skips due to sandboxProblem(),
+name the skip; a skip is not launcher integration proof.
+N2: cli/tests/thread-launch.test.mjs now depends on library/tests/helpers.mjs
+mappingEntry() and library/tests/fixtures/mapping.json. Changes to that fixture
+must rerun the CLI launch file.
+N3: harness/tests/library-tools.test.mjs compares the type enum to mapping.mjs
+TYPES, so adding a mapped type cannot silently leave the typed tool behind.
+
+These edits are local code/docs only. No Node, RED/GREEN run, mutant, claim,
+HTTPS Git or push. New local pin goes to Dewey/Mos/Sage for focused review.
+
+## sage-4163 — row224-r2 static rebase, 2026-10-24
+
+New isolated worktree: `/mnt/storage/scratch/della-row224-r2`.
+Branch `della/row224-r2`, base refactor `487500a16f4ab5902c318509fdec6acc56a543ca`.
+Only the two row-owned commits were cherry-picked, in order:
+`38e322ea0` -> `327073400`; `23816cf28` -> `e138b2c55`.
+No old prerequisite commits were copied into this series. Rows 216 and 217
+are now upstream. Row 266 remains a landing dependency: rebase on its landing
+when Sage announces it. No broker hunk touches room.read or its hydration.
+
+One content conflict: the footer of cli/tests/thread-launch.test.mjs. Kept
+both upstream C2-09a test bodies and every assertion, followed by our unchanged
+C2-05b launched-bundle test. No test was removed or weakened. Range-diff shows
+only that context relocation and the upstream sandbox workspace expression
+beside launcher's added library flag. The B1 commit is patch-identical.
+
+B1 answer: e138b2c55 retains max(lastFetch, lastError.at), the repeated-read
+regression and M-B1 specification. Dewey already checked the original fix at
+23816cf28 in dewey-0853; it still needs executed mutant and gate evidence.
+N2 dependency also includes harness/tests/library-tools.test.mjs importing
+library/src/mapping.mjs TYPES; changes there must rerun that harness file.
+
+Static checks: complete-range git diff --check clean; nine manifest paths.
+Scanned packages/*/tests for every changed basename alongside literal 64-hex
+hashes (three lines on either side): no matching hash pins. Broker and tools
+add no imports; no RUNNER_FILES or sandbox mount changes.
+No Node, syntax check, test, mutant, install or build was run. The historical
+verification ledger above records the original preparation, not current gate
+permission. Under sage-4163 the required gate is Dewey's manifest approval,
+whole bus and harness suites, plus every scripts/test-*.sh on Sage's gate;
+record every skip. Tests and mutants wait for Sage's explicit CLEAR. Static
+Git and pushing this new branch are authorized now. Shared logs remain
+unchanged; Sage owns their append-only landing receipts.
+
+## sage-4181 — row266 landing rebase, 2026-10-24
+
+Rebased the complete r2 series onto refactor
+`3e5041b43b36d7f1c5ba7ce2f14b3634fe0955db` under new branch
+`della/row224-r3`; r2 is preserved, no force-push. No conflicting files and
+no manual conflict resolutions. Range-diff: all three prior commits equal
+(212aef616, 82d6cc62c, c509dcb6e). B1 remains patch-identical.
+Complete-range diff --check is clean. No test, syntax or mutant run.
+
+Own touched test files, each to run whole in Sage's slot:
+- packages/bus/tests/library-lookups.test.mjs
+- packages/cli/tests/thread-launch.test.mjs
+- packages/harness/tests/library-tools.test.mjs
+
+Tests changed by the new upstream base, also named for the rebase-rule gate:
+- packages/bus/tests/room-check.test.mjs
+- packages/plugins/tests/room-channel.test.mjs
+- packages/supervisor/tests/pressure.test.mjs
+- packages/supervisor/tests/purity.test.mjs
+- packages/supervisor/tests/rules.test.mjs
+- packages/webui/tests/room-browser.test.mjs
+- packages/webui/tests/room-http.test.mjs
+
+None of those seven upstream test files has a row224-owned diff. Full bus and
+harness suites plus every scripts/test-*.sh remain the row gate; the listed
+CLI and upstream files require whole-file runs under sage-4181 too. Dewey's
+delta review follows Sage's run. No CLEAR is inferred from the rebase.
+
+## sage-4192 CLEAR — run receipt and old-test stop, 2026-10-24
+
+Candidate named by CLEAR: a1a7357457a31d219b99effa9b312ec78d06f060.
+Fresh mktemp TMPDIR: /mnt/storage/scratch/tmp/della-224-4192.r3L7cj.
+Each command used nice -n 19 and timeout -k 10 300 node --test FILE.
+Inherited OS niceness was -4, so nice initially yielded 15; corrected the
+current runner tree to absolute 19 during the CLI run. Future runs must set
+absolute 19 before spawning. No other seat's processes were changed.
+
+First whole bus/tests/library-lookups.test.mjs run: 11 tests, 8 pass, 3 fail,
+0 skipped, duration 1.173 s (exit 1). All three are this row's new tests.
+Root causes: Broker clones businesses, so mutating the original fixture did
+not publish the second project or the delisting; runtime requires the
+selected harness to be enabled. Fixed only new fixture setup: reloadBusiness
+after each of the two changes and plugins.harness ['pi'] in runtime fixture.
+All assertions and production code are unchanged. Whole-file rerun: 11 pass,
+0 fail/cancelled/skipped, 1.322 s (exit 0). B1 regression included and passed;
+M-B1 has not been executed.
+
+Next whole cli/tests/thread-launch.test.mjs reported OLD-test reds at :167,
+:216 and :241. On observing them stopped only this run's process tree; no
+rerun or next file was started. Interrupted-file summary: 0 pass, 3 fail,
+1 cancelled, 0 skipped, 62.988 s. Returned slot to Sage in della-0041 under
+mos-1592. No old test changed. No in-review move: the third own file, all
+seven new-base files, both whole suites and mutant evidence remain pending.
+No shell/full landing gate was run.
+
+Exact completed run receipts:
+
+```text
+{"name": "packages/bus/tests/library-lookups.test.mjs", "command": ["nice", "-n", "19", "timeout", "-k", "10", "300", "node", "--test", "packages/bus/tests/library-lookups.test.mjs"], "exit": 1, "seconds": 1.173, "TMPDIR": "/mnt/storage/scratch/tmp/della-224-4192.r3L7cj"}
+{"name": "packages/bus/tests/library-lookups.test.mjs", "command": ["nice", "-n", "19", "timeout", "-k", "10", "300", "node", "--test", "packages/bus/tests/library-lookups.test.mjs"], "exit": 0, "seconds": 1.322, "TMPDIR": "/mnt/storage/scratch/tmp/della-224-4192.r3L7cj"}
+```
+
+Old-test failure output (interrupted whole file, not a whole-file pass):
+
+```text
+✖ REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it (20120.78425ms)
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't (185.485131ms)
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it (30082.743341ms)
+
+Interrupted while running:
+
+⚠ packages/cli/tests/thread-launch.test.mjs (packages/cli/tests/thread-launch.test.mjs:1:1)
+✖ packages/cli/tests/thread-launch.test.mjs (62982.9717ms)
+ℹ tests 4
+ℹ suites 0
+ℹ pass 0
+ℹ fail 3
+ℹ cancelled 1
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 62987.534861
+
+✖ failing tests:
+
+test at packages/cli/tests/thread-launch.test.mjs:167:1
+✖ REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it (20120.78425ms)
+  Error: timed out waiting
+      at until (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:48:9)
+      at async ask (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:153:17)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:179:17)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3)
+
+test at packages/cli/tests/thread-launch.test.mjs:216:1
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't (185.485131ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  + actual - expected
+
+  + 'harness-binary-missing'
+  - 'capacity-full'
+
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:227:10)
+      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: 'harness-binary-missing',
+    expected: 'capacity-full',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+
+test at packages/cli/tests/thread-launch.test.mjs:241:1
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it (30082.743341ms)
+  Error: timed out waiting
+      at until (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:48:9)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:251:3)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
+
+test at packages/cli/tests/thread-launch.test.mjs:1:1
+✖ packages/cli/tests/thread-launch.test.mjs (62982.9717ms)
+  'Promise resolution is still pending but the event loop has already resolved'
+```
+
+Receipt correction: copied test output contained two whitespace-only lines;
+complete-range diff-check caught them. Trimmed those log lines in this
+follow-up; no test/code or failure text changed, and no test was rerun.
+
+## sage-4195 / mos-1595 — pre-install evidence
+
+No canonical node_modules link made; that suggestion was refused under
+mos-1575. Before installing anything in this worktree, ran:
+
+```text
+$ ls -l node_modules/@earendil-works/pi-coding-agent/dist/bundle/cli.js
+ls: cannot access 'node_modules/@earendil-works/pi-coding-agent/dist/bundle/cli.js': No such file or directory
+rc=2
+```
+
+The file is missing, so the authorized local npm ci follows. This is an
+environment finding; prior existing-test reds do not establish a row-code
+regression. No old-test edit or rerun preceded this CLEAR.
+
+## sage-4195 — install and single-run STOP receipt
+
+```text
+$ [ -L node_modules ] && rm node_modules; timeout -k 10 900 npm ci --ignore-scripts --no-audit --no-fund
+npm warn deprecated [email protected]: Use your platform's native DOMException instead
+added 128 packages in 2s
+npm_ci_rc=0
+$ readlink -f node_modules/.bin/pi
+/mnt/storage/scratch/della-row224-r2/node_modules/@earendil-works/pi-coding-agent/dist/bundle/cli.js
+```
+
+One authorized whole-file invocation, no retry or test edit. Absolute runner
+and timeout niceness 19 before launch; observed Node parent/worker niceness
+16 during execution (host ananicy rule), recorded without stopping for nice.
+Fresh TMPDIR and command in receipt below. Stopped test process tree upon
+observing existing-test reds. Interrupted summary: 0 pass, 2 fail, 1 cancelled,
+0 skipped; exit 1, 40.056 s. This is not a whole-file pass. The capacity test
+now receives launch-failed, rather than harness-binary-missing. Root cause of
+that launch failure is not established. No assertion/production changes.
+Slot returned to Sage in della-0044 for escalation to Mos; all other files,
+suites and M-B1 remain held pending their own CLEAR.
+
+```text
+{
+  "command": [
+    "timeout",
+    "-k",
+    "10",
+    "900",
+    "node",
+    "--test",
+    "packages/cli/tests/thread-launch.test.mjs"
+  ],
+  "TMPDIR": "/mnt/storage/scratch/tmp/della-224-4195._yq176su",
+  "exit": 1,
+  "seconds": 40.056,
+  "start_runner_nice": 19,
+  "observed_timeout_nice": 19
+}
+```
+
+Failure output:
+
+```text
+✖ REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it (20109.08171ms)
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't (330.738356ms)
+
+Interrupted while running:
+
+⚠ packages/cli/tests/thread-launch.test.mjs (packages/cli/tests/thread-launch.test.mjs:1:1)
+✖ packages/cli/tests/thread-launch.test.mjs (40023.3188ms)
+ℹ tests 3
+ℹ suites 0
+ℹ pass 0
+ℹ fail 2
+ℹ cancelled 1
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 40027.912798
+
+✖ failing tests:
+
+test at packages/cli/tests/thread-launch.test.mjs:167:1
+✖ REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it (20109.08171ms)
+  Error: timed out waiting
+      at until (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:48:9)
+      at runNextTicks (node:internal/process/task_queues:65:5)
+      at process.processTimers (node:internal/timers:615:9)
+      at async ask (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:153:17)
+      at async TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:179:17)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3)
+
+test at packages/cli/tests/thread-launch.test.mjs:216:1
+✖ REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't (330.738356ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  + actual - expected
+
+  + 'launch-failed'
+  - 'capacity-full'
+
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:227:10)
+      at runNextTicks (node:internal/process/task_queues:65:5)
+      at process.processTimers (node:internal/timers:615:9)
+      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: 'launch-failed',
+    expected: 'capacity-full',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+
+test at packages/cli/tests/thread-launch.test.mjs:1:1
+✖ packages/cli/tests/thread-launch.test.mjs (40023.3188ms)
+  'Promise resolution is still pending but the event loop has already resolved'
+```
+
+## sage-4204 — chief credential fixture correction (unrun)
+
+Sage's control pair with a 29-byte TMPDIR: base 3e5041b43 passes 14/14;
+ed985c044 passes all 14 existing tests but this row's new CLI fixture refuses
+chief-library-gitea-required before launch. Added only chief.credentials.gitea
+as a copy of the fixture coder's reference in the C2-05b edit callback, matching
+cli/tests/launcher.test.mjs:35 and trackers-boot.test.mjs:17. This is a reference
+to synthetic fixture credentials; no credential value was read or introduced.
+All assertions, old tests and production code unchanged. No run performed.
+
+The earlier 48-byte TMPDIR explains the launch-failed reds through the
+107-byte tools.sock limit, as confirmed by Sage's control. Future named CLEAR
+uses shell TMPDIR=$(mktemp -d /mnt/storage/scratch/tmp/gXXX), 29 bytes with
+alphanumeric suffix, not Python mkdtemp or a canonical node_modules link.
+Next authorized run order: whole thread-launch first, other eight files, whole
+bus/harness suites, M-B1; all await next CLEAR after Fethry/Gyro slots.
+
+## sage-4208 — first-file red, sequence stopped
+
+Named candidate 6160b4981. Whole thread-launch.test.mjs invoked once.
+Shell-created TMPDIR /mnt/storage/scratch/tmp/gCXV, 29 bytes; absolute runner
+and timeout niceness 19 at start, Node observed 16 afterwards (host policy).
+15 tests: all 14 existing tests pass, the one new C2-05b fails; no skips or
+cancellations. Exit 1 in 18.740 s. Stopped sequence and returned slot to Sage
+in della-0047 before any edit or rerun. No other file, suite or mutant ran.
+The original r3 list has nine files beyond thread-launch (two row-owned plus
+seven upstream), rather than eight; none started in this CLEAR.
+
+New-test failure is call(...).find is not a function in existing ask helper
+:153, called by new C2-05b :550. Root cause not yet established; no assertion,
+fixture or production change made. Await Sage's own-new-test ruling.
+
+Exact run receipt:
+
+```text
+{"number": 1, "name": "packages/cli/tests/thread-launch.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/cli/tests/thread-launch.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gCXV", "start_nice": 19, "observed_timeout_nice": 19, "exit": 1, "seconds": 18.74}
+```
+
+Failure output:
+
+```text
+ℹ tests 15
+ℹ suites 0
+ℹ pass 14
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 18707.936662
+
+✖ failing tests:
+
+test at packages/cli/tests/thread-launch.test.mjs:540:1
+✖ C2-05b a real launched bundle gets lookups for a library project without a library checkout (139.729167ms)
+  TypeError: call(...).find is not a function
+      at file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:153:71
+      at until (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:44:21)
+      at ask (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:153:23)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/cli/tests/thread-launch.test.mjs:550:9)
+      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)
+```
+
+## sage-4210 — new-test async citation fixture fix
+
+Only C2-05b now inlines send/wait, awaits thread.messages before .find, and
+keeps the from_role assistant / to_role human assertions previously provided
+by ask. Comment names broker.mjs:4854 async citation hydration. Existing ask,
+old tests and production unchanged. This is Sage's own-new-test ruling under
+mos-1590; Dewey re-reviews the delta. Whole-file rerun once authorized, then
+the nine other files, whole bus/harness, M-B1 and clean-tree check on green.
+Each gets a fresh shell gXXX TMPDIR and absolute nice 19; any red stops.
+
+## sage-4210 — resumed sequence, harness new-test red
+
+On 8f1b045f4: whole CLI 15/15 pass, no skips (19.164 s); whole bus lookup
+11/11 pass, no skips (1.309 s). Own new harness file 1 pass, 3 fail, no skips
+(0.129 s); stopped sequence, returned slot in della-0050 before edits/reruns.
+Each invocation used fresh shell gXXX TMPDIR, 29 bytes. Runner was set to
+absolute nice 19 before first spawn; host subsequently reniced runner too,
+so timeout process observations were 19, -4, -4. Correct future driver to set
+absolute 19 in each child before exec, as well as parent. Priority-only change
+did not stop these runs. No claim that later timeout processes retained 19.
+
+All three new harness failures are fixture validation: roles.bean.credentials
+must reference gitea (got none). Shared role() helper in this row creates bean
+without its required credential reference. No fixture/assertion/production edit
+or rerun yet; awaiting Sage's ruling. Seven upstream files, whole bus/harness
+suites and M-B1 not run. No full landing gate or in-review move.
+
+Exact receipts:
+
+```text
+{"number": 1, "name": "packages/cli/tests/thread-launch.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/cli/tests/thread-launch.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gBj5", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 19.164}
+{"number": 2, "name": "packages/bus/tests/library-lookups.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/bus/tests/library-lookups.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gD8X", "start_nice": 19, "observed_timeout_nice": -4, "exit": 0, "seconds": 1.309}
+{"number": 3, "name": "packages/harness/tests/library-tools.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/harness/tests/library-tools.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gt7o", "start_nice": 19, "observed_timeout_nice": -4, "exit": 1, "seconds": 0.129}
+```
+
+Harness failure output:
+
+```text
+✖ M3: per-role snapshots contain six names, or eight with the C2-08 web grant (6.427541ms)
+✔ every noncreative role gets lookups when a library is configured, not otherwise (6.837154ms)
+✖ lookup schemas require a universe even for get, include paging, and cannot select repo or commit (1.52147ms)
+✖ bundle flag reaches both harness tool manifests and creative prompt without generic tools (2.019053ms)
+ℹ tests 4
+ℹ suites 0
+ℹ pass 1
+ℹ fail 3
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 99.111266
+
+✖ failing tests:
+
+test at packages/harness/tests/library-tools.test.mjs:19:1
+✖ M3: per-role snapshots contain six names, or eight with the C2-08 web grant (6.427541ms)
+  Error [BusinessError]: /mnt/storage/scratch/tmp/gt7o/mosaic-harness-biz-CZEENl/businesses/acme.json roles.bean.credentials must reference exactly the services its role definition needs (gitea; got none)
+      at refuse (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/errors.mjs:12:9)
+      at checkCredentialMap (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:51:5)
+      at checkRoles (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:162:20)
+      at validateBusinessDocument (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:251:34)
+      at resolvedFor (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/helpers.mjs:46:20)
+      at role (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:13:49)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:21:42)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17) {
+    exitCode: 2
+  }
+
+test at packages/harness/tests/library-tools.test.mjs:38:1
+✖ lookup schemas require a universe even for get, include paging, and cannot select repo or commit (1.52147ms)
+  Error [BusinessError]: /mnt/storage/scratch/tmp/gt7o/mosaic-harness-biz-iAwXhO/businesses/acme.json roles.bean.credentials must reference exactly the services its role definition needs (gitea; got none)
+      at refuse (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/errors.mjs:12:9)
+      at checkCredentialMap (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:51:5)
+      at checkRoles (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:162:20)
+      at validateBusinessDocument (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:251:34)
+      at resolvedFor (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/helpers.mjs:46:20)
+      at role (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:13:49)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:39:40)
+      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) {
+    exitCode: 2
+  }
+
+test at packages/harness/tests/library-tools.test.mjs:57:1
+✖ bundle flag reaches both harness tool manifests and creative prompt without generic tools (2.019053ms)
+  Error [BusinessError]: /mnt/storage/scratch/tmp/gt7o/mosaic-harness-biz-c2N3Bv/businesses/acme.json roles.bean.credentials must reference exactly the services its role definition needs (gitea; got none)
+      at refuse (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/errors.mjs:12:9)
+      at checkCredentialMap (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:51:5)
+      at checkRoles (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:162:20)
+      at validateBusinessDocument (file:///mnt/storage/scratch/della-row224-r2/packages/business/src/business.mjs:251:34)
+      at resolvedFor (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/helpers.mjs:46:20)
+      at role (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:13:49)
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/harness/tests/library-tools.test.mjs:60:65)
+      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) {
+    exitCode: 2
+  }
+```
+
+## sage-4213 — creative fixture credential reference
+
+Only the new library-tools.test.mjs role() helper now gives bean its required
+gitea reference copied from coder, matching creative.test.mjs:27. No assertion,
+shared helper, old test or production change. One whole harness-file retry
+then seven upstream files, whole bus/harness, M-B1 and clean-tree check are
+cleared; no CLI or lookup rerun needed (both passed, unchanged). Each child
+sets absolute niceness 19 before exec, with fresh shell gXXX TMPDIR.
+
+## sage-4213 — GREEN verification and M-B1 receipt
+
+Verified candidate e4c0c8931; prior CLI/lookup passes on 8f1b045f4 remain
+applicable under sage-4213 (only harness fixture and receipts changed).
+Every run below used a fresh shell mktemp -d /mnt/storage/scratch/tmp/gXXX,
+29 bytes. Each child set absolute niceness 19 immediately before exec; timeout
+process observations were 19 for all ten runs and M-B1. Bus-suite Node later
+observed at nice 16, consistent with host ananicy policy; no stop for nice.
+No unexpected red, cancellation or skip in this cleared sequence.
+
+Whole-file results:
+
+| File or suite | Pass | Fail | Skip | Seconds |
+| --- | ---: | ---: | ---: | ---: |
+| packages/harness/tests/library-tools.test.mjs | 4 | 0 | 0 | 0.213 |
+| packages/bus/tests/room-check.test.mjs | 2 | 0 | 0 | 0.21 |
+| packages/plugins/tests/room-channel.test.mjs | 1 | 0 | 0 | 0.102 |
+| packages/supervisor/tests/pressure.test.mjs | 15 | 0 | 0 | 0.101 |
+| packages/supervisor/tests/purity.test.mjs | 1 | 0 | 0 | 0.102 |
+| packages/supervisor/tests/rules.test.mjs | 29 | 0 | 0 | 0.102 |
+| packages/webui/tests/room-browser.test.mjs | 9 | 0 | 0 | 6.801 |
+| packages/webui/tests/room-http.test.mjs | 7 | 0 | 0 | 0.183 |
+| bus-whole | 1011 | 0 | 0 | 30.46 |
+| harness-whole | 176 | 0 | 0 | 13.346 |
+
+Earlier cleared whole CLI 15/15 (19.164 s), bus lookup 11/11 (1.309 s),
+zero skips. Whole bus includes lookup again; whole harness includes fixture
+file again. No full shell/landing gate run: every scripts/test-*.sh belongs
+to Sage's landing gate, not this CLEAR.
+
+M-B1: temporarily replaced only lastError.at freshness term with -Infinity.
+Whole lookup file: 10 pass, 1 expected fail, no skips; killed at :178 attempted
+assertion (actual 2, expected 1, recent lastError prevents another sync).
+Restored exact original runtime bytes in finally. Afterwards git diff --stat
+and git status --porcelain both empty against committed e4c0c8931, before
+adding this receipt. Compared with named 6160b4981 the only later package
+changes are Sage-authorized async CLI fixture and harness credential fixture;
+no mutant or production change remains. No extra post-restore rerun.
+
+Exact commands, TMPDIRs, exit codes and elapsed receipts:
+
+```text
+{"number": 1, "name": "packages/harness/tests/library-tools.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/harness/tests/library-tools.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gct3", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.213}
+{"number": 2, "name": "packages/bus/tests/room-check.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/bus/tests/room-check.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/g0ki", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.21}
+{"number": 3, "name": "packages/plugins/tests/room-channel.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/plugins/tests/room-channel.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gyTq", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.102}
+{"number": 4, "name": "packages/supervisor/tests/pressure.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/supervisor/tests/pressure.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gK1n", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.101}
+{"number": 5, "name": "packages/supervisor/tests/purity.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/supervisor/tests/purity.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gFne", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.102}
+{"number": 6, "name": "packages/supervisor/tests/rules.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/supervisor/tests/rules.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gs9Y", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.102}
+{"number": 7, "name": "packages/webui/tests/room-browser.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/webui/tests/room-browser.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gP9P", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 6.801}
+{"number": 8, "name": "packages/webui/tests/room-http.test.mjs", "command": ["timeout", "-k", "10", "900", "node", "--test", "packages/webui/tests/room-http.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/gP9G", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 0.183}
+{"number": 9, "name": "bus-whole", "command": ["timeout", "-k", "10", "1800", "node", "--test", "packages/bus/tests/access-revoke.test.mjs", "packages/bus/tests/account-migration.test.mjs", "packages/bus/tests/address.test.mjs", "packages/bus/tests/agents.test.mjs", "packages/bus/tests/approval-binding.test.mjs", "packages/bus/tests/broker.test.mjs", "packages/bus/tests/business.test.mjs", "packages/bus/tests/channel-proof.test.mjs", "packages/bus/tests/chief-of-staff.test.mjs", "packages/bus/tests/citation-availability.test.mjs", "packages/bus/tests/citation-guard.test.mjs", "packages/bus/tests/citation-runtime.test.mjs", "packages/bus/tests/comment-cursors.test.mjs", "packages/bus/tests/comment-migration.test.mjs", "packages/bus/tests/console-decide.test.mjs", "packages/bus/tests/creative.test.mjs", "packages/bus/tests/credential-claim.test.mjs", "packages/bus/tests/credential-status.test.mjs", "packages/bus/tests/credential-store.test.mjs", "packages/bus/tests/credential-verbs.test.mjs", "packages/bus/tests/credentials.test.mjs", "packages/bus/tests/csuite-messaging.test.mjs", "packages/bus/tests/daily-quota-runtime.test.mjs", "packages/bus/tests/decision-close.test.mjs", "packages/bus/tests/decision-route.test.mjs", "packages/bus/tests/decisions.test.mjs", "packages/bus/tests/end-launch.test.mjs", "packages/bus/tests/fire-revokes-grants.test.mjs", "packages/bus/tests/gitea-grant-docker.test.mjs", "packages/bus/tests/gitea-grant.test.mjs", "packages/bus/tests/gitea-migration.test.mjs", "packages/bus/tests/grant-enroll.test.mjs", "packages/bus/tests/grant-executor.test.mjs", "packages/bus/tests/grant-host.test.mjs", "packages/bus/tests/grant-migration.test.mjs", "packages/bus/tests/grant-scope-runtime.test.mjs", "packages/bus/tests/grant-scope.test.mjs", "packages/bus/tests/hard-waits.test.mjs", "packages/bus/tests/host-run.test.mjs", "packages/bus/tests/host-tools.test.mjs", "packages/bus/tests/human.test.mjs", "packages/bus/tests/instances-verb.test.mjs", "packages/bus/tests/interpreter.test.mjs", "packages/bus/tests/land.test.mjs", "packages/bus/tests/launch-notice.test.mjs", "packages/bus/tests/launcher-released.test.mjs", "packages/bus/tests/library-credential.test.mjs", "packages/bus/tests/library-lookups.test.mjs", "packages/bus/tests/library-sync.test.mjs", "packages/bus/tests/library.test.mjs", "packages/bus/tests/lifecycle-revoke.test.mjs", "packages/bus/tests/lifecycle-verbs.test.mjs", "packages/bus/tests/limit-checks.test.mjs", "packages/bus/tests/limit-stop.test.mjs", "packages/bus/tests/limits-runtime.test.mjs", "packages/bus/tests/limits.test.mjs", "packages/bus/tests/message-citation.test.mjs", "packages/bus/tests/message-filter.test.mjs", "packages/bus/tests/messages.test.mjs", "packages/bus/tests/messaging.test.mjs", "packages/bus/tests/name-migration.test.mjs", "packages/bus/tests/names.test.mjs", "packages/bus/tests/peer-transport.test.mjs", "packages/bus/tests/peercred.test.mjs", "packages/bus/tests/plugins-verb.test.mjs", "packages/bus/tests/principal.test.mjs", "packages/bus/tests/process.test.mjs", "packages/bus/tests/processing-runtime.test.mjs", "packages/bus/tests/processing-timeout.test.mjs", "packages/bus/tests/processing-web.test.mjs", "packages/bus/tests/processing.test.mjs", "packages/bus/tests/project-await.test.mjs", "packages/bus/tests/project-files.test.mjs", "packages/bus/tests/project-runtime.test.mjs", "packages/bus/tests/publish.test.mjs", "packages/bus/tests/reload.test.mjs", "packages/bus/tests/replies.test.mjs", "packages/bus/tests/requirements.test.mjs", "packages/bus/tests/review.test.mjs", "packages/bus/tests/revoke-window.test.mjs", "packages/bus/tests/room-check.test.mjs", "packages/bus/tests/rooms.test.mjs", "packages/bus/tests/routes-verb.test.mjs", "packages/bus/tests/schema.test.mjs", "packages/bus/tests/session-clear.test.mjs", "packages/bus/tests/session-compactions.test.mjs", "packages/bus/tests/sessions.test.mjs", "packages/bus/tests/single-use.test.mjs", "packages/bus/tests/spec-migration.test.mjs", "packages/bus/tests/spec-review.test.mjs", "packages/bus/tests/spec-socket.test.mjs", "packages/bus/tests/spec.test.mjs", "packages/bus/tests/staff-request.test.mjs", "packages/bus/tests/state.test.mjs", "packages/bus/tests/store.test.mjs", "packages/bus/tests/task-page.test.mjs", "packages/bus/tests/task-read.test.mjs", "packages/bus/tests/tasks.test.mjs", "packages/bus/tests/tester-threads.test.mjs", "packages/bus/tests/tester-writes.test.mjs", "packages/bus/tests/tester.test.mjs", "packages/bus/tests/thread-claims.test.mjs", "packages/bus/tests/thread-migration.test.mjs", "packages/bus/tests/thread-shares.test.mjs", "packages/bus/tests/threads.test.mjs", "packages/bus/tests/transport.test.mjs", "packages/bus/tests/usage-broker.test.mjs", "packages/bus/tests/usage-migration.test.mjs", "packages/bus/tests/usage-runtime.test.mjs", "packages/bus/tests/usage.test.mjs", "packages/bus/tests/user-principal.test.mjs", "packages/bus/tests/viewer.test.mjs", "paLine truncated
+{"number": 10, "name": "harness-whole", "command": ["timeout", "-k", "10", "1800", "node", "--test", "packages/harness/tests/bundle.test.mjs", "packages/harness/tests/citation-runner.test.mjs", "packages/harness/tests/claude-gate.test.mjs", "packages/harness/tests/claude-session.test.mjs", "packages/harness/tests/creative.test.mjs", "packages/harness/tests/gate.test.mjs", "packages/harness/tests/git-tools.test.mjs", "packages/harness/tests/library-tools.test.mjs", "packages/harness/tests/mcp-server.test.mjs", "packages/harness/tests/pi-session.test.mjs", "packages/harness/tests/raise-domain.test.mjs", "packages/harness/tests/runner.test.mjs", "packages/harness/tests/skills.test.mjs", "packages/harness/tests/spec-tools.test.mjs", "packages/harness/tests/tools.test.mjs"], "TMPDIR": "/mnt/storage/scratch/tmp/g8Yn", "start_nice": 19, "observed_timeout_nice": 19, "exit": 0, "seconds": 13.346}
+{
+  "mutant": "M-B1",
+  "change": "drop lastError.at term from recentAttempt",
+  "command": [
+    "timeout",
+    "-k",
+    "10",
+    "900",
+    "node",
+    "--test",
+    "packages/bus/tests/library-lookups.test.mjs"
+  ],
+  "TMPDIR": "/mnt/storage/scratch/tmp/g8my",
+  "start_nice": 19,
+  "observed_timeout_nice": 19,
+  "exit": 1,
+  "seconds": 1.359
+}
+$ git diff --stat
+(empty)
+$ git status --porcelain
+(empty)
+HEAD=e4c0c8931 (authorized fixture fix after 6160b4981)
+```
+
+M-B1 output:
+
+```text
+✔ all five agent verbs read the configured served commit through real queries (130.428728ms)
+✔ each verb refuses missing universe and unknown keys before host work (78.900515ms)
+✔ no library, missing host adapter and undeclared project refuse library-not-configured (149.899073ms)
+✔ reads need the current holder on each call; human/tester/reader are not agents (90.636537ms)
+✔ releasing a claim during an async lookup fences the response (60.938885ms)
+✔ a business library removed during an async read cannot leak its result (51.783488ms)
+✖ freshness boundary, unknown last fetch and failed fetch still use immutable served state (123.453393ms)
+✔ an unreadable sync state fails closed; a busy sync keeps serving the existing pin (89.763849ms)
+✔ a stale lookup sees the commit published by its sync, not the prior served commit (108.213675ms)
+✔ real socket awaits lookup results and rechecks rejected query arguments (152.413684ms)
+✔ runtime actually injects the lookup adapter, without exposing human library.file (157.701866ms)
+ℹ tests 11
+ℹ suites 0
+ℹ pass 10
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 1327.433364
+
+✖ failing tests:
+
+test at packages/bus/tests/library-lookups.test.mjs:153:1
+✖ freshness boundary, unknown last fetch and failed fetch still use immutable served state (123.453393ms)
+  AssertionError [ERR_ASSERTION]: recent lastError prevents another sync even though lastFetch is null
+
+  2 !== 1
+
+      at TestContext.<anonymous> (file:///mnt/storage/scratch/della-row224-r2/packages/bus/tests/library-lookups.test.mjs:178:12)
+      at async Test.run (node:internal/test_runner/test:1409:7)
+      at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
+    generatedMessage: false,
+    code: 'ERR_ASSERTION',
+    actual: 2,
+    expected: 1,
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+```
@@ -0,0 +1,166 @@
+# Row 257: Q198 S1 pressure parser and pure rules evaluator
+
+Issue #1762. Brief: `docs/plans/2026-10-21_post-v1-row-briefs.md`, "Brief: Q198 S1 pressure parser and
+pure rules evaluator" and "Gate: Q198 S1" (cca206cdc). Design: `docs/plans/2026-10-21_q198-system-manager.md`
+r6.1, section 8 row S1 and section 4 (D4). Owner Morgana, reviewer Filbert, gate owner Sage (sage-2196).
+Post-v1: MVP rows and re-pin windows go ahead of it on the slot. Base: refactor cca206cdc.
+
+## Recorded choices (sage-2196 accepted each)
+
+1. **Placement.** A new package, `packages/supervisor` (`@mosaic/supervisor`), shaped like
+   packages/runs. Nothing on refactor parsed loadavg, PSI, meminfo or cgroup limits (`git grep`; the
+   only hit was an awk line in scripts/case2-precheck.sh). S2 adds the sampler process to the same
+   package. Packages aren't registered centrally, so no other file changes.
+2. **Provider scope** (429, quota, Retry-After, the half-open probe) is out. The brief puts it in S3
+   and S5.
+3. **PSI** is not required on a host that has never shown it, so a kernel built without PSI skips the
+   PSI rows instead of holding forever. Once a sample has carried PSI, it is required: a later missing
+   or stale PSI signal holds with `health-unknown`. That is the case sage-2196 asked for.
+   - Tradeoff: I latch on the first sample that carries PSI, not only on the very first sample. So PSI
+     that appears late and then disappears also holds. This is stricter than "present at the first
+     sample", and it never skips a signal the host has shown.
+4. **Memory under a cgroup.** Available memory = min(MemAvailable, limit - memory.current) at each
+   limited level. memory.current counts page cache, so this errs toward holding.
+   - Follow-up, not in this row: subtract reclaimable cache using memory.stat `inactive_file`, if S2's
+     live samples show holds that the host's MemAvailable doesn't support.
+
+Rulings on two readings from the build (sage-2202, re morgana-0057):
+
+5. **PSI latch.** PSI becomes required on the first sample that carries it. This is stricter than
+   "present at the first sample" and fails closed: a PSI file that disappears after it was seen is a
+   missing signal, so health-unknown holds.
+6. **PSI count across resources.** Design line 152 says "CPU some ≥20, memory full ≥2, or I/O full
+   ≥10, for 3 samples". The window applies to the whole disjunction, so any PSI condition on 3
+   consecutive samples holds. If Filbert reads it per resource at review, the review finding decides,
+   and the fix is a single counter.
+
+Other readings of the D4 table, made in the build:
+- **Memory floors.** "Whichever demands more free memory" means the larger floor applies. Hold below
+  max(15% x limit, 1 GiB); release above max(25% x limit, 2 GiB).
+- **Edges as written.** Hold at ≥ for load and PSI, < for memory. Release at ≤ 0.55 for load, < for
+  PSI, > for memory. Critical below 5% of the limit and below 1 GiB of disk.
+- **Sample counts.** "For 3 samples" means 3 consecutive samples. The count resets after a gap of more
+  than 6 s (the stale limit) between samples. The PSI row counts as one row (ruling 6), and the
+  reasons name the resources over on the latest sample.
+- **Memory holds on one sample.** The table's memory row has no sample count.
+- **Release** needs every applicable release condition on every sample for 30 s, by the samples' own
+  times (`>= 30000` ms after the first qualifying sample). A dead-band sample or any hold restarts the
+  window, and so does a gap of more than 6 s.
+- **Start held.** `initialState()` is held, because nothing has been seen yet. The first healthy
+  sample starts the 30 s window.
+- **Missing or stale.** Required signals are load, memory, oom and disk, plus PSI once seen. A signal
+  holds at once with `health-unknown` if it is:
+  - missing;
+  - non-numeric, negative or zero where a divisor;
+  - more than 6 s older than its sample (6 s exactly is fresh);
+  - stamped later than its sample.
+  Disk and OOM are required because the critical row can't be evaluated without them.
+- **Host-only OOM.** `/proc/vmstat` `oom_kill` gives the OOM counter when there's no cgroup
+  memory.events. The parser returns null for a kernel without it, and the sampler then has no OOM
+  signal (health-unknown).
+- **Critical** latches. It ends only when the caller passes `reconciled` with no critical condition in
+  the sample, then goes through held and the normal 30 s release. The evaluator never sets
+  `reconciled` and has no kill-switch path. Critical reasons accumulate while latched.
+- **OOM counter.** The first OOM sample is the baseline. A falling counter (a recreated cgroup) resets
+  the baseline with a note, not an event.
+- **Clock going backwards.** A sample earlier than the last one holds with `health-unknown` (unknown
+  `clock`, note `clock-backwards`).
+- **Swap activity** is parsed (`pswpin`, `pswpout`) and has no rule. D4 lists it as a signal with no
+  threshold.
+- **Settings.** `resolveRules` refuses:
+  - unknown keys and non-numbers;
+  - a release at or past its hold (load, each PSI resource);
+  - memory release floors at or below the hold floors;
+  - fractions outside (0, 1);
+  - PSI values outside 0 to 100;
+  - sample counts that aren't integers ≥ 1;
+  - a negative release window;
+  - a stale limit at or below the sample interval;
+  - a critical memory fraction at or above the hold fraction;
+  - a non-positive disk floor.
+- **Large byte values.** Parsed with `Number`. A memory.max above 2^53 loses precision, but it only
+  takes part in a min against MemTotal.
+
+## Round 2 (Filbert r1 APPROVE c30188 notes, sage-2212)
+
+- N1: `merge` checked unknown keys with `key in base`, so inherited names (`toString`, `constructor`,
+  `__proto__`) passed the check and were dropped instead of refused. It now uses
+  `Object.hasOwn(base, key)`, and the refusal test has those three cases.
+- N2: the critical-memory edge was tested only on a 32 GiB limit, where 5% is not an integer, so a
+  `<` to `<=` mutant survived. The test adds a 20 GiB limit, where 5% is exactly 1 GiB, and M8 is that
+  mutant. I checked the other memory edges for the same gap:
+  - The hold floor is non-integer on 32 GiB but is tested at exactly 1 GiB on a 4 GiB limit.
+  - The release floors are 8 GiB on 32 GiB and 2 GiB on 4 GiB, both integers.
+  - The disk edge is 1 GiB.
+
+  None has the gap.
+
+## Files
+
+- `packages/supervisor/package.json`, `README.md`
+- `src/errors.mjs`: `SupervisorError` with `kind` parse, rules or sample.
+- `src/pressure.mjs`: the nine parsers, `effectiveCpus` and `effectiveMemory`.
+- `src/rules.mjs`: `DEFAULT_RULES`, `resolveRules`, `initialState`, `evaluate`.
+- `src/index.mjs`
+- `tests/pressure.test.mjs`: parsers on kernel-shaped fixture text, with malformed, truncated and
+  repeated-key cases. Effective CPU cases cover the host-only fallback, cpuset, fractional and nested
+  `cpu.max`, and `max`. Effective memory cases cover the host-only fallback, `max`, nested levels,
+  usage over the limit, a limit above MemTotal and a missing memory.current.
+- `tests/rules.test.mjs`: the D4 table on a fake clock.
+  - Each hold and release threshold on both sides of its edge.
+  - Three-sample counting and the gap reset.
+  - The 30 s release at 29 999 and 30 000 ms, and the dead-band restart.
+  - Missing, stale, future and malformed signals.
+  - PSI never present, and PSI lost after it was present.
+  - Critical OOM, memory and disk at their edges, the reconciliation latch and the counter reset.
+  - A backwards clock, input state left unchanged, and settings refusals and overrides.
+- `tests/purity.test.mjs`: a static check that src imports only its own files and uses no
+  fs, child_process, net, os, process, dynamic import, Date or timers.
+
+No test reads /proc, /sys or a cgroup, starts a build, opens a network socket or generates load. No new
+dependency.
+
+## Mutants (each must fail its named test; the brief requires M1 and M2)
+
+| Mutant | Edit | Named test |
+|---|---|---|
+| M1 hold edge | `ratio >= rules.load.hold` becomes `>` | load holds at 0.80 for 3 samples and not at 0.7999 |
+| M2 early release | `now - next.releaseSince >= rules.releaseMs` becomes `>= 0` | the first state is held, and healthy samples open it after exactly 30 s |
+| M3 memory floor | the hold floor `Math.max` becomes `Math.min` | memory holds below the larger floor, on one sample |
+| M4 sample count | `next.loadCount >= rules.load.samples` becomes `>= 1` | load holds at 0.80 for 3 samples and not at 0.7999 |
+| M5 stale | the `now - signal.at > rules.staleMs` check is removed | a signal is stale at more than 6 s old and fresh at exactly 6 s |
+| M6 effective CPU | the quota `Math.min` becomes `Math.max` | effective CPUs take the smallest of host, cpuset and every quota level |
+| M7 critical latch | the `!reconciled` critical branch is removed | critical stays until reconciliation, then still waits the 30 s release |
+| M8 critical memory edge (r2) | `available < rules.critical.memoryFraction * limit` becomes `<=` | memory under 5% and disk under 1 GiB are critical, at their edges |
+
+## Gate (Sage's slot, on CLEAR only)
+
+- The three test files, each whole, then `node --test tests/` in packages/supervisor as the package
+  suite.
+- Then M1 to M8, each on its named test, restored after each.
+- umask 022, TMPDIR from `mktemp -d /mnt/storage/scratch/tmp/gXXXXXX`.
+- The kit is /mnt/storage/scratch/morgana-r257 (slot257.sh, mutate.py). It refuses unless HEAD is the
+  candidate and the tree is clean, and stops after two unexpected failures (mos-0823).
+- Static checks before the slot: `node --check` on every file, run from `/`. No test has run yet.
+
+## Slot result (sage-4159 CLEAR, 2026-10-24 17:00:27Z to 17:00:30Z, candidate 1261fa2d8)
+
+Run as `busy.sh && timeout -k 10 1500 slot257.sh` in its own session (setsid). The busy check read
+CLEAR. The worktree was checked out at 1261fa2d8 with a clean tree. Filbert's approved code is
+unchanged. The summary is in `gate-run.log` and the per-run node output in `mutants-run.log`.
+
+| Run | tests | pass | fail | skip | cancelled | todo |
+|---|---|---|---|---|---|---|
+| tests/pressure.test.mjs whole | 15 | 15 | 0 | 0 | 0 | 0 |
+| tests/rules.test.mjs whole | 29 | 29 | 0 | 0 | 0 | 0 |
+| tests/purity.test.mjs whole | 1 | 1 | 0 | 0 | 0 | 0 |
+| package suite `node --test tests/` | 45 | 45 | 0 | 0 | 0 | 0 |
+
+Mutants: 8 of 8 killed. Each one ran only its named test (1 test, rc=1), and each failure was an
+AssertionError in that test, not a crash: M1 hold edge, M2 early release, M3 memory floor, M4 sample
+count, M5 stale, M6 effective CPU, M7 critical latch, M8 critical memory edge.
+
+Restore check: `git checkout -- packages/supervisor` ran after each mutant, and the script found the
+tree clean every time. At the end HEAD was 1261fa2d8 and `git status --porcelain` was empty. After the
+run no node, python or bash process had its cwd under the kit or the worktree, and no g257 TMPDIR was
+left behind. The run reached no scripts/test-*.sh.
@@ -0,0 +1,34 @@
+CLEAR
+== files 2026-10-24T17:00:27Z
+file-pressure          rc=0    1s ℹ pass 15 ℹ fail 0
+file-rules             rc=0    0s ℹ pass 29 ℹ fail 0
+file-purity            rc=0    0s ℹ pass 1 ℹ fail 0
+== package suite 2026-10-24T17:00:28Z
+suite-supervisor       rc=0    0s ℹ pass 45 ℹ fail 0
+== mx 2026-10-24T17:00:28Z (each must fail its named test)
+M1 applied to rules.mjs
+mx-M1                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M1 KILLED
+M2 applied to rules.mjs
+mx-M2                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M2 KILLED
+M3 applied to rules.mjs
+mx-M3                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M3 KILLED
+M4 applied to rules.mjs
+mx-M4                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M4 KILLED
+M5 applied to rules.mjs
+mx-M5                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M5 KILLED
+M6 applied to pressure.mjs
+mx-M6                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M6 KILLED
+M7 applied to rules.mjs
+mx-M7                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M7 KILLED
+M8 applied to rules.mjs
+mx-M8                  rc=1    0s ℹ pass 0 ℹ fail 1
+  mx-M8 KILLED
+restored at 1261fa2d8
+SLOT257_DONE 2026-10-24T17:00:30Z
@@ -0,0 +1,391 @@
+===== file-pressure.log
+✔ loadavg parses the three loads (1.192277ms)
+✔ a malformed loadavg throws (0.412303ms)
+✔ meminfo returns bytes and keeps unitless counts (0.258214ms)
+✔ meminfo without MemAvailable, with a repeated key or a bad line throws (0.206592ms)
+✔ PSI parses some and full, and cpu may lack full (0.374747ms)
+✔ PSI without a full line for memory or io, or with a bad line, throws (0.195229ms)
+✔ CPU lists count distinct CPUs (0.237299ms)
+✔ cpu.max gives the quota in CPUs, or null for max (0.23685ms)
+✔ memory.max, memory.current and memory.events (0.351243ms)
+✔ vmstat gives swap counters and the host OOM counter (0.234271ms)
+✔ effective CPUs fall back to the host count with no cgroup input (0.119728ms)
+✔ effective CPUs take the smallest of host, cpuset and every quota level (0.117052ms)
+✔ effective memory falls back to the host with no cgroup levels, or only max (0.609639ms)
+✔ effective memory uses the tightest limited level (0.187466ms)
+✔ a limited level without memory.current throws (0.096904ms)
+ℹ tests 15
+ℹ suites 0
+ℹ pass 15
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 171.66419
+===== file-rules.log
+✔ the first state is held, and healthy samples open it after exactly 30 s (2.048214ms)
+✔ load holds at 0.80 for 3 samples and not at 0.7999 (1.121376ms)
+✔ load divides by effective CPUs, fractional ones included (0.360874ms)
+✔ a gap of more than 6 s resets the consecutive count (0.343221ms)
+✔ load releases at 0.55 and not at 0.5501 (0.435882ms)
+✔ a dead-band sample restarts the 30 s release window (0.376884ms)
+✔ memory holds below the larger floor, on one sample (0.259125ms)
+✔ on a small limit the 1 GiB floor is the larger one (0.346965ms)
+✔ memory releases only above the larger release floor (0.906516ms)
+✔ each PSI hold threshold holds at its value for 3 samples and not just below (0.661209ms)
+✔ the PSI count runs across resources (0.15624ms)
+✔ each PSI release threshold blocks at its value and releases just below (0.613751ms)
+✔ a missing required signal holds at once with health-unknown (0.388768ms)
+✔ a signal is stale at more than 6 s old and fresh at exactly 6 s (0.446828ms)
+✔ malformed signal values count as missing (0.787389ms)
+✔ after health-unknown, recovery waits the full 30 s (0.34472ms)
+✔ a host that never had PSI skips the PSI rows (0.201995ms)
+✔ PSI that disappears after it was present holds with health-unknown (0.634442ms)
+✔ a rise in the OOM kill counter is critical; the first sample is the baseline (0.230518ms)
+✔ a falling OOM counter resets the baseline with a note, not an event (0.208182ms)
+✔ memory under 5% and disk under 1 GiB are critical, at their edges (0.800954ms)
+✔ critical stays until reconciliation, then still waits the 30 s release (0.585483ms)
+✔ critical reasons accumulate while critical (0.174367ms)
+✔ a clock that goes backwards holds with health-unknown (0.165886ms)
+✔ a sample without a numeric time throws (0.515819ms)
+✔ evaluate doesn't change the state it was given (0.327166ms)
+✔ resolveRules with no overrides is the D4 table, frozen (0.502534ms)
+✔ overrides apply in the evaluator (0.291524ms)
+✔ contradictory or unknown settings refuse (1.168994ms)
+ℹ tests 29
+ℹ suites 0
+ℹ pass 29
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 86.686704
+===== file-purity.log
+✔ src reads no file, process, network or clock (1.611513ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 1
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 63.38547
+===== suite-supervisor.log
+✔ loadavg parses the three loads (1.322312ms)
+✔ a malformed loadavg throws (0.491714ms)
+✔ meminfo returns bytes and keeps unitless counts (0.306568ms)
+✔ meminfo without MemAvailable, with a repeated key or a bad line throws (0.282108ms)
+✔ PSI parses some and full, and cpu may lack full (0.382364ms)
+✔ PSI without a full line for memory or io, or with a bad line, throws (0.229427ms)
+✔ CPU lists count distinct CPUs (0.310693ms)
+✔ cpu.max gives the quota in CPUs, or null for max (0.258658ms)
+✔ memory.max, memory.current and memory.events (0.36499ms)
+✔ vmstat gives swap counters and the host OOM counter (0.27834ms)
+✔ effective CPUs fall back to the host count with no cgroup input (0.148614ms)
+✔ effective CPUs take the smallest of host, cpuset and every quota level (0.118641ms)
+✔ effective memory falls back to the host with no cgroup levels, or only max (0.189321ms)
+✔ effective memory uses the tightest limited level (0.248126ms)
+✔ a limited level without memory.current throws (0.174502ms)
+✔ src reads no file, process, network or clock (1.698537ms)
+✔ the first state is held, and healthy samples open it after exactly 30 s (2.722678ms)
+✔ load holds at 0.80 for 3 samples and not at 0.7999 (1.31022ms)
+✔ load divides by effective CPUs, fractional ones included (0.457608ms)
+✔ a gap of more than 6 s resets the consecutive count (0.487291ms)
+✔ load releases at 0.55 and not at 0.5501 (0.471881ms)
+✔ a dead-band sample restarts the 30 s release window (0.407363ms)
+✔ memory holds below the larger floor, on one sample (0.311888ms)
+✔ on a small limit the 1 GiB floor is the larger one (0.337859ms)
+✔ memory releases only above the larger release floor (0.852137ms)
+✔ each PSI hold threshold holds at its value for 3 samples and not just below (0.670722ms)
+✔ the PSI count runs across resources (0.168238ms)
+✔ each PSI release threshold blocks at its value and releases just below (0.706245ms)
+✔ a missing required signal holds at once with health-unknown (0.45638ms)
+✔ a signal is stale at more than 6 s old and fresh at exactly 6 s (0.501209ms)
+✔ malformed signal values count as missing (0.703616ms)
+✔ after health-unknown, recovery waits the full 30 s (0.252741ms)
+✔ a host that never had PSI skips the PSI rows (0.136341ms)
+✔ PSI that disappears after it was present holds with health-unknown (0.302628ms)
+✔ a rise in the OOM kill counter is critical; the first sample is the baseline (0.181417ms)
+✔ a falling OOM counter resets the baseline with a note, not an event (0.166744ms)
+✔ memory under 5% and disk under 1 GiB are critical, at their edges (0.59429ms)
+✔ critical stays until reconciliation, then still waits the 30 s release (0.346404ms)
+✔ critical reasons accumulate while critical (0.111712ms)
+✔ a clock that goes backwards holds with health-unknown (0.098686ms)
+✔ a sample without a numeric time throws (0.425754ms)
+✔ evaluate doesn't change the state it was given (0.239173ms)
+✔ resolveRules with no overrides is the D4 table, frozen (0.368226ms)
+✔ overrides apply in the evaluator (0.251687ms)
+✔ contradictory or unknown settings refuse (0.917827ms)
+ℹ tests 45
+ℹ suites 0
+ℹ pass 45
+ℹ fail 0
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 92.173971
+===== mx-M1.log
+✖ load holds at 0.80 for 3 samples and not at 0.7999 (2.627622ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 53.826624
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:75:1
+✖ load holds at 0.80 for 3 samples and not at 0.7999 (2.627622ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+  + actual - expected
+  
+    [
+      'open',
+      'open',
+  +   'open'
+  -   'held'
+    ]
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:77:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: [ 'open', 'open', 'open' ],
+    expected: [ 'open', 'open', 'held' ],
+    operator: 'deepStrictEqual',
+    diff: 'simple'
+  }
+===== mx-M2.log
+✖ the first state is held, and healthy samples open it after exactly 30 s (1.670671ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 48.463372
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:62:1
+✖ the first state is held, and healthy samples open it after exactly 30 s (1.670671ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  
+  'open' !== 'held'
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:65:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 'open',
+    expected: 'held',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+===== mx-M3.log
+✖ memory holds below the larger floor, on one sample (2.628385ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 54.087261
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:119:1
+✖ memory holds below the larger floor, on one sample (2.628385ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  
+  'open' !== 'held'
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:125:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 'open',
+    expected: 'held',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+===== mx-M4.log
+✖ load holds at 0.80 for 3 samples and not at 0.7999 (2.72525ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 54.494912
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:75:1
+✖ load holds at 0.80 for 3 samples and not at 0.7999 (2.72525ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+  + actual - expected
+  
+    [
+  -   'open',
+  -   'open',
+      'held',
+  +   'held',
+  +   'held'
+    ]
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:77:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: [ 'held', 'held', 'held' ],
+    expected: [ 'open', 'open', 'held' ],
+    operator: 'deepStrictEqual',
+    diff: 'simple'
+  }
+===== mx-M5.log
+✖ a signal is stale at more than 6 s old and fresh at exactly 6 s (2.946775ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 58.672563
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:187:1
+✖ a signal is stale at more than 6 s old and fresh at exactly 6 s (2.946775ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+  + actual - expected
+  
+  + []
+  - [
+  -   'load'
+  - ]
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:191:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: [],
+    expected: [ 'load' ],
+    operator: 'deepStrictEqual',
+    diff: 'simple'
+  }
+===== mx-M6.log
+✖ effective CPUs take the smallest of host, cpuset and every quota level (1.625079ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 55.012035
+
+✖ failing tests:
+
+test at tests/pressure.test.mjs:101:1
+✖ effective CPUs take the smallest of host, cpuset and every quota level (1.625079ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  
+  4 !== 1.5
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/pressure.test.mjs:103:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 4,
+    expected: 1.5,
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
+===== mx-M7.log
+✖ critical stays until reconciliation, then still waits the 30 s release (4.842568ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 54.317924
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:259:1
+✖ critical stays until reconciliation, then still waits the 30 s release (4.842568ms)
+  AssertionError [ERR_ASSERTION]: The expression evaluated to a falsy value:
+  
+    assert.ok(waiting.decisions.every((d) => d.mode === "critical" && d.reasons[0] === "critical-disk"))
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:262:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: false,
+    expected: true,
+    operator: '==',
+    diff: 'simple'
+  }
+===== mx-M8.log
+✖ memory under 5% and disk under 1 GiB are critical, at their edges (3.080014ms)
+ℹ tests 1
+ℹ suites 0
+ℹ pass 0
+ℹ fail 1
+ℹ cancelled 0
+ℹ skipped 0
+ℹ todo 0
+ℹ duration_ms 49.440823
+
+✖ failing tests:
+
+test at tests/rules.test.mjs:245:1
+✖ memory under 5% and disk under 1 GiB are critical, at their edges (3.080014ms)
+  AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+  
+  'critical' !== 'held'
+  
+      at TestContext.<anonymous> (file:///home/jwoltje/.t3/worktrees/mosaic-stack/morgana-row257/packages/supervisor/tests/rules.test.mjs:253:10)
+      at Test.runInAsyncScope (node:async_hooks:226:14)
+      at Test.run (node:internal/test_runner/test:1402:25)
+      at Test.start (node:internal/test_runner/test:1262:17)
+      at startSubtestAfterBootstrap (node:internal/test_runner/harness:387:17) {
+    generatedMessage: true,
+    code: 'ERR_ASSERTION',
+    actual: 'critical',
+    expected: 'held',
+    operator: 'strictEqual',
+    diff: 'simple'
+  }
@@ -101,7 +101,16 @@ export const TASK_PAGE_MAX = 200;
 // request allowed past the ordinary 64 KiB envelope (server.mjs and client.mjs), up to its content cap.
 export const PROJECT_FILE_VERBS = Object.freeze(['project.files', 'project.file', 'project.file.save']);
 // C2-03a: library.sync is the human's fetch, and with `accept` the one way past library-diverged.
-export const LIBRARY_VERBS = Object.freeze(['library.file', 'library.status', 'library.sync']);
+// Row 224: pure agent lookups are separate from the three human-only verbs. Listing them
+// here also makes server.mjs await their host effects instead of serializing a Promise as {}.
+const LIBRARY_LOOKUPS = Object.freeze({
+  'library.find': { method: 'find', fields: ['universe', 'query', 'type', 'book', 'scope', 'offset'], required: ['universe', 'query'] },
+  'library.get': { method: 'get', fields: ['universe', 'path', 'from', 'links_from'], required: ['universe', 'path'] },
+  'library.search': { method: 'search', fields: ['universe', 'text', 'book', 'scope', 'offset'], required: ['universe', 'text'] },
+  'library.manuscript': { method: 'manuscript', fields: ['universe', 'book', 'scope', 'chapter', 'from', 'to'], required: ['universe', 'book'] },
+  'library.universe': { method: 'universeInfo', fields: ['universe'], required: ['universe'] },
+});
+export const LIBRARY_VERBS = Object.freeze(['library.file', 'library.status', 'library.sync', ...Object.keys(LIBRARY_LOOKUPS)]);
 export const PROJECT_SAVE_VERB = 'project.file.save';
 export const PROJECT_SAVE_REQUEST_MAX = 1024 * 1024 + 64 * 1024;
 export const WEB_VERBS =Object.freeze(['web.search', 'web.fetch']);
@@ -5352,10 +5361,42 @@ export class Broker {
      throw this.#refused(s, ProjectFailure && e instanceof ProjectFailure ? new BusError(e.code) : e, request);
    }
  }
+  // Row 224 C2-05b: the agent never supplies a host repo, commit or business. Its current
+  // holder and business entry are rechecked before/after awaits; runtime owns Git and queries.
+  async #requestLibraryLookup(s, { verb, args }) {
+    try {
+      this.#agent(s);
+      const business = this.#business(s.business);
+      const projects = Object.entries(business.projects ?? {}).filter(([, entry]) => entry.kind === 'library');
+      if (!projects.length || typeof this.#library?.lookup !== 'function') fail('library-not-configured');
+      const spec = LIBRARY_LOOKUPS[verb];
+      keys(args, ['project', ...spec.fields], spec.required);
+      if (!text(args.universe, 160)) fail('invalid-request');
+      if (args.project === undefined && projects.length !== 1) fail('invalid-request');
+      const project = args.project ?? projects[0][0];
+      if (!text(project, 160) || !projects.some(([name]) => name === project)) fail('library-not-configured');
+      const revision = JSON.stringify(business.projects[project]);
+      const authorize = () => {
+        this.#agent(s);
+        this.#processingGate(s, verb);
+        if (JSON.stringify(this.#business(s.business).projects?.[project]) !== revision) fail('library-not-configured');
+      };
+      const { project: ignored, ...query } = args;
+      authorize();
+      const result = await this.#library.lookup({ business, project }, { method: spec.method, args: query, authorize });
+      authorize();
+      this.#secretCheck(result);
+      return result;
+    } catch (error) {
+      const Failure = this.#library?.LibraryError;
+      throw this.#refused(s, Failure && error instanceof Failure ? new BusError(error.code) : error, { verb, args });
+    }
+  }
  // C2-04 M4: only a verified human reads library text or status. Host Git
  // functions stay injected, preserving this module's sandbox import closure.
  async #requestLibrary(s, request) {
    const { verb, args } = request;
+    if (Object.hasOwn(LIBRARY_LOOKUPS, verb)) return this.#requestLibraryLookup(s, request);
    try {
      this.#human(s);
      const fields = verb === 'library.file' ? ['project', 'path'] : verb === 'library.sync' ? ['project', 'accept'] : ['project'];
@@ -87,6 +87,38 @@ export async function harnessLevels({ log = (e) => process.stderr.write(`plugins
  }
  return (name) => levels.get(name) ?? null;
 }
+// Row 224 C2-05b: a host-only adapter. A failed fetch keeps serving immutable old
+// objects, as C2-03a requires; no caller may select a repo, commit or sync --accept.
+export function createLibraryLookup({ dataRoot, sync, now = () => Date.now() }) {
+  const methods = { find: libraryModule.find, get: libraryModule.get, search: libraryModule.search,
+    manuscript: libraryModule.manuscript, universeInfo: libraryModule.universeInfo };
+  return async (context, { method, args, authorize }) => {
+    if (!Object.hasOwn(methods, method)) throw new libraryModule.LibraryError('query-argument-invalid', 'unknown lookup');
+    authorize();
+    const source = { ...context, dataRoot };
+    let state = await libraryModule.libraryStatus(source);
+    authorize();
+    // sage-2819 / dewey-0852: failed attempts also pace inline retries. Otherwise an
+    // outage makes every lookup refetch while lastFetch remains old or null.
+    const recentAttempt = Math.max(state.lastFetch === null ? -Infinity : Date.parse(state.lastFetch),
+      state.lastError === null ? -Infinity : Date.parse(state.lastError.at));
+    const age = now() - recentAttempt;
+    if (age > libraryModule.SYNC_INTERVAL_MS || age < 0) {
+      try { await sync(source); }
+      catch (error) {
+        // A timer may already be fetching this mirror. Its current served state is still safe.
+        if (!(error instanceof libraryModule.LibraryError) || error.code !== 'library-sync-busy') throw error;
+      }
+      authorize();
+      state = await libraryModule.libraryStatus(source);
+    }
+    if (!state.served) throw new libraryModule.LibraryError('library-commit', 'library has never been synced');
+    authorize();
+    return methods[method]({ repo: libraryModule.mirrorPath(source), commit: state.served,
+      mapping: libraryModule.checkMapping(context.business.projects[context.project]) }, args);
+  };
+}
+
 export async function startBroker({
  dataRoot,
  businesses,
@@ -310,6 +342,8 @@ export async function startBroker({
      store,
      businesses,
      library: {
+        lookup: createLibraryLookup({ dataRoot, sync: context =>
+          processing.work(() => libraryModule.sync(context, syncOptions(context.business))) }),
        readFile: context => libraryModule.readLibraryFile({ ...context, dataRoot }),
        status: context => libraryModule.libraryStatus({ ...context, dataRoot }),
        sync: (context, { accept }) => processing.work(() => libraryModule.sync({ ...context, dataRoot }, { ...syncOptions(context.business), accept })),
@@ -0,0 +1,237 @@
+// Row 224: exercise broker authorization, real C2-05a queries and host served snapshots.
+// All bodies and remotes are made up. External sync is replaced only at its trusted host seam.
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { mkdirSync, writeFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { Store } from '../src/store.mjs';
+import { Broker } from '../src/broker.mjs';
+import { createLibraryLookup, startBroker } from '../src/runtime.mjs';
+import { serve } from '../src/server.mjs';
+import { Client } from '../src/client.mjs';
+import * as library from '../../library/src/index.mjs';
+import { scratchRepo, note } from '../../library/tests/query-fixture.mjs';
+import { mappingEntry, git } from '../../library/tests/helpers.mjs';
+
+const NOW = Date.parse('2026-10-22T16:00:00.000Z');
+const VERBS = ['library.find', 'library.get', 'library.search', 'library.manuscript', 'library.universe'];
+const GET = { universe: 'harbor', path: 'Book One/Characters/Tomas.md' };
+const ARGS = [
+  { universe: 'harbor', query: 'Tomas' }, GET,
+  { universe: 'harbor', text: 'ferry' }, { universe: 'harbor', book: 'Book One' }, { universe: 'harbor' },
+];
+const TEXTS = {
+  'Book One/Characters/Tomas.md': note('character', 'Tomas', 'He runs the ferry. [[Elsewhere]]'),
+  'Book One/Chapters/01.md': '# A ferry\nOne line.\n',
+  'Book One/Playground/What If.md': note('character', 'Maybe Tomas', 'Unwritten ferry.'),
+  'Second World/Characters/Elsewhere.md': note('character', 'Elsewhere', 'Other ferry.'),
+};
+
+async function world(t, { projects, adapter, claimed = true, now = () => NOW } = {}) {
+  const f = scratchRepo(t, TEXTS), dataRoot = join(f.root, 'data');
+  mkdirSync(dataRoot);
+  const business = { id: 'acme', human: 'jason', vars: { 'bus.tester': true },
+    projects: projects ?? { books: mappingEntry() }, arbiters: { technical: 'coder', delivery: 'coder' },
+    roles: { coder: { definition: 'coder', authority: { withinRole: [], crossRole: [] } } } };
+  const context = { business, project: 'books', dataRoot };
+  let mirror = null, state = null, fetches = 0;
+  if (business.projects.books?.kind === 'library') {
+    mirror = await library.ensureMirror(context);
+    git(f.repo, '-c', 'protocol.file.allow=always', 'push', '-q', mirror, 'HEAD:refs/heads/served');
+    state = { version: 1, branch: 'main', served: f.commit, lastFetch: new Date(NOW).toISOString(),
+      lastError: null, diverged: null, problems: [] };
+    writeFileSync(join(mirror, library.SYNC_STATE_FILE), JSON.stringify(state), { mode: 0o600 });
+  }
+  const setState = patch => {
+    state = { ...state, ...patch };
+    writeFileSync(join(mirror, library.SYNC_STATE_FILE), JSON.stringify(state), { mode: 0o600 });
+  };
+  const lookup = createLibraryLookup({ dataRoot, now, sync: async () => {
+    fetches++;
+    setState({ lastFetch: new Date(now()).toISOString() });
+    return { state, code: null };
+  } });
+  const store = new Store(dataRoot);
+  t.after(() => store.close());
+  const broker = new Broker({ store, businesses: { acme: business },
+    library: adapter ?? { lookup, LibraryError: library.LibraryError } });
+  const agent = broker.bindLaunch({ business: 'acme', role: 'coder', run: 'r224', harness: 'pi' });
+  if (claimed) broker.request(agent, { verb: 'role.claim' });
+  const human = broker.bindHuman({ business: 'acme', human: 'jason', via: 'cli', outsideAgent: true });
+  const reader = broker.bindReader({ business: 'acme' }), tester = broker.bindTester({ business: 'acme' });
+  const call = (verb, args = {}, cap = agent) => Promise.resolve().then(() => broker.request(cap, { verb, args }));
+  return { ...f, dataRoot, business, context, mirror, store, broker, agent, human, reader, tester,
+    call, lookup, setState, fetches: () => fetches };
+}
+
+test('all five agent verbs read the configured served commit through real queries', async t => {
+  const f = await world(t);
+  const [find, get, search, manuscript, universe] = await Promise.all(VERBS.map((verb, i) => f.call(verb, ARGS[i])));
+  for (const result of [find, get, search, manuscript, universe]) assert.equal(result.commit, f.commit);
+  assert.deepEqual(find.results.map(x => x.path), ['Book One/Characters/Tomas.md']);
+  assert.match(JSON.stringify(get.lines), /He runs the ferry/);
+  assert.deepEqual(get.links_out, []); // The only target is in another universe.
+  assert.ok(search.results.length > 0);
+  assert.ok(search.results.every(x => !x.path.startsWith('Second World/') && x.scope === 'canon'));
+  assert.equal(manuscript.path, 'Book One/Chapters/01.md');
+  assert.deepEqual(universe.books, ['Book One']);
+  assert.equal(f.fetches(), 0);
+  const playground = await f.call('library.find', { universe: 'harbor', query: '', scope: 'playground' });
+  assert.deepEqual(playground.results.map(x => x.path), ['Book One/Playground/What If.md']);
+  assert.equal(await f.call('library.get', { universe: 'harbor', path: 'Second World/Characters/Elsewhere.md' }), null);
+});
+
+test('each verb refuses missing universe and unknown keys before host work', async t => {
+  let calls = 0;
+  const f = await world(t, { adapter: { lookup: () => { calls++; } } });
+  for (const [i, verb] of VERBS.entries()) {
+    const { universe, ...missing } = ARGS[i];
+    await assert.rejects(f.call(verb, missing), { code: 'invalid-request' });
+    for (const extra of [{ repo: '/elsewhere' }, { commit: 'b'.repeat(40) }, { business: 'other' }, { accept: 'b'.repeat(40) }])
+      await assert.rejects(f.call(verb, { ...ARGS[i], ...extra }), { code: 'invalid-request' });
+    await assert.rejects(f.call(verb, { ...ARGS[i], universe: '' }), { code: 'invalid-request' });
+  }
+  assert.equal(calls, 0);
+});
+
+test('no library, missing host adapter and undeclared project refuse library-not-configured', async t => {
+  const noLibrary = await world(t, { projects: {} });
+  const noAdapter = await world(t, { adapter: {} });
+  const f = await world(t);
+  for (const [i, verb] of VERBS.entries()) {
+    await assert.rejects(noLibrary.call(verb, ARGS[i]), { code: 'library-not-configured' });
+    await assert.rejects(noAdapter.call(verb, ARGS[i]), { code: 'library-not-configured' });
+    await assert.rejects(f.call(verb, { ...ARGS[i], project: 'other' }), { code: 'library-not-configured' });
+  }
+  f.business.projects.second = mappingEntry();
+  f.broker.reloadBusiness('acme', f.business);
+  await assert.rejects(f.call('library.get', GET), { code: 'invalid-request' });
+  assert.equal((await f.call('library.get', { ...GET, project: 'books' })).commit, f.commit);
+});
+
+test('reads need the current holder on each call; human/tester/reader are not agents', async t => {
+  const f = await world(t, { claimed: false });
+  for (const [i, verb] of VERBS.entries()) {
+    await assert.rejects(f.call(verb, ARGS[i]), { code: 'not-holder' });
+    await assert.rejects(f.call(verb, ARGS[i], f.human), { code: 'agent-required' });
+    await assert.rejects(f.call(verb, ARGS[i], f.tester), { code: 'tester-refused' });
+    await assert.rejects(f.call(verb, ARGS[i], f.reader), { code: 'read-only' });
+  }
+  f.broker.request(f.agent, { verb: 'role.claim' });
+  assert.equal((await f.call('library.get', GET)).commit, f.commit);
+  f.broker.request(f.agent, { verb: 'role.release' });
+  await assert.rejects(f.call('library.get', GET), { code: 'not-holder' });
+});
+
+test('releasing a claim during an async lookup fences the response', { timeout: 30_000 }, async t => {
+  let release, entered;
+  const started = new Promise(resolve => { entered = resolve; });
+  const f = await world(t, { adapter: { lookup: async () => {
+    entered(); await new Promise(resolve => { release = resolve; }); return { lines: [[1, 'not returned']] };
+  } } });
+  const pending = f.call('library.get', GET);
+  await started;
+  f.broker.request(f.agent, { verb: 'role.release' });
+  release();
+  await assert.rejects(pending, { code: 'not-holder' });
+});
+
+test('a business library removed during an async read cannot leak its result', { timeout: 30_000 }, async t => {
+  let release, entered;
+  const started = new Promise(resolve => { entered = resolve; });
+  const f = await world(t, { adapter: { lookup: async () => {
+    entered(); await new Promise(resolve => { release = resolve; }); return { lines: [[1, 'not returned']] };
+  } } });
+  const pending = f.call('library.get', GET);
+  await started;
+  delete f.business.projects.books;
+  f.broker.reloadBusiness('acme', f.business);
+  release();
+  await assert.rejects(pending, { code: 'library-not-configured' });
+});
+
+test('freshness boundary, unknown last fetch and failed fetch still use immutable served state', async t => {
+  const f = await world(t);
+  f.setState({ lastFetch: new Date(NOW - 60_000).toISOString() });
+  await f.call('library.get', GET);
+  assert.equal(f.fetches(), 0);
+  f.setState({ lastFetch: new Date(NOW - 60_001).toISOString() });
+  await f.call('library.get', GET);
+  assert.equal(f.fetches(), 1);
+  f.setState({ lastFetch: null });
+  await f.call('library.universe', { universe: 'harbor' });
+  assert.equal(f.fetches(), 2);
+  let attempted = 0, clock = NOW;
+  const failing = createLibraryLookup({ dataRoot: f.dataRoot, now: () => clock, sync: async () => {
+    attempted++;
+    f.setState({ lastError: { code: 'library-fetch-failed', at: new Date(clock).toISOString() } });
+    return { code: 'library-fetch-failed' };
+  } });
+  f.setState({ lastFetch: null });
+  const result = await failing(f.context, { method: 'get', args: GET, authorize() {} });
+  assert.equal(attempted, 1);
+  assert.equal(result.commit, f.commit);
+  for (const elapsed of [1, 59_999, 60_000]) {
+    clock = NOW + elapsed;
+    const retry = await failing(f.context, { method: 'get', args: GET, authorize() {} });
+    assert.equal(retry.commit, f.commit, 'serve the old pin during the failure cooldown');
+    assert.equal(attempted, 1, 'recent lastError prevents another sync even though lastFetch is null');
+  }
+  clock = NOW + 60_001;
+  assert.equal((await failing(f.context, { method: 'get', args: GET, authorize() {} })).commit, f.commit);
+  assert.equal(attempted, 2, 'retry only after the failed-attempt interval expires');
+});
+
+test('an unreadable sync state fails closed; a busy sync keeps serving the existing pin', async t => {
+  const f = await world(t);
+  const lookup = createLibraryLookup({ dataRoot: f.dataRoot, now: () => NOW, sync: async () => {
+    throw new library.LibraryError('library-sync-busy', 'another fetch');
+  } });
+  f.setState({ lastFetch: null });
+  assert.equal((await lookup(f.context, { method: 'get', args: GET, authorize() {} })).commit, f.commit);
+  writeFileSync(join(f.mirror, library.SYNC_STATE_FILE), '{bad json', { mode: 0o600 });
+  await assert.rejects(f.call('library.get', GET), { code: 'library-state-invalid' });
+});
+
+test('a stale lookup sees the commit published by its sync, not the prior served commit', async t => {
+  const f = await world(t);
+  writeFileSync(join(f.repo, GET.path), note('character', 'Tomas', 'Changed ferry.'));
+  git(f.repo, 'add', '-A'); git(f.repo, 'commit', '-qm', 'second fixture');
+  const next = git(f.repo, 'rev-parse', 'HEAD');
+  const lookup = createLibraryLookup({ dataRoot: f.dataRoot, now: () => NOW, sync: async () => {
+    git(f.repo, '-c', 'protocol.file.allow=always', 'push', '-q', f.mirror, 'HEAD:refs/heads/served');
+    f.setState({ served: next, lastFetch: new Date(NOW).toISOString() });
+    return { code: null };
+  } });
+  f.setState({ lastFetch: null });
+  const result = await lookup(f.context, { method: 'get', args: GET, authorize() {} });
+  assert.equal(result.commit, next);
+  assert.match(JSON.stringify(result.lines), /Changed ferry/);
+});
+
+test('real socket awaits lookup results and rechecks rejected query arguments', { timeout: 30_000 }, async t => {
+  const f = await world(t);
+  const path = join(f.root, 'lookup.sock');
+  const server = await serve({ broker: f.broker, path }); t.after(() => server.close());
+  const client = new Client({ path, cap: f.agent });
+  const result = await client.call('library.get', GET);
+  assert.equal(result.commit, f.commit);
+  await assert.rejects(client.call('library.find', { universe: 'harbor', query: '', scope: 'anything' }), /query-argument-invalid/);
+});
+
+test('runtime actually injects the lookup adapter, without exposing human library.file', { timeout: 30_000 }, async t => {
+  const f = scratchRepo(t, TEXTS), dataRoot = join(f.root, 'runtime'); mkdirSync(dataRoot);
+  const business = { id: 'acme', human: 'jason', plugins: { harness: ['pi'] }, projects: { books: mappingEntry() },
+    arbiters: { technical: 'coder', delivery: 'coder' },
+    roles: { coder: { definition: 'coder', authority: { withinRole: [], crossRole: [] } } } };
+  const runtime = await startBroker({ dataRoot, businesses: { acme: business } }); t.after(() => runtime.close());
+  const mirror = library.mirrorPath({ business, project: 'books', dataRoot });
+  git(f.repo, '-c', 'protocol.file.allow=always', 'push', '-q', mirror, 'HEAD:refs/heads/served');
+  writeFileSync(join(mirror, library.SYNC_STATE_FILE), JSON.stringify({ version: 1, branch: 'main', served: f.commit,
+    lastFetch: new Date().toISOString(), lastError: null, diverged: null, problems: [] }), { mode: 0o600 });
+  const cap = runtime.broker.bindLaunch({ business: 'acme', role: 'coder', run: 'r224-runtime', harness: 'pi' });
+  runtime.broker.request(cap, { verb: 'role.claim' });
+  assert.equal((await runtime.broker.request(cap, { verb: 'library.get', args: GET })).commit, f.commit);
+  await assert.rejects(runtime.broker.request(cap, { verb: 'library.file', args: { project: 'books', path: GET.path } }),
+    { code: 'human-required' });
+});
@@ -528,6 +528,7 @@ export function createLauncher({
      contract: readFileSync(resolved.contract, "utf8"),
      arbiter: Object.values(b.arbiters).includes(instance),
      tracker,
+      library: Object.values(b.projects ?? {}).some(project => project.kind === "library"),
      credentials,
      session: { run, launchedBy, workspace: inSandbox, toolSocket, turnMarker, checkouts: inSandbox === workspace ? checkouts : checkouts.map((c) => ({ ...c, path: join(inSandbox, relative(workspace, c.path)) })) },
      harness,
@@ -27,6 +27,7 @@ import { bootConfig, loadSystem } from "../src/config.mjs";
 import { startTimeOf } from "../src/host.mjs";
 import { createLauncher } from "../src/launcher.mjs";
 import { fakeHarnesses, fixture, tmp } from "./helpers.mjs";
+import { mappingEntry } from "../../library/tests/helpers.mjs";
 // Row 264a (#1769): a thread made by hand gets the default session the 3k-3l migration gives a
 // legacy thread, with the thread's id.
 const DEFAULT_SESSION = [
@@ -533,3 +534,29 @@ test('C2-09a: terminating one creative thread does not signal an unselected peer
  await until(() => !readSessions(f.dataRoot).some(row => row.run === runs[0]));
  assert.ok(readSessions(f.dataRoot).some(row => row.run === runs[1]));
 });
+
+// Row224: the launcher must derive library presence from business projects, not
+// from session checkouts (a library never has an agent clone).
+test("C2-05b a real launched bundle gets lookups for a library project without a library checkout", { skip, timeout: 60000 }, async t => {
+  const prepared = prepare(t, { idle: 10, edit: doc => {
+    doc.projects.books = mappingEntry();
+    doc.roles.chief.credentials = { gitea: { ...doc.roles.coder.credentials.gitea } };
+    return doc;
+  } });
+  const { f } = prepared;
+  const host = await start(t, prepared);
+  const project = host.call("project.create", { name: "library work", repo: "stack" }).id;
+  const thread = host.call("thread.create", { project, name: "lookup" }).id;
+  const sent = host.call("thread.send", { thread, body: "inspect bundle" });
+  // broker.mjs:4854 uses async citation hydration for a business with a library.
+  const reply = await until(async () => (await host.call("thread.messages", { thread })).find(m => m.in_reply_to === sent.id && m.class === "RESULT"));
+  assert.equal(reply.from_role, "assistant");
+  assert.equal(reply.to_role, "human");
+  const run = launchLog(f).find(e => e.event === "launch" && e.thread === thread).run;
+  const tools = JSON.parse(readFileSync(join(f.dataRoot, "launches", "acme", run, "bundle", "tools.json"), "utf8"));
+  assert.deepEqual(tools.filter(tool => tool.name.startsWith("library_")).map(tool => tool.name),
+    ["library_find", "library_get", "library_search", "library_manuscript", "library_universe"]);
+  const [session] = threadRuns(f, thread);
+  assert.ok(session);
+  assert.ok(!session.checkouts?.some(checkout => checkout.project === "books"));
+});
@@ -292,6 +292,7 @@ function prompt({ contract, resolved, session, tools, untyped, builtins, persona
 //   resolved     resolveInstance(...) output
 //   contract     the role contract's text
 //   arbiter      true when the business names this instance as an arbiter
+//   library      true when the trusted business configuration has a library project
 //   tracker      true when the broker has task verbs for the business
 //   credentials  the broker's credentialStatus(...) for the instance (metadata only)
 //   session      { run, launchedBy, workspace, toolSocket, turnMarker, checkouts }
@@ -309,11 +310,11 @@ function prompt({ contract, resolved, session, tools, untyped, builtins, persona
 //                (row 213); an instance with persona.sha256 and no personaDir refuses
 // Returns { manifest, files, policy, tools, env } with absolute paths; env is the module's
 // adapter variables, which the host writes into session.json.
-export function buildBundle({ dir, resolved, contract, arbiter = false, tracker = false, credentials = [], session, harness, route = "primary", routeReason = null, harnessVersion = null, models = null, land = false, skillsDir = null, personaDir = null }) {
+export function buildBundle({ dir, resolved, contract, arbiter = false, tracker = false, library = false, credentials = [], session, harness, route = "primary", routeReason = null, harnessVersion = null, models = null, land = false, skillsDir = null, personaDir = null }) {
  if (route !== "primary" && route !== "fallback") throw new BundleError(`route ${JSON.stringify(route)} isn't primary or fallback`);
  const model = sessionModel(resolved, models, route);
  const web = webPlan(resolved, model.harness, harness.builtinWeb());
-  const tools = typedTools({ resolved, arbiter, tracker, projects: (session.checkouts ?? []).map((c) => c.project), webTyped: !web.builtin, land });
+  const tools = typedTools({ resolved, arbiter, tracker, library, projects: (session.checkouts ?? []).map((c) => c.project), webTyped: !web.builtin, land });
  const untyped = untypedActions(resolved, tools);
  const persona = readPersona(resolved, personaDir);
  mkdirSync(dir, { recursive: true, mode: 0o700 });
@@ -78,9 +78,10 @@ const TASK_TOOLS = {

 const MESSAGE_CLASSES = ["REQUEST", "ASSIGNMENT", "REVIEW-REQUEST", "REVIEW-RESULT", "RESULT", "INFO", "DECISION", "REACTION", "BLOCK"];

-// typedTools({ resolved, arbiter, tracker, projects, land }) -> [{ name, verb, action, description, parameters }]
+// typedTools({ resolved, arbiter, tracker, projects, land, library }) -> [{ name, verb, action, description, parameters }]
 //   resolved  resolveInstance(...) output for the session's instance
 //   arbiter   true when the business names this instance as an arbiter
+//   library   true when the trusted business configuration has a library project
 //   tracker   true when the broker has task verbs for the business
 //   projects  the project ids the session has a clone of
 //   land      true when the role and thread hold a merge decision a landing could use (landHeld)
@@ -88,7 +89,7 @@ const MESSAGE_CLASSES = ["REQUEST", "ASSIGNMENT", "REVIEW-REQUEST", "REVIEW-RESU
 // `verb` is the broker verb; the `launch` tool has verb "launch" and goes
 // to the host instead, and "working.push", "working.fetch" and
 // "working.land" go to the host's git socket.
-export function typedTools({ resolved, arbiter = false, tracker = false, projects = [], webTyped = true, land = false }) {
+export function typedTools({ resolved, arbiter = false, tracker = false, projects = [], webTyped = true, land = false, library = false }) {
  const held = new Set([...resolved.limits.authority.withinRole, ...resolved.limits.authority.crossRole]);
  const tools = [];
  const add = (name, verb, action, description, parameters) => tools.push({ name, verb, action, description, parameters });
@@ -222,6 +223,32 @@ export function typedTools({ resolved, arbiter = false, tracker = false, project
      url: str("The https url to fetch", { maxLength: 2048 }),
    }, ["url"]));
  }
+  // Row224: no library clone or token reaches a session. The broker chooses the served
+  // commit and requires a universe on every call; cursors page without cutting replies.
+  if (library) {
+    const universe = str("Universe ID in the configured library", { minLength: 1 });
+    const project = str("Library project ID; omit only when the business has one library");
+    const scope = str("canon by default; playground is opt-in", { enum: ["canon", "playground"] });
+    const book = str("Book folder from library_universe");
+    const offset = { type: "integer", minimum: 0, description: "next from the previous page" };
+    const line = { type: "integer", minimum: 1, description: "One-based line number" };
+    const base = { universe, project };
+    add("library_find", "library.find", null, "Find names in one universe, at the served commit. At most 50 results; continue with next as offset.", obj({
+      ...base, query: str("Case-insensitive name or filename substring; empty matches all"),
+      type: str("Mapped type", { enum: ["character", "place", "research", "tracker", "summary"] }),
+      book, scope, offset,
+    }, ["universe", "query"]));
+    add("library_get", "library.get", null, "Read a mapped note and visible links in one universe at the served commit. next pages lines; links_next pages links. An explicit own-universe playground path is readable.", obj({
+      ...base, path: str("Mapped note path relative to the library"), from: line, links_from: offset,
+    }, ["universe", "path"]));
+    add("library_search", "library.search", null, "Search text in one universe at the served commit. At most 50 hits; use next as offset. Playground is opt-in.", obj({
+      ...base, text: str("Nonempty case-insensitive substring", { minLength: 1 }), book, scope, offset,
+    }, ["universe", "text"]));
+    add("library_manuscript", "library.manuscript", null, "Read one chapter of a book at the served commit, at most 400 lines. Omit chapter for the first; continue with next or next_chapter.", obj({
+      ...base, book, scope, chapter: str("Chapter filename without extension"), from: line, to: line,
+    }, ["universe", "book"]));
+    add("library_universe", "library.universe", null, "Read a universe's mapping at the served commit: books, types, playground prefixes, and hybrid sources/constraints/notes or draft metadata.", obj(base, ["universe"]));
+  }
  add("read_spec", "spec.read", null, "Read a project's committed north-star spec and its file history. commit is an optional full reachable commit ID. The file commit, rather than HEAD, is what a decision cites. confirmed says the file commit was authored by the business's human.", obj({
    project: str("Project ID from the business file"),
    commit: str("Optional full historical commit ID", { pattern: "^[0-9a-f]{40}$" }),
@@ -277,6 +304,11 @@ export function typedTools({ resolved, arbiter = false, tracker = false, project
    if (held.has("task.create"))
      add("list_requirements", "requirements", null, "List the approved PRD's requirement ids, each with a one-line title. task_create takes only these. When none fits a request, raise a prd.approve decision instead of creating the task.", obj({}));
  }
+  // mos-1308 / M3: no generic spec, evidence, tracker, decision or write tools. The
+  // C2-08 web grant still supplies broker web reads to companion and research only.
+  if (CREATIVE_DEFINITIONS.includes(resolved.definition))
+    return tools.filter(tool => tool.name === "send_message" || tool.name.startsWith("library_") ||
+      tool.name === "web_search" || tool.name === "web_fetch");
  return tools;
 }

@@ -0,0 +1,71 @@
+// Row224 M3: exact creative tool sets preserve the existing C2-08 web grants.
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { mkdirSync, readFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { typedTools } from '../src/tools.mjs';
+import { buildBundle } from '../src/bundle.mjs';
+import { TYPES } from '../../library/src/mapping.mjs';
+import { HARNESS, REPO_SKILLS, resolvedFor, scratch } from './helpers.mjs';
+
+const LOOKUPS = ['library_find', 'library_get', 'library_search', 'library_manuscript', 'library_universe'];
+const CREATIVE = ['companion', 'research', 'ideas', 'proofreader', 'fact-checker', 'continuity'];
+const role = (t, definition, harness = 'pi') => resolvedFor(t, 'bean', d => {
+  d.roles.bean = { definition, credentials: { gitea: { ...d.roles.coder.credentials.gitea } }, vars: { harness, model: 'claude-sonnet-5-5', thinking: 'high' } };
+});
+const expected = definition => ['send_message', ...(['companion', 'research'].includes(definition)
+  ? ['web_search', 'web_fetch'] : []), ...LOOKUPS];
+
+test('M3: per-role snapshots contain six names, or eight with the C2-08 web grant', t => {
+  for (const definition of CREATIVE) {
+    const tools = typedTools({ resolved: role(t, definition), library: true, tracker: true, arbiter: true });
+    assert.deepEqual(tools.map(t => t.name), expected(definition), definition);
+    assert.ok(tools.every(t => t.parameters.additionalProperties === false));
+  }
+});
+
+test('every noncreative role gets lookups when a library is configured, not otherwise', t => {
+  for (const instance of ['coder', 'reviewer', 'pm', 'chief']) {
+    const resolved = resolvedFor(t, instance);
+    const ordinary = typedTools({ resolved }).map(t => t.name);
+    assert.ok(!ordinary.some(name => name.startsWith('library_')));
+    const tools = typedTools({ resolved, library: true });
+    assert.deepEqual(tools.filter(t => t.name.startsWith('library_')).map(t => t.name), LOOKUPS);
+    assert.deepEqual(tools.filter(t => !t.name.startsWith('library_')).map(t => t.name), ordinary);
+  }
+});
+
+test('lookup schemas require a universe even for get, include paging, and cannot select repo or commit', t => {
+  const tools = typedTools({ resolved: role(t, 'ideas'), library: true });
+  const required = [ ['universe', 'query'], ['universe', 'path'], ['universe', 'text'], ['universe', 'book'], ['universe'] ];
+  for (const [i, tool] of tools.filter(t => t.name.startsWith('library_')).entries()) {
+    assert.deepEqual(tool.parameters.required, required[i]);
+    assert.equal(tool.verb, LOOKUPS[i].replace('_', '.'));
+    assert.equal(tool.action, null);
+    assert.equal(tool.parameters.additionalProperties, false);
+    for (const key of ['repo', 'commit', 'business', 'accept']) assert.equal(Object.hasOwn(tool.parameters.properties, key), false);
+  }
+  const byName = Object.fromEntries(tools.map(t => [t.name, t]));
+  assert.deepEqual(byName.library_find.parameters.properties.scope.enum, ['canon', 'playground']);
+  assert.deepEqual(byName.library_find.parameters.properties.type.enum, [...TYPES]);
+  assert.equal(byName.library_find.parameters.properties.offset.minimum, 0);
+  assert.equal(byName.library_get.parameters.properties.from.minimum, 1);
+  assert.equal(byName.library_get.parameters.properties.links_from.minimum, 0);
+  assert.equal(byName.library_manuscript.parameters.properties.chapter.type, 'string');
+});
+
+test('bundle flag reaches both harness tool manifests and creative prompt without generic tools', t => {
+  for (const definition of CREATIVE) for (const harness of ['pi', 'claude-code']) {
+    const dir = scratch(t), workspace = join(dir, 'ws'); mkdirSync(workspace);
+    const b = buildBundle({ dir: join(dir, 'bundle'), resolved: role(t, definition, harness), library: true,
+      contract: '# Creative\n', tracker: true, arbiter: true, skillsDir: REPO_SKILLS,
+      session: { run: 'r224', launchedBy: 'chief', workspace, toolSocket: join(dir, 't.sock'), turnMarker: join(dir, 'turn.done') },
+      harness: HARNESS[harness] });
+    assert.deepEqual(b.tools.map(t => t.name), expected(definition), `${definition} ${harness}`);
+    const serialized = JSON.parse(readFileSync(b.files.tools, 'utf8'));
+    assert.deepEqual(serialized.map(t => t.name), expected(definition));
+    const prompt = readFileSync(b.files.prompt, 'utf8');
+    assert.match(prompt, /library_find/);
+    assert.doesNotMatch(prompt, /Bus tools: [^\n]*(read_spec|list_agents|inbox|trail|write_record|raise_decision|list_tasks)/);
+  }
+});
@@ -0,0 +1,80 @@
+# Supervisor
+
+Q198 S1 (row 257, #1762): parsers for the host pressure inputs in design D4
+(`docs/plans/2026-10-21_q198-system-manager.md`), and a pure evaluator that turns timestamped samples
+into a hold or release decision. Nothing here samples the host, runs a process or timer, or enforces
+anything. The live sampler, the Console view and admission are S2 and S3.
+
+```sh
+node --test packages/supervisor/tests/
+```
+
+## Parsers
+
+Each parser takes file text the caller already read. Text that isn't the shape the kernel writes throws
+a `SupervisorError` with `kind: "parse"`; a sampler treats that as a missing signal.
+
+| Export | Input | Returns |
+|---|---|---|
+| `parseLoadavg` | `/proc/loadavg` | `{ load1, load5, load15 }` |
+| `parseMeminfo` | `/proc/meminfo` | `{ memTotal, memAvailable, swapTotal, swapFree }` in bytes |
+| `parsePsi(text, resource)` | `/proc/pressure/{cpu,memory,io}` or a cgroup `*.pressure` | `{ some, full }`, each `{ avg10, avg60, avg300, total }`; `full` is null only for cpu |
+| `parseCpuList` | `/sys/devices/system/cpu/online`, `cpuset.cpus.effective` | how many CPUs the list names |
+| `parseCpuMax` | `cpu.max` | the quota in CPUs, or null for `max` |
+| `parseMemoryMax` | `memory.max` | bytes, or null for `max` |
+| `parseMemoryCurrent` | `memory.current` | bytes |
+| `parseMemoryEvents` | `memory.events` | `{ oom, oomKill }` |
+| `parseVmstat` | `/proc/vmstat` | `{ pswpin, pswpout, oomKill }`; `oomKill` is the host-only OOM counter, null when absent |
+
+`effectiveCpus({ online, cpuset, cpuMax })` is the smallest of the host count, the cpuset and the quota
+at every cgroup level given; a fractional quota stays fractional. `effectiveMemory({ meminfo, levels })`
+takes cgroup levels as `{ max, current }` text. The limit is the smallest of `MemTotal` and every numeric
+`memory.max`. Available memory is the smallest of `MemAvailable` and `max - current` at each limited level.
+`memory.current` counts page cache, so this errs toward holding. With no cgroup input both functions use
+the host's figures.
+
+## Evaluator
+
+`evaluate(state, sample, rules, { reconciled })` returns `{ state, decision }`. It starts from
+`initialState()`, which is held: no signal has been seen yet. Time is the sample's `at` in milliseconds.
+The evaluator never reads the clock.
+
+A sample has these signals: `load { at, load1, cpus }`, `memory { at, available, limit }`,
+`psi { at, cpuSome, memoryFull, ioFull }` (avg10 percentages), `oom { at, kills }` and `disk { at, free }`.
+
+| Signal | Hold | Release |
+|---|---|---|
+| `load1 / cpus` | ≥ 0.80 on 3 consecutive samples | ≤ 0.55 |
+| available memory | < max(15% of limit, 1 GiB), on one sample | > max(25% of limit, 2 GiB) |
+| PSI avg10 | cpu some ≥ 20, memory full ≥ 2 or io full ≥ 10, on 3 consecutive samples | cpu some < 10, memory full < 0.5 and io full < 3 |
+| critical | OOM kill counter rises, memory < 5% of limit, or disk free < 1 GiB | the caller passes `reconciled`, then the normal release |
+
+- **Release** needs every applicable release condition on every sample for 30 s. A dead-band
+  sample (between hold and release) or a new hold restarts the window.
+- **Missing or stale:** a required signal that is missing, malformed, more than 6 s older than the
+  sample, or later than it holds at once with `health-unknown`. `load`, `memory`, `oom` and `disk` are
+  always required. PSI becomes required once a sample has carried it. A host without PSI skips the PSI
+  rows, and one that loses it holds.
+- **Consecutive counts** reset after a gap of more than 6 s between samples. The PSI count runs across
+  resources: any PSI hold condition on 3 consecutive samples holds.
+- **OOM:** the first OOM sample is the baseline. A counter that falls (a recreated cgroup) resets the
+  baseline with the note `oom-counter-reset`.
+- **Critical** never ends on thresholds alone. `reconciled` only counts once no critical condition
+  remains, and the 30 s release still follows. The evaluator never sets it and never touches a kill
+  switch.
+- **A clock that goes backwards** holds with `health-unknown` and the note `clock-backwards`.
+
+`decision` is `{ mode, reasons, unknown, critical, releaseAt, notes }`.
+- `mode` is `open`, `held` or `critical`.
+- `reasons` are `health-unknown`, `load-high`, `memory-low`, `psi-cpu`, `psi-memory`, `psi-io`,
+  `hysteresis`, `release-pending` or the critical codes `critical-oom`, `critical-memory` and
+  `critical-disk`.
+- `releaseAt` is set while a release is pending.
+
+`DEFAULT_RULES` is the D4 table, frozen. `resolveRules(overrides)` merges overrides key by key. It refuses
+with `kind: "rules"` on an unknown key, a non-number or a contradictory pair, for example:
+- a release threshold at or past its hold;
+- a release floor at or below its hold floor;
+- a critical memory fraction at or above the hold fraction;
+- a stale limit at or below the sample interval.
+Provider scope (429, quota, Retry-After) is not here; it belongs to S3 and S5.
@@ -0,0 +1,11 @@
+{
+  "name": "@mosaic/supervisor",
+  "version": "0.1.0",
+  "private": true,
+  "description": "Q198 S1: parsers for host pressure inputs and a pure hold and release rules evaluator. No sampler, process or enforcement.",
+  "license": "UNLICENSED",
+  "type": "module",
+  "engines": { "node": ">=24" },
+  "exports": { ".": "./src/index.mjs" },
+  "scripts": { "test": "node --test tests/" }
+}
@@ -0,0 +1,10 @@
+// Every refusal in this package is a SupervisorError. `kind` is "parse" for
+// input text that isn't the shape the kernel writes, and "rules" for settings
+// the evaluator refuses.
+export class SupervisorError extends Error {
+  constructor(message, kind) {
+    super(message);
+    this.name = "SupervisorError";
+    this.kind = kind;
+  }
+}
@@ -0,0 +1,10 @@
+// @mosaic/supervisor: Q198 S1. Parsers for host pressure inputs and a pure
+// rules evaluator. Nothing here reads a file, the clock or the environment,
+// and nothing enforces: no sampler, process, timer, bus or Console (S2, S3).
+
+export { SupervisorError } from "./errors.mjs";
+export {
+  parseLoadavg, parseMeminfo, parsePsi, parseCpuList, parseCpuMax, parseMemoryMax, parseMemoryCurrent,
+  parseMemoryEvents, parseVmstat, effectiveCpus, effectiveMemory,
+} from "./pressure.mjs";
+export { DEFAULT_RULES, resolveRules, initialState, evaluate } from "./rules.mjs";
@@ -0,0 +1,165 @@
+// Parsers for the host pressure inputs Q198 D4 names, and the effective CPU
+// count and memory limit they give. Every function takes file text the caller
+// already read and returns numbers. Nothing here opens a file. Text that isn't
+// the shape the kernel writes throws a SupervisorError of kind "parse"; the
+// caller turns that into a missing signal.
+
+import { SupervisorError } from "./errors.mjs";
+
+const fail = (what, why) => { throw new SupervisorError(`${what}: ${why}`, "parse"); };
+
+function text(what, value) {
+  if (typeof value !== "string") fail(what, "expected file text");
+  return value.endsWith("\n") ? value.slice(0, -1) : value;
+}
+
+function integer(what, value) {
+  if (!/^\d+$/.test(value)) fail(what, `not a non-negative integer: ${JSON.stringify(value)}`);
+  return Number(value);
+}
+
+function decimal(what, value) {
+  if (!/^\d+(\.\d+)?$/.test(value)) fail(what, `not a non-negative number: ${JSON.stringify(value)}`);
+  return Number(value);
+}
+
+// "key value" lines (memory.events, /proc/vmstat). A repeated key throws.
+function keyedIntegers(what, raw) {
+  const out = new Map();
+  for (const line of text(what, raw).split("\n")) {
+    const m = /^([a-z0-9_]+) (\d+)$/.exec(line);
+    if (!m) fail(what, `bad line ${JSON.stringify(line)}`);
+    if (out.has(m[1])) fail(what, `repeated key ${m[1]}`);
+    out.set(m[1], integer(what, m[2]));
+  }
+  return out;
+}
+
+// /proc/loadavg: "0.52 0.58 0.59 1/1234 56789".
+export function parseLoadavg(raw) {
+  const m = /^(\d+\.\d+) (\d+\.\d+) (\d+\.\d+) (\d+)\/(\d+) (\d+)$/.exec(text("loadavg", raw));
+  if (!m) fail("loadavg", "not the /proc/loadavg shape");
+  return { load1: Number(m[1]), load5: Number(m[2]), load15: Number(m[3]) };
+}
+
+// /proc/meminfo. Values are returned in bytes; lines without a unit (the
+// HugePages counts) are kept as plain counts.
+export function parseMeminfo(raw) {
+  const fields = new Map();
+  for (const line of text("meminfo", raw).split("\n")) {
+    const m = /^([A-Za-z0-9_()]+):\s+(\d+)( kB)?$/.exec(line);
+    if (!m) fail("meminfo", `bad line ${JSON.stringify(line)}`);
+    if (fields.has(m[1])) fail("meminfo", `repeated key ${m[1]}`);
+    fields.set(m[1], integer("meminfo", m[2]) * (m[3] ? 1024 : 1));
+  }
+  for (const key of ["MemTotal", "MemAvailable"]) if (!fields.has(key)) fail("meminfo", `no ${key}`);
+  return {
+    memTotal: fields.get("MemTotal"),
+    memAvailable: fields.get("MemAvailable"),
+    swapTotal: fields.get("SwapTotal") ?? null,
+    swapFree: fields.get("SwapFree") ?? null,
+  };
+}
+
+// /proc/pressure/{cpu,memory,io} or a cgroup's *.pressure file. The cpu file
+// may lack the "full" line on older kernels; memory and io must have it.
+export function parsePsi(raw, resource) {
+  if (!["cpu", "memory", "io"].includes(resource)) fail("psi", `unknown resource ${JSON.stringify(resource)}`);
+  const what = `psi ${resource}`;
+  const out = { some: null, full: null };
+  for (const line of text(what, raw).split("\n")) {
+    const m = /^(some|full) avg10=(\S+) avg60=(\S+) avg300=(\S+) total=(\S+)$/.exec(line);
+    if (!m) fail(what, `bad line ${JSON.stringify(line)}`);
+    if (out[m[1]]) fail(what, `repeated ${m[1]} line`);
+    out[m[1]] = { avg10: decimal(what, m[2]), avg60: decimal(what, m[3]), avg300: decimal(what, m[4]), total: integer(what, m[5]) };
+  }
+  if (!out.some) fail(what, "no some line");
+  if (!out.full && resource !== "cpu") fail(what, "no full line");
+  return out;
+}
+
+// A CPU list such as /sys/devices/system/cpu/online or cpuset.cpus.effective:
+// "0-3,6,8-9". Returns how many distinct CPUs it names.
+export function parseCpuList(raw) {
+  const body = text("cpu list", raw);
+  if (body === "") fail("cpu list", "empty");
+  const cpus = new Set();
+  for (const part of body.split(",")) {
+    const m = /^(\d+)(?:-(\d+))?$/.exec(part);
+    if (!m) fail("cpu list", `bad range ${JSON.stringify(part)}`);
+    const lo = integer("cpu list", m[1]);
+    const hi = m[2] === undefined ? lo : integer("cpu list", m[2]);
+    if (hi < lo) fail("cpu list", `range ${part} runs backwards`);
+    for (let c = lo; c <= hi; c++) cpus.add(c);
+  }
+  return cpus.size;
+}
+
+// cgroup v2 cpu.max: "max 100000" (no quota) or "50000 100000". Returns the
+// CPUs the quota allows, or null for no quota.
+export function parseCpuMax(raw) {
+  const m = /^(max|\d+) (\d+)$/.exec(text("cpu.max", raw));
+  if (!m) fail("cpu.max", "not the cpu.max shape");
+  const period = integer("cpu.max", m[2]);
+  if (period === 0) fail("cpu.max", "period is 0");
+  return m[1] === "max" ? null : integer("cpu.max", m[1]) / period;
+}
+
+// cgroup v2 memory.max: "max" (no limit) or bytes. Returns null for "max".
+export function parseMemoryMax(raw) {
+  const body = text("memory.max", raw);
+  return body === "max" ? null : integer("memory.max", body);
+}
+
+// cgroup v2 memory.current: bytes.
+export function parseMemoryCurrent(raw) {
+  return integer("memory.current", text("memory.current", raw));
+}
+
+// cgroup v2 memory.events. oom_kill is the counter the critical row watches.
+export function parseMemoryEvents(raw) {
+  const fields = keyedIntegers("memory.events", raw);
+  if (!fields.has("oom_kill")) fail("memory.events", "no oom_kill");
+  return { oom: fields.get("oom") ?? null, oomKill: fields.get("oom_kill") };
+}
+
+// /proc/vmstat. Swap activity is reported only (D4 has no threshold for it).
+// oom_kill is the host-only OOM counter; it is null on a kernel without it.
+export function parseVmstat(raw) {
+  const fields = keyedIntegers("vmstat", raw);
+  for (const key of ["pswpin", "pswpout"]) if (!fields.has(key)) fail("vmstat", `no ${key}`);
+  return { pswpin: fields.get("pswpin"), pswpout: fields.get("pswpout"), oomKill: fields.get("oom_kill") ?? null };
+}
+
+// Effective CPUs: the smallest of the host's online CPUs, the cpuset and the
+// quota at every cgroup level given. With no cgroup input it is the host count.
+// A fractional quota stays fractional.
+export function effectiveCpus({ online, cpuset = null, cpuMax = [] }) {
+  let cpus = parseCpuList(online);
+  if (cpuset !== null) cpus = Math.min(cpus, parseCpuList(cpuset));
+  for (const level of cpuMax) {
+    const quota = parseCpuMax(level);
+    if (quota !== null) cpus = Math.min(cpus, quota);
+  }
+  return cpus;
+}
+
+// Effective memory. `levels` lists the cgroup levels that apply, each
+// { max, current } as file text. The limit is the smallest of MemTotal and every
+// numeric memory.max. Available memory is the smallest of MemAvailable and
+// (max - current) at every limited level. memory.current counts page cache,
+// so this errs toward holding. With no levels it is the host's figures.
+export function effectiveMemory({ meminfo, levels = [] }) {
+  const host = parseMeminfo(meminfo);
+  let limit = host.memTotal;
+  let available = host.memAvailable;
+  for (const level of levels) {
+    const max = parseMemoryMax(level.max);
+    if (max === null) continue;
+    if (level.current === undefined || level.current === null) fail("memory.current", "missing for a limited level");
+    const current = parseMemoryCurrent(level.current);
+    limit = Math.min(limit, max);
+    available = Math.min(available, Math.max(0, max - current));
+  }
+  return { limit, available };
+}
@@ -0,0 +1,201 @@
+// The Q198 D4 hold and release rules as a pure evaluator. evaluate() takes the
+// previous state, one timestamped sample and the rules, and returns the next
+// state and a decision. It never reads the clock, a file or the environment:
+// time is the sample's `at`, in milliseconds. Nothing here enforces anything;
+// the decision is advice for S2 and S3.
+
+import { SupervisorError } from "./errors.mjs";
+
+const GiB = 1024 ** 3;
+
+// The D4 table. Defaults are the design's proposals, not measured limits.
+export const DEFAULT_RULES = deepFreeze({
+  sampleMs: 2000,
+  staleMs: 6000,
+  releaseMs: 30000,
+  load: { hold: 0.8, release: 0.55, samples: 3 },
+  memory: { holdFraction: 0.15, holdBytes: 1 * GiB, releaseFraction: 0.25, releaseBytes: 2 * GiB },
+  psi: {
+    samples: 3,
+    hold: { cpuSome: 20, memoryFull: 2, ioFull: 10 },
+    release: { cpuSome: 10, memoryFull: 0.5, ioFull: 3 },
+  },
+  critical: { memoryFraction: 0.05, diskBytes: 1 * GiB },
+});
+
+function deepFreeze(o) {
+  for (const v of Object.values(o)) if (v && typeof v === "object") deepFreeze(v);
+  return Object.freeze(o);
+}
+
+const refuse = (why) => { throw new SupervisorError(`rules: ${why}`, "rules"); };
+
+// Overrides merge onto the defaults key by key. An unknown key, a value of the
+// wrong type or a contradictory pair refuses.
+function merge(base, over, at) {
+  if (over === undefined) return structuredClone(base);
+  if (!over || typeof over !== "object" || Array.isArray(over)) refuse(`${at || "rules"} must be an object`);
+  const out = {};
+  for (const key of Object.keys(over)) if (!Object.hasOwn(base, key)) refuse(`unknown key ${at ? `${at}.` : ""}${key}`);
+  for (const [key, value] of Object.entries(base)) {
+    const name = at ? `${at}.${key}` : key;
+    if (typeof value === "object") out[key] = merge(value, over[key], name);
+    else {
+      const v = over[key] ?? value;
+      if (typeof v !== "number" || !Number.isFinite(v)) refuse(`${name} must be a finite number`);
+      out[key] = v;
+    }
+  }
+  return out;
+}
+
+export function resolveRules(overrides = {}) {
+  const r = merge(DEFAULT_RULES, overrides, "");
+  const check = (ok, why) => { if (!ok) refuse(why); };
+  const fraction = (v) => v > 0 && v < 1;
+  const percent = (v) => v >= 0 && v <= 100;
+  check(r.sampleMs > 0, "sampleMs must be above 0");
+  check(r.staleMs > r.sampleMs, "staleMs must be above sampleMs");
+  check(r.releaseMs >= 0, "releaseMs must not be negative");
+  for (const k of ["load", "psi"]) check(Number.isInteger(r[k].samples) && r[k].samples >= 1, `${k}.samples must be an integer of at least 1`);
+  check(r.load.release > 0 && r.load.release < r.load.hold, "load.release must be above 0 and below load.hold");
+  check(fraction(r.memory.holdFraction) && fraction(r.memory.releaseFraction), "memory fractions must be between 0 and 1");
+  check(r.memory.releaseFraction > r.memory.holdFraction, "memory.releaseFraction must be above memory.holdFraction");
+  check(r.memory.holdBytes >= 0 && r.memory.releaseBytes > r.memory.holdBytes, "memory.releaseBytes must be above memory.holdBytes");
+  for (const k of ["cpuSome", "memoryFull", "ioFull"]) {
+    check(percent(r.psi.hold[k]) && percent(r.psi.release[k]), `psi ${k} values must be percentages`);
+    check(r.psi.release[k] > 0 && r.psi.release[k] < r.psi.hold[k], `psi.release.${k} must be above 0 and below psi.hold.${k}`);
+  }
+  check(fraction(r.critical.memoryFraction) && r.critical.memoryFraction < r.memory.holdFraction,
+    "critical.memoryFraction must be between 0 and memory.holdFraction");
+  check(r.critical.diskBytes > 0, "critical.diskBytes must be above 0");
+  return deepFreeze(r);
+}
+
+// The state before any sample: held, because no signal has been seen yet.
+export function initialState() {
+  return { mode: "held", lastAt: null, loadCount: 0, psiCount: 0, psiSeen: false, oomBaseline: null, releaseSince: null, critical: [] };
+}
+
+const SIGNAL_FIELDS = {
+  load: ["load1", "cpus"],
+  memory: ["available", "limit"],
+  psi: ["cpuSome", "memoryFull", "ioFull"],
+  oom: ["kills"],
+  disk: ["free"],
+};
+
+// A signal is usable when every field is a non-negative finite number, cpus
+// and limit are above 0, and its own timestamp is no later than the sample and
+// no more than staleMs before it.
+function fresh(name, signal, now, rules) {
+  if (!signal || typeof signal !== "object") return false;
+  if (typeof signal.at !== "number" || !Number.isFinite(signal.at)) return false;
+  if (signal.at > now || now - signal.at > rules.staleMs) return false;
+  for (const f of SIGNAL_FIELDS[name]) if (typeof signal[f] !== "number" || !Number.isFinite(signal[f]) || signal[f] < 0) return false;
+  if (name === "load" && signal.cpus <= 0) return false;
+  if (name === "memory" && signal.limit <= 0) return false;
+  return true;
+}
+
+// Sample: { at, load: { at, load1, cpus }, memory: { at, available, limit },
+// psi: { at, cpuSome, memoryFull, ioFull } (avg10 percentages),
+// oom: { at, kills }, disk: { at, free } }. `reconciled` is the caller's word
+// that reconciliation finished; only it lets a critical hold end.
+export function evaluate(state, sample, rules = DEFAULT_RULES, { reconciled = false } = {}) {
+  if (!sample || typeof sample.at !== "number" || !Number.isFinite(sample.at)) {
+    throw new SupervisorError("sample: at must be a finite number of milliseconds", "sample");
+  }
+  const now = sample.at;
+  const next = { ...state, critical: [...state.critical], lastAt: now };
+  const unknown = [];
+  const notes = [];
+  const gap = state.lastAt === null ? Infinity : now - state.lastAt;
+  // A count of consecutive samples survives only a gap of at most staleMs.
+  const contiguous = gap >= 0 && gap <= rules.staleMs;
+  if (gap < 0) { unknown.push("clock"); notes.push("clock-backwards"); }
+
+  let loadHold = false, loadReleases = false;
+  if (fresh("load", sample.load, now, rules)) {
+    const ratio = sample.load.load1 / sample.load.cpus;
+    next.loadCount = ratio >= rules.load.hold ? (contiguous ? state.loadCount : 0) + 1 : 0;
+    loadHold = next.loadCount >= rules.load.samples;
+    loadReleases = ratio <= rules.load.release;
+  } else { unknown.push("load"); next.loadCount = 0; }
+
+  let memoryLow = false, memoryReleases = false, criticalMemory = false;
+  if (fresh("memory", sample.memory, now, rules)) {
+    const { available, limit } = sample.memory;
+    const m = rules.memory;
+    // "Whichever demands more free memory": the larger floor applies.
+    memoryLow = available < Math.max(m.holdFraction * limit, m.holdBytes);
+    memoryReleases = available > Math.max(m.releaseFraction * limit, m.releaseBytes);
+    criticalMemory = available < rules.critical.memoryFraction * limit;
+  } else unknown.push("memory");
+
+  // PSI is required once it has been seen. A host that never had it skips the
+  // PSI rows; one that loses it holds with health-unknown.
+  let psiHold = false, psiReleases = true;
+  const psiOver = [];
+  if (sample.psi !== undefined && sample.psi !== null) next.psiSeen = true;
+  if (fresh("psi", sample.psi, now, rules)) {
+    const p = sample.psi, h = rules.psi.hold, r = rules.psi.release;
+    if (p.cpuSome >= h.cpuSome) psiOver.push("psi-cpu");
+    if (p.memoryFull >= h.memoryFull) psiOver.push("psi-memory");
+    if (p.ioFull >= h.ioFull) psiOver.push("psi-io");
+    next.psiCount = psiOver.length ? (contiguous ? state.psiCount : 0) + 1 : 0;
+    psiHold = next.psiCount >= rules.psi.samples;
+    psiReleases = p.cpuSome < r.cpuSome && p.memoryFull < r.memoryFull && p.ioFull < r.ioFull;
+  } else {
+    next.psiCount = 0;
+    if (next.psiSeen) { unknown.push("psi"); psiReleases = false; }
+  }
+
+  let criticalOom = false;
+  if (fresh("oom", sample.oom, now, rules)) {
+    const kills = sample.oom.kills;
+    if (state.oomBaseline !== null && kills > state.oomBaseline) criticalOom = true;
+    if (state.oomBaseline !== null && kills < state.oomBaseline) notes.push("oom-counter-reset");
+    next.oomBaseline = kills;
+  } else unknown.push("oom");
+
+  let criticalDisk = false;
+  if (fresh("disk", sample.disk, now, rules)) criticalDisk = sample.disk.free < rules.critical.diskBytes;
+  else unknown.push("disk");
+
+  const criticalNow = [];
+  if (criticalOom) criticalNow.push("critical-oom");
+  if (criticalMemory) criticalNow.push("critical-memory");
+  if (criticalDisk) criticalNow.push("critical-disk");
+
+  const decide = (mode, reasons, releaseAt = null) => {
+    next.mode = mode;
+    return { state: next, decision: { mode, reasons, unknown, critical: [...next.critical], releaseAt, notes } };
+  };
+
+  if (criticalNow.length) {
+    for (const c of criticalNow) if (!next.critical.includes(c)) next.critical.push(c);
+    next.releaseSince = null;
+    return decide("critical", [...next.critical]);
+  }
+  // Critical ends only on the caller's reconciliation, never on thresholds alone.
+  if (state.mode === "critical" && !reconciled) {
+    next.releaseSince = null;
+    return decide("critical", [...next.critical]);
+  }
+  const mode = state.mode === "critical" ? "held" : state.mode;
+  next.critical = [];
+
+  const reasons = [];
+  if (unknown.length) reasons.push("health-unknown");
+  if (loadHold) reasons.push("load-high");
+  if (memoryLow) reasons.push("memory-low");
+  if (psiHold) reasons.push(...psiOver);
+  if (reasons.length) { next.releaseSince = null; return decide("held", reasons); }
+  if (mode === "open") { next.releaseSince = null; return decide("open", []); }
+
+  if (!(loadReleases && memoryReleases && psiReleases)) { next.releaseSince = null; return decide("held", ["hysteresis"]); }
+  next.releaseSince = state.releaseSince !== null && contiguous ? state.releaseSince : now;
+  if (now - next.releaseSince >= rules.releaseMs) { next.releaseSince = null; return decide("open", []); }
+  return decide("held", ["release-pending"], next.releaseSince + rules.releaseMs);
+}
@@ -0,0 +1,133 @@
+// Parser and effective-limit tests. Every input is fixture text shaped like
+// the kernel's files; nothing reads /proc, /sys or a cgroup.
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import {
+  SupervisorError, parseLoadavg, parseMeminfo, parsePsi, parseCpuList, parseCpuMax, parseMemoryMax,
+  parseMemoryCurrent, parseMemoryEvents, parseVmstat, effectiveCpus, effectiveMemory,
+} from "../src/index.mjs";
+
+const GiB = 1024 ** 3;
+const isParse = (re) => (e) => e instanceof SupervisorError && e.kind === "parse" && re.test(e.message);
+
+const MEMINFO = [
+  "MemTotal:       32768000 kB",
+  "MemFree:         1024000 kB",
+  "MemAvailable:    8192000 kB",
+  "SwapTotal:       4096000 kB",
+  "SwapFree:        4000000 kB",
+  "HugePages_Total:       0",
+  "Hugepagesize:       2048 kB",
+  "",
+].join("\n");
+
+test("loadavg parses the three loads", () => {
+  assert.deepEqual(parseLoadavg("0.52 1.58 12.00 3/1234 56789\n"), { load1: 0.52, load5: 1.58, load15: 12 });
+});
+
+test("a malformed loadavg throws", () => {
+  for (const bad of ["", "0.52 0.58 0.59\n", "0.52 0.58 0.59 1/2\n", "x 0.58 0.59 1/2 3\n", "0.52 0.58 0.59 1/2 3 4\n", 42]) {
+    assert.throws(() => parseLoadavg(bad), isParse(/loadavg/), JSON.stringify(bad));
+  }
+});
+
+test("meminfo returns bytes and keeps unitless counts", () => {
+  assert.deepEqual(parseMeminfo(MEMINFO), {
+    memTotal: 32768000 * 1024, memAvailable: 8192000 * 1024, swapTotal: 4096000 * 1024, swapFree: 4000000 * 1024,
+  });
+});
+
+test("meminfo without MemAvailable, with a repeated key or a bad line throws", () => {
+  assert.throws(() => parseMeminfo("MemTotal: 1 kB\n"), isParse(/no MemAvailable/));
+  assert.throws(() => parseMeminfo(MEMINFO + "MemTotal: 1 kB\n"), isParse(/repeated key MemTotal/));
+  assert.throws(() => parseMeminfo(MEMINFO + "Broken line\n"), isParse(/bad line/));
+  assert.throws(() => parseMeminfo(MEMINFO.replace("8192000", "-1")), isParse(/bad line/));
+});
+
+test("PSI parses some and full, and cpu may lack full", () => {
+  const mem = "some avg10=1.50 avg60=0.20 avg300=0.00 total=123\nfull avg10=0.75 avg60=0.10 avg300=0.00 total=45\n";
+  assert.deepEqual(parsePsi(mem, "memory"), {
+    some: { avg10: 1.5, avg60: 0.2, avg300: 0, total: 123 },
+    full: { avg10: 0.75, avg60: 0.1, avg300: 0, total: 45 },
+  });
+  assert.equal(parsePsi("some avg10=20.00 avg60=0.00 avg300=0.00 total=9\n", "cpu").full, null);
+});
+
+test("PSI without a full line for memory or io, or with a bad line, throws", () => {
+  const someOnly = "some avg10=0.00 avg60=0.00 avg300=0.00 total=0\n";
+  assert.throws(() => parsePsi(someOnly, "memory"), isParse(/no full line/));
+  assert.throws(() => parsePsi(someOnly, "io"), isParse(/no full line/));
+  assert.throws(() => parsePsi("full avg10=0.00 avg60=0.00 avg300=0.00 total=0\n", "cpu"), isParse(/no some line/));
+  assert.throws(() => parsePsi(someOnly + someOnly, "cpu"), isParse(/repeated some/));
+  assert.throws(() => parsePsi("some avg10=x avg60=0.00 avg300=0.00 total=0\n", "cpu"), isParse(/not a non-negative number/));
+  assert.throws(() => parsePsi(someOnly, "gpu"), isParse(/unknown resource/));
+});
+
+test("CPU lists count distinct CPUs", () => {
+  assert.equal(parseCpuList("0-3,6,8-9\n"), 7);
+  assert.equal(parseCpuList("0\n"), 1);
+  assert.equal(parseCpuList("0-3,2-5"), 6);
+  for (const bad of ["", "\n", "3-1", "0,,1", "a-b", "0-"]) assert.throws(() => parseCpuList(bad), isParse(/cpu list/), bad);
+});
+
+test("cpu.max gives the quota in CPUs, or null for max", () => {
+  assert.equal(parseCpuMax("max 100000\n"), null);
+  assert.equal(parseCpuMax("50000 100000\n"), 0.5);
+  assert.equal(parseCpuMax("200000 100000\n"), 2);
+  for (const bad of ["max", "50000 0", "-1 100000", "max max"]) assert.throws(() => parseCpuMax(bad), isParse(/cpu.max/), bad);
+});
+
+test("memory.max, memory.current and memory.events", () => {
+  assert.equal(parseMemoryMax("max\n"), null);
+  assert.equal(parseMemoryMax("4294967296\n"), 4 * GiB);
+  assert.throws(() => parseMemoryMax("4G\n"), isParse(/memory.max/));
+  assert.equal(parseMemoryCurrent("123456\n"), 123456);
+  assert.throws(() => parseMemoryCurrent(""), isParse(/memory.current/));
+  assert.deepEqual(parseMemoryEvents("low 0\nhigh 4\nmax 2\noom 1\noom_kill 1\noom_group_kill 0\n"), { oom: 1, oomKill: 1 });
+  assert.throws(() => parseMemoryEvents("low 0\noom 1\n"), isParse(/no oom_kill/));
+  assert.throws(() => parseMemoryEvents("oom_kill 1\noom_kill 2\n"), isParse(/repeated key/));
+});
+
+test("vmstat gives swap counters and the host OOM counter", () => {
+  assert.deepEqual(parseVmstat("nr_free_pages 100\npswpin 7\npswpout 9\noom_kill 3\n"), { pswpin: 7, pswpout: 9, oomKill: 3 });
+  assert.deepEqual(parseVmstat("pswpin 0\npswpout 0\n"), { pswpin: 0, pswpout: 0, oomKill: null });
+  assert.throws(() => parseVmstat("pswpin 0\n"), isParse(/no pswpout/));
+});
+
+test("effective CPUs fall back to the host count with no cgroup input", () => {
+  assert.equal(effectiveCpus({ online: "0-15\n" }), 16);
+});
+
+test("effective CPUs take the smallest of host, cpuset and every quota level", () => {
+  assert.equal(effectiveCpus({ online: "0-15\n", cpuset: "0-3\n" }), 4);
+  assert.equal(effectiveCpus({ online: "0-15\n", cpuset: "0-3\n", cpuMax: ["max 100000\n", "150000 100000\n"] }), 1.5);
+  // The outer level is the tighter one.
+  assert.equal(effectiveCpus({ online: "0-15\n", cpuMax: ["800000 100000\n", "200000 100000\n"] }), 2);
+  // A quota above the host count doesn't raise it.
+  assert.equal(effectiveCpus({ online: "0-1\n", cpuMax: ["800000 100000\n"] }), 2);
+  assert.equal(effectiveCpus({ online: "0-15\n", cpuMax: ["max 100000\n"] }), 16);
+});
+
+test("effective memory falls back to the host with no cgroup levels, or only max", () => {
+  const host = { limit: 32768000 * 1024, available: 8192000 * 1024 };
+  assert.deepEqual(effectiveMemory({ meminfo: MEMINFO }), host);
+  assert.deepEqual(effectiveMemory({ meminfo: MEMINFO, levels: [{ max: "max\n" }] }), host);
+});
+
+test("effective memory uses the tightest limited level", () => {
+  // 4 GiB limit with 3 GiB used: 1 GiB available, below the host's MemAvailable.
+  assert.deepEqual(effectiveMemory({ meminfo: MEMINFO, levels: [{ max: `${4 * GiB}\n`, current: `${3 * GiB}\n` }] }),
+    { limit: 4 * GiB, available: 1 * GiB });
+  // Nested: the inner level is loose, the outer one is nearly full.
+  assert.deepEqual(effectiveMemory({ meminfo: MEMINFO, levels: [
+    { max: "max\n" }, { max: `${16 * GiB}\n`, current: `${2 * GiB}\n` }, { max: `${6 * GiB}\n`, current: `${5.5 * GiB}\n` },
+  ] }), { limit: 6 * GiB, available: 0.5 * GiB });
+  // Usage above the limit floors at 0.
+  assert.equal(effectiveMemory({ meminfo: MEMINFO, levels: [{ max: "100\n", current: "200\n" }] }).available, 0);
+  // A limit above MemTotal doesn't raise the limit.
+  assert.equal(effectiveMemory({ meminfo: MEMINFO, levels: [{ max: `${64 * GiB}\n`, current: "0\n" }] }).limit, 32768000 * 1024);
+});
+
+test("a limited level without memory.current throws", () => {
+  assert.throws(() => effectiveMemory({ meminfo: MEMINFO, levels: [{ max: `${4 * GiB}\n` }] }), isParse(/missing for a limited level/));
+});
@@ -0,0 +1,28 @@
+// S1 has no live enforcement: the source must not reach the filesystem, a
+// process, the network or the clock. This reads the package's own source text.
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import fs from "node:fs";
+import path from "node:path";
+
+const SRC = path.join(import.meta.dirname, "..", "src");
+const FORBIDDEN = [
+  /\bfrom\s+["'](node:)?(fs|fs\/promises|child_process|net|http|https|dgram|tls|worker_threads|os)["']/,
+  /\bimport\s*\(/,
+  /\brequire\s*\(/,
+  /\bprocess\./,
+  /\bDate\.now\b/,
+  /\bnew Date\b/,
+  /\bperformance\.now\b/,
+  /\bset(Timeout|Interval|Immediate)\b/,
+];
+
+test("src reads no file, process, network or clock", () => {
+  const files = fs.readdirSync(SRC).filter((f) => f.endsWith(".mjs"));
+  assert.deepEqual(files.sort(), ["errors.mjs", "index.mjs", "pressure.mjs", "rules.mjs"]);
+  for (const f of files) {
+    const body = fs.readFileSync(path.join(SRC, f), "utf8");
+    for (const re of FORBIDDEN) assert.doesNotMatch(body, re, `${f} matches ${re}`);
+    for (const m of body.matchAll(/\bfrom\s+["']([^"']+)["']/g)) assert.match(m[1], /^\.\/[a-z]+\.mjs$/, `${f} imports ${m[1]}`);
+  }
+});
@@ -0,0 +1,339 @@
+// Evaluator tests on a fake clock: each sample's `at` is the time. Synthetic
+// numbers only; nothing samples the host or generates load.
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { SupervisorError, DEFAULT_RULES, resolveRules, initialState, evaluate } from "../src/index.mjs";
+
+const GiB = 1024 ** 3;
+const LIMIT = 32 * GiB;
+const R = DEFAULT_RULES;
+
+// A healthy sample at `at`. `patch` changes fields per signal; null drops one.
+function sample(at, patch = {}) {
+  const base = {
+    load: { load1: 0.1, cpus: 1 },
+    memory: { available: 16 * GiB, limit: LIMIT },
+    psi: { cpuSome: 0, memoryFull: 0, ioFull: 0 },
+    oom: { kills: 0 },
+    disk: { free: 100 * GiB },
+  };
+  const out = { at };
+  for (const [name, fields] of Object.entries(base)) {
+    if (patch[name] === null) continue;
+    out[name] = { at, ...fields, ...patch[name] };
+  }
+  return out;
+}
+
+// Fold samples through evaluate; returns every decision and the last state.
+function run(state, samples, rules = R, opts) {
+  const decisions = [];
+  for (const s of samples) {
+    const r = evaluate(state, s, rules, typeof opts === "function" ? opts(s) : opts);
+    state = r.state;
+    decisions.push(r.decision);
+  }
+  return { state, decisions, last: decisions.at(-1) };
+}
+
+// Samples every 2 s from `from` to `to` inclusive.
+function every2s(from, to, patch) {
+  const out = [];
+  for (let at = from; at <= to; at += 2000) out.push(sample(at, typeof patch === "function" ? patch(at) : patch));
+  return out;
+}
+
+// An open state whose last sample was at 30000.
+function opened() {
+  const { state, last } = run(initialState(), every2s(0, 30000));
+  assert.equal(last.mode, "open");
+  return state;
+}
+
+// A state held by a load hold, last sample at 36000.
+function heldByLoad() {
+  const { state, last } = run(opened(), every2s(32000, 36000, { load: { load1: 0.9 } }));
+  assert.deepEqual(last.reasons, ["load-high"]);
+  return state;
+}
+
+const modes = (r) => r.decisions.map((d) => d.mode);
+
+test("the first state is held, and healthy samples open it after exactly 30 s", () => {
+  assert.equal(initialState().mode, "held");
+  const first = evaluate(initialState(), sample(0));
+  assert.equal(first.decision.mode, "held");
+  assert.deepEqual(first.decision.reasons, ["release-pending"]);
+  assert.equal(first.decision.releaseAt, 30000);
+  const r = run(initialState(), [sample(0), sample(2000), sample(6000), sample(10000), sample(14000), sample(18000),
+    sample(22000), sample(26000), sample(29999), sample(30000)]);
+  assert.deepEqual(r.decisions.at(-2).reasons, ["release-pending"]);
+  assert.equal(r.decisions.at(-2).mode, "held");
+  assert.equal(r.last.mode, "open");
+});
+
+test("load holds at 0.80 for 3 samples and not at 0.7999", () => {
+  const at = run(opened(), every2s(32000, 36000, { load: { load1: 0.8 } }));
+  assert.deepEqual(modes(at), ["open", "open", "held"]);
+  assert.deepEqual(at.last.reasons, ["load-high"]);
+  const below = run(opened(), every2s(32000, 50000, { load: { load1: 0.7999 } }));
+  assert.ok(below.decisions.every((d) => d.mode === "open"));
+});
+
+test("load divides by effective CPUs, fractional ones included", () => {
+  const r = run(opened(), every2s(32000, 36000, { load: { load1: 0.4, cpus: 0.5 } }));
+  assert.equal(r.last.mode, "held");
+  const r2 = run(opened(), every2s(32000, 36000, { load: { load1: 3.1, cpus: 4 } }));
+  assert.equal(r2.last.mode, "open");
+});
+
+test("a gap of more than 6 s resets the consecutive count", () => {
+  const high = { load: { load1: 0.9 } };
+  const r = run(opened(), [sample(32000, high), sample(34000, high), sample(40001, high), sample(42001, high), sample(44001, high)]);
+  assert.deepEqual(modes(r), ["open", "open", "open", "open", "held"]);
+  const ok = run(opened(), [sample(32000, high), sample(34000, high), sample(40000, high)]);
+  assert.equal(ok.last.mode, "held");
+});
+
+test("load releases at 0.55 and not at 0.5501", () => {
+  const dead = run(heldByLoad(), every2s(38000, 80000, { load: { load1: 0.5501 } }));
+  assert.ok(dead.decisions.every((d) => d.mode === "held" && d.reasons[0] === "hysteresis"));
+  const r = run(heldByLoad(), every2s(38000, 68000, { load: { load1: 0.55 } }));
+  assert.equal(r.decisions.at(-2).mode, "held");
+  assert.equal(r.last.mode, "open");
+});
+
+test("a dead-band sample restarts the 30 s release window", () => {
+  const r = run(heldByLoad(), [
+    ...every2s(38000, 60000),
+    sample(62000, { load: { load1: 0.6 } }),
+    ...every2s(64000, 92000),
+    sample(94000),
+  ]);
+  const at = (t) => r.decisions[r.decisions.length - 1 - (94000 - t) / 2000];
+  assert.equal(at(62000).reasons[0], "hysteresis");
+  assert.equal(at(92000).mode, "held");
+  assert.equal(at(94000).mode, "open");
+});
+
+test("memory holds below the larger floor, on one sample", () => {
+  const floor = Math.max(R.memory.holdFraction * LIMIT, R.memory.holdBytes);
+  assert.ok(floor > R.memory.holdBytes); // 15% of 32 GiB is the larger floor here
+  const just = Math.ceil(floor);
+  assert.equal(evaluate(opened(), sample(32000, { memory: { available: just } })).decision.mode, "open");
+  const low = evaluate(opened(), sample(32000, { memory: { available: just - 1 } })).decision;
+  assert.equal(low.mode, "held");
+  assert.deepEqual(low.reasons, ["memory-low"]);
+});
+
+test("on a small limit the 1 GiB floor is the larger one", () => {
+  const small = 4 * GiB; // 15% is 0.6 GiB, so 1 GiB applies
+  const s = (available) => sample(32000, { memory: { available, limit: small } });
+  assert.equal(evaluate(opened(), s(1 * GiB)).decision.mode, "open");
+  assert.deepEqual(evaluate(opened(), s(1 * GiB - 1)).decision.reasons, ["memory-low"]);
+});
+
+test("memory releases only above the larger release floor", () => {
+  // 3 GiB is below the 15% floor (4.8 GiB) and above the 5% critical line (1.6 GiB).
+  const held = evaluate(opened(), sample(32000, { memory: { available: 3 * GiB } })).state;
+  assert.equal(held.mode, "held");
+  const rel = Math.max(R.memory.releaseFraction * LIMIT, R.memory.releaseBytes);
+  const stay = run(held, every2s(34000, 80000, { memory: { available: Math.floor(rel) } }));
+  assert.ok(stay.decisions.every((d) => d.mode === "held"));
+  const go = run(held, every2s(34000, 64000, { memory: { available: Math.floor(rel) + 1 } }));
+  assert.equal(go.last.mode, "open");
+  const small = { limit: 4 * GiB }; // 25% is 1 GiB, so 2 GiB applies
+  const stay2 = run(held, every2s(34000, 80000, { memory: { ...small, available: 2 * GiB } }));
+  assert.ok(stay2.decisions.every((d) => d.mode === "held"));
+  const go2 = run(held, every2s(34000, 64000, { memory: { ...small, available: 2 * GiB + 1 } }));
+  assert.equal(go2.last.mode, "open");
+});
+
+test("each PSI hold threshold holds at its value for 3 samples and not just below", () => {
+  for (const [field, code] of [["cpuSome", "psi-cpu"], ["memoryFull", "psi-memory"], ["ioFull", "psi-io"]]) {
+    const at = run(opened(), every2s(32000, 36000, { psi: { [field]: R.psi.hold[field] } }));
+    assert.deepEqual(modes(at), ["open", "open", "held"], field);
+    assert.deepEqual(at.last.reasons, [code], field);
+    const below = run(opened(), every2s(32000, 50000, { psi: { [field]: R.psi.hold[field] - 0.01 } }));
+    assert.ok(below.decisions.every((d) => d.mode === "open"), field);
+  }
+});
+
+test("the PSI count runs across resources", () => {
+  const r = run(opened(), [sample(32000, { psi: { cpuSome: 25 } }), sample(34000, { psi: { memoryFull: 3 } }), sample(36000, { psi: { ioFull: 12 } })]);
+  assert.deepEqual(modes(r), ["open", "open", "held"]);
+  assert.deepEqual(r.last.reasons, ["psi-io"]);
+});
+
+test("each PSI release threshold blocks at its value and releases just below", () => {
+  const held = run(opened(), every2s(32000, 36000, { psi: { cpuSome: 30 } })).state;
+  for (const field of ["cpuSome", "memoryFull", "ioFull"]) {
+    const stay = run(held, every2s(38000, 80000, { psi: { [field]: R.psi.release[field] } }));
+    assert.ok(stay.decisions.every((d) => d.mode === "held" && d.reasons[0] === "hysteresis"), field);
+    const go = run(held, every2s(38000, 68000, { psi: { [field]: R.psi.release[field] - 0.01 } }));
+    assert.equal(go.last.mode, "open", field);
+  }
+});
+
+test("a missing required signal holds at once with health-unknown", () => {
+  for (const name of ["load", "memory", "oom", "disk"]) {
+    const d = evaluate(opened(), sample(32000, { [name]: null })).decision;
+    assert.equal(d.mode, "held", name);
+    assert.deepEqual(d.reasons, ["health-unknown"], name);
+    assert.deepEqual(d.unknown, [name], name);
+  }
+});
+
+test("a signal is stale at more than 6 s old and fresh at exactly 6 s", () => {
+  const stale = { at: 32000, load1: 0.1, cpus: 1 };
+  const s = (signalAt) => ({ ...sample(32000), load: { ...stale, at: signalAt } });
+  assert.equal(evaluate(opened(), s(26000)).decision.mode, "open");
+  assert.deepEqual(evaluate(opened(), s(25999)).decision.unknown, ["load"]);
+  assert.deepEqual(evaluate(opened(), s(32001)).decision.unknown, ["load"]); // later than the sample
+});
+
+test("malformed signal values count as missing", () => {
+  for (const patch of [{ load: { load1: NaN } }, { load: { cpus: 0 } }, { load: { load1: -1 } }, { memory: { limit: 0 } },
+    { memory: { available: "1" } }, { oom: { kills: Infinity } }, { disk: { free: undefined } }]) {
+    const d = evaluate(opened(), sample(32000, patch)).decision;
+    assert.deepEqual(d.reasons, ["health-unknown"], JSON.stringify(patch));
+  }
+});
+
+test("after health-unknown, recovery waits the full 30 s", () => {
+  const unknown = evaluate(opened(), sample(32000, { load: null })).state;
+  const r = run(unknown, every2s(34000, 64000));
+  assert.equal(r.decisions.at(-2).mode, "held");
+  assert.equal(r.last.mode, "open");
+});
+
+test("a host that never had PSI skips the PSI rows", () => {
+  const r = run(initialState(), every2s(0, 30000, { psi: null }));
+  assert.equal(r.last.mode, "open");
+  assert.deepEqual(r.last.unknown, []);
+});
+
+test("PSI that disappears after it was present holds with health-unknown", () => {
+  const d = evaluate(opened(), sample(32000, { psi: null })).decision;
+  assert.equal(d.mode, "held");
+  assert.deepEqual(d.reasons, ["health-unknown"]);
+  assert.deepEqual(d.unknown, ["psi"]);
+  // Also when it first appears late, then goes.
+  const late = run(initialState(), [...every2s(0, 30000, { psi: null }), sample(32000), sample(34000, { psi: null })]);
+  assert.deepEqual(late.last.unknown, ["psi"]);
+  // A stale PSI signal counts the same.
+  const stalePsi = { ...sample(32000), psi: { at: 25000, cpuSome: 0, memoryFull: 0, ioFull: 0 } };
+  assert.deepEqual(evaluate(opened(), stalePsi).decision.unknown, ["psi"]);
+});
+
+test("a rise in the OOM kill counter is critical; the first sample is the baseline", () => {
+  const first = evaluate(initialState(), sample(0, { oom: { kills: 5 } }));
+  assert.notEqual(first.decision.mode, "critical");
+  const r = run(opened(), [sample(32000, { oom: { kills: 0 } }), sample(34000, { oom: { kills: 1 } })]);
+  assert.equal(r.last.mode, "critical");
+  assert.deepEqual(r.last.reasons, ["critical-oom"]);
+});
+
+test("a falling OOM counter resets the baseline with a note, not an event", () => {
+  const s = run(initialState(), every2s(0, 30000, { oom: { kills: 6 } })).state;
+  assert.equal(s.mode, "open");
+  const r = run(s, [sample(32000, { oom: { kills: 2 } }), sample(34000, { oom: { kills: 2 } })]);
+  assert.deepEqual(r.decisions[0].notes, ["oom-counter-reset"]);
+  assert.ok(r.decisions.every((d) => d.mode === "open"));
+});
+
+test("memory under 5% and disk under 1 GiB are critical, at their edges", () => {
+  const five = R.critical.memoryFraction * LIMIT;
+  assert.equal(evaluate(opened(), sample(32000, { memory: { available: Math.ceil(five) } })).decision.mode, "held");
+  const mem = evaluate(opened(), sample(32000, { memory: { available: Math.ceil(five) - 1 } })).decision;
+  assert.equal(mem.mode, "critical");
+  assert.deepEqual(mem.reasons, ["critical-memory"]);
+  // On 20 GiB the 5% line is exactly 1 GiB, so the edge itself is tested.
+  const s20 = (available) => sample(32000, { memory: { available, limit: 20 * GiB } });
+  assert.equal(evaluate(opened(), s20(1 * GiB)).decision.mode, "held");
+  assert.deepEqual(evaluate(opened(), s20(1 * GiB - 1)).decision.reasons, ["critical-memory"]);
+  assert.equal(evaluate(opened(), sample(32000, { disk: { free: 1 * GiB } })).decision.mode, "open");
+  assert.deepEqual(evaluate(opened(), sample(32000, { disk: { free: 1 * GiB - 1 } })).decision.reasons, ["critical-disk"]);
+});
+
+test("critical stays until reconciliation, then still waits the 30 s release", () => {
+  const crit = evaluate(opened(), sample(32000, { disk: { free: 0 } })).state;
+  const waiting = run(crit, every2s(34000, 120000));
+  assert.ok(waiting.decisions.every((d) => d.mode === "critical" && d.reasons[0] === "critical-disk"));
+  // Reconciled while the condition is still there: still critical.
+  assert.equal(evaluate(crit, sample(34000, { disk: { free: 0 } }), R, { reconciled: true }).decision.mode, "critical");
+  // Reconciled and healthy: held, then open 30 s later.
+  const after = run(waiting.state, every2s(122000, 152000), R, (s) => ({ reconciled: s.at === 122000 }));
+  assert.deepEqual(after.decisions[0].reasons, ["release-pending"]);
+  assert.deepEqual(after.decisions[0].critical, []);
+  assert.equal(after.decisions.at(-2).mode, "held");
+  assert.equal(after.last.mode, "open");
+});
+
+test("critical reasons accumulate while critical", () => {
+  const r = run(opened(), [sample(32000, { disk: { free: 0 } }), sample(34000, { oom: { kills: 3 } })]);
+  assert.deepEqual(r.last.reasons, ["critical-disk", "critical-oom"]);
+});
+
+test("a clock that goes backwards holds with health-unknown", () => {
+  const d = evaluate(opened(), sample(20000)).decision;
+  assert.equal(d.mode, "held");
+  assert.deepEqual(d.unknown, ["clock"]);
+  assert.deepEqual(d.notes, ["clock-backwards"]);
+});
+
+test("a sample without a numeric time throws", () => {
+  for (const bad of [null, {}, { at: "1" }, { at: NaN }]) {
+    assert.throws(() => evaluate(initialState(), bad), (e) => e instanceof SupervisorError && e.kind === "sample");
+  }
+});
+
+test("evaluate doesn't change the state it was given", () => {
+  const s = Object.freeze({ ...opened(), critical: Object.freeze([]) });
+  assert.doesNotThrow(() => evaluate(s, sample(32000, { disk: { free: 0 } })));
+  assert.equal(s.mode, "open");
+});
+
+test("resolveRules with no overrides is the D4 table, frozen", () => {
+  assert.deepEqual(resolveRules(), DEFAULT_RULES);
+  assert.ok(Object.isFrozen(DEFAULT_RULES) && Object.isFrozen(DEFAULT_RULES.psi.hold));
+  assert.deepEqual(DEFAULT_RULES.load, { hold: 0.8, release: 0.55, samples: 3 });
+  assert.equal(DEFAULT_RULES.releaseMs, 30000);
+  assert.equal(DEFAULT_RULES.staleMs, 6000);
+});
+
+test("overrides apply in the evaluator", () => {
+  const rules = resolveRules({ releaseMs: 10000, load: { samples: 1 } });
+  const r = run(initialState(), every2s(0, 10000), rules);
+  assert.equal(r.last.mode, "open");
+  assert.equal(evaluate(r.state, sample(12000, { load: { load1: 0.9 } }), rules).decision.mode, "held");
+});
+
+test("contradictory or unknown settings refuse", () => {
+  const cases = [
+    [{ load: { release: 0.8 } }, /load.release must be above 0 and below load.hold/],
+    [{ load: { hold: 0.5 } }, /load.release must be above 0 and below load.hold/],
+    [{ memory: { releaseFraction: 0.15 } }, /releaseFraction must be above/],
+    [{ memory: { releaseBytes: 1 * GiB } }, /releaseBytes must be above/],
+    [{ memory: { holdFraction: 1.2 } }, /between 0 and 1/],
+    [{ psi: { release: { ioFull: 10 } } }, /psi.release.ioFull must be above 0 and below psi.hold.ioFull/],
+    [{ psi: { hold: { cpuSome: 120 } } }, /percentages/],
+    [{ psi: { samples: 0 } }, /psi.samples must be an integer/],
+    [{ load: { samples: 1.5 } }, /load.samples must be an integer/],
+    [{ staleMs: 2000 }, /staleMs must be above sampleMs/],
+    [{ releaseMs: -1 }, /releaseMs must not be negative/],
+    [{ critical: { memoryFraction: 0.15 } }, /critical.memoryFraction/],
+    [{ critical: { diskBytes: 0 } }, /critical.diskBytes/],
+    [{ loadd: {} }, /unknown key loadd/],
+    [{ psi: { hold: { gpu: 1 } } }, /unknown key psi.hold.gpu/],
+    [{ load: { toString: 1 } }, /unknown key load.toString/],
+    [{ constructor: {} }, /unknown key constructor/],
+    [JSON.parse('{"memory":{"__proto__":{}}}'), /unknown key memory.__proto__/],
+    [{ load: { hold: "0.8" } }, /load.hold must be a finite number/],
+    [{ load: 1 }, /load must be an object/],
+    [[], /rules must be an object/],
+  ];
+  for (const [over, re] of cases) {
+    assert.throws(() => resolveRules(over), (e) => e instanceof SupervisorError && e.kind === "rules" && re.test(e.message), JSON.stringify(over));
+  }
+});
Author	SHA1	Message	Date
jason.woltje	f268f4de49	row224: record whole-suite passes and killed retry mutant	2026-10-24 13:43:47 -05:00
jason.woltje	e4c0c8931e	row224: supply required reference in creative tool fixture	2026-10-24 13:41:58 -05:00
jason.woltje	63827cc0bd	row224: record CLI and bus passes and harness fixture red	2026-10-24 13:40:57 -05:00
jason.woltje	8f1b045f40	row224: await citation hydration in new launch test	2026-10-24 13:39:55 -05:00
jason.woltje	b98b9e64a0	row224: record new CLI test failure and held sequence	2026-10-24 13:37:44 -05:00
jason.woltje	6160b49810	row224: supply chief Gitea reference in new launch fixture	2026-10-24 13:31:19 -05:00
jason.woltje	5c5886d2d8	row224: record local install and single CLI run failure	2026-10-24 13:21:02 -05:00
jason.woltje	ed985c0442	row224: trim whitespace in plain-text failure receipt	2026-10-24 13:15:54 -05:00
jason.woltje	532938beeb	row224: fix new fixture setup and record old-test stop	2026-10-24 13:15:45 -05:00
jason.woltje	a1a7357457	row224: record row266 rebase and whole-file gate list (unrun)	2026-10-24 13:02:16 -05:00
jason.woltje	c509dcb6ee	row224: record static rebase and pending gate (unrun)	2026-10-24 13:02:00 -05:00
jason.woltje	82d6cc62c6	row224: pace failed inline sync attempts (unrun)	2026-10-24 13:02:00 -05:00
jason.woltje	212aef6161	row224: draft broker library lookups and typed tools (unrun)	2026-10-24 13:02:00 -05:00
jason.woltje	3e5041b43b	Row 266: record owner review move and missing request credential	2026-10-24 12:11:42 -05:00
jason.woltje	b5fb6280df	Row 266: record full gate and sixteen isolated mutant kills	2026-10-24 12:11:42 -05:00
jason.woltje	e1092e673e	Row 266: assert allowed room plugin dispatch does not reject	2026-10-24 12:11:42 -05:00
jason.woltje	abc11152a0	Row 266: add Console room timeline and member completion	2026-10-24 12:11:42 -05:00
jason.woltje	73692e1bb6	morgana: row 257 slot result on `1261fa2d8` (sage-4159): three files whole 15/29/1 pass, supervisor suite 45/45, mutants M1-M8 all killed by assertion, tree restored; BUILD.md and evidence only	2026-10-24 12:02:34 -05:00
jason.woltje	fc5f282902	morgana: row 257 r2 (filbert r1 N1, N2): Object.hasOwn unknown-key refusal with inherited-name cases; critical memory edge on a 20 GiB limit (M8)	2026-10-24 12:02:34 -05:00
jason.woltje	045dd758a3	morgana: row 257 BUILD.md records sage-2202 rulings (PSI latch on first seen, PSI count across resources)	2026-10-24 12:02:34 -05:00
jason.woltje	2d7ebe012d	morgana: row 257 build (Q198 S1, #1762 ): @mosaic/supervisor pressure parsers and pure D4 rules evaluator, tests and mutant plan; tests wait for Sage's slot	2026-10-24 12:02:34 -05:00