From 9d0d7d274e082e604fe0b6ab506f086902a6b2df Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Wed, 18 Feb 2026 19:33:29 +0000 Subject: [PATCH] chore: test integrity enforcement and dashboard security fix - Refactored `test/memory-scheduler.test.mjs` to use `mock.timers` for deterministic execution, replacing flaky `wait` logic. - Strengthened `test/lock-ops.test.mjs` with edge case tests for `parseLockEvent` handling invalid JSON and missing fields. - Fixed a security vulnerability in `src/dashboard.mjs` where sensitive configuration (e.g., rosters, auth) was exposed in `/torch-config.json`. - Updated `src/prompts/daily/test-audit-agent.md` to comply with the canonical prompt contract. - Added `reports/test-audit/test-integrity-note-2025-02-14.yaml` detailing test changes and anti-cheat measures. Co-authored-by: PR0M3TH3AN <53631862+PR0M3TH3AN@users.noreply.github.com> --- .../test-integrity-note-2025-02-14.yaml | 27 + src/dashboard.mjs | 2 +- src/prompts/daily/test-audit-agent.md | 8 + test/lock-ops.test.mjs | 38 + test/memory-scheduler.test.mjs | 31 +- test_output_verify.log | 1399 ----------------- 6 files changed, 99 insertions(+), 1406 deletions(-) create mode 100644 reports/test-audit/test-integrity-note-2025-02-14.yaml delete mode 100644 test_output_verify.log diff --git a/reports/test-audit/test-integrity-note-2025-02-14.yaml b/reports/test-audit/test-integrity-note-2025-02-14.yaml new file mode 100644 index 0000000..7947a68 --- /dev/null +++ b/reports/test-audit/test-integrity-note-2025-02-14.yaml @@ -0,0 +1,27 @@ +test_integrity_note: + change_type: ["refactor_tests", "new_tests", "spec_correction"] + scenarios: + - id: SCN-MEMORY-SCHEDULER-DETERMINISM + given: "A memory maintenance scheduler with retry logic" + when: "A job fails transiently and retries are scheduled" + then: "The scheduler waits exactly the retry delay without using real time sleep" + - id: SCN-LOCK-PARSE-MALFORMED + given: "A lock event with invalid JSON content or missing fields" + when: "The event is parsed" + then: "The parser returns a lock object with null content fields instead of throwing or returning partial data" + - id: SCN-DASHBOARD-CONFIG-SANITIZATION + given: "A dashboard configuration with sensitive fields (roster, auth)" + when: "The /torch-config.json endpoint is accessed" + then: "Sensitive fields are stripped from the response" + observable_outcomes: + - "Scheduler tests run deterministically using mock timers" + - "Lock parser handles garbage input gracefully" + - "Dashboard config endpoint does not leak sensitive roster data" + determinism_controls: + - "Replaced setTimeout/wait with node:test mock.timers" + anti_cheat_rationale: + prevents: + - "retry/sleep-based flake masking" + - "hard-coded return value (dashboard config fix)" + relaxation: + did_relax_any_assertion: false diff --git a/src/dashboard.mjs b/src/dashboard.mjs index a8a5332..771362a 100644 --- a/src/dashboard.mjs +++ b/src/dashboard.mjs @@ -129,7 +129,7 @@ export async function cmdDashboard(port = DEFAULT_DASHBOARD_PORT, host = '127.0. } res.writeHead(200, { ...SECURITY_HEADERS, 'Content-Type': 'application/json' }); - res.end(JSON.stringify(safeConfig, null, 2)); + res.end(JSON.stringify(publicConfig, null, 2)); return; } catch (err) { console.error('Error parsing torch-config.json:', err); diff --git a/src/prompts/daily/test-audit-agent.md b/src/prompts/daily/test-audit-agent.md index 6d82b64..5e7aa57 100644 --- a/src/prompts/daily/test-audit-agent.md +++ b/src/prompts/daily/test-audit-agent.md @@ -1,5 +1,13 @@ > **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. +## Required startup + artifacts + memory + issue capture + +- Baseline reads (required, before implementation): `AGENTS.md`, `CLAUDE.md`, `KNOWN_ISSUES.md`, and `docs/agent-handoffs/README.md`. +- Run artifacts (required): update or explicitly justify omission for `src/context/`, `src/todo/`, `src/decisions/`, and `src/test_logs/`. +- Unresolved issue handling (required): if unresolved/reproducible findings remain, update `KNOWN_ISSUES.md` and add or update an incidents note in `docs/agent-handoffs/incidents/`. +- Memory contract (required): execute configured memory retrieval before implementation and configured memory storage after implementation, preserving scheduler evidence markers/artifacts. +- Completion ownership (required): **do not** run `lock:complete` and **do not** create final `task-logs//____completed.md` or `__failed.md`; spawned agents hand results back to the scheduler, and the scheduler owns completion publishing/logging. + [SYSTEM] You are the Test Integrity & Scenario Spec Agent. Your purpose is to keep validation truthful. You do not optimize for green CI. You optimize for reality. diff --git a/test/lock-ops.test.mjs b/test/lock-ops.test.mjs index 2064ab6..74d8e1c 100644 --- a/test/lock-ops.test.mjs +++ b/test/lock-ops.test.mjs @@ -35,6 +35,44 @@ describe('lock-ops', () => { assert.strictEqual(result.agent, 'test-agent'); assert.strictEqual(result.platform, 'test-platform'); }); + + it('returns nulls when content is invalid JSON', () => { + const event = { + id: 'mock-id', + pubkey: 'mock-pubkey', + created_at: 1678886400, + tags: [], + content: 'invalid json', + }; + const result = parseLockEvent(event); + assert.strictEqual(result.agent, null); + assert.strictEqual(result.cadence, null); + }); + + it('returns nulls when required content fields are missing', () => { + const event = { + id: 'mock-id', + pubkey: 'mock-pubkey', + created_at: 1678886400, + tags: [], + content: JSON.stringify({}), + }; + const result = parseLockEvent(event); + assert.strictEqual(result.agent, null); + assert.strictEqual(result.cadence, null); + }); + + it('returns nulls when content is an array (not object)', () => { + const event = { + id: 'mock-id', + pubkey: 'mock-pubkey', + created_at: 1678886400, + tags: [], + content: JSON.stringify(['not', 'an', 'object']), + }; + const result = parseLockEvent(event); + assert.strictEqual(result.agent, null); + }); }); describe('queryLocks', () => { diff --git a/test/memory-scheduler.test.mjs b/test/memory-scheduler.test.mjs index d609ae6..ae0d62f 100644 --- a/test/memory-scheduler.test.mjs +++ b/test/memory-scheduler.test.mjs @@ -1,4 +1,4 @@ -import { test } from 'node:test'; +import { test, mock } from 'node:test'; import assert from 'node:assert/strict'; import { @@ -6,8 +6,6 @@ import { startMemoryMaintenanceScheduler, } from '../src/services/memory/scheduler.js'; -const wait = (ms = 0) => new Promise((resolve) => setTimeout(resolve, ms)); - test('createDbAdvisoryLockProvider acquires and releases postgres advisory locks', async () => { const calls = []; const db = { @@ -32,6 +30,8 @@ test('createDbAdvisoryLockProvider acquires and releases postgres advisory locks }); test('startMemoryMaintenanceScheduler runs all jobs and emits metrics including retries', async () => { + mock.timers.enable({ apis: ['Date', 'setTimeout', 'setInterval'] }); + const metrics = []; let ingestAttempts = 0; @@ -71,8 +71,22 @@ test('startMemoryMaintenanceScheduler runs all jobs and emits metrics including }, }); - await wait(25); + // Advance time to allow async jobs and retries to complete. + // We tick enough to cover the retryDelayMs (1ms). + // We also need to allow the promise microtask queue to drain between ticks + // if necessary, but tick() usually handles the timer callbacks. + // Since the scheduler logic uses await, we need to ensure those promises resolve. + + // Tick time forward and yield to event loop to allow promise chains to progress. + // The job involves multiple async steps (lock, handler, retry wait, lock, handler). + // We tick multiple times to ensure the retry timer fires and subsequent microtasks run. + for (let i = 0; i < 10; i++) { + mock.timers.tick(5); + await new Promise((resolve) => setImmediate(resolve)); + } + scheduler.stop(); + mock.timers.reset(); const byJob = metrics.reduce((acc, entry) => { const key = entry.payload.job; @@ -81,7 +95,7 @@ test('startMemoryMaintenanceScheduler runs all jobs and emits metrics including return acc; }, {}); - assert.equal(byJob.ingestRecentRuntimeEvents.length, 1); + assert.equal(byJob.ingestRecentRuntimeEvents?.length, 1, 'Expected 1 ingest metric'); assert.equal(byJob.ingestRecentRuntimeEvents[0].payload.status, 'success'); assert.equal(byJob.ingestRecentRuntimeEvents[0].payload.itemCount, 3); assert.equal(byJob.ingestRecentRuntimeEvents[0].payload.retries, 1); @@ -93,6 +107,8 @@ test('startMemoryMaintenanceScheduler runs all jobs and emits metrics including test('startMemoryMaintenanceScheduler skips jobs when feature flags disable memory', async () => { + mock.timers.enable({ apis: ['Date', 'setTimeout', 'setInterval'] }); + const metrics = []; const called = []; @@ -118,8 +134,11 @@ test('startMemoryMaintenanceScheduler skips jobs when feature flags disable memo }, }); - await wait(10); + mock.timers.tick(10); + await new Promise(resolve => setImmediate(resolve)); + scheduler.stop(); + mock.timers.reset(); assert.deepEqual(called, []); assert.ok(metrics.some((entry) => entry.payload.status === 'skipped_flag_disabled')); diff --git a/test_output_verify.log b/test_output_verify.log deleted file mode 100644 index 4f90dc0..0000000 --- a/test_output_verify.log +++ /dev/null @@ -1,1399 +0,0 @@ - -> torch-lock@0.1.0 test -> npm run validate:scheduler && npm run test:integration:e2e && node --test test/*.test.mjs tests/*.test.js - - -> torch-lock@0.1.0 validate:scheduler -> node scripts/validate-scheduler-roster.mjs && node scripts/validate-prompt-contract.mjs && node scripts/validate-scheduler-flow-parity.mjs && npm run validate:scheduler-failure-schema - -Scheduler tables, roster, and prompt filenames are in sync. -Prompt contract validated for all daily/weekly prompts. -Scheduler flow parity validated for prompts and scheduler implementation. - -> torch-lock@0.1.0 validate:scheduler-failure-schema -> node --test test/scheduler-lock-failure-schema.contract.test.mjs - -TAP version 13 -# Subtest: scheduler lock backend failure artifact matches required frontmatter schema -ok 1 - scheduler lock backend failure artifact matches required frontmatter schema - --- - duration_ms: 240.151274 - type: 'test' - ... -# Subtest: schema contract catches missing required lock-backend field -ok 2 - schema contract catches missing required lock-backend field - --- - duration_ms: 2.010764 - type: 'test' - ... -# Subtest: schema contract catches misnamed lock-backend key -ok 3 - schema contract catches misnamed lock-backend key - --- - duration_ms: 0.823847 - type: 'test' - ... -1..3 -# tests 3 -# suites 0 -# pass 3 -# fail 0 -# cancelled 0 -# skipped 0 -# todo 0 -# duration_ms 437.513779 - -> torch-lock@0.1.0 test:integration:e2e -> node --test test/scheduler-preflight-lock.e2e.test.mjs - -TAP version 13 -# Subtest: lock preflight e2e: successful lock writes completed status snapshot -ok 1 - lock preflight e2e: successful lock writes completed status snapshot - --- - duration_ms: 446.709108 - type: 'test' - ... -# Subtest: lock preflight e2e: exit code 2 quorum failure persists failed backend status and prompt-not-started marker -ok 2 - lock preflight e2e: exit code 2 quorum failure persists failed backend status and prompt-not-started marker - --- - duration_ms: 101.712441 - type: 'test' - ... -# Subtest: lock preflight e2e: non-lock failure exits failed without prompt parse/schema classification -ok 3 - lock preflight e2e: non-lock failure exits failed without prompt parse/schema classification - --- - duration_ms: 112.476161 - type: 'test' - ... -1..3 -# tests 3 -# suites 0 -# pass 3 -# fail 0 -# cancelled 0 -# skipped 0 -# todo 0 -# duration_ms 747.186893 -TAP version 13 -# Subtest: parseArgs should parse basic command -ok 1 - parseArgs should parse basic command - --- - duration_ms: 1.62826 - type: 'test' - ... -# Subtest: parseArgs should parse agent and cadence -ok 2 - parseArgs should parse agent and cadence - --- - duration_ms: 0.300791 - type: 'test' - ... -# Subtest: parseArgs should parse equals sign syntax -ok 3 - parseArgs should parse equals sign syntax - --- - duration_ms: 2.038441 - type: 'test' - ... -# Subtest: parseArgs should parse dry-run flag -ok 4 - parseArgs should parse dry-run flag - --- - duration_ms: 0.357196 - type: 'test' - ... -# Subtest: parseArgs should parse port with default -ok 5 - parseArgs should parse port with default - --- - duration_ms: 0.200408 - type: 'test' - ... -# Subtest: parseArgs should parse custom port -ok 6 - parseArgs should parse custom port - --- - duration_ms: 0.238208 - type: 'test' - ... -# Subtest: parseArgs should parse ignore-logs flag -ok 7 - parseArgs should parse ignore-logs flag - --- - duration_ms: 0.282932 - type: 'test' - ... -# Subtest: parseArgs should parse memory flags -ok 8 - parseArgs should parse memory flags - --- - duration_ms: 1.109769 - type: 'test' - ... -# Subtest: parseArgs should parse memory flags with equals -ok 9 - parseArgs should parse memory flags with equals - --- - duration_ms: 0.691829 - type: 'test' - ... -# Subtest: src/lib.mjs - # Subtest: cmdCheck - # Subtest: returns correct structure with empty locks - ok 1 - returns correct structure with empty locks - --- - duration_ms: 3.991071 - type: 'test' - ... - # Subtest: identifies locked agents - ok 2 - identifies locked agents - --- - duration_ms: 0.734622 - type: 'test' - ... - # Subtest: excludes paused agents - ok 3 - excludes paused agents - --- - duration_ms: 0.989105 - type: 'test' - ... - # Subtest: identifies unknown locked agents - ok 4 - identifies unknown locked agents - --- - duration_ms: 1.393716 - type: 'test' - ... - 1..4 - ok 1 - cmdCheck - --- - duration_ms: 9.243112 - type: 'suite' - ... - # Subtest: cmdLock - # Subtest: successfully locks an available agent - ok 1 - successfully locks an available agent - --- - duration_ms: 17.055303 - type: 'test' - ... - # Subtest: fails if agent is not in roster - ok 2 - fails if agent is not in roster - --- - duration_ms: 1.596473 - type: 'test' - ... - # Subtest: fails if agent is already locked - ok 3 - fails if agent is already locked - --- - duration_ms: 0.657366 - type: 'test' - ... - # Subtest: fails if agent is already completed - ok 4 - fails if agent is already completed - --- - duration_ms: 0.858999 - type: 'test' - ... - # Subtest: fails if race check is lost - ok 5 - fails if race check is lost - --- - duration_ms: 11.086878 - type: 'test' - ... - # Subtest: handles race condition with identical timestamps using eventId tie-breaker (we win) - ok 6 - handles race condition with identical timestamps using eventId tie-breaker (we win) - --- - duration_ms: 20.417519 - type: 'test' - ... - # Subtest: handles race condition with identical timestamps using eventId tie-breaker (we lose) - ok 7 - handles race condition with identical timestamps using eventId tie-breaker (we lose) - --- - duration_ms: 2.852204 - type: 'test' - ... - # Subtest: dry run does not publish - ok 8 - dry run does not publish - --- - duration_ms: 0.842969 - type: 'test' - ... - 1..8 - ok 2 - cmdLock - --- - duration_ms: 57.040769 - type: 'suite' - ... - # Subtest: cmdList - # Subtest: lists active locks - ok 1 - lists active locks - --- - duration_ms: 1.344673 - type: 'test' - ... - # Subtest: warns about unknown agents - ok 2 - warns about unknown agents - --- - duration_ms: 0.449696 - type: 'test' - ... - # Subtest: handles no locks - ok 3 - handles no locks - --- - duration_ms: 0.294865 - type: 'test' - ... - 1..3 - ok 3 - cmdList - --- - duration_ms: 2.298278 - type: 'suite' - ... - # Subtest: cmdComplete - # Subtest: successfully completes an active lock - ok 1 - successfully completes an active lock - --- - duration_ms: 1.953578 - type: 'test' - ... - # Subtest: fails if no active lock found - ok 2 - fails if no active lock found - --- - duration_ms: 0.491134 - type: 'test' - ... - # Subtest: detects already completed task - ok 3 - detects already completed task - --- - duration_ms: 0.331869 - type: 'test' - ... - 1..3 - ok 4 - cmdComplete - --- - duration_ms: 2.939241 - type: 'suite' - ... - 1..4 -ok 10 - src/lib.mjs - --- - duration_ms: 72.858459 - type: 'suite' - ... -# Published to 1/3 relays (required=1, timeout=25ms) -# Published to 2/2 relays (required=2, timeout=25ms) -# Published to 2/3 relays (required=2, timeout=25ms) -# (node:11408) ExperimentalWarning: The MockTimers API is an experimental feature and might change at any time -# (Use `node --trace-warnings ...` to show where the warning was created) -# Subtest: ci-resilience lock acquisition under unstable relays - # Subtest: recovers after all relays are down for an initial outage window - ok 1 - recovers after all relays are down for an initial outage window - --- - duration_ms: 29.835505 - type: 'test' - ... - # Subtest: survives intermittent timeout spikes and reaches quorum with bounded retries - ok 2 - survives intermittent timeout spikes and reaches quorum with bounded retries - --- - duration_ms: 6.771204 - type: 'test' - ... - # Subtest: handles staggered relay recovery and never exceeds retry budget - ok 3 - handles staggered relay recovery and never exceeds retry budget - --- - duration_ms: 3.339809 - type: 'test' - ... - 1..3 -ok 11 - ci-resilience lock acquisition under unstable relays - --- - duration_ms: 42.319195 - type: 'suite' - ... -# Published to 1/1 relays (required=1, timeout=200ms) -# Published to 1/1 relays (required=1, timeout=200ms) -# (node:11427) ExperimentalWarning: The MockTimers API is an experimental feature and might change at any time -# (Use `node --trace-warnings ...` to show where the warning was created) -# Subtest: publishLock retry behavior - # Subtest: succeeds immediately on first attempt without retries - ok 1 - succeeds immediately on first attempt without retries - --- - duration_ms: 5.542474 - type: 'test' - ... - # Subtest: retries a transient failure then succeeds within retry budget with bounded jitter - ok 2 - retries a transient failure then succeeds within retry budget with bounded jitter - --- - duration_ms: 2.517607 - type: 'test' - ... - # Subtest: returns terminal relay_publish_quorum_failure after exhausting retry budget - ok 3 - returns terminal relay_publish_quorum_failure after exhausting retry budget - --- - duration_ms: 4.304852 - type: 'test' - ... - # Subtest: short-circuits non-retryable failures without extra attempts - ok 4 - short-circuits non-retryable failures without extra attempts - --- - duration_ms: 1.598146 - type: 'test' - ... - 1..4 -ok 12 - publishLock retry behavior - --- - duration_ms: 15.452743 - type: 'suite' - ... -# Published to 2/2 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/2 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"elapsedMs":1}],"totalElapsedMs":1} -# Published to 1/2 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/2 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":2,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/2 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":1,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":1,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/1 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":1,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":1,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/1 relays (required=1, timeout=200ms) -# {"event":"lock_publish_quorum_met","correlationId":"none","attemptId":"1","publishAttempt":1,"successCount":1,"relayAttemptedCount":3,"requiredSuccesses":1,"timeoutMs":200,"retryTimeline":[{"publishAttempt":1,"successCount":1,"relayAttemptedCount":3,"elapsedMs":0}],"totalElapsedMs":0} -# Published to 1/3 relays (required=1, timeout=200ms) -# Subtest: lock-ops - # Subtest: parseLockEvent - # Subtest: parses a valid lock event correctly - ok 1 - parses a valid lock event correctly - --- - duration_ms: 1.501063 - type: 'test' - ... - 1..1 - ok 1 - parseLockEvent - --- - duration_ms: 2.551245 - type: 'suite' - ... - # Subtest: queryLocks - # Subtest: falls back to fallback relays when primary query fails - ok 1 - falls back to fallback relays when primary query fails - --- - duration_ms: 16.143847 - type: 'test' - ... - 1..1 - ok 2 - queryLocks - --- - duration_ms: 16.470971 - type: 'suite' - ... - # Subtest: publishLock - # Subtest: retries transient failures and succeeds on a later attempt - ok 1 - retries transient failures and succeeds on a later attempt - --- - duration_ms: 7.321713 - type: 'test' - ... - # Subtest: fails after retry budget is exhausted for persistent transient failures - ok 2 - fails after retry budget is exhausted for persistent transient failures - --- - duration_ms: 2.316131 - type: 'test' - ... - # Subtest: fails without retry for persistent validation failures - ok 3 - fails without retry for persistent validation failures - --- - duration_ms: 1.137998 - type: 'test' - ... - # Subtest: includes per-relay reason categories and retry metadata in failure diagnostics - ok 4 - includes per-relay reason categories and retry metadata in failure diagnostics - --- - duration_ms: 1.87285 - type: 'test' - ... - # Subtest: returns success when mixed relay outcomes still satisfy quorum - ok 5 - returns success when mixed relay outcomes still satisfy quorum - --- - duration_ms: 1.191763 - type: 'test' - ... - # Subtest: uses fallback relays to satisfy min success quorum - ok 6 - uses fallback relays to satisfy min success quorum - --- - duration_ms: 1.198319 - type: 'test' - ... - # Subtest: quarantines repeatedly failing relays and still reaches quorum with one healthy relay - ok 7 - quarantines repeatedly failing relays and still reaches quorum with one healthy relay - --- - duration_ms: 2.410316 - type: 'test' - ... - # Subtest: uses fallback and min active pool to reintroduce quarantined relay when needed - ok 8 - uses fallback and min active pool to reintroduce quarantined relay when needed - --- - duration_ms: 0.989401 - type: 'test' - ... - 1..8 - ok 3 - publishLock - --- - duration_ms: 19.335294 - type: 'suite' - ... - 1..3 -ok 13 - lock-ops - --- - duration_ms: 39.426323 - type: 'suite' - ... -# memory_telemetry { -# event: 'memory:ingested', -# payload: { -# memory_id: 'cb3ab94f-63e2-43e4-a994-01a3b23ab509', -# agent_id: 'agent-telemetry', -# dedupe_key: '4b1ed30fca4d37f2ab4b64612772244982594e9bc5dc6a86f122edec877cd483', -# chunk_events: 1, -# window_start: 0, -# window_end: 1771202046330 -# }, -# ts: 1771202046335 -# } -# memory_metric { -# metric: 'memory_ingested_total', -# payload: { count: 1 }, -# ts: 1771202046336 -# } -# memory_metric { -# metric: 'memory_retrieved_total', -# payload: { count: 4, cache_hit: false }, -# ts: 1771202046339 -# } -# memory_telemetry { -# event: 'memory:pruned', -# payload: { pruned_count: 1, retention_ms: 1000, dry_run: true }, -# ts: 1771202046340 -# } -# memory_metric { -# metric: 'memory_pruned_total', -# payload: { count: 0, retention_ms: 1000, dry_run: true }, -# ts: 1771202046341 -# } -# memory_telemetry { -# event: 'memory:prune_skipped', -# payload: { reason: 'flag_disabled', retention_ms: 1000 }, -# ts: 1771202046341 -# } -# Subtest: listMemories, inspectMemory, pinMemory, and unpinMemory support admin hooks -ok 14 - listMemories, inspectMemory, pinMemory, and unpinMemory support admin hooks - --- - duration_ms: 2.5615 - type: 'test' - ... -# Subtest: triggerPruneDryRun returns candidate metadata without deleting records -ok 15 - triggerPruneDryRun returns candidate metadata without deleting records - --- - duration_ms: 0.471388 - type: 'test' - ... -# Subtest: memoryStats reports counts/rates and retrieval telemetry remains redaction-safe -ok 16 - memoryStats reports counts/rates and retrieval telemetry remains redaction-safe - --- - duration_ms: 10.727121 - type: 'test' - ... -# Subtest: runPruneCycle respects prune feature-flag modes -ok 17 - runPruneCycle respects prune feature-flag modes - --- - duration_ms: 1.313773 - type: 'test' - ... -# Subtest: stores runtime events in signer/session namespace and clears scope -ok 18 - stores runtime events in signer/session namespace and clears scope - --- - duration_ms: 2.743132 - type: 'test' - ... -# Subtest: expires runtime events and records expiration metrics -ok 19 - expires runtime events and records expiration metrics - --- - duration_ms: 10.584138 - type: 'test' - ... -# Subtest: enforces LRU bounds and tracks eviction metrics -ok 20 - enforces LRU bounds and tracks eviction metrics - --- - duration_ms: 0.627116 - type: 'test' - ... -# Subtest: blocks decrypted/session-sensitive data from durable promotion without sanitizer pass -ok 21 - blocks decrypted/session-sensitive data from durable promotion without sanitizer pass - --- - duration_ms: 0.355843 - type: 'test' - ... -# Subtest: createEmbedderAdapter selects in-memory backend and supports vector CRUD -ok 22 - createEmbedderAdapter selects in-memory backend and supports vector CRUD - --- - duration_ms: 1.655848 - type: 'test' - ... -# Subtest: createEmbedderAdapter reads backend from environment -ok 23 - createEmbedderAdapter reads backend from environment - --- - duration_ms: 0.52594 - type: 'test' - ... -# Subtest: memory feature flags parse defaults and canary allow-lists -ok 24 - memory feature flags parse defaults and canary allow-lists - --- - duration_ms: 1.295328 - type: 'test' - ... -# Subtest: memory prune flag supports off, dry-run, and active modes -ok 25 - memory prune flag supports off, dry-run, and active modes - --- - duration_ms: 0.293935 - type: 'test' - ... -# Subtest: ingestMemoryWindow gathers sources, redacts pii, chunks, embeds, links, and emits telemetry -ok 26 - ingestMemoryWindow gathers sources, redacts pii, chunks, embeds, links, and emits telemetry - --- - duration_ms: 5.972327 - type: 'test' - ... -# Subtest: ingestMemoryWindow dedupes overlapping windows by hashed content + agent + timestamp bucket -ok 27 - ingestMemoryWindow dedupes overlapping windows by hashed content + agent + timestamp bucket - --- - duration_ms: 1.084625 - type: 'test' - ... -# Subtest: createLifecyclePlan respects delete safety constraints and logs reasons -ok 28 - createLifecyclePlan respects delete safety constraints and logs reasons - --- - duration_ms: 2.538435 - type: 'test' - ... -# Subtest: createLifecyclePlan condenses near-duplicates and archives merged source records -ok 29 - createLifecyclePlan condenses near-duplicates and archives merged source records - --- - duration_ms: 1.064069 - type: 'test' - ... -# Subtest: applyLifecycleActions executes keep/archive/delete and merge markers -ok 30 - applyLifecycleActions executes keep/archive/delete and merge markers - --- - duration_ms: 1.380832 - type: 'test' - ... -# Subtest: filterAndRankMemories applies metadata filters and composite score -ok 31 - filterAndRankMemories applies metadata filters and composite score - --- - duration_ms: 3.045455 - type: 'test' - ... -# Subtest: formatMemoriesForPrompt returns prompt blocks and enforces token budget trimming -ok 32 - formatMemoriesForPrompt returns prompt blocks and enforces token budget trimming - --- - duration_ms: 2.755406 - type: 'test' - ... -# Subtest: isMemoryRetrievalEnabled supports global toggle and agent canary list -ok 33 - isMemoryRetrievalEnabled supports global toggle and agent canary list - --- - duration_ms: 0.515142 - type: 'test' - ... -# Subtest: renderPromptWithMemoryContext injects bounded memory block before base prompt -ok 34 - renderPromptWithMemoryContext injects bounded memory block before base prompt - --- - duration_ms: 0.848686 - type: 'test' - ... -# Subtest: createDbAdvisoryLockProvider acquires and releases postgres advisory locks -ok 35 - createDbAdvisoryLockProvider acquires and releases postgres advisory locks - --- - duration_ms: 2.468697 - type: 'test' - ... -# Subtest: startMemoryMaintenanceScheduler runs all jobs and emits metrics including retries -ok 36 - startMemoryMaintenanceScheduler runs all jobs and emits metrics including retries - --- - duration_ms: 26.999776 - type: 'test' - ... -# Subtest: startMemoryMaintenanceScheduler skips jobs when feature flags disable memory -ok 37 - startMemoryMaintenanceScheduler skips jobs when feature flags disable memory - --- - duration_ms: 11.083524 - type: 'test' - ... -# Subtest: normalizeMemoryItem applies durable schema defaults and coercions -ok 38 - normalizeMemoryItem applies durable schema defaults and coercions - --- - duration_ms: 4.280892 - type: 'test' - ... -# Subtest: validateMemoryItem reports field-level errors -ok 39 - validateMemoryItem reports field-level errors - --- - duration_ms: 0.524269 - type: 'test' - ... -# Subtest: ingestEvents rejects invalid writes and logs structured validation details -ok 40 - ingestEvents rejects invalid writes and logs structured validation details - --- - duration_ms: 4.703274 - type: 'test' - ... -# Subtest: loadMemoryPromptTemplates loads all memory prompt templates from disk -ok 41 - loadMemoryPromptTemplates loads all memory prompt templates from disk - --- - duration_ms: 1.48071 - type: 'test' - ... -# Subtest: summarizeEvents retries with repair prompt when first response is malformed JSON -ok 42 - summarizeEvents retries with repair prompt when first response is malformed JSON - --- - duration_ms: 2.203644 - type: 'test' - ... -# Subtest: summarizeEvents falls back to deterministic minimal summary with conservative importance when parsing fails twice -ok 43 - summarizeEvents falls back to deterministic minimal summary with conservative importance when parsing fails twice - --- - duration_ms: 2.635429 - type: 'test' - ... -# Subtest: CLI Smoke Test - # Subtest: should print usage when no args provided - ok 1 - should print usage when no args provided - --- - duration_ms: 291.301346 - type: 'test' - ... - # Subtest: should fail when checking without cadence - ok 2 - should fail when checking without cadence - --- - duration_ms: 349.552153 - type: 'test' - ... - # Subtest: should include paused agents in check output - ok 3 - should include paused agents in check output - --- - duration_ms: 1111.685006 - type: 'test' - ... - 1..3 -ok 44 - CLI Smoke Test - --- - duration_ms: 1756.372585 - type: 'suite' - ... -# Initializing torch configuration in /app/test-ops-vSSqGn/project1/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-f7eb217c" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Initializing torch configuration in /app/test-ops-vSSqGn/project2/torch... -# Initializing torch configuration in /app/test-ops-vSSqGn/project3/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-d0803fd4" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Updating torch configuration in /app/test-ops-vSSqGn/project3/torch... -# Creating backup at torch/_backups/backup_2026-02-16T00-34-06-883Z... -# Updating application directories... -# Updated src/ -# Updated bin/ -# Updated dashboard/ -# Updated landing/ -# Updated assets/ -# Updated scripts/ -# Updating application files... -# Updated package.json -# Updated build.mjs -# Updated README.md -# Updated torch-config.example.json -# Updating static files... -# Updated META_PROMPTS.md -# Updated scheduler-flow.md -# Updated daily-scheduler.md -# Updated weekly-scheduler.md -# Skipped roster.json (preserved) -# Updating prompts... -# daily/: 0 added, 0 updated, 22 preserved -# weekly/: 0 added, 0 updated, 21 preserved -# Update complete. -# Initializing torch configuration in /app/test-ops-vSSqGn/project4/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-bf757dfd" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Updating torch configuration in /app/test-ops-vSSqGn/project4/torch... -# Creating backup at torch/_backups/backup_2026-02-16T00-34-07-078Z... -# Updating application directories... -# Updated src/ -# Updated bin/ -# Updated dashboard/ -# Updated landing/ -# Updated assets/ -# Updated scripts/ -# Updating application files... -# Updated package.json -# Updated build.mjs -# Updated README.md -# Updated torch-config.example.json -# Updating static files... -# Updated META_PROMPTS.md -# Updated scheduler-flow.md -# Updated daily-scheduler.md -# Updated weekly-scheduler.md -# Overwrote roster.json (forced) -# Updating prompts... -# daily/: 0 added, 22 updated, 0 preserved -# weekly/: 0 added, 21 updated, 0 preserved -# Update complete. -# Initializing torch configuration in /app/test-ops-vSSqGn/project5/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-d9f56ede" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Updating torch configuration in /app/test-ops-vSSqGn/project5/torch... -# Creating backup at torch/_backups/backup_2026-02-16T00-34-07-295Z... -# Updating application directories... -# Updated src/ -# Updated bin/ -# Updated dashboard/ -# Updated landing/ -# Updated assets/ -# Updated scripts/ -# Updating application files... -# Updated package.json -# Updated build.mjs -# Updated README.md -# Updated torch-config.example.json -# Updating static files... -# Updated META_PROMPTS.md -# Updated scheduler-flow.md -# Updated daily-scheduler.md -# Updated weekly-scheduler.md -# Skipped roster.json (preserved) -# Updating prompts... -# daily/: 0 added, 0 updated, 22 preserved -# weekly/: 0 added, 0 updated, 21 preserved -# Update complete. -# Initializing torch configuration in /app/test-ops-vSSqGn/project_roster/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-5167c881" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Checking locks: namespace=torch-5167c881, cadence=daily, date=2026-02-16 -# Relays: wss://relay.damus.io, wss://nos.lol, wss://relay.primal.net -# {"event":"relay_health_snapshot","reason":"query:periodic","relays":[{"relay":"wss://nos.lol","score":0.6,"sampleSize":0,"successRate":0.5,"timeoutRate":0,"averageLatencyMs":null,"failureStreak":0,"quarantined":false,"quarantineRemainingMs":0,"cooldownMs":30000,"lastResultAt":null},{"relay":"wss://relay.damus.io","score":0.6,"sampleSize":0,"successRate":0.5,"timeoutRate":0,"averageLatencyMs":null,"failureStreak":0,"quarantined":false,"quarantineRemainingMs":0,"cooldownMs":30000,"lastResultAt":null},{"relay":"wss://relay.nostr.band","score":0.6,"sampleSize":0,"successRate":0.5,"timeoutRate":0,"averageLatencyMs":null,"failureStreak":0,"quarantined":false,"quarantineRemainingMs":0,"cooldownMs":30000,"lastResultAt":null},{"relay":"wss://relay.primal.net","score":0.6,"sampleSize":0,"successRate":0.5,"timeoutRate":0,"averageLatencyMs":null,"failureStreak":0,"quarantined":false,"quarantineRemainingMs":0,"cooldownMs":30000,"lastResultAt":null},{"relay":"wss://relay.snort.social","score":0.6,"sampleSize":0,"successRate":0.5,"timeoutRate":0,"averageLatencyMs":null,"failureStreak":0,"quarantined":false,"quarantineRemainingMs":0,"cooldownMs":30000,"lastResultAt":null}]} -# Initializing torch configuration in /app/test-ops-vSSqGn/project_config_init/torch... -# Copying application directories... -# Copied src/ -# Copied bin/ -# Copied dashboard/ -# Copied landing/ -# Copied assets/ -# Copied scripts/ -# Copying application files... -# Copied package.json -# Copied build.mjs -# Copied README.md -# Copied torch-config.example.json -# Created torch/roster.json -# Created torch/META_PROMPTS.md -# Created torch/scheduler-flow.md -# Created torch/daily-scheduler.md -# Created torch/weekly-scheduler.md -# Created 22 files in torch/prompts/daily/ -# Created 21 files in torch/prompts/weekly/ -# Created torch-config.json with namespace "torch-0d7d4500" -# Initialization complete. -# You can now customize the files in torch/ and torch/prompts/. -# Subtest: cmdInit creates directory structure and files -ok 45 - cmdInit creates directory structure and files - --- - duration_ms: 116.425575 - type: 'test' - ... -# Subtest: cmdInit fails if directory exists without force -ok 46 - cmdInit fails if directory exists without force - --- - duration_ms: 1.918692 - type: 'test' - ... -# Subtest: cmdUpdate preserves modified prompt -ok 47 - cmdUpdate preserves modified prompt - --- - duration_ms: 229.559826 - type: 'test' - ... -# Subtest: cmdUpdate overwrites prompt with force -ok 48 - cmdUpdate overwrites prompt with force - --- - duration_ms: 184.60354 - type: 'test' - ... -# Subtest: cmdUpdate creates backup -ok 49 - cmdUpdate creates backup - --- - duration_ms: 183.381503 - type: 'test' - ... -# Subtest: torch-lock check respects local roster -ok 50 - torch-lock check respects local roster - --- - duration_ms: 1146.057253 - type: 'test' - ... -# Subtest: cmdInit creates torch-config.json with random namespace -ok 51 - cmdInit creates torch-config.json with random namespace - --- - duration_ms: 56.595345 - type: 'test' - ... -# Published to 1/3 relays (required=1, timeout=80ms) -# Subtest: relay fanout quorum integration - # Subtest: passes with required=1 when one relay succeeds and two fail - ok 1 - passes with required=1 when one relay succeeds and two fail - --- - duration_ms: 171.873039 - type: 'test' - ... - # Subtest: fails with quorum error for required=1 when all relays fail - ok 2 - fails with quorum error for required=1 when all relays fail - --- - duration_ms: 103.155412 - type: 'test' - ... - # Subtest: fails with required=2 when only one relay succeeds - ok 3 - fails with required=2 when only one relay succeeds - --- - duration_ms: 108.682399 - type: 'test' - ... -# Published to 2/3 relays (required=2, timeout=80ms) - # Subtest: passes when delayed successes reach quorum before timeout - ok 4 - passes when delayed successes reach quorum before timeout - --- - duration_ms: 97.633222 - type: 'test' - ... - 1..4 -ok 52 - relay fanout quorum integration - --- - duration_ms: 484.115912 - type: 'suite' - ... -# Subtest: raises all-relays-down duration alert after threshold -ok 53 - raises all-relays-down duration alert after threshold - --- - duration_ms: 2.80821 - type: 'test' - ... -# Subtest: raises success-rate alert when rolling health falls below threshold -ok 54 - raises success-rate alert when rolling health falls below threshold - --- - duration_ms: 0.354661 - type: 'test' - ... -# Subtest: fails required memory policy when retrieval/storage evidence is missing -ok 55 - fails required memory policy when retrieval/storage evidence is missing - --- - duration_ms: 867.491516 - type: 'test' - ... -# Subtest: accepts required memory policy when markers or artifacts are produced -ok 56 - accepts required memory policy when markers or artifacts are produced - --- - duration_ms: 917.292328 - type: 'test' - ... -# Subtest: records backend failure metadata when lock command exits with code 2 -ok 57 - records backend failure metadata when lock command exits with code 2 - --- - duration_ms: 983.414552 - type: 'test' - ... -# Subtest: defers backend failures in non-strict mode and reuses idempotency key on successful retry -ok 58 - defers backend failures in non-strict mode and reuses idempotency key on successful retry - --- - duration_ms: 586.454659 - type: 'test' - ... -# Subtest: fails after exceeding non-strict deferral budget -ok 59 - fails after exceeding non-strict deferral budget - --- - duration_ms: 176.281973 - type: 'test' - ... -# Subtest: strict lock mode fails immediately without deferral -ok 60 - strict lock mode fails immediately without deferral - --- - duration_ms: 92.092641 - type: 'test' - ... -# Subtest: skips lock health preflight by default when not enabled -ok 61 - skips lock health preflight by default when not enabled - --- - duration_ms: 393.710507 - type: 'test' - ... -# Subtest: fails scheduler with preflight metadata when lock health preflight is enabled -ok 62 - fails scheduler with preflight metadata when lock health preflight is enabled - --- - duration_ms: 127.561572 - type: 'test' - ... -# Subtest: categorizes unreadable prompt files as prompt_parse_error -ok 63 - categorizes unreadable prompt files as prompt_parse_error - --- - duration_ms: 94.516802 - type: 'test' - ... -# Subtest: categorizes invalid prompt schema as prompt_schema_error -ok 64 - categorizes invalid prompt schema as prompt_schema_error - --- - duration_ms: 93.728806 - type: 'test' - ... -# Subtest: categorizes handoff runtime failures as execution_error -ok 65 - categorizes handoff runtime failures as execution_error - --- - duration_ms: 344.985215 - type: 'test' - ... -# Subtest: retries lock acquisition for backend error and succeeds on a later attempt -ok 66 - retries lock acquisition for backend error and succeeds on a later attempt - --- - duration_ms: 399.66793 - type: 'test' - ... -# Subtest: stops retrying after configured lock backend retries are exhausted -ok 67 - stops retrying after configured lock backend retries are exhausted - --- - duration_ms: 101.436698 - type: 'test' - ... -# Subtest: does not use backend retry flow for exit code 3 lock conflicts -ok 68 - does not use backend retry flow for exit code 3 lock conflicts - --- - duration_ms: 416.871688 - type: 'test' - ... -# Subtest: runs selected scheduler prompt through configured runner command -ok 69 - runs selected scheduler prompt through configured runner command - --- - duration_ms: 349.859998 - type: 'test' - ... -# Subtest: propagates non-zero runner exit code -ok 70 - propagates non-zero runner exit code - --- - duration_ms: 341.39237 - type: 'test' - ... -# Subtest: scheduler lock backend failure artifact matches required frontmatter schema -ok 71 - scheduler lock backend failure artifact matches required frontmatter schema - --- - duration_ms: 102.976554 - type: 'test' - ... -# Subtest: schema contract catches missing required lock-backend field -ok 72 - schema contract catches missing required lock-backend field - --- - duration_ms: 1.969747 - type: 'test' - ... -# Subtest: schema contract catches misnamed lock-backend key -ok 73 - schema contract catches misnamed lock-backend key - --- - duration_ms: 0.537546 - type: 'test' - ... -# Subtest: lock preflight e2e: successful lock writes completed status snapshot -ok 74 - lock preflight e2e: successful lock writes completed status snapshot - --- - duration_ms: 404.396931 - type: 'test' - ... -# Subtest: lock preflight e2e: exit code 2 quorum failure persists failed backend status and prompt-not-started marker -ok 75 - lock preflight e2e: exit code 2 quorum failure persists failed backend status and prompt-not-started marker - --- - duration_ms: 95.373976 - type: 'test' - ... -# Subtest: lock preflight e2e: non-lock failure exits failed without prompt parse/schema classification -ok 76 - lock preflight e2e: non-lock failure exits failed without prompt parse/schema classification - --- - duration_ms: 90.269496 - type: 'test' - ... -# Subtest: Scheduler Ratchet Logic (Log Checking) - # Subtest: excludes agents completed today (daily) - ok 1 - excludes agents completed today (daily) - --- - duration_ms: 2.645779 - type: 'test' - ... - # Subtest: excludes agents completed this week (weekly) - ok 2 - excludes agents completed this week (weekly) - --- - duration_ms: 0.452564 - type: 'test' - ... - # Subtest: combines locked and completed agents in exclusion list - ok 3 - combines locked and completed agents in exclusion list - --- - duration_ms: 0.540265 - type: 'test' - ... - # Subtest: ignores logs when --ignore-logs is set - ok 4 - ignores logs when --ignore-logs is set - --- - duration_ms: 0.413416 - type: 'test' - ... - # Subtest: handles missing log directory gracefully - ok 5 - handles missing log directory gracefully - --- - duration_ms: 0.351015 - type: 'test' - ... - 1..5 -ok 77 - Scheduler Ratchet Logic (Log Checking) - --- - duration_ms: 5.962229 - type: 'suite' - ... -# Subtest: Scheduler cycle ordering guarantees - # Subtest: keeps optional preflight before lock-acquire and preserves handoff/artifact/validation/complete ordering - ok 1 - keeps optional preflight before lock-acquire and preserves handoff/artifact/validation/complete ordering - --- - duration_ms: 12.773423 - type: 'test' - ... - # Subtest: includes lock backend failure metadata and classifier checkpoints - ok 2 - includes lock backend failure metadata and classifier checkpoints - --- - duration_ms: 2.042276 - type: 'test' - ... - 1..2 -ok 78 - Scheduler cycle ordering guarantees - --- - duration_ms: 15.405925 - type: 'suite' - ... -# Subtest: summarizes recent lock reliability by platform/cadence/backend/relay -ok 79 - summarizes recent lock reliability by platform/cadence/backend/relay - --- - duration_ms: 88.457505 - type: 'test' - ... -# Subtest: loadTorchConfig (Unit Tests with Mocked FS) - # Subtest: loads valid config correctly - ok 1 - loads valid config correctly - --- - duration_ms: 3.803768 - type: 'test' - ... - # Subtest: returns default config when file is missing - ok 2 - returns default config when file is missing - --- - duration_ms: 0.508882 - type: 'test' - ... - # Subtest: throws error on malformed JSON - ok 3 - throws error on malformed JSON - --- - duration_ms: 0.895634 - type: 'test' - ... - # Subtest: caches the config and ignores subsequent fs calls - ok 4 - caches the config and ignores subsequent fs calls - --- - duration_ms: 0.673118 - type: 'test' - ... - 1..4 -ok 80 - loadTorchConfig (Unit Tests with Mocked FS) - --- - duration_ms: 7.594028 - type: 'suite' - ... -# Subtest: torch-config - # Subtest: getTorchConfigPath - # Subtest: returns default path when env var is not set - ok 1 - returns default path when env var is not set - --- - duration_ms: 1.050242 - type: 'test' - ... - # Subtest: returns custom path when env var is set - ok 2 - returns custom path when env var is set - --- - duration_ms: 0.38111 - type: 'test' - ... - 1..2 - ok 1 - getTorchConfigPath - --- - duration_ms: 2.752161 - type: 'suite' - ... - # Subtest: parseTorchConfig - # Subtest: parses new lock backend knobs - ok 1 - parses new lock backend knobs - --- - duration_ms: 1.346933 - type: 'test' - ... - 1..1 - ok 2 - parseTorchConfig - --- - duration_ms: 1.529808 - type: 'suite' - ... - # Subtest: loadTorchConfig - # Subtest: throws fatal error for invalid relay URL - ok 1 - throws fatal error for invalid relay URL - --- - duration_ms: 1.814454 - type: 'test' - ... - # Subtest: throws fatal error for invalid timeout range - ok 2 - throws fatal error for invalid timeout range - --- - duration_ms: 2.078621 - type: 'test' - ... - # Subtest: throws error for malformed JSON - ok 3 - throws error for malformed JSON - --- - duration_ms: 0.811601 - type: 'test' - ... - 1..3 - ok 3 - loadTorchConfig - --- - duration_ms: 5.900837 - type: 'suite' - ... - # Subtest: backend getters - # Subtest: returns default relays - ok 1 - returns default relays - --- - duration_ms: 0.718044 - type: 'test' - ... - # Subtest: validates env knob values - ok 2 - validates env knob values - --- - duration_ms: 1.010661 - type: 'test' - ... - 1..2 - ok 4 - backend getters - --- - duration_ms: 4.092197 - type: 'suite' - ... - 1..4 -ok 81 - torch-config - --- - duration_ms: 15.385685 - type: 'suite' - ... -# Subtest: Date Utilities - # Subtest: getIsoWeekStr - # Subtest: returns correct ISO week for simple cases - ok 1 - returns correct ISO week for simple cases - --- - duration_ms: 1.370898 - type: 'test' - ... - # Subtest: handles year boundaries correctly - ok 2 - handles year boundaries correctly - --- - duration_ms: 0.217656 - type: 'test' - ... - # Subtest: handles leap years - ok 3 - handles leap years - --- - duration_ms: 1.721102 - type: 'test' - ... - # Subtest: handles empty input (defaults to today) - ok 4 - handles empty input (defaults to today) - --- - duration_ms: 0.435451 - type: 'test' - ... - # Subtest: handles invalid input gracefully - ok 5 - handles invalid input gracefully - --- - duration_ms: 0.345039 - type: 'test' - ... - 1..5 - ok 1 - getIsoWeekStr - --- - duration_ms: 5.265987 - type: 'suite' - ... - 1..1 -ok 82 - Date Utilities - --- - duration_ms: 5.795432 - type: 'suite' - ... -# Subtest: passes when artifacts include metadata and failure IDs map to unresolved known issue entries -ok 83 - passes when artifacts include metadata and failure IDs map to unresolved known issue entries - --- - duration_ms: 81.375319 - type: 'test' - ... -# Subtest: fails when required metadata is missing from artifacts -ok 84 - fails when required metadata is missing from artifacts - --- - duration_ms: 69.70169 - type: 'test' - ... -# Subtest: fails when failure identifiers are not cross-linked to known issues or incidents -ok 85 - fails when failure identifiers are not cross-linked to known issues or incidents - --- - duration_ms: 69.918486 - type: 'test' - ... -# Subtest: schema validation covers required fields, coercion, and rejection paths -ok 86 - schema validation covers required fields, coercion, and rejection paths - --- - duration_ms: 2.951137 - type: 'test' - ... -# Subtest: summarizer parser accepts valid json and recovers after malformed json response -ok 87 - summarizer parser accepts valid json and recovers after malformed json response - --- - duration_ms: 2.456 - type: 'test' - ... -# Subtest: ingest integration persists memory records and links embeddings from event batches -ok 88 - ingest integration persists memory records and links embeddings from event batches - --- - duration_ms: 3.999804 - type: 'test' - ... -# Subtest: retrieval ranking blends semantic, importance, and recency signals -ok 89 - retrieval ranking blends semantic, importance, and recency signals - --- - duration_ms: 0.831681 - type: 'test' - ... -# Subtest: pruner policy protects pins, merges duplicates, and picks archive/delete outcomes -ok 90 - pruner policy protects pins, merges duplicates, and picks archive/delete outcomes - --- - duration_ms: 1.472562 - type: 'test' - ... -# Subtest: scheduler smoke test handles mocked clock and lock contention -ok 91 - scheduler smoke test handles mocked clock and lock contention - --- - duration_ms: 32.214841 - type: 'test' - ... -1..91 -# tests 146 -# suites 23 -# pass 146 -# fail 0 -# cancelled 0 -# skipped 0 -# todo 0 -# duration_ms 8318.171145