Files
TORCH/reports/test-audit/flakiness-matrix.json
T
google-labs-jules[bot]andPR0M3TH3AN 964f33b91c daily: test-audit-agent execution and tooling fix
Executed test-audit-agent.
- Fixed scripts/test-audit/run-flaky-check.mjs to exclude Playwright tests by default.
- Generated audit report in reports/test-audit/.
- Created completion log.

Co-authored-by: PR0M3TH3AN <[email protected]>
2026-02-24 19:18:57 +00:00

766 lines
18 KiB
JSON

{
"Build artifacts verification # SKIP dist/ not found — run npm run build first": {
"pass": 5,
"fail": 0
},
"parseArgs should parse basic command": {
"pass": 5,
"fail": 0
},
"parseArgs should parse agent and cadence": {
"pass": 5,
"fail": 0
},
"parseArgs should parse equals sign syntax": {
"pass": 5,
"fail": 0
},
"parseArgs should parse dry-run flag": {
"pass": 5,
"fail": 0
},
"parseArgs should parse port with default": {
"pass": 5,
"fail": 0
},
"parseArgs should parse custom port": {
"pass": 5,
"fail": 0
},
"parseArgs should parse ignore-logs flag": {
"pass": 5,
"fail": 0
},
"parseArgs should parse memory flags": {
"pass": 5,
"fail": 0
},
"parseArgs should parse memory flags with equals": {
"pass": 5,
"fail": 0
},
"cmdList": {
"pass": 5,
"fail": 0
},
"cmdRemove reports nothing when no TORCH installation exists": {
"pass": 5,
"fail": 0
},
"cmdRemove with --force removes torch/ directory": {
"pass": 5,
"fail": 0
},
"cmdRemove removes runtime artifacts (task-logs, .scheduler-memory)": {
"pass": 5,
"fail": 0
},
"cmdRemove removes src/proposals/ and cleans empty src/": {
"pass": 5,
"fail": 0
},
"cmdRemove cleans torch:* scripts from host package.json": {
"pass": 5,
"fail": 0
},
"cmdRemove cancels when user declines confirmation": {
"pass": 5,
"fail": 0
},
"cmdRemove confirmed via mockAnswers removes artifacts": {
"pass": 5,
"fail": 0
},
"Dashboard Authentication": {
"pass": 5,
"fail": 0
},
"Dashboard Configuration Exposure Security": {
"pass": 5,
"fail": 0
},
"Dashboard Configuration Security": {
"pass": 5,
"fail": 0
},
"Dashboard Path Traversal Security Fix": {
"pass": 5,
"fail": 0
},
"Dashboard File Access Security": {
"pass": 5,
"fail": 0
},
"ExitError": {
"pass": 5,
"fail": 0
},
"createProposal should throw error for disallowed target": {
"pass": 5,
"fail": 0
},
"validateProposal should return invalid for disallowed target": {
"pass": 5,
"fail": 0
},
"validateProposal should return valid for allowed target": {
"pass": 5,
"fail": 0
},
"Governance Service Security: Command Injection Prevention": {
"pass": 5,
"fail": 0
},
"SCN-proposal-create: createProposal writes meta.json, new.md, change.diff": {
"pass": 5,
"fail": 0
},
"SCN-proposal-list: listProposals returns created proposal; status filter works": {
"pass": 5,
"fail": 0
},
"SCN-proposal-reject: rejectProposal marks proposal with rejected status and reason": {
"pass": 5,
"fail": 0
},
"SCN-archive-naming: applyProposal archives with timestamp_hash filename and sidecar": {
"pass": 5,
"fail": 0
},
"SCN-version-list: listPromptVersions returns versions newest-first with metadata": {
"pass": 5,
"fail": 0
},
"SCN-rollback-latest: rollbackPrompt restores the most recently archived content": {
"pass": 5,
"fail": 0
},
"SCN-rollback-hash: rollbackPrompt --strategy <fragment> restores matching archive": {
"pass": 5,
"fail": 0
},
"cmdInit should validate install directory name": {
"pass": 5,
"fail": 0
},
"src/lib.mjs": {
"pass": 5,
"fail": 0
},
"ci-resilience lock acquisition under unstable relays": {
"pass": 5,
"fail": 0
},
"publishLock retry behavior": {
"pass": 5,
"fail": 0
},
"lock-ops": {
"pass": 5,
"fail": 0
},
"getCompletedAgents": {
"pass": 5,
"fail": 0
},
"main dispatch": {
"pass": 5,
"fail": 0
},
"listMemories, inspectMemory, pinMemory, and unpinMemory support admin hooks": {
"pass": 5,
"fail": 0
},
"triggerPruneDryRun returns candidate metadata without deleting records": {
"pass": 5,
"fail": 0
},
"memoryStats reports counts/rates and retrieval telemetry remains redaction-safe": {
"pass": 5,
"fail": 0
},
"runPruneCycle respects prune feature-flag modes": {
"pass": 5,
"fail": 0
},
"markMemoryMerged delegates to repository and clears cache": {
"pass": 5,
"fail": 0
},
"stores runtime events in signer/session namespace and clears scope": {
"pass": 5,
"fail": 0
},
"expires runtime events and records expiration metrics": {
"pass": 5,
"fail": 0
},
"enforces LRU bounds and tracks eviction metrics": {
"pass": 5,
"fail": 0
},
"blocks decrypted/session-sensitive data from durable promotion without sanitizer pass": {
"pass": 5,
"fail": 0
},
"createEmbedderAdapter selects in-memory backend and supports vector CRUD": {
"pass": 5,
"fail": 0
},
"createEmbedderAdapter reads backend from environment": {
"pass": 5,
"fail": 0
},
"memory feature flags parse defaults and canary allow-lists": {
"pass": 5,
"fail": 0
},
"memory prune flag supports off, dry-run, and active modes": {
"pass": 5,
"fail": 0
},
"estimateTokenCount returns heuristic count": {
"pass": 5,
"fail": 0
},
"formatMemoryBlock converts memory record to display block": {
"pass": 5,
"fail": 0
},
"formatMemoryBlock handles missing optional fields and default clamping": {
"pass": 5,
"fail": 0
},
"formatMemoryBlock respects custom clamping options": {
"pass": 5,
"fail": 0
},
"formatMemoryBlock handles edge cases for clamping": {
"pass": 5,
"fail": 0
},
"formatMemoriesForPrompt enforces token budget and k limit": {
"pass": 5,
"fail": 0
},
"formatMemoriesForPrompt handles aggressive budget fitting": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext injects context when enabled": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext returns base prompt when disabled": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles missing query or service": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles circular agentContext gracefully": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles agentContext as array of strings": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles agentContext as plain object": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles agentContext as primitives": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext calls updateMemoryUsage for retrieved memories": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles empty memories gracefully": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext handles null/undefined memories gracefully": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext respects TORCH_MEMORY_ENABLED=false": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext respects retrieval allowlist": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext passes k and tokenBudget": {
"pass": 5,
"fail": 0
},
"getRelevantMemories uses cached results when available": {
"pass": 5,
"fail": 0
},
"getRelevantMemories calls ranker and updates cache on miss": {
"pass": 5,
"fail": 0
},
"getRelevantMemories passes correct parameters to ranker": {
"pass": 5,
"fail": 0
},
"getRelevantMemories triggers updateMemoryUsage on repository": {
"pass": 5,
"fail": 0
},
"ingestEvents": {
"pass": 5,
"fail": 0
},
"ingestMemoryWindow gathers sources, redacts pii, chunks, embeds, links, and emits telemetry": {
"pass": 5,
"fail": 0
},
"ingestMemoryWindow dedupes overlapping windows by hashed content + agent + timestamp bucket": {
"pass": 5,
"fail": 0
},
"pinMemory pins the memory and clears the cache": {
"pass": 5,
"fail": 0
},
"pinMemory returns null for non-existent ID but still clears cache": {
"pass": 5,
"fail": 0
},
"unpinMemory unpins the memory and clears the cache": {
"pass": 5,
"fail": 0
},
"unpinMemory returns null for non-existent ID but still clears cache": {
"pass": 5,
"fail": 0
},
"createLifecyclePlan respects delete safety constraints and logs reasons": {
"pass": 5,
"fail": 0
},
"createLifecyclePlan condenses near-duplicates and archives merged source records": {
"pass": 5,
"fail": 0
},
"applyLifecycleActions executes keep/archive/delete and merge markers": {
"pass": 5,
"fail": 0
},
"filterAndRankMemories applies metadata filters and composite score": {
"pass": 5,
"fail": 0
},
"formatMemoriesForPrompt returns prompt blocks and enforces token budget trimming": {
"pass": 5,
"fail": 0
},
"isMemoryRetrievalEnabled supports global toggle and agent canary list": {
"pass": 5,
"fail": 0
},
"renderPromptWithMemoryContext injects bounded memory block before base prompt": {
"pass": 5,
"fail": 0
},
"runPruneCycle respects off mode": {
"pass": 5,
"fail": 0
},
"runPruneCycle respects dry-run mode": {
"pass": 5,
"fail": 0
},
"runPruneCycle removes stale unpinned memories in active mode": {
"pass": 5,
"fail": 0
},
"runPruneCycle starts scheduler if requested": {
"pass": 5,
"fail": 0
},
"createDbAdvisoryLockProvider acquires and releases postgres advisory locks": {
"pass": 5,
"fail": 0
},
"startMemoryMaintenanceScheduler runs all jobs and emits metrics including retries": {
"pass": 5,
"fail": 0
},
"startMemoryMaintenanceScheduler skips jobs when feature flags disable memory": {
"pass": 5,
"fail": 0
},
"normalizeMemoryItem applies durable schema defaults and coercions": {
"pass": 5,
"fail": 0
},
"validateMemoryItem reports field-level errors": {
"pass": 5,
"fail": 0
},
"ingestEvents rejects invalid writes and logs structured validation details": {
"pass": 5,
"fail": 0
},
"memoryStats with empty repository returns zero counts and rates": {
"pass": 5,
"fail": 0
},
"memoryStats with populated repository returns correct counts and totals": {
"pass": 5,
"fail": 0
},
"memoryStats calculates ingest throughput based on window": {
"pass": 5,
"fail": 0
},
"memoryStats reflects deleted count from prune cycle": {
"pass": 5,
"fail": 0
},
"memoryStats handles windowMs parameter correctly": {
"pass": 5,
"fail": 0
},
"loadMemoryPromptTemplates loads all memory prompt templates from disk": {
"pass": 5,
"fail": 0
},
"summarizeEvents retries with repair prompt when first response is malformed JSON": {
"pass": 5,
"fail": 0
},
"summarizeEvents falls back to deterministic minimal summary with conservative importance when parsing fails twice": {
"pass": 5,
"fail": 0
},
"telemetry should not log to stdout or stderr by default": {
"pass": 5,
"fail": 0
},
"telemetry should log to stderr when NODE_DEBUG=torch-memory is set": {
"pass": 5,
"fail": 0
},
"schema validation covers required fields, coercion, and rejection paths": {
"pass": 5,
"fail": 0
},
"summarizer parser accepts valid json and recovers after malformed json response": {
"pass": 5,
"fail": 0
},
"ingest integration persists memory records and links embeddings from event batches": {
"pass": 5,
"fail": 0
},
"retrieval ranking blends semantic, importance, and recency signals": {
"pass": 5,
"fail": 0
},
"pruner policy protects pins, merges duplicates, and picks archive/delete outcomes": {
"pass": 5,
"fail": 0
},
"scheduler smoke test handles mocked clock and lock contention": {
"pass": 5,
"fail": 0
},
"CLI Smoke Test": {
"pass": 5,
"fail": 0
},
"ops.mjs: cmdInit creates .gitignore with node_modules": {
"pass": 5,
"fail": 0
},
"ops.mjs: cmdInit appends to existing .gitignore": {
"pass": 5,
"fail": 0
},
"cmdInit creates directory structure and files": {
"pass": 5,
"fail": 0
},
"cmdInit fails if directory exists without force": {
"pass": 5,
"fail": 0
},
"cmdUpdate preserves modified prompt": {
"pass": 5,
"fail": 0
},
"cmdUpdate overwrites prompt with force": {
"pass": 5,
"fail": 0
},
"cmdUpdate creates backup": {
"pass": 5,
"fail": 0
},
"torch-lock check respects local roster": {
"pass": 5,
"fail": 0
},
"cmdInit creates torch-config.json with random namespace": {
"pass": 5,
"fail": 0
},
"relay fanout quorum integration": {
"pass": 5,
"fail": 0
},
"RelayHealthManager": {
"pass": 5,
"fail": 0
},
"evaluateAlertThresholds": {
"pass": 5,
"fail": 0
},
"summarizeHistory - basic statistics calculation": {
"pass": 5,
"fail": 0
},
"summarizeHistory - handles empty history": {
"pass": 5,
"fail": 0
},
"summarizeHistory - respects time window for stats": {
"pass": 5,
"fail": 0
},
"summarizeHistory - allDownDurationMinutes considers outside window entries": {
"pass": 5,
"fail": 0
},
"summarizeHistory - allDownDurationMinutes is null if never healthy": {
"pass": 5,
"fail": 0
},
"summarizeHistory - allDownDurationMinutes is 0 if currently healthy": {
"pass": 5,
"fail": 0
},
"summarizeHistory - handles malformed entries gracefully": {
"pass": 5,
"fail": 0
},
"summarizeHistory - handles valid timestamp but missing summary": {
"pass": 5,
"fail": 0
},
"summarizeHistory - healthy entry with invalid timestamp results in NaN duration": {
"pass": 5,
"fail": 0
},
"Roster (Unit Tests with Dependency Injection)": {
"pass": 5,
"fail": 0
},
"fails required memory policy when retrieval/storage evidence is missing": {
"pass": 5,
"fail": 0
},
"accepts required memory policy when markers or artifacts are produced": {
"pass": 5,
"fail": 0
},
"records backend failure metadata when lock command exits with code 2": {
"pass": 5,
"fail": 0
},
"defers backend failures in non-strict mode and reuses idempotency key on successful retry": {
"pass": 5,
"fail": 0
},
"fails after exceeding non-strict deferral budget": {
"pass": 5,
"fail": 0
},
"strict lock mode fails immediately without deferral": {
"pass": 5,
"fail": 0
},
"skips lock health preflight by default when not enabled": {
"pass": 5,
"fail": 0
},
"fails scheduler with preflight metadata when lock health preflight is enabled": {
"pass": 5,
"fail": 0
},
"categorizes unreadable prompt files as prompt_parse_error": {
"pass": 5,
"fail": 0
},
"categorizes invalid prompt schema as prompt_schema_error": {
"pass": 5,
"fail": 0
},
"categorizes handoff runtime failures as execution_error": {
"pass": 5,
"fail": 0
},
"retries lock acquisition for backend error and succeeds on a later attempt": {
"pass": 5,
"fail": 0
},
"stops retrying after configured lock backend retries are exhausted": {
"pass": 5,
"fail": 0
},
"does not use backend retry flow for exit code 3 lock conflicts": {
"pass": 5,
"fail": 0
},
"retries handoff command for retryable network failures and succeeds": {
"pass": 5,
"fail": 0
},
"uses fallback platform for handoff when primary platform fails": {
"pass": 5,
"fail": 0
},
"fails before lock acquisition when runner health preflight command fails": {
"pass": 5,
"fail": 0
},
"uses exclusion payload from mixed JSON lock:check output": {
"pass": 5,
"fail": 0
},
"runs selected scheduler prompt through configured runner command": {
"pass": 5,
"fail": 0
},
"propagates non-zero runner exit code": {
"pass": 5,
"fail": 0
},
"scheduler lock backend failure artifact matches required frontmatter schema": {
"pass": 5,
"fail": 0
},
"schema contract catches missing required lock-backend field": {
"pass": 5,
"fail": 0
},
"schema contract catches misnamed lock-backend key": {
"pass": 5,
"fail": 0
},
"lock preflight e2e: successful lock writes completed status snapshot": {
"pass": 5,
"fail": 0
},
"lock preflight e2e: exit code 2 quorum failure persists failed backend status and prompt-not-started marker": {
"pass": 5,
"fail": 0
},
"lock preflight e2e: non-lock failure exits failed without prompt parse/schema classification": {
"pass": 5,
"fail": 0
},
"Scheduler Ratchet Logic (Log Checking)": {
"pass": 5,
"fail": 0
},
"Scheduler cycle ordering guarantees": {
"pass": 5,
"fail": 0
},
"parseDateValue": {
"pass": 5,
"fail": 0
},
"isStrictSchedulerLogFilename": {
"pass": 5,
"fail": 0
},
"parseAgentFromFilename": {
"pass": 5,
"fail": 0
},
"parseTimestampFromFilename": {
"pass": 5,
"fail": 0
},
"parseFrontmatterCreatedAt / parseFrontmatterAgent": {
"pass": 5,
"fail": 0
},
"buildRecentlyRunExclusionSet — scenarios": {
"pass": 5,
"fail": 0
},
"CADENCE_WINDOW_MS constants": {
"pass": 5,
"fail": 0
},
"secureRandom": {
"pass": 5,
"fail": 0
},
"summarizes recent lock reliability by platform/cadence/backend/relay": {
"pass": 5,
"fail": 0
},
"run-flaky-check reports pass/fail counts from TAP output files": {
"pass": 5,
"fail": 0
},
"loadTorchConfig (Unit Tests with Mocked FS)": {
"pass": 5,
"fail": 0
},
"torch-config": {
"pass": 5,
"fail": 0
},
"Async Utilities": {
"pass": 5,
"fail": 0
},
"Date Utilities": {
"pass": 5,
"fail": 0
},
"Relay Utilities": {
"pass": 5,
"fail": 0
},
"Platform Utilities": {
"pass": 5,
"fail": 0
},
"File Utilities": {
"pass": 5,
"fail": 0
},
"String Utilities": {
"pass": 5,
"fail": 0
},
"passes when artifacts include metadata and failure IDs map to unresolved known issue entries": {
"pass": 5,
"fail": 0
},
"fails when required metadata is missing from artifacts": {
"pass": 5,
"fail": 0
},
"fails when failure identifiers are not cross-linked to known issues or incidents": {
"pass": 5,
"fail": 0
}
}