Cleanup repo structure and consolidate tests

- Consolidated `tests/` into `test/`
- Moved `test-audit/` scripts to `scripts/test-audit/`
- Updated audit scripts to support configurable output directory
- Removed root clutter (`test_output.txt`)
- Updated documentation and agent prompts

Co-authored-by: PR0M3TH3AN <[email protected]>

AGENTS.md

@@ -125,6 +125,7 @@ Agents must keep the repository root clean. Do not create log files, temporary o
 *   **Test Logs**: `test_logs/` (e.g., `test_logs/test_output_full.txt`).
 *   **Task Logs**: `task-logs/` (e.g., `task-logs/daily/`).
 *   **Artifacts**: `artifacts/` (for raw data, repros, or other artifacts).
+*   **Scripts**: `scripts/` (e.g., `scripts/test-audit/`).
 *   **General Logs**: `logs/` (if needed, otherwise `task-logs/`).
 
 **Prohibitions:**

package.json

@@ -21,6 +21,7 @@
     "src/docs/",
     "scripts/check-file-size.mjs",
     "scripts/check-innerhtml.mjs",
+    "scripts/test-audit/",
     "scripts/memory/",
     "skills/",
     "dashboard/",
@@ -30,7 +31,7 @@
     "TORCH.md"
   ],
   "scripts": {
-    "test": "npm run validate:scheduler && npm run test:integration:e2e && node --test test/*.test.mjs tests/*.test.js",
+    "test": "npm run validate:scheduler && npm run test:integration:e2e && node --test test/*.test.mjs test/*.test.js",
     "test:unit:lock-backend": "node --test test/lock-ops.test.mjs test/lock-ops-publish-retry.test.mjs",
     "lock:check:daily": "node bin/torch-lock.mjs check --cadence daily",
     "lock:check:weekly": "node bin/torch-lock.mjs check --cadence weekly",

reports/test-audit/flakiness-matrix.json

@@ -1,4 +1,16 @@
 {
+  "scripts/agent/load-test.mjs": {
+    "pass": 0,
+    "fail": 5
+  },
+  "scripts/agent/smoke-test.mjs": {
+    "pass": 0,
+    "fail": 5
+  },
+  "Build artifacts verification": {
+    "pass": 5,
+    "fail": 0
+  },
   "parseArgs should parse basic command": {
     "pass": 5,
     "fail": 0
@@ -35,6 +47,38 @@
     "pass": 5,
     "fail": 0
   },
+  "cmdList": {
+    "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
+  },
+  "test/fixtures/memory-fixtures.js": {
+    "pass": 5,
+    "fail": 0
+  },
+  "cmdInit should validate install directory name": {
+    "pass": 5,
+    "fail": 0
+  },
   "src/lib.mjs": {
     "pass": 5,
     "fail": 0
@@ -51,6 +95,10 @@
     "pass": 5,
     "fail": 0
   },
+  "lock-utils": {
+    "pass": 5,
+    "fail": 0
+  },
   "listMemories, inspectMemory, pinMemory, and unpinMemory support admin hooks": {
     "pass": 5,
     "fail": 0
@@ -67,6 +115,10 @@
     "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
@@ -99,6 +151,106 @@
     "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
@@ -107,6 +259,22 @@
     "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
@@ -135,6 +303,22 @@
     "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
@@ -159,6 +343,26 @@
     "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
@@ -171,6 +375,38 @@
     "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
@@ -207,11 +443,51 @@
     "pass": 5,
     "fail": 0
   },
-  "raises all-relays-down duration alert after threshold": {
+  "RelayHealthManager": {
     "pass": 5,
     "fail": 0
   },
-  "raises success-rate alert when rolling health falls below threshold": {
+  "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
   },
@@ -311,6 +587,10 @@
     "pass": 5,
     "fail": 0
   },
+  "secureRandom": {
+    "pass": 5,
+    "fail": 0
+  },
   "summarizes recent lock reliability by platform/cadence/backend/relay": {
     "pass": 5,
     "fail": 0
@@ -327,6 +607,10 @@
     "pass": 5,
     "fail": 0
   },
+  "File Utilities": {
+    "pass": 5,
+    "fail": 0
+  },
   "passes when artifacts include metadata and failure IDs map to unresolved known issue entries": {
     "pass": 5,
     "fail": 0
@@ -338,29 +622,5 @@
   "fails when failure identifiers are not cross-linked to known issues or incidents": {
     "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
   }
 }

reports/test-audit/suspicious-tests.json

@@ -1,4 +1,10 @@
 [
+  {
+    "file": "test/fixtures/memory-fixtures.js",
+    "issues": [
+      "No obvious assertions"
+    ]
+  },
   {
     "file": "test/memory-cache.test.mjs",
     "issues": [
@@ -6,7 +12,7 @@
     ]
   },
   {
-    "file": "test/memory-scheduler.test.mjs",
+    "file": "test/memory.test.js",
     "issues": [
       "Found setTimeout()"
     ]
@@ -16,17 +22,5 @@
     "issues": [
       "Found setTimeout()"
     ]
-  },
-  {
-    "file": "tests/fixtures/memory-fixtures.js",
-    "issues": [
-      "No obvious assertions"
-    ]
-  },
-  {
-    "file": "tests/memory.test.js",
-    "issues": [
-      "Found setTimeout()"
-    ]
   }
 ]

scripts/test-audit/run-flaky-check.mjs

@@ -1,13 +1,29 @@
 import { spawn } from 'node:child_process';
-import { writeFileSync } from 'node:fs';
+import { writeFileSync, mkdirSync } from 'node:fs';
+import { join } from 'node:path';
 
 const RUNS = 5;
 const results = {};
 
+// Parse arguments to separate our flags from test runner args
+const args = process.argv.slice(2);
+let outputDir = 'reports/test-audit';
+const testArgs = [];
+
+for (let i = 0; i < args.length; i++) {
+  if (args[i] === '--output-dir') {
+    outputDir = args[i + 1];
+    i++; // Skip next arg
+  } else {
+    testArgs.push(args[i]);
+  }
+}
+
 async function runTests(i) {
   console.log(`Run ${i + 1}/${RUNS}...`);
   return new Promise((resolve) => {
-    const child = spawn('node', ['--test', ...process.argv.slice(2)], {
+    // Pass strictly the test args to the child process
+    const child = spawn('node', ['--test', ...testArgs], {
       stdio: ['ignore', 'pipe', 'pipe']
     });
 
@@ -38,8 +54,12 @@ async function main() {
     await runTests(i);
   }
 
-  writeFileSync('test-audit/flakiness-matrix.json', JSON.stringify(results, null, 2));
+  // Ensure output directory exists
-  console.log('Flakiness matrix written.');
+  mkdirSync(outputDir, { recursive: true });
+
+  const outputPath = join(outputDir, 'flakiness-matrix.json');
+  writeFileSync(outputPath, JSON.stringify(results, null, 2));
+  console.log(`Flakiness matrix written to ${outputPath}.`);
 }
 
 main();

scripts/test-audit/run-static-analysis.mjs

@@ -1,4 +1,4 @@
-import { readFileSync, writeFileSync, readdirSync, statSync } from 'node:fs';
+import { readFileSync, writeFileSync, readdirSync, statSync, mkdirSync } from 'node:fs';
 import { join } from 'node:path';
 
 function getFiles(dir, files = []) {
@@ -18,7 +18,19 @@ function getFiles(dir, files = []) {
   return files;
 }
 
-const testFiles = [...getFiles('test'), ...getFiles('tests')];
+// Parse arguments
+const args = process.argv.slice(2);
+let outputDir = 'reports/test-audit';
+
+for (let i = 0; i < args.length; i++) {
+  if (args[i] === '--output-dir') {
+    outputDir = args[i + 1];
+    i++;
+  }
+}
+
+// Only scan test/ directory now, as tests/ was consolidated
+const testFiles = [...getFiles('test')];
 const suspicious = [];
 
 for (const file of testFiles) {
@@ -45,5 +57,10 @@ for (const file of testFiles) {
   }
 }
 
-writeFileSync('test-audit/suspicious-tests.json', JSON.stringify(suspicious, null, 2));
+// Ensure output directory exists
+mkdirSync(outputDir, { recursive: true });
+
+const outputPath = join(outputDir, 'suspicious-tests.json');
+writeFileSync(outputPath, JSON.stringify(suspicious, null, 2));
 console.log(`Found ${suspicious.length} suspicious files.`);
+console.log(`Report written to ${outputPath}.`);

src/prompts/daily/test-audit-agent.md

@@ -22,6 +22,8 @@ CONSTITUTION (non-negotiable):
 MISSION:
 1) Inspect repo to discover test runners, CI entry points, and existing test layers.
 2) Audit tests for: behavior fidelity, determinism, and cheat vectors.
+   - Use provided audit tools in `scripts/test-audit/` (e.g., `run-flaky-check.mjs`, `run-static-analysis.mjs`) to identify flaky or suspicious tests.
+   - Ensure all tool outputs and reports are saved to `reports/test-audit/`.
 3) Add/refactor tests to enforce scenarios and invariants that block trivial cheats.
 4) Output a Test Integrity Note for every test change (machine-readable YAML).
 

test-audit/coverage-run.log

@@ -1,151 +0,0 @@
-TAP version 13
-# Subtest: parseArgs should parse basic command
-ok 1 - parseArgs should parse basic command
-  ---
-  duration_ms: 2.074523
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse agent and cadence
-ok 2 - parseArgs should parse agent and cadence
-  ---
-  duration_ms: 0.373647
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse equals sign syntax
-ok 3 - parseArgs should parse equals sign syntax
-  ---
-  duration_ms: 0.204255
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse dry-run flag
-ok 4 - parseArgs should parse dry-run flag
-  ---
-  duration_ms: 0.16969
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse port with default
-ok 5 - parseArgs should parse port with default
-  ---
-  duration_ms: 0.170406
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse custom port
-ok 6 - parseArgs should parse custom port
-  ---
-  duration_ms: 0.211104
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse ignore-logs flag
-ok 7 - parseArgs should parse ignore-logs flag
-  ---
-  duration_ms: 0.273681
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse memory flags
-ok 8 - parseArgs should parse memory flags
-  ---
-  duration_ms: 5.033281
-  type: 'test'
-  ...
-# Subtest: parseArgs should parse memory flags with equals
-ok 9 - parseArgs should parse memory flags with equals
-  ---
-  duration_ms: 0.269666
-  type: 'test'
-  ...
-1..9
-# tests 9
-# suites 0
-# pass 9
-# fail 0
-# cancelled 0
-# skipped 0
-# todo 0
-# duration_ms 32.484347
-# start of coverage report
-# ---------------------------------------------------------------------
-# file                 | line % | branch % | funcs % | uncovered lines
-# ---------------------------------------------------------------------
-# src                  |        |          |         |
-#  cli-parser.mjs      |  76.99 |    85.71 |  100.00 | 52 56 86-109
-#  constants.mjs       | 100.00 |   100.00 |  100.00 |
-# test                 |        |          |         |
-#  cli-parser.test.mjs | 100.00 |   100.00 |  100.00 |
-# ---------------------------------------------------------------------
-# all files            |  87.50 |    88.33 |  100.00 |
-# ---------------------------------------------------------------------
-# end of coverage report
-TAP version 13
-# node:internal/modules/cjs/loader:1386
-#   throw err;
-#   ^
-# Error: Cannot find module '/app/test'
-#     at Function._resolveFilename (node:internal/modules/cjs/loader:1383:15)
-#     at defaultResolveImpl (node:internal/modules/cjs/loader:1025:19)
-#     at resolveForCJSWithHooks (node:internal/modules/cjs/loader:1030:22)
-#     at Function._load (node:internal/modules/cjs/loader:1192:37)
-#     at TracingChannel.traceSync (node:diagnostics_channel:328:14)
-#     at wrapModuleLoad (node:internal/modules/cjs/loader:237:24)
-#     at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:171:5)
-#     at node:internal/main/run_main_module:36:49 {
-#   code: 'MODULE_NOT_FOUND',
-#   requireStack: []
-# }
-# Node.js v22.22.0
-# Subtest: test
-not ok 1 - test
-  ---
-  duration_ms: 51.535733
-  type: 'test'
-  location: '/app/test:1:1'
-  failureType: 'testCodeFailure'
-  exitCode: 1
-  signal: ~
-  error: 'test failed'
-  code: 'ERR_TEST_FAILURE'
-  ...
-# node:internal/modules/cjs/loader:1386
-#   throw err;
-#   ^
-# Error: Cannot find module '/app/tests'
-#     at Function._resolveFilename (node:internal/modules/cjs/loader:1383:15)
-#     at defaultResolveImpl (node:internal/modules/cjs/loader:1025:19)
-#     at resolveForCJSWithHooks (node:internal/modules/cjs/loader:1030:22)
-#     at Function._load (node:internal/modules/cjs/loader:1192:37)
-#     at TracingChannel.traceSync (node:diagnostics_channel:328:14)
-#     at wrapModuleLoad (node:internal/modules/cjs/loader:237:24)
-#     at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:171:5)
-#     at node:internal/main/run_main_module:36:49 {
-#   code: 'MODULE_NOT_FOUND',
-#   requireStack: []
-# }
-# Node.js v22.22.0
-# Subtest: tests
-not ok 2 - tests
-  ---
-  duration_ms: 50.740646
-  type: 'test'
-  location: '/app/tests:1:1'
-  failureType: 'testCodeFailure'
-  exitCode: 1
-  signal: ~
-  error: 'test failed'
-  code: 'ERR_TEST_FAILURE'
-  ...
-1..2
-# tests 2
-# suites 0
-# pass 0
-# fail 2
-# cancelled 0
-# skipped 0
-# todo 0
-# duration_ms 66.495879
-# start of coverage report
-# ----------------------------------------------------------
-# file      | line % | branch % | funcs % | uncovered lines
-# ----------------------------------------------------------
-# ----------------------------------------------------------
-# all files | 100.00 |   100.00 |  100.00 |
-# ----------------------------------------------------------
-# end of coverage report