audrey 1.0.0 → 1.0.2

package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md

@@ -24,13 +24,13 @@ These numbers measure Audrey's local call path under an in-process mock embeddin
 
 ## Behavioral Regression Result
 
-The current `benchmarks/output/summary.json` was generated on 2026-05-13T08:33:24.917Z with command `node benchmarks/run.js --provider mock --dimensions 64` (Ledger: E24). It reports:
+The current `benchmarks/output/summary.json` was generated on 2026-05-29T03:45:32.997Z with command `node benchmarks/run.js --provider mock --dimensions 64` (Ledger: E24). It reports:
 
 | System | Score Percent | Pass Rate | Average Duration Ms |
 |---|---:|---:|---:|
-| Audrey | 100 | 100 | 15.083333333333334 |
-| Vector Only | 41.66666666666667 | 25 | 0.25 |
-| Keyword + Recency | 41.66666666666667 | 25 | 0.5 |
+| Audrey | 100 | 100 | 15.416666666666666 |
+| Vector Only | 41.66666666666667 | 25 | 0.3333333333333333 |
+| Keyword + Recency | 41.66666666666667 | 25 | 0.6666666666666666 |
 | Recent Window | 37.5 | 25 | 0 |
 
 This output is a regression-gate result. The baselines are toy local baselines used to catch retrieval and lifecycle regressions in the Audrey codebase. They are not external systems, not tuned competitor implementations, and not GuardBench baselines (Ledger: E23-E24). The current suite covers retrieval and operation families such as information extraction, knowledge updates, multi-session reasoning, conflict resolution, procedural learning, privacy boundary, overwrite, delete-and-abstain, semantic merge, and procedural merge (Ledger: E23-E24).
@@ -55,7 +55,7 @@ It reports local adapters only, not external-system comparisons (Ledger: E46):
 | Evidence recall | 100% |
 | Redaction leaks | 0 |
 | Recall-degradation detection | 100% |
-| Guard latency p50 / p95 | 3.214 ms / 21.395 ms |
+| Guard latency p50 / p95 | 2.916 ms / 21.17 ms |
 | Published artifact raw-secret leaks | 0 |
 | Audrey Guard decision accuracy | 100% |
 | No-memory decision accuracy | 10% |

package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md

@@ -344,7 +344,7 @@ The deterministic demo, `audrey demo --scenario repeated-failure`, constructs a
 
 The current paper version has two implemented empirical anchors. First, `benchmarks/snapshots/perf-0.22.2.json` reports canonical local performance under the mock-provider methodology: generated on 2026-05-01 from git SHA `e2e821b`, using mock 64-dimensional in-process embeddings, hybrid recall limit 5, and corpus sizes 100, 1,000, and 5,000 on Node 25.5.0 with a 24-core Ryzen 9 7900X3D and 62.9 GB RAM (Ledger: E20). Under that methodology, hybrid recall p95 is 1.82 ms, 2.364 ms, and 3.417 ms for those three sizes, and encode p95 is 0.589 ms, 2.147 ms, and 1.838 ms (Ledger: E21-E22).
 
-Second, `bench:memory:check` is wired into the release gate and enforces retrieval/lifecycle benchmark guardrails against weak local baselines (Ledger: E23). The current checked-in output reports a 2026-05-08 mock-provider run in which Audrey scores 100% with 100% pass rate, while the strongest listed local baselines score 41.67% with 25% pass rate in that output (Ledger: E24). These numbers support regression-gate honesty; they do not replace GuardBench.
+Second, `bench:memory:check` is wired into the release gate as an **internal regression suite**, not a competitive benchmark. It exists to catch retrieval/lifecycle regressions in Audrey itself. The suite includes hand-tuned weak local baselines (vector-only, keyword-plus-recency, recent-window) whose role is to anchor a relative pass margin — they are not stand-ins for production memory systems, and their scores should not be cited as comparative claims about any external system (Ledger: E23). The current checked-in output reports a 2026-05-08 mock-provider run in which Audrey scores 100% with 100% pass rate and the listed local stub baselines score in the 25-42% range in that same run (Ledger: E24). These numbers support regression-gate honesty inside this repository; they are not cross-system results and they do not replace GuardBench.
 
 The README benchmark table currently differs from the canonical JSON snapshot, so the paper quotes only the JSON snapshot and tracks the README correction as a follow-up (Ledger: E28).
 
@@ -895,13 +895,13 @@ These numbers measure Audrey's local call path under an in-process mock embeddin
 
 ### Behavioral Regression Result
 
-The current `benchmarks/output/summary.json` was generated on 2026-05-13T08:33:24.917Z with command `node benchmarks/run.js --provider mock --dimensions 64` (Ledger: E24). It reports:
+The current `benchmarks/output/summary.json` was generated on 2026-05-29T03:45:32.997Z with command `node benchmarks/run.js --provider mock --dimensions 64` (Ledger: E24). It reports:
 
 | System | Score Percent | Pass Rate | Average Duration Ms |
 |---|---:|---:|---:|
-| Audrey | 100 | 100 | 15.083333333333334 |
-| Vector Only | 41.66666666666667 | 25 | 0.25 |
-| Keyword + Recency | 41.66666666666667 | 25 | 0.5 |
+| Audrey | 100 | 100 | 15.416666666666666 |
+| Vector Only | 41.66666666666667 | 25 | 0.3333333333333333 |
+| Keyword + Recency | 41.66666666666667 | 25 | 0.6666666666666666 |
 | Recent Window | 37.5 | 25 | 0 |
 
 This output is a regression-gate result. The baselines are toy local baselines used to catch retrieval and lifecycle regressions in the Audrey codebase. They are not external systems, not tuned competitor implementations, and not GuardBench baselines (Ledger: E23-E24). The current suite covers retrieval and operation families such as information extraction, knowledge updates, multi-session reasoning, conflict resolution, procedural learning, privacy boundary, overwrite, delete-and-abstain, semantic merge, and procedural merge (Ledger: E23-E24).
@@ -924,7 +924,7 @@ It reports local adapters only, not external-system comparisons (Ledger: E46):
 | Evidence recall | 100% |
 | Redaction leaks | 0 |
 | Recall-degradation detection | 100% |
-| Guard latency p50 / p95 | 3.214 ms / 21.395 ms |
+| Guard latency p50 / p95 | 2.916 ms / 21.17 ms |
 | Published artifact raw-secret leaks | 0 |
 | Audrey Guard decision accuracy | 100% |
 | No-memory decision accuracy | 10% |

package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md

@@ -49,7 +49,7 @@ Every implementation claim in the paper should point to one or more ledger IDs i
 | E43 - Audrey exposes a Claude Code hook generator, guarded settings apply path, and hook-mode Guard command: `hook-config claude-code` emits hooks, `hook-config claude-code --apply --scope project|user` merges them into Claude Code settings with backup/idempotence, `guard --hook --fail-on-warn` consumes PreToolUse JSON and returns `hookSpecificOutput.permissionDecision`, and `observe-tool` records post-tool events. Codex hook wiring remains pending on a stable host hook surface. | Hook integration boundary | README.md; mcp-server/index.ts; tests/mcp-server.test.js | Yes, focused Vitest and CLI hook smoke passed on 2026-05-12 |
 | E44 - Audrey preflight events now persist `preflight_evidence_ids` and `audrey_guard_action_key`; `memory_validate` accepts optional `preflight_event_id`, action key, and evidence ids, persists them on the validation audit event, and rejects validation lineage when the memory id was not evidence for that preflight. | Validation lineage implementation | src/action-key.ts; src/controller.ts; src/preflight.ts; src/audrey.ts; mcp-server/index.ts; tests/controller.test.js | Yes, focused Vitest passed on 2026-05-12 |
 | E45 - Preflight risk scoring uses a fixed severity map (`info=0.1`, `low=0.25`, `medium=0.55`, `high=0.85`), sorts warnings by severity, and strict mode blocks on high-severity warnings; the scoring path does not consume validation feedback. | Fixed risk scoring boundary | src/preflight.ts:6-60,291-299,332-338; src/feedback.ts:3-18,70-163 | Yes, 2026-05-08 |
-| E46 - `benchmarks/guardbench.js` runs ten local comparative GuardBench scenarios across Audrey Guard, no-memory, recent-window, vector-only, and FTS-only adapters and writes `benchmarks/output/guardbench-summary.json`, `benchmarks/output/guardbench-manifest.json`, and `benchmarks/output/guardbench-raw.json`; the latest local run has Audrey Guard passing 10/10 scenarios with 100% prevention rate, 0% false-block rate, 100% evidence recall, zero decision-output redaction leaks, zero published artifact raw-secret leaks, 100% recall-degradation detection, 100% decision accuracy, and 3.214ms/21.395ms p50/p95 guard latency under the mock-provider methodology. Baseline decision accuracy was no-memory 10%, recent-window 60%, vector-only 40%, and FTS-only 10%, with 0% full-contract pass rate for each baseline. | GuardBench local comparative results | benchmarks/guardbench.js; benchmarks/output/guardbench-summary.json; benchmarks/output/guardbench-manifest.json; benchmarks/output/guardbench-raw.json; package.json | Yes, `npm run bench:guard:check` passed on 2026-05-13 |
+| E46 - `benchmarks/guardbench.js` runs ten local comparative GuardBench scenarios across Audrey Guard, no-memory, recent-window, vector-only, and FTS-only adapters and writes `benchmarks/output/guardbench-summary.json`, `benchmarks/output/guardbench-manifest.json`, and `benchmarks/output/guardbench-raw.json`; the latest local run has Audrey Guard passing 10/10 scenarios with 100% prevention rate, 0% false-block rate, 100% evidence recall, zero decision-output redaction leaks, zero published artifact raw-secret leaks, 100% recall-degradation detection, 100% decision accuracy, and 2.916ms/21.17ms p50/p95 guard latency under the mock-provider methodology. Baseline decision accuracy was no-memory 10%, recent-window 60%, vector-only 40%, and FTS-only 10%, with 0% full-contract pass rate for each baseline. | GuardBench local comparative results | benchmarks/guardbench.js; benchmarks/output/guardbench-summary.json; benchmarks/output/guardbench-manifest.json; benchmarks/output/guardbench-raw.json; package.json | Yes, `npm run bench:guard:check` passed on 2026-05-13 |
 | E47 - GuardBench accepts external ESM adapters through `--adapter`, supports `default`, `adapter`, or `createGuardBenchAdapter()` exports, withholds `expectedDecision` and `requiredEvidence` during adapter execution, then scores adapter output against the same full-contract decision/evidence/redaction checks. | GuardBench external adapter contract | benchmarks/guardbench.js; tests/guardbench.test.js; package.json | Yes, `node scripts/run-vitest.mjs run tests/guardbench.test.js` passed on 2026-05-12 |
 | E48 - Audrey ships a Mem0 Platform GuardBench adapter that uses the current Mem0 REST shape: V3 async memory add with event polling, V2 filtered memory search, and user-entity cleanup. It requires runtime `MEM0_API_KEY` and is not run by default. | First external-system GuardBench adapter | benchmarks/adapters/mem0-platform.mjs; tests/guardbench.test.js; README.md | Import/contract and mocked REST-flow tests passed on 2026-05-12; live Mem0 run not yet executed |
 | E49 - GuardBench ships a credential-free example external adapter and a `bench:guard:adapter-smoke` script so the adapter loader can be exercised through the real CLI path without external credentials. | External adapter smoke path | benchmarks/adapters/example-allow.mjs; package.json; README.md; tests/guardbench.test.js | Yes, `npm run bench:guard:adapter-smoke` passed on 2026-05-12 |

package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json

@@ -1,11 +1,11 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "Audrey arXiv source package",
-  "generatedAt": "2026-05-13T23:33:56.985Z",
+  "generatedAt": "2026-05-29T03:45:42.097Z",
   "sourceMarkdown": "docs/paper/audrey-paper-v1.md",
   "publicationPack": "docs/paper/publication-pack.json",
   "sourceHashes": {
-    "sourceMarkdown": "3f9c807f0e0e82b0f19018b83900b62efecc17ff9bcee5b493a5d4fe0528ad7a",
+    "sourceMarkdown": "f2afc1cda24b1ba91cf39429e7836ead97c7a1c815b294b3d623bb20d8f5e7e6",
     "publicationPack": "a1a523d5938faea72be568b843ac3890e61cea6070b0cfa46acf22ad3d2fb974",
     "referencesBib": "c0bfcaf7bfe37d6933c812e46352be8a95397eaa430a0f5bc94037600a53f654"
   },
@@ -13,8 +13,8 @@
     {
       "path": "main.tex",
       "source": "docs/paper/audrey-paper-v1.md",
-      "bytes": 122247,
-      "sha256": "b0122e625380ad9a6aff78e2acbd5984b558c054962f8774f77fee70e6588d06"
+      "bytes": 122667,
+      "sha256": "e3ee98ea8c523e8f394b8fbbc73e206f0d6126b7349df5669206d4d48d9feea6"
     },
     {
       "path": "references.bib",

package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex

@@ -385,7 +385,7 @@ The deterministic demo, \texttt{audrey demo --scenario repeated-failure}, constr
 
 The current paper version has two implemented empirical anchors. First, \texttt{benchmarks/snapshots/perf-0.22.2.json} reports canonical local performance under the mock-provider methodology: generated on 2026-05-01 from git SHA \texttt{e2e821b}, using mock 64-dimensional in-process embeddings, hybrid recall limit 5, and corpus sizes 100, 1,000, and 5,000 on Node 25.5.0 with a 24-core Ryzen 9 7900X3D and 62.9 GB RAM (Ledger: E20). Under that methodology, hybrid recall p95 is 1.82 ms, 2.364 ms, and 3.417 ms for those three sizes, and encode p95 is 0.589 ms, 2.147 ms, and 1.838 ms (Ledger: E21-E22).
 
-Second, \texttt{bench:memory:check} is wired into the release gate and enforces retrieval/lifecycle benchmark guardrails against weak local baselines (Ledger: E23). The current checked-in output reports a 2026-05-08 mock-provider run in which Audrey scores 100\% with 100\% pass rate, while the strongest listed local baselines score 41.67\% with 25\% pass rate in that output (Ledger: E24). These numbers support regression-gate honesty; they do not replace GuardBench.
+Second, \texttt{bench:memory:check} is wired into the release gate as an **internal regression suite**, not a competitive benchmark. It exists to catch retrieval/lifecycle regressions in Audrey itself. The suite includes hand-tuned weak local baselines (vector-only, keyword-plus-recency, recent-window) whose role is to anchor a relative pass margin — they are not stand-ins for production memory systems, and their scores should not be cited as comparative claims about any external system (Ledger: E23). The current checked-in output reports a 2026-05-08 mock-provider run in which Audrey scores 100\% with 100\% pass rate and the listed local stub baselines score in the 25-42\% range in that same run (Ledger: E24). These numbers support regression-gate honesty inside this repository; they are not cross-system results and they do not replace GuardBench.
 
 The README benchmark table currently differs from the canonical JSON snapshot, so the paper quotes only the JSON snapshot and tracks the README correction as a follow-up (Ledger: E28).
 
@@ -729,13 +729,13 @@ These numbers measure Audrey's local call path under an in-process mock embeddin
 
 \subsection{Behavioral Regression Result}
 
-The current \texttt{benchmarks/output/summary.json} was generated on 2026-05-13T08:33:24.917Z with command \texttt{node benchmarks/run.js --provider mock --dimensions 64} (Ledger: E24). It reports:
+The current \texttt{benchmarks/output/summary.json} was generated on 2026-05-29T03:45:32.997Z with command \texttt{node benchmarks/run.js --provider mock --dimensions 64} (Ledger: E24). It reports:
 
 \begin{verbatim}
 | System | Score Percent | Pass Rate | Average Duration Ms |
-| Audrey | 100 | 100 | 15.083333333333334 |
-| Vector Only | 41.66666666666667 | 25 | 0.25 |
-| Keyword + Recency | 41.66666666666667 | 25 | 0.5 |
+| Audrey | 100 | 100 | 15.416666666666666 |
+| Vector Only | 41.66666666666667 | 25 | 0.3333333333333333 |
+| Keyword + Recency | 41.66666666666667 | 25 | 0.6666666666666666 |
 | Recent Window | 37.5 | 25 | 0 |
 \end{verbatim}
 
@@ -759,7 +759,7 @@ It reports local adapters only, not external-system comparisons (Ledger: E46):
 | Evidence recall | 100% |
 | Redaction leaks | 0 |
 | Recall-degradation detection | 100% |
-| Guard latency p50 / p95 | 3.214 ms / 21.395 ms |
+| Guard latency p50 / p95 | 2.916 ms / 21.17 ms |
 | Published artifact raw-secret leaks | 0 |
 | Audrey Guard decision accuracy | 100% |
 | No-memory decision accuracy | 10% |

package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json

@@ -1,13 +1,13 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "Audrey arXiv compile check",
-  "generatedAt": "2026-05-13T23:33:57.318Z",
+  "generatedAt": "2026-05-29T03:45:42.412Z",
   "source": {
     "sourceDir": "docs/paper/output/arxiv",
     "manifest": "docs/paper/output/arxiv/arxiv-manifest.json",
-    "manifestSha256": "386121a5f6234f56a370c5c54bde4ff12fc462921e7e5770d6968a4710271df8",
+    "manifestSha256": "6364c368755a4188d5b2deea9e3fe80201f5fa55658e6ae570141e54c5293bc6",
     "mainTex": "docs/paper/output/arxiv/main.tex",
-    "mainTexSha256": "b0122e625380ad9a6aff78e2acbd5984b558c054962f8774f77fee70e6588d06",
+    "mainTexSha256": "e3ee98ea8c523e8f394b8fbbc73e206f0d6126b7349df5669206d4d48d9feea6",
     "referencesBib": "docs/paper/output/arxiv/references.bib",
     "referencesBibSha256": "c0bfcaf7bfe37d6933c812e46352be8a95397eaa430a0f5bc94037600a53f654"
   },

package/docs/paper/output/submission-bundle/package.json

@@ -1,6 +1,6 @@
 {
   "name": "audrey",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "description": "Local-first memory runtime for AI agents with recall, consolidation, memory reflexes, contradiction detection, and tool-trace learning",
   "type": "module",
   "main": "dist/src/index.js",
@@ -71,10 +71,10 @@
     "pretest": "npm run build && npm run test:artifacts",
     "test": "node scripts/run-vitest.mjs",
     "test:watch": "node scripts/run-vitest.mjs watch",
-    "test:artifacts": "npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run paper:arxiv && npm run paper:arxiv:verify && npm run paper:arxiv:compile && npm run paper:bundle && npm run paper:bundle:verify",
-    "release:gate": "npm run typecheck && npm test && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run smoke:cli && npm run security:audit && npm run pack:check",
-    "release:gate:sandbox": "npm run build && npm run typecheck && npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run smoke:cli && npm run security:audit && npm run pack:check",
-    "release:gate:paper": "npm run build && npm run typecheck && npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run paper:sync && npm run paper:arxiv && npm run paper:arxiv:verify && npm run paper:arxiv:compile && npm run paper:launch-plan && npm run paper:launch-results && npm run paper:bundle && npm run paper:bundle:verify && npm run paper:verify && npm run release:readiness && npm run smoke:cli && npm run security:audit && npm run pack:check",
+    "test:artifacts": "npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run paper:sync && npm run paper:arxiv && npm run paper:arxiv:verify && npm run paper:arxiv:compile && npm run paper:bundle && npm run paper:bundle:verify && npm run paper:verify",
+    "release:gate": "npm run typecheck && npm run lint && npm run format:check && npm test && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run smoke:cli && npm run security:audit && npm run pack:check",
+    "release:gate:sandbox": "npm run build && npm run typecheck && npm run lint && npm run format:check && npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run smoke:cli && npm run security:audit && npm run pack:check",
+    "release:gate:paper": "npm run build && npm run typecheck && npm run lint && npm run format:check && npm run bench:perf && npm run bench:memory:check && npm run bench:guard:check && npm run bench:guard:card && npm run bench:guard:bundle && npm run bench:guard:bundle:verify && npm run bench:guard:leaderboard && npm run bench:guard:adapter-registry:validate && npm run bench:guard:external:dry-run && npm run bench:guard:external:evidence && npm run bench:guard:adapter-module:validate && npm run bench:guard:adapter-self-test && npm run bench:guard:adapter-self-test:validate && npm run bench:guard:validate && npm run bench:guard:publication:verify && npm run python:release:check && npm run paper:sync && npm run paper:arxiv && npm run paper:arxiv:verify && npm run paper:arxiv:compile && npm run paper:launch-plan && npm run paper:launch-results && npm run paper:bundle && npm run paper:bundle:verify && npm run paper:verify && npm run release:readiness && npm run smoke:cli && npm run security:audit && npm run pack:check",
     "release:cut:plan": "node scripts/prepare-release-cut.mjs --json",
     "release:cut:apply": "node scripts/prepare-release-cut.mjs --apply",
     "release:readiness": "node scripts/verify-release-readiness.mjs --allow-pending",
@@ -135,6 +135,10 @@
     "paper:sync": "node scripts/sync-paper-artifacts.mjs",
     "paper:verify": "node scripts/verify-paper-artifacts.mjs",
     "typecheck": "tsc --noEmit",
+    "lint": "eslint .",
+    "lint:fix": "eslint . --fix",
+    "format": "prettier --write \"src/**/*.ts\" \"mcp-server/**/*.ts\" \"tests/**/*.js\" \"benchmarks/**/*.{js,mjs}\" \"scripts/**/*.{js,mjs}\" \"examples/**/*.js\" \"*.{js,mjs}\" \".prettierrc.json\"",
+    "format:check": "prettier --check \"src/**/*.ts\" \"mcp-server/**/*.ts\" \"tests/**/*.js\" \"benchmarks/**/*.{js,mjs}\" \"scripts/**/*.{js,mjs}\" \"examples/**/*.js\" \"*.{js,mjs}\" \".prettierrc.json\"",
     "serve": "node dist/mcp-server/index.js serve",
     "docker:build": "docker build -t audrey:local .",
     "docker:up": "docker compose up -d --build",
@@ -200,11 +204,20 @@
     "zod": "^4.4.3"
   },
   "devDependencies": {
+    "@eslint/js": "^10.0.1",
     "@types/better-sqlite3": "^7.6.13",
     "@types/node": "^25.6.2",
+    "eslint": "^10.4.0",
+    "eslint-config-prettier": "^10.1.8",
+    "globals": "^17.6.0",
+    "prettier": "^3.8.3",
     "typescript": "^6.0.3",
+    "typescript-eslint": "^8.60.0",
     "vitest": "^4.1.5"
   },
+  "overrides": {
+    "qs": "^6.15.2"
+  },
   "directories": {
     "example": "examples",
     "test": "tests"

package/docs/paper/output/submission-bundle/paper-submission-manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "Audrey paper submission bundle",
-  "generatedAt": "2026-05-13T23:33:57.713Z",
+  "generatedAt": "2026-05-29T03:45:42.799Z",
   "sourceRoot": ".",
   "outDir": "docs/paper/output/submission-bundle",
   "claimVerification": {
@@ -17,33 +17,33 @@
     "scenarios": 10,
     "redactionLeaks": 0,
     "artifactLeaks": 0,
-    "latencyP50Ms": 3.097,
-    "latencyP95Ms": 29.711
+    "latencyP50Ms": 2.916,
+    "latencyP95Ms": 21.17
   },
   "files": [
     {
       "path": "benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json",
       "source": "benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json",
-      "bytes": 1261,
-      "sha256": "b9fa6d2343c56a8231c1f2d12330676ac760c7d7157d2479e5fbd345c09baacd"
+      "bytes": 1266,
+      "sha256": "5e17a9311141e22d1df5e86a802c29981d9bd6427de3ed3af00bee3d75f2011c"
     },
     {
       "path": "benchmarks/output/external/guardbench-external-dry-run.json",
       "source": "benchmarks/output/external/guardbench-external-dry-run.json",
       "bytes": 1831,
-      "sha256": "988dc23a7d4724bd76f7e1a01c89bf1c7708e38d24dcae0baafed5ea37e6aa20"
+      "sha256": "32eaacbacf59ad6046e442bae6ab72920806f8607a1439170203ef46b6f18d7c"
     },
     {
       "path": "benchmarks/output/external/guardbench-external-evidence.json",
       "source": "benchmarks/output/external/guardbench-external-evidence.json",
       "bytes": 1638,
-      "sha256": "685572d86fb30ac6a6249f0cd1b6a6058b10d6784d88a4a25e0fc17136637379"
+      "sha256": "617e4f00748b5c563a9c0a146b91712369854b6b00d4a72fe0375a37260966e8"
     },
     {
       "path": "benchmarks/output/guardbench-conformance-card.json",
       "source": "benchmarks/output/guardbench-conformance-card.json",
-      "bytes": 1735,
-      "sha256": "0709bb4d93a797764e4ed5655c575390a57554a42625398d378c8ec0f23bd2b4"
+      "bytes": 1733,
+      "sha256": "a32ce0a46b2f031e827caa0896fdd6a870acf92f6bccb481ca661a3ea4b74a79"
     },
     {
       "path": "benchmarks/output/guardbench-manifest.json",
@@ -54,44 +54,44 @@
     {
       "path": "benchmarks/output/guardbench-raw.json",
       "source": "benchmarks/output/guardbench-raw.json",
-      "bytes": 39429,
-      "sha256": "c5b9c68cf946478fbfba617f17717e05ea3e01301089de19153d59e77e674bc6"
+      "bytes": 43407,
+      "sha256": "15b39fd1a65709a89455fbfcaf815daf364b204fa526d5065cc12fcaed281d28"
     },
     {
       "path": "benchmarks/output/guardbench-summary.json",
       "source": "benchmarks/output/guardbench-summary.json",
-      "bytes": 64381,
-      "sha256": "2a6d5ee83cce2502135fb0442ef8cd3f2679fdc38c84207612c22a800a7a113a"
+      "bytes": 69260,
+      "sha256": "e8669cd6c80dc3dc849b3c4fcc473ea706eb3a760bced69682d0dc2396b2e233"
     },
     {
       "path": "benchmarks/output/leaderboard/guardbench-leaderboard.json",
       "source": "benchmarks/output/leaderboard/guardbench-leaderboard.json",
-      "bytes": 2798,
-      "sha256": "55c6fabf3e4ccf399650aadf7d34e83d4bcdd5cfe26439e3d50a7cf9dac0ec66"
+      "bytes": 2796,
+      "sha256": "4468365e70f156f01e202721644f5e6d273b8482bc740e15b484484acde33ef9"
     },
     {
       "path": "benchmarks/output/leaderboard/guardbench-leaderboard.md",
       "source": "benchmarks/output/leaderboard/guardbench-leaderboard.md",
-      "bytes": 364,
-      "sha256": "d04ac3106b4b4d5563b9cdddb1f5816ff62ad0636836d29f8b91af1d80755458"
+      "bytes": 363,
+      "sha256": "e492fd96572fa8b2464357aad7b3f3c7e321ad42a11a18b9a343b23b349fc4be"
     },
     {
       "path": "benchmarks/output/submission-bundle/submission-manifest.json",
       "source": "benchmarks/output/submission-bundle/submission-manifest.json",
-      "bytes": 3986,
-      "sha256": "2c37a32eab5dba72b197971ed7a63173d7a395d0e65707a5490a7a868b332c6f"
+      "bytes": 3984,
+      "sha256": "cc43138aef6db9998079d5b7b638861af497f43e737f731f52fc0fd4abd00da8"
     },
     {
       "path": "benchmarks/output/submission-bundle/validation-report.json",
       "source": "benchmarks/output/submission-bundle/validation-report.json",
       "bytes": 739,
-      "sha256": "9734a26b31a7511fbba361f22245dd6325b65fe47d1072fa59df7eeb15d724a1"
+      "sha256": "6f6c385d8db108b1a5e30de389a1131bece70ccb18c552a5f005f7dbe377d695"
     },
     {
       "path": "benchmarks/output/summary.json",
       "source": "benchmarks/output/summary.json",
-      "bytes": 100749,
-      "sha256": "75d778ce194cf9122b3e58bd361b2e15ecc5c1597aa62c060f567011af73963e"
+      "bytes": 100748,
+      "sha256": "8ad41efec05b0f099a818e64fd191707be5bf6317d41fc353869df10c18918c7"
     },
     {
       "path": "benchmarks/schemas/guardbench-adapter-registry.schema.json",
@@ -150,8 +150,8 @@
     {
       "path": "benchmarks/schemas/guardbench-raw.schema.json",
       "source": "benchmarks/schemas/guardbench-raw.schema.json",
-      "bytes": 5057,
-      "sha256": "f419685932a5549d5efef611b1dbbe585300365de3c977fcfedf174672f6bc3a"
+      "bytes": 5653,
+      "sha256": "2893204554696b69e4e1478f0d147cb95603b5f698ff112ebe9de45904b44045"
     },
     {
       "path": "benchmarks/schemas/guardbench-submission-manifest.schema.json",
@@ -162,8 +162,8 @@
     {
       "path": "benchmarks/schemas/guardbench-summary.schema.json",
       "source": "benchmarks/schemas/guardbench-summary.schema.json",
-      "bytes": 7331,
-      "sha256": "ac70b448c730fb8b01899615477a167a64734d16304c39d661b2b3130e8aa1da"
+      "bytes": 8004,
+      "sha256": "2545b83cdd1d5d5d9abd535950779b5bbf3e5a2b04c3a36c35c2bbacc5efd9d9"
     },
     {
       "path": "docs/AUDREY_PAPER_OUTLINE.md",
@@ -216,8 +216,8 @@
     {
       "path": "docs/paper/07-evaluation.md",
       "source": "docs/paper/07-evaluation.md",
-      "bytes": 11240,
-      "sha256": "8062c2f8b2a50af7d921a0358db85f9e65bee742f4c8e2244cadb8756c4fe703"
+      "bytes": 11268,
+      "sha256": "4e712ef36a936df5034c67aff5c0167013aeb0b843067b6499ab7f47c2cb39e7"
     },
     {
       "path": "docs/paper/08-discussion-limitations.md",
@@ -252,8 +252,8 @@
     {
       "path": "docs/paper/audrey-paper-v1.md",
       "source": "docs/paper/audrey-paper-v1.md",
-      "bytes": 116195,
-      "sha256": "3f9c807f0e0e82b0f19018b83900b62efecc17ff9bcee5b493a5d4fe0528ad7a"
+      "bytes": 116616,
+      "sha256": "f2afc1cda24b1ba91cf39429e7836ead97c7a1c815b294b3d623bb20d8f5e7e6"
     },
     {
       "path": "docs/paper/browser-launch-plan.json",
@@ -294,26 +294,26 @@
     {
       "path": "docs/paper/evidence-ledger.md",
       "source": "docs/paper/evidence-ledger.md",
-      "bytes": 61844,
-      "sha256": "2a376be83b65df3a7038ddbd684e809d538ef35cbe34d91eb309773502bb5920"
+      "bytes": 61843,
+      "sha256": "3dbf5d3b80937b468da063df7b884ba2d8a0d1e52d2c0d27a3a60f287cfdd9a2"
     },
     {
       "path": "docs/paper/output/arxiv-compile-report.json",
       "source": "docs/paper/output/arxiv-compile-report.json",
       "bytes": 924,
-      "sha256": "11018bea60272ce8467675cf6491e9a7dbfeb3a774ee502dd1adc8ba5d3b1112"
+      "sha256": "245aef38f5f4edca073731ed0c35560a7a3f67b0be52571e0bee172d155d7b99"
     },
     {
       "path": "docs/paper/output/arxiv/arxiv-manifest.json",
       "source": "docs/paper/output/arxiv/arxiv-manifest.json",
       "bytes": 1316,
-      "sha256": "386121a5f6234f56a370c5c54bde4ff12fc462921e7e5770d6968a4710271df8"
+      "sha256": "6364c368755a4188d5b2deea9e3fe80201f5fa55658e6ae570141e54c5293bc6"
     },
     {
       "path": "docs/paper/output/arxiv/main.tex",
       "source": "docs/paper/output/arxiv/main.tex",
-      "bytes": 122247,
-      "sha256": "b0122e625380ad9a6aff78e2acbd5984b558c054962f8774f77fee70e6588d06"
+      "bytes": 122667,
+      "sha256": "e3ee98ea8c523e8f394b8fbbc73e206f0d6126b7349df5669206d4d48d9feea6"
     },
     {
       "path": "docs/paper/output/arxiv/README-arxiv.txt",
@@ -366,14 +366,14 @@
     {
       "path": "package.json",
       "source": "package.json",
-      "bytes": 11668,
-      "sha256": "0892c9cdc5bab8f5036a12ef3cad5eb0b509eea86813f5d49cda29f6d38653c2"
+      "bytes": 12529,
+      "sha256": "08eed72a235182d32ee495c7fea7f98d5641d855ef387f36f8a57adfbd10eb4e"
     },
     {
       "path": "README.md",
       "source": "README.md",
-      "bytes": 24693,
-      "sha256": "f7c5ac813046ad9f3def5fea67bbae8f1f817b38201d57f9a3565b04470681c6"
+      "bytes": 26368,
+      "sha256": "4a0c524c65557c042f1752d29c668dfa3656fba6c53be335e50adefc8e9d3597"
     }
   ]
 }

package/examples/fintech-ops-demo.js

@@ -11,7 +11,8 @@ async function demo() {
 
   console.log('--- Encoding payment-operations incidents ---');
   await brain.encode({
-    content: 'Processor X returned HTTP 429 when payout retries exceeded 120 requests per minute for marketplace merchants.',
+    content:
+      'Processor X returned HTTP 429 when payout retries exceeded 120 requests per minute for marketplace merchants.',
     source: 'direct-observation',
     salience: 0.9,
     tags: ['payments', 'payouts', 'rate-limit'],
@@ -19,7 +20,8 @@ async function demo() {
   });
 
   await brain.encode({
-    content: 'On-call notes show payout incident volume drops after retry batches are capped at 50 merchants per worker.',
+    content:
+      'On-call notes show payout incident volume drops after retry batches are capped at 50 merchants per worker.',
     source: 'tool-result',
     salience: 0.8,
     tags: ['payments', 'payouts', 'ops'],
@@ -27,7 +29,8 @@ async function demo() {
   });
 
   await brain.encode({
-    content: 'Risk operations requested automatic escalation when payout failures affect more than three merchants in the same hour.',
+    content:
+      'Risk operations requested automatic escalation when payout failures affect more than three merchants in the same hour.',
     source: 'told-by-user',
     salience: 0.7,
     tags: ['payments', 'escalation', 'risk'],
@@ -39,9 +42,13 @@ async function demo() {
     minClusterSize: 3,
     similarityThreshold: -0.3,
     extractPrinciple: () => ({
-      content: 'When payout retries spike, cap retry batches and escalate once multiple merchants are affected in the same hour.',
+      content:
+        'When payout retries spike, cap retry batches and escalate once multiple merchants are affected in the same hour.',
       type: 'procedural',
-      conditions: ['payout failures > 3 merchants per hour', 'processor returns 429 or throttling errors'],
+      conditions: [
+        'payout failures > 3 merchants per hour',
+        'processor returns 429 or throttling errors',
+      ],
     }),
   });
 

package/examples/healthcare-ops-demo.js

@@ -11,7 +11,8 @@ async function demo() {
 
   console.log('--- Encoding care-coordination observations ---');
   await brain.encode({
-    content: 'Referral queue delays drop when missing imaging notes are requested before prior-authorization submission.',
+    content:
+      'Referral queue delays drop when missing imaging notes are requested before prior-authorization submission.',
     source: 'direct-observation',
     salience: 0.9,
     tags: ['healthcare-ops', 'prior-auth', 'referrals'],
@@ -19,7 +20,8 @@ async function demo() {
   });
 
   await brain.encode({
-    content: 'Scheduling team reports the highest callback completion rate between 4pm and 6pm for discharge follow-up.',
+    content:
+      'Scheduling team reports the highest callback completion rate between 4pm and 6pm for discharge follow-up.',
     source: 'tool-result',
     salience: 0.8,
     tags: ['healthcare-ops', 'follow-up', 'scheduling'],
@@ -27,7 +29,8 @@ async function demo() {
   });
 
   await brain.encode({
-    content: 'Care coordinators want interpreter requirements captured in every handoff note before outreach starts.',
+    content:
+      'Care coordinators want interpreter requirements captured in every handoff note before outreach starts.',
     source: 'told-by-user',
     salience: 0.7,
     tags: ['healthcare-ops', 'handoff', 'interpreter'],
@@ -39,7 +42,8 @@ async function demo() {
     minClusterSize: 3,
     similarityThreshold: -0.3,
     extractPrinciple: () => ({
-      content: 'For care-coordination workflows, collect missing documentation and communication preferences before outreach or prior-auth submission.',
+      content:
+        'For care-coordination workflows, collect missing documentation and communication preferences before outreach or prior-auth submission.',
       type: 'procedural',
       conditions: ['prior-auth missing documentation', 'handoff note lacks outreach constraints'],
     }),