audrey 1.1.2 → 1.1.3

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 1.1 ships one normalized lifecycle adapter and host-specific configuration for current Claude Code and Codex CLIs. `audrey install --host auto` registers MCP and applies hooks for detected hosts from stable executable paths. `hook-config` supports preview, scoped apply, private backups, and idempotent Audrey-handler replacement; `uninstall` supports non-mutating preview and removes Audrey-owned registrations and handlers in the selected scope. Session and prompt hooks inject bounded, agent-scoped context; PreToolUse creates Guard receipts; post-tool events correlate outcomes by `session_id + tool_use_id`; sanitized failures may form durable memories; Stop and PostCompact run due-only maintenance. Codex requires explicit non-managed hook trust through `/hooks`. Hook errors fail open unless `AUDREY_HOOK_FAIL_CLOSED=1`. Coverage remains limited to events and tool paths emitted by the host, and each hook starts a short-lived Audrey process rather than using a persistent daemon. | Automatic lifecycle integration and boundary | README.md; CHANGELOG.md; mcp-server/hooks.ts; mcp-server/index.ts; src/autopilot.ts; tests/autopilot.test.js; tests/hooks-config.test.js; tests/mcp-server.test.js | Yes, build plus 191 focused install, hook, Autopilot, preflight, controller, and HTTP tests passed on 2026-07-10 |
 | 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. Preflight embedding queries are bounded, while exact action identity hashes the full normalized, redacted action so large inputs with a shared prefix do not collide. | 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 2026-07-10, including a large-action prefix-collision regression |
 | 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 4.253ms/21.196ms 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 4.607ms/21.585ms 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": "2026-07-13T14:48:55.293Z",
+  "generatedAt": "2026-07-13T15:07:37.754Z",
   "sourceMarkdown": "docs/paper/audrey-paper-v1.md",
   "publicationPack": "docs/paper/publication-pack.json",
   "sourceHashes": {
-    "sourceMarkdown": "7db503c10b25314daa46e31fc65c98d18cd86895fe7bf44501e108626c4a3cac",
+    "sourceMarkdown": "de42ec49d0be877b824288959d0ac48d13f78ac571aa93acb7cc288f931d20f6",
     "publicationPack": "a1a523d5938faea72be568b843ac3890e61cea6070b0cfa46acf22ad3d2fb974",
     "referencesBib": "c0bfcaf7bfe37d6933c812e46352be8a95397eaa430a0f5bc94037600a53f654"
   },
@@ -13,8 +13,8 @@
     {
       "path": "main.tex",
       "source": "docs/paper/audrey-paper-v1.md",
-      "bytes": 124825,
-      "sha256": "d9d0cf25cad4e59d6234643eb875bd5d74b4d45acd106e9bc01c7454e7240622"
+      "bytes": 124842,
+      "sha256": "0e122e6bd050e3fbf8e62ab3b363b12ebb00c7c8a4618b9fa4971d19e798bcc7"
     },
     {
       "path": "references.bib",

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

@@ -731,14 +731,14 @@ 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 2026-07-13T14:48:45.265Z 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 2026-07-13T15:07:26.566Z 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 | 16.583333333333332 |
-| Vector Only | 41.66666666666667 | 25 | 0.16666666666666666 |
-| Keyword + Recency | 41.66666666666667 | 25 | 0.75 |
-| Recent Window | 37.5 | 25 | 0 |
+| Audrey | 100 | 100 | 19.333333333333332 |
+| Vector Only | 41.66666666666667 | 25 | 0.25 |
+| Keyword + Recency | 41.66666666666667 | 25 | 0.5833333333333334 |
+| Recent Window | 37.5 | 25 | 0.08333333333333333 |
 \end{verbatim}
 
 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).
@@ -761,7 +761,7 @@ 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 | 4.253 ms / 21.196 ms |
+| Guard latency p50 / p95 | 4.607 ms / 21.585 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": "2026-07-13T14:48:57.090Z",
+  "generatedAt": "2026-07-13T15:07:39.643Z",
   "source": {
     "sourceDir": "docs/paper/output/arxiv",
     "manifest": "docs/paper/output/arxiv/arxiv-manifest.json",
-    "manifestSha256": "de555f986f650735f8b4184eb93504b20d94dbd1e8510d839311fbf7e7d69429",
+    "manifestSha256": "d91eaefbca39c49e79990ef58314bbaa502184dae14596a498c2b6d8ba2f7df2",
     "mainTex": "docs/paper/output/arxiv/main.tex",
-    "mainTexSha256": "d9d0cf25cad4e59d6234643eb875bd5d74b4d45acd106e9bc01c7454e7240622",
+    "mainTexSha256": "0e122e6bd050e3fbf8e62ab3b363b12ebb00c7c8a4618b9fa4971d19e798bcc7",
     "referencesBib": "docs/paper/output/arxiv/references.bib",
     "referencesBibSha256": "c0bfcaf7bfe37d6933c812e46352be8a95397eaa430a0f5bc94037600a53f654"
   },

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

@@ -1,7 +1,7 @@
 {
   "name": "audrey",
-  "version": "1.1.2",
-  "mcpName": "io.github.evilander/audrey",
+  "version": "1.1.3",
+  "mcpName": "io.github.Evilander/audrey",
   "description": "Automatic, evidence-backed memory and pre-action Guard for Codex, Claude Code, and custom AI agents",
   "type": "module",
   "main": "dist/src/index.js",

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

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "Audrey paper submission bundle",
-  "generatedAt": "2026-07-13T14:48:57.367Z",
+  "generatedAt": "2026-07-13T15:07:39.931Z",
   "sourceRoot": ".",
   "outDir": "docs/paper/output/submission-bundle",
   "claimVerification": {
@@ -17,33 +17,33 @@
     "scenarios": 10,
     "redactionLeaks": 0,
     "artifactLeaks": 0,
-    "latencyP50Ms": 4.253,
-    "latencyP95Ms": 21.196
+    "latencyP50Ms": 4.607,
+    "latencyP95Ms": 21.585
   },
   "files": [
     {
       "path": "benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json",
       "source": "benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json",
       "bytes": 1267,
-      "sha256": "ba28d37d8f8add0f97c12048a5badb7df65507bf15fa66a82ec46da3622676b2"
+      "sha256": "c5ec2d2632cbe0a93b2de477ed24b6b60edf472af5f87badaef6d13df8c60dc0"
     },
     {
       "path": "benchmarks/output/external/guardbench-external-dry-run.json",
       "source": "benchmarks/output/external/guardbench-external-dry-run.json",
       "bytes": 1831,
-      "sha256": "e4b8c62e4e890b8b866fd40d53e06482776e7dbea5b696e8c3a3f7f96edff130"
+      "sha256": "fc869b31a721ee3af3b9e6ed0ade29605ab4b5fbaea08ce1ced82a081c286cf5"
     },
     {
       "path": "benchmarks/output/external/guardbench-external-evidence.json",
       "source": "benchmarks/output/external/guardbench-external-evidence.json",
       "bytes": 1638,
-      "sha256": "280ca446e26e434ad62e3db8438811ac8430ef0096907d25937558898df71ff1"
+      "sha256": "1fdd81a5b379f0b064a3c0da28b01d46ddbe525488cbe661e701b539f79ded96"
     },
     {
       "path": "benchmarks/output/guardbench-conformance-card.json",
       "source": "benchmarks/output/guardbench-conformance-card.json",
       "bytes": 1735,
-      "sha256": "8613dfacbf592e7d409b38f7c92ffa188bc5e8dc18664fc338b4de2ad80a9f6a"
+      "sha256": "88cf564ed1fd374ae2d639095833a22be8c2961797dd4eede927b62836fd497a"
     },
     {
       "path": "benchmarks/output/guardbench-manifest.json",
@@ -54,44 +54,44 @@
     {
       "path": "benchmarks/output/guardbench-raw.json",
       "source": "benchmarks/output/guardbench-raw.json",
-      "bytes": 43837,
-      "sha256": "786b03ff8570444620c23b35621bbb14897f06310de7e8bd3a337a1acf5ce776"
+      "bytes": 43839,
+      "sha256": "20a91ed7ca54a3b5b47b3a3f9ecde4ae8d53cc2b9bdbb5cb1ce6347e2224497b"
     },
     {
       "path": "benchmarks/output/guardbench-summary.json",
       "source": "benchmarks/output/guardbench-summary.json",
-      "bytes": 70085,
-      "sha256": "3ba1c059558aa8b511ae510276078930649ba6aca9669324148726fac10c7ee8"
+      "bytes": 70089,
+      "sha256": "53b22e040ace0b91784e99684ffd740c95740171c00bf65388590aeb493c7c7d"
     },
     {
       "path": "benchmarks/output/leaderboard/guardbench-leaderboard.json",
       "source": "benchmarks/output/leaderboard/guardbench-leaderboard.json",
       "bytes": 2798,
-      "sha256": "fab0b024f320a592ce31cc5105c645e8e701162b38cfe781744cbf5d3e5b4cc9"
+      "sha256": "ec7a71aab68864b02a69ff11f905a2a639766499ed24d74c85a2288ab18b5c48"
     },
     {
       "path": "benchmarks/output/leaderboard/guardbench-leaderboard.md",
       "source": "benchmarks/output/leaderboard/guardbench-leaderboard.md",
       "bytes": 364,
-      "sha256": "f175d7797ce317d3f274eb2793a167ab5e72559041dc110f93bbce15f8c8322c"
+      "sha256": "bb8f7ab20c31aecdd9f5cccca414948771108d05be19cde5e28b2d5f218f23fd"
     },
     {
       "path": "benchmarks/output/submission-bundle/submission-manifest.json",
       "source": "benchmarks/output/submission-bundle/submission-manifest.json",
       "bytes": 3986,
-      "sha256": "22014796e9cda3d2ce655733587b2be031d809a72727e40c7ab19440edfd8ebb"
+      "sha256": "20aea68240aeb46767a7f9f328086710e5a1aa6146c0a42733264dec4baedfbb"
     },
     {
       "path": "benchmarks/output/submission-bundle/validation-report.json",
       "source": "benchmarks/output/submission-bundle/validation-report.json",
       "bytes": 739,
-      "sha256": "b8358a7b2833672d06b44809aff428211b9936e7e91a913b45d49248b66de701"
+      "sha256": "c94efafc7e1417812675cfd76a1654e016ed72aed78c461d34802cc55ed10961"
     },
     {
       "path": "benchmarks/output/summary.json",
       "source": "benchmarks/output/summary.json",
-      "bytes": 100733,
-      "sha256": "3acda2a7cbc09a9b379ea4f5b8cca8c70b2104285420d15627f76886cc886f4d"
+      "bytes": 100760,
+      "sha256": "535b983a60cb97ddd85e5d57712e2eb3640e7c91ea57b8d63bef0f5103336ba8"
     },
     {
       "path": "benchmarks/schemas/guardbench-adapter-registry.schema.json",
@@ -216,8 +216,8 @@
     {
       "path": "docs/paper/07-evaluation.md",
       "source": "docs/paper/07-evaluation.md",
-      "bytes": 11256,
-      "sha256": "6cfcf5edc6d8d32898c821f67ea753a2526bc6f7a058d870eee909205ae42a32"
+      "bytes": 11273,
+      "sha256": "821a782eb8dbcb9c7943295fefff47afaeb349d1aa356ba7463248331e8fe12a"
     },
     {
       "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": 118711,
-      "sha256": "7db503c10b25314daa46e31fc65c98d18cd86895fe7bf44501e108626c4a3cac"
+      "bytes": 118728,
+      "sha256": "de42ec49d0be877b824288959d0ac48d13f78ac571aa93acb7cc288f931d20f6"
     },
     {
       "path": "docs/paper/browser-launch-plan.json",
@@ -295,25 +295,25 @@
       "path": "docs/paper/evidence-ledger.md",
       "source": "docs/paper/evidence-ledger.md",
       "bytes": 63088,
-      "sha256": "3be5f920d901cb9c04749bdd656db89e076234404711846a283c921744241655"
+      "sha256": "2b3511f9465fb8fef1330036410b5a647d930ebd2bab6ab308c8ff03a70ab278"
     },
     {
       "path": "docs/paper/output/arxiv-compile-report.json",
       "source": "docs/paper/output/arxiv-compile-report.json",
       "bytes": 924,
-      "sha256": "ece8ad32fb21efbfbf29e80faae510bb4f1240c57011176b7dbd159ddd7bc726"
+      "sha256": "95ff0c1933a56a5d127796b08152c4dd57ff8623f24c159829f6642bdbc78e62"
     },
     {
       "path": "docs/paper/output/arxiv/arxiv-manifest.json",
       "source": "docs/paper/output/arxiv/arxiv-manifest.json",
       "bytes": 1316,
-      "sha256": "de555f986f650735f8b4184eb93504b20d94dbd1e8510d839311fbf7e7d69429"
+      "sha256": "d91eaefbca39c49e79990ef58314bbaa502184dae14596a498c2b6d8ba2f7df2"
     },
     {
       "path": "docs/paper/output/arxiv/main.tex",
       "source": "docs/paper/output/arxiv/main.tex",
-      "bytes": 124825,
-      "sha256": "d9d0cf25cad4e59d6234643eb875bd5d74b4d45acd106e9bc01c7454e7240622"
+      "bytes": 124842,
+      "sha256": "0e122e6bd050e3fbf8e62ab3b363b12ebb00c7c8a4618b9fa4971d19e798bcc7"
     },
     {
       "path": "docs/paper/output/arxiv/README-arxiv.txt",
@@ -367,13 +367,13 @@
       "path": "package.json",
       "source": "package.json",
       "bytes": 12751,
-      "sha256": "990dfcd1793a5965882b973944890315daf8d0752ee1bf3e2ec0cb747e77c91c"
+      "sha256": "95d71cbce2f9b389668cad1531ca82456845c31d98b74bf0bcf4cd70835219c7"
     },
     {
       "path": "README.md",
       "source": "README.md",
       "bytes": 22764,
-      "sha256": "70f8a05c07140a3b3f6ce310b77b96b05e0d03300364178c81289a7b45c74257"
+      "sha256": "13e0a9f8977e5f8edb7f8ceebe3b7f8c5bd2a328129446e2fb6bf3c601a63d23"
     }
   ]
 }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "audrey",
-  "version": "1.1.2",
-  "mcpName": "io.github.evilander/audrey",
+  "version": "1.1.3",
+  "mcpName": "io.github.Evilander/audrey",
   "description": "Automatic, evidence-backed memory and pre-action Guard for Codex, Claude Code, and custom AI agents",
   "type": "module",
   "main": "dist/src/index.js",