kenaz 0.3.3 → 0.3.5

package/core/dev/jev-eval/README.md

@@ -1,101 +1,101 @@
-# Kenaz Jev 離線評測工具
+# Kenaz Jev 離線評測工具
 
 > **LEGACY (TASK_1987, 2026-09-21)**: the Muninn observer this integration overlays (translateAndClassifyMessages via muninn-watcher) is retired from all default paths; the Dashboard *Jev-assisted judgments* switch stays OFF and reaches no live consumer. Evidence and decision: `dev/MUNINN_RETIREMENT.md`. The research harness below remains runnable offline.
-
-這是 J0/J1 研究原型。用途是驗證資料格式、API adapter、回放與評分流程；尚未接入 Dashboard、Synapse 或 Muninn。`promotion_eligible` 固定為 `false`，不會因合成資料拿到高分就自動上線。
-
-需要 Node.js 22 以上。使用內建模組，不需 npm install。以下命令從 KenazAI 根目錄執行。
-
-## 離線操作
-
-```powershell
-node --test dev/jev-eval/test/*.test.mjs
-node dev/jev-eval/cli.mjs validate --dataset dev/jev-eval/fixtures/synthetic.jsonl
-node dev/jev-eval/cli.mjs evaluate --dataset dev/jev-eval/fixtures/synthetic.jsonl --provider rules
-node dev/jev-eval/cli.mjs template
-node dev/jev-eval/cli.mjs preflight
-```
-
-`rules` 是簡單、可重複的本地基準，不是 Jev 模型或其品質模擬。報告可能顯示錯誤，這是比較基準的觀察結果；工程測試綠燈只代表評測工具符合測試契約。
-
-CLI 的 JSON 輸出可供其他工具讀取。先檢查 exit code，再解析 stdout；錯誤不代表資料集得零分。不要把 live provider 的不可用/逾時樣本當作正確回答。
-
-## 資料與回放
-
-故障研究矩陣可離線執行：`node dev/jev-eval/resilience.mjs`。它用本機 HTTP fixture 驗證 off、shadow、evaluation-active，結果分開記錄 provider 失敗與 fallback 交付。shadow 透過 deliver callback 先交付基準，但函式回傳的 Promise 仍等待觀察結果，不能將 await 直接當作產品非阻塞介面。這不是 production provider，沒有安裝版驗收宣告。
-
-人工盲審工具：
-
-```powershell
-node dev/jev-eval/review.mjs export --dataset dev/jev-eval/fixtures/synthetic.jsonl --out review-new.json
-node dev/jev-eval/review.mjs apply --dataset dev/jev-eval/fixtures/synthetic.jsonl --reviews review-new.json --out reviewed-new.jsonl
-```
-
-export 隱藏原始 gold 與模型結果；人工填寫 decision、reviewed、reviewer、reviewed_at（UTC ISO 時間）後才能 apply。apply 要求每筆完整、身分和 hash 相符，且輸出必須是新檔，不覆寫來源。先寫同目錄暫存檔再以 hard link 發布，檔案系統若不支援 hard link 會失敗，不降級成覆寫。審閱旗標是聲明，不是真人身分驗證。
-
-本輪已準備 [6 筆真實片段待審檔](reports/conversation-review.pending.json) 與 [11 筆合成案例待審檔](reports/synthetic-review.pending.json)，皆未填答案。來源、比較設計、剩餘缺口見 [VALIDATION_PROGRESS.md](VALIDATION_PROGRESS.md)。
-
-資料使用 JSONL，一行一筆，欄位包括 schema_version、id、project_id、session_id、group_id、task_id、event_id、event_seq、task_revision、purpose、language、split、provenance、state。
-
-- correction：`labels.correction` 是 gold，`state.message` 是待判斷原文，`state.assumptions` 是必要前提。
-- relevance：`candidates` 含穩定 id、text 和 grade 0–3。grade 只用於評測，不送到 Jev。
-- provenance 明確區分 synthetic/real 與 agent_proposed/human_verified。審閱流程見 [ANNOTATION_GUIDE.md](ANNOTATION_GUIDE.md)。
-- 同 session/group 不能跨 development、calibration、held_out，避免資料洩漏。
-
-回放 prediction 必須與 dataset 的 id/project/session/task/event/sequence/revision 及 state_hash 對應，並包含 model、question_set_version、status、failure_reason、http_status、usage、latency_ms，以及 correction_probability 或 scores。改了原文或候選後不能沿用舊結果。每筆資料必須有一筆 prediction；未回答使用明確失敗狀態及 null，不把缺失或非法分數當成 0。完整契約以 schema.mjs 的 validatePrediction 為準。
-
-```powershell
-node dev/jev-eval/cli.mjs evaluate --dataset <dataset.jsonl> --provider replay --predictions <predictions.jsonl>
-```
-
-回放延遲是錄製資料，rules 延遲是本地計算時間，兩者都不是當下 Jev 網路延遲。`--split held_out` 用於凍結問法與門檻後的驗收，不得用它反覆調參。
-
-修正分類以 0.5 為研究門檻；recall_including_abstentions 將未回答的正例計入漏失，Brier 僅涵蓋已回答案例，須搭配 coverage 判讀。重排只排序已回答的候選，但 NDCG 的理想排序包含所有候選；另列完整查詢限定的 NDCG 與候選覆蓋率。全部 grade=0 的查詢不納入 NDCG/Recall 平均，排除數會列出。這些數字不含信賴區間，不能直接當上線驗收。
-
-## 真實 API 測試
-
-live 模式需要本機 `TYPESAFE_API_KEY`。請透過本機安全設定配置，不把 key 貼到聊天、JSONL、報告、git 或命令列參數。
-
-`preflight` 只回報金鑰是否存在與固定模型版本，不連網、不輸出金鑰。CLI 不提供 endpoint 或模型覆寫選項。
-
-```powershell
-node dev/jev-eval/cli.mjs evaluate --dataset dev/jev-eval/fixtures/synthetic.jsonl --provider live --timeout-ms 800
-```
-
-這個命令會把指定資料集的必要 state/候選文字送到 TypeSafe API，因此僅使用已準備可外送的資料。預設固定模型版本 `jev-1.13.0`。工具不掃描環境檔案、不擷取 live session、不自動上傳 Synapse，也不在離線模式使用金鑰。
-
-本原型沒有同步重試；總期限應涵蓋 response body。401/422、429/529、畸形回答、缺少題目、越界分数都需要在結果中辨認，不以原始 HTTP body 作錯誤訊息，避免供應商回顯的敏感資料流入 log。
-
-## 評估邊界
-
-### 2026-09-20 API 冒煙實測
-
-已安裝並使用專案的 [TypeSafe skill](../../.agents/skills/typesafe-ai/SKILL.md)，以官方即時 API/model 文件核對既有 adapter，無需更改請求格式。金鑰僅透過測試子程序環境變數使用，未保存於專案。
-
-[實測 JSON](reports/live-smoke-2026-09-20.json) 保留兩輪各 11 筆合成案例：10 秒期限輪全部成功，p50 273ms、最大 736ms；800ms 期限輪全部成功，p50 272ms、最大 653ms。更正辨識各為 8/8，兩筆可計算的排序查詢 NDCG@5 為 1；全無相關候選的第三筆不納入此平均。同期 rules 更正辨識為 4/8，NDCG@5 約 0.822。
-
-共執行三輪 API 請求，中間一輪工具輸出被截斷，不計入保留的統計。兩輪使用相同小型合成資料；重複輸入的服務端快取狀態未知，p95/p99 因每輪僅 11 筆均等於最大值。這不是獨立真人品質評估、穩態尾延遲或 production SLO。下一步仍是人工覆核的真實評測集與現行分類／排序基準比較，production 未啟用 Jev。
-
-目前附帶的是小型合成回歸集合，標籤由代理提出。它不能取代計畫中的 500 則訊息、100 組 recall 與 30 段交接情境，也不構成真人驗證的 held-out 效果。
-
-正式報告需另補：繁中/英文分開標註、現行 Haiku 與 Synapse 的公平基準、延遲分布、人工複核，以及壓縮/交接後任務是否真的更少漂移。沒有供應商實測就不能宣稱 Jev 比現有流程快或準。
-
-## 來源
-
-現有 Muninn 分類基準的隔離執行與本機額度阻塞紀錄，見 [BASELINE_COMPARISON.md](BASELINE_COMPARISON.md)。`node dev/jev-eval/muninn-baseline.mjs` 預設只做離線契約檢查；live 須明確指定 CLI，且只接受合成資料。回傳報告的 status 也必須成功，不能只用 exit code 判定模型回答有效。
-
-- [完整導入規劃](../JEV_INTEGRATION_PLAN.md)
-- [TypeSafe API](https://docs.typesafe.ai/api)
-- [模型版本與語言限制](https://docs.typesafe.ai/models)
-- [機率與 confidence](https://docs.typesafe.ai/confidence)
-- [Jev 已知限制](https://docs.typesafe.ai/model-jaggedness/jev-1.13)
-
-所有 production 功能開關保持既有狀態；本目錄的工具不會啟用模型、修改任務狀態、寫入記憶權重或啟動額外常駐服務。
-
-## Local historical corpus preparation
-
-The separate opt-in `corpus.mjs` tool inventories authorized local history without network calls. See [HISTORICAL_CORPUS.md](HISTORICAL_CORPUS.md): 458 unreviewed candidates, 42 short of target, not a labelled evaluation set. Existing evaluation CLI does not automatically collect or upload history.
-
-Local observed-context restoration and read-only review packets: [CONTEXT_REVIEW.md](CONTEXT_REVIEW.md). 419 partial, 23 missing, 16 rejected; 0 human-reviewed.
-
-Current consolidated findings and local annotation pilot: [EVALUATION_STATUS.md](EVALUATION_STATUS.md).
+
+這是 J0/J1 研究原型。用途是驗證資料格式、API adapter、回放與評分流程；尚未接入 Dashboard、Synapse 或 Muninn。`promotion_eligible` 固定為 `false`，不會因合成資料拿到高分就自動上線。
+
+需要 Node.js 22 以上。使用內建模組，不需 npm install。以下命令從 KenazAI 根目錄執行。
+
+## 離線操作
+
+```powershell
+node --test dev/jev-eval/test/*.test.mjs
+node dev/jev-eval/cli.mjs validate --dataset dev/jev-eval/fixtures/synthetic.jsonl
+node dev/jev-eval/cli.mjs evaluate --dataset dev/jev-eval/fixtures/synthetic.jsonl --provider rules
+node dev/jev-eval/cli.mjs template
+node dev/jev-eval/cli.mjs preflight
+```
+
+`rules` 是簡單、可重複的本地基準，不是 Jev 模型或其品質模擬。報告可能顯示錯誤，這是比較基準的觀察結果；工程測試綠燈只代表評測工具符合測試契約。
+
+CLI 的 JSON 輸出可供其他工具讀取。先檢查 exit code，再解析 stdout；錯誤不代表資料集得零分。不要把 live provider 的不可用/逾時樣本當作正確回答。
+
+## 資料與回放
+
+故障研究矩陣可離線執行：`node dev/jev-eval/resilience.mjs`。它用本機 HTTP fixture 驗證 off、shadow、evaluation-active，結果分開記錄 provider 失敗與 fallback 交付。shadow 透過 deliver callback 先交付基準，但函式回傳的 Promise 仍等待觀察結果，不能將 await 直接當作產品非阻塞介面。這不是 production provider，沒有安裝版驗收宣告。
+
+人工盲審工具：
+
+```powershell
+node dev/jev-eval/review.mjs export --dataset dev/jev-eval/fixtures/synthetic.jsonl --out review-new.json
+node dev/jev-eval/review.mjs apply --dataset dev/jev-eval/fixtures/synthetic.jsonl --reviews review-new.json --out reviewed-new.jsonl
+```
+
+export 隱藏原始 gold 與模型結果；人工填寫 decision、reviewed、reviewer、reviewed_at（UTC ISO 時間）後才能 apply。apply 要求每筆完整、身分和 hash 相符，且輸出必須是新檔，不覆寫來源。先寫同目錄暫存檔再以 hard link 發布，檔案系統若不支援 hard link 會失敗，不降級成覆寫。審閱旗標是聲明，不是真人身分驗證。
+
+本輪已準備 [6 筆真實片段待審檔](reports/conversation-review.pending.json) 與 [11 筆合成案例待審檔](reports/synthetic-review.pending.json)，皆未填答案。來源、比較設計、剩餘缺口見 [VALIDATION_PROGRESS.md](VALIDATION_PROGRESS.md)。
+
+資料使用 JSONL，一行一筆，欄位包括 schema_version、id、project_id、session_id、group_id、task_id、event_id、event_seq、task_revision、purpose、language、split、provenance、state。
+
+- correction：`labels.correction` 是 gold，`state.message` 是待判斷原文，`state.assumptions` 是必要前提。
+- relevance：`candidates` 含穩定 id、text 和 grade 0–3。grade 只用於評測，不送到 Jev。
+- provenance 明確區分 synthetic/real 與 agent_proposed/human_verified。審閱流程見 [ANNOTATION_GUIDE.md](ANNOTATION_GUIDE.md)。
+- 同 session/group 不能跨 development、calibration、held_out，避免資料洩漏。
+
+回放 prediction 必須與 dataset 的 id/project/session/task/event/sequence/revision 及 state_hash 對應，並包含 model、question_set_version、status、failure_reason、http_status、usage、latency_ms，以及 correction_probability 或 scores。改了原文或候選後不能沿用舊結果。每筆資料必須有一筆 prediction；未回答使用明確失敗狀態及 null，不把缺失或非法分數當成 0。完整契約以 schema.mjs 的 validatePrediction 為準。
+
+```powershell
+node dev/jev-eval/cli.mjs evaluate --dataset <dataset.jsonl> --provider replay --predictions <predictions.jsonl>
+```
+
+回放延遲是錄製資料，rules 延遲是本地計算時間，兩者都不是當下 Jev 網路延遲。`--split held_out` 用於凍結問法與門檻後的驗收，不得用它反覆調參。
+
+修正分類以 0.5 為研究門檻；recall_including_abstentions 將未回答的正例計入漏失，Brier 僅涵蓋已回答案例，須搭配 coverage 判讀。重排只排序已回答的候選，但 NDCG 的理想排序包含所有候選；另列完整查詢限定的 NDCG 與候選覆蓋率。全部 grade=0 的查詢不納入 NDCG/Recall 平均，排除數會列出。這些數字不含信賴區間，不能直接當上線驗收。
+
+## 真實 API 測試
+
+live 模式需要本機 `TYPESAFE_API_KEY`。請透過本機安全設定配置，不把 key 貼到聊天、JSONL、報告、git 或命令列參數。
+
+`preflight` 只回報金鑰是否存在與固定模型版本，不連網、不輸出金鑰。CLI 不提供 endpoint 或模型覆寫選項。
+
+```powershell
+node dev/jev-eval/cli.mjs evaluate --dataset dev/jev-eval/fixtures/synthetic.jsonl --provider live --timeout-ms 800
+```
+
+這個命令會把指定資料集的必要 state/候選文字送到 TypeSafe API，因此僅使用已準備可外送的資料。預設固定模型版本 `jev-1.13.0`。工具不掃描環境檔案、不擷取 live session、不自動上傳 Synapse，也不在離線模式使用金鑰。
+
+本原型沒有同步重試；總期限應涵蓋 response body。401/422、429/529、畸形回答、缺少題目、越界分数都需要在結果中辨認，不以原始 HTTP body 作錯誤訊息，避免供應商回顯的敏感資料流入 log。
+
+## 評估邊界
+
+### 2026-09-20 API 冒煙實測
+
+已安裝並使用專案的 [TypeSafe skill](../../.agents/skills/typesafe-ai/SKILL.md)，以官方即時 API/model 文件核對既有 adapter，無需更改請求格式。金鑰僅透過測試子程序環境變數使用，未保存於專案。
+
+[實測 JSON](reports/live-smoke-2026-09-20.json) 保留兩輪各 11 筆合成案例：10 秒期限輪全部成功，p50 273ms、最大 736ms；800ms 期限輪全部成功，p50 272ms、最大 653ms。更正辨識各為 8/8，兩筆可計算的排序查詢 NDCG@5 為 1；全無相關候選的第三筆不納入此平均。同期 rules 更正辨識為 4/8，NDCG@5 約 0.822。
+
+共執行三輪 API 請求，中間一輪工具輸出被截斷，不計入保留的統計。兩輪使用相同小型合成資料；重複輸入的服務端快取狀態未知，p95/p99 因每輪僅 11 筆均等於最大值。這不是獨立真人品質評估、穩態尾延遲或 production SLO。下一步仍是人工覆核的真實評測集與現行分類／排序基準比較，production 未啟用 Jev。
+
+目前附帶的是小型合成回歸集合，標籤由代理提出。它不能取代計畫中的 500 則訊息、100 組 recall 與 30 段交接情境，也不構成真人驗證的 held-out 效果。
+
+正式報告需另補：繁中/英文分開標註、現行 Haiku 與 Synapse 的公平基準、延遲分布、人工複核，以及壓縮/交接後任務是否真的更少漂移。沒有供應商實測就不能宣稱 Jev 比現有流程快或準。
+
+## 來源
+
+現有 Muninn 分類基準的隔離執行與本機額度阻塞紀錄，見 [BASELINE_COMPARISON.md](BASELINE_COMPARISON.md)。`node dev/jev-eval/muninn-baseline.mjs` 預設只做離線契約檢查；live 須明確指定 CLI，且只接受合成資料。回傳報告的 status 也必須成功，不能只用 exit code 判定模型回答有效。
+
+- [完整導入規劃](../JEV_INTEGRATION_PLAN.md)
+- [TypeSafe API](https://docs.typesafe.ai/api)
+- [模型版本與語言限制](https://docs.typesafe.ai/models)
+- [機率與 confidence](https://docs.typesafe.ai/confidence)
+- [Jev 已知限制](https://docs.typesafe.ai/model-jaggedness/jev-1.13)
+
+所有 production 功能開關保持既有狀態；本目錄的工具不會啟用模型、修改任務狀態、寫入記憶權重或啟動額外常駐服務。
+
+## Local historical corpus preparation
+
+The separate opt-in `corpus.mjs` tool inventories authorized local history without network calls. See [HISTORICAL_CORPUS.md](HISTORICAL_CORPUS.md): 458 unreviewed candidates, 42 short of target, not a labelled evaluation set. Existing evaluation CLI does not automatically collect or upload history.
+
+Local observed-context restoration and read-only review packets: [CONTEXT_REVIEW.md](CONTEXT_REVIEW.md). 419 partial, 23 missing, 16 rejected; 0 human-reviewed.
+
+Current consolidated findings and local annotation pilot: [EVALUATION_STATUS.md](EVALUATION_STATUS.md).

package/core/dev/jev-eval/THALAMUS_RANKING.md

@@ -1,58 +1,58 @@
-# Jev Thalamus context ranking
-
-Status: local implementation verified, 2026-09-20. No installed release or real relevance improvement claimed.
-
-## Delivery contract
-
-The single Dashboard **Jev-assisted judgments** switch (TASK_1970) controls both existing project-local fields, `jevThalamusEnabled` and `jevCorrectionEnabled`, in one atomic settings request. Both default to false. Runtime fields remain separate for compatibility, while the Dashboard presents one control. The server reads `TYPESAFE_API_KEY` from its environment; no developer key is embedded or returned.
-
-The shared Rust service receives the current task and a bounded shortlist, asks one TypeSafe Score question per candidate, and returns a stable descending permutation. Same-score ties retain input order. It preserves all candidates; existing delivery budgets decide what is shown. It does not alter Thalamus potential, firing thresholds, decay, propagation, or cascade chain order.
-
-POST `/api/synapse/jev-thalamus-rank` accepts `{projectPath, taskContext, candidates:[{id,text}]}`. The project must be an explicit existing absolute directory with its own opt-in flag. The response is `{orderedIds,status,reason}`; only `status: ranked` may change delivery. Unknown or duplicated returned IDs must never be applied by consumers.
-
-Limits: at most eight candidates; task 4096 UTF-8 bytes; candidate text 2048 bytes and ID 512 bytes; request 32 KiB; provider response 64 KiB. The fixed provider is `https://api.typesafe.ai/v1/systemone`, model `jev-1.13.0`. One 800 ms deadline covers provider transport and body, with no retry or redirect. Config reads have separate bounds, so 800 ms is not an end-to-end workflow latency promise.
-
-Missing/false/malformed config, missing key, unusable input, sensitive-text patterns, timeout, HTTP failure or invalid Score envelope preserve baseline order. Disabling the flag while a request runs discards its result. Sensitive-text checks are conservative heuristics, not a guarantee that arbitrary text contains no secrets. No raw-text decision telemetry is written by this service.
-
-## Consumers
-
-- Native Claude UserPromptSubmit: TASK_44 wiring orders recalled Active Sensing entries before the existing 800-character rendering budget. It sends the current bounded prompt and existing candidate summaries, not the full transcript. The hook retains original context, DDx/reflex messages, and Alaya output.
-- MCP `thalamus_context`: optional `taskContext` enables ranking of delivered near-threshold/recent-fire/cluster-symbol lists. Names, paths, and docstrings come from the project's existing read-only search index. Missing context or candidates retains baseline. A 200 ms caller deadline bounds enrichment waiting; the blocking SQLite worker may finish later. This is not hard cancellation of database computation.
-- Bifrost does not invoke native `.claude/hooks/` automatically. This implementation does not claim automatic Bifrost injection; its callers need the explicit MCP context argument.
-
-TASK_44 corrected the existing native hook recall mismatch (`query` instead of required `q`) and added explicit `projectPath` to recall and turn-context requests. Its separate existing seconds/milliseconds cooldown mismatch is outside this change.
-
-## Settings and feedback
-
-TASK_1970 supersedes the separate UI introduced in TASK_1967 with one Default Models switch and one overall feedback area. GET status uses `feature=all`, derives both flags from the same config snapshot, and reports mixed legacy settings explicitly. A toggle sends both flags with the same value in one request and requires both acknowledgements. New overall feedback is tagged `all`; previous correction/Thalamus records retain their classifications, and legacy records without a discriminator belong to correction. Feedback is overall experience, not labeled ground truth.
-
-## Verification and rollout
-
-Parent verified `node --test .claude/hooks/jev-thalamus-context.test.js`: 7/7 passed. This executes the real hook in a fixture VM and checks rendered selection before truncation, exact OFF/failure fallback, disabled-in-flight results, request bounds, and preserved safety/Alaya content. `node dev/scripts/run-rust-tests.js jev_thalamus` passed 12/12 tests (parent inspected the canonical runner log). Coverage includes shared scoring, read-only enrichment, actual route OFF/body limit, and MCP no-context/OFF behavior. The positive MCP path is assembled from those tested components; no live provider-to-MCP run was performed. Parent reran the two focused Jest files: 17/17 passed. Full Dashboard TypeScript checking passed with --noEmit --incremental false. Final combined `node dev/scripts/run-rust-tests.js jev` passed 23/23 (12 ranking/route/MCP + 11 settings). Together with 77 Node and 17 Jest tests, 117 engineering checks passed. Existing correction/research regression: `node --test .formation/tools/jev-correction.test.js dev/jev-eval/test/*.test.mjs` passed 70 tests during this work.
-
-Real Jev quality, Chinese-task relevance, representative end-to-end latency and comparison against baseline remain unmeasured for this feature. Offline mocked ranking validates delivery and fallback, not model accuracy. No historical session data was uploaded during this implementation.
-
-The core stager includes tracked `.claude` files only. A new untracked hook helper is omitted from an actual package until it is included in the tracked release candidate. No installer build, merge, or release has been performed.
-
-References: [TypeSafe API](https://docs.typesafe.ai/api), [Score](https://docs.typesafe.ai/primitives/score), [reranking cookbook](https://docs.typesafe.ai/cookbooks/rerank_typesafe). Official examples motivate the mechanism; they are not Kenaz measurements.
-
-## Task tracking migration
-
-The user explicitly restored KenazAI as the tracking project. Existing implementations were not redispatched. Old quotation cards retain their history and forward references, with duplicate tracking closed as superseded; this does not cancel the implementation.
-
-| quotation history | KenazAI authoritative task | Scope |
-| --- | --- | --- |
-| TASK_43 | TASK_1965 | Shared Rust ranker and MCP/HTTP delivery |
-| TASK_44 | TASK_1966 | Native hook delivery |
-| TASK_45 | TASK_1967 | Independent settings and feedback |
-| TASK_46 | TASK_1968 | Verification documentation |
-
-TASK_1970 UI update: parent verified focused Jest 23/23, including actual panel SSR with exactly one checkbox, mixed legacy state, one-request dual-flag persistence, and partial-acknowledgement rejection. Canonical Rust filter `jev` passed 26/26; full Dashboard TypeScript and diff checks passed. Live combined status returned feature=all, enabled=true, mixed=false, both flags=true; runtime keyConfigured remained false, so no provider probe was sent.
-
-TASK_1971 follow-up: Windows startup falls back to HKCU Environment TYPESAFE_API_KEY
-only when absent from the inherited process environment. Six startup tests and
-12 Jev regression tests passed. After natural dev reload, combined status reported
-keyConfigured=true; one synthetic live request returned ranked, orderedIds
-[startup, docx], reason=null. Client elapsed time was 2726ms including localhost
-request overhead; this is not a provider-only latency measurement or quality eval.
-No real transcript was sent, and installed release packaging remains unverified.
+# Jev Thalamus context ranking
+
+Status: local implementation verified, 2026-09-20. No installed release or real relevance improvement claimed.
+
+## Delivery contract
+
+The single Dashboard **Jev-assisted judgments** switch (TASK_1970) controls both existing project-local fields, `jevThalamusEnabled` and `jevCorrectionEnabled`, in one atomic settings request. Both default to false. Runtime fields remain separate for compatibility, while the Dashboard presents one control. The server reads `TYPESAFE_API_KEY` from its environment; no developer key is embedded or returned.
+
+The shared Rust service receives the current task and a bounded shortlist, asks one TypeSafe Score question per candidate, and returns a stable descending permutation. Same-score ties retain input order. It preserves all candidates; existing delivery budgets decide what is shown. It does not alter Thalamus potential, firing thresholds, decay, propagation, or cascade chain order.
+
+POST `/api/synapse/jev-thalamus-rank` accepts `{projectPath, taskContext, candidates:[{id,text}]}`. The project must be an explicit existing absolute directory with its own opt-in flag. The response is `{orderedIds,status,reason}`; only `status: ranked` may change delivery. Unknown or duplicated returned IDs must never be applied by consumers.
+
+Limits: at most eight candidates; task 4096 UTF-8 bytes; candidate text 2048 bytes and ID 512 bytes; request 32 KiB; provider response 64 KiB. The fixed provider is `https://api.typesafe.ai/v1/systemone`, model `jev-1.13.0`. One 800 ms deadline covers provider transport and body, with no retry or redirect. Config reads have separate bounds, so 800 ms is not an end-to-end workflow latency promise.
+
+Missing/false/malformed config, missing key, unusable input, sensitive-text patterns, timeout, HTTP failure or invalid Score envelope preserve baseline order. Disabling the flag while a request runs discards its result. Sensitive-text checks are conservative heuristics, not a guarantee that arbitrary text contains no secrets. No raw-text decision telemetry is written by this service.
+
+## Consumers
+
+- Native Claude UserPromptSubmit: TASK_44 wiring orders recalled Active Sensing entries before the existing 800-character rendering budget. It sends the current bounded prompt and existing candidate summaries, not the full transcript. The hook retains original context, DDx/reflex messages, and Alaya output.
+- MCP `thalamus_context`: optional `taskContext` enables ranking of delivered near-threshold/recent-fire/cluster-symbol lists. Names, paths, and docstrings come from the project's existing read-only search index. Missing context or candidates retains baseline. A 200 ms caller deadline bounds enrichment waiting; the blocking SQLite worker may finish later. This is not hard cancellation of database computation.
+- Bifrost does not invoke native `.claude/hooks/` automatically. This implementation does not claim automatic Bifrost injection; its callers need the explicit MCP context argument.
+
+TASK_44 corrected the existing native hook recall mismatch (`query` instead of required `q`) and added explicit `projectPath` to recall and turn-context requests. Its separate existing seconds/milliseconds cooldown mismatch is outside this change.
+
+## Settings and feedback
+
+TASK_1970 supersedes the separate UI introduced in TASK_1967 with one Default Models switch and one overall feedback area. GET status uses `feature=all`, derives both flags from the same config snapshot, and reports mixed legacy settings explicitly. A toggle sends both flags with the same value in one request and requires both acknowledgements. New overall feedback is tagged `all`; previous correction/Thalamus records retain their classifications, and legacy records without a discriminator belong to correction. Feedback is overall experience, not labeled ground truth.
+
+## Verification and rollout
+
+Parent verified `node --test .claude/hooks/jev-thalamus-context.test.js`: 7/7 passed. This executes the real hook in a fixture VM and checks rendered selection before truncation, exact OFF/failure fallback, disabled-in-flight results, request bounds, and preserved safety/Alaya content. `node dev/scripts/run-rust-tests.js jev_thalamus` passed 12/12 tests (parent inspected the canonical runner log). Coverage includes shared scoring, read-only enrichment, actual route OFF/body limit, and MCP no-context/OFF behavior. The positive MCP path is assembled from those tested components; no live provider-to-MCP run was performed. Parent reran the two focused Jest files: 17/17 passed. Full Dashboard TypeScript checking passed with --noEmit --incremental false. Final combined `node dev/scripts/run-rust-tests.js jev` passed 23/23 (12 ranking/route/MCP + 11 settings). Together with 77 Node and 17 Jest tests, 117 engineering checks passed. Existing correction/research regression: `node --test .formation/tools/jev-correction.test.js dev/jev-eval/test/*.test.mjs` passed 70 tests during this work.
+
+Real Jev quality, Chinese-task relevance, representative end-to-end latency and comparison against baseline remain unmeasured for this feature. Offline mocked ranking validates delivery and fallback, not model accuracy. No historical session data was uploaded during this implementation.
+
+The core stager includes tracked `.claude` files only. A new untracked hook helper is omitted from an actual package until it is included in the tracked release candidate. No installer build, merge, or release has been performed.
+
+References: [TypeSafe API](https://docs.typesafe.ai/api), [Score](https://docs.typesafe.ai/primitives/score), [reranking cookbook](https://docs.typesafe.ai/cookbooks/rerank_typesafe). Official examples motivate the mechanism; they are not Kenaz measurements.
+
+## Task tracking migration
+
+The user explicitly restored KenazAI as the tracking project. Existing implementations were not redispatched. Old quotation cards retain their history and forward references, with duplicate tracking closed as superseded; this does not cancel the implementation.
+
+| quotation history | KenazAI authoritative task | Scope |
+| --- | --- | --- |
+| TASK_43 | TASK_1965 | Shared Rust ranker and MCP/HTTP delivery |
+| TASK_44 | TASK_1966 | Native hook delivery |
+| TASK_45 | TASK_1967 | Independent settings and feedback |
+| TASK_46 | TASK_1968 | Verification documentation |
+
+TASK_1970 UI update: parent verified focused Jest 23/23, including actual panel SSR with exactly one checkbox, mixed legacy state, one-request dual-flag persistence, and partial-acknowledgement rejection. Canonical Rust filter `jev` passed 26/26; full Dashboard TypeScript and diff checks passed. Live combined status returned feature=all, enabled=true, mixed=false, both flags=true; runtime keyConfigured remained false, so no provider probe was sent.
+
+TASK_1971 follow-up: Windows startup falls back to HKCU Environment TYPESAFE_API_KEY
+only when absent from the inherited process environment. Six startup tests and
+12 Jev regression tests passed. After natural dev reload, combined status reported
+keyConfigured=true; one synthetic live request returned ranked, orderedIds
+[startup, docx], reason=null. Client elapsed time was 2726ms including localhost
+request overhead; this is not a provider-only latency measurement or quality eval.
+No real transcript was sent, and installed release packaging remains unverified.

package/core/dev/jev-eval/reports/annotation-pilot-2026-09-20.json

@@ -1,32 +1,32 @@
-{
-  "schema_version": 1,
-  "date": "2026-09-20",
-  "count": 12,
-  "sample_groups": 12,
-  "sampling": "12-case short-context convenience pilot; <=1800 characters total; up to4 each targetlength0-15,16-60,61+; sorted id, uniquegroups; not representative or held-out",
-  "separate_agent_reviews": 2,
-  "reviewers_independent_humans": false,
-  "same_label_including_null": 10,
-  "non_null_agreed": 9,
-  "agreed_positive": 2,
-  "agreed_negative": 7,
-  "both_unresolved": 1,
-  "disagreements": 2,
-  "needs_adjudication": 3,
-  "human_verified": 0,
-  "jev_real_case_predictions": 0,
-  "promotion_eligible": false,
-  "evidence_substrings_verified": 49,
-  "private_artifact_hashes": {
-    "pilot.json": "36de481aa3d231084e8d130d2836d34f124e8cea234b4d1edd1b0fdbdbec0781",
-    "reviewer-a.json": "b25b74d8d6bcd13acf9040630121d4976eadba4f09aa6b4cff5e4fa29df21e95",
-    "reviewer-b.json": "a4c73c239136dd2a83db1f03a4bb4689aecaf07a98faee24c6b2028988b7adc3",
-    "comparison.json": "44768dedd253618c41ae7366ee0a850b9d6ab5948292a72b4e7de3ee5293d287"
-  },
-  "limitations": [
-    "Same model-family agent proposals are correlated; agreement is not accuracy or independent human verification.",
-    "Convenience short-context pilot, no held-out or population inference.",
-    "Two disagreements preserved without forced consensus; one shared null also unresolved.",
-    "No Jev or Haiku request made for these real cases."
-  ]
-}
+{
+  "schema_version": 1,
+  "date": "2026-09-20",
+  "count": 12,
+  "sample_groups": 12,
+  "sampling": "12-case short-context convenience pilot; <=1800 characters total; up to4 each targetlength0-15,16-60,61+; sorted id, uniquegroups; not representative or held-out",
+  "separate_agent_reviews": 2,
+  "reviewers_independent_humans": false,
+  "same_label_including_null": 10,
+  "non_null_agreed": 9,
+  "agreed_positive": 2,
+  "agreed_negative": 7,
+  "both_unresolved": 1,
+  "disagreements": 2,
+  "needs_adjudication": 3,
+  "human_verified": 0,
+  "jev_real_case_predictions": 0,
+  "promotion_eligible": false,
+  "evidence_substrings_verified": 49,
+  "private_artifact_hashes": {
+    "pilot.json": "36de481aa3d231084e8d130d2836d34f124e8cea234b4d1edd1b0fdbdbec0781",
+    "reviewer-a.json": "b25b74d8d6bcd13acf9040630121d4976eadba4f09aa6b4cff5e4fa29df21e95",
+    "reviewer-b.json": "a4c73c239136dd2a83db1f03a4bb4689aecaf07a98faee24c6b2028988b7adc3",
+    "comparison.json": "44768dedd253618c41ae7366ee0a850b9d6ab5948292a72b4e7de3ee5293d287"
+  },
+  "limitations": [
+    "Same model-family agent proposals are correlated; agreement is not accuracy or independent human verification.",
+    "Convenience short-context pilot, no held-out or population inference.",
+    "Two disagreements preserved without forced consensus; one shared null also unresolved.",
+    "No Jev or Haiku request made for these real cases."
+  ]
+}

package/core/dev/jev-eval/reports/context-review-2026-09-20.json

@@ -1,48 +1,48 @@
-{
-  "schema_version": 1,
-  "count": 458,
-  "local_only": true,
-  "promotion_eligible": false,
-  "gold_labels": 0,
-  "status_counts": {
-    "restored": 0,
-    "partial": 419,
-    "missing": 23,
-    "rejected": 16
-  },
-  "limitations": [
-    "Observed text only; no claims that assistant statements are true.",
-    "Prefix hashes describe the current source snapshot; original corpus had no prefix hash, so historical immutability is not established.",
-    "Missing/truncated context must be reviewed before annotation.",
-    "No model calls or inferred goals/assumptions/labels."
-  ],
-  "verification": {
-    "tests_passed": 54,
-    "context_tests_passed": 10,
-    "source_text_items_verified": 2352,
-    "prefix_hashes_verified": 442,
-    "ids_preserved": 458,
-    "html_articles": 458,
-    "active_html_elements": 0,
-    "detected_credential_patterns_in_export": 0,
-    "external_model_requests": 0,
-    "human_verified": 0,
-    "input_pending_sha256": "5f5a10efc646863feae904df71493854f25a3d8f82993c1b066ae6ddea9b9a0d",
-    "review_packet_sha256": "0afb91d29be4dc004b5fd2fdefba98237cd6e060f8c0cd501415fa8bdc5baefa",
-    "source_code_sha256": "fde7ed3ba6a8071c6b51a84ca3ca0d1e994670663e619d2473bd81dbe20edea3"
-  },
-  "gap_counts": {
-    "missing_parent": 3,
-    "credential_context": 123,
-    "generated_context": 221,
-    "history_window": 126,
-    "turn_limit": 357,
-    "compaction_or_rollback": 95,
-    "ancestor_scope_mismatch": 26,
-    "text_truncated": 23,
-    "nonvisible_message": 10,
-    "unparsed_record": 5,
-    "missing_ancestor": 3
-  },
-  "rejection_notes": "16 cases in one Claude source: repeated attachment UUIDs with differing parentUuid make ancestry ambiguous. Metadata-only slug changes alone are tolerated."
-}
+{
+  "schema_version": 1,
+  "count": 458,
+  "local_only": true,
+  "promotion_eligible": false,
+  "gold_labels": 0,
+  "status_counts": {
+    "restored": 0,
+    "partial": 419,
+    "missing": 23,
+    "rejected": 16
+  },
+  "limitations": [
+    "Observed text only; no claims that assistant statements are true.",
+    "Prefix hashes describe the current source snapshot; original corpus had no prefix hash, so historical immutability is not established.",
+    "Missing/truncated context must be reviewed before annotation.",
+    "No model calls or inferred goals/assumptions/labels."
+  ],
+  "verification": {
+    "tests_passed": 54,
+    "context_tests_passed": 10,
+    "source_text_items_verified": 2352,
+    "prefix_hashes_verified": 442,
+    "ids_preserved": 458,
+    "html_articles": 458,
+    "active_html_elements": 0,
+    "detected_credential_patterns_in_export": 0,
+    "external_model_requests": 0,
+    "human_verified": 0,
+    "input_pending_sha256": "5f5a10efc646863feae904df71493854f25a3d8f82993c1b066ae6ddea9b9a0d",
+    "review_packet_sha256": "0afb91d29be4dc004b5fd2fdefba98237cd6e060f8c0cd501415fa8bdc5baefa",
+    "source_code_sha256": "fde7ed3ba6a8071c6b51a84ca3ca0d1e994670663e619d2473bd81dbe20edea3"
+  },
+  "gap_counts": {
+    "missing_parent": 3,
+    "credential_context": 123,
+    "generated_context": 221,
+    "history_window": 126,
+    "turn_limit": 357,
+    "compaction_or_rollback": 95,
+    "ancestor_scope_mismatch": 26,
+    "text_truncated": 23,
+    "nonvisible_message": 10,
+    "unparsed_record": 5,
+    "missing_ancestor": 3
+  },
+  "rejection_notes": "16 cases in one Claude source: repeated attachment UUIDs with differing parentUuid make ancestry ambiguous. Metadata-only slug changes alone are tolerated."
+}

package/core/dev/jev-eval/reports/history-corpus-2026-09-20.json

@@ -1,52 +1,52 @@
-{
-  "schema_version": 1,
-  "local_only": true,
-  "promotion_eligible": false,
-  "gold_labels": 0,
-  "target": 500,
-  "selected": 458,
-  "shortfall": 42,
-  "files_discovered": 638,
-  "candidate_count": 580,
-  "unique_count": 458,
-  "duplicate_count": 122,
-  "family_groups": 68,
-  "selected_sessions": 68,
-  "selected_groups": 68,
-  "exclusions": {
-    "records": 149355,
-    "automation_seed": 314,
-    "out_of_scope_or_subagent": 403,
-    "bytes_read": 402005275,
-    "excluded_files": 335,
-    "generated_message": 230,
-    "credential_message": 498,
-    "adjacent_duplicate": 11,
-    "oversize_line": 10,
-    "response_fallback_discarded": 371,
-    "response_fallback_candidates": 35,
-    "session_identity_change": 7,
-    "cross_file_automation_candidates": 0
-  },
-  "limitations": [
-    "Pending annotation only; no task goals or gold labels inferred.",
-    "Context contains preceding eligible user message only, not assistant context.",
-    "Secret detection is conservative heuristic, not a guarantee; review locally before reuse.",
-    "Explicit lineage and duplicate messages >=160 characters merge families; short duplicates are removed without merging; no split assigned."
-  ],
-  "verification": {
-    "tests_passed": 44,
-    "corpus_tests_passed": 11,
-    "source_counts": {
-      "claude": 160,
-      "codex": 298
-    },
-    "context_missing": 57,
-    "pending_sha256": "5f5a10efc646863feae904df71493854f25a3d8f82993c1b066ae6ddea9b9a0d",
-    "source_sha256": "61c69be358f848ee88fff2ec9d31975b91bd73fda16d8c243af2195db774575f",
-    "parent_checked_unique_ids_messages_manifest": true,
-    "human_verified": 0,
-    "external_requests": 0,
-    "first_export_rejected": true
-  }
-}
+{
+  "schema_version": 1,
+  "local_only": true,
+  "promotion_eligible": false,
+  "gold_labels": 0,
+  "target": 500,
+  "selected": 458,
+  "shortfall": 42,
+  "files_discovered": 638,
+  "candidate_count": 580,
+  "unique_count": 458,
+  "duplicate_count": 122,
+  "family_groups": 68,
+  "selected_sessions": 68,
+  "selected_groups": 68,
+  "exclusions": {
+    "records": 149355,
+    "automation_seed": 314,
+    "out_of_scope_or_subagent": 403,
+    "bytes_read": 402005275,
+    "excluded_files": 335,
+    "generated_message": 230,
+    "credential_message": 498,
+    "adjacent_duplicate": 11,
+    "oversize_line": 10,
+    "response_fallback_discarded": 371,
+    "response_fallback_candidates": 35,
+    "session_identity_change": 7,
+    "cross_file_automation_candidates": 0
+  },
+  "limitations": [
+    "Pending annotation only; no task goals or gold labels inferred.",
+    "Context contains preceding eligible user message only, not assistant context.",
+    "Secret detection is conservative heuristic, not a guarantee; review locally before reuse.",
+    "Explicit lineage and duplicate messages >=160 characters merge families; short duplicates are removed without merging; no split assigned."
+  ],
+  "verification": {
+    "tests_passed": 44,
+    "corpus_tests_passed": 11,
+    "source_counts": {
+      "claude": 160,
+      "codex": 298
+    },
+    "context_missing": 57,
+    "pending_sha256": "5f5a10efc646863feae904df71493854f25a3d8f82993c1b066ae6ddea9b9a0d",
+    "source_sha256": "61c69be358f848ee88fff2ec9d31975b91bd73fda16d8c243af2195db774575f",
+    "parent_checked_unique_ids_messages_manifest": true,
+    "human_verified": 0,
+    "external_requests": 0,
+    "first_export_rejected": true
+  }
+}