claude-spotter 1.5.2 → 1.5.4

package/CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## 1.5.4 — 2026-08-05
+
+- **Throughlineを提案監査の実行条件から撤去。** Claude / CodexのUserPromptSubmitは、
+  `auditorContext`のmode、Throughlineのfreshness、取得成否に関係なく、現在のuser promptと
+  host-local tool catalogで監査する。daemonも旧`audit:false`やcontext payloadで監査を止めず、
+  Throughline本文を監査AIへ渡さない。
+- **評価文脈だけを独立取得。** 提案が出た時のThroughline `observer-read`は改善用証拠として
+  一度だけ取得し、失敗時は評価文脈だけをunavailableにする。監査結果、親へのtool提案、
+  成功Hook eventには影響させず、retryやbackground回収も追加しない。
+- **停止を正常passへ偽装しない。** 旧版で`context_disabled` / `context_not_fresh` /
+  `auditor_context`となっていた経路を削除し、以後の監査成功turnは提案なしの場合も評価母数へ入る。
+  install / doctor / READMEもThroughlineを`evaluation context`として表示する。
+- **検証。** disabled / stale / provider error / legacy payload / observer-read failureを含む
+  Claude・Codex回帰テストとfull suite 588件（586 pass / 2 platform skip）を通過した。
+
+## 1.5.3 — 2026-08-04
+
+- **dashboardの難解な集計略号を廃止。** 概要cardとproject/tool別内訳の
+  `S/P/I/C/A/M`を、対象ターン、ツール提案あり、提案ツール数、利用判定済み、
+  実際に使用、判定不能の日本語表示へ置き換える。集計schemaとCLIの内部キーは変更しない。
+- **率の意味を式ではなく言葉で表示。** 提案率は「ツール提案あり ÷ 対象ターン」、
+  採用率は「実際に使用 ÷ 利用判定済み」と併記する。
+
 ## 1.5.2 — 2026-08-04
 
 - **Mac LaunchAgentでNodeを解決。** `spotter`の絶対pathだけでなく、env shebangが使う

package/README.ja.md

@@ -156,11 +156,16 @@ flowchart LR
 
 両者に共通するのは **「主体に頼らない仕組み」**。併用できます。
 
-### Throughline auditor context（既定ON）
+### Throughlineの提案時評価文脈（任意）
 
-`spotter install`はPATH上のThroughlineを絶対パスへ解決できる場合、auditor contextを既定で有効化します。
-旧版の既定`disabled` markerも通常の再installで有効化されます。過去に明示的に無効化したprojectは
-`origin: explicit`として保持され、勝手に再有効化されません。無効化するには次を実行します。
+Spotterの提案AIはThroughlineを使わず、Throughlineの導入・設定・freshness・取得成否に関係なく
+UserPromptSubmitごとに監査します。Throughlineは、提案が出た時に改善分析用の別文脈を
+`observer-read`で一度だけ記録する任意経路です。取得できなくても`context_unavailable`として記録するだけで、
+監査や親への助言には影響しません。
+
+`spotter install`がPATH上のThroughlineを絶対パスへ解決できる場合、この評価証拠の取得経路を既定で設定します。
+既存互換の`--auditor-context`名はmarker設定に残っていますが、監査のON/OFFは制御しません。
+評価文脈の取得だけを無効化するには次を実行します。
 
 ```bash
 spotter install -y --auditor-context disabled
@@ -183,24 +188,8 @@ spotter install -y --auditor-context throughline `
   --throughline-arg 'C:\absolute\path\to\throughline\bin\throughline.mjs'
 ```
 
-この connector の AI 呼出しは Codex CLI のみです。コンテキストを argv には載せず、AI へは stdin 経由で
-渡します。Haiku はこの context path に未対応であり、呼び出しません。Throughline 結果が `fresh` の時だけ
-AI 呼出し候補になり、それ以外の status では AI を呼びません。enabled connector の障害は hidden fallback
-ではなく固定 warning として出します。
-
-Throughline から渡すのは fresh な完了済み L2 user/assistant pair だけです。直近 2 pair (N=2)、各 body は
-600 文字、合計は 4,000 文字に制限します。Spotter は Throughline の L2、`reason`、`raw` を親へ反射せず、
-親には安全な catalog tool ID から作る固定・非命令形の助言だけを渡します。`spotter doctor` は command / args
-を表示せず、auditor-context mode と固定の availability detail だけを表示します。
-
-v2 model-matrix では context choice を明示できます。
-
-```bash
-spotter auditor model-matrix --fixtures test/fixtures/auditor-model-matrix.v2.json \
-  --recent-turns 2 --body-cap 600
-```
-
-評価結論はN=2 / 600です。既定ONは確定済みで、7日・30 fresh resultの実運用測定は精度改善に使います。
+`spotter doctor`はこの経路を`evaluation context`として表示し、command / argsや会話本文は表示しません。
+observer snapshotは端末内の評価SQLiteにだけ保存され、network送信、retry、background回収は行いません。
 
 ## よく使うコマンド
 

package/README.md

@@ -156,12 +156,18 @@ The audited catalog is host-local: Claude uses `<project>/.spotter/tool-db.json`
 
 Both share the principle of **"don't rely on the primary agent to do it itself."** They compose well — you can run them together.
 
-### Throughline auditor context (default-on)
+### Optional Throughline evidence for proposal evaluation
 
-When `spotter install` can resolve Throughline on PATH to an absolute executable,
-auditor context is enabled by default. A normal reinstall migrates legacy markers
-whose disabled state came from the old default. An explicit project opt-out is
-stored with `origin: explicit` and is never silently re-enabled. Disable it with:
+Spotter's proposal auditor does not use Throughline. Every UserPromptSubmit
+audit runs independently of Throughline installation, configuration, freshness, or read
+failures. When Spotter emits a proposal, the evaluation recorder may call
+Throughline `observer-read` once to save separate improvement evidence. A failed
+read is recorded as `context_unavailable` and never changes auditing or parent advice.
+
+When `spotter install` resolves Throughline on PATH to an absolute executable, it
+configures this evaluation-evidence path by default. The legacy option name
+`--auditor-context` remains for marker compatibility but no longer controls whether
+auditing runs. Disable only the evidence capture with:
 
 ```bash
 spotter install -y --auditor-context disabled
@@ -185,28 +191,9 @@ spotter install -y --auditor-context throughline `
   --throughline-arg 'C:\absolute\path\to\throughline\bin\throughline.mjs'
 ```
 
-The connector is Codex CLI-only. It sends no context in argv: the bounded
-projection is supplied to that AI over stdin. Haiku does not support this
-context path and is never called for it. Only a `fresh` Throughline result is
-eligible for an AI call; every other status skips AI. An enabled connector
-failure becomes a fixed warning, not a hidden fallback.
-
-Throughline contributes only fresh, completed L2 user/assistant pairs: two
-recent pairs (N=2), each body capped at 600 characters and 4,000 characters in
-total. Spotter never reflects Throughline L2, `reason`, or `raw` to the parent.
-The parent receives only fixed non-imperative advice built from safe catalog tool
-IDs. `spotter doctor` displays the auditor-context mode and a fixed availability
-detail without printing its command or arguments.
-
-The v2 model-matrix can make the context choice explicit:
-
-```bash
-spotter auditor model-matrix --fixtures test/fixtures/auditor-model-matrix.v2.json \
-  --recent-turns 2 --body-cap 600
-```
-
-The evaluated setting is N=2 / 600. Default-on is final; the 7-day,
-30-fresh-result sample is used only to identify precision improvements.
+`spotter doctor` reports this as `evaluation context` without printing commands,
+arguments, or conversation text. Observer snapshots stay in the terminal-local
+evaluation SQLite. Spotter adds no network upload, retry, or background recovery.
 
 ## Common commands
 
@@ -256,8 +243,9 @@ spotter uninstall        # remove hooks from this project (leaves ~/.spotter int
 
 The dashboard is local-first. Every terminal reads its own `~/.spotter/evaluation.db`; the hub
 keeps only a static device-to-upstream map and does not copy evaluation data into a cloud database.
-The device view shows `S/P/I/C/A/M`, proposal and adoption rates, project/tool breakdowns,
-non-adopted cases, and the two separately captured context sources. The hub checks health only
+The device view shows Japanese labels for every evaluation metric, proposal and adoption rates
+with their numerator and denominator, project/tool breakdowns, non-adopted cases, and the two
+separately captured context sources. The hub checks health only
 when the device list is requested, so an offline terminal is isolated without a background monitor
 or retry queue.
 

package/bin/spotter.mjs

@@ -28,8 +28,8 @@ Usage:
                                         [--throughline-command ABS] [--throughline-arg VALUE]
                                         register hooks in <cwd>/.claude/settings.json
                                         and create <cwd>/.spotter/marker.json
-                                        (Throughline on PATH enables context by default;
-                                         pass disabled for a persistent project opt-out)
+                                        (Throughline on PATH enables proposal-time
+                                         evaluation evidence by default; it never gates auditing)
                                         (run inside each project you want audited)
   spotter install --user [-y]           legacy: register globally in ~/.claude/settings.json
                                         (NOT RECOMMENDED — fires for every Claude Code session

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-spotter",
-  "version": "1.5.2",
+  "version": "1.5.4",
   "description": "Audit agent running alongside Claude Code that catches missed tool calls — 気づく役と実行する役の分離",
   "type": "module",
   "bin": {

package/src/cli/codex-hook-cmd.mjs

@@ -30,10 +30,6 @@ import {
   hookEventsPath,
   summarizeHookEvents,
 } from '../core/hook-event-log.mjs';
-import {
-  loadAuditorContext,
-  readProjectAuditorContextConfig,
-} from '../core/auditor-context.mjs';
 import { observeRuntimeErrorIsolatedSafe } from '../core/runtime-error-store.mjs';
 import { createEvaluationStore } from '../core/evaluation-store.mjs';
 import { loadEvaluationObserverContext } from '../core/evaluation-context.mjs';
@@ -130,8 +126,6 @@ export async function runCodexUserPromptSubmitHook({
   createAuditorBackendFn = createAuditorBackend,
   recordHookEventFn = appendCodexHookEvent,
   discardLegacyPendingFn = discardLegacyPending,
-  readAuditorContextConfigFn = readProjectAuditorContextConfig,
-  loadAuditorContextFn = loadAuditorContext,
   writeOutput = (text) => process.stdout.write(text),
   writeError = (text) => process.stderr.write(text),
   runtimeErrorObserver = async () => ({ collected: false, reason: 'observer_not_configured' }),
@@ -147,12 +141,10 @@ export async function runCodexUserPromptSubmitHook({
   const projectRoot = findSpotterMarker(input.cwd);
   if (!projectRoot) return;
   const startedAt = Date.now();
-  let contextDurationMs = null;
-  let auditorContextConfig;
 
   const prompt = requireString(input, 'prompt');
   const sessionId = codexSessionId(input);
-  const recordEvaluation = async ({ auditStatus, proposedToolIds = [], backend = null, model = null, auditorSeenContext = null, config = undefined }) => {
+  const recordEvaluation = async ({ auditStatus, proposedToolIds = [], backend = null, model = null }) => {
     if (!sessionId) {
       reportEvaluationFailure(writeError);
       return;
@@ -167,7 +159,6 @@ export async function runCodexUserPromptSubmitHook({
           projectRoot,
           host: 'codex',
           sessionId,
-          config,
           recordedAtMs: proposedAtMs,
         });
       }
@@ -182,7 +173,7 @@ export async function runCodexUserPromptSubmitHook({
           sessionId,
           auditStatus,
           requestText: prompt,
-          auditorSeenContext,
+          auditorSeenContext: null,
           observerContextStatus: observerContext.status,
           observerSnapshot: observerContext.snapshot,
           proposedToolIds: proposals.resolvedToolIds,
@@ -198,97 +189,6 @@ export async function runCodexUserPromptSubmitHook({
     }
   };
   const legacyPending = await discardLegacyPendingFn({ projectRoot, sessionId: codexSessionId(input) });
-  let context;
-  const contextStartedAt = Date.now();
-  try {
-    const config = await readAuditorContextConfigFn(projectRoot);
-    auditorContextConfig = config;
-    contextDurationMs = Date.now() - contextStartedAt;
-    if (config.mode === 'disabled') {
-      await recordEvaluation({ auditStatus: 'skipped' });
-      await recordCodexHookEventSafe(recordHookEventFn, {
-        projectRoot,
-        event: {
-          hook: 'UserPromptSubmit',
-          status: 'skipped',
-          reason: 'context_disabled',
-          contextStatus: 'disabled',
-          contextDurationMs,
-          legacyPendingDiagnostic: legacyPending.diagnostic,
-          durationMs: Date.now() - startedAt,
-        },
-      }, writeError);
-      return;
-    }
-    context = await loadAuditorContextFn({
-      config,
-      host: 'codex',
-      sessionId: requireCodexSessionId(input),
-      projectRoot,
-      transcriptPath: requireString(input, 'transcript_path'),
-    });
-    contextDurationMs = Date.now() - contextStartedAt;
-  } catch (err) {
-    await recordEvaluation({ auditStatus: 'error' });
-    await observeRuntimeFailure(runtimeErrorObserver, 'auditor_unavailable');
-    contextDurationMs = Date.now() - contextStartedAt;
-    const failure = projectBackendFailure(err?.code);
-    safeWriteError(writeError, failure.stderr);
-    await recordCodexHookEventSafe(recordHookEventFn, {
-      projectRoot,
-      event: {
-        hook: 'UserPromptSubmit',
-        status: 'error',
-        code: failure.code,
-        reason: 'auditor_context',
-        contextDurationMs,
-        legacyPendingDiagnostic: legacyPending.diagnostic,
-        durationMs: Date.now() - startedAt,
-      },
-    }, writeError);
-    writeCodexSystemMessage({ systemMessage: failure.systemMessage, writeOutput });
-    return;
-  }
-  if (context.status === 'unavailable' || context.status === 'schema_mismatch') {
-    await recordEvaluation({ auditStatus: 'error' });
-    await observeRuntimeFailure(runtimeErrorObserver, 'auditor_unavailable');
-    const failure = projectBackendFailure(context.status === 'unavailable'
-      ? 'E_AUDITOR_CONTEXT_UNAVAILABLE'
-      : 'E_AUDITOR_CONTEXT_SCHEMA');
-    safeWriteError(writeError, failure.stderr);
-    await recordCodexHookEventSafe(recordHookEventFn, {
-      projectRoot,
-      event: {
-        hook: 'UserPromptSubmit',
-        status: 'error',
-        code: failure.code,
-        reason: 'auditor_context_status',
-        contextDurationMs,
-        legacyPendingDiagnostic: legacyPending.diagnostic,
-        durationMs: Date.now() - startedAt,
-      },
-    }, writeError);
-    writeCodexSystemMessage({ systemMessage: failure.systemMessage, writeOutput });
-    return;
-  }
-  if (context.status !== 'fresh') {
-    await recordEvaluation({ auditStatus: 'skipped' });
-    await recordCodexHookEventSafe(recordHookEventFn, {
-      projectRoot,
-      event: {
-        hook: 'UserPromptSubmit',
-        status: 'skipped',
-        reason: 'context_not_fresh',
-        contextStatus: context.status,
-        contextTurns: 0,
-        contextChars: 0,
-        contextDurationMs,
-        legacyPendingDiagnostic: legacyPending.diagnostic,
-        durationMs: Date.now() - startedAt,
-      },
-    }, writeError);
-    return;
-  }
 
   let catalog;
   let backend;
@@ -301,8 +201,6 @@ export async function runCodexUserPromptSubmitHook({
     judgment = await backend.judge({
       stage: 'user_input',
       userInput: prompt,
-      recentContext: context.turns,
-      contextStatus: 'fresh',
     });
   } catch (err) {
     await recordEvaluation({ auditStatus: 'error', backend: err?.backend ?? null, model: err?.diagnostics?.modelSelection?.effectiveModel ?? null });
@@ -332,10 +230,6 @@ export async function runCodexUserPromptSubmitHook({
       backend: judgment.meta?.backend ?? backend.name ?? 'unknown',
       pass: judgment.pass,
       missingTools: projectToolIds(judgment.findings.map((finding) => finding.toolName)),
-      contextStatus: 'fresh',
-      contextTurns: context.stats.returnedTurns,
-      contextChars: context.stats.chars,
-      contextDurationMs,
       ...compactCodexModelSelectionForEvent(judgment.meta?.modelSelection),
       legacyPendingDiagnostic: legacyPending.diagnostic,
       backendDurationMs: judgment.meta?.durationMs ?? null,
@@ -357,8 +251,6 @@ export async function runCodexUserPromptSubmitHook({
     proposedToolIds: toolIds,
     backend: judgment.meta?.backend ?? backend.name ?? 'unknown',
     model: judgment.meta?.modelSelection?.effectiveModel ?? null,
-    auditorSeenContext: JSON.stringify(context.turns),
-    config: auditorContextConfig,
   });
   const advice = projectParentAdvice(toolIds);
   if (advice) writeCodexUserPromptContexts({ contexts: [advice], writeOutput });
@@ -848,14 +740,6 @@ function codexSessionId(payload) {
   return typeof value === 'string' && value.length > 0 ? value : null;
 }
 
-function requireCodexSessionId(payload) {
-  const value = codexSessionId(payload);
-  if (value) return value;
-  const err = new Error('session_id is required');
-  err.code = 'E_AUDITOR_CONTEXT_INPUT';
-  throw err;
-}
-
 // v1.4.19: legacy pending migration is handled only by `discardLegacyPending` on
 // UserPromptSubmit. Stop findings are never persisted for a future parent prompt.
 

package/src/cli/doctor.mjs

@@ -78,7 +78,7 @@ export async function runDoctor() {
     if (!sidecar.ok) warnings += 1;
 
     const auditorContext = await inspectAuditorContextConfiguration({ projectRoot });
-    mark(auditorContext.ok, `auditor context: ${auditorContext.mode}`, auditorContext.detail);
+    mark(auditorContext.ok, `evaluation context: ${auditorContext.mode}`, auditorContext.detail);
     if (!auditorContext.ok) warnings += 1;
   }
 

package/src/cli/factory-diagnostics.mjs

@@ -45,7 +45,7 @@ export async function runFactoryDiagnostics({
   if (contextMode === null) {
     checks.push(check('throughline_context', 'fail', 'invalid_context_configuration'));
   } else if (contextMode === 'disabled') {
-    checks.push(check('throughline_context', 'skipped', 'context_disabled'));
+    checks.push(check('throughline_context', 'skipped', 'evaluation_evidence_disabled'));
   } else {
     const context = await inspectAuditorContextFn({ projectRoot });
     checks.push(context?.ok === true && context?.mode === 'throughline'

package/src/cli/install.mjs

@@ -102,12 +102,12 @@ export async function runInstall({
     };
     await writeFile(markerPath, JSON.stringify(marker, null, 2) + '\n', 'utf8');
     console.log(`  wrote ${markerPath}`);
-    console.log(`  auditor context: ${preservedAuditorContext.mode} (${preservedAuditorContext.origin})`);
+    console.log(`  evaluation context provider: ${preservedAuditorContext.mode} (${preservedAuditorContext.origin})`);
     if (preservedAuditorContext.mode === 'throughline') {
-      console.log('  sends bounded completed user/assistant text to the selected Codex auditor; disable with:');
+      console.log('  captures bounded proposal-time observer evidence; this never gates auditing; disable evidence capture with:');
       console.log('    spotter install -y --auditor-context disabled');
     } else if (preservedAuditorContext.reason === 'throughline_unavailable') {
-      console.log('  Throughline was not found; context auditing remains disabled (no current-only fallback)');
+      console.log('  Throughline was not found; proposal-time observer evidence is unavailable, but auditing remains active');
     }
   }
 

package/src/daemon/daemon.mjs

@@ -277,30 +277,7 @@ export async function startDaemon({
       ? payload.observation_id
       : null;
 
-    if (payload.audit === false) {
-      logFn('user_input: audit skipped because fresh context was unavailable');
-      return { pass: true, missing_tools: [], reason: 'auditor_context_not_fresh' };
-    }
-
-    const hasContext = payload.context_status !== undefined || payload.recent_context !== undefined;
-    if (hasContext && (payload.context_status !== 'fresh' || !Array.isArray(payload.recent_context))) {
-      const err = new Error('context-bearing user_input payload must include fresh recent_context');
-      err.code = 'E_AUDITOR_CONTEXT_INPUT';
-      throw err;
-    }
-    if (hasContext && auditorBackend.name === 'haiku') {
-      const err = new Error('recent conversation context is not supported by the haiku auditor backend');
-      err.code = 'E_AUDITOR_CONTEXT_BACKEND_UNSUPPORTED';
-      throw err;
-    }
-    const judgment = await runAuditorJudgment(hasContext
-      ? {
-          stage: 'user_input',
-          userInput,
-          recentContext: payload.recent_context,
-          contextStatus: 'fresh',
-        }
-      : { stage: 'user_input', userInput });
+    const judgment = await runAuditorJudgment({ stage: 'user_input', userInput });
     const result = legacyResultFromJudgment(judgment);
     const meta = judgment.meta ?? {};
     logFn(

package/src/dashboard/render.mjs

@@ -3,6 +3,14 @@
 // opens EvaluationStore or asks Throughline for context.
 
 const METRIC_KEYS = ['S', 'P', 'I', 'C', 'A', 'M'];
+const METRIC_LABELS = {
+  S: '対象ターン',
+  P: 'ツール提案あり',
+  I: '提案ツール数',
+  C: '利用判定済み',
+  A: '実際に使用',
+  M: '判定不能',
+};
 
 /**
  * Render a complete dashboard document.
@@ -96,7 +104,7 @@ function renderDeviceContent({ overview, cases, caseDetail, filters, action }) {
   return `${renderFilters(filters, action)}
 <section aria-labelledby="overview-heading">
   <div class="section-heading"><h2 id="overview-heading">概要</h2>${renderRates(totals)}</div>
-  <div class="metrics" aria-label="評価メトリクス">${METRIC_KEYS.map((key) => `<article class="metric"><span>${key}</span><strong>${escapeHtml(metric(totals, key))}</strong></article>`).join('')}</div>
+  <div class="metrics" aria-label="評価メトリクス">${METRIC_KEYS.map((key) => `<article class="metric"><span>${METRIC_LABELS[key]}</span><strong>${escapeHtml(metric(totals, key))}</strong></article>`).join('')}</div>
 </section>
 ${renderBreakdown('project-breakdown', 'project別内訳', projects)}
 ${renderBreakdown('tool-breakdown', 'tool別内訳', tools)}
@@ -119,13 +127,13 @@ function renderFilters(filters, action) {
 function renderRates(summary) {
   const proposal = rate(metricNumber(summary, 'P'), metricNumber(summary, 'S'));
   const adoption = rate(metricNumber(summary, 'A'), metricNumber(summary, 'C'));
-  return `<dl class="rates"><div><dt>提案率 P/S</dt><dd>${escapeHtml(proposal)}</dd></div><div><dt>採用率 A/C</dt><dd>${escapeHtml(adoption)}</dd></div></dl>`;
+  return `<dl class="rates"><div><dt>提案率<small>ツール提案あり ÷ 対象ターン</small></dt><dd>${escapeHtml(proposal)}</dd></div><div><dt>採用率<small>実際に使用 ÷ 利用判定済み</small></dt><dd>${escapeHtml(adoption)}</dd></div></dl>`;
 }
 
 function renderBreakdown(id, title, rows) {
   return `<section aria-labelledby="${id}">
   <h2 id="${id}">${title}</h2>
-  ${rows.length === 0 ? '<p class="empty">該当するデータはありません。</p>' : `<div class="table-wrap"><table><thead><tr><th scope="col">項目</th>${METRIC_KEYS.map((key) => `<th scope="col">${key}</th>`).join('')}<th scope="col">提案率</th><th scope="col">採用率</th></tr></thead><tbody>${rows.map(([label, summary]) => `<tr><th scope="row">${escapeHtml(label)}</th>${METRIC_KEYS.map((key) => `<td>${escapeHtml(metric(summary, key))}</td>`).join('')}<td>${escapeHtml(rate(metricNumber(summary, 'P'), metricNumber(summary, 'S')))}</td><td>${escapeHtml(rate(metricNumber(summary, 'A'), metricNumber(summary, 'C')))}</td></tr>`).join('')}</tbody></table></div>`}
+  ${rows.length === 0 ? '<p class="empty">該当するデータはありません。</p>' : `<div class="table-wrap"><table><thead><tr><th scope="col">項目</th>${METRIC_KEYS.map((key) => `<th scope="col">${METRIC_LABELS[key]}</th>`).join('')}<th scope="col">提案率</th><th scope="col">採用率</th></tr></thead><tbody>${rows.map(([label, summary]) => `<tr><th scope="row">${escapeHtml(label)}</th>${METRIC_KEYS.map((key) => `<td>${escapeHtml(metric(summary, key))}</td>`).join('')}<td>${escapeHtml(rate(metricNumber(summary, 'P'), metricNumber(summary, 'S')))}</td><td>${escapeHtml(rate(metricNumber(summary, 'A'), metricNumber(summary, 'C')))}</td></tr>`).join('')}</tbody></table></div>`}
 </section>`;
 }
 
@@ -217,8 +225,8 @@ h1 { margin: .25rem 0; font-size: clamp(1.75rem, 4vw, 2.5rem); } h2 { margin-top
 .device { align-items: center; border: 1px solid #ccd4dd; border-radius: 999px; color: inherit; display: inline-flex; gap: .45rem; padding: .45rem .7rem; text-decoration: none; }
 .device[aria-current="page"] { border-color: #1c63b8; box-shadow: 0 0 0 2px #b8d6fa; }.device small { color: #52606d; }.status-dot { background: #a03333; border-radius: 50%; height: .55rem; width: .55rem; }.online .status-dot { background: #16803c; }
 .filters { align-items: end; display: flex; flex-wrap: wrap; gap: .75rem; margin: 1.5rem 0; }.filters label { display: grid; font-size: .85rem; gap: .25rem; }.filters input, button { border: 1px solid #aeb8c4; border-radius: .35rem; font: inherit; padding: .45rem; }button { background: #1c63b8; color: white; cursor: pointer; }
-.section-heading { align-items: baseline; display: flex; flex-wrap: wrap; gap: 1rem; justify-content: space-between; }.rates { display: flex; gap: 1.25rem; margin: 0; }.rates div { display: flex; gap: .35rem; }.rates dt { color: #52606d; }.rates dd { font-weight: 700; margin: 0; }
-.metrics { display: grid; gap: .75rem; grid-template-columns: repeat(6, minmax(90px, 1fr)); }.metric { background: #fff; border: 1px solid #d7dce2; border-radius: .5rem; padding: .8rem; }.metric span { color: #52606d; display: block; }.metric strong { font-size: 1.5rem; }
+.section-heading { align-items: baseline; display: flex; flex-wrap: wrap; gap: 1rem; justify-content: space-between; }.rates { display: flex; gap: 1.25rem; margin: 0; }.rates div { display: flex; gap: .45rem; }.rates dt { color: #52606d; }.rates dt small { display: block; font-size: .72rem; }.rates dd { font-weight: 700; margin: 0; }
+.metrics { display: grid; gap: .75rem; grid-template-columns: repeat(6, minmax(110px, 1fr)); }.metric { background: #fff; border: 1px solid #d7dce2; border-radius: .5rem; padding: .8rem; }.metric span { color: #52606d; display: block; }.metric strong { font-size: 1.5rem; }
 .table-wrap { overflow-x: auto; }table { border-collapse: collapse; min-width: 680px; width: 100%; }th, td { border-bottom: 1px solid #d7dce2; padding: .6rem; text-align: left; vertical-align: top; }thead { background: #eaf0f6; }tbody tr:nth-child(even) { background: #fbfcfd; }
 .case-detail { border-top: 2px solid #1c63b8; margin-top: 2.5rem; }.metadata { display: flex; flex-wrap: wrap; gap: 1rem; }.metadata div { min-width: 12rem; }.metadata dt { color: #52606d; }.metadata dd { margin: .2rem 0; overflow-wrap: anywhere; }pre { background: #1e2935; color: #e6edf3; margin: 0; overflow-x: auto; padding: 1rem; white-space: pre-wrap; word-break: break-word; }
 @media (max-width: 700px) { .dashboard { padding-top: 1rem; }.metrics { grid-template-columns: repeat(3, 1fr); }.filters { align-items: stretch; flex-direction: column; }.filters input, button { width: 100%; }.rates { flex-direction: column; gap: .25rem; } }

package/src/hooks/user-prompt.mjs

@@ -25,10 +25,6 @@ import { sendRequest, TransportError } from '../daemon/transport.mjs';
 import { spawnDaemonAndWaitReady } from './spawn-daemon.mjs';
 import { discardLegacyPending } from './pending-context.mjs';
 import { projectBackendFailure, projectParentAdvice, projectToolIds } from './parent-output-projector.mjs';
-import {
-  loadAuditorContext,
-  readProjectAuditorContextConfig,
-} from '../core/auditor-context.mjs';
 import { randomUUID } from 'node:crypto';
 import { createEvaluationStore } from '../core/evaluation-store.mjs';
 import { loadEvaluationObserverContext } from '../core/evaluation-context.mjs';
@@ -41,8 +37,6 @@ export async function runUserPrompt({
   sendRequestFn = sendRequest,
   spawnDaemonAndWaitReadyFn = spawnDaemonAndWaitReady,
   discardLegacyPendingFn = discardLegacyPending,
-  readAuditorContextConfigFn = readProjectAuditorContextConfig,
-  loadAuditorContextFn = loadAuditorContext,
   recordHookEventFn = recordClaudeHookEvent,
   createEvaluationStoreFn = createEvaluationStore,
   loadEvaluationObserverContextFn = loadEvaluationObserverContext,
@@ -62,10 +56,9 @@ export async function runUserPrompt({
   const observationId = randomUUIDFn();
   const projectRoot = findSpotterMarker(input.cwd);
   const startedAt = Date.now();
-  let contextDurationMs = null;
   let evaluationWriteFailed = false;
 
-  const safelyRecordEvaluation = async ({ auditStatus, result = null, auditContext = null }) => {
+  const safelyRecordEvaluation = async ({ auditStatus, result = null }) => {
     if (!projectRoot) return;
     try {
       const proposedToolIds = auditStatus === 'success' && result?.pass !== true
@@ -77,7 +70,6 @@ export async function runUserPrompt({
           projectRoot,
           host: 'claude',
           sessionId,
-          config: auditContext?.config,
           recordedAtMs: proposalRecordedAtMs,
         })
         : { status: 'not_requested', snapshot: null };
@@ -94,7 +86,7 @@ export async function runUserPrompt({
           sessionId,
           auditStatus,
           requestText: prompt,
-          auditorSeenContext: auditContext?.turns ? JSON.stringify(auditContext.turns) : null,
+          auditorSeenContext: null,
           observerContextStatus: observer.status,
           observerSnapshot: observer.snapshot,
           proposedToolIds,
@@ -128,7 +120,6 @@ export async function runUserPrompt({
         status: 'degraded',
         code: failure.code,
         reason,
-        contextDurationMs,
         legacyPendingDiagnostic: legacyPending.diagnostic,
         durationMs: Date.now() - startedAt,
       },
@@ -151,108 +142,12 @@ export async function runUserPrompt({
     }
   };
 
-  const syncUserInputWithoutAudit = async (contextStatus) => {
-    try {
-      const response = await sendDaemonPayload({
-        user_input: prompt,
-        observation_id: observationId,
-        audit: false,
-        context_status: contextStatus,
-      });
-      if (response.ok !== true) {
-        await degrade({ code: response.error?.code ?? 'E_INTERNAL', reason: 'daemon_state_sync' });
-        return false;
-      }
-      return true;
-    } catch (err) {
-      await degrade({ code: err?.code, reason: 'daemon_state_sync' });
-      return false;
-    }
-  };
-
-  let context;
-  let auditorContextConfig;
-  const contextStartedAt = Date.now();
-  try {
-    const config = await readAuditorContextConfigFn(projectRoot);
-    auditorContextConfig = config;
-    contextDurationMs = Date.now() - contextStartedAt;
-    if (config.mode === 'disabled') {
-      if (!await syncUserInputWithoutAudit('disabled')) {
-        await safelyRecordEvaluation({ auditStatus: 'error' });
-        return;
-      }
-      await safelyRecordEvaluation({ auditStatus: 'skipped' });
-      await recordHookEventFn({
-        projectRoot,
-        event: {
-          hook: 'UserPromptSubmit',
-          status: 'skipped',
-          reason: 'context_disabled',
-          contextStatus: 'disabled',
-          contextDurationMs,
-          legacyPendingDiagnostic: legacyPending.diagnostic,
-          durationMs: Date.now() - startedAt,
-        },
-      });
-      return;
-    }
-    context = await loadAuditorContextFn({
-      config,
-      host: 'claude',
-      sessionId,
-      projectRoot,
-      transcriptPath: requireString(input, 'transcript_path'),
-    });
-    contextDurationMs = Date.now() - contextStartedAt;
-  } catch (err) {
-    contextDurationMs = Date.now() - contextStartedAt;
-    await degrade({ code: err?.code, reason: 'auditor_context' });
-    await safelyRecordEvaluation({ auditStatus: 'error' });
-    return;
-  }
-
-  if (context.status === 'unavailable' || context.status === 'schema_mismatch') {
-    await degrade({
-      code: context.status === 'unavailable'
-        ? 'E_AUDITOR_CONTEXT_UNAVAILABLE'
-        : 'E_AUDITOR_CONTEXT_SCHEMA',
-      reason: 'auditor_context_status',
-    });
-    await safelyRecordEvaluation({ auditStatus: 'error' });
-    return;
-  }
-  if (context.status !== 'fresh') {
-    if (!await syncUserInputWithoutAudit(context.status)) {
-      await safelyRecordEvaluation({ auditStatus: 'error' });
-      return;
-    }
-    await safelyRecordEvaluation({ auditStatus: 'skipped' });
-    await recordHookEventFn({
-      projectRoot,
-      event: {
-        hook: 'UserPromptSubmit',
-        status: 'skipped',
-        reason: 'context_not_fresh',
-        contextStatus: context.status,
-        contextTurns: 0,
-        contextChars: 0,
-        contextDurationMs,
-        legacyPendingDiagnostic: legacyPending.diagnostic,
-        durationMs: Date.now() - startedAt,
-      },
-    });
-    return;
-  }
-
   let response;
   try {
     response = await sendDaemonPayload({
       user_input: prompt,
       observation_id: observationId,
       audit: true,
-      context_status: 'fresh',
-      recent_context: context.turns,
     });
   } catch (err) {
     await degrade({ code: err?.code ?? 'E_RESURRECT_FAILED', reason: 'transport_or_resurrect' });
@@ -278,7 +173,6 @@ export async function runUserPrompt({
   await safelyRecordEvaluation({
     auditStatus: 'success',
     result,
-    auditContext: { config: auditorContextConfig, turns: context.turns },
   });
   if (advice) emitAdditionalContext(writeOutput, advice);
 
@@ -289,10 +183,6 @@ export async function runUserPrompt({
       status: 'success',
       pass: result.pass === true,
       missingTools: toolIds,
-      contextStatus: 'fresh',
-      contextTurns: context.stats.returnedTurns,
-      contextChars: context.stats.chars,
-      contextDurationMs,
       legacyPendingDiagnostic: legacyPending.diagnostic,
       durationMs: Date.now() - startedAt,
     },