claude-spotter 1.5.3 → 1.5.5

package/CHANGELOG.md

@@ -1,5 +1,30 @@
 # Changelog
 
+## 1.5.5 — 2026-08-05
+
+- **提案時文脈をexact sessionへ戻した。** 評価記録がproject全体の最新threadを読む
+  `observer-read`を誤って使っていた経路を撤去し、既存のThroughline `auditor-context`へ一本化した。
+  Claude / CodexのUserPromptSubmit hookから提案元の`session_id`、`host`、`transcript_path`を渡し、
+  提案直前の完了turnを非採用caseへ保存できる。
+- **重複adapterを廃止。** 評価専用readerは、すでにfreshness・本文上限・exact-session照合を持つ
+  `loadAuditorContext`を再利用する。Throughline本文をauditor入力へ戻さず、監査と評価証拠の分離は維持する。
+- **検証。** 既存adapterへの引数接続とClaude / Codex hookのfocused testを通過した。
+
+## 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

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。提案が出た時だけ、改善分析用の別文脈としてThroughline
+`auditor-context`を提案元のexact sessionとtranscriptで一度だけ呼びます。返されたfreshな直前完了turnは
+監査入力と混ぜずに保存します。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。
+評価文脈は端末内の評価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
 
@@ -217,12 +206,16 @@ spotter db rebuild       # Claude local + Claude global DB を両方消してか
 spotter status           # 稼働中の daemon 一覧
 spotter doctor           # 環境診断 (Node / claude CLI / Codex readiness / tool-db 整合性)
 spotter diagnostics logs # daemon log から pass=false / backend latency / anomaly signal を集計
+spotter diagnostics factory
+                         # factory向けread-only診断snapshotをJSONで出力
+spotter diagnostics runtime-errors
+                         # opt-in端末内runtime error集計をread-only表示（network送信なし）
 spotter evaluation report
                          # 端末内DBからproject横断の提案率・tool採用率を集計
 spotter evaluation cases --outcome not-adopted
                          # 提案されたが同じturnで使われなかったtool itemを一覧
 spotter evaluation case <observation-id>
-                         # request、2種類の文脈、提案、利用、outcomeを確認
+                         # request、任意のThroughline snapshot、提案、利用、outcomeを確認
 spotter dashboard device --id mac --name Mac
                          # この端末の評価DBを127.0.0.1:53940で配信
 spotter dashboard hub --config dashboard-hub.json --host 172.18.0.1
@@ -247,8 +240,9 @@ spotter uninstall        # hook 登録を解除 (~/.spotter は残す)
 
 dashboardはlocal-firstで動く。各端末が自身の`~/.spotter/evaluation.db`を読み、hubは固定の
 端末・upstream対応だけを持つ。評価データをcloud DBへ複製しない。端末画面では
-`S/P/I/C/A/M`、提案率、採用率、project/tool内訳、非採用case、別々に取得した2種類の文脈を
-確認できる。health確認は端末一覧request時だけなので、端末がofflineでもbackground監視や
+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、提案率、採用率、
+project/tool内訳、非採用case、監査対象request、任意の提案時Throughline証拠を確認できる。
+health確認は端末一覧request時だけなので、端末がofflineでもbackground監視や
 retry queueを作らず、その端末だけを切り離せる。
 
 4端末のservice、reverse tunnel、Caddy/Cloudflare構成は

package/README.md

@@ -156,12 +156,20 @@ 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 calls Throughline
+`auditor-context` once with the proposing host's exact session ID and transcript path.
+The bounded, fresh completed turns are saved as separate improvement evidence; they are
+never auditor input. 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 +193,9 @@ 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
 
@@ -231,7 +220,7 @@ spotter evaluation report
 spotter evaluation cases --outcome not-adopted
                          # list proposed tools that were not used in the same turn
 spotter evaluation case <observation-id>
-                         # inspect request, Spotter context, Throughline snapshot, proposal, usage, and outcome
+                         # inspect request, optional Throughline snapshot, proposal, usage, and outcome
 spotter dashboard device --id mac --name Mac
                          # serve this terminal's local evaluation DB on 127.0.0.1:53940
 spotter dashboard hub --config dashboard-hub.json --host 172.18.0.1
@@ -257,8 +246,8 @@ 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 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
+with their numerator and denominator, project/tool breakdowns, non-adopted cases, the request
+audited by Spotter, and optional proposal-time Throughline evidence. 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/docs/11_dashboard-operations.md

@@ -1,5 +1,8 @@
 # Spotter評価dashboard運用
 
+現行配布版: **v1.5.4**（2026-08-05）。Mac、main-server、FOX WSL2、FOX Windows nativeへ
+global install済み。v1.5.4は監査gate修正でありdashboard routing構成はv1.5.3から変更していない。
+
 ## 固定構成
 
 各端末のdevice serverはloopbackだけで待ち受ける。main-server、Mac、FOX WSL2は

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-spotter",
-  "version": "1.5.3",
+  "version": "1.5.5",
   "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

@@ -30,13 +30,9 @@ 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';
+import { loadEvaluationContext } from '../core/evaluation-context.mjs';
 import {
   canonicalizeCodexNestedMcpToolIds,
   canonicalizeCodexSkillReadToolIds,
@@ -130,13 +126,11 @@ 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' }),
   createEvaluationStoreFn = createEvaluationStore,
-  loadEvaluationObserverContextFn = loadEvaluationObserverContext,
+  loadEvaluationContextFn = loadEvaluationContext,
   randomUUIDFn = randomUUID,
   now = () => Date.now(),
 } = {}) {
@@ -147,27 +141,25 @@ 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;
     }
     const proposals = canonicalizeProposedToolIds(proposedToolIds);
-    let observerContext = { status: 'not_requested', snapshot: null };
+    let evaluationContext = { status: 'not_requested', snapshot: null };
     let proposedAtMs = recordedAtMs;
     try {
       if (auditStatus === 'success' && proposals.resolvedToolIds.length > 0) {
         proposedAtMs = now();
-        observerContext = await loadEvaluationObserverContextFn({
+        evaluationContext = await loadEvaluationContextFn({
           projectRoot,
           host: 'codex',
           sessionId,
-          config,
+          transcriptPath: input.transcript_path,
           recordedAtMs: proposedAtMs,
         });
       }
@@ -182,9 +174,9 @@ export async function runCodexUserPromptSubmitHook({
           sessionId,
           auditStatus,
           requestText: prompt,
-          auditorSeenContext,
-          observerContextStatus: observerContext.status,
-          observerSnapshot: observerContext.snapshot,
+          auditorSeenContext: null,
+          observerContextStatus: evaluationContext.status,
+          observerSnapshot: evaluationContext.snapshot,
           proposedToolIds: proposals.resolvedToolIds,
           backend,
           model,
@@ -198,97 +190,6 @@ 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 +202,6 @@ 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 +231,6 @@ 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 +252,6 @@ 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 +741,6 @@ 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/core/evaluation-context.mjs

@@ -1,45 +1,33 @@
-import { execFile } from 'node:child_process';
-import { createHash } from 'node:crypto';
 import { realpath } from 'node:fs/promises';
 import { isAbsolute } from 'node:path';
-import { promisify } from 'node:util';
 
 import {
   DEFAULT_AUDITOR_CONTEXT_MAX_BUFFER,
   DEFAULT_AUDITOR_CONTEXT_TIMEOUT_MS,
+  loadAuditorContext,
   readProjectAuditorContextConfig,
 } from './auditor-context.mjs';
 
-export const THROUGHLINE_OBSERVER_READ_SCHEMA = 'throughline.observer_read.v1';
-export const EVALUATION_OBSERVER_CONTEXT_AVAILABLE = 'context_available';
-export const EVALUATION_OBSERVER_CONTEXT_UNAVAILABLE = 'context_unavailable';
-export const DEFAULT_EVALUATION_OBSERVER_LIMIT = 10;
-
-const execFileAsync = promisify(execFile);
-const UNAVAILABLE_STATUSES = new Set([
-  'projection_pending',
-  'ambiguous_parent',
-  'resync_required',
-  'error',
-]);
+export const EVALUATION_CONTEXT_AVAILABLE = 'context_available';
+export const EVALUATION_CONTEXT_UNAVAILABLE = 'context_unavailable';
 
 /**
- * Reads one bounded, proposal-time Throughline observer snapshot.
- *
- * This is deliberately separate from auditor-context.mjs: the returned snapshot
- * is evaluation evidence and must never become auditor input.
+ * Reads the exact-session Throughline context used only as proposal-time
+ * evaluation evidence. It must never become auditor input.
  */
-export async function loadEvaluationObserverContext({
+export async function loadEvaluationContext({
   projectRoot,
   host,
   sessionId,
+  transcriptPath,
   config,
   recordedAtMs = Date.now(),
   timeoutMs = DEFAULT_AUDITOR_CONTEXT_TIMEOUT_MS,
   maxBuffer = DEFAULT_AUDITOR_CONTEXT_MAX_BUFFER,
-  execFileFn = execFileAsync,
+  execFileFn,
   realpathFn = realpath,
   readConfigFn = readProjectAuditorContextConfig,
+  loadAuditorContextFn = loadAuditorContext,
 } = {}) {
   if (!Number.isSafeInteger(recordedAtMs) || recordedAtMs < 0) {
     throw new TypeError('recordedAtMs must be a non-negative safe integer');
@@ -56,6 +44,9 @@ export async function loadEvaluationObserverContext({
   if (host === 'codex' && sessionId === 'codex:') {
     throw new TypeError('sessionId must identify a thread');
   }
+  if (typeof transcriptPath !== 'string' || transcriptPath.length === 0 || !isAbsoluteProjectPath(transcriptPath)) {
+    throw new TypeError('transcriptPath must be an absolute path');
+  }
 
   let canonicalProjectRoot;
   try {
@@ -75,110 +66,42 @@ export async function loadEvaluationObserverContext({
   if (effectiveConfig?.mode !== 'throughline') {
     return unavailableResult(recordedAtMs, 'provider_disabled');
   }
-  if (!isDirectCommandConfig(effectiveConfig)) {
-    return unavailableResult(recordedAtMs, 'config_unavailable');
-  }
-
-  let stdout;
-  try {
-    ({ stdout } = await execFileFn(effectiveConfig.command, [
-      ...effectiveConfig.args,
-      'observer-read',
-      '--project', canonicalProjectRoot,
-      '--limit', String(DEFAULT_EVALUATION_OBSERVER_LIMIT),
-      '--json',
-    ], {
-      encoding: 'utf8',
-      timeout: timeoutMs,
-      maxBuffer,
-      windowsHide: true,
-      shell: false,
-    }));
-  } catch {
-    return unavailableResult(recordedAtMs, 'observer_read_failed');
-  }
 
   let snapshot;
   try {
-    snapshot = JSON.parse(stdout);
+    snapshot = await loadAuditorContextFn({
+      config: effectiveConfig,
+      host,
+      sessionId,
+      projectRoot: canonicalProjectRoot,
+      transcriptPath,
+      timeoutMs,
+      maxBuffer,
+      ...(execFileFn === undefined ? {} : { execFileFn }),
+    });
   } catch {
-    return unavailableResult(recordedAtMs, 'observer_read_invalid');
+    return unavailableResult(recordedAtMs, 'auditor_context_failed');
   }
 
-  if (UNAVAILABLE_STATUSES.has(snapshot?.status)) {
-    return unavailableResult(recordedAtMs, `observer_${snapshot.status}`);
-  }
-  if (!isObserverSnapshot(snapshot)) {
-    return unavailableResult(recordedAtMs, 'observer_read_invalid');
-  }
-  if (snapshot.host !== null && snapshot.host !== host) {
-    return unavailableResult(recordedAtMs, 'observer_host_mismatch');
-  }
-  if (snapshot.thread_sha256 !== null && snapshot.thread_sha256 !== expectedThreadHash(host, sessionId)) {
-    return unavailableResult(recordedAtMs, 'observer_session_mismatch');
+  if (snapshot.status !== 'fresh') {
+    return unavailableResult(recordedAtMs, `auditor_context_${snapshot.status}`);
   }
   return Object.freeze({
-    status: EVALUATION_OBSERVER_CONTEXT_AVAILABLE,
+    status: EVALUATION_CONTEXT_AVAILABLE,
     recordedAtMs,
-    snapshot: freezeSnapshot(snapshot),
+    snapshot,
   });
 }
 
 function unavailableResult(recordedAtMs, reason) {
   return Object.freeze({
-    status: EVALUATION_OBSERVER_CONTEXT_UNAVAILABLE,
+    status: EVALUATION_CONTEXT_UNAVAILABLE,
     recordedAtMs,
     reason,
     snapshot: null,
   });
 }
 
-function isDirectCommandConfig(config) {
-  return config && config.mode === 'throughline' &&
-    isAbsoluteProjectPath(config.command) &&
-    !/\.(?:cmd|bat)$/i.test(config.command) &&
-    Array.isArray(config.args) &&
-    config.args.every((arg) => typeof arg === 'string' && arg.length > 0);
-}
-
 function isAbsoluteProjectPath(value) {
   return isAbsolute(value) || /^[A-Za-z]:[\\/]/.test(value);
 }
-
-function isObserverSnapshot(value) {
-  if (!isRecord(value) || value.schema !== THROUGHLINE_OBSERVER_READ_SCHEMA || value.status !== 'snapshot') return false;
-  if (!Array.isArray(value.turns) || value.turns.length > DEFAULT_EVALUATION_OBSERVER_LIMIT) return false;
-  if (typeof value.historyTruncated !== 'boolean' || !isNullableString(value.afterCursor) || !isNullableString(value.throughCursor)) return false;
-  if (!isRecord(value.page) || typeof value.page.complete !== 'boolean' || !isNullableString(value.page.nextToken)) return false;
-  if (value.host === null) return value.thread_sha256 === null && value.turns.length === 0;
-  if ((value.host !== 'claude' && value.host !== 'codex') || !/^[a-f0-9]{64}$/.test(value.thread_sha256)) return false;
-  return value.turns.every((turn) => isRecord(turn) &&
-    turn.host === value.host && turn.thread_sha256 === value.thread_sha256);
-}
-
-// Throughline observer-read hashes the Claude session ID directly. Codex hook
-// session IDs may already carry Throughline's `codex:` namespace, while the
-// observer feed hashes the underlying Codex thread ID.
-function expectedThreadHash(host, sessionId) {
-  const threadId = host === 'codex' && sessionId.startsWith('codex:')
-    ? sessionId.slice('codex:'.length)
-    : sessionId;
-  if (threadId.length === 0) throw new TypeError('sessionId must identify a thread');
-  return createHash('sha256').update(threadId, 'utf8').digest('hex');
-}
-
-function freezeSnapshot(snapshot) {
-  return Object.freeze({
-    ...snapshot,
-    turns: Object.freeze(snapshot.turns.map((turn) => Object.freeze({ ...turn }))),
-    page: Object.freeze({ ...snapshot.page }),
-  });
-}
-
-function isNullableString(value) {
-  return value === null || typeof value === 'string';
-}
-
-function isRecord(value) {
-  return value !== null && typeof value === 'object' && !Array.isArray(value);
-}

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/hooks/user-prompt.mjs

@@ -25,13 +25,9 @@ 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';
+import { loadEvaluationContext } from '../core/evaluation-context.mjs';
 import { version } from '../version.mjs';
 
 const TIMEOUT_MS = 50_000;
@@ -41,11 +37,9 @@ export async function runUserPrompt({
   sendRequestFn = sendRequest,
   spawnDaemonAndWaitReadyFn = spawnDaemonAndWaitReady,
   discardLegacyPendingFn = discardLegacyPending,
-  readAuditorContextConfigFn = readProjectAuditorContextConfig,
-  loadAuditorContextFn = loadAuditorContext,
   recordHookEventFn = recordClaudeHookEvent,
   createEvaluationStoreFn = createEvaluationStore,
-  loadEvaluationObserverContextFn = loadEvaluationObserverContext,
+  loadEvaluationContextFn = loadEvaluationContext,
   randomUUIDFn = randomUUID,
   spotterVersion = version,
   now = Date.now,
@@ -62,22 +56,21 @@ 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
         ? projectToolIds(Array.isArray(result?.missing_tools) ? result.missing_tools.map((entry) => entry?.name) : [])
         : [];
       const proposalRecordedAtMs = proposedToolIds.length > 0 ? now() : null;
-      const observer = proposedToolIds.length > 0
-        ? await loadEvaluationObserverContextFn({
+      const evaluationContext = proposedToolIds.length > 0
+        ? await loadEvaluationContextFn({
           projectRoot,
           host: 'claude',
           sessionId,
-          config: auditContext?.config,
+          transcriptPath: input.transcript_path,
           recordedAtMs: proposalRecordedAtMs,
         })
         : { status: 'not_requested', snapshot: null };
@@ -94,9 +87,9 @@ export async function runUserPrompt({
           sessionId,
           auditStatus,
           requestText: prompt,
-          auditorSeenContext: auditContext?.turns ? JSON.stringify(auditContext.turns) : null,
-          observerContextStatus: observer.status,
-          observerSnapshot: observer.snapshot,
+          auditorSeenContext: null,
+          observerContextStatus: evaluationContext.status,
+          observerSnapshot: evaluationContext.snapshot,
           proposedToolIds,
           backend: result?.evaluation_meta?.backend ?? null,
           model: result?.evaluation_meta?.model ?? null,
@@ -128,7 +121,6 @@ export async function runUserPrompt({
         status: 'degraded',
         code: failure.code,
         reason,
-        contextDurationMs,
         legacyPendingDiagnostic: legacyPending.diagnostic,
         durationMs: Date.now() - startedAt,
       },
@@ -151,108 +143,12 @@ 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 +174,6 @@ export async function runUserPrompt({
   await safelyRecordEvaluation({
     auditStatus: 'success',
     result,
-    auditContext: { config: auditorContextConfig, turns: context.turns },
   });
   if (advice) emitAdditionalContext(writeOutput, advice);
 
@@ -289,10 +184,6 @@ 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,
     },