feat: MistakeTracker + file-provenance ledger (v2.7.4)

Two native-inference hardening features from boocode_code_review_v2 §1 #12.

MistakeTracker: new pure mistake-tracker.ts tracks consecutive heterogeneous
tool failures (kinds surfaced per tool from tool-phase.ts). On 3 in a row the
turn loop soft-nudges (model-facing recovery guidance + mistake_recovery
sentinel + reset), then escalates to stopping the turn (cap-hit-style, Continue
affordance) on a re-trip. Complements doom-loop (identical repeats) + cap-hit.

File-provenance ledger: compaction.ts derives a deterministic ## Files Read list
from the head messages' read-tool calls and injects it into the rolling-summary
prompt so provenance survives compaction (no new table; read-only).

mistake_recovery sentinel: MessageMetadata arm (server + web) + MessageBubble
render branch. Built by 2 parallel agents. Server 545 tests passing (23 new);
build + web tsc clean. Native-inference only. Builds on v2.7.3.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/server/src/services/inference/turn.ts

@@ -22,6 +22,13 @@ import { resolveToolBudget } from './budget.js';
 import {
   detectDoomLoop,
 } from './sentinels.js';
+import {
+  detectMistakePattern,
+  freshMistakeState,
+  recordStep,
+  MISTAKE_RECOVERY_NOTE,
+  type MistakeState,
+} from './mistake-tracker.js';
 import {
   buildMessagesPayload,
   loadContext,
@@ -39,6 +46,7 @@ import {
   runCapHitSummary,
   runDoomLoopSummary,
   runStepCapSummary,
+  insertMistakeRecoverySentinel,
 } from './sentinel-summaries.js';
 
 // v1.14.0: hard ceiling on the number of stream-and-tool iterations per
@@ -144,6 +152,16 @@ export interface TurnArgs {
   // boundaries by runInference, same as toolsUsed. Doom-loop check at the
   // top of runAssistantTurn slices the last DOOM_LOOP_THRESHOLD entries.
   recentToolCalls: ToolCall[];
+  // v#12 MistakeTracker: heterogeneous-failure recovery state. Loop-local,
+  // reset per runInference (user-message boundary) like recentToolCalls. Folds
+  // tool-phase outcomes via recordStep each iteration; detectMistakePattern
+  // gates the nudge/escalate decision.
+  mistakeTracker: MistakeState;
+  // v#12: transient model-facing recovery note set when a nudge fires. Consumed
+  // (appended as a role:'system' message + cleared) on the NEXT payload build.
+  // Never persisted — mirrors how the cap-hit/doom-loop notes live only inside
+  // the summary call's messages array.
+  pendingRecoveryNote?: string;
   signal: AbortSignal | undefined;
 }
 
@@ -188,6 +206,12 @@ export async function runAssistantTurn(
   let toolsUsed = args.toolsUsed;
   let recentToolCalls = args.recentToolCalls;
   let assistantMessageId = args.assistantMessageId;
+  // v#12 MistakeTracker: the tracker state is carried on `args` (mutated in
+  // place by recordStep). pendingRecoveryNote is a loop-local because it is a
+  // single-step transient — set when a nudge fires, consumed (injected into the
+  // next payload) and cleared on the following iteration.
+  const mistakeTracker = args.mistakeTracker;
+  let pendingRecoveryNote: string | undefined = args.pendingRecoveryNote;
 
   while (stepNumber < effectiveCap) {
     // ---- doom-loop check (moved from top-of-function) ----
@@ -196,7 +220,7 @@ export async function runAssistantTurn(
       // Need fresh history for the summary.
       const loaded = await loadContext(ctx.sql, sessionId, chatId);
       if (loaded) {
-        const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
+        const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
         await runDoomLoopSummary(ctx, iterArgs, loaded.session, loaded.project, loaded.history, agent, loop);
       }
       break;
@@ -206,7 +230,7 @@ export async function runAssistantTurn(
     if (toolsUsed >= budget) {
       const loaded = await loadContext(ctx.sql, sessionId, chatId);
       if (loaded) {
-        const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
+        const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
         await runCapHitSummary(ctx, iterArgs, loaded.session, loaded.project, loaded.history, agent, budget);
       }
       break;
@@ -265,7 +289,16 @@ export async function runAssistantTurn(
       }
     }
 
-    const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
+    // v#12 MistakeTracker: if the prior iteration's nudge fired, append the
+    // transient recovery note to THIS payload (consumed exactly once, then
+    // cleared). Never persisted — same lifecycle as the cap-hit/doom-loop
+    // summary notes, which live only inside the in-memory messages array.
+    if (pendingRecoveryNote) {
+      messages.push({ role: 'system', content: pendingRecoveryNote });
+      pendingRecoveryNote = undefined;
+    }
+
+    const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
     const state: StreamPhaseState = { accumulated: '', startedAt: null };
     let result: StreamResult;
     try {
@@ -305,10 +338,78 @@ export async function runAssistantTurn(
     recentToolCalls = [...recentToolCalls, ...toolPhaseResult.toolCalls];
     stepNumber++;
 
+    // v#12 MistakeTracker: fold this iteration's tool outcomes into the
+    // tracker, in order. recordStep mutates `mistakeTracker` in place (it is
+    // the same object referenced by args). A 'success' clears the streak.
+    for (const o of toolPhaseResult.outcomes) {
+      recordStep(mistakeTracker, o);
+    }
+
     if (toolPhaseResult.action !== 'continue') {
-      // 'paused' (user input) or 'synthesis_done' — stop the loop.
+      // 'paused' (user input) or 'synthesis_done' — stop the loop. The turn is
+      // already ending, so neither a nudge nor an escalate would change the
+      // control flow; we skip the mistake decision here.
       break;
     }
+
+    // v#12 MistakeTracker: heterogeneous-failure decision. Only evaluated on
+    // the 'continue' path (the only case where the loop would otherwise
+    // proceed to another step). Complements the doom-loop check above, which
+    // only catches *identical* repeats.
+    const mistake = detectMistakePattern(mistakeTracker);
+    if (mistake === 'nudge') {
+      // Soft intervention: inject model-facing recovery guidance into the NEXT
+      // step's payload, drop a UI sentinel, bump nudges, reset the streak, and
+      // continue. The note is consumed (and cleared) at the top of the next
+      // iteration's payload build.
+      pendingRecoveryNote = MISTAKE_RECOVERY_NOTE;
+      const failureKinds = [...mistakeTracker.run];
+      await insertMistakeRecoverySentinel(ctx, sessionId, chatId, {
+        failureKinds,
+        count: failureKinds.length,
+        escalated: false,
+        canContinue: true,
+      });
+      mistakeTracker.nudges += 1;
+      mistakeTracker.run = [];
+      ctx.log.info(
+        { sessionId, chatId, step: stepNumber, nudges: mistakeTracker.nudges, failureKinds },
+        'mistake_recovery nudge',
+      );
+      assistantMessageId = toolPhaseResult.nextAssistantId!;
+      continue;
+    }
+    if (mistake === 'escalate') {
+      // The nudge didn't break the failure run — stop the turn (cap-hit-style)
+      // to avoid burning the whole step budget on heterogeneous failures. The
+      // next assistant row is still 'streaming'; finalize it as a short note so
+      // the slot doesn't dangle, then drop the escalate sentinel.
+      const failureKinds = [...mistakeTracker.run];
+      assistantMessageId = toolPhaseResult.nextAssistantId!;
+      await ctx.sql`
+        UPDATE messages
+        SET content = '', status = 'complete', finished_at = clock_timestamp()
+        WHERE id = ${assistantMessageId}
+      `;
+      ctx.publish(sessionId, {
+        type: 'message_complete',
+        message_id: assistantMessageId,
+        chat_id: chatId,
+      });
+      await insertMistakeRecoverySentinel(ctx, sessionId, chatId, {
+        failureKinds,
+        count: failureKinds.length,
+        escalated: true,
+        canContinue: true,
+      });
+      ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+      ctx.log.info(
+        { sessionId, chatId, step: stepNumber, failureKinds },
+        'mistake_recovery escalate — stopping turn',
+      );
+      break;
+    }
+
     // 'continue' — advance to next assistant message.
     assistantMessageId = toolPhaseResult.nextAssistantId!;
   }
@@ -320,7 +421,7 @@ export async function runAssistantTurn(
   if (stepNumber >= effectiveCap && effectiveCap < Infinity) {
     const loaded = await loadContext(ctx.sql, sessionId, chatId);
     if (loaded) {
-      const capArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
+      const capArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
       await runStepCapSummary(ctx, capArgs, loaded.session, loaded.project, loaded.history, agent, stepNumber, effectiveCap);
     }
   }
@@ -378,12 +479,16 @@ export async function runInference(
   // per-call budget.
   // v1.11.6: recentToolCalls also resets — doom-loop detection is scoped
   // to a single user-message turn, so a Continue starts with no history.
+  // v#12 MistakeTracker: fresh per user-message turn, like recentToolCalls.
+  // Tracks consecutive heterogeneous tool failures across the loop's
+  // stream-and-tool iterations within this turn.
   return runAssistantTurn(ctx, {
     sessionId,
     chatId,
     assistantMessageId,
     toolsUsed: 0,
     recentToolCalls: [],
+    mistakeTracker: freshMistakeState(),
     signal,
   });
 }