gsd-pi 2.76.0-dev.fe143342a → 2.77.0-dev.1594b263e

package/dist/resources/extensions/gsd/auto.js

@@ -24,9 +24,9 @@ import { acquireSessionLock, getSessionLockStatus, releaseSessionLock, updateSes
 import { resolveAutoSupervisorConfig, loadEffectiveGSDPreferences, getIsolationMode, } from "./preferences.js";
 import { sendDesktopNotification } from "./notifications.js";
 import { getBudgetAlertLevel, getNewBudgetAlertLevel, getBudgetEnforcementAction, } from "./auto-budget.js";
-import { markToolStart as _markToolStart, markToolEnd as _markToolEnd, getOldestInFlightToolAgeMs as _getOldestInFlightToolAgeMs, clearInFlightTools, isToolInvocationError, isQueuedUserMessageSkip, } from "./auto-tool-tracking.js";
+import { markToolStart as _markToolStart, markToolEnd as _markToolEnd, getOldestInFlightToolAgeMs as _getOldestInFlightToolAgeMs, clearInFlightTools, isToolInvocationError, isQueuedUserMessageSkip, isDeterministicPolicyError, } from "./auto-tool-tracking.js";
 import { closeoutUnit } from "./auto-unit-closeout.js";
-import { selectAndApplyModel, resolveModelId } from "./auto-model-selection.js";
+import { selectAndApplyModel, resolveModelId, clearToolBaseline } from "./auto-model-selection.js";
 import { resetRoutingHistory, recordOutcome } from "./routing-history.js";
 import { resetHookState, runPreDispatchHooks, restoreHookState, clearPersistedHookState, } from "./post-unit-hooks.js";
 import { runGSDDoctor, rebuildState } from "./doctor.js";
@@ -37,8 +37,9 @@ import { getRtkSessionSavings } from "../shared/rtk-session-stats.js";
 import { deactivateGSD } from "../shared/gsd-phase-state.js";
 import { initMetrics, resetMetrics, getLedger, getProjectTotals, formatCost, formatTokenCount, } from "./metrics.js";
 import { setLogBasePath, logWarning } from "./workflow-logger.js";
+import { preflightCleanRoot, postflightPopStash } from "./clean-root-preflight.js";
 import { homedir } from "node:os";
-import { join } from "node:path";
+import { isAbsolute, join } from "node:path";
 import { pathToFileURL } from "node:url";
 import { readFileSync, existsSync, mkdirSync, writeFileSync, unlinkSync } from "node:fs";
 import { atomicWriteSync } from "./atomic-write.js";
@@ -50,16 +51,24 @@ import { pruneQueueOrder } from "./queue-order.js";
 import { startCommandPolling as _startCommandPolling, isRemoteConfigured } from "../remote-questions/manager.js";
 import { debugLog, isDebugEnabled, writeDebugSummary } from "./debug-logger.js";
 import { reconcileMergeState, } from "./auto-recovery.js";
+import { classifyMilestoneSummaryContent } from "./milestone-summary-classifier.js";
 import { resolveDispatch, DISPATCH_RULES } from "./auto-dispatch.js";
 import { getErrorMessage } from "./error-utils.js";
 import { recoverFailedMigration } from "./migrate-external.js";
 import { initRegistry, convertDispatchRules } from "./rule-registry.js";
 import { emitJournalEvent as _emitJournalEvent } from "./journal.js";
-import { updateProgressWidget as _updateProgressWidget, updateSliceProgressCache, clearSliceProgressCache, hideFooter, } from "./auto-dashboard.js";
+import { updateProgressWidget as _updateProgressWidget, updateSliceProgressCache, clearSliceProgressCache, } from "./auto-dashboard.js";
 import { registerSigtermHandler as _registerSigtermHandler, deregisterSigtermHandler as _deregisterSigtermHandler, } from "./auto-supervisor.js";
 import { isDbAvailable, getMilestone } from "./gsd-db.js";
 import { countPendingCaptures } from "./captures.js";
-import { clearCmuxSidebar, logCmuxEvent, syncCmuxSidebar } from "../cmux/index.js";
+import { CMUX_CHANNELS } from "../shared/cmux-events.js";
+function makeCmuxEmitters(pi) {
+    return {
+        syncCmuxSidebar: (preferences, state) => pi.events.emit(CMUX_CHANNELS.SIDEBAR, { action: "sync", preferences, state }),
+        logCmuxEvent: (preferences, message, level) => pi.events.emit(CMUX_CHANNELS.LOG, { preferences, message, level: level ?? "info" }),
+        clearCmuxSidebar: (preferences) => pi.events.emit(CMUX_CHANNELS.SIDEBAR, { action: "clear", preferences }),
+    };
+}
 // ── Extracted modules ──────────────────────────────────────────────────────
 import { startUnitSupervision } from "./auto-timers.js";
 import { runPostUnitVerification } from "./auto-verification.js";
@@ -73,7 +82,7 @@ import { WorktreeResolver, } from "./worktree-resolver.js";
 import { reorderForCaching } from "./prompt-ordering.js";
 // ─── Session State ─────────────────────────────────────────────────────────
 import { AutoSession, } from "./auto/session.js";
-export { MAX_UNIT_DISPATCHES, STUB_RECOVERY_THRESHOLD, MAX_LIFETIME_DISPATCHES, NEW_SESSION_TIMEOUT_MS, } from "./auto/session.js";
+export { STUB_RECOVERY_THRESHOLD, NEW_SESSION_TIMEOUT_MS, } from "./auto/session.js";
 // ── ENCAPSULATION INVARIANT ─────────────────────────────────────────────────
 // ALL mutable auto-mode state lives in the AutoSession class (auto/session.ts).
 // This file must NOT declare module-level `let` or `var` variables for state.
@@ -136,6 +145,31 @@ function restoreMilestoneLockEnv() {
     s.hadMilestoneLockEnv = false;
     s.milestoneLockEnvCaptured = false;
 }
+function normalizeSessionFilePath(raw) {
+    if (typeof raw !== "string")
+        return null;
+    const trimmed = raw.trim();
+    if (!trimmed)
+        return null;
+    const firstLine = trimmed.split(/\r?\n/, 1)[0]?.trim() ?? "";
+    if (!firstLine)
+        return null;
+    // Guard against accidental message concatenation by trimming to .jsonl.
+    const jsonlIndex = firstLine.toLowerCase().indexOf(".jsonl");
+    const candidate = jsonlIndex >= 0 ? firstLine.slice(0, jsonlIndex + ".jsonl".length) : firstLine;
+    if (!isAbsolute(candidate))
+        return null;
+    if (!candidate.toLowerCase().endsWith(".jsonl"))
+        return null;
+    return candidate;
+}
+function synthesizePausedSessionRecovery(basePath, unitType, unitId, sessionFile) {
+    const activityDir = join(gsdRoot(basePath), "activity");
+    return synthesizeCrashRecovery(basePath, unitType, unitId, sessionFile, activityDir);
+}
+export function _synthesizePausedSessionRecoveryForTest(basePath, unitType, unitId, sessionFile) {
+    return synthesizePausedSessionRecovery(basePath, unitType, unitId, sessionFile);
+}
 export function startAutoDetached(ctx, pi, base, verboseMode, options) {
     void startAuto(ctx, pi, base, verboseMode, options).catch((err) => {
         const message = getErrorMessage(err);
@@ -248,6 +282,10 @@ export function getAutoDashboardData() {
 export function isAutoActive() {
     return s.active;
 }
+/** Test-only seam for validating auto-mode guards (#4704). Do not use in production code. */
+export function _setAutoActiveForTest(active) {
+    s.active = active;
+}
 export function isAutoPaused() {
     return s.paused;
 }
@@ -289,13 +327,15 @@ export function markToolEnd(toolCallId) {
 /**
  * Record a tool invocation error on the current session (#2883).
  * Called from tool_execution_end when a GSD tool fails with isError.
- * Only stores the error if it matches the tool-invocation-error pattern
- * (malformed/truncated JSON), not normal business-logic errors.
+ * Stores the error if it matches:
+ *   - tool-invocation-error pattern (malformed/truncated JSON)
+ *   - queued-user-message skip pattern
+ *   - deterministic policy rejection (#4973, e.g. context_write_blocked)
  */
 export function recordToolInvocationError(toolName, errorMsg) {
     if (!s.active)
         return;
-    if (isToolInvocationError(errorMsg) || isQueuedUserMessageSkip(errorMsg)) {
+    if (isToolInvocationError(errorMsg) || isQueuedUserMessageSkip(errorMsg) || isDeterministicPolicyError(errorMsg)) {
         s.lastToolInvocationError = `${toolName}: ${errorMsg}`;
     }
 }
@@ -427,7 +467,6 @@ function handleLostSessionLock(ctx, lockStatus) {
     restoreProjectRootEnv();
     restoreMilestoneLockEnv();
     deregisterSigtermHandler();
-    clearCmuxSidebar(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences);
     const base = lockBase();
     const lockFilePath = base ? join(gsdRoot(base), "auto.lock") : "unknown";
     const recoverySuggestion = "\nTo recover, run: gsd doctor --fix";
@@ -443,7 +482,6 @@ function handleLostSessionLock(ctx, lockStatus) {
     ctx?.ui.notify(message, "error");
     ctx?.ui.setStatus("gsd-auto", undefined);
     ctx?.ui.setWidget("gsd-progress", undefined);
-    ctx?.ui.setFooter(undefined);
     if (ctx)
         initHealthWidget(ctx);
 }
@@ -480,7 +518,6 @@ function cleanupAfterLoopExit(ctx) {
     if (!s.paused) {
         ctx.ui.setStatus("gsd-auto", undefined);
         ctx.ui.setWidget("gsd-progress", undefined);
-        ctx.ui.setFooter(undefined);
         initHealthWidget(ctx);
     }
     // Restore CWD out of worktree back to original project root
@@ -500,6 +537,40 @@ export async function stopAuto(ctx, pi, reason) {
         return;
     const loadedPreferences = loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences;
     const reasonSuffix = reason ? ` — ${reason}` : "";
+    // #4764 — telemetry: record the exit reason and whether the current milestone
+    // was merged before we entered stopAuto. This is the producer-side signal for
+    // the #4761 orphan class: milestoneMerged=false + currentMilestoneId present
+    // is exactly the pattern that strands work.
+    try {
+        const { emitAutoExit } = await import("./worktree-telemetry.js");
+        // Normalize the free-form reason to a closed set so the telemetry
+        // aggregator buckets stably. Raw detail is preserved in the phases.ts
+        // notification and the notify'd error string.
+        const rawReason = reason ?? "stop";
+        const normalizedReason = rawReason.startsWith("Blocked:")
+            ? "blocked"
+            : rawReason.startsWith("Merge conflict")
+                ? "merge-conflict"
+                : rawReason.startsWith("Merge error") || rawReason.startsWith("Merge failed")
+                    ? "merge-failed"
+                    : rawReason.startsWith("slice-merge-conflict")
+                        ? "slice-merge-conflict"
+                        : rawReason === "All milestones complete"
+                            ? "all-complete"
+                            : rawReason === "No active milestone"
+                                ? "no-active-milestone"
+                                : rawReason === "stop" || rawReason === "pause"
+                                    ? rawReason
+                                    : "other";
+        emitAutoExit(s.originalBasePath || s.basePath, {
+            reason: normalizedReason,
+            milestoneId: s.currentMilestoneId ?? undefined,
+            milestoneMerged: s.milestoneMergedInPhases === true,
+        });
+    }
+    catch (err) {
+        logWarning("engine", `auto-exit telemetry failed: ${err instanceof Error ? err.message : String(err)}`);
+    }
     try {
         // ── Step 1: Timers and locks ──
         try {
@@ -657,8 +728,12 @@ export async function stopAuto(ctx, pi, reason) {
         }
         // ── Step 9: Cmux sidebar / event log ──
         try {
-            clearCmuxSidebar(loadedPreferences);
-            logCmuxEvent(loadedPreferences, `Auto-mode stopped${reasonSuffix || ""}.`, reason?.startsWith("Blocked:") ? "warning" : "info");
+            pi?.events.emit(CMUX_CHANNELS.SIDEBAR, { action: "clear", preferences: loadedPreferences });
+            pi?.events.emit(CMUX_CHANNELS.LOG, {
+                preferences: loadedPreferences,
+                message: `Auto-mode stopped${reasonSuffix || ""}.`,
+                level: reason?.startsWith("Blocked:") ? "warning" : "info",
+            });
         }
         catch (e) {
             debugLog("stop-cleanup-cmux", { error: e instanceof Error ? e.message : String(e) });
@@ -743,11 +818,16 @@ export async function stopAuto(ctx, pi, reason) {
         // UI cleanup
         ctx?.ui.setStatus("gsd-auto", undefined);
         ctx?.ui.setWidget("gsd-progress", undefined);
-        ctx?.ui.setFooter(undefined);
         if (ctx)
             initHealthWidget(ctx);
         restoreProjectRootEnv();
         restoreMilestoneLockEnv();
+        // Drop the active-tool baseline so a subsequent /gsd auto run on the
+        // same `pi` instance recaptures from the live tool set rather than
+        // restoring this session's snapshot and silently undoing any tool
+        // changes the user made between sessions (#4959 / CodeRabbit).
+        if (pi)
+            clearToolBaseline(pi);
         // Reset all session state in one call
         s.reset();
     }
@@ -778,7 +858,7 @@ export async function pauseAuto(ctx, _pi, _errorContext) {
     // Pass errorContext so runUnitPhase can distinguish user-initiated pause
     // from provider-error pause and avoid hard-stopping (#2762).
     resolveAgentEndCancelled(_errorContext);
-    s.pausedSessionFile = ctx?.sessionManager?.getSessionFile() ?? null;
+    s.pausedSessionFile = normalizeSessionFilePath(ctx?.sessionManager?.getSessionFile() ?? null);
     // Persist paused-session metadata so resume survives /exit (#1383).
     // The fresh-start bootstrap checks for this file and restores worktree context.
     try {
@@ -832,7 +912,6 @@ export async function pauseAuto(ctx, _pi, _errorContext) {
     s.verificationRetryCount.clear();
     ctx?.ui.setStatus("gsd-auto", "paused");
     ctx?.ui.setWidget("gsd-progress", undefined);
-    ctx?.ui.setFooter(undefined);
     if (ctx)
         initHealthWidget(ctx);
     const resumeCmd = s.stepMode ? "/gsd next" : "/gsd auto";
@@ -877,11 +956,12 @@ function buildResolver() {
  * Build the LoopDeps object from auto.ts private scope.
  * This bundles all private functions that autoLoop needs without exporting them.
  */
-function buildLoopDeps() {
+function buildLoopDeps(pi) {
     // Initialize the unified rule registry with converted dispatch rules.
     // Must happen before LoopDeps is assembled so facade functions
     // (resolveDispatch, runPreDispatchHooks, etc.) delegate to the registry.
     initRegistry(convertDispatchRules(DISPATCH_RULES));
+    const cmux = makeCmuxEmitters(pi);
     return {
         lockBase,
         buildSnapshotOpts,
@@ -889,8 +969,11 @@ function buildLoopDeps() {
         pauseAuto,
         clearUnitTimeout,
         updateProgressWidget,
-        syncCmuxSidebar,
-        logCmuxEvent,
+        ...cmux,
+        handleLostSessionLock: (ctx, lockStatus) => {
+            cmux.clearCmuxSidebar(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences);
+            handleLostSessionLock(ctx, lockStatus);
+        },
         // State and cache
         invalidateAllCaches,
         deriveState,
@@ -905,7 +988,6 @@ function buildLoopDeps() {
         // Session lock
         validateSessionLock: getSessionLockStatus,
         updateSessionLock,
-        handleLostSessionLock,
         // Milestone transition
         sendDesktopNotification,
         setActiveMilestoneId,
@@ -978,6 +1060,9 @@ function buildLoopDeps() {
         },
         // Journal
         emitJournalEvent: (entry) => _emitJournalEvent(s.basePath, entry),
+        // Clean-root preflight gate (#2909)
+        preflightCleanRoot,
+        postflightPopStash,
     };
 }
 /**
@@ -990,6 +1075,15 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         debugLog("startAuto", { phase: "already-active", skipping: true });
         return;
     }
+    // On a *fresh* start, drop any stale active-tool baseline left by a prior
+    // auto session that didn't run stopAuto cleanly.  Skip on resume: pauseAuto
+    // leaves the last provider-trimmed active tools in place, so clearing here
+    // would let the next selectAndApplyModel recapture that already-narrowed
+    // set as the new baseline — exactly the cross-unit poisoning this PR is
+    // fixing (#4959 / CodeRabbit Major).  The pre-pause baseline survives in
+    // the WeakMap keyed by `pi`.
+    if (!s.paused)
+        clearToolBaseline(pi);
     const requestedStepMode = options?.step ?? false;
     const interruptedAssessment = options?.interrupted ?? null;
     if (options?.milestoneLock !== undefined) {
@@ -1034,7 +1128,9 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
                     unlinkSync(pausedPath);
                 }
                 catch (e) {
-                    logWarning("session", `pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                    if (e.code !== "ENOENT") {
+                        logWarning("session", `pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                    }
                 }
                 ctx.ui.notify(`Resuming paused custom workflow${meta.activeRunDir ? ` (${meta.activeRunDir})` : ""}.`, "info");
             }
@@ -1047,12 +1143,23 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
                     // Validate the milestone still exists and isn't already complete (#1664).
                     const mDir = resolveMilestonePath(base, meta.milestoneId);
                     const summaryFile = resolveMilestoneFile(base, meta.milestoneId, "SUMMARY");
-                    if (!mDir || summaryFile) {
+                    let summaryIsTerminal = false;
+                    if (summaryFile) {
+                        try {
+                            summaryIsTerminal = classifyMilestoneSummaryContent(readFileSync(summaryFile, "utf-8")) !== "failure";
+                        }
+                        catch {
+                            summaryIsTerminal = false;
+                        }
+                    }
+                    if (!mDir || summaryIsTerminal) {
                         try {
                             unlinkSync(pausedPath);
                         }
                         catch (err) {
-                            logWarning("session", `pause file cleanup failed: ${err instanceof Error ? err.message : String(err)}`, { file: "auto.ts" });
+                            if (err.code !== "ENOENT") {
+                                logWarning("session", `pause file cleanup failed: ${err instanceof Error ? err.message : String(err)}`, { file: "auto.ts" });
+                            }
                         }
                         ctx.ui.notify(`Paused milestone ${meta.milestoneId} is ${!mDir ? "missing" : "already complete"}. Starting fresh.`, "info");
                     }
@@ -1060,7 +1167,7 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
                         s.currentMilestoneId = meta.milestoneId;
                         s.originalBasePath = meta.originalBasePath || base;
                         s.stepMode = meta.stepMode ?? requestedStepMode;
-                        s.pausedSessionFile = meta.sessionFile ?? null;
+                        s.pausedSessionFile = normalizeSessionFilePath(meta.sessionFile ?? null);
                         s.pausedUnitType = meta.unitType ?? null;
                         s.pausedUnitId = meta.unitId ?? null;
                         s.autoStartTime = meta.autoStartTime || Date.now();
@@ -1070,7 +1177,9 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
                             unlinkSync(pausedPath);
                         }
                         catch (e) {
-                            logWarning("session", `pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                            if (e.code !== "ENOENT") {
+                                logWarning("session", `pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                            }
                         }
                         ctx.ui.notify(`Resuming paused session for ${meta.milestoneId}${meta.worktreePath && existsSync(meta.worktreePath) ? ` (worktree)` : ""}.`, "info");
                     }
@@ -1080,7 +1189,9 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
                         unlinkSync(pausedPath);
                     }
                     catch (e) {
-                        logWarning("session", `stale pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                        if (e.code !== "ENOENT") {
+                            logWarning("session", `stale pause file cleanup failed: ${e instanceof Error ? e.message : String(e)}`, { file: "auto.ts" });
+                        }
                     }
                 }
             }
@@ -1130,22 +1241,23 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
             ctx.ui.notify(`Cannot resume: ${resumeLock.reason}`, "error");
             return;
         }
-        // Lock acquired — now safe to delete the pause file
-        if (s.pausedSessionFile) {
-            try {
-                unlinkSync(s.pausedSessionFile);
-            }
-            catch (err) {
-                logWarning("session", `pause file cleanup failed: ${err instanceof Error ? err.message : String(err)}`, { file: "auto.ts" });
-            }
-            s.pausedSessionFile = null;
-        }
         s.paused = false;
         s.active = true;
         s.verbose = verboseMode;
         s.stepMode = requestedStepMode;
         s.cmdCtx = ctx;
         s.basePath = base;
+        // ── Resume worktree: if the paused session was inside a milestone worktree,
+        // apply that path as the dispatch basePath immediately (#3723).
+        // This ensures the dispatch loop runs from the worktree directory even when
+        // enterMilestone guard conditions differ between the original and resumed
+        // session (e.g. isolation mode changed, detectWorktreeName differs across
+        // process restarts).  We guard with existsSync so a stale or deleted
+        // worktree directory safely falls back to the project root.
+        const resumeWorktreePath = freshStartAssessment.pausedSession?.worktreePath;
+        if (resumeWorktreePath && existsSync(resumeWorktreePath)) {
+            s.basePath = resumeWorktreePath;
+        }
         // Ensure the workflow-logger audit log is pinned to the project root
         // even when auto-mode is entered via a path that bypasses the
         // bootstrap/dynamic-tools ensureDbOpen() → setLogBasePath() chain
@@ -1175,7 +1287,7 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         }
         registerSigtermHandler(lockBase());
         ctx.ui.setStatus("gsd-auto", s.stepMode ? "next" : "auto");
-        ctx.ui.setFooter(hideFooter);
+        ctx.ui.setWidget("gsd-health", undefined);
         ctx.ui.notify(s.stepMode ? "Step-mode resumed." : "Auto-mode resumed.", "info");
         restoreHookState(s.basePath);
         // Re-sync managed resources on resume so long-lived auto sessions pick up
@@ -1197,7 +1309,7 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         await openProjectDbIfPresent(s.basePath);
         try {
             await rebuildState(s.basePath);
-            syncCmuxSidebar(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, await deriveState(s.basePath));
+            pi.events.emit(CMUX_CHANNELS.SIDEBAR, { action: "sync", preferences: loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, state: await deriveState(s.basePath) });
         }
         catch (e) {
             debugLog("resume-rebuild-state-failed", {
@@ -1217,8 +1329,7 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         }
         invalidateAllCaches();
         if (s.pausedSessionFile) {
-            const activityDir = join(gsdRoot(s.basePath), "activity");
-            const recovery = synthesizeCrashRecovery(s.basePath, s.currentUnit?.type ?? s.pausedUnitType ?? "unknown", s.currentUnit?.id ?? s.pausedUnitId ?? "unknown", s.pausedSessionFile ?? undefined, activityDir);
+            const recovery = synthesizePausedSessionRecovery(s.basePath, s.currentUnit?.type ?? s.pausedUnitType ?? "unknown", s.currentUnit?.id ?? s.pausedUnitId ?? "unknown", s.pausedSessionFile);
             if (recovery && recovery.trace.toolCallCount > 0) {
                 s.pendingCrashRecovery = recovery.prompt;
                 ctx.ui.notify(`Recovered ${recovery.trace.toolCallCount} tool calls from paused session. Resuming with context.`, "info");
@@ -1227,14 +1338,14 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         }
         updateSessionLock(lockBase(), "resuming", s.currentMilestoneId ?? "unknown");
         writeLock(lockBase(), "resuming", s.currentMilestoneId ?? "unknown");
-        logCmuxEvent(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, s.stepMode ? "Step-mode resumed." : "Auto-mode resumed.", "progress");
+        pi.events.emit(CMUX_CHANNELS.LOG, { preferences: loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, message: s.stepMode ? "Step-mode resumed." : "Auto-mode resumed.", level: "progress" });
         captureProjectRootEnv(s.originalBasePath || s.basePath);
         startAutoCommandPolling(s.basePath);
         await runAutoLoopWithUok({
             ctx,
             pi,
             s,
-            deps: buildLoopDeps(),
+            deps: buildLoopDeps(pi),
             runKernelLoop: runUokKernelLoop,
             runLegacyLoop: runLegacyAutoLoop,
         });
@@ -1253,20 +1364,20 @@ export async function startAuto(ctx, pi, base, verboseMode, options) {
         return;
     captureProjectRootEnv(s.originalBasePath || s.basePath);
     try {
-        syncCmuxSidebar(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, await deriveState(s.basePath));
+        pi.events.emit(CMUX_CHANNELS.SIDEBAR, { action: "sync", preferences: loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, state: await deriveState(s.basePath) });
     }
     catch (err) {
         // Best-effort only — sidebar sync must never block auto-mode startup
         logWarning("engine", `cmux sync failed: ${err instanceof Error ? err.message : String(err)}`, { file: "auto.ts" });
     }
-    logCmuxEvent(loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, requestedStepMode ? "Step-mode started." : "Auto-mode started.", "progress");
+    pi.events.emit(CMUX_CHANNELS.LOG, { preferences: loadEffectiveGSDPreferences(s.basePath || undefined)?.preferences, message: requestedStepMode ? "Step-mode started." : "Auto-mode started.", level: "progress" });
     startAutoCommandPolling(s.basePath);
     // Dispatch the first unit
     await runAutoLoopWithUok({
         ctx,
         pi,
         s,
-        deps: buildLoopDeps(),
+        deps: buildLoopDeps(pi),
         runKernelLoop: runUokKernelLoop,
         runLegacyLoop: runLegacyAutoLoop,
     });
@@ -1364,8 +1475,8 @@ export async function dispatchHookUnit(ctx, pi, hookName, triggerUnitType, trigg
                 `Ensure the model is defined in models.json and has auth configured.`, "warning");
         }
     }
-    const sessionFile = ctx.sessionManager.getSessionFile();
-    writeLock(lockBase(), hookUnitType, triggerUnitId, sessionFile);
+    const sessionFile = normalizeSessionFilePath(ctx.sessionManager.getSessionFile());
+    writeLock(lockBase(), hookUnitType, triggerUnitId, sessionFile ?? undefined);
     clearUnitTimeout();
     const supervisor = resolveAutoSupervisorConfig();
     const hookHardTimeoutMs = (supervisor.hard_timeout_minutes ?? 30) * 60 * 1000;

package/dist/resources/extensions/gsd/bootstrap/agent-end-recovery.js

@@ -1,5 +1,6 @@
 import { logWarning } from "../workflow-logger.js";
-import { checkAutoStartAfterDiscuss } from "../guided-flow.js";
+import { checkAutoStartAfterDiscuss, maybeHandleReadyPhraseWithoutFiles, maybeHandleEmptyIntentTurn, resetEmptyTurnCounter, } from "../guided-flow.js";
+import { clearPathCache } from "../paths.js";
 import { getAutoDashboardData, getAutoModeStartModel, isAutoActive, pauseAuto, setCurrentDispatchedModelId } from "../auto.js";
 import { getNextFallbackModel, resolveModelWithFallbacksForUnit } from "../preferences.js";
 import { pauseAutoForProviderError } from "../provider-error-pause.js";
@@ -11,7 +12,15 @@ import { classifyError, createRetryState, resetRetryState, isTransient, } from "
 import { blockModel, isModelBlocked } from "../blocked-models.js";
 const retryState = createRetryState();
 const MAX_NETWORK_RETRIES = 2;
-const MAX_TRANSIENT_AUTO_RESUMES = 8;
+/**
+ * Cap on auto-resume attempts for sustained transient-provider errors.
+ *
+ * Exported so tests assert against the shared constant instead of
+ * regex-scraping the source literal (see #4837). Raising this value to
+ * handle longer provider overloads should update the single constant; the
+ * test in provider-errors.test.ts consumes it directly.
+ */
+export const MAX_TRANSIENT_AUTO_RESUMES = 8;
 /**
  * Reset the module-level retry state so a resumed auto-session starts fresh.
  * Called by provider-error-resume.ts before startAuto() — without this, the
@@ -49,10 +58,32 @@ async function pauseTransientWithBackoff(cls, pi, ctx, errorDetail, isRateLimit)
     });
 }
 export async function handleAgentEnd(pi, event, ctx) {
+    // #4648 — Invalidate the directory-listing cache before any artifact-existence
+    // checks. The LLM may have written milestone files (CONTEXT.md, ROADMAP.md,
+    // PROJECT.md, REQUIREMENTS.md) via tool calls during the turn that just
+    // ended. `paths.ts` caches readdir() results without a TTL, so without this
+    // flush, `resolveMilestoneFile` returns the pre-write listing and the guards
+    // below (`checkAutoStartAfterDiscuss` and `maybeHandleReadyPhraseWithoutFiles`)
+    // falsely report files as missing — producing a spurious "ready signal
+    // rejected" loop even though the files are on disk.
+    clearPathCache();
     if (checkAutoStartAfterDiscuss()) {
         clearDiscussionFlowState();
         return;
     }
+    // #4573 — When the LLM emits "Milestone X ready." but the required files
+    // are missing, `checkAutoStartAfterDiscuss` returns false silently. Surface
+    // that and nudge the LLM to complete the writes before the user hits the
+    // downstream "All milestones complete" warning loop.
+    if (maybeHandleReadyPhraseWithoutFiles(event))
+        return;
+    // #4573 — Empty-turn recovery: if the LLM announced intent in prose but
+    // emitted no tool calls, nudge it to execute. Fires only when auto-mode is
+    // active or a discussion autostart is pending (non-auto interactive discuss
+    // is user-driven). Runs before `isAutoActive` early return so pending
+    // discussions (where isAutoActive may be false) still get recovered.
+    if (maybeHandleEmptyIntentTurn(event, isAutoActive()))
+        return;
     if (!isAutoActive())
         return;
     if (isSessionSwitchInFlight())
@@ -286,6 +317,9 @@ export async function handleAgentEnd(pi, event, ctx) {
     // ── Success path ─────────────────────────────────────────────────────────
     try {
         resetRetryState(retryState);
+        // #4573 — Reset the empty-turn counter on any successful agent turn so
+        // transient stalls don't accumulate across independent units.
+        resetEmptyTurnCounter();
         resolveAgentEnd(event);
     }
     catch (err) {