gsd-pi 2.77.0-dev.eaa4973bc → 2.78.0-dev.aeeb2ca00

package/src/resources/extensions/gsd/auto-worktree.ts

@@ -98,6 +98,66 @@ const ROOT_STATE_FILES = [
   // because the project root is authoritative for preferences (#2684).
 ] as const;
 
+/**
+ * Pop a stash entry by tracking the unique marker embedded in its message so
+ * concurrent stash operations against the same project root cannot cause us to
+ * pop the wrong entry.
+ *
+ * If `stashMarker` is null or no longer present in the stash list (e.g. a
+ * concurrent process popped/dropped it), leaves the stash list untouched and
+ * returns null.
+ *
+ * Throws on pop failure so callers can handle conflict cases the same way
+ * they would with the prior `git stash pop` form. When throwing after a
+ * targeted pop attempt, the error is annotated with the targeted stash ref.
+ *
+ * (Issue #4980 HIGH-6)
+ */
+function popStashByRef(basePath: string, stashMarker: string | null): string | null {
+  let popArg: string | null = null;
+  if (stashMarker) {
+    try {
+      const list = execFileSync("git", ["stash", "list", "--format=%gd%x00%s"], {
+        cwd: basePath,
+        stdio: ["ignore", "pipe", "pipe"],
+        encoding: "utf-8",
+      }).trim().split("\n").filter(Boolean);
+      for (const entry of list) {
+        const [ref, subject] = entry.split("\0");
+        if (ref && subject?.includes(stashMarker)) {
+          popArg = ref;
+          break;
+        }
+      }
+    } catch (err) {
+      logWarning("worktree", `stash list lookup failed; leaving stash untouched: ${err instanceof Error ? err.message : String(err)}`);
+    }
+  }
+  if (!popArg) {
+    logWarning("worktree", "recorded stash entry could not be resolved; skipping automatic pop");
+    return null;
+  }
+  try {
+    execFileSync("git", ["stash", "pop", popArg], {
+      cwd: basePath,
+      stdio: ["ignore", "pipe", "pipe"],
+      encoding: "utf-8",
+    });
+  } catch (err) {
+    if (err && typeof err === "object") {
+      (err as { stashRef?: string }).stashRef = popArg;
+    }
+    throw err;
+  }
+  return popArg;
+}
+
+function stashRefFromError(err: unknown): string | null {
+  if (!err || typeof err !== "object") return null;
+  const stashRef = (err as { stashRef?: unknown }).stashRef;
+  return typeof stashRef === "string" && stashRef.length > 0 ? stashRef : null;
+}
+
 /**
  * Check if two filesystem paths resolve to the same real location.
  * Returns false if either path cannot be resolved (e.g. doesn't exist).
@@ -971,6 +1031,32 @@ export function enterBranchModeForMilestone(
       validatedPrefBranch ??
       nativeDetectMainBranch(basePath);
 
+    // TOCTOU ancestry guard (Issue #4980 HIGH-3).
+    //
+    // The outer `branchExists` check at line 1012 is racy: a concurrent
+    // process (parallel-orchestrator worker, side-by-side `gsd` instance,
+    // or manual `git branch` invocation) may have created the branch with
+    // real commits between that check and this point. `nativeBranchForceReset`
+    // does `git branch -f`, which silently overwrites the branch ref —
+    // orphaning any commits not reachable from `startPoint`. Re-check
+    // immediately before the destructive call and refuse if the branch
+    // suddenly exists with non-ancestor commits.
+    //
+    // Note: under single-threaded execution this is rarely reached, but it
+    // is NOT dead code — it is the only barrier against a TOCTOU-induced
+    // commit loss in this code path.
+    const concurrentlyCreated = nativeBranchExists(basePath, branch);
+    if (
+      concurrentlyCreated &&
+      !nativeIsAncestor(basePath, branch, startPoint)
+    ) {
+      throw new GSDError(
+        GSD_GIT_ERROR,
+        `Branch "${branch}" was created concurrently with commits not reachable from "${startPoint}". ` +
+        `Refusing to force-reset — would orphan prior work. ` +
+        `Resume the existing milestone or run \`git branch -D ${branch}\` to discard.`,
+      );
+    }
     // nativeBranchForceReset creates (or resets) branch at startPoint,
     // then checkout switches HEAD to it.
     nativeBranchForceReset(basePath, branch, startPoint);
@@ -1576,7 +1662,20 @@ export function mergeMilestoneToMain(
 
   // 5. Checkout integration branch (skip if already current — avoids git error
   //    when main is already checked out in the project-root worktree, #757)
+  //
+  // Refuse to proceed if the project root is in detached HEAD state. Silently
+  // running `nativeCheckoutBranch(mainBranch)` on a detached HEAD would
+  // abandon the user's deliberately-checked-out commit (mid-bisect, reviewing
+  // a tag, CI checkout-sha) without warning. (Issue #4980 HIGH-10)
   const currentBranchAtBase = nativeGetCurrentBranch(originalBasePath_);
+  if (!currentBranchAtBase || currentBranchAtBase.length === 0) {
+    process.chdir(previousCwd);
+    throw new GSDError(
+      GSD_GIT_ERROR,
+      `Project root is in detached HEAD state — cannot perform milestone merge. ` +
+      `Checkout an integration branch (e.g. \`git checkout ${mainBranch}\`) before resuming.`,
+    );
+  }
   if (currentBranchAtBase !== mainBranch) {
     nativeCheckoutBranch(originalBasePath_, mainBranch);
   }
@@ -1768,6 +1867,11 @@ export function mergeMilestoneToMain(
   }
 
   let stashed = false;
+  // Embed a unique marker in the stash message so subsequent pop/drop targets
+  // the entry we created, not whatever happens to be at stash@{0} (concurrent
+  // milestone merges share the project-root stash list and can shift positions).
+  // (Issue #4980 HIGH-6)
+  let stashMarker: string | null = null;
   try {
     const status = execFileSync("git", ["status", "--porcelain"], {
       cwd: originalBasePath_,
@@ -1775,9 +1879,10 @@ export function mergeMilestoneToMain(
       encoding: "utf-8",
     }).trim();
     if (status) {
+      stashMarker = `gsd-pre-merge:${milestoneId}:${process.pid}:${Date.now()}:${process.hrtime.bigint().toString(36)}`;
       execFileSync(
         "git",
-        ["stash", "push", "--include-untracked", "-m", `gsd: pre-merge stash for ${milestoneId}`],
+        ["stash", "push", "--include-untracked", "-m", `gsd: pre-merge stash for ${milestoneId} [${stashMarker}]`],
         { cwd: originalBasePath_, stdio: ["ignore", "pipe", "pipe"], encoding: "utf-8" },
       );
       stashed = true;
@@ -1834,11 +1939,7 @@ export function mergeMilestoneToMain(
       // Pop stash before throwing so local work is not lost.
       if (stashed) {
         try {
-          execFileSync("git", ["stash", "pop"], {
-            cwd: originalBasePath_,
-            stdio: ["ignore", "pipe", "pipe"],
-            encoding: "utf-8",
-          });
+          popStashByRef(originalBasePath_, stashMarker);
         } catch (err) { /* stash pop conflict is non-fatal */
           logWarning("worktree", `git stash pop failed: ${err instanceof Error ? err.message : String(err)}`);
         }
@@ -1910,11 +2011,7 @@ export function mergeMilestoneToMain(
         // Pop stash before throwing so local work is not lost (#2151).
         if (stashed) {
           try {
-            execFileSync("git", ["stash", "pop"], {
-              cwd: originalBasePath_,
-              stdio: ["ignore", "pipe", "pipe"],
-              encoding: "utf-8",
-            });
+            popStashByRef(originalBasePath_, stashMarker);
           } catch (err) { /* stash pop conflict is non-fatal */
             logWarning("worktree", `git stash pop failed: ${err instanceof Error ? err.message : String(err)}`);
           }
@@ -1962,13 +2059,11 @@ export function mergeMilestoneToMain(
   // or the commit content.  Conflict on pop is non-fatal — the stash entry is
   // preserved and the user can resolve manually with `git stash pop`.
   if (stashed) {
+    let stashRefForDrop: string | null = null;
     try {
-      execFileSync("git", ["stash", "pop"], {
-        cwd: originalBasePath_,
-        stdio: ["ignore", "pipe", "pipe"],
-        encoding: "utf-8",
-      });
+      stashRefForDrop = popStashByRef(originalBasePath_, stashMarker);
     } catch (e) {
+      stashRefForDrop = stashRefFromError(e);
       logWarning("worktree", `git stash pop failed, attempting conflict resolution: ${(e as Error).message}`);
       // Stash pop after squash merge can conflict on .gsd/ state files that
       // diverged between branches.  Left unresolved, these UU entries block
@@ -1997,22 +2092,31 @@ export function mergeMilestoneToMain(
         }
       }
 
-      if (nonGsdUU.length === 0) {
+      if (gsdUU.length > 0 && nonGsdUU.length === 0) {
         // All conflicts were .gsd/ files — safe to drop the stash
-        try {
-          execFileSync("git", ["stash", "drop"], {
-            cwd: originalBasePath_,
-            stdio: ["ignore", "pipe", "pipe"],
-            encoding: "utf-8",
-          });
-        } catch (err) { /* stash may already be consumed */
-          logWarning("worktree", `git stash drop failed: ${err instanceof Error ? err.message : String(err)}`);
+        if (stashRefForDrop) {
+          try {
+            execFileSync("git", ["stash", "drop", stashRefForDrop], {
+              cwd: originalBasePath_,
+              stdio: ["ignore", "pipe", "pipe"],
+              encoding: "utf-8",
+            });
+          } catch (err) { /* stash may already be consumed */
+            logWarning("worktree", `git stash drop failed: ${err instanceof Error ? err.message : String(err)}`);
+          }
+        } else {
+          logWarning("worktree", "recorded stash entry could not be resolved; skipping automatic drop");
         }
-      } else {
+      } else if (nonGsdUU.length > 0) {
         // Non-.gsd conflicts remain — leave stash for manual resolution
         logWarning("reconcile", "Stash pop conflict on non-.gsd files after merge", {
           files: nonGsdUU.join(", "),
         });
+      } else {
+        logWarning(
+          "worktree",
+          "git stash pop failed without resolvable conflict files; leaving stash for manual recovery",
+        );
       }
     }
   }

package/src/resources/extensions/gsd/auto.ts

@@ -84,10 +84,11 @@ import {
   clearInFlightTools,
   isToolInvocationError,
   isQueuedUserMessageSkip,
+  isDeterministicPolicyError,
 } from "./auto-tool-tracking.js";
 import { closeoutUnit } from "./auto-unit-closeout.js";
 import { recoverTimedOutUnit } from "./auto-timeout-recovery.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 {
   checkPostUnitHooks,
@@ -169,6 +170,7 @@ import {
   buildLoopRemediationSteps,
   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";
@@ -231,9 +233,7 @@ import { reorderForCaching } from "./prompt-ordering.js";
 
 import {
   AutoSession,
-  MAX_UNIT_DISPATCHES,
   STUB_RECOVERY_THRESHOLD,
-  MAX_LIFETIME_DISPATCHES,
   NEW_SESSION_TIMEOUT_MS,
 } from "./auto/session.js";
 import type {
@@ -242,9 +242,7 @@ import type {
   StartModel,
 } from "./auto/session.js";
 export {
-  MAX_UNIT_DISPATCHES,
   STUB_RECOVERY_THRESHOLD,
-  MAX_LIFETIME_DISPATCHES,
   NEW_SESSION_TIMEOUT_MS,
 } from "./auto/session.js";
 export type {
@@ -336,6 +334,25 @@ function normalizeSessionFilePath(raw: unknown): string | null {
   return candidate;
 }
 
+function synthesizePausedSessionRecovery(
+  basePath: string,
+  unitType: string,
+  unitId: string,
+  sessionFile: string,
+): ReturnType<typeof synthesizeCrashRecovery> {
+  const activityDir = join(gsdRoot(basePath), "activity");
+  return synthesizeCrashRecovery(basePath, unitType, unitId, sessionFile, activityDir);
+}
+
+export function _synthesizePausedSessionRecoveryForTest(
+  basePath: string,
+  unitType: string,
+  unitId: string,
+  sessionFile: string,
+): ReturnType<typeof synthesizeCrashRecovery> {
+  return synthesizePausedSessionRecovery(basePath, unitType, unitId, sessionFile);
+}
+
 export function startAutoDetached(
   ctx: ExtensionCommandContext,
   pi: ExtensionAPI,
@@ -543,12 +560,14 @@ export function markToolEnd(toolCallId: string): void {
 /**
  * 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: string, errorMsg: string): void {
   if (!s.active) return;
-  if (isToolInvocationError(errorMsg) || isQueuedUserMessageSkip(errorMsg)) {
+  if (isToolInvocationError(errorMsg) || isQueuedUserMessageSkip(errorMsg) || isDeterministicPolicyError(errorMsg)) {
     s.lastToolInvocationError = `${toolName}: ${errorMsg}`;
   }
 }
@@ -795,6 +814,43 @@ export async function stopAuto(
   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");
+    type AutoExitReason =
+      | "pause" | "stop" | "blocked" | "merge-conflict" | "merge-failed"
+      | "slice-merge-conflict" | "all-complete" | "no-active-milestone" | "other";
+    // 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: AutoExitReason = 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 {
@@ -1050,6 +1106,12 @@ export async function stopAuto(
     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();
   }
@@ -1350,6 +1412,15 @@ export async function startAuto(
     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) {
@@ -1419,7 +1490,15 @@ export async function startAuto(
           // 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) {
               if ((err as NodeJS.ErrnoException).code !== "ENOENT") {
                 logWarning("session", `pause file cleanup failed: ${err instanceof Error ? err.message : String(err)}`, { file: "auto.ts" });
@@ -1510,16 +1589,6 @@ export async function startAuto(
       return;
     }
 
-    // Lock acquired — now safe to delete the pause file
-    if (s.pausedSessionFile) {
-      try { unlinkSync(s.pausedSessionFile); } catch (err) {
-        if ((err as NodeJS.ErrnoException).code !== "ENOENT") {
-          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;
@@ -1617,13 +1686,11 @@ export async function startAuto(
     invalidateAllCaches();
 
     if (s.pausedSessionFile) {
-      const activityDir = join(gsdRoot(s.basePath), "activity");
-      const recovery = synthesizeCrashRecovery(
+      const recovery = synthesizePausedSessionRecovery(
         s.basePath,
         s.currentUnit?.type ?? s.pausedUnitType ?? "unknown",
         s.currentUnit?.id ?? s.pausedUnitId ?? "unknown",
-        s.pausedSessionFile ?? undefined,
-        activityDir,
+        s.pausedSessionFile,
       );
       if (recovery && recovery.trace.toolCallCount > 0) {
         s.pendingCrashRecovery = recovery.prompt;

package/src/resources/extensions/gsd/bootstrap/agent-end-recovery.ts

@@ -7,6 +7,7 @@ import {
   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";
@@ -25,7 +26,15 @@ 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.
@@ -76,6 +85,16 @@ export async function handleAgentEnd(
   event: { messages: any[] },
   ctx: ExtensionContext,
 ): Promise<void> {
+  // #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;