gsd-pi 2.76.0-dev.fe143342a → 2.77.0-dev.1d17f366c

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

@@ -61,7 +61,9 @@ import { restoreHookState, resetHookState } from "./post-unit-hooks.js";
 import { resetProactiveHealing, setLevelChangeCallback } from "./doctor-proactive.js";
 import { snapshotSkills } from "./skill-discovery.js";
 import { isDbAvailable, getMilestone, openDatabase, getDbStatus } from "./gsd-db.js";
-import { hideFooter } from "./auto-dashboard.js";
+import { isClosedStatus } from "./status-guards.js";
+import { classifyMilestoneSummaryContent } from "./milestone-summary-classifier.js";
+
 import {
   debugLog,
   enableDebug,
@@ -74,6 +76,7 @@ import type { AutoSession } from "./auto/session.js";
 import {
   existsSync,
   mkdirSync,
+  readFileSync,
   readdirSync,
   rmSync,
   statSync,
@@ -419,16 +422,35 @@ export async function bootstrapAutoSession(
     // Invalidate caches before initial state derivation
     invalidateAllCaches();
 
-    // Clean stale runtime unit files for completed milestones (#887)
-    cleanStaleRuntimeUnits(
-      gsdRoot(base),
-      (mid) => !!resolveMilestoneFile(base, mid, "SUMMARY"),
-    );
-
     // Open the project-root DB before deriveState so DB-backed state
     // derivation (queue-order, task status) works on a cold start (#2841).
+    // Must happen before cleanStaleRuntimeUnits so the cleanup predicate can
+    // consult DB status and avoid clearing runtime units for milestones that
+    // only have a failure-path SUMMARY on disk (#4663).
     await openProjectDbIfPresent(base);
 
+    // Clean stale runtime unit files for completed milestones (#887).
+    // DB-authoritative: when DB is available, require DB status to be closed
+    // before clearing runtime units. A SUMMARY file alone is no longer
+    // trusted as proof of completion (#4663). Fall back to SUMMARY-file
+    // presence only when DB is unavailable (legacy/pre-migration).
+    cleanStaleRuntimeUnits(
+      gsdRoot(base),
+      (mid) => {
+        if (isDbAvailable()) {
+          const row = getMilestone(mid);
+          return !!row && isClosedStatus(row.status);
+        }
+        const summaryFile = resolveMilestoneFile(base, mid, "SUMMARY");
+        if (!summaryFile) return false;
+        try {
+          return classifyMilestoneSummaryContent(readFileSync(summaryFile, "utf-8")) !== "failure";
+        } catch {
+          return false;
+        }
+      },
+    );
+
     // ── Orphaned milestone branch audit ──
     // Catches completed milestones whose teardown (merge + branch delete)
     // was lost due to session ending between completion and teardown.
@@ -553,37 +575,15 @@ export async function bootstrapAutoSession(
         const { showSmartEntry } = await import("./guided-flow.js");
         await showSmartEntry(ctx, pi, base, { step: requestedStepMode });
 
-        invalidateAllCaches();
-        const postState = await deriveState(base);
-        if (
-          postState.activeMilestone &&
-          postState.phase !== "complete" &&
-          postState.phase !== "pre-planning"
-        ) {
-          s.consecutiveCompleteBootstraps = 0; // Successfully advanced past "complete"
-          state = postState;
-        } else if (
-          postState.activeMilestone &&
-          postState.phase === "pre-planning"
-        ) {
-          const contextFile = resolveMilestoneFile(
-            base,
-            postState.activeMilestone.id,
-            "CONTEXT",
-          );
-          const hasContext = !!(contextFile && (await loadFile(contextFile)));
-          if (hasContext) {
-            state = postState;
-          } else {
-            ctx.ui.notify(
-              "Discussion completed but no milestone context was written. Run /gsd to try the discussion again, or /gsd auto after creating the milestone manually.",
-              "warning",
-            );
-            return releaseLockAndReturn();
-          }
-        } else {
-          return releaseLockAndReturn();
-        }
+        // showSmartEntry dispatches via pi.sendMessage() which is fire-and-forget:
+        // it queues the message and returns immediately, before the LLM turn runs.
+        // Checking postState here would always see the pre-dispatch state, causing
+        // the premature "Discussion completed but..." warning (#3420).
+        //
+        // checkAutoStartAfterDiscuss (in guided-flow.ts) already handles re-entering
+        // auto-mode by calling startAutoDetached after the discussion completes.
+        // Release the lock and let the async dispatch proceed.
+        return releaseLockAndReturn();
       }
 
       // Active milestone exists but has no roadmap
@@ -595,17 +595,16 @@ export async function bootstrapAutoSession(
           const { showSmartEntry } = await import("./guided-flow.js");
           await showSmartEntry(ctx, pi, base, { step: requestedStepMode });
 
-          invalidateAllCaches();
-          const postState = await deriveState(base);
-          if (postState.activeMilestone && postState.phase !== "pre-planning") {
-            state = postState;
-          } else {
-            ctx.ui.notify(
-              "Discussion completed but milestone context is still missing. Run /gsd to try again.",
-              "warning",
-            );
-            return releaseLockAndReturn();
-          }
+          // showSmartEntry dispatches via pi.sendMessage() which is fire-and-forget:
+          // it queues the message and returns immediately, before the LLM turn runs.
+          // Checking postState here fires before the LLM has had a turn, so the
+          // pre-planning phase would still appear unchanged and a premature warning
+          // would be emitted (#3420).
+          //
+          // checkAutoStartAfterDiscuss (in guided-flow.ts) already handles re-entering
+          // auto-mode by calling startAutoDetached after the discussion completes.
+          // Release the lock and let the async dispatch proceed.
+          return releaseLockAndReturn();
         }
       }
 
@@ -824,9 +823,6 @@ export async function bootstrapAutoSession(
     }
 
     ctx.ui.setStatus("gsd-auto", s.stepMode ? "next" : "auto");
-    ctx.ui.setFooter(hideFooter);
-    // Hide gsd-health during AUTO — gsd-progress is the single source of truth
-    // for last-commit / cost / health signal while auto is running.
     ctx.ui.setWidget("gsd-health", undefined);
     const modeLabel = s.stepMode ? "Step-mode" : "Auto-mode";
     const pendingCount = (state.registry ?? []).filter(

package/src/resources/extensions/gsd/auto-timeout-recovery.ts

@@ -18,7 +18,7 @@ import {
 } from "./auto-recovery.js";
 import { existsSync } from "node:fs";
 
-import { resolveAgentEnd } from "./auto-loop.js";
+import { bumpAndResolveSynthetic } from "./auto/resolve.js";
 
 export interface RecoveryContext {
   basePath: string;
@@ -35,6 +35,13 @@ export async function recoverTimedOutUnit(
   reason: "idle" | "hard",
   rctx: RecoveryContext,
 ): Promise<"recovered" | "paused"> {
+  // Note on turn epoch: the bump is intentionally NOT unconditional at
+  // function entry. Two branches below (the "steering retry" paths) keep
+  // the same LLM turn alive and let it try again — they must NOT bump,
+  // otherwise the retry's legitimate writes get marked stale and drop.
+  // Each advance branch calls `bumpAndResolveSynthetic` to bump+resolve
+  // atomically. Search for that helper to find all supersede sites.
+
   const { basePath, verbose, currentUnitStartedAt, unitRecoveryCount } = rctx;
 
   const runtime = readUnitRuntimeRecord(basePath, unitType, unitId);
@@ -74,7 +81,7 @@ export async function recoverTimedOutUnit(
         "info",
       );
       unitRecoveryCount.delete(recoveryKey);
-      resolveAgentEnd({ messages: [], _synthetic: "timeout-recovery" } as any);
+      bumpAndResolveSynthetic(`timeout-recovery:${reason}:${unitType}/${unitId}`);
       return "recovered";
     }
 
@@ -145,7 +152,7 @@ export async function recoverTimedOutUnit(
         "warning",
       );
       unitRecoveryCount.delete(recoveryKey);
-      resolveAgentEnd({ messages: [], _synthetic: "timeout-recovery" } as any);
+      bumpAndResolveSynthetic(`timeout-recovery:${reason}:${unitType}/${unitId}`);
       return "recovered";
     }
 
@@ -179,7 +186,7 @@ export async function recoverTimedOutUnit(
       "info",
     );
     unitRecoveryCount.delete(recoveryKey);
-    resolveAgentEnd({ messages: [], _synthetic: "timeout-recovery" } as any);
+    bumpAndResolveSynthetic(`timeout-recovery:${reason}:${unitType}/${unitId}`);
     return "recovered";
   }
 
@@ -265,7 +272,7 @@ export async function recoverTimedOutUnit(
       "warning",
     );
     unitRecoveryCount.delete(recoveryKey);
-    resolveAgentEnd({ messages: [], _synthetic: "timeout-recovery" } as any);
+    bumpAndResolveSynthetic(`timeout-recovery:${reason}:${unitType}/${unitId}`);
     return "recovered";
   }
 

package/src/resources/extensions/gsd/auto-unit-closeout.ts

@@ -45,9 +45,20 @@ export async function closeoutUnit(
       const { buildMemoryLLMCall, extractMemoriesFromUnit } = await import('./memory-extractor.js');
       const llmCallFn = buildMemoryLLMCall(ctx);
       if (llmCallFn) {
-        extractMemoriesFromUnit(activityFile, unitType, unitId, llmCallFn).catch((err) => {
-          logWarning("engine", `memory extraction failed for ${unitType}/${unitId}: ${(err as Error).message}`);
-        });
+        // Awaited: a fire-and-forget here lets memory-extractor writes land in
+        // .gsd/ after closeoutUnit returns but before the milestone merge
+        // runs, which made the working tree appear dirty to `git merge
+        // --squash` (root cause class of #4704). Completion latency is now
+        // bounded by the extractor's LLM call, which is the acceptable price
+        // for not racing the merge boundary.
+        try {
+          await extractMemoriesFromUnit(activityFile, unitType, unitId, llmCallFn);
+        } catch (err) {
+          logWarning(
+            "engine",
+            `memory extraction failed for ${unitType}/${unitId}: ${(err as Error).message}`,
+          );
+        }
       }
     } catch (err) { /* non-fatal */
       logWarning("engine", `operation failed: ${err instanceof Error ? err.message : String(err)}`);

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

@@ -26,6 +26,9 @@ import {
   isDbAvailable,
   getMilestone,
   getMilestoneSlices,
+  closeDatabase,
+  openDatabase,
+  getDbPath,
 } from "./gsd-db.js";
 import { atomicWriteSync } from "./atomic-write.js";
 import { execFileSync } from "node:child_process";
@@ -238,14 +241,6 @@ function clearProjectRootStateFiles(basePath: string, milestoneId: string): void
   }
 }
 
-function isProjectGsdSymlink(basePath: string): boolean {
-  try {
-    return lstatSyncFn(join(basePath, ".gsd")).isSymbolicLink();
-  } catch {
-    return false;
-  }
-}
-
 // ─── Build Artifact Auto-Resolve ─────────────────────────────────────────────
 
 /** Patterns for machine-generated build artifacts that can be safely
@@ -1664,73 +1659,63 @@ export function mergeMilestoneToMain(
     }
   }
 
-  // 7. Stash any pre-existing dirty files so the squash merge is not
-  //    blocked by unrelated local changes (#2151).  clearProjectRootStateFiles
-  //    only removes untracked .gsd/ files; tracked dirty files elsewhere (e.g.
-  //    .planning/work-state.json with stash conflict markers) are invisible to
-  //    that cleanup but will cause `git merge --squash` to reject.
-  let stashed = false;
-  try {
-    const status = execFileSync("git", ["status", "--porcelain"], {
-      cwd: originalBasePath_,
-      stdio: ["ignore", "pipe", "pipe"],
-      encoding: "utf-8",
-    }).trim();
-    if (status) {
-      // Use --include-untracked to stash untracked files that would block
-      // the squash merge, but EXCLUDE .gsd/milestones/ (#2505).
-      // --include-untracked without exclusion sweeps queued milestone
-      // CONTEXT files into the stash. If stash pop later fails, those files
-      // are permanently trapped in the stash entry and lost on the next
-      // stash push or drop.
-      //
-      // When `.gsd` itself is a symlink, Git rejects pathspecs below it
-      // ("beyond a symbolic link"). In that layout, exclude the whole symlink
-      // and keep stashing real project files that could block the merge.
-      const stashPathspecs = isProjectGsdSymlink(originalBasePath_)
-        ? [".", ":(exclude).gsd"]
-        : [":(exclude).gsd/milestones"];
-      execFileSync(
-        "git",
-        [
-          "stash", "push", "--include-untracked",
-          "-m", `gsd: pre-merge stash for ${milestoneId}`,
-          "--", ...stashPathspecs,
-        ],
-        { cwd: originalBasePath_, stdio: ["ignore", "pipe", "pipe"], encoding: "utf-8" },
-      );
-      stashed = true;
-    }
-  } catch (err) {
-    // Stash failure is non-fatal — proceed without stash and let the merge
-    // report the dirty tree if it fails.
-    logWarning("worktree", `git stash failed: ${err instanceof Error ? err.message : String(err)}`);
-  }
-
-  // 7a. Shelter queued milestone directories before the squash merge (#2505).
+  // 7. Shelter queued milestone directories before the squash merge (#2505).
   // The milestone branch may contain copies of queued milestone dirs (via
   // copyPlanningArtifacts), so `git merge --squash` rejects when those same
   // files exist as untracked in the working tree. Temporarily move them to
   // a backup location, then restore after the merge+commit.
+  //
+  // MUST run BEFORE the pre-merge stash (step 7a) so `--include-untracked`
+  // does not sweep queued CONTEXT files into the stash. If stash pop later
+  // fails, files trapped inside the stash are permanently lost (#2505).
   const milestonesDir = join(gsdRoot(originalBasePath_), "milestones");
   const shelterDir = join(gsdRoot(originalBasePath_), ".milestone-shelter");
   const shelteredDirs: string[] = [];
+  let shelterRestored = false;
 
   // Helper: restore sheltered milestone directories (#2505).
   // Called on both success and error paths to ensure queued CONTEXT files
-  // are never permanently lost.
+  // are never permanently lost. Idempotent — the error path may fire after
+  // the success path has already restored and removed the shelter dir; a
+  // second call is a no-op instead of logging a misleading "shelter restore
+  // failed: ENOENT" error for shelter sources that were cleaned up legitimately.
   const restoreShelter = (): void => {
+    if (shelterRestored) return;
+    shelterRestored = true;
     if (shelteredDirs.length === 0) return;
+    let restoreFailed = false;
     for (const dirName of shelteredDirs) {
+      const src = join(shelterDir, dirName);
+      // If the shelter source is missing the restore cannot proceed for this
+      // entry. Distinguish "legitimately missing" (shelter dir removed by a
+      // prior successful restore or never copied) from a surprising ENOENT
+      // inside an otherwise-populated shelter.
+      if (!existsSync(src)) {
+        logWarning(
+          "worktree",
+          `shelter source missing for ${dirName}; skipping restore (shelter already cleaned or entry never staged)`,
+        );
+        continue;
+      }
       try {
         mkdirSync(milestonesDir, { recursive: true });
-        cpSync(join(shelterDir, dirName), join(milestonesDir, dirName), { recursive: true, force: true });
+        cpSync(src, join(milestonesDir, dirName), { recursive: true, force: true });
       } catch (err) { /* best-effort */
-        logError("worktree", `shelter restore failed: ${err instanceof Error ? err.message : String(err)}`);
+        restoreFailed = true;
+        logError("worktree", `shelter restore failed (${dirName}): ${err instanceof Error ? err.message : String(err)}`);
       }
     }
-    try { rmSync(shelterDir, { recursive: true, force: true }); } catch (err) { /* best-effort */
-      logWarning("worktree", `shelter cleanup failed: ${err instanceof Error ? err.message : String(err)}`);
+    // Preserve the shelter if any per-entry restore failed — it is the only
+    // surviving copy of the queued milestone dirs (sources were deleted during
+    // shelter). Deleting it here would permanently lose those files (#2505).
+    if (restoreFailed) {
+      logWarning("worktree", `shelter retained at ${shelterDir} — manual recovery required for unrestored entries`);
+      return;
+    }
+    if (existsSync(shelterDir)) {
+      try { rmSync(shelterDir, { recursive: true, force: true }); } catch (err) { /* best-effort */
+        logWarning("worktree", `shelter cleanup failed: ${err instanceof Error ? err.message : String(err)}`);
+      }
     }
   };
 
@@ -1759,6 +1744,58 @@ export function mergeMilestoneToMain(
     logWarning("worktree", `milestone shelter operation failed: ${err instanceof Error ? err.message : String(err)}`);
   }
 
+  // 7a. Stash pre-existing dirty files so the squash merge is not blocked by
+  //     unrelated local changes (#2151). Includes untracked files to handle
+  //     locally-added files that conflict with tracked files on the milestone
+  //     branch. Passing NO pathspec lets git skip gitignored paths silently;
+  //     adding an explicit pathspec trips a `git add`-style fatal on ignored
+  //     entries (e.g. a gitignored `.gsd` symlink under ADR-002) (#4573).
+  //     Queued CONTEXT files under `.gsd/milestones/*` are already sheltered
+  //     in step 7 above, so they won't be swept into the stash.
+  // On Windows, SQLite holds mandatory file locks on the gsd.db WAL/SHM
+  // sidecars while the connection is open. `git stash --include-untracked`
+  // walks those files and fails with EBUSY (#4704). Close the DB before
+  // stashing so Windows releases the handles; reopen after. No-op on
+  // POSIX, where advisory locks don't block git.
+  const needsDbCycle = process.platform === "win32" && isDbAvailable();
+  const dbPathToReopen = needsDbCycle ? getDbPath() : null;
+  if (needsDbCycle) {
+    try {
+      closeDatabase();
+    } catch (err) {
+      logWarning("worktree", `pre-stash db close failed: ${err instanceof Error ? err.message : String(err)}`);
+    }
+  }
+
+  let stashed = false;
+  try {
+    const status = execFileSync("git", ["status", "--porcelain"], {
+      cwd: originalBasePath_,
+      stdio: ["ignore", "pipe", "pipe"],
+      encoding: "utf-8",
+    }).trim();
+    if (status) {
+      execFileSync(
+        "git",
+        ["stash", "push", "--include-untracked", "-m", `gsd: pre-merge stash for ${milestoneId}`],
+        { cwd: originalBasePath_, stdio: ["ignore", "pipe", "pipe"], encoding: "utf-8" },
+      );
+      stashed = true;
+    }
+  } catch (err) {
+    // Stash failure is non-fatal — proceed without stash and let the merge
+    // report the dirty tree if it fails.
+    logWarning("worktree", `git stash failed: ${err instanceof Error ? err.message : String(err)}`);
+  }
+
+  if (needsDbCycle && dbPathToReopen) {
+    try {
+      openDatabase(dbPathToReopen);
+    } catch (err) {
+      logWarning("worktree", `post-stash db reopen failed: ${err instanceof Error ? err.message : String(err)}`);
+    }
+  }
+
   // 7b. Clean up stale merge state before attempting squash merge (#2912).
   // A leftover MERGE_HEAD (from a previous failed merge, libgit2 native path,
   // or interrupted operation) causes `git merge --squash` to refuse with
@@ -2012,21 +2049,38 @@ export function mergeMilestoneToMain(
   // When a milestone only produced .gsd/ metadata (summaries, roadmaps) but no
   // real code, the user sees "milestone complete" but nothing changed in their
   // codebase. Surface this so the caller can warn the user.
+  //
+  // Bug #4385 fix: use `git diff-tree --root` instead of `git diff HEAD~1 HEAD`.
+  // `HEAD~1` does not exist on initial commits and is unreliable on shallow clones
+  // and merge commits. `diff-tree --root` handles all three cases correctly.
+  // The empty-tree hash (4b825dc…) is the universal fallback for refs that don't exist.
+  const GIT_EMPTY_TREE = "4b825dc642cb6eb9a060e54bf8d69288fbee4904";
   let codeFilesChanged = false;
   if (!nothingToCommit) {
     try {
-      const mergedFiles = nativeDiffNumstat(
-        originalBasePath_,
-        "HEAD~1",
-        "HEAD",
-      );
-      codeFilesChanged = mergedFiles.some(
-        (entry) => !entry.path.startsWith(".gsd/"),
-      );
+      const diffTreeOutput = execFileSync(
+        "git",
+        ["diff-tree", "--root", "--no-commit-id", "-r", "--name-only", "HEAD"],
+        { cwd: originalBasePath_, stdio: ["ignore", "pipe", "pipe"], encoding: "utf-8" },
+      ).trim();
+      const mergedFiles = diffTreeOutput ? diffTreeOutput.split("\n").filter(Boolean) : [];
+      codeFilesChanged = mergedFiles.some((f) => !f.startsWith(".gsd/"));
     } catch (e) {
-      // If HEAD~1 doesn't exist (first commit), assume code was changed
-      logWarning("worktree", `diff numstat failed (assuming code changed): ${(e as Error).message}`);
-      codeFilesChanged = true;
+      // diff-tree failed (e.g. unborn HEAD in a brand-new repo) — fall back to
+      // comparing against the empty tree so initial-commit repos still report changes.
+      try {
+        const fallbackOutput = execFileSync(
+          "git",
+          ["diff", "--name-only", GIT_EMPTY_TREE, "HEAD"],
+          { cwd: originalBasePath_, stdio: ["ignore", "pipe", "pipe"], encoding: "utf-8" },
+        ).trim();
+        const fallbackFiles = fallbackOutput ? fallbackOutput.split("\n").filter(Boolean) : [];
+        codeFilesChanged = fallbackFiles.some((f) => !f.startsWith(".gsd/"));
+      } catch {
+        // Truly unable to determine — assume code was changed to avoid silent data loss
+        logWarning("worktree", `diff-tree and empty-tree fallback both failed (assuming code changed): ${(e as Error).message}`);
+        codeFilesChanged = true;
+      }
     }
   }