gsd-pi 2.80.0-dev.c5f2443b3 → 2.80.0-dev.d4fc28e6b

package/src/resources/extensions/gsd/git-service.ts

@@ -14,6 +14,7 @@ import { isAbsolute, join, normalize, relative, resolve, sep } from "node:path";
 import { gsdRoot } from "./paths.js";
 import { GIT_NO_PROMPT_ENV } from "./git-constants.js";
 import { loadEffectiveGSDPreferences } from "./preferences.js";
+import { logWarning } from "./workflow-logger.js";
 
 
 import {
@@ -722,16 +723,53 @@ export class GitServiceImpl {
     if (keyFiles.length === 0) return false;
 
     const allExclusions = [...RUNTIME_EXCLUSION_PATHS, ...extraExclusions];
-    const paths = Array.from(new Set(
-      keyFiles
-        .map(file => normalizeRepoRelativePath(this.basePath, file))
-        .filter((file): file is string => file !== null)
-        .filter(file => !isExcludedScopedPath(file, allExclusions)),
-    ));
+    const normalized = keyFiles
+      .map(file => normalizeRepoRelativePath(this.basePath, file))
+      .filter((file): file is string => file !== null)
+      .filter(file => !isExcludedScopedPath(file, allExclusions));
+
+    // Drop entries that don't exist on disk. The LLM occasionally lists files
+    // it intended to write but didn't (or names them with wrong casing/path).
+    // Pre-`b304f738b` `git add -A` swallowed these silently; the scoped
+    // pathspec form passes each path explicitly, so a single bad entry made
+    // the whole commit fail (see #5500). Filter so valid paths still commit.
+    const missing: string[] = [];
+    const existing: string[] = [];
+    for (const path of normalized) {
+      if (existsSync(join(this.basePath, path))) {
+        existing.push(path);
+      } else {
+        missing.push(path);
+      }
+    }
+    if (missing.length > 0) {
+      logWarning(
+        "engine",
+        `scoped stage: dropping ${missing.length} non-existent keyFile(s) from task commit: ${missing.join(", ")}`,
+        { file: "git-service.ts" },
+      );
+    }
+
+    const paths = Array.from(new Set(existing));
     if (paths.length === 0) return false;
 
-    nativeAddPaths(this.basePath, paths);
-    return true;
+    try {
+      nativeAddPaths(this.basePath, paths);
+      return true;
+    } catch (err) {
+      // Defense-in-depth: even after existence filtering, libgit2/git can
+      // still reject paths (gitignore matches, case-only differences on
+      // case-insensitive FS, submodule boundaries). Returning false lets
+      // autoCommit fall through to smartStage so the commit still goes out
+      // — restoring the resilience the unscoped path used to provide.
+      const msg = err instanceof Error ? err.message : String(err);
+      logWarning(
+        "engine",
+        `scoped stage failed (${msg}); falling back to smartStage`,
+        { file: "git-service.ts" },
+      );
+      return false;
+    }
   }
 
   /** Tracks whether runtime file cleanup has run this session. */

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

@@ -31,7 +31,7 @@ export interface GraphStep {
   status: "pending" | "active" | "complete" | "expanded";
   /** The prompt to dispatch for this step. */
   prompt: string;
-  /** IDs of steps that must be "complete" before this step can run. */
+  /** IDs of steps that must be terminal before this step can run. */
   dependsOn: string[];
   /** For iteration instances: ID of the parent step that was expanded. */
   parentStepId?: string;
@@ -152,10 +152,17 @@ export function writeGraph(runDir: string, graph: WorkflowGraph): void {
 }
 
 /**
- * Get the next pending step whose dependencies are all complete.
+ * Return whether a graph step status satisfies dependency edges.
+ */
+export function isTerminalStepStatus(status: GraphStep["status"] | undefined): boolean {
+  return status === "complete" || status === "expanded";
+}
+
+/**
+ * Get the next pending step whose dependencies are all terminal.
  *
  * Returns the first step (in array order) with status "pending" where
- * every step in its `dependsOn` list has status "complete".
+ * every step in its `dependsOn` list has status "complete" or "expanded".
  *
  * @param graph — the workflow graph to query
  * @returns The next dispatchable step, or null if none available
@@ -165,8 +172,8 @@ export function getNextPendingStep(graph: WorkflowGraph): GraphStep | null {
 
   for (const step of graph.steps) {
     if (step.status !== "pending") continue;
-    const depsComplete = step.dependsOn.every(
-      (depId) => statusMap.get(depId) === "complete",
+    const depsComplete = step.dependsOn.every((depId) =>
+      isTerminalStepStatus(statusMap.get(depId)),
     );
     if (depsComplete) return step;
   }

package/src/resources/extensions/gsd/gsd-db.ts

@@ -23,6 +23,7 @@
 // excluded from this invariant.
 
 import { createRequire } from "node:module";
+import { createHash } from "node:crypto";
 import { existsSync, copyFileSync, mkdirSync, realpathSync } from "node:fs";
 import { dirname } from "node:path";
 import type { Decision, Requirement, GateRow, GateId, GateScope, GateStatus, GateVerdict } from "./types.js";
@@ -77,6 +78,9 @@ import {
   applyMigrationV21StructuredMemories,
   applyMigrationV22QualityGateRepair,
   applyMigrationV23MilestoneQueue,
+  applyMigrationV26MilestoneCommitAttributions,
+  applyMigrationV27ArtifactHash,
+  applyMigrationV28MemoryLastHitAt,
 } from "./db-migration-steps.js";
 import { isMemoriesFtsAvailableSchema, tryCreateMemoriesFtsSchema } from "./db-memory-fts-schema.js";
 import { createDbOpenState, type DbOpenPhase } from "./db-open-state.js";
@@ -105,7 +109,7 @@ const providerLoader = createSqliteProviderLoader({
   writeStderr: (message: string) => process.stderr.write(message),
 });
 
-export const SCHEMA_VERSION = 25;
+export const SCHEMA_VERSION = 28;
 
 function initSchema(db: DbAdapter, fileBacked: boolean): void {
   if (fileBacked) db.exec("PRAGMA journal_mode=WAL");
@@ -329,6 +333,21 @@ function migrateSchema(db: DbAdapter): void {
       recordSchemaVersion(db, 25);
     }
 
+    if (currentVersion < 26) {
+      applyMigrationV26MilestoneCommitAttributions(db);
+      recordSchemaVersion(db, 26);
+    }
+
+    if (currentVersion < 27) {
+      applyMigrationV27ArtifactHash(db);
+      recordSchemaVersion(db, 27);
+    }
+
+    if (currentVersion < 28) {
+      applyMigrationV28MemoryLastHitAt(db);
+      recordSchemaVersion(db, 28);
+    }
+
     db.exec("COMMIT");
   } catch (err) {
     db.exec("ROLLBACK");
@@ -907,9 +926,10 @@ export function insertArtifact(a: {
   full_content: string;
 }): void {
   if (!currentDb) throw new GSDError(GSD_STALE_STATE, "gsd-db: No database open");
+  const contentHash = createHash("sha256").update(a.full_content).digest("hex");
   currentDb.prepare(
-    `INSERT OR REPLACE INTO artifacts (path, artifact_type, milestone_id, slice_id, task_id, full_content, imported_at)
-     VALUES (:path, :artifact_type, :milestone_id, :slice_id, :task_id, :full_content, :imported_at)`,
+    `INSERT OR REPLACE INTO artifacts (path, artifact_type, milestone_id, slice_id, task_id, full_content, imported_at, content_hash)
+     VALUES (:path, :artifact_type, :milestone_id, :slice_id, :task_id, :full_content, :imported_at, :content_hash)`,
   ).run({
     ":path": a.path,
     ":artifact_type": a.artifact_type,
@@ -918,6 +938,7 @@ export function insertArtifact(a: {
     ":task_id": a.task_id,
     ":full_content": a.full_content,
     ":imported_at": new Date().toISOString(),
+    ":content_hash": contentHash,
   });
 }
 
@@ -1349,6 +1370,45 @@ export function getSliceTasks(milestoneId: string, sliceId: string): TaskRow[] {
   return rows.map(rowToTask);
 }
 
+export function getCompletedMilestoneTaskFileHints(milestoneId: string): string[] {
+  if (!currentDb) return [];
+  const rows = currentDb.prepare(
+    `SELECT files, key_files
+     FROM tasks
+     WHERE milestone_id = :mid AND status IN ('complete', 'done')`,
+  ).all({ ":mid": milestoneId }) as Array<Record<string, unknown>>;
+
+  const hints = new Set<string>();
+  for (const row of rows) {
+    for (const raw of [row["files"], row["key_files"]]) {
+      for (const file of parseStringArrayColumn(raw)) {
+        const normalized = normalizeRepoPath(file);
+        if (normalized) hints.add(normalized);
+      }
+    }
+  }
+  return [...hints];
+}
+
+function parseStringArrayColumn(raw: unknown): string[] {
+  if (Array.isArray(raw)) return raw.filter((entry): entry is string => typeof entry === "string");
+  if (typeof raw !== "string") return [];
+  const trimmed = raw.trim();
+  if (!trimmed) return [];
+  try {
+    const parsed = JSON.parse(trimmed);
+    if (Array.isArray(parsed)) return parsed.filter((entry): entry is string => typeof entry === "string");
+    if (typeof parsed === "string") return [parsed];
+  } catch {
+    return trimmed.split(",");
+  }
+  return [];
+}
+
+function normalizeRepoPath(file: string): string {
+  return file.trim().replace(/\\/g, "/").replace(/^\.\/+/, "");
+}
+
 // ─── ADR-011 Phase 2 escalation helpers ──────────────────────────────────
 
 /** Set pause-on-escalation state on a completed task. Mutually exclusive with awaiting_review. */
@@ -1750,6 +1810,13 @@ export function reconcileWorktreeDb(
       const hasEscalationAwaiting = wtTaskInfo.some((col) => col["name"] === "escalation_awaiting_review");
       const hasEscalationArtifact = wtTaskInfo.some((col) => col["name"] === "escalation_artifact_path");
       const hasEscalationOverride = wtTaskInfo.some((col) => col["name"] === "escalation_override_applied_at");
+      const wtArtifactInfo = adapter.prepare("PRAGMA wt.table_info('artifacts')").all();
+      const hasArtifactContentHash = wtArtifactInfo.some((col) => col["name"] === "content_hash");
+      const wtMemoryInfo = adapter.prepare("PRAGMA wt.table_info('memories')").all();
+      const hasMemoryScope = wtMemoryInfo.some((col) => col["name"] === "scope");
+      const hasMemoryTags = wtMemoryInfo.some((col) => col["name"] === "tags");
+      const hasMemoryStructuredFields = wtMemoryInfo.some((col) => col["name"] === "structured_fields");
+      const hasMemoryLastHitAt = wtMemoryInfo.some((col) => col["name"] === "last_hit_at");
 
       const decConf = adapter.prepare(
         `SELECT m.id FROM decisions m INNER JOIN wt.decisions w ON m.id = w.id WHERE m.decision != w.decision OR m.choice != w.choice OR m.rationale != w.rationale OR ${
@@ -1797,12 +1864,17 @@ export function reconcileWorktreeDb(
           FROM wt.requirements
         `).run());
 
+        // V27: preserve content_hash. If the worktree predates V27 (no column),
+        // fall back to the main DB's existing hash so reconcile doesn't null
+        // out integrity fingerprints on artifacts that were unchanged in wt.
         merged.artifacts = countChanges(adapter.prepare(`
           INSERT OR REPLACE INTO artifacts (
-            path, artifact_type, milestone_id, slice_id, task_id, full_content, imported_at
+            path, artifact_type, milestone_id, slice_id, task_id, full_content, imported_at, content_hash
           )
-          SELECT path, artifact_type, milestone_id, slice_id, task_id, full_content, imported_at
-          FROM wt.artifacts
+          SELECT w.path, w.artifact_type, w.milestone_id, w.slice_id, w.task_id, w.full_content, w.imported_at,
+                 ${hasArtifactContentHash ? "w.content_hash" : "m.content_hash"}
+          FROM wt.artifacts w
+          LEFT JOIN artifacts m ON m.path = w.path
         `).run());
 
         // Merge milestones — worktree may have updated status/planning fields.
@@ -1904,15 +1976,25 @@ export function reconcileWorktreeDb(
           LEFT JOIN tasks m ON m.milestone_id = w.milestone_id AND m.slice_id = w.slice_id AND m.id = w.id
         `).run());
 
-        // Merge memories — keep worktree-learned insights
+        // Merge memories — keep worktree-learned insights.
+        // V18 (scope, tags), V21 (structured_fields), V28 (last_hit_at): for each
+        // column the wt may not yet have (older worktree DB), fall back to the
+        // main DB's existing value via LEFT JOIN so reconcile never silently
+        // resets these fields to defaults on rows that already had them.
         merged.memories = countChanges(adapter.prepare(`
           INSERT OR REPLACE INTO memories (
             seq, id, category, content, confidence, source_unit_type, source_unit_id,
-            created_at, updated_at, superseded_by, hit_count
+            created_at, updated_at, superseded_by, hit_count,
+            scope, tags, structured_fields, last_hit_at
           )
-          SELECT seq, id, category, content, confidence, source_unit_type, source_unit_id,
-                 created_at, updated_at, superseded_by, hit_count
-          FROM wt.memories
+          SELECT w.seq, w.id, w.category, w.content, w.confidence, w.source_unit_type, w.source_unit_id,
+                 w.created_at, w.updated_at, w.superseded_by, w.hit_count,
+                 ${hasMemoryScope ? "w.scope" : "COALESCE(m.scope, 'project')"},
+                 ${hasMemoryTags ? "w.tags" : "COALESCE(m.tags, '[]')"},
+                 ${hasMemoryStructuredFields ? "w.structured_fields" : "m.structured_fields"},
+                 ${hasMemoryLastHitAt ? "w.last_hit_at" : "m.last_hit_at"}
+          FROM wt.memories w
+          LEFT JOIN memories m ON m.id = w.id
         `).run());
 
         // Merge verification evidence — append-only, use INSERT OR IGNORE to avoid duplicates
@@ -2073,6 +2155,9 @@ export function deleteMilestone(milestoneId: string): void {
     currentDb!.prepare(
       `DELETE FROM artifacts WHERE milestone_id = :mid`,
     ).run({ ":mid": milestoneId });
+    currentDb!.prepare(
+      `DELETE FROM milestone_commit_attributions WHERE milestone_id = :mid`,
+    ).run({ ":mid": milestoneId });
     currentDb!.prepare(
       `DELETE FROM milestone_leases WHERE milestone_id = :mid`,
     ).run({ ":mid": milestoneId });
@@ -2391,6 +2476,75 @@ export function upsertTurnGitTransaction(entry: {
   });
 }
 
+export function getMilestoneCommitAttributionShas(milestoneId: string): string[] {
+  if (!currentDb) return [];
+  const rows = currentDb.prepare(
+    `SELECT commit_sha
+     FROM milestone_commit_attributions
+     WHERE milestone_id = :mid
+     ORDER BY created_at, commit_sha`,
+  ).all({ ":mid": milestoneId }) as Array<Record<string, unknown>>;
+  return rows
+    .map((row) => typeof row["commit_sha"] === "string" ? row["commit_sha"] : "")
+    .filter(Boolean);
+}
+
+export function recordMilestoneCommitAttribution(entry: {
+  commitSha: string;
+  milestoneId: string;
+  sliceId?: string;
+  taskId?: string;
+  source: "recorded" | "backfill";
+  confidence: number;
+  files: string[];
+  createdAt: string;
+}): void {
+  if (!currentDb) return;
+  transaction(() => {
+    currentDb!.prepare(
+      `INSERT OR REPLACE INTO milestone_commit_attributions (
+        commit_sha, milestone_id, slice_id, task_id, source, confidence, files_json, created_at
+      ) VALUES (
+        :commit_sha, :milestone_id, :slice_id, :task_id, :source, :confidence, :files_json, :created_at
+      )`,
+    ).run({
+      ":commit_sha": entry.commitSha,
+      ":milestone_id": entry.milestoneId,
+      ":slice_id": entry.sliceId ?? null,
+      ":task_id": entry.taskId ?? null,
+      ":source": entry.source,
+      ":confidence": entry.confidence,
+      ":files_json": JSON.stringify(entry.files),
+      ":created_at": entry.createdAt,
+    });
+
+    currentDb!.prepare(
+      `INSERT OR IGNORE INTO audit_events (
+        event_id, trace_id, turn_id, caused_by, category, type, ts, payload_json
+      ) VALUES (
+        :event_id, :trace_id, :turn_id, :caused_by, :category, :type, :ts, :payload_json
+      )`,
+    ).run({
+      ":event_id": `milestone-commit-attribution:${entry.milestoneId}:${entry.commitSha}`,
+      ":trace_id": "milestone-commit-attribution",
+      ":turn_id": null,
+      ":caused_by": null,
+      ":category": "git",
+      ":type": "milestone-commit-attribution-recorded",
+      ":ts": entry.createdAt,
+      ":payload_json": JSON.stringify({
+        commitSha: entry.commitSha,
+        milestoneId: entry.milestoneId,
+        sliceId: entry.sliceId ?? null,
+        taskId: entry.taskId ?? null,
+        source: entry.source,
+        confidence: entry.confidence,
+        files: entry.files,
+      }),
+    });
+  });
+}
+
 export function insertAuditEvent(entry: {
   eventId: string;
   traceId: string;
@@ -2494,6 +2648,7 @@ export function clearEngineHierarchy(): void {
     currentDb!.exec("DELETE FROM slice_dependencies");
     currentDb!.exec("DELETE FROM assessments");
     currentDb!.exec("DELETE FROM replan_history");
+    currentDb!.exec("DELETE FROM milestone_commit_attributions");
     currentDb!.exec("DELETE FROM tasks");
     currentDb!.exec("DELETE FROM slices");
     currentDb!.exec("DELETE FROM milestone_leases");
@@ -2944,8 +3099,8 @@ export function updateMemoryContentRow(
 export function incrementMemoryHitCount(id: string, updatedAt: string): void {
   if (!currentDb) throw new GSDError(GSD_STALE_STATE, "gsd-db: No database open");
   currentDb.prepare(
-    "UPDATE memories SET hit_count = hit_count + 1, updated_at = :updated_at WHERE id = :id",
-  ).run({ ":updated_at": updatedAt, ":id": id });
+    "UPDATE memories SET hit_count = hit_count + 1, updated_at = :updated_at, last_hit_at = :last_hit_at WHERE id = :id",
+  ).run({ ":updated_at": updatedAt, ":last_hit_at": updatedAt, ":id": id });
 }
 
 export function supersedeMemoryRow(oldId: string, newId: string, updatedAt: string): void {