gsd-pi 2.45.0 → 2.46.0-dev.cc9d310

package/src/resources/extensions/gsd/doctor-checks.ts

@@ -5,7 +5,7 @@ import type { DoctorIssue, DoctorIssueCode } from "./doctor-types.js";
 import { readRepoMeta, externalProjectsRoot, cleanNumberedGsdVariants } from "./repo-identity.js";
 import { loadFile } from "./files.js";
 import { parseRoadmap as parseLegacyRoadmap } from "./parsers-legacy.js";
-import { isDbAvailable, getMilestoneSlices } from "./gsd-db.js";
+import { isDbAvailable, _getAdapter, getMilestoneSlices } from "./gsd-db.js";
 import { resolveMilestoneFile, milestonesDir, gsdRoot, resolveGsdRootFile, relGsdRootFile } from "./paths.js";
 import { deriveState, isMilestoneComplete } from "./state.js";
 import { saveFile } from "./files.js";
@@ -19,13 +19,15 @@ import { getAllWorktreeHealth } from "./worktree-health.js";
 import { readAllSessionStatuses, isSessionStale, removeSessionStatus } from "./session-status-io.js";
 import { recoverFailedMigration } from "./migrate-external.js";
 import { loadEffectiveGSDPreferences } from "./preferences.js";
+import { readEvents } from "./workflow-events.js";
+import { renderAllProjections } from "./workflow-projections.js";
 
 export async function checkGitHealth(
   basePath: string,
   issues: DoctorIssue[],
   fixesApplied: string[],
   shouldFix: (code: DoctorIssueCode) => boolean,
-  isolationMode: "none" | "worktree" | "branch" = "worktree",
+  isolationMode: "none" | "worktree" | "branch" = "none",
 ): Promise<void> {
   // Degrade gracefully if not a git repo
   if (!nativeIsRepo(basePath)) {
@@ -1111,3 +1113,179 @@ export async function checkGlobalHealth(
     // Non-fatal — global health check must not block per-project doctor
   }
 }
+
+// ── Engine Health Checks ────────────────────────────────────────────────────
+// DB constraint violation detection and projection drift checks.
+
+export async function checkEngineHealth(
+  basePath: string,
+  issues: DoctorIssue[],
+  fixesApplied: string[],
+): Promise<void> {
+  // ── DB constraint violation detection (full doctor only, not pre-dispatch per D-10) ──
+  try {
+    if (isDbAvailable()) {
+      const adapter = _getAdapter()!;
+
+      // a. Orphaned tasks (task.slice_id points to non-existent slice)
+      try {
+        const orphanedTasks = adapter
+          .prepare(
+            `SELECT t.id, t.slice_id, t.milestone_id
+             FROM tasks t
+             LEFT JOIN slices s ON t.milestone_id = s.milestone_id AND t.slice_id = s.id
+             WHERE s.id IS NULL`,
+          )
+          .all() as Array<{ id: string; slice_id: string; milestone_id: string }>;
+
+        for (const row of orphanedTasks) {
+          issues.push({
+            severity: "error",
+            code: "db_orphaned_task",
+            scope: "task",
+            unitId: `${row.milestone_id}/${row.slice_id}/${row.id}`,
+            message: `Task ${row.id} references slice ${row.slice_id} in milestone ${row.milestone_id} but no such slice exists in the database`,
+            fixable: false,
+          });
+        }
+      } catch {
+        // Non-fatal — orphaned task check failed
+      }
+
+      // b. Orphaned slices (slice.milestone_id points to non-existent milestone)
+      try {
+        const orphanedSlices = adapter
+          .prepare(
+            `SELECT s.id, s.milestone_id
+             FROM slices s
+             LEFT JOIN milestones m ON s.milestone_id = m.id
+             WHERE m.id IS NULL`,
+          )
+          .all() as Array<{ id: string; milestone_id: string }>;
+
+        for (const row of orphanedSlices) {
+          issues.push({
+            severity: "error",
+            code: "db_orphaned_slice",
+            scope: "slice",
+            unitId: `${row.milestone_id}/${row.id}`,
+            message: `Slice ${row.id} references milestone ${row.milestone_id} but no such milestone exists in the database`,
+            fixable: false,
+          });
+        }
+      } catch {
+        // Non-fatal — orphaned slice check failed
+      }
+
+      // c. Tasks marked complete without summaries
+      try {
+        const doneTasks = adapter
+          .prepare(
+            `SELECT id, slice_id, milestone_id FROM tasks
+             WHERE status = 'done' AND (summary IS NULL OR summary = '')`,
+          )
+          .all() as Array<{ id: string; slice_id: string; milestone_id: string }>;
+
+        for (const row of doneTasks) {
+          issues.push({
+            severity: "warning",
+            code: "db_done_task_no_summary",
+            scope: "task",
+            unitId: `${row.milestone_id}/${row.slice_id}/${row.id}`,
+            message: `Task ${row.id} is marked done but has no summary in the database`,
+            fixable: false,
+          });
+        }
+      } catch {
+        // Non-fatal — done-task-no-summary check failed
+      }
+
+      // d. Duplicate entity IDs (safety check)
+      try {
+        const dupMilestones = adapter
+          .prepare("SELECT id, COUNT(*) as cnt FROM milestones GROUP BY id HAVING cnt > 1")
+          .all() as Array<{ id: string; cnt: number }>;
+        for (const row of dupMilestones) {
+          issues.push({
+            severity: "error",
+            code: "db_duplicate_id",
+            scope: "milestone",
+            unitId: row.id,
+            message: `Duplicate milestone ID "${row.id}" appears ${row.cnt} times in the database`,
+            fixable: false,
+          });
+        }
+
+        const dupSlices = adapter
+          .prepare("SELECT id, milestone_id, COUNT(*) as cnt FROM slices GROUP BY id, milestone_id HAVING cnt > 1")
+          .all() as Array<{ id: string; milestone_id: string; cnt: number }>;
+        for (const row of dupSlices) {
+          issues.push({
+            severity: "error",
+            code: "db_duplicate_id",
+            scope: "slice",
+            unitId: `${row.milestone_id}/${row.id}`,
+            message: `Duplicate slice ID "${row.id}" in milestone ${row.milestone_id} appears ${row.cnt} times`,
+            fixable: false,
+          });
+        }
+
+        const dupTasks = adapter
+          .prepare("SELECT id, slice_id, milestone_id, COUNT(*) as cnt FROM tasks GROUP BY id, slice_id, milestone_id HAVING cnt > 1")
+          .all() as Array<{ id: string; slice_id: string; milestone_id: string; cnt: number }>;
+        for (const row of dupTasks) {
+          issues.push({
+            severity: "error",
+            code: "db_duplicate_id",
+            scope: "task",
+            unitId: `${row.milestone_id}/${row.slice_id}/${row.id}`,
+            message: `Duplicate task ID "${row.id}" in slice ${row.slice_id} appears ${row.cnt} times`,
+            fixable: false,
+          });
+        }
+      } catch {
+        // Non-fatal — duplicate ID check failed
+      }
+    }
+  } catch {
+    // Non-fatal — DB constraint checks failed entirely
+  }
+
+  // ── Projection drift detection ──────────────────────────────────────────
+  // If the DB is available, check whether markdown projections are stale
+  // relative to the event log and re-render them.
+  try {
+    if (isDbAvailable()) {
+      const eventLogPath = join(basePath, ".gsd", "event-log.jsonl");
+      const events = readEvents(eventLogPath);
+      if (events.length > 0) {
+        const lastEventTs = new Date(events[events.length - 1]!.ts).getTime();
+        const state = await deriveState(basePath);
+        for (const milestone of state.registry) {
+          if (milestone.status === "complete") continue;
+          const roadmapPath = resolveMilestoneFile(basePath, milestone.id, "ROADMAP");
+          if (!roadmapPath || !existsSync(roadmapPath)) {
+            try {
+              await renderAllProjections(basePath, milestone.id);
+              fixesApplied.push(`re-rendered missing projections for ${milestone.id}`);
+            } catch {
+              // Non-fatal — projection re-render failed
+            }
+            continue;
+          }
+          const projectionMtime = statSync(roadmapPath).mtimeMs;
+          if (lastEventTs > projectionMtime) {
+            try {
+              await renderAllProjections(basePath, milestone.id);
+              fixesApplied.push(`re-rendered stale projections for ${milestone.id}`);
+            } catch {
+              // Non-fatal — projection re-render failed
+            }
+          }
+        }
+      }
+    }
+  } catch {
+    // Non-fatal — projection drift check must never block doctor
+  }
+}

package/src/resources/extensions/gsd/doctor-types.ts

@@ -70,7 +70,13 @@ export type DoctorIssueCode =
   | "large_planning_file"
   // Slow environment checks (opt-in via --build / --test flags)
   | "env_build"
-  | "env_test";
+  | "env_test"
+  // Engine health checks (Phase 4)
+  | "db_orphaned_task"
+  | "db_orphaned_slice"
+  | "db_done_task_no_summary"
+  | "db_duplicate_id"
+  | "projection_drift";
 
 /**
  * Issue codes that represent global or completion-critical state.

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

@@ -12,7 +12,7 @@ import { loadEffectiveGSDPreferences, type GSDPreferences } from "./preferences.
 import type { DoctorIssue, DoctorIssueCode, DoctorReport } from "./doctor-types.js";
 import { GLOBAL_STATE_CODES } from "./doctor-types.js";
 import type { RoadmapSliceEntry } from "./types.js";
-import { checkGitHealth, checkRuntimeHealth, checkGlobalHealth } from "./doctor-checks.js";
+import { checkGitHealth, checkRuntimeHealth, checkGlobalHealth, checkEngineHealth } from "./doctor-checks.js";
 import { checkEnvironmentHealth } from "./doctor-environment.js";
 import { runProviderChecks } from "./doctor-providers.js";
 
@@ -360,8 +360,8 @@ export async function runGSDDoctor(basePath: string, options?: { fix?: boolean;
   // Git health checks — timed
   const t0git = Date.now();
   const isolationMode: "none" | "worktree" | "branch" = options?.isolationMode ??
-    (prefs?.preferences?.git?.isolation === "none" ? "none" :
-    prefs?.preferences?.git?.isolation === "branch" ? "branch" : "worktree");
+    (prefs?.preferences?.git?.isolation === "worktree" ? "worktree" :
+    prefs?.preferences?.git?.isolation === "branch" ? "branch" : "none");
   await checkGitHealth(basePath, issues, fixesApplied, shouldFix, isolationMode);
   const gitMs = Date.now() - t0git;
 
@@ -382,6 +382,9 @@ export async function runGSDDoctor(basePath: string, options?: { fix?: boolean;
   });
   const envMs = Date.now() - t0env;
 
+  // Engine health checks — DB constraints and projection drift
+  await checkEngineHealth(basePath, issues, fixesApplied);
+
   const milestonesPath = milestonesDir(basePath);
   if (!existsSync(milestonesPath)) {
     const report: DoctorReport = { ok: issues.every(i => i.severity !== "error"), basePath, issues, fixesApplied, timing: { git: gitMs, runtime: runtimeMs, environment: envMs, gsdState: 0 } };

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

@@ -78,8 +78,12 @@ function loadProvider(): void {
     // unavailable
   }
 
+  const nodeMajor = parseInt(process.versions.node.split(".")[0], 10);
+  const versionHint = nodeMajor < 22
+    ? ` GSD requires Node >= 22.0.0 (current: v${process.versions.node}). Upgrade Node to fix this.`
+    : "";
   process.stderr.write(
-    "gsd-db: No SQLite provider available (tried node:sqlite, better-sqlite3)\n",
+    `gsd-db: No SQLite provider available (tried node:sqlite, better-sqlite3).${versionHint}\n`,
   );
 }
 
@@ -145,7 +149,7 @@ function openRawDb(path: string): unknown {
   return new Database(path);
 }
 
-const SCHEMA_VERSION = 10;
+const SCHEMA_VERSION = 11;
 
 function initSchema(db: DbAdapter, fileBacked: boolean): void {
   if (fileBacked) db.exec("PRAGMA journal_mode=WAL");
@@ -619,6 +623,13 @@ function migrateSchema(db: DbAdapter): void {
 
     if (currentVersion < 11) {
       ensureColumn(db, "tasks", "full_plan_md", `ALTER TABLE tasks ADD COLUMN full_plan_md TEXT NOT NULL DEFAULT ''`);
+      // Add unique constraint to replan_history for idempotency:
+      // one replan record per blocker task per slice per milestone.
+      db.exec(`
+        CREATE UNIQUE INDEX IF NOT EXISTS idx_replan_history_unique
+        ON replan_history(milestone_id, slice_id, task_id)
+        WHERE slice_id IS NOT NULL AND task_id IS NOT NULL
+      `);
 
       db.prepare("INSERT INTO schema_version (version, applied_at) VALUES (:version, :applied_at)").run({
         ":version": 11,
@@ -1602,8 +1613,10 @@ export function insertReplanHistory(entry: {
   replacementArtifactPath?: string | null;
 }): void {
   if (!currentDb) throw new GSDError(GSD_STALE_STATE, "gsd-db: No database open");
+  // INSERT OR REPLACE: idempotent on (milestone_id, slice_id, task_id) via schema v11 unique index.
+  // Retrying the same replan silently updates summary instead of accumulating duplicate rows.
   currentDb.prepare(
-    `INSERT INTO replan_history (milestone_id, slice_id, task_id, summary, previous_artifact_path, replacement_artifact_path, created_at)
+    `INSERT OR REPLACE INTO replan_history (milestone_id, slice_id, task_id, summary, previous_artifact_path, replacement_artifact_path, created_at)
      VALUES (:milestone_id, :slice_id, :task_id, :summary, :previous_artifact_path, :replacement_artifact_path, :created_at)`,
   ).run({
     ":milestone_id": entry.milestoneId,

package/src/resources/extensions/gsd/guided-flow.ts

@@ -910,8 +910,7 @@ export async function showSmartEntry(
     // when the user exits during init wizard or discuss phase before any
     // real auto-mode work begins.
     const isBootstrapCrash = crashLock.unitType === "starting"
-      && crashLock.unitId === "bootstrap"
-      && crashLock.completedUnits === 0;
+      && crashLock.unitId === "bootstrap";
 
     if (!isBootstrapCrash) {
       const resume = await showNextAction(ctx, {

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

@@ -32,7 +32,12 @@ export type JournalEventType =
   | "milestone-transition"
   | "stuck-detected"
   | "sidecar-dequeue"
-  | "iteration-end";
+  | "iteration-end"
+  | "worktree-enter"
+  | "worktree-create-failed"
+  | "worktree-skip"
+  | "worktree-merge-start"
+  | "worktree-merge-failed";
 
 /** A single structured event in the journal. */
 export interface JournalEntry {

package/src/resources/extensions/gsd/parallel-merge.ts

@@ -37,7 +37,7 @@ export function determineMergeOrder(
   workers: WorkerInfo[],
   order: MergeOrder = "sequential",
 ): string[] {
-  const completed = workers.filter(w => w.state === "stopped" && w.completedUnits > 0);
+  const completed = workers.filter(w => w.state === "stopped");
   if (order === "by-completion") {
     return completed
       .sort((a, b) => a.startedAt - b.startedAt) // earliest first

package/src/resources/extensions/gsd/parallel-orchestrator.ts

@@ -52,7 +52,6 @@ export interface WorkerInfo {
   worktreePath: string;
   startedAt: number;
   state: "running" | "paused" | "stopped" | "error";
-  completedUnits: number;
   cost: number;
   cleanup?: () => void;
 }
@@ -83,7 +82,6 @@ export interface PersistedState {
     worktreePath: string;
     startedAt: number;
     state: "running" | "paused" | "stopped" | "error";
-    completedUnits: number;
     cost: number;
   }>;
   totalCost: number;
@@ -114,7 +112,6 @@ export function persistState(basePath: string): void {
         worktreePath: w.worktreePath,
         startedAt: w.startedAt,
         state: w.state,
-        completedUnits: w.completedUnits,
         cost: w.cost,
       })),
       totalCost: state.totalCost,
@@ -226,7 +223,6 @@ function restoreRuntimeState(basePath: string): boolean {
         worktreePath: diskStatus?.worktreePath ?? w.worktreePath,
         startedAt: w.startedAt,
         state: diskStatus?.state ?? w.state,
-        completedUnits: diskStatus?.completedUnits ?? w.completedUnits,
         cost: diskStatus?.cost ?? w.cost,
       });
     }
@@ -261,7 +257,6 @@ function restoreRuntimeState(basePath: string): boolean {
       worktreePath: status.worktreePath,
       startedAt: status.startedAt,
       state: status.state,
-      completedUnits: status.completedUnits,
       cost: status.cost,
     });
     state.totalCost += status.cost;
@@ -389,7 +384,6 @@ export async function startParallel(
         worktreePath: w.worktreePath,
         startedAt: w.startedAt,
         state: "running",
-        completedUnits: w.completedUnits,
         cost: w.cost,
       });
       adopted.push(w.milestoneId);
@@ -440,7 +434,6 @@ export async function startParallel(
         worktreePath: wtPath,
         startedAt: now,
         state: "running",
-        completedUnits: 0,
         cost: 0,
       };
 
@@ -602,7 +595,7 @@ export function spawnWorker(
     pid: worker.pid,
     state: "running",
     currentUnit: null,
-    completedUnits: worker.completedUnits,
+    completedUnits: 0,
     cost: worker.cost,
     lastHeartbeat: Date.now(),
     startedAt: worker.startedAt,
@@ -645,7 +638,7 @@ export function spawnWorker(
       pid: w.pid,
       state: w.state,
       currentUnit: null,
-      completedUnits: w.completedUnits,
+      completedUnits: 0,
       cost: w.cost,
       lastHeartbeat: Date.now(),
       startedAt: w.startedAt,
@@ -727,14 +720,6 @@ function processWorkerLine(basePath: string, milestoneId: string, line: string):
       }
     }
 
-    // Track completed units (each message_end from assistant = progress)
-    if (msg.role === "assistant") {
-      const worker = state.workers.get(milestoneId);
-      if (worker) {
-        worker.completedUnits++;
-      }
-    }
-
     // Update session status file so dashboard sees live cost
     const worker = state.workers.get(milestoneId);
     if (worker) {
@@ -743,7 +728,7 @@ function processWorkerLine(basePath: string, milestoneId: string, line: string):
         pid: worker.pid,
         state: worker.state,
         currentUnit: null,
-        completedUnits: worker.completedUnits,
+        completedUnits: 0,
         cost: worker.cost,
         lastHeartbeat: Date.now(),
         startedAt: worker.startedAt,
@@ -762,7 +747,7 @@ function processWorkerLine(basePath: string, milestoneId: string, line: string):
         pid: worker.pid,
         state: worker.state,
         currentUnit: null,
-        completedUnits: worker.completedUnits,
+        completedUnits: 0,
         cost: worker.cost,
         lastHeartbeat: Date.now(),
         startedAt: worker.startedAt,
@@ -930,14 +915,13 @@ export function refreshWorkerStatuses(
       if (!isPidAlive(worker.pid)) {
         worker.cleanup?.();
         worker.cleanup = undefined;
-        worker.state = worker.completedUnits > 0 ? "stopped" : "error";
+        worker.state = "error";
         worker.process = null;
       }
       continue;
     }
 
     worker.state = diskStatus.state;
-    worker.completedUnits = diskStatus.completedUnits;
     worker.cost = diskStatus.cost;
     worker.pid = diskStatus.pid;
   }

package/src/resources/extensions/gsd/preferences-types.ts

@@ -34,7 +34,7 @@ export const MODE_DEFAULTS: Record<WorkflowMode, Partial<GSDPreferences>> = {
       push_branches: false,
       pre_merge_check: false,
       merge_strategy: "squash",
-      isolation: "worktree",
+      isolation: "none",
     },
     unique_milestone_ids: false,
   },
@@ -44,7 +44,7 @@ export const MODE_DEFAULTS: Record<WorkflowMode, Partial<GSDPreferences>> = {
       push_branches: true,
       pre_merge_check: true,
       merge_strategy: "squash",
-      isolation: "worktree",
+      isolation: "none",
     },
     unique_milestone_ids: true,
   },

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

@@ -497,13 +497,17 @@ export function resolvePreDispatchHooks(): PreDispatchHookConfig[] {
 
 /**
  * Resolve the effective git isolation mode from preferences.
- * Returns "worktree" (default), "branch", or "none".
+ * Returns "none" (default), "worktree", or "branch".
+ *
+ * Default is "none" so GSD works out of the box without preferences.md.
+ * Worktree isolation requires explicit opt-in because it depends on git
+ * branch infrastructure that must be set up before use.
  */
 export function getIsolationMode(): "none" | "worktree" | "branch" {
   const prefs = loadEffectiveGSDPreferences()?.preferences?.git;
-  if (prefs?.isolation === "none") return "none";
+  if (prefs?.isolation === "worktree") return "worktree";
   if (prefs?.isolation === "branch") return "branch";
-  return "worktree"; // default
+  return "none"; // default — no isolation, work on current branch
 }
 
 export function resolveParallelConfig(prefs: GSDPreferences | undefined): import("./types.js").ParallelConfig {

package/src/resources/extensions/gsd/prompts/complete-milestone.md

@@ -17,18 +17,31 @@ All relevant context has been preloaded below — the roadmap, all slice summari
 Then:
 1. Use the **Milestone Summary** output template from the inlined context above
 2. {{skillActivation}}
-3. **Verify code changes exist.** Run `git diff --stat HEAD $(git merge-base HEAD main) -- ':!.gsd/'` (or the equivalent for the integration branch). If no non-`.gsd/` files appear in the diff, the milestone produced only planning artifacts and no actual code. In that case, do NOT mark the milestone as passing verification — document the gap clearly in the summary and state that implementation is missing.
-4. Verify each **success criterion** from the milestone definition in `{{roadmapPath}}`. For each criterion, confirm it was met with specific evidence from slice summaries, test results, or observable behavior. List any criterion that was NOT met.
-5. Verify the milestone's **definition of done** — all slices are `[x]`, all slice summaries exist, and any cross-slice integration points work correctly.
+3. **Verify code changes exist.** Run `git diff --stat HEAD $(git merge-base HEAD main) -- ':!.gsd/'` (or the equivalent for the integration branch). If no non-`.gsd/` files appear in the diff, the milestone produced only planning artifacts and no actual code. Record this as a **verification failure**.
+4. Verify each **success criterion** from the milestone definition in `{{roadmapPath}}`. For each criterion, confirm it was met with specific evidence from slice summaries, test results, or observable behavior. Record any criterion that was NOT met as a **verification failure**.
+5. Verify the milestone's **definition of done** — all slices are `[x]`, all slice summaries exist, and any cross-slice integration points work correctly. Record any unmet items as a **verification failure**.
 6. Validate **requirement status transitions**. For each requirement that changed status during this milestone, confirm the transition is supported by evidence. Requirements can move between Active, Validated, Deferred, Blocked, or Out of Scope — but only with proof.
-7. **Persist completion through `gsd_complete_milestone`.** Call it with: `milestoneId`, `title`, `oneLiner`, `narrative`, `successCriteriaResults`, `definitionOfDoneResults`, `requirementOutcomes`, `keyDecisions`, `keyFiles`, `lessonsLearned`, `followUps`, `deviations`. The tool updates the milestone status in the DB, renders `{{milestoneSummaryPath}}`, and validates all slices are complete before proceeding.
-8. Update `.gsd/REQUIREMENTS.md` if any requirement status transitions were validated in step 6.
+
+### Verification Gate — STOP if verification failed
+
+**If ANY verification failure was recorded in steps 3, 4, or 5, you MUST follow the failure path below. Do NOT proceed to step 7.**
+
+**Failure path** (verification failed):
+- Do NOT call `gsd_complete_milestone` — the milestone must not be marked as complete.
+- Do NOT update `.gsd/PROJECT.md` to reflect completion.
+- Do NOT update `.gsd/REQUIREMENTS.md` to mark requirements as validated.
+- Write a clear summary of what failed and why to help the next attempt.
+- Say: "Milestone {{milestoneId}} verification FAILED — not complete." and stop.
+
+**Success path** (all verifications passed — continue with steps 7–11):
+
+7. **Persist completion through `gsd_complete_milestone`.** Call it with: `milestoneId`, `title`, `oneLiner`, `narrative`, `successCriteriaResults`, `definitionOfDoneResults`, `requirementOutcomes`, `keyDecisions`, `keyFiles`, `lessonsLearned`, `followUps`, `deviations`, `verificationPassed: true`. The tool updates the milestone status in the DB, renders `{{milestoneSummaryPath}}`, and validates all slices are complete before proceeding.
+8. For each requirement whose status changed in step 6, call `gsd_requirement_update` with the requirement ID and updated `status` and `validation` fields — the tool regenerates `.gsd/REQUIREMENTS.md` automatically.
 9. Update `.gsd/PROJECT.md` to reflect milestone completion and current project state.
 10. Review all slice summaries for cross-cutting lessons, patterns, or gotchas that emerged during this milestone. Append any non-obvious, reusable insights to `.gsd/KNOWLEDGE.md`.
 11. Do not commit manually — the system auto-commits your changes after this unit completes.
+- Say: "Milestone {{milestoneId}} complete."
 
-**Important:** Do NOT skip the code change verification, success criteria, or definition of done verification (steps 3-5). The milestone summary must reflect actual verified outcomes, not assumed success. If any criterion was not met or no code changes exist, document it clearly in the summary and do not mark the milestone as passing verification.
+**Important:** Do NOT skip the code change verification, success criteria, or definition of done verification (steps 3-5). The milestone summary must reflect actual verified outcomes, not assumed success. Verification failures BLOCK completion — there is no override. The milestone stays in its current state until issues are resolved and verification is re-run.
 
 **File system safety:** When scanning milestone directories for evidence, use `ls` or `find` to list directory contents first — never pass a directory path (e.g. `tasks/`, `slices/`) directly to the `read` tool. The `read` tool only accepts file paths, not directories.
-
-When done, say: "Milestone {{milestoneId}} complete."

package/src/resources/extensions/gsd/prompts/complete-slice.md

@@ -23,28 +23,15 @@ Then:
 2. {{skillActivation}}
 3. Run all slice-level verification checks defined in the slice plan. All must pass before marking the slice done. If any fail, fix them first.
 4. If the slice plan includes observability/diagnostic surfaces, confirm they work. Skip this for simple slices that don't have observability sections.
-5. If `.gsd/REQUIREMENTS.md` exists, update it based on what this slice actually proved. Move requirements between Active, Validated, Deferred, Blocked, or Out of Scope only when the evidence from execution supports that change.
-6. Call the `gsd_slice_complete` tool (alias: `gsd_complete_slice`) to record the slice as complete. The tool validates all tasks are complete, updates the slice status in the DB, renders the summary to `{{sliceSummaryPath}}`, UAT to `{{sliceUatPath}}`, and re-renders `{{roadmapPath}}` — all atomically. Read the summary and UAT templates at `~/.gsd/agent/extensions/gsd/templates/` to understand the expected structure, then pass the following parameters:
-
-   **Identity:** `sliceId`, `milestoneId`, `sliceTitle`
-
-   **Narrative:** `oneLiner` (one-line summary of what the slice accomplished), `narrative` (detailed account of what happened across all tasks), `verification` (what was verified and how), `deviations` (deviations from plan, or "None."), `knownLimitations` (gaps or limitations, or "None."), `followUps` (follow-up work discovered, or "None.")
-
-   **Files:** `keyFiles` (array of key file paths), `filesModified` (array of `{path, description}` objects for all files changed)
-
-   **Requirements:** `requirementsAdvanced` (array of `{id, how}`), `requirementsValidated` (array of `{id, proof}`), `requirementsInvalidated` (array of `{id, what}`), `requirementsSurfaced` (array of new requirement strings)
-
-   **Patterns & decisions:** `keyDecisions` (array of decision strings), `patternsEstablished` (array), `observabilitySurfaces` (array)
-
-   **Dependencies:** `provides` (what this slice provides downstream), `affects` (downstream slice IDs affected), `requires` (array of `{slice, provides}` for upstream dependencies consumed), `drillDownPaths` (paths to task summaries)
-
-   **UAT content:** `uatContent` — the UAT markdown body. This must be a concrete UAT script with real test cases derived from the slice plan and task summaries. Include preconditions, numbered steps with expected outcomes, and edge cases. This must NOT be a placeholder or generic template — tailor every test case to what this slice actually built. The tool writes it to `{{sliceUatPath}}`.
-
-7. Review task summaries for `key_decisions`. Append any significant decisions to `.gsd/DECISIONS.md` if missing.
-8. Review task summaries for patterns, gotchas, or non-obvious lessons learned. If any would save future agents from repeating investigation or hitting the same issues, append them to `.gsd/KNOWLEDGE.md`. Only add entries that are genuinely useful — don't pad with obvious observations.
-9. Do not run git commands — the system commits your changes and handles any merge after this unit succeeds.
-10. Update `.gsd/PROJECT.md` if it exists — refresh current state if needed.
-
-**You MUST call `gsd_slice_complete` before finishing.** The tool handles writing `{{sliceSummaryPath}}`, `{{sliceUatPath}}`, and updating `{{roadmapPath}}` atomically. You must still review decisions and knowledge manually (steps 7-8).
+5. If this slice produced evidence that a requirement changed status (Active → Validated, Active → Deferred, etc.), call `gsd_save_decision` with scope="requirement", decision="{requirement-id}", choice="{new-status}", rationale="{evidence}". Do NOT write `.gsd/REQUIREMENTS.md` directly — the engine renders it from the database.
+6. Write `{{sliceSummaryPath}}` (compress all task summaries).
+7. Write `{{sliceUatPath}}` — a concrete UAT script with real test cases derived from the slice plan and task summaries. Include preconditions, numbered steps with expected outcomes, and edge cases. This must NOT be a placeholder or generic template — tailor every test case to what this slice actually built.
+8. Review task summaries for `key_decisions`. Append any significant decisions to `.gsd/DECISIONS.md` if missing.
+9. Review task summaries for patterns, gotchas, or non-obvious lessons learned. If any would save future agents from repeating investigation or hitting the same issues, append them to `.gsd/KNOWLEDGE.md`. Only add entries that are genuinely useful — don't pad with obvious observations.
+10. Call `gsd_complete_slice` with milestone_id, slice_id, the slice summary, and the UAT result. Do NOT manually mark the roadmap checkbox — the tool writes to the DB and renders the ROADMAP.md projection automatically.
+11. Do not run git commands — the system commits your changes and handles any merge after this unit succeeds.
+12. Update `.gsd/PROJECT.md` if it exists — refresh current state if needed.
+
+**You MUST do ALL THREE before finishing: (1) write `{{sliceSummaryPath}}`, (2) write `{{sliceUatPath}}`, (3) call `gsd_complete_slice`. The unit will not be marked complete if any of these are missing.**
 
 When done, say: "Slice {{sliceId}} complete."

package/src/resources/extensions/gsd/prompts/discuss.md

@@ -203,7 +203,7 @@ When writing context.md, preserve the user's exact terminology, emphasis, and sp
 
 4. Write `{{contextPath}}` — use the **Context** output template below. Preserve key risks, unknowns, existing codebase constraints, integration points, and relevant requirements surfaced during discussion.
 5. Call `gsd_plan_milestone` to create the roadmap. Decompose into demoable vertical slices with risk, depends, demo sentences, proof strategy, verification classes, milestone definition of done, requirement coverage, and a boundary map. If the milestone crosses multiple runtime boundaries, include an explicit final integration slice that proves the assembled system works end-to-end in a real environment. Use the **Roadmap** output template below to structure the tool call parameters.
-6. Seed `.gsd/DECISIONS.md` — use the **Decisions** output template below. Append rows for any architectural or pattern decisions made during discussion.
+6. For each architectural or pattern decision made during discussion, call `gsd_decision_save` — the tool auto-assigns IDs and regenerates `.gsd/DECISIONS.md` automatically.
 7. {{commitInstruction}}
 
 After writing the files, say exactly: "Milestone {{milestoneId}} ready." — nothing else. Auto-mode will start automatically.
@@ -217,7 +217,7 @@ Once the user confirms the milestone split:
 1. For each milestone, call `gsd_milestone_generate_id` to get its ID — never invent milestone IDs manually. Then `mkdir -p .gsd/milestones/<ID>/slices`.
 2. Write `.gsd/PROJECT.md` — use the **Project** output template below.
 3. Write `.gsd/REQUIREMENTS.md` — use the **Requirements** output template below. Capture Active, Deferred, Out of Scope, and any already Validated requirements. Later milestones may have provisional ownership where slice plans do not exist yet.
-4. Seed `.gsd/DECISIONS.md` — use the **Decisions** output template below.
+4. For any architectural or pattern decisions made during discussion, call `gsd_decision_save` — the tool auto-assigns IDs and regenerates `.gsd/DECISIONS.md` automatically.
 
 #### Phase 2: Primary milestone
 

package/src/resources/extensions/gsd/prompts/execute-task.md

@@ -63,23 +63,13 @@ Then:
 11. **Blocker discovery:** If execution reveals that the remaining slice plan is fundamentally invalid — not just a bug or minor deviation, but a plan-invalidating finding like a wrong API, missing capability, or architectural mismatch — set `blocker_discovered: true` in the task summary frontmatter and describe the blocker clearly in the summary narrative. Do NOT set `blocker_discovered: true` for ordinary debugging, minor deviations, or issues that can be fixed within the current task or the remaining plan. This flag triggers an automatic replan of the slice.
 12. If you made an architectural, pattern, library, or observability decision during this task that downstream work should know about, append it to `.gsd/DECISIONS.md` (read the template at `~/.gsd/agent/extensions/gsd/templates/decisions.md` if the file doesn't exist yet). Not every task produces decisions — only append when a meaningful choice was made.
 13. If you discover a non-obvious rule, recurring gotcha, or useful pattern during execution, append it to `.gsd/KNOWLEDGE.md`. Only add entries that would save future agents from repeating your investigation. Don't add obvious things.
-14. Call the `gsd_task_complete` tool (alias: `gsd_complete_task`) to record the task completion. This single tool call atomically updates the task status in the DB, renders the summary file to `{{taskSummaryPath}}`, and re-renders the plan file at `{{planPath}}`. Read the summary template at `~/.gsd/agent/extensions/gsd/templates/task-summary.md` to understand the expected structure — but pass the content as tool parameters, not as a file write. The tool parameters are:
-    - `taskId`: "{{taskId}}"
-    - `sliceId`: "{{sliceId}}"
-    - `milestoneId`: "{{milestoneId}}"
-    - `oneLiner`: One-line summary of what was accomplished (becomes the commit message)
-    - `narrative`: Detailed narrative of what happened during the task
-    - `verification`: What was verified and how — commands run, tests passed, behavior confirmed
-    - `deviations`: Deviations from the task plan, or "None."
-    - `knownIssues`: Known issues discovered but not fixed, or "None."
-    - `keyFiles`: Array of key files created or modified
-    - `keyDecisions`: Array of key decisions made during this task
-    - `blockerDiscovered`: Whether a plan-invalidating blocker was discovered (boolean)
-    - `verificationEvidence`: Array of `{ command, exitCode, verdict, durationMs }` objects from the verification gate
-15. Do not run git commands — the system reads your task summary after completion and creates a meaningful commit from it (type inferred from title, message from your one-liner, key files from frontmatter). Write a clear, specific one-liner in the summary — it becomes the commit message.
+14. Read the template at `~/.gsd/agent/extensions/gsd/templates/task-summary.md`
+15. Write `{{taskSummaryPath}}`
+16. Call `gsd_complete_task` with milestone_id, slice_id, task_id, and a summary of what was accomplished. This is your final required step — do NOT manually edit PLAN.md checkboxes. The tool marks the task complete, updates the DB, and renders PLAN.md automatically.
+17. Do not run git commands — the system reads your task summary after completion and creates a meaningful commit from it (type inferred from title, message from your one-liner, key files from frontmatter). Write a clear, specific one-liner in the summary — it becomes the commit message.
 
 All work stays in your working directory: `{{workingDirectory}}`.
 
-**You MUST call `gsd_task_complete` before finishing.** The tool handles writing `{{taskSummaryPath}}` and updating the plan file at `{{planPath}}` — do not write the summary file or modify the plan file manually.
+**You MUST call `gsd_complete_task` AND write `{{taskSummaryPath}}` before finishing.**
 
 When done, say: "Task {{taskId}} complete."