@opengsd/gsd-pi 1.2.0-dev.9ad8ae33 → 1.2.0-dev.a6376d75

package/src/resources/extensions/gsd/health-widget.ts

@@ -4,7 +4,7 @@
 import type { ExtensionContext } from "@gsd/pi-coding-agent";
 import type { GSDState } from "./types.js";
 import { runProviderChecks, summariseProviderIssues } from "./doctor-providers.js";
-import { runEnvironmentChecks } from "./doctor-environment.js";
+import { runEnvironmentChecks, runEnvironmentChecksAsync } from "./doctor-environment.js";
 import { loadEffectiveGSDPreferences } from "./preferences.js";
 import { nativeIsRepo, nativeLastCommitEpoch, nativeGetCurrentBranch, nativeCommitSubject } from "./native-git-bridge.js";
 import { loadLedgerFromDisk, getProjectTotals } from "./metrics.js";
@@ -22,7 +22,31 @@ export const HEALTH_WIDGET_ACTIVE_HINTS =
 
 // ── Data loader ────────────────────────────────────────────────────────────────
 
-function loadHealthWidgetData(basePath: string): HealthWidgetData {
+// Last-commit lookup is subprocess-backed (native-git-bridge → git spawns),
+// so it is treated like the other expensive checks: skipped on first paint,
+// run only by the background refresh.
+function loadLastCommitInfo(basePath: string): { epoch: number | null; message: string | null } {
+  try {
+    if (nativeIsRepo(basePath)) {
+      const branch = nativeGetCurrentBranch(basePath);
+      const epoch = nativeLastCommitEpoch(basePath, branch || "HEAD");
+      if (epoch > 0) {
+        return { epoch, message: nativeCommitSubject(basePath, branch || "HEAD") || null };
+      }
+    }
+  } catch { /* non-fatal */ }
+  return { epoch: null, message: null };
+}
+
+function loadHealthWidgetData(
+  basePath: string,
+  options?: { includeChecks?: boolean },
+): HealthWidgetData {
+  // `includeChecks` gates the expensive subprocess-backed checks (provider +
+  // environment doctor: `lsof`, `docker`, `node --version`, ...). The initial
+  // synchronous render passes `false` so first paint is never blocked on them;
+  // the async refresh (off the first-paint path) runs the full suite.
+  const includeChecks = options?.includeChecks ?? true;
   let budgetCeiling: number | undefined;
   let budgetSpent = 0;
   let providerIssue: string | null = null;
@@ -44,40 +68,73 @@ function loadHealthWidgetData(basePath: string): HealthWidgetData {
     }
   } catch { /* non-fatal */ }
 
+  if (includeChecks) {
+    try {
+      const providerResults = runProviderChecks();
+      providerIssue = summariseProviderIssues(providerResults);
+    } catch { /* non-fatal */ }
+
+    try {
+      const envResults = runEnvironmentChecks(basePath);
+      for (const r of envResults) {
+        if (r.status === "error") environmentErrorCount++;
+        else if (r.status === "warning") environmentWarningCount++;
+      }
+    } catch { /* non-fatal */ }
+  }
+
+  // ── Last commit info ── (git spawns — gated like the other expensive checks)
+  if (includeChecks) {
+    const commit = loadLastCommitInfo(basePath);
+    lastCommitEpoch = commit.epoch;
+    lastCommitMessage = commit.message;
+  }
+
+  return {
+    projectState,
+    budgetCeiling,
+    budgetSpent,
+    providerIssue,
+    environmentErrorCount,
+    environmentWarningCount,
+    lastCommitEpoch,
+    lastCommitMessage,
+    lastRefreshed: Date.now(),
+  };
+}
+
+// Non-blocking variant used by the widget's background refresh: the cheap fields
+// come from the synchronous snapshot, then provider + environment checks are
+// layered in off the event-loop critical path (env checks run concurrently via
+// runEnvironmentChecksAsync). Keeps the always-on widget from stalling the UI on
+// its initial enrichment or its 60s refresh.
+async function loadHealthWidgetDataAsync(basePath: string): Promise<HealthWidgetData> {
+  const data = loadHealthWidgetData(basePath, { includeChecks: false });
+  let providerIssue = data.providerIssue;
+  let environmentErrorCount = 0;
+  let environmentWarningCount = 0;
+
   try {
-    const providerResults = runProviderChecks();
-    providerIssue = summariseProviderIssues(providerResults);
+    providerIssue = summariseProviderIssues(runProviderChecks());
   } catch { /* non-fatal */ }
 
   try {
-    const envResults = runEnvironmentChecks(basePath);
+    const envResults = await runEnvironmentChecksAsync(basePath);
     for (const r of envResults) {
       if (r.status === "error") environmentErrorCount++;
       else if (r.status === "warning") environmentWarningCount++;
     }
   } catch { /* non-fatal */ }
 
-  // ── Last commit info ──
-  try {
-    if (nativeIsRepo(basePath)) {
-      const branch = nativeGetCurrentBranch(basePath);
-      const epoch = nativeLastCommitEpoch(basePath, branch || "HEAD");
-      if (epoch > 0) {
-        lastCommitEpoch = epoch;
-        lastCommitMessage = nativeCommitSubject(basePath, branch || "HEAD") || null;
-      }
-    }
-  } catch { /* non-fatal */ }
+  const commit = loadLastCommitInfo(basePath);
 
   return {
-    projectState,
-    budgetCeiling,
-    budgetSpent,
+    ...data,
     providerIssue,
     environmentErrorCount,
     environmentWarningCount,
-    lastCommitEpoch,
-    lastCommitMessage,
+    lastCommitEpoch: commit.epoch,
+    lastCommitMessage: commit.message,
     lastRefreshed: Date.now(),
   };
 }
@@ -95,8 +152,13 @@ export function initHealthWidget(ctx: ExtensionContext): void {
 
   const basePath = projectRoot();
 
-  // String-array fallback — used in RPC mode (factory is a no-op there)
-  const initialData = loadHealthWidgetData(basePath);
+  // String-array fallback — used in RPC mode (factory is a no-op there).
+  // Skip the expensive provider/environment doctor checks here: this runs
+  // synchronously on the interactive-startup path, where running them would
+  // block first paint by ~0.9s (lsof/docker probes, otherwise run again
+  // immediately by the factory below). The factory's async refresh fills in
+  // real health once the screen is up.
+  const initialData = loadHealthWidgetData(basePath, { includeChecks: false });
   ctx.ui.setWidget("gsd-health", buildHealthLines(initialData), { placement: "belowEditor" });
 
   // Factory-based widget for TUI mode — replaces the string-array above
@@ -110,7 +172,7 @@ export function initHealthWidget(ctx: ExtensionContext): void {
       if (refreshInFlight) return;
       refreshInFlight = true;
       try {
-        data = loadHealthWidgetData(basePath);
+        data = await loadHealthWidgetDataAsync(basePath);
         cachedLines = undefined;
         if (!isDisposed) _tui.requestRender();
       } catch { /* non-fatal */ } finally {
@@ -118,9 +180,11 @@ export function initHealthWidget(ctx: ExtensionContext): void {
       }
     };
 
-    // Fire first enrichment immediately. requestRender() inside is a no-op
-    // if the widget has not yet rendered, so this is safe before factory return.
-    void refresh();
+    // Fire the first full enrichment off the first-paint path. setTimeout(0)
+    // yields to the initial render + input loop, so the expensive doctor checks
+    // (provider + environment) never delay the moment the user sees the UI.
+    // requestRender() inside refresh repaints the widget once data is ready.
+    setTimeout(() => { void refresh(); }, 0);
 
     const refreshTimer = setInterval(() => {
       void refresh();

package/src/resources/extensions/gsd/mcp-bridge.ts

@@ -0,0 +1,39 @@
+// mcp-bridge.ts — stable runtime seam for MCP server consumption (phase 1).
+export {
+  loadWriteGateSnapshot,
+  shouldBlockPendingGateInSnapshot,
+  shouldBlockQueueExecutionInSnapshot,
+} from "./bootstrap/write-gate.js";
+export { ensureDbOpen } from "./bootstrap/dynamic-tools.js";
+export {
+  _getAdapter,
+  checkpointDatabase,
+  closeDatabase,
+  getAllMilestones,
+  getDb,
+  getGateResults,
+  getMilestoneSlices,
+  getPendingGates,
+  getSliceTasks,
+  insertDecision,
+  insertMilestone,
+  insertSlice,
+  openDatabase,
+  upsertMilestonePlanning,
+} from "./gsd-db.js";
+export { invalidateStateCache, isReusableGhostMilestone } from "./state.js";
+export { loadEffectiveGSDPreferences } from "./preferences.js";
+export {
+  saveDecisionToDb,
+  saveRequirementToDb,
+  updateRequirementInDb,
+} from "./db-writer.js";
+export { rebuildState } from "./doctor.js";
+export { queryJournal } from "./journal.js";
+export {
+  claimReservedId,
+  findMilestoneIds,
+  getReservedMilestoneIds,
+  milestoneIdSort,
+  nextMilestoneId,
+} from "./milestone-ids.js";

package/src/resources/extensions/gsd/milestone-settlement.ts

@@ -74,8 +74,8 @@ export function evaluateAllCompleteSettlement(
     action: "pause",
     message:
       `Milestone ${milestoneId} is complete, but its worktree branch has not been merged to main. ` +
-      `Retry with \`/gsd dispatch complete-milestone ${milestoneId}\` or merge manually.`,
-    nextAction: `Retry \`/gsd dispatch complete-milestone ${milestoneId}\` or merge manually.`,
+      `Retry with \`/gsd dispatch complete-milestone ${milestoneId}\` to finish the system-owned merge.`,
+    nextAction: `Retry \`/gsd dispatch complete-milestone ${milestoneId}\`.`,
     milestoneId,
   };
 }

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

@@ -4,7 +4,12 @@
 import { execFileSync } from "node:child_process";
 import type { NotificationPreferences } from "./types.js";
 import { loadEffectiveGSDPreferences } from "./preferences.js";
-import { sendRemoteNotification } from "../remote-questions/notify.js";
+import { sendRemoteNotification as _sendRemoteNotification } from "../remote-questions/notify.js";
+
+/** Swappable dispatcher for remote notifications — exported so tests can mock it. */
+export const remoteNotificationDispatcher = {
+  send: _sendRemoteNotification,
+};
 
 export type NotifyLevel = "info" | "success" | "warning" | "error";
 export type NotificationKind = "complete" | "error" | "budget" | "milestone" | "attention";
@@ -30,28 +35,30 @@ export function sendDesktopNotification(
   level: NotifyLevel = "info",
   kind: NotificationKind = "complete",
   projectName?: string,
+  deps: { notifications?: NotificationPreferences } = {},
 ): void {
   // When a projectName is provided and the title is the default "GSD",
   // replace it with a project-qualified title for multi-project clarity.
   if (projectName && title === "GSD") {
     title = formatNotificationTitle(projectName);
   }
-  const loaded = loadEffectiveGSDPreferences()?.preferences;
+  const loadedPreferences = loadEffectiveGSDPreferences()?.preferences;
+  const notifications = deps.notifications ?? loadedPreferences?.notifications;
 
   // Remote notifications fire independently of desktop preferences.
   // sendRemoteNotification handles "not configured" gracefully (early return).
-  void sendRemoteNotification(title, message).catch(() => {});
+  void remoteNotificationDispatcher.send(title, message).catch(() => {});
 
-  if (!shouldSendDesktopNotification(kind, loaded?.notifications)) return;
+  if (!shouldSendDesktopNotification(kind, notifications)) return;
 
   // cmux delivery and desktop delivery are independent — if cmux import or
   // delivery fails, we must still attempt the native desktop notification.
   const runCmux = async () => {
     try {
       const { CmuxClient, emitOsc777Notification, resolveCmuxConfig } = await import("../cmux/index.js");
-      const cmux = resolveCmuxConfig(loaded);
+      const cmux = resolveCmuxConfig(loadedPreferences);
       if (cmux.notifications) {
-        const delivered = CmuxClient.fromPreferences(loaded).notify(title, message);
+        const delivered = CmuxClient.fromPreferences(loadedPreferences).notify(title, message);
         if (delivered) return true;
         emitOsc777Notification(title, message);
       }

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

@@ -38,7 +38,7 @@ Use `subagent` only when useful: reviewer, security, or tester. Apply findings b
 10. Prepare `gsd_slice_complete` content with camelCase fields `milestoneId`, `sliceId`, `sliceTitle`, `oneLiner`, `narrative`, `verification`, and `uatContent`.
 11. Draft concrete UAT with preconditions, steps, expected outcomes, edge cases, and UAT Type. Declare the type as a bullet under a `## UAT Type` heading, exactly like `- UAT mode: browser-executable`.
     **Web apps:** when inlined Web App UAT guidance is present, declare `browser-executable` or `runtime-executable` (not `artifact-driven`) for localhost/browser/screenshot steps; include dev-server preconditions and name Playwright specs when they exist.
-12. Review the inlined task-summary excerpts for DECISIONS.md/KNOWLEDGE.md-worthy decisions and gotchas. Read full `*-SUMMARY.md` only if needed. Capture with `capture_thought`; do not append knowledge files.
+12. Review the inlined task-summary excerpts for DECISIONS.md/KNOWLEDGE.md-worthy decisions and gotchas. Read full `*-SUMMARY.md` only if needed. Capture with `gsd_capture_thought` (MCP-scoped `mcp__...__gsd_capture_thought`), not bare `capture_thought`; do not append knowledge files.
 13. When verification passes, call `gsd_slice_complete`. The DB-backed tool is the canonical write path. Do **not** manually write `{{sliceSummaryPath}}`. Do **not** manually write `{{sliceUatPath}}`. Do not edit roadmap checkboxes.
 14. Do not run git commands.
 15. If the current project state needs refresh, call `gsd_summary_save` with `artifact_type: "PROJECT"` and the full updated project markdown as `content`; omit `milestone_id`. Do not write or edit `.gsd/PROJECT.md` directly.

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

@@ -52,6 +52,7 @@ You execute. The inlined task plan is authoritative. Verify referenced files and
 
 - If task sections exist for Failure Modes (Q5), Load Profile (Q6), Negative Tests (Q7), or Observability Impact, implement and verify them.
 - Verify must-haves with concrete commands or observable behavior.
+- Run verification commands through `gsd_exec` / Context Mode evidence when workflow MCP tools are presented. Use `gsd_exec_search` before rerunning noisy checks, and `gsd_resume` after compaction or resume. Do not call direct `bash` for final verification evidence in this unit.
 - Run slice-level verification from the slice plan. Final tasks need all checks passing; intermediate tasks should record partial passes.
 - Populate `## Verification Evidence` with `formatEvidenceTable` rows: command, exit code, verdict, duration. If no checks were found, say so.
 - For UI/browser/DOM/user-visible web changes, exercise the real flow and record explicit checks.
@@ -64,7 +65,7 @@ Keep about **{{verificationBudget}}** for verification and summary. If context i
 
 - If the plan is fundamentally invalid, set `blocker_discovered: true` in the summary and explain.
 - For downstream-impacting ambiguity that cannot be resolved from code, plans, or decisions, include an `escalation` object with question, options, recommendation, rationale, and `continueWithDefault`.
-- Capture meaningful architecture/pattern/observability decisions with `capture_thought`; capture non-obvious gotchas or conventions only when they save future investigation.
+- Capture meaningful architecture/pattern/observability decisions with `gsd_capture_thought` (or MCP-scoped `mcp__...__gsd_capture_thought`) when workflow MCP tools are presented; capture non-obvious gotchas or conventions only when they save future investigation.
 - Use the inlined Task Summary template below. Read `{{taskSummaryTemplatePath}}` only if the inlined template is absent or visibly truncated.
 - Call `gsd_task_complete` with camelCase fields `milestoneId`, `sliceId`, `taskId`, `oneLiner`, `narrative`, `verification`, and `verificationEvidence`. Include `blockerDiscovered: true` when a stale-path safety failure or other plan-invalidating blocker prevents execution.
 - The DB-backed tool is the canonical write path. Do **not** manually write `{{taskSummaryPath}}` or edit PLAN.md checkboxes; the tool renders the summary and updates state.

package/src/resources/extensions/gsd/prompts/run-uat.md

@@ -10,6 +10,8 @@ If any inlined plan, summary, verification command, or prior artifact names an a
 
 All relevant context has been preloaded below. Start working immediately without re-reading these files.
 
+If a `.gsd/**` or `.gsd/**/*` glob returns no matches, treat that as a possible symlink-backed traversal limitation; do not infer that the GSD harness is missing. Use the preloaded UAT context and direct `.gsd/...` file paths named in this prompt instead.
+
 {{inlinedContext}}
 
 {{skillActivation}}

package/src/resources/extensions/gsd/prompts/workflow-start.md

@@ -25,4 +25,5 @@ Follow the workflow defined below. Execute each phase in order, completing one b
 3. **Atomic commits.** Commit working code after each meaningful change. Use conventional commit format: `<type>(<scope>): <description>`.
 4. **Verify before shipping.** Run the project's test suite and build before marking the workflow complete.
 5. **Decision gates, not ceremony.** After each phase, summarize what changed. For low/medium complexity, ask for confirmation only when the next phase depends on a real user choice or external approval. For high complexity, confirm before proceeding to each new phase.
-6. **Stay focused.** This is a {{complexity}}-complexity workflow. Match your ceremony level to the task — don't over-engineer or under-deliver.
+6. **Persist workflow state.** If the artifact directory contains `STATE.json`, update it after each phase: mark the finished phase `completed`, mark the next phase `active`, set `currentPhase` to the active phase index, and refresh `updatedAt`. When every phase is completed, set `completedAt` to the completion timestamp.
+7. **Stay focused.** This is a {{complexity}}-complexity workflow. Match your ceremony level to the task — don't over-engineer or under-deliver.

package/src/resources/extensions/gsd/skill-activation.ts

@@ -134,11 +134,8 @@ const SAFE_SKILL_NAME = /^[a-z0-9][a-z0-9-]*$/;
 function formatSkillActivationBlock(skillNames: string[]): string {
   const safe = skillNames.filter(name => SAFE_SKILL_NAME.test(name));
   if (safe.length === 0) return "";
-  // Use explicit parameter syntax so LLMs pass { skill: "..." } instead of { name: "..." }.
-  // The function-call-like syntax `Skill('name')` led LLMs to infer a positional
-  // parameter name, causing tool validation failures — see #2224.
-  const calls = safe.map(name => `Call Skill({ skill: '${name}' })`).join('. ');
-  return `<skill_activation>${calls}.</skill_activation>`;
+  const reads = safe.map(name => `Read the installed '${name}' skill file from <available_skills>`).join(". ");
+  return `<skill_activation>${reads}.</skill_activation>`;
 }
 
 /**
@@ -157,7 +154,7 @@ function formatSkillRecommendationsBlock(unitType: string | undefined, skillName
   if (!unitType) return "";
   const safe = skillNames.filter(name => SAFE_SKILL_NAME.test(name));
   if (safe.length === 0) return "";
-  return `<skill_recommendations unit="${unitType}">For this unit type, also consider invoking: ${safe.join(", ")}. Use Skill({ skill: 'name' }) when relevant — these are recommendations, not requirements.</skill_recommendations>`;
+  return `<skill_recommendations unit="${unitType}">For this unit type, also consider reading these installed skill files from <available_skills>: ${safe.join(", ")}. These are recommendations, not requirements.</skill_recommendations>`;
 }
 
 export function buildSkillActivationBlock(params: {

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

@@ -60,6 +60,7 @@ import {
   getAllMilestones,
   getMilestone,
   getMilestoneSlices,
+  getSlicesByMilestoneIds,
   getSliceTasks,
   getReplanHistory,
   getSlice,
@@ -477,13 +478,18 @@ async function buildRegistryAndFindActive(
   let activeMilestoneHasDraft = false;
   let firstDeferredQueuedShell: { id: string; title: string; deps: string[]; hasDraftContext: boolean } | null = null;
 
+  const activeMilestoneIds = milestones
+    .filter((m) => !parkedMilestoneIds.has(m.id))
+    .map((m) => m.id);
+  const slicesByMilestone = getSlicesByMilestoneIds(activeMilestoneIds);
+
   for (const m of milestones) {
     if (parkedMilestoneIds.has(m.id)) {
       registry.push({ id: m.id, title: stripMilestonePrefix(m.title) || m.id, status: 'parked' });
       continue;
     }
 
-    const slices = getMilestoneSlices(m.id);
+    const slices = slicesByMilestone.get(m.id) ?? [];
 
     // DB-authoritative completeness (#4179): only trust completeMilestoneIds,
     // which is itself derived from DB status. SUMMARY-file presence alone must

package/src/resources/extensions/gsd/tests/auto-abort-pause-regression.test.ts

@@ -2,7 +2,7 @@ import test from "node:test";
 import assert from "node:assert/strict";
 
 import { _buildAbortedPauseContext, isUserInitiatedAbortMessage } from "../bootstrap/agent-end-recovery.js";
-import { _buildCancelledUnitStopReason, _isPauseOriginCancelledResult } from "../auto/phases.js";
+import { _buildCancelledUnitStopReason, _isPauseOriginCancelledResult } from "../auto/phase-helpers.js";
 
 test("aborted agent_end maps errorMessage into structured aborted pause context", () => {
   const withMessage = _buildAbortedPauseContext({ errorMessage: "provider aborted request" });

package/src/resources/extensions/gsd/tests/auto-blocked-remediation-message.test.ts

@@ -1,7 +1,7 @@
 import test from "node:test";
 import assert from "node:assert/strict";
 
-import { runPreDispatch } from "../auto/phases.ts";
+import { runPreDispatch } from "../auto/pre-dispatch.ts";
 
 test("blocked remediation warning uses /gsd dispatch reassess and hides internal tool name", async () => {
   const notifications: Array<{ message: string; level?: string }> = [];