@opengsd/gsd-pi 1.2.0-dev.955e4da0 → 1.2.0-dev.a6376d75

package/dist/resources/extensions/gsd/milestone-settlement.js

@@ -43,8 +43,8 @@ export function evaluateAllCompleteSettlement(input) {
         reason: "merge-pending",
         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/dist/resources/extensions/gsd/notification-store.js

@@ -34,13 +34,16 @@ export function initNotificationStore(basePath) {
  * Append a notification entry to the store. Synchronous — safe to call
  * from the notify() shim which is declared void (not async).
  */
-export function appendNotification(message, severity, source = "notify") {
+export function appendNotification(message, severity, source = "notify", meta) {
     if (!_basePath)
         return;
     if (_suppressCount > 0)
         return;
     const persistedMessage = message.length > 500 ? message.slice(0, 500) + "…" : message;
-    const dedupKey = `${_basePath}:${severity}:${source}:${persistedMessage}`;
+    // Structured identity (kind + scope) keys dedup when present, so a rephrased
+    // message of the same event still dedups; otherwise fall back to the prose.
+    const identity = meta?.kind ? `${meta.kind}:${meta.scope ?? ""}` : persistedMessage;
+    const dedupKey = `${_basePath}:${severity}:${source}:${identity}`;
     const now = Date.now();
     const lastSeen = _recentMessageTimestamps.get(dedupKey);
     if (lastSeen !== undefined && now - lastSeen < DEDUP_WINDOW_MS)
@@ -59,6 +62,8 @@ export function appendNotification(message, severity, source = "notify") {
         message: persistedMessage,
         source,
         read: false,
+        ...(meta?.kind ? { kind: meta.kind } : {}),
+        ...(meta?.scope ? { scope: meta.scope } : {}),
     };
     try {
         const dir = join(_basePath, ".gsd");
@@ -77,12 +82,14 @@ export function appendNotification(message, severity, source = "notify") {
 }
 /**
  * Read all notification entries from disk. Returns newest-first.
+ * An optional filter narrows by structured identity (kind and/or scope).
  */
-export function readNotifications(basePath) {
+export function readNotifications(basePath, filter) {
     const bp = basePath ?? _basePath;
     if (!bp)
         return [];
-    return _readEntriesFromDisk(bp).reverse();
+    const entries = _readEntriesFromDisk(bp).filter((e) => (!filter?.kind || e.kind === filter.kind) && (!filter?.scope || e.scope === filter.scope));
+    return entries.reverse();
 }
 /**
  * Mark all notifications as read. Atomic rewrite via temp-file + rename.

package/dist/resources/extensions/gsd/notifications.js

@@ -2,31 +2,36 @@
 // Cross-platform desktop notifications for auto-mode events.
 import { execFileSync } from "node:child_process";
 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,
+};
 /**
  * Send a native desktop notification. Non-blocking, non-fatal.
  * macOS: osascript, Linux: notify-send, Windows: skipped.
  */
-export function sendDesktopNotification(title, message, level = "info", kind = "complete", projectName) {
+export function sendDesktopNotification(title, message, level = "info", kind = "complete", projectName, deps = {}) {
     // 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(() => { });
-    if (!shouldSendDesktopNotification(kind, loaded?.notifications))
+    void remoteNotificationDispatcher.send(title, message).catch(() => { });
+    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/dist/resources/extensions/gsd/parallel-monitor-overlay.js

@@ -70,8 +70,7 @@ function discoverWorkers(basePath) {
     }
     return [...mids].sort();
 }
-function querySliceProgress(basePath, mid) {
-    const workRoot = worktreePathFor(basePath, mid);
+function querySliceProgress(basePath, mid, workRoot = worktreePathFor(basePath, mid)) {
     const dbPath = resolveGsdPathContract(workRoot, basePath).projectDb;
     if (!existsSync(dbPath))
         return [];
@@ -141,9 +140,12 @@ function collectWorkerData(basePath) {
     const parallelDir = join(basePath, ".gsd", "parallel");
     const workers = [];
     for (const mid of mids) {
+        // Resolve the worktree path once per worker per tick — this runs on a
+        // 5-second refresh interval and worktreePathFor probes the filesystem.
+        const workRoot = worktreePathFor(basePath, mid);
         const status = readJsonSafe(join(parallelDir, `${mid}.status.json`));
-        const lock = readJsonSafe(join(worktreePathFor(basePath, mid), ".gsd", "auto.lock"));
-        const slices = querySliceProgress(basePath, mid);
+        const lock = readJsonSafe(join(workRoot, ".gsd", "auto.lock"));
+        const slices = querySliceProgress(basePath, mid, workRoot);
         const pid = lock?.pid || status?.pid || 0;
         const alive = pid ? isPidAlive(pid) : false;
         // Heartbeat: prefer status.json if PID matches, else use file mtime

package/dist/resources/extensions/gsd/parsers-legacy.js

@@ -1,10 +1,22 @@
 // GSD Extension - Legacy Parsers
 // parseRoadmap() and parsePlan() extracted from files.ts.
-// Used only by: md-importer.ts (migration), state.ts (pre-migration fallback),
-// markdown-renderer.ts (detectStaleRenders disk-vs-DB comparison),
-// commands-maintenance.ts (cold-path branch cleanup), and tests.
 //
-// NOT used in the dispatch loop or any hot-path runtime code.
+// ADR-017: the DB is the single source of truth; `.gsd/*.md` files are
+// projections. These parsers may be imported ONLY for:
+//   - migration/import (md-importer, workflow-migration, migration-auto-check)
+//   - drift detection that compares both sources by design
+//     (state-reconciliation/drift, markdown-renderer stale-render detection)
+//   - explicit pre-migration / DB-unavailable fallbacks (state.ts,
+//     reactive-graph.ts, auto-recovery.ts)
+//   - diagnostics and display/telemetry-only surfaces (doctor,
+//     doctor-git-checks, workspace-index, visualizer-data, auto-prompts
+//     context text, commands-maintenance, milestone-closeout, github-sync)
+//   - tests
+//
+// Dispatch/gate/completion DECISION paths must NOT import this module — they
+// read the DB via gsd-db queries (e.g. getMilestoneSliceSummaries). Enforced
+// by tests/parsers-legacy-importers.test.ts; new importers must be added to
+// its allowlist with a one-line justification.
 import { extractSection, parseBullets, extractBoldField, extractAllSections, registerCacheClearCallback } from './files.js';
 import { splitFrontmatter } from '../shared/frontmatter.js';
 import { nativeParseRoadmap, nativeParsePlanFile } from './native-parser-bridge.js';

package/dist/resources/extensions/gsd/paths.js

@@ -139,6 +139,33 @@ export function clearPathCache() {
     nativeTreeBase = null;
 }
 // ─── Name Builders ─────────────────────────────────────────────────────────
+/** Directories owned by the GSD framework — metadata, never project source. */
+export const FRAMEWORK_METADATA_DIRS = [".gsd", ".planning", ".audits"];
+/**
+ * Every artifact suffix used with the name builders below — the single source
+ * for the `<ID>-<SUFFIX>.md` naming vocabulary. Extend this list when a new
+ * artifact type is introduced; consumers (md-importer walking, pre-execution
+ * artifact detection) pick it up from here.
+ */
+export const PLANNING_ARTIFACT_SUFFIXES = [
+    "CONTEXT",
+    "CONTEXT-DRAFT",
+    "ROADMAP",
+    "PLAN",
+    "REPLAN",
+    "SUMMARY",
+    "RESEARCH",
+    "VALIDATION",
+    "ASSESSMENT",
+    "UAT",
+    "DISCUSSION",
+    "EVAL-REVIEW",
+    "PARKED",
+    "VERIFICATION-FAILED",
+    "CONTINUE",
+];
+/** Matches a bare planning-artifact file name, e.g. "M001-CONTEXT.md", "S01-PLAN.md". */
+export const PLANNING_ARTIFACT_NAME_RE = new RegExp(`^[MST]\\d+-(${PLANNING_ARTIFACT_SUFFIXES.join("|")})\\.md$`, "i");
 /**
  * Build a milestone-level file name.
  * ("M001", "CONTEXT") → "M001-CONTEXT.md"

package/dist/resources/extensions/gsd/pre-execution-checks.js

@@ -20,6 +20,7 @@ import { spawn } from "node:child_process";
 import { homedir } from "node:os";
 import { isAbsolute, relative, resolve } from "node:path";
 import { validateVerificationCommand } from "./verification-gate.js";
+import { FRAMEWORK_METADATA_DIRS, PLANNING_ARTIFACT_NAME_RE } from "./paths.js";
 const NPM_COMMAND = process.platform === "win32" ? "npm.cmd" : "npm";
 function inputExistsOnDisk(normalizedFile, basePath, context) {
     if (existsSync(resolve(basePath, normalizedFile)))
@@ -510,6 +511,10 @@ export function checkFilePathConsistency(tasks, basePath, context) {
                 continue;
             if (!shouldValidateInputAsPath(file))
                 continue;
+            // Planning-artifact references are owned by checkPlanningArtifactReferences,
+            // which reports a precise removal message instead of "doesn't exist".
+            if (isPlanningArtifactReference(file, basePath, context))
+                continue;
             // Normalize path for consistent comparison
             const normalizedFile = toComparisonPath(file, basePath);
             if (containsGlobPattern(normalizedFile))
@@ -546,6 +551,71 @@ export function checkFilePathConsistency(tasks, basePath, context) {
     }
     return results;
 }
+// ─── Planning Artifact Reference Check ───────────────────────────────────────
+function isFrameworkMetadataPath(normalizedFile) {
+    return normalizedFile.split("/").some((segment) => FRAMEWORK_METADATA_DIRS.includes(segment.toLowerCase()));
+}
+/**
+ * True when a task IO entry references a GSD planning artifact.
+ *
+ * Task inputs are source files only — planning artifacts are projections of DB
+ * state that the framework preloads as composed context (see CONTEXT.md "Task
+ * Input"). Two triggers, deliberately different in strictness:
+ *
+ * - Any path entering framework-owned metadata (.gsd/, .planning/, .audits/)
+ *   is always a violation, even when the file exists.
+ * - A bare artifact-style basename (M001-CONTEXT.md, S01-PLAN.md, …) is a
+ *   violation only when it does NOT resolve to a real file. When such a file
+ *   genuinely exists in the source tree (e.g. a fixture), it is a source file
+ *   and stays legal; a path with directory components is likewise left to the
+ *   ordinary existence checks.
+ */
+function isPlanningArtifactReference(rawEntry, basePath, context) {
+    if (!shouldValidateInputAsPath(rawEntry))
+        return false;
+    const normalized = toComparisonPath(rawEntry, basePath);
+    if (isFrameworkMetadataPath(normalized))
+        return true;
+    return (!normalized.includes("/") &&
+        PLANNING_ARTIFACT_NAME_RE.test(normalized) &&
+        !inputExistsOnDisk(normalized, basePath, context));
+}
+/**
+ * Block GSD planning artifacts in task IO fields (inputs, files, expectedOutput).
+ *
+ * For inputs/files the violation smuggles a projection into the executor's
+ * preloaded source context; for expectedOutput it promises a write the runtime
+ * write-gate would reject mid-execution. Both get a precise message so the
+ * planning retry steers toward *removing* the reference, not creating the file.
+ * checkFilePathConsistency and checkTaskOrdering skip entries this check owns.
+ */
+export function checkPlanningArtifactReferences(tasks, basePath, context) {
+    const results = [];
+    for (const task of tasks) {
+        const fields = [
+            { label: "inputs", entries: task.inputs },
+            { label: "files", entries: task.files },
+            { label: "expectedOutput", entries: task.expected_output },
+        ];
+        for (const { label, entries } of fields) {
+            for (const file of entries) {
+                if (!isPlanningArtifactReference(file, basePath, context))
+                    continue;
+                const message = label === "expectedOutput"
+                    ? `Task ${task.id} lists '${file}' in expectedOutput — GSD planning artifacts are written by workflow tools (e.g. gsd_summary_save), never by tasks; remove it`
+                    : `Task ${task.id} lists '${file}' in ${label} — GSD planning artifacts are projections preloaded as context, never task ${label}; remove it`;
+                results.push({
+                    category: "file",
+                    target: file,
+                    passed: false,
+                    message,
+                    blocking: true,
+                });
+            }
+        }
+    }
+    return results;
+}
 // ─── Task Ordering Check ─────────────────────────────────────────────────────
 /**
  * Detect impossible task ordering: task N reads a file that task N+M creates.
@@ -583,6 +653,10 @@ export function checkTaskOrdering(tasks, basePath, context) {
                 continue;
             if (!shouldValidateInputAsPath(file))
                 continue;
+            // Owned by checkPlanningArtifactReferences — avoid a duplicate sequence
+            // finding on top of the removal message.
+            if (isPlanningArtifactReference(file, basePath, context))
+                continue;
             const normalizedFile = toComparisonPath(file, basePath);
             if (containsGlobPattern(normalizedFile))
                 continue;
@@ -611,6 +685,21 @@ export function checkTaskOrdering(tasks, basePath, context) {
     }
     return results;
 }
+// ─── Shared Path-Check Composition ───────────────────────────────────────────
+/**
+ * The synchronous path-shaped checks, in order. One list shared by the
+ * plan-persist gate (gsd_plan_slice) and the dispatch gate
+ * (runPreExecutionChecks) so the two cannot drift — the checks coordinate
+ * ownership of planning-artifact entries via isPlanningArtifactReference
+ * skips, which only works when they run as a set.
+ */
+export function runTaskPathChecks(tasks, basePath, context) {
+    return [
+        ...checkPlanningArtifactReferences(tasks, basePath, context),
+        ...checkFilePathConsistency(tasks, basePath, context),
+        ...checkTaskOrdering(tasks, basePath, context),
+    ];
+}
 /**
  * Extract function signatures from code blocks in task description.
  * Uses heuristic regex — not an AST parser.
@@ -741,11 +830,10 @@ export async function runPreExecutionChecks(tasks, basePath, context) {
     const startTime = Date.now();
     const allChecks = [];
     // Run sync checks first
-    const fileChecks = checkFilePathConsistency(tasks, basePath, context);
-    const orderingChecks = checkTaskOrdering(tasks, basePath, context);
+    const pathChecks = runTaskPathChecks(tasks, basePath, context);
     const contractChecks = checkInterfaceContracts(tasks, basePath);
     const verificationChecks = checkVerificationCommands(tasks);
-    allChecks.push(...fileChecks, ...orderingChecks, ...contractChecks, ...verificationChecks);
+    allChecks.push(...pathChecks, ...contractChecks, ...verificationChecks);
     // Run async package checks
     const packageChecks = await checkPackageExistence(tasks, basePath);
     allChecks.push(...packageChecks);

package/dist/resources/extensions/gsd/preferences-models.js

@@ -11,6 +11,7 @@ import { join } from "node:path";
 import { gsdHome } from "./gsd-home.js";
 import { canonicalModelForTier, defaultRoutingConfig, resolveModelForTier } from "./model-router.js";
 import { loadEffectiveGSDPreferences, getGlobalGSDPreferencesPath } from "./preferences.js";
+import { getUnitPhaseChain } from "./unit-registry.js";
 /**
  * Resolve which model ID to use for a given auto-mode unit type.
  * Returns undefined if no model preference is set for this unit type.
@@ -29,53 +30,18 @@ export function resolveModelForUnit(unitType) {
  * (`resolveThinkingLevelForUnit`) so the two never drift (ADR-026).
  */
 export function phaseChainForUnit(unitType) {
-    switch (unitType) {
-        case "research-milestone":
-        case "research-slice":
-        // Deep-mode project research orchestrator. Reads PROJECT.md / REQUIREMENTS.md
-        // and fans out research subagents. Routes to the research bucket.
-        case "research-project":
-            return ["research"];
-        case "plan-milestone":
-        case "plan-slice":
-        case "refine-slice":
-        case "replan-slice":
-            return ["planning"];
-        // Deep-mode project-level discussion units route to the same model bucket
-        // as milestone-level discussion (interactive interview style). Workflow
-        // preferences and research-decision are tiny ask_user_questions style units
-        // that share the discuss bucket because they are conversational. All fall
-        // back to planning when no `discuss` bucket is set.
-        case "discuss-milestone":
-        case "discuss-slice":
-        case "discuss-project":
-        case "discuss-requirements":
-        case "workflow-preferences":
-        case "research-decision":
-            return ["discuss", "planning"];
-        case "execute-task":
-        case "reactive-execute":
-            return ["execution"];
-        case "execute-task-simple":
-            return ["execution_simple", "execution"];
-        case "complete-slice":
-        case "complete-milestone":
-        case "worktree-merge":
-            return ["completion"];
-        case "run-uat":
-            return ["uat", "completion"];
-        case "reassess-roadmap":
-        case "rewrite-docs":
-        case "gate-evaluate":
-        case "validate-milestone":
-            return ["validation", "planning"];
-        default:
-            // Subagent unit types (e.g., "subagent", "subagent/scout")
-            if (unitType === "subagent" || unitType.startsWith("subagent/")) {
-                return ["subagent"];
-            }
-            return undefined;
+    // Unit types declare their chain on their Unit Descriptor (ADR-033).
+    const declared = getUnitPhaseChain(unitType);
+    if (declared)
+        return [...declared];
+    // Dispatch types without a Unit Descriptor.
+    if (unitType === "worktree-merge")
+        return ["completion"];
+    // Subagent unit types (e.g., "subagent", "subagent/scout")
+    if (unitType === "subagent" || unitType.startsWith("subagent/")) {
+        return ["subagent"];
     }
+    return undefined;
 }
 /**
  * Find the phase bucket whose `models` entry wins the chain for a unit, plus
@@ -196,8 +162,8 @@ export function resolveThinkingLevelForUnit(unitType) {
  * Returns `{ provider, id }` or `undefined` if no model preference is
  * configured.
  */
-export function resolveDefaultSessionModel(sessionProvider) {
-    const prefs = loadEffectiveGSDPreferences(undefined, { availableModelIds: [] });
+export function resolveDefaultSessionModel(sessionProvider, basePath) {
+    const prefs = loadEffectiveGSDPreferences(basePath, { availableModelIds: [] });
     const models = prefs?.preferences?.models;
     if (!models)
         return undefined;

package/dist/resources/extensions/gsd/projection-flush.js

@@ -0,0 +1,7 @@
+// Project/App: gsd-pi
+// File Purpose: Single workflow projection flush seam for mutation exits.
+import { renderAllProjections } from "./workflow-projections.js";
+export async function flushWorkflowProjections(basePath, scope) {
+    await renderAllProjections(basePath, scope.milestoneId);
+    return { milestoneId: scope.milestoneId };
+}

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

@@ -24,7 +24,7 @@ Use `subagent` only when useful: reviewer, security, or tester. Apply findings b
 
 1. Use the inlined Slice Summary and UAT templates.
 2. {{skillActivation}}
-3. Run all slice-level verification through `gsd_exec` / Context Mode evidence; refresh current state if needed. Do not use direct `bash` for verification commands.
+3. Run all slice-level verification through `gsd_exec` / Context Mode evidence; refresh current state if needed. Do not use direct `bash` for verification commands. See the prepended **Tool Surface** block for unavailable tools.
 4. Complete only when every required check passes. If verification fails or source changes are needed, do **not** edit source files in this unit and do **not** call `gsd_slice_complete`.
 5. If verification fails:
    - Task-specific regressions: if the failure is in files the task touched and pre-task verification evidence shows it was absent before that task ran, call `gsd_task_reopen` with that task and reason.
@@ -36,9 +36,9 @@ Use `subagent` only when useful: reviewer, security, or tester. Apply findings b
 8. Address every Gate to Close. Q8 = **Operational Readiness**: health signal, failure signal, recovery, monitoring gaps. Omit empty sections.
 9. If requirement status changed, call `gsd_requirement_update`; do not write `.gsd/REQUIREMENTS.md` directly.
 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.
+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.
@@ -49,4 +49,4 @@ Use `subagent` only when useful: reviewer, security, or tester. Apply findings b
 
 **You MUST call `gsd_slice_complete` with summary and UAT content only after verification passes.**
 
-When done, say: "Slice {{sliceId}} complete."
+When done, say: "Slice {{sliceId}} complete." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/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.
@@ -76,4 +77,4 @@ Keep about **{{verificationBudget}}** for verification and summary. If context i
 
 **You MUST call `gsd_task_complete` before finishing, including when the stale-path safety rule stops execution.**
 
-When done, say: "Task {{taskId}} complete."
+When done, say: "Task {{taskId}} complete." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/plan-milestone.md

@@ -118,4 +118,4 @@ If external API keys or secrets are required, use the inlined **Secrets Manifest
 
 If no external API keys or secrets are required, skip this step; do not create an empty manifest.
 
-When done, say: "Milestone {{milestoneId}} planned."
+When done, say: "Milestone {{milestoneId}} planned." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/plan-slice.md

@@ -45,7 +45,7 @@ If slice research is inlined, trust its architectural findings, but verify every
 6. Include Threat Surface (Q3), Requirement Impact (Q4), proof level, observability, integration closure, Failure Modes (Q5), Load Profile (Q6), and Negative Tests (Q7) only where applicable.
 7. Right-size tasks. Simple slices can be one task; split only when context, ownership, or verification boundaries justify it.
 8. Task `verify` commands must be safe, simple commands. Do not use shell pipes, redirects, semicolons, backticks, command substitution, output trimming, or grep regex alternation with `|`. If multiple checks are needed, create a small test file and run it with `node --test` or a package test script, or use separate simple commands joined only with `&&`. For absence checks, verify a pattern does not exist with `! grep -q 'pattern' file` or `! rg -q 'pattern' file`; do not use `grep -c` or `rg -c` to assert zero matches because count commands exit 1 when they find zero matches, and the verification gate treats that as failure.
-9. Each task needs the exact `gsd_plan_slice.tasks[]` shape: `taskId`, `title`, `description`, `estimate`, `files`, `verify`, `inputs`, `expectedOutput`, and optional `observabilityImpact`. `description` should contain the Why / Do / Done-when narrative. `files`, `inputs`, and `expectedOutput` must be JSON arrays of strings, even when there is only one path (for example, `"inputs": ["src/index.ts"]`, never `"inputs": "src/index.ts"`). Use paths relative to `{{workingDirectory}}`; do not put absolute paths to the original checkout or any directory outside `{{workingDirectory}}` in `files`, `inputs`, `expectedOutput`, or verification commands. **`expectedOutput` must only list files the task actually creates or overwrites on disk.** Do NOT include files the task merely reads, verifies, tests, or describes — those belong in `inputs`, `verify`, `description`, or slice success criteria. If a task is a pure verification or test task that produces no new files, `expectedOutput` must be `[]`; if it writes a test-result log or assertion output file, list only that concrete file path. A file that does not yet exist on disk and is needed as an `input` must be produced by an earlier task's `expectedOutput` — if no prior task creates it, add a task before this one that does.
+9. Each task needs the exact `gsd_plan_slice.tasks[]` shape: `taskId`, `title`, `description`, `estimate`, `files`, `verify`, `inputs`, `expectedOutput`, and optional `observabilityImpact`. `description` should contain the Why / Do / Done-when narrative. `files`, `inputs`, and `expectedOutput` must be JSON arrays of strings, even when there is only one path (for example, `"inputs": ["src/index.ts"]`, never `"inputs": "src/index.ts"`). Use paths relative to `{{workingDirectory}}`; do not put absolute paths to the original checkout or any directory outside `{{workingDirectory}}` in `files`, `inputs`, `expectedOutput`, or verification commands. **`expectedOutput` must only list files the task actually creates or overwrites on disk.** Do NOT include files the task merely reads, verifies, tests, or describes — those belong in `inputs`, `verify`, `description`, or slice success criteria. If a task is a pure verification or test task that produces no new files, `expectedOutput` must be `[]`; if it writes a test-result log or assertion output file, list only that concrete file path. A file that does not yet exist on disk and is needed as an `input` must be produced by an earlier task's `expectedOutput` — if no prior task creates it, add a task before this one that does. Never list GSD planning artifacts — anything under `.gsd/`, `.planning/`, or `.audits/`, or artifact names like `M001-CONTEXT.md` / `S01-PLAN.md` — in `inputs`, `files`, or `expectedOutput`: their content is preloaded as context, and they are written by workflow tools, not by tasks.
 10. Persist with `gsd_plan_slice` using `milestoneId`, `sliceId`, `goal`, optional `successCriteria`/`proofLevel`/`integrationClosure`/`observabilityImpact`, and `tasks`. `gsd_plan_slice` handles task persistence transactionally and renders `{{outputPath}}` plus task plans; do not call `gsd_plan_task`. The DB-backed tool is the canonical write path. Do **not** rely on direct `PLAN.md` writes as the source of truth.
 11. Self-audit before finishing: goal/demo closure, requirement coverage, deliverable coverage audit (cross-check every file listed in CONTEXT.md `## Scope` / `### In Scope` against task `files` or `expectedOutput`), locked decisions, concrete paths, dependency order, wiring, scope size, proof truthfulness, feature completeness, and quality gates. Quality gates: non-trivial slices/tasks include specific Q3-Q7 coverage where applicable.
 12. If planning creates structural decisions, call `gsd_decision_save` for each; the tool persists the decision and regenerates `.gsd/DECISIONS.md`.
@@ -57,4 +57,4 @@ The slice directory already exists. Do not mkdir.
 
 **You MUST call `gsd_plan_slice` to persist planning state before finishing, unless the stale-path safety rule above stops the unit before safe planning can occur.**
 
-When done, say: "Slice {{sliceId}} planned."
+When done, say: "Slice {{sliceId}} planned." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/quick-task.md

@@ -37,4 +37,4 @@ You are executing a GSD quick task — a lightweight, focused unit of work outsi
 - <what was tested/verified>
 ```
 
-When done, say: "Quick task {{taskNum}} complete."
+When done, say: "Quick task {{taskNum}} complete." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/reassess-roadmap.md

@@ -67,4 +67,4 @@ If `.gsd/REQUIREMENTS.md` exists and requirement ownership or status changed, up
 
 **DB access safety:** Do NOT query `.gsd/gsd.db` directly via `sqlite3` or `node -e require('better-sqlite3')`. Use `gsd_milestone_status` to read current milestone and slice state. All roadmap mutations go through `gsd_reassess_roadmap` — the tool writes to the DB and re-renders ROADMAP.md atomically.
 
-When done, say: "Roadmap reassessed."
+When done, say: "Roadmap reassessed." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/refine-slice.md

@@ -65,7 +65,7 @@ Then:
 3. Define slice-level verification: the objective stopping condition. Plan real test files with real assertions; for simple slices, executable commands are fine.
    **Web apps:** when inlined Web App UAT guidance is present, follow it for Playwright scaffolding and browser-capable verification commands.
 4. For non-trivial slices, plan observability / proof level / integration closure, threat surface, and requirement impact. Omit entirely for simple slices.
-5. Decompose the slice into tasks that fit one context window each. Every task passed to `gsd_plan_slice` must use the exact keys `taskId`, `title`, `description`, `estimate`, `files`, `verify`, `inputs`, `expectedOutput`, and optional `observabilityImpact`. Put Why / Do / Done-when detail in `description`. `files`, `inputs`, and `expectedOutput` must be JSON arrays of strings, even for one path (for example, `"expectedOutput": ["src/index.ts"]`, never `"expectedOutput": "src/index.ts"`). `expectedOutput` is path-only: list only files the task creates or overwrites, and use `[]` for pure verification tasks.
+5. Decompose the slice into tasks that fit one context window each. Every task passed to `gsd_plan_slice` must use the exact keys `taskId`, `title`, `description`, `estimate`, `files`, `verify`, `inputs`, `expectedOutput`, and optional `observabilityImpact`. Put Why / Do / Done-when detail in `description`. `files`, `inputs`, and `expectedOutput` must be JSON arrays of strings, even for one path (for example, `"expectedOutput": ["src/index.ts"]`, never `"expectedOutput": "src/index.ts"`). `expectedOutput` is path-only: list only files the task creates or overwrites, and use `[]` for pure verification tasks. Never list GSD planning artifacts — anything under `.gsd/`, `.planning/`, or `.audits/`, or artifact names like `M001-CONTEXT.md` / `S01-PLAN.md` — in `inputs`, `files`, or `expectedOutput`: their content is preloaded as context, and they are written by workflow tools, not by tasks.
 6. **Persist planning state through `gsd_plan_slice`.** Call it with the full payload. The tool writes to the DB and renders `{{outputPath}}` and `{{slicePath}}/tasks/T##-PLAN.md` automatically. Do NOT rely on direct `PLAN.md` writes.
 7. **Self-audit the plan.** If every task were completed exactly as written, the slice goal/demo should be true. Every must-have maps to a task. Inputs and Expected Output are backtick-wrapped file paths.
 8. If refinement produced structural decisions that diverge from the sketch, call `gsd_decision_save` for each; the tool persists the decision and regenerates `.gsd/DECISIONS.md`.
@@ -77,4 +77,4 @@ The slice directory and tasks/ subdirectory already exist. Do NOT mkdir.
 
 **You MUST call `gsd_plan_slice` to persist planning state before finishing.** After success, the pipeline clears the sketch flag on next state derivation; the on-disk PLAN file is the signal.
 
-When done, say: "Slice {{sliceId}} refined."
+When done, say: "Slice {{sliceId}} refined." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/replan-slice.md

@@ -34,8 +34,8 @@ Consider these captures when rewriting the remaining tasks — they represent th
 
 1. Use the inlined blocker summary excerpt first. Read the full blocker task summary only if the excerpt is absent, marked truncated, or lacks the specific blocker evidence needed to replan.
 2. Analyze the remaining `[ ]` tasks in the slice plan. Determine which are still valid, which need modification, and which should be replaced.
-3. **Persist replan state through `gsd_replan_slice`.** Call it with: `milestoneId`, `sliceId`, `blockerTaskId`, `blockerDescription`, `whatChanged`, `updatedTasks` (array of task objects with taskId, title, description, estimate, files, verify, inputs, expectedOutput), `removedTaskIds` (array of task ID strings). The tool structurally enforces preservation of completed tasks, writes replan history to the DB, re-renders `{{planPath}}`, and renders `{{replanPath}}`. Preserve or update the Threat Surface and Requirement Impact sections if the replan changes the slice's security posture or requirement coverage.
+3. **Persist replan state through `gsd_replan_slice`.** Call it with: `milestoneId`, `sliceId`, `blockerTaskId`, `blockerDescription`, `whatChanged`, `updatedTasks` (array of task objects with taskId, title, description, estimate, files, verify, inputs, expectedOutput), `removedTaskIds` (array of task ID strings). Never list GSD planning artifacts — anything under `.gsd/`, `.planning/`, or `.audits/`, or artifact names like `M001-CONTEXT.md` / `S01-PLAN.md` — in `inputs`, `files`, or `expectedOutput`: their content is preloaded as context, and they are written by workflow tools, not by tasks. The tool structurally enforces preservation of completed tasks, writes replan history to the DB, re-renders `{{planPath}}`, and renders `{{replanPath}}`. Preserve or update the Threat Surface and Requirement Impact sections if the replan changes the slice's security posture or requirement coverage.
 4. If any incomplete task had a `T0x-PLAN.md`, remove or rewrite it to match the new task description.
 5. Do not commit manually — the system auto-commits your changes after this unit completes.
 
-When done, say: "Slice {{sliceId}} replanned."
+When done, say: "Slice {{sliceId}} replanned." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/research-milestone.md

@@ -46,4 +46,4 @@ Then research the codebase and relevant technologies. Narrate key findings and s
 
 **You MUST call `gsd_summary_save` with the research content before finishing.**
 
-When done, say: "Milestone {{milestoneId}} researched."
+When done, say: "Milestone {{milestoneId}} researched." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/research-slice.md

@@ -55,4 +55,4 @@ The slice directory already exists at `{{slicePath}}/`. Do NOT mkdir.
 
 **You MUST call `gsd_summary_save` with the research content before finishing.**
 
-When done, say: "Slice {{sliceId}} researched."
+When done, say: "Slice {{sliceId}} researched." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/resources/extensions/gsd/prompts/rewrite-docs.md

@@ -30,4 +30,4 @@ An override was issued by the user that changes a fundamental decision or approa
 
 **You MUST update the relevant documents AND mark overrides as resolved in `{{overridesPath}}` before finishing.**
 
-When done, say: "Override applied across all documents."
+When done, say: "Override applied across all documents." Say this exactly once — if you already said it in a prior message, do not repeat it.

package/dist/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}}
@@ -27,21 +29,23 @@ You are the UAT runner. Execute every check defined in `{{uatPath}}` as deeply a
 ### Automation rules by mode
 
 - `artifact-driven` — verify with shell commands, scripts, file reads, and artifact structure checks.
-- `browser-executable` — use browser tools to navigate to the target URL and verify expected behavior. Prefer direct `browser_*` tools when available. Capture screenshots as evidence. Record pass/fail with specific assertions.
-- `runtime-executable` — execute the specified command or script. Capture stdout/stderr as evidence. Record pass/fail based on exit code and output.
+- `browser-executable` — use browser tools to navigate to the target URL and verify expected behavior. Prefer direct `browser_*` tools when available. Capture screenshots as evidence. Record pass/fail with specific assertions. When the UAT **Evidence** section names a self-contained runtime harness (for example `npm run test:uat` or `node tests/browser/search-uat.mjs`), treat the effective mode as **runtime-executable** instead: run that command only and do not start a separate server or `browser_navigate` to a hardcoded localhost port.
+- `runtime-executable` — execute the specified command or script. Capture stdout/stderr as evidence. Record pass/fail based on exit code and output. When the verification script starts its own dev/static server (for example `node tests/browser/search-uat.mjs`), do **not** start a separate server with `uat-service-start` — the script owns server lifecycle and binds an ephemeral port. If a server is already running, pass its URL via `UAT_BASE_URL` or `PORT` in the `gsd_uat_exec` environment instead of hardcoding a fixed port like 4173.
 - `live-runtime` — exercise the real runtime path. Start or connect to the app/service if needed, use browser/runtime/network checks, and verify observable behavior.
 - `mixed` — run all automatable artifact-driven and live-runtime checks. Separate any remaining human-only checks explicitly.
 - `human-experience` — automate setup, preconditions, screenshots, logs, and objective checks, but do **not** invent subjective PASS results. Mark taste-based, experiential, or purely human-judgment checks as `NEEDS-HUMAN`. Use an overall verdict of `PASS` when all automatable checks succeed (even if human-only checks remain as `NEEDS-HUMAN`). Use `PARTIAL` only when automatable checks themselves were inconclusive.
 
 ### Evidence tools
 
-Choose the lightest tool that proves the check honestly:
+The **Tool Surface** block prepended above lists unavailable tools for this unit. In short:
 
 - Run automated checks with `gsd_uat_exec`
   - Use `uat-artifact-check` as `intent` for static file, grep, structure, or artifact checks.
   - Use `uat-runtime-check` as `intent` for executing tests, scripts, or runtime assertions.
   - Use `uat-browser-check` as `intent` for browser interaction or screenshot-backed UI checks.
-  - Use `uat-service-start` as `intent` only when starting or connecting to an app/service.
+  - Use `uat-service-start` as `intent` only when starting or connecting to an app/service that the UAT checks will not start themselves.
+  - Do not start a dev/static server separately when a runtime test script owns server lifecycle — run the script directly instead.
+  - When you do start a service, capture the URL from its stdout (for example `Ready at http://127.0.0.1:PORT`) and pass it to downstream checks via `UAT_BASE_URL` rather than assuming a fixed port.
   - Use `uat-log-inspection` as `intent` for checking logs or captured output files.
   - The result-table evidence mode is separate; do not use `artifact`, `runtime`, or `human-follow-up` as `intent`.
 - Run `grep` / `rg` checks against files
@@ -98,4 +102,4 @@ checks: [{
 
 **You MUST call `gsd_uat_result_save` before finishing. Do not write the assessment file directly, and do not call `gsd_summary_save` as a substitute.**
 
-When done, say: "UAT {{sliceId}} complete."
+When done, say: "UAT {{sliceId}} complete." Say this exactly once — if you already said it in a prior message, do not repeat it.