@opengsd/gsd-pi 1.2.0-dev.fb12b103 → 1.2.0-dev.fbdca60b

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

@@ -38,4 +38,4 @@ Consider these captures when rewriting the remaining tasks — they represent th
 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/src/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/src/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/src/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/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}}
@@ -27,8 +29,8 @@ 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.
@@ -41,7 +43,9 @@ The **Tool Surface** block prepended above lists unavailable tools for this unit
   - 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.

package/src/resources/extensions/gsd/prompts/triage-captures.md

@@ -65,4 +65,4 @@ Classify each capture as one of:
 
 **Important:** Do NOT execute any resolutions. Only classify and update CAPTURES.md. Resolution execution happens separately (in auto-mode dispatch or manually by the user).
 
-When done, say: "Triage complete."
+When done, say: "Triage complete." Say this exactly once — if you already said it in a prior message, do not repeat it.

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

@@ -87,4 +87,4 @@ If verdict is `needs-remediation`:
 
 **File system safety:** When scanning milestone directories, use `ls` or `find` first. Never pass a directory path such as `tasks/` or `slices/` directly to `read`; it only accepts files.
 
-When done, say: "Milestone {{milestoneId}} validation complete — verdict: <verdict>."
+When done, say: "Milestone {{milestoneId}} validation complete — verdict: <verdict>." Say this exactly once — if you already said it in a prior message, do not repeat it.

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/reactive-graph.ts

@@ -12,7 +12,11 @@
 import type { TaskIO, DerivedTaskNode, ReactiveExecutionState } from "./types.js";
 import { loadFile, parseTaskPlanIO } from "./files.js";
 import { isDbAvailable, getSliceTasks } from "./gsd-db.js";
+// Explicit degraded-mode fallback ONLY (ADR-017): parsePlan is consulted when
+// the DB is unavailable or has no task rows for the slice; the DB path in
+// loadSliceTaskIO always wins when rows exist, and the fallback logs a warning.
 import { parsePlan } from "./parsers-legacy.js";
+import { logWarning } from "./workflow-logger.js";
 import { resolveTasksDir, resolveTaskFiles } from "./paths.js";
 import { join } from "node:path";
 import { loadJsonFileOrNull, saveJsonFile } from "./json-persistence.js";
@@ -224,7 +228,13 @@ export async function loadSliceTaskIO(
   } catch { /* fall through */ }
 
   if (!taskEntries) {
-    // File-based fallback: parse slice plan for task entries
+    // Degraded-mode fallback (ADR-017): no DB task rows for this slice —
+    // parse the PLAN.md projection instead. Warn so silent drift from the
+    // DB-authoritative path is visible in logs.
+    logWarning(
+      "projection",
+      `reactive-graph: DB unavailable or no task rows for ${mid}/${sid}; falling back to PLAN.md parsing`,
+    );
     const parsed = parsePlan(planContent);
     if (parsed.tasks.length > 0) {
       taskEntries = parsed.tasks.map(t => ({

package/src/resources/extensions/gsd/roadmap-slices.ts

@@ -154,6 +154,29 @@ function parseTableSlices(section: string): RoadmapSliceEntry[] {
   return slices;
 }
 
+function looksLikeTable(section: string): boolean {
+  const lines = section.split("\n");
+
+  // Checkbox format takes precedence — embedded demo tables must not switch mode (#721).
+  if (lines.some(line => /^\s*-\s+\[[ xX]\]/.test(line))) {
+    return false;
+  }
+
+  const pipeLines = lines.filter(line => /^\s*\|/.test(line));
+  if (pipeLines.length < 2) return false;
+
+  const hasSeparatorRow = pipeLines.some((line, index) => {
+    if (index === 0) return false;
+    const cells = line.split("|").map(c => c.trim()).filter(Boolean);
+    return /^\s*\|[\s:-]+\|/.test(line) && cells.length >= 2 && cells.every(c => /^[\s:-]+$/.test(c));
+  });
+
+  if (hasSeparatorRow) return true;
+
+  // Tables without a separator row still expose slice IDs in data rows.
+  return pipeLines.some(line => /\bS\d+\b/.test(line));
+}
+
 export function parseRoadmapSlices(content: string): RoadmapSliceEntry[] {
   const slicesSection = extractSlicesSection(content);
   if (!slicesSection) {
@@ -165,9 +188,11 @@ export function parseRoadmapSlices(content: string): RoadmapSliceEntry[] {
 
   // Try table format first — if the section contains pipe-delimited rows with
   // slice IDs, parse them as a table (#1736).
-  const tableSlices = parseTableSlices(slicesSection);
-  if (tableSlices.length > 0) {
-    return tableSlices;
+  if (looksLikeTable(slicesSection)) {
+    const tableSlices = parseTableSlices(slicesSection);
+    if (tableSlices.length > 0) {
+      return tableSlices;
+    }
   }
 
   // Standard checkbox format

package/src/resources/extensions/gsd/session-lock.ts

@@ -387,7 +387,7 @@ export function acquireSessionLock(basePath: string): SessionLockResult {
     // #3218: Provide actionable workaround when lock recovery fails
     const lockDirPath = lockTarget + ".lock";
     const reason = existingPid
-      ? `Another auto-mode session (PID ${existingPid}) appears to be running.\nStop it with \`kill ${existingPid}\` before starting a new session.`
+      ? `Another auto-mode session (PID ${existingPid}) appears to be running.\nRun \`/gsd stop\` for graceful shutdown, or choose "Force start" from \`/gsd auto\` to terminate it.`
       : `Another auto-mode session lock is stuck on this project.\nRun: rm -rf "${lockDirPath}" && rm -f "${lp}"`;
 
     return { acquired: false, reason, existingPid };

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

@@ -13,6 +13,11 @@ import type {
   MilestoneRegistryEntry,
 } from './types.js';
 
+// Pre-migration fallback ONLY (ADR-017): deriveState must work on projects
+// whose DB does not exist yet (before md-importer runs), so it parses markdown
+// projections when `isDbAvailable()` is false or the DB has no rows. Once the
+// DB is populated, decision reads go through gsd-db queries — these parsers
+// must never be consulted when DB data is present.
 import {
   parseRoadmap,
   parsePlan,
@@ -55,6 +60,7 @@ import {
   getAllMilestones,
   getMilestone,
   getMilestoneSlices,
+  getSlicesByMilestoneIds,
   getSliceTasks,
   getReplanHistory,
   getSlice,
@@ -472,13 +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 }> = [];