gsd-pi 2.43.0 → 2.44.0-dev.0b97ffd

package/src/resources/extensions/gsd/parsers-legacy.ts

@@ -0,0 +1,271 @@
+// 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.
+
+import { extractSection, parseBullets, extractBoldField, extractAllSections, registerCacheClearCallback } from './files.js';
+import { splitFrontmatter } from '../shared/frontmatter.js';
+import { nativeParseRoadmap, nativeParsePlanFile } from './native-parser-bridge.js';
+import { debugTime, debugCount } from './debug-logger.js';
+import { CACHE_MAX } from './constants.js';
+
+import type {
+  Roadmap, BoundaryMapEntry,
+  SlicePlan, TaskPlanEntry,
+} from './types.js';
+
+// Re-export parseRoadmapSlices so callers can import all legacy parsers from one module
+import { parseRoadmapSlices } from './roadmap-slices.js';
+export { parseRoadmapSlices };
+
+// ─── Parse Cache (local to this module) ───────────────────────────────────
+
+/** Fast composite key: length + first/mid/last 100 chars. The middle sample
+ *  prevents collisions when only a few characters change in the interior of
+ *  a file (e.g., a checkbox [ ] → [x] that doesn't alter length or endpoints). */
+function cacheKey(content: string): string {
+  const len = content.length;
+  const head = content.slice(0, 100);
+  const midStart = Math.max(0, Math.floor(len / 2) - 50);
+  const mid = len > 200 ? content.slice(midStart, midStart + 100) : '';
+  const tail = len > 100 ? content.slice(-100) : '';
+  return `${len}:${head}:${mid}:${tail}`;
+}
+
+const _parseCache = new Map<string, unknown>();
+
+function cachedParse<T>(content: string, tag: string, parseFn: (c: string) => T): T {
+  const key = tag + '|' + cacheKey(content);
+  if (_parseCache.has(key)) return _parseCache.get(key) as T;
+  if (_parseCache.size >= CACHE_MAX) _parseCache.clear();
+  const result = parseFn(content);
+  _parseCache.set(key, result);
+  return result;
+}
+
+/** Clear the legacy parser cache. Called by clearParseCache() in files.ts. */
+export function clearLegacyParseCache(): void {
+  _parseCache.clear();
+}
+
+// Register with files.ts so clearParseCache() also clears our cache
+registerCacheClearCallback(clearLegacyParseCache);
+
+// ─── Roadmap Parser ────────────────────────────────────────────────────────
+
+export function parseRoadmap(content: string): Roadmap {
+  return cachedParse(content, 'roadmap', _parseRoadmapImpl);
+}
+
+function _parseRoadmapImpl(content: string): Roadmap {
+  const stopTimer = debugTime("parse-roadmap");
+  // Try native parser first for better performance
+  const nativeResult = nativeParseRoadmap(content);
+  if (nativeResult) {
+    stopTimer({ native: true, slices: nativeResult.slices.length, boundaryEntries: nativeResult.boundaryMap.length });
+    debugCount("parseRoadmapCalls");
+    return nativeResult;
+  }
+
+  const lines = content.split('\n');
+
+  const h1 = lines.find(l => l.startsWith('# '));
+  const title = h1 ? h1.slice(2).trim() : '';
+  const vision = extractBoldField(content, 'Vision') || '';
+
+  const scSection = extractSection(content, 'Success Criteria', 2) ||
+    (() => {
+      const idx = content.indexOf('**Success Criteria:**');
+      if (idx === -1) return '';
+      const rest = content.slice(idx);
+      const nextSection = rest.indexOf('\n---');
+      const block = rest.slice(0, nextSection === -1 ? undefined : nextSection);
+      const firstNewline = block.indexOf('\n');
+      return firstNewline === -1 ? '' : block.slice(firstNewline + 1);
+    })();
+  const successCriteria = scSection ? parseBullets(scSection) : [];
+
+  // Slices
+  const slices = parseRoadmapSlices(content);
+
+  // Boundary map
+  const boundaryMap: BoundaryMapEntry[] = [];
+  const bmSection = extractSection(content, 'Boundary Map');
+
+  if (bmSection) {
+    const h3Sections = extractAllSections(bmSection, 3);
+    for (const [heading, sectionContent] of h3Sections) {
+      const arrowMatch = heading.match(/^(\S+)\s*→\s*(\S+)/);
+      if (!arrowMatch) continue;
+
+      const fromSlice = arrowMatch[1];
+      const toSlice = arrowMatch[2];
+
+      let produces = '';
+      let consumes = '';
+
+      // Use indexOf-based parsing instead of [\s\S]*? regex to avoid
+      // catastrophic backtracking on content with code fences (#468).
+      const prodIdx = sectionContent.search(/^Produces:\s*$/m);
+      if (prodIdx !== -1) {
+        const afterProd = sectionContent.indexOf('\n', prodIdx);
+        if (afterProd !== -1) {
+          const consIdx = sectionContent.search(/^Consumes/m);
+          const endIdx = consIdx !== -1 && consIdx > afterProd ? consIdx : sectionContent.length;
+          produces = sectionContent.slice(afterProd + 1, endIdx).trim();
+        }
+      }
+
+      const consLineMatch = sectionContent.match(/^Consumes[^:]*:\s*(.+)$/m);
+      if (consLineMatch) {
+        consumes = consLineMatch[1].trim();
+      }
+      if (!consumes) {
+        const consIdx = sectionContent.search(/^Consumes[^:]*:\s*$/m);
+        if (consIdx !== -1) {
+          const afterCons = sectionContent.indexOf('\n', consIdx);
+          if (afterCons !== -1) {
+            consumes = sectionContent.slice(afterCons + 1).trim();
+          }
+        }
+      }
+
+      boundaryMap.push({ fromSlice, toSlice, produces, consumes });
+    }
+  }
+
+  const result = { title, vision, successCriteria, slices, boundaryMap };
+  stopTimer({ native: false, slices: slices.length, boundaryEntries: boundaryMap.length });
+  debugCount("parseRoadmapCalls");
+  return result;
+}
+
+// ─── Slice Plan Parser ─────────────────────────────────────────────────────
+
+export function parsePlan(content: string): SlicePlan {
+  return cachedParse(content, 'plan', _parsePlanImpl);
+}
+
+function _parsePlanImpl(content: string): SlicePlan {
+  const stopTimer = debugTime("parse-plan");
+  const [, body] = splitFrontmatter(content);
+  // Try native parser first for better performance
+  const nativeResult = nativeParsePlanFile(body);
+  if (nativeResult) {
+    stopTimer({ native: true });
+    return {
+      id: nativeResult.id,
+      title: nativeResult.title,
+      goal: nativeResult.goal,
+      demo: nativeResult.demo,
+      mustHaves: nativeResult.mustHaves,
+      tasks: nativeResult.tasks.map(t => ({
+        id: t.id,
+        title: t.title,
+        description: t.description,
+        done: t.done,
+        estimate: t.estimate,
+        ...(t.files.length > 0 ? { files: t.files } : {}),
+        ...(t.verify ? { verify: t.verify } : {}),
+      })),
+      filesLikelyTouched: nativeResult.filesLikelyTouched,
+    };
+  }
+
+  const lines = body.split('\n');
+
+  const h1 = lines.find(l => l.startsWith('# '));
+  let id = '';
+  let title = '';
+  if (h1) {
+    const match = h1.match(/^#\s+(\w+):\s+(.+)/);
+    if (match) {
+      id = match[1];
+      title = match[2].trim();
+    } else {
+      title = h1.slice(2).trim();
+    }
+  }
+
+  const goal = extractBoldField(body, 'Goal') || '';
+  const demo = extractBoldField(body, 'Demo') || '';
+
+  const mhSection = extractSection(body, 'Must-Haves');
+  const mustHaves = mhSection ? parseBullets(mhSection) : [];
+
+  const tasksSection = extractSection(body, 'Tasks');
+  const tasks: TaskPlanEntry[] = [];
+
+  if (tasksSection) {
+    const taskLines = tasksSection.split('\n');
+    let currentTask: TaskPlanEntry | null = null;
+
+    for (const line of taskLines) {
+      const cbMatch = line.match(/^-\s+\[([ xX])\]\s+\*\*([\w.]+):\s+(.+?)\*\*\s*(.*)/);
+      // Heading-style: ### T01 -- Title, ### T01: Title, ### T01 — Title
+      const hdMatch = !cbMatch ? line.match(/^#{2,4}\s+([\w.]+)\s*(?:--|—|:)\s*(.+)/) : null;
+      if (cbMatch || hdMatch) {
+        if (currentTask) tasks.push(currentTask);
+
+        if (cbMatch) {
+          const rest = cbMatch[4] || '';
+          const estMatch = rest.match(/`est:([^`]+)`/);
+          const estimate = estMatch ? estMatch[1] : '';
+
+          currentTask = {
+            id: cbMatch[2],
+            title: cbMatch[3],
+            description: '',
+            done: cbMatch[1].toLowerCase() === 'x',
+            estimate,
+          };
+        } else {
+          const rest = hdMatch![2] || '';
+          const titleEstMatch = rest.match(/^(.+?)\s*`est:([^`]+)`\s*$/);
+          const title = titleEstMatch ? titleEstMatch[1].trim() : rest.trim();
+          const estimate = titleEstMatch ? titleEstMatch[2] : '';
+
+          currentTask = {
+            id: hdMatch![1],
+            title,
+            description: '',
+            done: false,
+            estimate,
+          };
+        }
+      } else if (currentTask && line.match(/^\s*-\s+Files:\s*(.*)/)) {
+        const filesMatch = line.match(/^\s*-\s+Files:\s*(.*)/);
+        if (filesMatch) {
+          currentTask.files = filesMatch[1]
+            .split(',')
+            .map(f => f.replace(/`/g, '').trim())
+            .filter(f => f.length > 0);
+        }
+      } else if (currentTask && line.match(/^\s*-\s+Verify:\s*(.*)/)) {
+        const verifyMatch = line.match(/^\s*-\s+Verify:\s*(.*)/);
+        if (verifyMatch) {
+          currentTask.verify = verifyMatch[1].trim();
+        }
+      } else if (currentTask && line.trim() && !line.startsWith('#')) {
+        const desc = line.trim();
+        if (desc) {
+          currentTask.description = currentTask.description
+            ? currentTask.description + ' ' + desc
+            : desc;
+        }
+      }
+    }
+    if (currentTask) tasks.push(currentTask);
+  }
+
+  const filesSection = extractSection(body, 'Files Likely Touched');
+  const filesLikelyTouched = filesSection ? parseBullets(filesSection) : [];
+
+  const result = { id, title, goal, demo, mustHaves, tasks, filesLikelyTouched };
+  stopTimer({ tasks: tasks.length });
+  debugCount("parsePlanCalls");
+  return result;
+}

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

@@ -90,6 +90,7 @@ export const KNOWN_PREFERENCE_KEYS = new Set<string>([
   "github",
   "service_tier",
   "forensics_dedup",
+  "show_token_cost",
 ]);
 
 /** Canonical list of all dispatch unit types. */
@@ -226,6 +227,8 @@ export interface GSDPreferences {
   service_tier?: "priority" | "flex";
   /** Opt-in: search existing issues and PRs before filing from /gsd forensics. Uses additional AI tokens. */
   forensics_dedup?: boolean;
+  /** Opt-in: show per-prompt and cumulative session token cost in the footer. Default: false. */
+  show_token_cost?: boolean;
 }
 
 export interface LoadedGSDPreferences {

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

@@ -747,5 +747,14 @@ export function validatePreferences(preferences: GSDPreferences): {
     }
   }
 
+  // ─── Show Token Cost ──────────────────────────────────────────────
+  if (preferences.show_token_cost !== undefined) {
+    if (typeof preferences.show_token_cost === "boolean") {
+      validated.show_token_cost = preferences.show_token_cost;
+    } else {
+      errors.push("show_token_cost must be a boolean");
+    }
+  }
+
   return { preferences: validated, errors, warnings };
 }

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

@@ -342,6 +342,7 @@ function mergePreferences(base: GSDPreferences, override: GSDPreferences): GSDPr
       : undefined,
     service_tier: override.service_tier ?? base.service_tier,
     forensics_dedup: override.forensics_dedup ?? base.forensics_dedup,
+    show_token_cost: override.show_token_cost ?? base.show_token_cost,
   };
 }
 

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

@@ -24,14 +24,27 @@ Then:
 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. 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. Mark {{sliceId}} done in `{{roadmapPath}}` (change `[ ]` to `[x]`)
-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) mark {{sliceId}} as `[x]` in `{{roadmapPath}}`. The unit will not be marked complete if any of these files are missing.**
+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).
 
 When done, say: "Slice {{sliceId}} complete."

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

@@ -202,7 +202,7 @@ Once the user is satisfied, in a single pass:
 When writing context.md, preserve the user's exact terminology, emphasis, and specific framing from the discussion. Do not paraphrase user nuance into generic summaries. If the user said "craft feel," write "craft feel" — not "high-quality user experience." If they emphasized a specific constraint or negative requirement, carry that emphasis through verbatim. The context file is downstream agents' only window into this conversation — flattening specifics into generics loses the signal that shaped every decision.
 
 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. Write `{{roadmapPath}}` — use the **Roadmap** output template below. Decompose into demoable vertical slices with checkboxes, 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.
+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.
 7. {{commitInstruction}}
 
@@ -222,7 +222,7 @@ Once the user confirms the milestone split:
 #### Phase 2: Primary milestone
 
 5. Write a full `CONTEXT.md` for the primary milestone (the one discussed in depth).
-6. Write a `ROADMAP.md` for **only the primary milestone** — detail-planning later milestones now is waste because the codebase will change. Include requirement coverage and a milestone definition of done.
+6. Call `gsd_plan_milestone` for **only the primary milestone** — detail-planning later milestones now is waste because the codebase will change. Include requirement coverage and a milestone definition of done.
 
 #### MANDATORY: depends_on Frontmatter in CONTEXT.md
 

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

@@ -63,13 +63,23 @@ 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. Read the template at `~/.gsd/agent/extensions/gsd/templates/task-summary.md`
-15. Write `{{taskSummaryPath}}`
-16. Mark {{taskId}} done in `{{planPath}}` (change `[ ]` to `[x]`)
-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.
+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.
 
 All work stays in your working directory: `{{workingDirectory}}`.
 
-**You MUST mark {{taskId}} as `[x]` in `{{planPath}}` AND write `{{taskSummaryPath}}` before finishing.**
+**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.
 
 When done, say: "Task {{taskId}} complete."

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

@@ -1,3 +1,3 @@
-Complete slice {{sliceId}} ("{{sliceTitle}}") of milestone {{milestoneId}}. Your working directory is `{{workingDirectory}}` — all file operations must use this path. All tasks are done. Your slice summary is the primary record of what was built — downstream agents (reassess-roadmap, future slice researchers) read it to understand what this slice delivered and what to watch out for. Use the **Slice Summary** and **UAT** output templates below. {{skillActivation}} Write `{{sliceId}}-SUMMARY.md` (compress task summaries), write `{{sliceId}}-UAT.md`, and fill the `UAT Type` plus `Not Proven By This UAT` sections explicitly so the artifact states what class of acceptance it covers and what still remains unproven. Review task summaries for `key_decisions` and ensure any significant ones are in `.gsd/DECISIONS.md`. Mark the slice checkbox done in the roadmap, update milestone summary, Do not commit or merge manually — the system handles this after the unit completes.
+Complete slice {{sliceId}} ("{{sliceTitle}}") of milestone {{milestoneId}}. Your working directory is `{{workingDirectory}}` — all file operations must use this path. All tasks are done. Your slice summary is the primary record of what was built — downstream agents (reassess-roadmap, future slice researchers) read it to understand what this slice delivered and what to watch out for. Use the **Slice Summary** and **UAT** output templates below to understand the expected structure. {{skillActivation}} Call `gsd_slice_complete` to record completion — the tool writes `{{sliceId}}-SUMMARY.md`, `{{sliceId}}-UAT.md`, and toggles the roadmap checkbox atomically. Fill the `UAT Type` plus `Not Proven By This UAT` sections explicitly in `uatContent` so the artifact states what class of acceptance it covers and what still remains unproven. Review task summaries for `key_decisions` and ensure any significant ones are in `.gsd/DECISIONS.md`. Do not commit or merge manually — the system handles this after the unit completes.
 
 {{inlinedTemplates}}

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

@@ -1,3 +1,3 @@
-Execute the next task: {{taskId}} ("{{taskTitle}}") in slice {{sliceId}} of milestone {{milestoneId}}. Read the task plan (`{{taskId}}-PLAN.md`), load relevant summaries from prior tasks, and execute each step. Verify must-haves when done. If the task touches UI, browser flows, DOM behavior, or user-visible web state, exercise the real flow in the browser, prefer `browser_batch` for obvious sequences, prefer `browser_assert` for explicit pass/fail verification, use `browser_diff` when an action's effect is ambiguous, and use browser diagnostics when validating async or failure-prone UI. If you made an architectural, pattern, or library decision, append it to `.gsd/DECISIONS.md`. Use the **Task Summary** output template below. Write `{{taskId}}-SUMMARY.md`, mark it done, commit, and advance. {{skillActivation}} If running long and not all steps are finished, stop implementing and prioritize writing a clean partial summary over attempting one more step — a recoverable handoff is more valuable than a half-finished step with no documentation. If verification fails, debug methodically: form a hypothesis and test that specific theory before changing anything, change one variable at a time, read entire functions not just the suspect line, distinguish observable facts from assumptions, and if 3+ fixes fail without progress stop and reassess your mental model — list what you know for certain, what you've ruled out, and form fresh hypotheses. Don't fix symptoms — understand why something fails before changing code.
+Execute the next task: {{taskId}} ("{{taskTitle}}") in slice {{sliceId}} of milestone {{milestoneId}}. Read the task plan (`{{taskId}}-PLAN.md`), load relevant summaries from prior tasks, and execute each step. Verify must-haves when done. If the task touches UI, browser flows, DOM behavior, or user-visible web state, exercise the real flow in the browser, prefer `browser_batch` for obvious sequences, prefer `browser_assert` for explicit pass/fail verification, use `browser_diff` when an action's effect is ambiguous, and use browser diagnostics when validating async or failure-prone UI. If you made an architectural, pattern, or library decision, append it to `.gsd/DECISIONS.md`. Use the **Task Summary** output template below. Call `gsd_task_complete` to record completion (it writes the summary, toggles the checkbox, and persists to DB atomically). {{skillActivation}} If running long and not all steps are finished, stop implementing and prioritize writing a clean partial summary over attempting one more step — a recoverable handoff is more valuable than a half-finished step with no documentation. If verification fails, debug methodically: form a hypothesis and test that specific theory before changing anything, change one variable at a time, read entire functions not just the suspect line, distinguish observable facts from assumptions, and if 3+ fixes fail without progress stop and reassess your mental model — list what you know for certain, what you've ruled out, and form fresh hypotheses. Don't fix symptoms — understand why something fails before changing code.
 
 {{inlinedTemplates}}

package/src/resources/extensions/gsd/prompts/guided-plan-milestone.md

@@ -1,4 +1,4 @@
-Plan milestone {{milestoneId}} ("{{milestoneTitle}}"). Read `.gsd/DECISIONS.md` if it exists — respect existing decisions. Read `.gsd/REQUIREMENTS.md` if it exists and treat Active requirements as the capability contract. If `REQUIREMENTS.md` is missing, continue in legacy compatibility mode but explicitly note missing requirement coverage. Use the **Roadmap** output template below. Create `{{milestoneId}}-ROADMAP.md` in the milestone directory with slices, risk levels, dependencies, demo sentences, verification classes, milestone definition of done, requirement coverage, and a boundary map. Write success criteria as observable truths, not implementation tasks. 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. If planning produces structural decisions, append them to `.gsd/DECISIONS.md`. {{skillActivation}}
+Plan milestone {{milestoneId}} ("{{milestoneTitle}}"). Read `.gsd/DECISIONS.md` if it exists — respect existing decisions. Read `.gsd/REQUIREMENTS.md` if it exists and treat Active requirements as the capability contract. If `REQUIREMENTS.md` is missing, continue in legacy compatibility mode but explicitly note missing requirement coverage. Use the **Roadmap** output template below to shape the milestone planning payload you send to `gsd_plan_milestone`. Call `gsd_plan_milestone` to persist the milestone planning fields and render `{{milestoneId}}-ROADMAP.md` from DB state. Do **not** write `{{milestoneId}}-ROADMAP.md`, `ROADMAP.md`, or other planning artifacts manually. If planning produces structural decisions, append them to `.gsd/DECISIONS.md`. {{skillActivation}}
 
 ## Requirement Rules
 

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

@@ -47,7 +47,7 @@ Then:
 2. {{skillActivation}}
 3. Create the roadmap: decompose into demoable vertical slices — as many as the work genuinely needs, no more. A simple feature might be 1 slice. Don't decompose for decomposition's sake.
 4. Order by risk (high-risk first)
-5. Write `{{outputPath}}` with checkboxes, risk, depends, demo sentences, proof strategy, verification classes, milestone definition of done, **requirement coverage**, and a boundary map. Write success criteria as observable truths, not implementation tasks. 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
+5. Call `gsd_plan_milestone` to persist the milestone planning fields and slice rows in the DB-backed planning path. Do **not** write `{{outputPath}}`, `ROADMAP.md`, or other planning artifacts manually — the planning tool owns roadmap rendering and persistence.
 6. If planning produced structural decisions (e.g. slice ordering rationale, technology choices, scope exclusions), append them to `.gsd/DECISIONS.md` (use the **Decisions** output template from the inlined context above if the file doesn't exist yet)
 
 ## Requirement Mapping Rules
@@ -80,15 +80,13 @@ Apply these when decomposing and ordering slices:
 
 ## Single-Slice Fast Path
 
-If the roadmap has only one slice, also write the slice plan and task plans inline during this unit — don't leave them for a separate planning session.
+If the roadmap has only one slice, also plan the slice and its tasks inline during this unit — don't leave them for a separate planning session.
 
-1. Use the **Slice Plan** and **Task Plan** output templates from the inlined context above
-2. `mkdir -p {{milestonePath}}/slices/S01/tasks`
-3. Write the S01 plan file at `{{milestonePath}}/slices/S01/S01-PLAN.md`
-4. Write individual task plans at `{{milestonePath}}/slices/S01/tasks/T01-PLAN.md`, etc.
-5. For simple slices, keep the plan lean — omit Proof Level, Integration Closure, and Observability sections if they would all be "none". Executable verification commands are sufficient.
+1. After `gsd_plan_milestone` returns, immediately call `gsd_plan_slice` for S01 with the full task breakdown
+2. Use the **Slice Plan** and **Task Plan** output templates from the inlined context above to structure the tool call parameters
+3. For simple slices, keep the plan lean — omit Proof Level, Integration Closure, and Observability sections if they would all be "none". Executable verification commands are sufficient.
 
-This eliminates a separate research-slice + plan-slice cycle when the work is straightforward.
+Do **not** write plan files manually — use the DB-backed tools so state stays consistent.
 
 ## Secret Forecasting
 
@@ -107,6 +105,4 @@ If this milestone requires any external API keys or secrets:
 
 If this milestone does not require any external API keys or secrets, skip this step entirely — do not create an empty manifest.
 
-**You MUST write the file `{{outputPath}}` before finishing.**
-
 When done, say: "Milestone {{milestoneId}} planned."

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

@@ -63,9 +63,8 @@ Then:
    - a matching task plan file with description, steps, must-haves, verification, inputs, and expected output
    - **Inputs and Expected Output must list concrete backtick-wrapped file paths** (e.g. `` `src/types.ts` ``). These are machine-parsed to derive task dependencies — vague prose without paths breaks parallel execution. Every task must have at least one output file path.
    - Observability Impact section **only if the task touches runtime boundaries, async flows, or error paths** — omit it otherwise
-6. Write `{{outputPath}}`
-7. Write individual task plans in `{{slicePath}}/tasks/`: `T01-PLAN.md`, `T02-PLAN.md`, etc.
-8. **Self-audit the plan.** Walk through each check — if any fail, fix the plan files before moving on:
+6. **Persist planning state through DB-backed tools.** Call `gsd_plan_slice` with the full slice planning payload (goal, demo, must-haves, verification, tasks, and metadata). Then call `gsd_plan_task` for each task to persist its planning fields. These tools write to the DB and render `{{outputPath}}` and `{{slicePath}}/tasks/T##-PLAN.md` files automatically. Do **not** rely on direct `PLAN.md` writes as the source of truth; the DB-backed tools are the canonical write path for slice and task planning state.
+7. **Self-audit the plan.** Walk through each check — if any fail, fix the plan files before moving on:
     - **Completion semantics:** If every task were completed exactly as written, the slice goal/demo should actually be true.
     - **Requirement coverage:** Every must-have in the slice maps to at least one task. No must-have is orphaned. If `REQUIREMENTS.md` exists, every Active requirement this slice owns maps to at least one task.
     - **Task completeness:** Every task has steps, must-haves, verification, inputs, and expected output — none are blank or vague. Inputs and Expected Output list backtick-wrapped file paths, not prose descriptions.
@@ -73,11 +72,9 @@ Then:
     - **Key links planned:** For every pair of artifacts that must connect, there is an explicit step that wires them.
     - **Scope sanity:** Target 2–5 steps and 3–8 files per task. 10+ steps or 12+ files — must split. Each task must be completable in a single fresh context window.
     - **Feature completeness:** Every task produces real, user-facing progress — not just internal scaffolding.
-9. If planning produced structural decisions, append them to `.gsd/DECISIONS.md`
-10. {{commitInstruction}}
+8. If planning produced structural decisions, append them to `.gsd/DECISIONS.md`
+9. {{commitInstruction}}
 
 The slice directory and tasks/ subdirectory already exist. Do NOT mkdir. All work stays in your working directory: `{{workingDirectory}}`.
 
-**You MUST write the file `{{outputPath}}` before finishing.**
-
 When done, say: "Slice {{sliceId}} planned."

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

@@ -8,7 +8,7 @@
 
 You are executing **multiple tasks in parallel** for this slice. The task graph below shows which tasks are ready for simultaneous execution based on their input/output dependencies.
 
-**Critical rule:** Use the `subagent` tool in **parallel mode** to dispatch all ready tasks simultaneously. Each subagent gets a full `execute-task` prompt and is responsible for its own implementation, verification, task summary, and checkbox updates. The parent batch agent orchestrates, verifies, and records failures only when a dispatched task failed before it could leave its own summary behind.
+**Critical rule:** Use the `subagent` tool in **parallel mode** to dispatch all ready tasks simultaneously. Each subagent gets a full `execute-task` prompt and is responsible for its own implementation, verification, task summary, and completion tool calls. The parent batch agent orchestrates, verifies, and records failures only when a dispatched task failed before it could leave its own summary behind.
 
 ## Task Dependency Graph
 
@@ -25,14 +25,14 @@ You are executing **multiple tasks in parallel** for this slice. The task graph
 1. **Dispatch all ready tasks** using `subagent` in parallel mode. Each subagent prompt is provided below.
 2. **Wait for all subagents** to complete.
 3. **Verify each dispatched task's outputs** — check that expected files were created/modified, that verification commands pass where applicable, and that each task wrote its own `T##-SUMMARY.md`.
-4. **Do not rewrite successful task summaries or duplicate checkbox edits.** Treat a subagent-written summary as authoritative for that task.
+4. **Do not rewrite successful task summaries or duplicate completion tool calls.** Treat a subagent-written summary as authoritative for that task.
 5. **If a failed task produced no summary, write a recovery summary for that task** with `blocker_discovered: true`, clear failure details, and leave the task unchecked so replan/retry has an authoritative record.
 6. **Preserve successful sibling tasks exactly as they landed.** Do not roll back good work because another parallel task failed.
 7. **Do NOT create a batch commit.** The surrounding unit lifecycle owns commits; this parent batch agent should not invent a second commit layer.
 8. **Report the batch outcome** — which tasks succeeded, which failed, and any output collisions or dependency surprises.
 
 If any subagent fails:
-- Keep successful task summaries and checkbox updates as-is
+- Keep successful task summaries and completion tool calls as-is
 - Write a failure summary only when the failed task did not leave one behind
 - Do not silently discard or overwrite another task's outputs
 - The orchestrator will handle re-dispatch or replanning on the next iteration

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

@@ -50,15 +50,14 @@ If all criteria have at least one remaining owning slice, the coverage check pas
 
 **If the roadmap is still good:**
 
-Write `{{assessmentPath}}` with a brief confirmation that roadmap coverage still holds after {{completedSliceId}}. If requirements exist, explicitly note whether requirement coverage remains sound.
+Write `{{assessmentPath}}` with a brief confirmation that roadmap coverage still holds after {{completedSliceId}}. If requirements exist, explicitly note whether requirement coverage remains sound. If `gsd_reassess_roadmap` is available, use it with `verdict: "roadmap-confirmed"`, an empty `sliceChanges` object, and the assessment text — the tool writes the assessment to the DB and renders ASSESSMENT.md.
 
 **If changes are needed:**
 
-1. Rewrite the remaining (unchecked) slices in `{{roadmapPath}}`. Keep completed slices exactly as they are (`[x]`). Update the boundary map for changed slices. Update the proof strategy if risks changed. Update requirement coverage if ownership or scope changed.
-2. Write `{{assessmentPath}}` explaining what changed and why — keep it brief and concrete.
-3. If `.gsd/REQUIREMENTS.md` exists and requirement ownership or status changed, update it.
-4. {{commitInstruction}}
-
-**You MUST write the file `{{assessmentPath}}` before finishing.**
+1. **Persist changes through `gsd_reassess_roadmap`.** Pass: `milestoneId`, `completedSliceId`, `verdict` (e.g. "roadmap-adjusted"), `assessment` (text explaining the decision), and `sliceChanges` with `modified` (array of sliceId, title, risk, depends, demo), `added` (same shape), `removed` (array of slice ID strings). The tool structurally enforces preservation of completed slices, writes the assessment to the DB, re-renders ROADMAP.md, and renders ASSESSMENT.md. Skip step 2 when this tool succeeds.
+2. **Degraded fallback — direct file writes:** If `gsd_reassess_roadmap` is not available, rewrite the remaining (unchecked) slices in `{{roadmapPath}}` directly. Keep completed slices exactly as they are (`[x]`). Update the boundary map for changed slices. Update the proof strategy if risks changed. Update requirement coverage if ownership or scope changed.
+3. Write `{{assessmentPath}}` explaining what changed and why — keep it brief and concrete.
+4. If `.gsd/REQUIREMENTS.md` exists and requirement ownership or status changed, update it.
+5. {{commitInstruction}}
 
 When done, say: "Roadmap reassessed."

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

@@ -32,19 +32,19 @@ Consider these captures when rewriting the remaining tasks — they represent th
 
 1. Read the blocker task summary carefully. Understand exactly what was discovered and why it blocks the current plan.
 2. Analyze the remaining `[ ]` tasks in the slice plan. Determine which are still valid, which need modification, and which should be replaced.
-3. Write `{{replanPath}}` documenting:
+3. **Persist replan state through `gsd_replan_slice`.** Call it with the following parameters: `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 PLAN.md, and renders REPLAN.md. Skip steps 4–5 when this tool succeeds.
+4. **Degraded fallback — direct file writes:** If `gsd_replan_slice` is not available, fall back to writing files directly. Write `{{replanPath}}` documenting:
    - What blocker was discovered and in which task
    - What changed in the plan and why
    - Which incomplete tasks were modified, added, or removed
    - Any new risks or considerations introduced by the replan
-4. Rewrite `{{planPath}}` with the updated slice plan:
+5. If using the degraded fallback, rewrite `{{planPath}}` with the updated slice plan:
    - Keep all `[x]` tasks exactly as they were (same IDs, same descriptions, same checkmarks)
    - Update the `[ ]` tasks to address the blocker
    - Ensure the slice Goal and Demo sections are still achievable with the new tasks, or update them if the blocker fundamentally changes what the slice can deliver
    - Update the Files Likely Touched section if the replan changes which files are affected
-5. If any incomplete task had a `T0x-PLAN.md`, remove or rewrite it to match the new task description.
-6. Do not commit manually — the system auto-commits your changes after this unit completes.
-
-**You MUST write `{{replanPath}}` and the updated slice plan before finishing.**
+   - If a DB-backed planning tool exists for this phase, use it as the source of truth and make any rewritten `PLAN.md` reflect that persisted state rather than bypassing it
+6. If any incomplete task had a `T0x-PLAN.md`, remove or rewrite it to match the new task description.
+7. Do not commit manually — the system auto-commits your changes after this unit completes.
 
 When done, say: "Slice {{sliceId}} replanned."