gsd-pi 2.80.0-dev.c5f2443b3 → 2.80.0-dev.d4fc28e6b

package/dist/resources/extensions/gsd/prompt-loader.js

@@ -111,15 +111,41 @@ function warmCache() {
     }
 }
 let warmCacheScheduled = false;
+let warmCacheRan = false;
+let warmCacheTimer;
+/**
+ * Synchronously snapshot the prompt/template tree into the cache.
+ *
+ * Safe to call immediately after `initResources()` because that function uses
+ * synchronous fs APIs — there is no race window that requires deferring the
+ * cache warm via setTimeout. Idempotent: subsequent calls are no-ops.
+ *
+ * Cancels the fallback `scheduleWarmCache` timer if it is still pending.
+ */
+export function primeCache() {
+    if (warmCacheRan)
+        return;
+    if (warmCacheTimer) {
+        clearTimeout(warmCacheTimer);
+        warmCacheTimer = undefined;
+    }
+    warmCacheScheduled = true;
+    warmCacheRan = true;
+    warmCache();
+}
 function scheduleWarmCache() {
     if (warmCacheScheduled)
         return;
     warmCacheScheduled = true;
     const run = () => {
+        warmCacheTimer = undefined;
+        if (warmCacheRan)
+            return;
+        warmCacheRan = true;
         warmCache();
     };
-    const timer = setTimeout(run, 1000);
-    timer.unref?.();
+    warmCacheTimer = setTimeout(run, 1000);
+    warmCacheTimer.unref?.();
 }
 // Snapshot the full prompt/template tree after import so extension startup only
 // pays for prompts that are actually needed immediately.

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

@@ -6,6 +6,8 @@ You are executing GSD auto-mode.
 
 Your working directory is `{{workingDirectory}}`. All file reads, writes, and shell commands MUST operate relative to this directory. Do NOT `cd` to any other directory.
 
+If any inlined plan, summary, verification command, or prior artifact names an absolute path outside `{{workingDirectory}}`, treat that path as stale context. Convert it to the equivalent relative path under `{{workingDirectory}}` before reading, writing, or executing. If no equivalent path exists under `{{workingDirectory}}`, record a verification failure and stop; do not edit or run commands in another checkout.
+
 ## Mission
 
 All slices are complete. Verify the integrated work, persist milestone completion, refresh project state, and write the final record future milestones will rely on.
@@ -16,28 +18,28 @@ Start with what the excerpts give you. Read full files when the section heads si
 
 **On-demand Read ordering:** Complete all slice SUMMARY Reads you need for cross-slice synthesis, the Decision Re-evaluation table, and LEARNINGS **before** calling `gsd_complete_milestone` (step 12). Once that tool runs, the milestone is marked complete in the DB, so it must be the final persistent milestone-closeout write.
 
-### Delegate Review Work
+### Closeout Review Mode
 
-Use `subagent` for review work needing fresh context, before drafting LEARNINGS:
+The inlined context includes a validation status block.
 
-- Cross-slice integrations or new public APIs -> **reviewer** with milestone diff and roadmap.
-- Auth, network, parsing, file IO, shell exec, or crypto -> **security** audit.
-- Significant tests added or changed -> **tester** coverage check against success criteria.
+- If it says a passing validation artifact is present, treat that artifact as authoritative for success criteria, requirement coverage, verification classes, and cross-slice integration. Do not delegate fresh reviewer/security/tester audits unless the validation artifact is internally inconsistent with the inlined summaries.
+- If validation is missing, stale, non-pass, or internally inconsistent, use `subagent` for review work needing fresh context before drafting LEARNINGS: cross-slice integrations or new public APIs -> **reviewer**; auth, network, parsing, file IO, shell exec, or crypto -> **security**; significant tests added or changed -> **tester**.
 
-Subagents report only; they do not write user source. Fold findings into Decision Re-evaluation and LEARNINGS before completion.
+Subagents report only; they do not write user source. Fold any findings into Decision Re-evaluation and LEARNINGS before completion.
 
 {{inlinedContext}}
 
 ## Steps
 
-1. Use the **Milestone Summary** output template from the inlined context above
-2. {{skillActivation}}
-3. **Verify code changes exist.** Compare milestone work against the integration branch (`main`, `master`, or recorded branch), using merge-base as older revision and `HEAD` as newer. If the diff lists non-`.gsd/` files, pass. If `HEAD` equals the integration branch/merge-base, treat it as a self-diff retry: inspect milestone-scoped commit evidence (`GSD-Unit: {{milestoneId}}` or production `GSD-Task: Sxx/Tyy` trailers touching `.gsd/milestones/{{milestoneId}}/`) and verify those commits touched non-`.gsd/` files. Record **verification failure** only when neither source shows implementation files.
-4. Verify every **success criterion** from `{{roadmapPath}}` with evidence from summaries, tests, or observable behavior. Record unmet criteria as **verification failure**.
-5. Verify **definition of done**: all slices `[x]`, summaries exist, and integrations work. Record unmet items as **verification failure**.
-6. If the roadmap includes a **Horizontal Checklist**, verify each item and note unchecked items in the summary.
-7. Fill the **Decision Re-evaluation** table: compare each key `.gsd/DECISIONS.md` decision from this milestone with what shipped, and flag decisions to revisit.
-8. Validate **requirement status transitions**. For each changed requirement, confirm evidence supports the new status. Requirements may move between Active, Validated, Deferred, Blocked, or Out of Scope only with proof.
+1. **Duplicate completion guard:** Call `gsd_milestone_status` for `{{milestoneId}}` before any durable writes. If the returned milestone **status is `complete`**, this is a stale or duplicate closeout turn: do NOT mutate requirements, do NOT refresh the project document, do NOT write LEARNINGS, and do NOT persist milestone completion again. Say: "Milestone {{milestoneId}} is already complete." and stop.
+2. Use the **Milestone Summary** output template from the inlined context above
+3. {{skillActivation}}
+4. **Verify code changes exist.** Compare milestone work against the integration branch (`main`, `master`, or recorded branch), using merge-base as older revision and `HEAD` as newer. If the diff lists non-`.gsd/` files, pass. If `HEAD` equals the integration branch/merge-base, treat it as a self-diff retry: inspect milestone-scoped commit evidence (`GSD-Unit: {{milestoneId}}` or production `GSD-Task: Sxx/Tyy` trailers touching `.gsd/milestones/{{milestoneId}}/`) and verify those commits touched non-`.gsd/` files. Record **verification failure** only when neither source shows implementation files.
+5. Verify every **success criterion** from `{{roadmapPath}}`. If passing validation is present, summarize the validation evidence instead of re-auditing it; otherwise verify with evidence from summaries, tests, or observable behavior. Record unmet criteria as **verification failure**.
+6. Verify **definition of done**: all slices `[x]`, summaries exist, and integrations work. If passing validation is present, trust its integration/verification verdict unless inconsistent with current artifacts. Record unmet items as **verification failure**.
+7. If the roadmap includes a **Horizontal Checklist**, verify each item and note unchecked items in the summary.
+8. Fill the **Decision Re-evaluation** table: compare each key `.gsd/DECISIONS.md` decision from this milestone with what shipped, and flag decisions to revisit.
+9. Validate **requirement status transitions**. For each changed requirement, confirm evidence supports the new status. Requirements may move between Active, Validated, Deferred, Blocked, or Out of Scope only with proof.
 
 **DB access safety:** Do NOT query `.gsd/gsd.db` directly via `sqlite3` or `node -e require('better-sqlite3')`; the engine owns the WAL connection. Use `gsd_milestone_status`, inlined context, or `gsd_*` tools; never direct SQL.
 
@@ -54,13 +56,13 @@ Subagents report only; they do not write user source. Fold findings into Decisio
 
 **Success path** (all verifications passed):
 
-9. For each requirement whose status changed in step 8, call `gsd_requirement_update` with the requirement ID and updated `status` and `validation` fields — the tool regenerates `.gsd/REQUIREMENTS.md` automatically. Do this BEFORE completing the milestone so requirement updates are persisted.
-10. Update `.gsd/PROJECT.md`: use the `write` tool with `path: ".gsd/PROJECT.md"` and `content` containing the full updated document reflecting milestone completion and current project state. Do NOT use the `edit` tool for this — PROJECT.md is a full-document refresh.
-11. Extract structured learnings from this milestone and persist them to the GSD memory store. Follow the procedure block immediately below — it writes `{{milestoneId}}-LEARNINGS.md` as the audit trail and persists Patterns, Lessons, and Decisions via `capture_thought` (categories: pattern, gotcha/convention, architecture). The memory store is the single source of truth for cross-session durable knowledge (ADR-013).
+10. For each requirement whose status changed in step 9, call `gsd_requirement_update` with the requirement ID and updated `status` and `validation` fields — the tool regenerates `.gsd/REQUIREMENTS.md` automatically. Do this BEFORE completing the milestone so requirement updates are persisted.
+11. Update `.gsd/PROJECT.md`: use the `write` tool with `path: ".gsd/PROJECT.md"` and `content` containing the full updated document reflecting milestone completion and current project state. Do NOT use the `edit` tool for this — PROJECT.md is a full-document refresh.
+12. Extract structured learnings from this milestone and persist them to the GSD memory store. Follow the procedure block immediately below — it writes `{{milestoneId}}-LEARNINGS.md` as the audit trail and persists Patterns, Lessons, and Decisions via `capture_thought` (categories: pattern, gotcha/convention, architecture). The memory store is the single source of truth for cross-session durable knowledge (ADR-013).
 
 {{extractLearningsSteps}}
 
-12. **Persist completion through `gsd_complete_milestone`.** Call it with the parameters below. This must be the final persistent write in the unit. The tool updates the milestone status in the DB, renders `{{milestoneSummaryPath}}`, and validates all slices are complete.
+13. **Persist completion through `gsd_complete_milestone`.** Call it with the parameters below. This must be the final persistent write in the unit. The tool updates the milestone status in the DB, renders `{{milestoneSummaryPath}}`, and validates all slices are complete.
 
    **Required parameters:**
    - `milestoneId` (string) — Milestone ID (e.g. M001)
@@ -79,7 +81,7 @@ Subagents report only; they do not write user source. Fold findings into Decisio
    - `followUps` (string) — Follow-up items for future milestones
    - `deviations` (string) — Deviations from the original plan
 
-13. Do not commit manually — the system auto-commits your changes after this unit completes.
+14. Do not commit manually — the system auto-commits your changes after this unit completes.
 - Say: "Milestone {{milestoneId}} complete."
 
 **Important:** Do NOT skip code-change, success-criteria, or definition-of-done verification (steps 3-5). The summary must reflect verified outcomes. Verification failures block completion; there is no override. If a verification tool fails, errors, or returns unexpected output, treat it as failure.

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

@@ -29,7 +29,7 @@ Use `subagent` only for fresh-context review when useful: reviewer for cross-cut
 7. If requirement status changed, call `gsd_requirement_update`; do not write `.gsd/REQUIREMENTS.md` directly.
 8. Prepare `gsd_slice_complete` content with camelCase fields `milestoneId`, `sliceId`, `sliceTitle`, `oneLiner`, `narrative`, `verification`, and `uatContent`.
 9. Draft concrete UAT with preconditions, numbered steps, expected outcomes, edge cases, UAT Type, and Not Proven By This UAT.
-10. Review task summaries for DECISIONS.md and KNOWLEDGE.md-worthy decisions, patterns, and gotchas. Capture significant items with `capture_thought`; do not append knowledge files directly.
+10. Review the inlined task-summary excerpts for DECISIONS.md and KNOWLEDGE.md-worthy decisions, patterns, and gotchas. Read full `*-SUMMARY.md` files only when an excerpt is absent, truncated, or lacks the specific evidence needed for the slice narrative. Capture significant items with `capture_thought`; do not append knowledge files directly.
 11. 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; the tool renders files and updates projections.
 12. Do not run git commands.
 13. Update `.gsd/PROJECT.md` with a full `write` only if the current project state needs refresh.

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

@@ -33,7 +33,7 @@ You execute. The inlined task plan is authoritative. Verify referenced files and
 ## Execution Rules
 
 1. Tersely narrate transitions, decisions, and verification outcomes between tool-call clusters.
-2. Call `memory_query` with 2-4 keywords from the task title and touched files unless this is purely mechanical.
+2. Use the injected memory/context blocks first. Call `memory_query` with 2-4 keywords from the task title and touched files only when no injected memory block exists or the inlined memory/context is insufficient for this task.
 3. {{skillActivation}} Follow activated skills before code edits.
 4. Execute the task plan. Before any `Write` that creates an artifact or output file, check whether that path already exists. If it does, read it first and decide whether the work is already done, should be extended, or truly needs replacement.
 5. Build real behavior through the intended surface; stubs/mocks belong in tests only.
@@ -59,11 +59,13 @@ 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.
-- Read the template at `{{taskSummaryTemplatePath}}`.
+- 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`.
 - 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.
 - Do not run git commands; the system commits from your summary.
 
+{{inlinedTemplates}}
+
 **Autonomous execution:** no human is available. Do not call `ask_user_questions` or `secure_env_collect`; make reasonable assumptions and document them.
 
 **You MUST call `gsd_task_complete` before finishing.**

package/dist/resources/extensions/gsd/prompts/parallel-research-slices.md

@@ -16,7 +16,7 @@ Dispatch ALL slices simultaneously using the `subagent` tool in **parallel mode*
 
 1. Call `subagent` with `tasks: [...]` containing one entry per slice below
 2. Wait for ALL subagents to complete
-3. Verify each slice's RESEARCH file was written (check the `.gsd/{{mid}}/` directory)
+3. Verify each slice's RESEARCH file was written (check `.gsd/milestones/{{mid}}/slices/<slice-id>/`)
 4. If a subagent failed to write its RESEARCH file, retry it **once** individually
 5. If it fails a second time, write a partial RESEARCH file for that slice with a `## BLOCKER` section explaining the failure — do NOT retry again
 6. Report which slices completed research and which (if any) needed a blocker note

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

@@ -48,7 +48,7 @@ Narrate decomposition reasoning in complete sentences: grouping, risk order, ver
 Then:
 1. Use the **Roadmap** output template from the inlined context above
 2. {{skillActivation}}
-3. Create only as many demoable vertical slices as the work genuinely needs.
+3. Create only as many demoable vertical slices as the work genuinely needs. Use 1-10 slices, sized to the work; tiny/single-file/static work should usually be one slice.
 4. Order by risk, high-risk first.
 5. Call `gsd_plan_milestone` to persist milestone fields, slice rows, and **Horizontal Checklist** through the DB-backed path. Fill checklist concerns considered during planning: requirements, decisions, shutdown, revenue, auth, shared resources, reconnection. Omit for trivial milestones. Do **not** write `{{outputPath}}`, `ROADMAP.md`, or other planning artifacts manually; the tool owns rendering and persistence.
 6. If planning produced structural decisions (slice ordering, technology choices, scope exclusions), call `gsd_decision_save` for each; the tool assigns IDs and regenerates `.gsd/DECISIONS.md`.
@@ -78,6 +78,8 @@ Apply these when decomposing and ordering slices:
 - Ship features, not proofs; use clearly marked realistic stubs only when necessary.
 - **Dependency format is comma-separated, never range syntax.** Write `depends:[S01,S02,S03]`, not `depends:[S01-S03]`.
 - Roadmap ambition must match the milestone; right-size decomposition.
+- Missing ecosystem markers are not a reason to over-plan. If Project Classification says `untyped-existing`, treat the listed content files as the project surface and use generic file-level workflow guidance.
+- For `untyped-existing` projects with 1-2 content files, prefer exactly one slice unless the request clearly spans multiple independent user-visible capabilities. For 3-5 content files, prefer 1-2 slices.
 
 ## Progressive Planning (ADR-011)
 

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

@@ -39,7 +39,7 @@ If slice research is inlined, trust it. Explore enough code to confirm paths, bo
 5. Define slice verification before tasks. Non-trivial slices need real tests or executable assertions; boundary contracts need contract-exercising checks. Tests must not read .gitignore/gitignored paths such as `.gsd/`, `.planning/`, or `.audits/`.
 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. Each task needs a concrete title, Why / Files / Do / Verify / Done when, plus task-plan description, steps, must-haves, verification, inputs, and expected output. Inputs and Expected Output must include concrete backtick-wrapped paths; each task needs at least one output path.
+8. Each task needs a concrete title, Why / Files / Do / Verify / Done when, plus task-plan description, steps, must-haves, verification, inputs, and expected output. Inputs and Expected Output must include concrete backtick-wrapped paths. 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. **`expected_output` must only list files the task actually creates or overwrites on disk.** Do NOT include files the task merely reads, verifies, or tests — those belong only in `inputs`. If a task is a pure verification or test task that produces no new files, its `expected_output` may be empty or limited to test-result artifacts (e.g. a log or assertion output). A file that does not yet exist on disk and is needed as an `input` must be produced by an earlier task's `expected_output` — if no prior task creates it, add a task before this one that does.
 9. Persist with `gsd_plan_slice` using goal, successCriteria, optional 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.
 10. Self-audit before finishing: goal/demo closure, requirement coverage, 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.
 11. If planning creates structural decisions, append them to `.gsd/DECISIONS.md`.

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

@@ -17,11 +17,7 @@ You are executing a GSD quick task — a lightweight, focused unit of work outsi
 5. Verify your work:
    - Run tests if applicable.
    - Verify both happy path and failure modes for non-trivial changes.
-6. Commit your changes atomically:
-   - Use conventional commit messages (feat:, fix:, refactor:, etc.)
-   - Stage only relevant files — never commit secrets or runtime files.
-   - Commit logical units separately if the task involves distinct changes.
-   - Quick tasks run outside the auto-mode lifecycle — there is no system auto-commit, so commit directly here.
+6. {{commitInstruction}}
 7. Write a brief summary to `{{summaryPath}}`:
    - Quick tasks operate outside the milestone/slice/task DB structure, so `gsd_summary_save` (which requires a `milestone_id`) cannot be used here. Write the file directly.
 

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

@@ -8,7 +8,7 @@ Your working directory is `{{workingDirectory}}`. All file reads, writes, and sh
 
 A completed task reported `blocker_discovered: true`, meaning the current slice plan cannot be executed as-is. Your job is to rewrite the remaining tasks in the slice plan to address the blocker while preserving all completed work.
 
-All relevant context has been preloaded below — the roadmap, current slice plan, the blocker task summary, and decisions are inlined. Start working immediately without re-reading these files.
+All relevant context has been preloaded below — the roadmap, current slice plan, blocker task summary excerpt, and decisions are inlined. Start working immediately without re-reading these files.
 
 {{inlinedContext}}
 
@@ -30,7 +30,7 @@ Consider these captures when rewriting the remaining tasks — they represent th
 
 ## Instructions
 
-1. Read the blocker task summary carefully. Understand exactly what was discovered and why it blocks the current plan.
+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.
 4. If any incomplete task had a `T0x-PLAN.md`, remove or rewrite it to match the new task description.

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

@@ -27,13 +27,13 @@ Roadmap, slice summaries, assessments, requirements, decisions, and project cont
 Call `subagent` with `tasks: [...]` containing ALL THREE reviewers simultaneously:
 
 **Reviewer A - Requirements Coverage**
-Prompt: "Review milestone {{milestoneId}} requirements coverage. Working directory: {{workingDirectory}}. Read `.gsd/{{milestoneId}}/REQUIREMENTS.md` or equivalent. For each requirement, check slice SUMMARY files in `.gsd/{{milestoneId}}/` and mark COVERED, PARTIAL, or MISSING. Output table: Requirement | Status | Evidence. End with one-line verdict: PASS if all covered, NEEDS-ATTENTION if partials exist, FAIL if any missing."
+Prompt: "Review milestone {{milestoneId}} requirements coverage. Working directory: {{workingDirectory}}. Read `.gsd/REQUIREMENTS.md` or use the inlined requirements context. For each requirement, check slice SUMMARY files under `.gsd/milestones/{{milestoneId}}/slices/` and mark COVERED, PARTIAL, or MISSING. Output table: Requirement | Status | Evidence. End with one-line verdict: PASS if all covered, NEEDS-ATTENTION if partials exist, FAIL if any missing."
 
 **Reviewer B - Cross-Slice Integration**
 Prompt: "Review milestone {{milestoneId}} cross-slice integration. Working directory: {{workingDirectory}}. Read `{{roadmapPath}}` and find the boundary map (produces/consumes contracts). For each boundary, confirm producer SUMMARY produced the artifact and consumer SUMMARY consumed it. Output table: Boundary | Producer Summary | Consumer Summary | Status. End with one-line verdict: PASS if all boundaries honored, NEEDS-ATTENTION if any gaps."
 
 **Reviewer C - Assessment & Acceptance Criteria**
-Prompt: "Review milestone {{milestoneId}} assessment evidence and acceptance criteria. Working directory: {{workingDirectory}}. Read `.gsd/{{milestoneId}}/CONTEXT.md` for criteria. Check slice ASSESSMENT files. Verify each criterion maps to a passing assessment or clear SUMMARY evidence. Then review inlined milestone verification classes. For each non-empty planned class, output table: Class | Planned Check | Evidence | Verdict. Use the exact class names `Contract`, `Integration`, `Operational`, and `UAT` whenever those classes are present. If no verification classes were planned, say that explicitly. Output sections `Acceptance Criteria` with checklist `[ ] Criterion | Evidence`, and `Verification Classes` with the table. End with one-line verdict: PASS if all criteria and classes are covered, NEEDS-ATTENTION if gaps exist."
+Prompt: "Review milestone {{milestoneId}} assessment evidence and acceptance criteria. Working directory: {{workingDirectory}}. Read `.gsd/milestones/{{milestoneId}}/{{milestoneId}}-CONTEXT.md` for criteria. Check slice SUMMARY/UAT files under `.gsd/milestones/{{milestoneId}}/slices/`. Verify each criterion maps to passing evidence. Then review inlined milestone verification classes. For each non-empty planned class, output table: Class | Planned Check | Evidence | Verdict. Use the exact class names `Contract`, `Integration`, `Operational`, and `UAT` whenever those classes are present. If no verification classes were planned, say that explicitly. Output sections `Acceptance Criteria` with checklist `[ ] Criterion | Evidence`, and `Verification Classes` with the table. End with one-line verdict: PASS if all criteria and classes are covered, NEEDS-ATTENTION if gaps exist."
 
 ### Step 2 - Synthesize Findings
 

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

@@ -8,8 +8,8 @@
  * Quick tasks live in `.gsd/quick/` and are tracked in STATE.md's
  * "Quick Tasks Completed" table.
  */
-import { existsSync, mkdirSync, readFileSync, readdirSync, rmSync, writeFileSync } from "node:fs";
-import { join } from "node:path";
+import { existsSync, mkdirSync, readFileSync, readdirSync, realpathSync, rmSync, writeFileSync } from "node:fs";
+import { isAbsolute, join, relative } from "node:path";
 import { loadPrompt } from "./prompt-loader.js";
 import { gsdRoot } from "./paths.js";
 import { GitServiceImpl, runGit } from "./git-service.js";
@@ -64,6 +64,37 @@ function ensureQuickDir(basePath, taskNum, slug) {
     mkdirSync(taskDir, { recursive: true });
     return taskDir;
 }
+function isPathInside(parent, child) {
+    const rel = relative(parent, child);
+    return rel === "" || (!!rel && !rel.startsWith("..") && !isAbsolute(rel));
+}
+function isExternalGsdRoot(basePath, root) {
+    try {
+        return !isPathInside(realpathSync(basePath), realpathSync(root));
+    }
+    catch {
+        return !isPathInside(basePath, root);
+    }
+}
+export function buildQuickCommitInstruction(basePath, root) {
+    const externalState = isExternalGsdRoot(basePath, root);
+    if (externalState) {
+        return [
+            "Commit repo changes atomically, but do not stage or commit `.gsd/quick/...`:",
+            "   - `.gsd/` resolves outside this git repository, so Git cannot stage quick-task summary files from the project repo.",
+            "   - Write the quick summary file directly at the requested path; that file is persisted by GSD external state.",
+            "   - Stage and commit only implementation/test/docs files that live inside the repository.",
+            "   - If the task only writes quick-task research/summary files and no repository files changed, do not run `git commit`; report that there was nothing in the project repo to commit.",
+        ].join("\n");
+    }
+    return [
+        "Commit your changes atomically:",
+        "   - Use conventional commit messages (feat:, fix:, refactor:, etc.)",
+        "   - Stage only relevant files — never commit secrets or runtime files.",
+        "   - Commit logical units separately if the task involves distinct changes.",
+        "   - Quick tasks run outside the auto-mode lifecycle — there is no system auto-commit, so commit directly here.",
+    ].join("\n");
+}
 function quickReturnStatePath(basePath) {
     return join(gsdRoot(basePath), "runtime", "quick-return.json");
 }
@@ -198,6 +229,7 @@ export async function handleQuick(args, ctx, pi) {
         taskDir: taskDirRel,
         branch: actualBranch,
         summaryPath,
+        commitInstruction: buildQuickCommitInstruction(basePath, root),
         date,
         taskNum: String(taskNum),
         slug,

package/dist/resources/extensions/gsd/safety/evidence-collector.js

@@ -14,6 +14,14 @@
 import { existsSync, mkdirSync, readFileSync, writeFileSync, renameSync, unlinkSync, } from "node:fs";
 import { join, dirname } from "node:path";
 import { randomBytes } from "node:crypto";
+const EXECUTION_TOOL_NAMES = new Set([
+    "bash",
+    "Bash",
+    "gsd_exec",
+    "gsd_exec_search",
+    "mcp__gsd-workflow__gsd_exec",
+    "mcp__gsd-workflow__gsd_exec_search",
+]);
 // ─── Module State ───────────────────────────────────────────────────────────
 let unitEvidence = [];
 // ─── Public API ─────────────────────────────────────────────────────────────
@@ -129,11 +137,11 @@ export function clearEvidenceFromDisk(basePath, milestoneId, sliceId, taskId) {
  * Exit codes and output are filled in by recordToolResult after execution.
  */
 export function recordToolCall(toolCallId, toolName, input) {
-    if (toolName === "bash" || toolName === "Bash") {
+    if (EXECUTION_TOOL_NAMES.has(toolName)) {
         unitEvidence.push({
             kind: "bash",
             toolCallId,
-            command: String(input.command ?? ""),
+            command: String(input.command ?? input.cmd ?? input.query ?? ""),
             exitCode: -1,
             outputSnippet: "",
             timestamp: Date.now(),

package/dist/resources/extensions/gsd/tools/context-mode-tool-result.js

@@ -0,0 +1,15 @@
+// Project/App: GSD-2
+// File Purpose: Shared Context Mode tool result helpers.
+export function contextModeDisabledResult(operation) {
+    return {
+        content: [
+            {
+                type: "text",
+                text: `${operation} is disabled by \`context_mode.enabled: false\` in preferences. ` +
+                    "Remove that override or set it to true to re-enable Context Mode tools.",
+            },
+        ],
+        details: { operation, error: "context_mode_disabled" },
+        isError: true,
+    };
+}

package/dist/resources/extensions/gsd/tools/exec-search-tool.js

@@ -3,7 +3,12 @@
 // Scans .gsd/exec/*.meta.json and returns a ranked summary so agents can
 // re-discover past runs without re-executing. Read-only; no DB writes.
 import { searchExecHistory } from "../exec-history.js";
+import { isContextModeEnabled } from "../preferences-types.js";
+import { contextModeDisabledResult } from "./context-mode-tool-result.js";
 export function executeExecSearch(params, opts) {
+    if (!isContextModeEnabled(opts.preferences)) {
+        return contextModeDisabledResult("gsd_exec_search");
+    }
     const searchOpts = {
         query: typeof params.query === "string" ? params.query : undefined,
         runtime: params.runtime,

package/dist/resources/extensions/gsd/tools/exec-tool.js

@@ -5,6 +5,7 @@
 // for MCP return.
 import { EXEC_DEFAULTS, runExecSandbox, } from "../exec-sandbox.js";
 import { isContextModeEnabled } from "../preferences-types.js";
+import { contextModeDisabledResult } from "./context-mode-tool-result.js";
 export function buildExecOptions(baseDir, cfg, extras) {
     const allowlist = Array.isArray(cfg?.exec_env_allowlist) ? cfg.exec_env_allowlist : EXEC_DEFAULTS.envAllowlist;
     const stdoutCap = clampNumber(cfg?.exec_stdout_cap_bytes, EXEC_DEFAULTS.stdoutCapBytes, 4_096, 16_777_216);
@@ -33,19 +34,6 @@ function clampNumber(value, fallback, min, max) {
 function isEnabled(prefs) {
     return isContextModeEnabled(prefs);
 }
-function disabledResult() {
-    return {
-        content: [
-            {
-                type: "text",
-                text: "gsd_exec is disabled by `context_mode.enabled: false` in preferences. Remove that " +
-                    "override (or set it to true) to re-enable sandboxed tool-output execution.",
-            },
-        ],
-        details: { operation: "gsd_exec", error: "context_mode_disabled" },
-        isError: true,
-    };
-}
 function paramError(message) {
     return {
         content: [{ type: "text", text: `Error: ${message}` }],
@@ -55,7 +43,7 @@ function paramError(message) {
 }
 export async function executeGsdExec(params, deps) {
     if (!isEnabled(deps.preferences))
-        return disabledResult();
+        return contextModeDisabledResult("gsd_exec");
     const runtime = params.runtime;
     if (runtime !== "bash" && runtime !== "node" && runtime !== "python") {
         return paramError(`invalid runtime "${String(runtime)}" — must be bash | node | python`);
@@ -67,7 +55,7 @@ export async function executeGsdExec(params, deps) {
     if (Buffer.byteLength(script, "utf8") > 200_000) {
         return paramError("script exceeds the 200 KB length limit");
     }
-    const opts = buildExecOptions(deps.baseDir, deps.preferences?.context_mode, { now: deps.now, generateId: deps.generateId });
+    const opts = buildExecOptions(deps.baseDir, deps.preferences?.context_mode, { env: deps.env, now: deps.now, generateId: deps.generateId });
     const run = deps.run ?? runExecSandbox;
     try {
         const result = await run({

package/dist/resources/extensions/gsd/tools/memory-tools.js

@@ -256,6 +256,7 @@ function includeSupersededMemories(rankedActive) {
                 scope: row["scope"] ?? "project",
                 tags,
                 structured_fields: structuredFields,
+                last_hit_at: row["last_hit_at"] ?? null,
             };
         });
     }

package/dist/resources/extensions/gsd/tools/plan-slice.js

@@ -8,6 +8,7 @@ import { renderAllProjections } from "../workflow-projections.js";
 import { writeManifest } from "../workflow-manifest.js";
 import { appendEvent } from "../workflow-events.js";
 import { logWarning } from "../workflow-logger.js";
+import { validatePlanningPathScope } from "../planning-path-scope.js";
 function validateTasks(value) {
     if (!Array.isArray(value) || value.length === 0) {
         throw new Error("tasks must be a non-empty array");
@@ -91,6 +92,14 @@ export async function handlePlanSlice(rawParams, basePath) {
     catch (err) {
         return { error: `validation failed: ${err.message}` };
     }
+    const pathScopeError = validatePlanningPathScope(basePath, params.tasks.flatMap((task, index) => [
+        { field: `tasks[${index}].files`, values: task.files },
+        { field: `tasks[${index}].inputs`, values: task.inputs },
+        { field: `tasks[${index}].expectedOutput`, values: task.expectedOutput },
+    ]));
+    if (pathScopeError) {
+        return { error: `validation failed: ${pathScopeError}` };
+    }
     // ── Guards + DB writes inside a single transaction (prevents TOCTOU) ───
     // Guards must be inside the transaction so the state they check cannot
     // change between the read and the write (#2723).

package/dist/resources/extensions/gsd/tools/plan-task.js

@@ -8,6 +8,7 @@ import { renderAllProjections } from "../workflow-projections.js";
 import { writeManifest } from "../workflow-manifest.js";
 import { appendEvent } from "../workflow-events.js";
 import { logWarning } from "../workflow-logger.js";
+import { validatePlanningPathScope } from "../planning-path-scope.js";
 function validateParams(params) {
     if (!isNonEmptyString(params?.milestoneId))
         throw new Error("milestoneId is required");
@@ -41,6 +42,14 @@ export async function handlePlanTask(rawParams, basePath) {
     catch (err) {
         return { error: `validation failed: ${err.message}` };
     }
+    const pathScopeError = validatePlanningPathScope(basePath, [
+        { field: "files", values: params.files },
+        { field: "inputs", values: params.inputs },
+        { field: "expectedOutput", values: params.expectedOutput },
+    ]);
+    if (pathScopeError) {
+        return { error: `validation failed: ${pathScopeError}` };
+    }
     // ── Guards + DB writes inside a single transaction (prevents TOCTOU) ───
     // Guards must be inside the transaction so the state they check cannot
     // change between the read and the write (#2723).

package/dist/resources/extensions/gsd/tools/resume-tool.js

@@ -2,7 +2,12 @@
 // agents can re-orient after compaction or session resume without
 // re-deriving project memory state.
 import { readCompactionSnapshot } from "../compaction-snapshot.js";
+import { isContextModeEnabled } from "../preferences-types.js";
+import { contextModeDisabledResult } from "./context-mode-tool-result.js";
 export function executeResume(_params, opts) {
+    if (!isContextModeEnabled(opts.preferences)) {
+        return contextModeDisabledResult("gsd_resume");
+    }
     const snapshot = readCompactionSnapshot(opts.baseDir);
     if (snapshot == null) {
         return {

package/dist/resources/extensions/gsd/tools/workflow-tool-executors.js

@@ -680,7 +680,7 @@ export async function executeMilestoneStatus(params, basePath = process.cwd()) {
             };
             return {
                 content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
-                details: { operation: "milestone_status", milestoneId: milestone.id, sliceCount: slices.length },
+                details: { operation: "milestone_status", ...result },
             };
         });
     }

package/dist/resources/extensions/gsd/unit-context-composer.js

@@ -80,7 +80,15 @@ const CONTEXT_MODE_LANE_LABELS = {
     orchestration: "orchestration",
     docs: "documentation",
 };
-const CONTEXT_MODE_GUIDANCE = "Use `gsd_exec` for noisy commands, `gsd_exec_search` before reruns, and `gsd_resume` after compaction or resume.";
+const CONTEXT_MODE_GUIDANCE_BY_LANE = {
+    interview: "Use `gsd_resume` to restore prior discussion, `gsd_exec` for noisy discovery, and `gsd_exec_search` before repeating scans.",
+    research: "Use `gsd_exec` for noisy research scans, `gsd_exec_search` before reruns, and `gsd_resume` to restore prior findings.",
+    planning: "Use `gsd_resume` for planning continuity, `gsd_exec` for noisy checks, and `gsd_exec_search` before rerunning diagnostics.",
+    execution: "Use `gsd_exec` for builds, tests, and diagnostics, `gsd_exec_search` before reruns, and `gsd_resume` after compaction or resume.",
+    verification: "Use `gsd_exec` for verification commands, `gsd_exec_search` to reuse prior evidence, and `gsd_resume` after compaction or resume.",
+    orchestration: "Use `gsd_resume` before resuming orchestration, `gsd_exec_search` to reuse prior runs, and `gsd_exec` for noisy coordination checks.",
+    docs: "Use `gsd_resume` for prior context, `gsd_exec_search` for saved evidence, and `gsd_exec` for noisy doc validation commands.",
+};
 /**
  * Render the Context Mode instruction lane for a unit type. Unknown unit
  * types, disabled config, and explicit `contextMode: "none"` all omit the
@@ -93,14 +101,15 @@ export function composeContextModeInstructions(unitType, opts) {
     if (!manifest || manifest.contextMode === "none")
         return "";
     const lane = CONTEXT_MODE_LANE_LABELS[manifest.contextMode];
+    const guidance = CONTEXT_MODE_GUIDANCE_BY_LANE[manifest.contextMode];
     if (opts.renderMode === "nested") {
-        return `Context Mode (${lane} lane): ${CONTEXT_MODE_GUIDANCE}`;
+        return `Context Mode (${lane} lane): ${guidance}`;
     }
     return [
         "## Context Mode",
         "",
         `Lane: **${lane} lane**.`,
-        CONTEXT_MODE_GUIDANCE,
+        guidance,
     ].join("\n");
 }
 const SECTION_SEPARATOR = "\n\n---\n\n";

package/dist/resources/extensions/gsd/unit-runtime.js

@@ -4,6 +4,8 @@ import { atomicWriteSync } from "./atomic-write.js";
 import { gsdRoot, relSliceFile, relTaskFile, resolveSliceFile, resolveTaskFile, } from "./paths.js";
 import { loadFile, parseTaskPlanMustHaves, countMustHavesMentionedInSummary } from "./files.js";
 import { parseUnitId } from "./unit-id.js";
+import { getTask, isDbAvailable, refreshOpenDatabaseFromDisk } from "./gsd-db.js";
+import { isClosedStatus } from "./status-guards.js";
 // Per-record advisory lock — prevents read-modify-write races between
 // concurrent writers updating disjoint fields of the same runtime record.
 // Within a single Node process this is moot (writeUnitRuntimeRecord is sync),
@@ -67,6 +69,17 @@ function withRecordLock(recordPath, fn) {
         catch { /* best-effort */ }
     }
 }
+export const IN_FLIGHT_RUNTIME_PHASES = new Set([
+    "dispatched",
+    "wrapup-warning-sent",
+    "timeout",
+    "finalize-timeout",
+    "crashed",
+    "paused",
+]);
+export function isInFlightRuntimePhase(phase) {
+    return IN_FLIGHT_RUNTIME_PHASES.has(phase);
+}
 function runtimeDir(basePath) {
     return join(gsdRoot(basePath), "runtime", "units");
 }
@@ -154,6 +167,12 @@ export async function inspectExecuteTaskDurability(basePath, unitId) {
     const escapedTid = tid.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
     const taskChecked = !!planContent && new RegExp(`^- \\[[xX]\\] \\*\\*${escapedTid}:`, "m").test(planContent);
     const nextActionAdvanced = !new RegExp(`Execute ${tid}\\b`).test(stateContent);
+    let dbComplete = false;
+    if (isDbAvailable()) {
+        refreshOpenDatabaseFromDisk();
+        const task = getTask(mid, sid, tid);
+        dbComplete = !!task && isClosedStatus(task.status);
+    }
     // Must-have coverage: load task plan and count mentions in summary
     let mustHaveCount = 0;
     let mustHavesMentionedInSummary = 0;
@@ -177,11 +196,14 @@ export async function inspectExecuteTaskDurability(basePath, unitId) {
         summaryExists,
         taskChecked,
         nextActionAdvanced,
+        dbComplete,
         mustHaveCount,
         mustHavesMentionedInSummary,
     };
 }
 export function formatExecuteTaskRecoveryStatus(status) {
+    if (status.dbComplete)
+        return "DB task status is closed";
     const missing = [];
     if (!status.summaryExists)
         missing.push(`summary missing (${status.summaryPath})`);