gsd-pi 2.80.0-dev.c5f2443b3 → 2.80.0-dev.cf9433f56

package/dist/resources/extensions/gsd/migrate/command.js

@@ -15,6 +15,43 @@ import { fileURLToPath } from "node:url";
 import { showNextAction } from "../../shared/tui.js";
 import { validatePlanningDirectory, parsePlanningDirectory, transformToGSD, generatePreview, writeGSDDirectory, } from "./index.js";
 import { homedir } from "node:os";
+import { ensureDbOpen } from "../bootstrap/dynamic-tools.js";
+import { clearEngineHierarchy, transaction } from "../gsd-db.js";
+import { migrateFromMarkdown } from "../md-importer.js";
+import { invalidateStateCache } from "../state.js";
+function assertMigrationImportMatchesPreview(imported, preview) {
+    const mismatches = [];
+    if (imported.hierarchy.milestones !== preview.milestoneCount) {
+        mismatches.push(`milestones ${imported.hierarchy.milestones}/${preview.milestoneCount}`);
+    }
+    if (imported.hierarchy.slices !== preview.totalSlices) {
+        mismatches.push(`slices ${imported.hierarchy.slices}/${preview.totalSlices}`);
+    }
+    if (imported.hierarchy.tasks !== preview.totalTasks) {
+        mismatches.push(`tasks ${imported.hierarchy.tasks}/${preview.totalTasks}`);
+    }
+    if (imported.requirements !== preview.requirements.total) {
+        mismatches.push(`requirements ${imported.requirements}/${preview.requirements.total}`);
+    }
+    if (mismatches.length > 0) {
+        throw new Error(`migration DB import verification failed: ${mismatches.join(", ")}`);
+    }
+}
+export async function importWrittenMigrationToDb(basePath, preview) {
+    const opened = await ensureDbOpen(basePath);
+    if (!opened) {
+        throw new Error(`failed to open or create the GSD database at ${basePath}`);
+    }
+    const counts = transaction(() => {
+        clearEngineHierarchy();
+        const imported = migrateFromMarkdown(basePath);
+        if (preview)
+            assertMigrationImportMatchesPreview(imported, preview);
+        return imported;
+    });
+    invalidateStateCache();
+    return counts;
+}
 /** Format preview stats for embedding in the review prompt. */
 function formatPreviewStats(preview) {
     const lines = [
@@ -126,12 +163,14 @@ export async function handleMigrate(args, ctx, pi) {
     ctx.ui.notify("Writing .gsd directory…", "info");
     const result = await writeGSDDirectory(project, process.cwd());
     const gsdPath = gsdRoot(process.cwd());
-    ctx.ui.notify(`✓ Migration complete — ${result.paths.length} file(s) written to .gsd/`, "info");
+    const imported = await importWrittenMigrationToDb(process.cwd(), preview);
+    ctx.ui.notify(`✓ Migration complete — ${result.paths.length} file(s) written to .gsd/ and ${imported.hierarchy.milestones}M/${imported.hierarchy.slices}S/${imported.hierarchy.tasks}T imported to the database`, "info");
     // ── Post-write review offer ────────────────────────────────────────────────
     const reviewChoice = await showNextAction(ctx, {
         title: "Migration written",
         summary: [
             `${result.paths.length} files written to .gsd/`,
+            `${imported.hierarchy.milestones} milestone(s), ${imported.hierarchy.slices} slice(s), and ${imported.hierarchy.tasks} task(s) imported to gsd.db`,
             "",
             "The agent can now review the migrated output against GSD-2 standards —",
             "checking structure, content quality, deriveState() round-trip, and",

package/dist/resources/extensions/gsd/migration-auto-check.js

@@ -0,0 +1,87 @@
+import { existsSync, readdirSync, readFileSync } from "node:fs";
+import { ensureDbOpen } from "./bootstrap/dynamic-tools.js";
+import { clearEngineHierarchy, getAllMilestones, getMilestoneSlices, getSliceTasks, isDbAvailable, transaction, } from "./gsd-db.js";
+import { migrateHierarchyToDb } from "./md-importer.js";
+import { parsePlan, parseRoadmap } from "./parsers-legacy.js";
+import { milestonesDir, resolveMilestoneFile, resolveSliceFile, } from "./paths.js";
+import { invalidateStateCache } from "./state.js";
+function zeroCounts() {
+    return { milestones: 0, slices: 0, tasks: 0 };
+}
+function sameCounts(a, b) {
+    return a.milestones === b.milestones && a.slices === b.slices && a.tasks === b.tasks;
+}
+export function countMarkdownHierarchy(basePath) {
+    const root = milestonesDir(basePath);
+    if (!existsSync(root))
+        return zeroCounts();
+    const counts = zeroCounts();
+    for (const entry of readdirSync(root, { withFileTypes: true })) {
+        if (!entry.isDirectory() || !/^M\d+/.test(entry.name))
+            continue;
+        counts.milestones++;
+        const roadmapPath = resolveMilestoneFile(basePath, entry.name, "ROADMAP");
+        if (!roadmapPath || !existsSync(roadmapPath))
+            continue;
+        const roadmap = parseRoadmap(readFileSync(roadmapPath, "utf-8"));
+        counts.slices += roadmap.slices.length;
+        for (const slice of roadmap.slices) {
+            const planPath = resolveSliceFile(basePath, entry.name, slice.id, "PLAN");
+            if (!planPath || !existsSync(planPath))
+                continue;
+            const plan = parsePlan(readFileSync(planPath, "utf-8"));
+            counts.tasks += plan.tasks.length;
+        }
+    }
+    return counts;
+}
+export function countDbHierarchy() {
+    if (!isDbAvailable())
+        return zeroCounts();
+    const counts = zeroCounts();
+    const milestones = getAllMilestones();
+    counts.milestones = milestones.length;
+    for (const milestone of milestones) {
+        const slices = getMilestoneSlices(milestone.id);
+        counts.slices += slices.length;
+        for (const slice of slices) {
+            counts.tasks += getSliceTasks(milestone.id, slice.id).length;
+        }
+    }
+    return counts;
+}
+export async function autoImportMarkdownHierarchyIfDbMismatch(basePath) {
+    const markdown = countMarkdownHierarchy(basePath);
+    if (sameCounts(markdown, zeroCounts())) {
+        return {
+            action: "none",
+            reason: "no-markdown",
+            markdown,
+            beforeDb: zeroCounts(),
+            afterDb: zeroCounts(),
+        };
+    }
+    const opened = await ensureDbOpen(basePath);
+    if (!opened || !isDbAvailable()) {
+        throw new Error(`failed to open or create the GSD database at ${basePath}`);
+    }
+    const beforeDb = countDbHierarchy();
+    if (sameCounts(markdown, beforeDb)) {
+        return { action: "none", reason: "in-sync", markdown, beforeDb, afterDb: beforeDb };
+    }
+    const reason = sameCounts(beforeDb, zeroCounts()) ? "db-empty" : "count-mismatch";
+    const imported = transaction(() => {
+        clearEngineHierarchy();
+        return migrateHierarchyToDb(basePath);
+    });
+    invalidateStateCache();
+    const afterDb = {
+        milestones: imported.milestones,
+        slices: imported.slices,
+        tasks: imported.tasks,
+    };
+    if (!sameCounts(markdown, afterDb)) {
+        throw new Error(`migration auto-import verification failed: markdown ${markdown.milestones}M/${markdown.slices}S/${markdown.tasks}T, db ${afterDb.milestones}M/${afterDb.slices}S/${afterDb.tasks}T`);
+    }
+    return { action: "imported", reason, markdown, beforeDb, afterDb };
+}

package/dist/resources/extensions/gsd/planning-path-scope.js

@@ -0,0 +1,26 @@
+import { isAbsolute, relative, resolve } from "node:path";
+import { normalizePlannedFileReference } from "./files.js";
+function isInsideBase(basePath, candidate) {
+    const base = resolve(basePath);
+    const abs = resolve(candidate);
+    const rel = relative(base, abs);
+    return rel === "" || (!!rel && !rel.startsWith("..") && !isAbsolute(rel));
+}
+/**
+ * Planning IO fields are execution contracts. Absolute paths are only safe when
+ * they stay inside the active working directory; in worktree mode, an absolute
+ * path to the original checkout makes executors edit the wrong tree.
+ */
+export function validatePlanningPathScope(basePath, fields) {
+    for (const { field, values } of fields) {
+        for (const raw of values) {
+            const candidate = normalizePlannedFileReference(raw);
+            if (!isAbsolute(candidate))
+                continue;
+            if (isInsideBase(basePath, candidate))
+                continue;
+            return `${field} contains absolute path outside working directory: ${candidate}. Use a path relative to ${basePath}.`;
+        }
+    }
+    return null;
+}

package/dist/resources/extensions/gsd/pr-evidence.js

@@ -8,8 +8,53 @@ const CHANGE_TYPE_LABELS = {
     docs: "Documentation only",
     chore: "Build, CI, or tooling changes",
 };
+// Per-item cap for user-supplied content. 2 KB gives slice titles plus
+// descriptions room while still bounding malicious DoS-via-PR-body input.
+const USER_CONTENT_CAP_BYTES = 2048;
+const TRUNCATION_SUFFIX = " … [truncated]";
+// Strips HTML comments, fake commit trailers (Co-Authored-By, Signed-off-by —
+// case-insensitive on the trailer name), and caps total length. Designed to
+// be a no-op for well-formed input; golden fixtures must remain byte-stable.
+// Trailer lines are removed (not rejected) so that a single bad line in an
+// otherwise legitimate description does not block the entire PR.
+function sanitizeUserContent(s) {
+    if (!s)
+        return s;
+    // Strip HTML comments greedily across newlines.
+    let out = s.replace(/<!--[\s\S]*?-->/g, "");
+    // Drop lines that look like commit trailers we do not want forged.
+    out = out
+        .split("\n")
+        .filter((line) => !/^\s*(co-authored-by|signed-off-by)\s*:/i.test(line))
+        .join("\n");
+    if (Buffer.byteLength(out, "utf8") > USER_CONTENT_CAP_BYTES) {
+        const budget = USER_CONTENT_CAP_BYTES - Buffer.byteLength(TRUNCATION_SUFFIX, "utf8");
+        // Truncate by code units to stay safely under the byte budget for ASCII;
+        // for multibyte content we conservatively walk back until under budget.
+        let sliced = out.slice(0, Math.max(0, budget));
+        while (Buffer.byteLength(sliced, "utf8") > budget && sliced.length > 0) {
+            sliced = sliced.slice(0, -1);
+        }
+        out = sliced + TRUNCATION_SUFFIX;
+    }
+    return out;
+}
+// Strips HTML comments and fake trailers without applying the length cap.
+// Used for short fields like linkedIssue where truncation would be confusing.
+function sanitizeIssueRef(s) {
+    if (!s)
+        return s;
+    let out = s.replace(/<!--[\s\S]*?-->/g, "");
+    out = out
+        .split("\n")
+        .filter((line) => !/^\s*(co-authored-by|signed-off-by)\s*:/i.test(line))
+        .join("\n");
+    return out;
+}
 function normalizeList(values) {
-    return (values ?? []).map((value) => value.trim()).filter(Boolean);
+    return (values ?? [])
+        .map((value) => sanitizeUserContent(value).trim())
+        .filter(Boolean);
 }
 function changeTypeChecklist(selected) {
     return Object.keys(CHANGE_TYPE_LABELS).map((type) => {
@@ -28,13 +73,17 @@ export function buildPrEvidence(input) {
     const subjectTitle = input.milestoneTitle?.trim() || subjectId;
     const changeType = input.changeType ?? "feat";
     const summaries = normalizeList(input.summaries);
+    const blockers = normalizeList(input.blockers);
     const roadmapItems = normalizeList(input.roadmapItems);
     const metrics = normalizeList(input.metrics);
     const testsRun = normalizeList(input.testsRun);
     const rollbackNotes = normalizeList(input.rollbackNotes);
-    const linkedIssue = input.linkedIssue?.trim() || "Not specified. Add an issue link before marking this PR ready if CONTRIBUTING.md requires one.";
-    const why = input.why?.trim() || `${capitalize(subjectKind)} work is complete and ready for review.`;
-    const how = input.how?.trim() || "Generated from GSD evidence and local workflow artifacts.";
+    // linkedIssue is sanitized but not length-capped: legitimate issue refs
+    // are short by nature, and truncating "Closes #123" would be unhelpful.
+    const linkedIssueRaw = input.linkedIssue ? sanitizeIssueRef(input.linkedIssue).trim() : "";
+    const linkedIssue = linkedIssueRaw || "Not specified. Add an issue link before marking this PR ready if CONTRIBUTING.md requires one.";
+    const why = (input.why ? sanitizeUserContent(input.why).trim() : "") || `${capitalize(subjectKind)} work is complete and ready for review.`;
+    const how = (input.how ? sanitizeUserContent(input.how).trim() : "") || "Generated from GSD evidence and local workflow artifacts.";
     const title = `${changeType}: ${subjectTitle}`;
     const sections = [
         "## TL;DR",
@@ -46,19 +95,11 @@ export function buildPrEvidence(input) {
         "## What",
         "",
         summaries.length > 0 ? summaries.join("\n\n") : `${capitalize(subjectKind)} ${subjectId} completed.`,
-        "",
-        "## Why",
-        "",
-        why,
-        "",
-        "## How",
-        "",
-        how,
-        "",
-        "## Linked Issue",
-        "",
-        linkedIssue,
     ];
+    if (blockers.length > 0) {
+        sections.push("", "## Blockers", "", blockers.map((blocker) => `- ${blocker}`).join("\n"));
+    }
+    sections.push("", "## Why", "", why, "", "## How", "", how, "", "## Linked Issue", "", linkedIssue);
     if (roadmapItems.length > 0) {
         sections.push("", "## Roadmap", "", roadmapItems.join("\n"));
     }

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

@@ -328,6 +328,8 @@ function shouldValidateInputAsPath(raw) {
     const trimmed = raw.trim();
     if (!trimmed)
         return false;
+    if (isRuntimeOnlyInput(trimmed))
+        return false;
     const candidate = extractPathFromAnnotation(trimmed);
     if (!candidate)
         return false;
@@ -349,6 +351,9 @@ function shouldValidateInputAsPath(raw) {
         /[\\/]/.test(candidate) ||
         /[*?[\]{}]/.test(candidate));
 }
+function isRuntimeOnlyInput(raw) {
+    return /\(\s*runtime\s*\)/i.test(raw);
+}
 function containsGlobPattern(candidate) {
     return ["*", "?", "[", "]", "{", "}"].some((char) => candidate.includes(char));
 }
@@ -461,6 +466,8 @@ export function checkTaskOrdering(tasks, basePath) {
         const task = tasks[i];
         const filesToCheck = [...task.inputs];
         for (const file of filesToCheck) {
+            if (isRuntimeOnlyInput(file))
+                continue;
             if (!shouldValidateInputAsPath(file))
                 continue;
             const normalizedFile = normalizeFilePath(file);

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

@@ -16,28 +16,28 @@ 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 +54,13 @@ 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 +79,7 @@ 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/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; each task needs at least one output path. 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.
 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/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,