gsd-pi 2.80.0-dev.e146beb20 → 2.80.0-dev.e6c48c3af

package/dist/resources/extensions/gsd/guided-flow.js

@@ -51,6 +51,21 @@ export { showQueue, handleQueueReorder, showQueueAdd, buildExistingMilestonesCon
 import { logWarning } from "./workflow-logger.js";
 import { deleteRuntimeKv } from "./db/runtime-kv.js";
 import { PAUSED_SESSION_KV_KEY } from "./interrupted-session.js";
+function scheduleAutoStartAfterIdle(ctx, pi, basePath, verboseMode, options, launch = startAutoDetached) {
+    const waitForIdle = typeof ctx.waitForIdle === "function"
+        ? ctx.waitForIdle.bind(ctx)
+        : async () => { };
+    void waitForIdle()
+        .then(() => {
+        setTimeout(() => launch(ctx, pi, basePath, verboseMode, options), 0);
+    })
+        .catch((err) => {
+        const message = err instanceof Error ? err.message : String(err);
+        ctx.ui.notify(`Auto-start failed while waiting for the prior turn to settle: ${message}`, "error");
+        logWarning("guided", `auto-start idle wait failed: ${message}`);
+    });
+}
+export const _scheduleAutoStartAfterIdleForTest = scheduleAutoStartAfterIdle;
 // ─── Scope-based validator wrappers ──────────────────────────────────────────
 // These thin wrappers accept a MilestoneScope so callers that already hold a
 // pinned scope never have to re-derive (basePath, milestoneId) separately.
@@ -325,7 +340,7 @@ async function dispatchNextDeepProjectSetupStage(entry) {
     const { DISPATCH_RULES, hasPendingDeepStage } = await import("./auto-dispatch.js");
     if (!hasPendingDeepStage(prefs, entry.basePath)) {
         pendingDeepProjectSetupMap.delete(entry.basePath);
-        startAutoDetached(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
+        scheduleAutoStartAfterIdle(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
         return true;
     }
     const state = await deriveState(entry.basePath);
@@ -359,14 +374,14 @@ async function dispatchNextDeepProjectSetupStage(entry) {
         }
         else if (hasPendingDeepStage(prefs, entry.basePath)) {
             pendingDeepProjectSetupMap.delete(entry.basePath);
-            startAutoDetached(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
+            scheduleAutoStartAfterIdle(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
             return true;
         }
         return false;
     }
     if (!USER_DRIVEN_DEEP_SETUP_UNITS.has(result.unitType)) {
         pendingDeepProjectSetupMap.delete(entry.basePath);
-        startAutoDetached(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
+        scheduleAutoStartAfterIdle(entry.ctx, entry.pi, entry.basePath, false, { step: entry.step });
         return true;
     }
     entry.currentUnitType = result.unitType;
@@ -544,7 +559,7 @@ export function checkAutoStartAfterDiscuss() {
     }
     pendingAutoStartMap.delete(basePath);
     ctx.ui.notify(`Milestone ${milestoneId} ready.`, "success");
-    startAutoDetached(ctx, pi, basePath, false, { step });
+    scheduleAutoStartAfterIdle(ctx, pi, basePath, false, { step });
     return true;
 }
 /**
@@ -1708,6 +1723,20 @@ export async function showSmartEntry(ctx, pi, basePath, options) {
             return;
         }
     }
+    if (interrupted.classification !== "recoverable") {
+        try {
+            const { autoImportMarkdownHierarchyIfDbMismatch } = await import("./migration-auto-check.js");
+            const result = await autoImportMarkdownHierarchyIfDbMismatch(basePath);
+            if (result.action === "imported") {
+                ctx.ui.notify(`Recovered migrated planning state into gsd.db (${result.reason}): ${result.afterDb.milestones} milestone(s), ${result.afterDb.slices} slice(s), ${result.afterDb.tasks} task(s).`, "info");
+            }
+        }
+        catch (err) {
+            const message = err instanceof Error ? err.message : String(err);
+            ctx.ui.notify(`GSD could not auto-import existing planning state into gsd.db: ${message}`, "warning");
+            logWarning("guided", `planning state auto-import failed: ${message}`, { file: "guided-flow.ts" });
+        }
+    }
     // Always derive from the project root — the assessment may have derived
     // state from a worktree path that was cleaned up in the stale branch above.
     const state = await deriveState(basePath);

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

@@ -14,6 +14,27 @@ const CATEGORY_PRIORITY = {
     environment: 4,
     preference: 5,
 };
+// ─── Scoring Helpers ─────────────────────────────────────────────────────────
+/**
+ * Time-decay factor for memory relevance scoring.
+ * Returns 1.0 for never-hit or recently-hit memories, decaying linearly to
+ * 0.7 for memories not accessed in 90+ days. Floor at 0.7 keeps old-but-valid
+ * knowledge from being fully suppressed.
+ *
+ * Defensive parsing: invalid timestamp strings (NaN from Date.parse) are
+ * treated as "no decay" rather than propagating NaN into score arithmetic.
+ * Future timestamps (clock skew, manual DB edits) clamp to daysAgo=0 so the
+ * factor stays in the documented [0.7, 1.0] contract.
+ */
+export function memoryDecayFactor(lastHitAt) {
+    if (!lastHitAt)
+        return 1.0;
+    const ts = Date.parse(lastHitAt);
+    if (!Number.isFinite(ts))
+        return 1.0;
+    const daysAgo = Math.max(0, (Date.now() - ts) / 86_400_000);
+    return Math.max(0.7, 1.0 - 0.3 * Math.min(1.0, daysAgo / 90));
+}
 // ─── Row Mapping ────────────────────────────────────────────────────────────
 function rowToMemory(row) {
     return {
@@ -31,6 +52,7 @@ function rowToMemory(row) {
         scope: row['scope'] ?? 'project',
         tags: parseTags(row['tags']),
         structured_fields: parseStructuredFields(row['structured_fields']),
+        last_hit_at: row['last_hit_at'] ?? null,
     };
 }
 function parseStructuredFields(raw) {
@@ -114,15 +136,37 @@ export function queryMemoriesRanked(opts) {
         ? semanticSearch(adapter, opts.queryVector, activeClause, 50)
         : [];
     if (keywordHits.length === 0 && semanticHits.length === 0 && !trimmedQuery) {
-        // No query at all — fall back to the existing ranked-by-score listing.
-        return getActiveMemoriesRanked(k).map((memory) => ({
-            memory,
-            score: memory.confidence * (1 + memory.hit_count * 0.1),
-            keywordRank: null,
-            semanticRank: null,
-            confidenceBoost: memory.confidence * (1 + memory.hit_count * 0.1),
-            reason: 'ranked',
-        })).filter((hit) => passesFilters(hit.memory, opts));
+        // No query at all — return top-k by decay-aware ranked score.
+        //
+        // Build the candidate pool from a direct SQL query that honors the
+        // request's activeClause (i.e. include_superseded). Using
+        // getActiveMemoriesRanked here would silently drop superseded rows even
+        // when the caller explicitly opted in, and would slice by raw score
+        // before decay/filters had a chance to reorder.
+        const candidatePool = Math.min(Math.max(k * 5, 50), 500);
+        const rows = adapter
+            .prepare(`SELECT * FROM memories ${activeClause}
+         ORDER BY (confidence * (1.0 + hit_count * 0.1)) DESC
+         LIMIT :limit`)
+            .all({ ':limit': candidatePool });
+        const ranked = [];
+        for (const row of rows) {
+            const memory = rowToMemory(row);
+            if (!passesFilters(memory, opts))
+                continue;
+            const decay = memoryDecayFactor(memory.last_hit_at);
+            const score = memory.confidence * (1 + memory.hit_count * 0.1) * decay;
+            ranked.push({
+                memory,
+                score,
+                keywordRank: null,
+                semanticRank: null,
+                confidenceBoost: score,
+                reason: 'ranked',
+            });
+        }
+        ranked.sort((a, b) => b.score - a.score);
+        return ranked.slice(0, k);
     }
     // 3) Reciprocal rank fusion — each hit contributes 1/(rrfK + rank).
     const fused = new Map();
@@ -155,7 +199,7 @@ export function queryMemoriesRanked(opts) {
     for (const entry of fused.values()) {
         if (!passesFilters(entry.memory, opts))
             continue;
-        const boost = entry.memory.confidence * (1 + entry.memory.hit_count * 0.1);
+        const boost = entry.memory.confidence * (1 + entry.memory.hit_count * 0.1) * memoryDecayFactor(entry.memory.last_hit_at);
         const reason = entry.kwRank != null && entry.semRank != null
             ? 'both'
             : entry.kwRank != null
@@ -194,6 +238,7 @@ function passesFilters(memory, filters) {
     }
     return true;
 }
+let ftsWarningEmitted = false;
 function keywordSearch(adapter, rawQuery, activeClause, limit) {
     const ftsAvailable = isFtsAvailable(adapter);
     if (ftsAvailable) {
@@ -215,14 +260,26 @@ function keywordSearch(adapter, rawQuery, activeClause, limit) {
             // fall through to LIKE
         }
     }
-    // LIKE fallback — scans the candidate pool.
+    // LIKE fallback — scans a capped candidate pool.
+    if (!ftsWarningEmitted) {
+        ftsWarningEmitted = true;
+        logWarning('memory-store', 'FTS5 unavailable — using LIKE fallback scan (consider enabling FTS5)');
+    }
     const terms = rawQuery
         .toLowerCase()
         .split(/[^a-z0-9_]+/)
         .filter((t) => t.length >= 2);
     if (terms.length === 0)
         return [];
-    const rows = adapter.prepare(`SELECT * FROM memories ${activeClause}`).all();
+    const preScanCap = Math.min(limit * 20, 2000);
+    // ORDER BY confidence-weighted hit_count DESC so the cap keeps the most
+    // valuable candidates instead of the oldest-by-rowid (which would silently
+    // exclude recently-stored memories on tables larger than preScanCap).
+    const rows = adapter
+        .prepare(`SELECT * FROM memories ${activeClause}
+       ORDER BY (confidence * (1.0 + hit_count * 0.1)) DESC
+       LIMIT :preScanCap`)
+        .all({ ':preScanCap': preScanCap });
     const scored = [];
     for (const row of rows) {
         const memory = rowToMemory(row);

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/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

@@ -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.
@@ -29,14 +31,15 @@ Subagents report only; they do not write user source. Fold any findings into Dec
 
 ## 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}}`. 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**.
-5. 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**.
-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.
 
@@ -53,13 +56,13 @@ Subagents report only; they do not write user source. Fold any findings into Dec
 
 **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)
@@ -78,7 +81,7 @@ Subagents report only; they do not write user source. Fold any findings into Dec
    - `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/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/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,