gsd-pi 2.80.0-dev.c5c38454b → 2.80.0-dev.e146beb20

package/src/resources/extensions/gsd/crash-recovery.ts

@@ -38,6 +38,7 @@ import { _getAdapter, isDbAvailable } from "./gsd-db.js";
 import { gsdRoot, normalizeRealPath } from "./paths.js";
 import { atomicWriteSync } from "./atomic-write.js";
 import { effectiveLockFile } from "./session-lock.js";
+import { isInFlightRuntimePhase, listUnitRuntimeRecords, type AutoUnitRuntimeRecord } from "./unit-runtime.js";
 
 export interface LockData {
   pid: number;
@@ -103,10 +104,40 @@ function getLatestDispatchForWorker(workerId: string):
   return row ?? null;
 }
 
-function workerToLockData(worker: AutoWorkerRow): LockData {
+function latestInFlightRuntimeRecord(basePath: string): AutoUnitRuntimeRecord | null {
+  const records = listUnitRuntimeRecords(basePath).filter((record) =>
+    isInFlightRuntimePhase(record.phase),
+  );
+  if (records.length === 0) return null;
+  return records.sort((a, b) => {
+    const bTime = b.updatedAt || b.startedAt || 0;
+    const aTime = a.updatedAt || a.startedAt || 0;
+    return bTime - aTime;
+  })[0] ?? null;
+}
+
+function runtimeRecordToLockData(worker: AutoWorkerRow, record: AutoUnitRuntimeRecord, sessionFile?: string): LockData {
+  const startedAt = Number.isFinite(record.startedAt)
+    ? new Date(record.startedAt).toISOString()
+    : worker.started_at;
+  return {
+    pid: worker.pid,
+    startedAt: worker.started_at,
+    unitType: record.unitType,
+    unitId: record.unitId,
+    unitStartedAt: startedAt,
+    sessionFile,
+  };
+}
+
+function workerToLockData(basePath: string, worker: AutoWorkerRow): LockData {
   const dispatch = getLatestDispatchForWorker(worker.worker_id);
   const sessionFile =
     getRuntimeKv<string>("worker", worker.worker_id, SESSION_FILE_KV_KEY) ?? undefined;
+  if (!dispatch) {
+    const runtimeRecord = latestInFlightRuntimeRecord(basePath);
+    if (runtimeRecord) return runtimeRecordToLockData(worker, runtimeRecord, sessionFile);
+  }
   return {
     pid: worker.pid,
     startedAt: worker.started_at,
@@ -204,7 +235,7 @@ export function readCrashLock(basePath: string): LockData | null {
     try {
       const projectRoot = normalizeRealPath(basePath);
       const stale = findStaleWorkerForProject(projectRoot);
-      if (stale) return workerToLockData(stale);
+      if (stale) return workerToLockData(basePath, stale);
     } catch {
       // Fall through to the legacy lock-file compatibility path.
     }
@@ -260,25 +291,48 @@ export function formatCrashInfo(lock: LockData): string {
  */
 export function emitCrashRecoveredUnitEnd(basePath: string, lock: LockData): void {
   if (!lock.unitType || !lock.unitId || lock.unitType === "starting") return;
+  emitOpenUnitEndForUnit(basePath, lock.unitType, lock.unitId, "crash-recovered");
+}
 
+export function emitOpenUnitEndForUnit(
+  basePath: string,
+  unitType: string,
+  unitId: string,
+  status: string,
+  errorContext?: { message: string; category: string; stopReason?: string; isTransient?: boolean; retryAfterMs?: number },
+): boolean {
   try {
     const all = queryJournal(basePath);
 
     const starts = all.filter(
-      (e) => e.eventType === "unit-start" && e.data?.unitId === lock.unitId,
+      (e) =>
+        e.eventType === "unit-start" &&
+        e.data?.unitType === unitType &&
+        e.data?.unitId === unitId,
     );
-    if (starts.length === 0) return;
+    if (starts.length === 0) return false;
 
-    const lastStart = starts[starts.length - 1];
+    const lastStart = [...starts].reverse().find((start) => {
+      return !all.some(
+        (e) =>
+          e.eventType === "unit-end" &&
+          e.data?.unitType === unitType &&
+          e.data?.unitId === unitId &&
+          e.causedBy?.flowId === start.flowId &&
+          e.causedBy?.seq === start.seq,
+      );
+    });
+    if (!lastStart) return false;
 
     const alreadyClosed = all.some(
       (e) =>
         e.eventType === "unit-end" &&
-        e.data?.unitId === lock.unitId &&
+        e.data?.unitType === unitType &&
+        e.data?.unitId === unitId &&
         e.causedBy?.flowId === lastStart.flowId &&
         e.causedBy?.seq === lastStart.seq,
     );
-    if (alreadyClosed) return;
+    if (alreadyClosed) return false;
 
     const maxSeq = all
       .filter((e) => e.flowId === lastStart.flowId)
@@ -290,15 +344,18 @@ export function emitCrashRecoveredUnitEnd(basePath: string, lock: LockData): voi
       seq: maxSeq + 1,
       eventType: "unit-end",
       data: {
-        unitType: lock.unitType,
-        unitId: lock.unitId,
-        status: "crash-recovered",
+        unitType,
+        unitId,
+        status,
         artifactVerified: false,
+        ...(errorContext ? { errorContext } : {}),
       },
       causedBy: { flowId: lastStart.flowId, seq: lastStart.seq },
     });
+    return true;
   } catch {
     // Never throw from crash recovery path.
+    return false;
   }
 }
 

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

@@ -6,6 +6,7 @@
  * flow to show when entering a project directory.
  */
 
+import { execFileSync } from "node:child_process";
 import { existsSync, openSync, readSync, closeSync, readdirSync, readFileSync, statSync } from "node:fs";
 import { dirname, join, parse as parsePath } from "node:path";
 import { homedir } from "node:os";
@@ -72,6 +73,22 @@ export interface ProjectSignals {
   verificationCommands: string[];
 }
 
+export type ProjectClassificationKind =
+  | "invalid-repo"
+  | "greenfield"
+  | "untyped-existing"
+  | "typed-existing";
+
+export interface ProjectClassification {
+  kind: ProjectClassificationKind;
+  signals: ProjectSignals;
+  trackedFiles: string[];
+  untrackedFiles: string[];
+  contentFiles: string[];
+  markers: string[];
+  reason: string;
+}
+
 // ─── Project File Markers ───────────────────────────────────────────────────────
 
 export const PROJECT_FILES = [
@@ -243,6 +260,7 @@ const TEST_MARKERS = [
 const RECURSIVE_SCAN_IGNORED_DIRS = new Set([
   ".git",
   ".gsd",
+  ".bg-shell",
   ".planning",
   ".plans",
   ".claude",
@@ -267,6 +285,8 @@ const RECURSIVE_SCAN_IGNORED_DIRS = new Set([
   "out",
 ]) as ReadonlySet<string>;
 
+const PROJECT_CONTENT_EXCLUDE_DIRS = RECURSIVE_SCAN_IGNORED_DIRS;
+
 /** Project file markers safe to detect recursively via suffix matching. */
 const ROOT_ONLY_PROJECT_FILES = new Set<string>([
   ".github/workflows",
@@ -536,6 +556,114 @@ export function detectProjectSignals(basePath: string): ProjectSignals {
   };
 }
 
+function normalizeGitPath(file: string): string {
+  return file.replaceAll("\\", "/").replace(/^\.\//, "");
+}
+
+function isProjectContentFile(file: string): boolean {
+  const normalized = normalizeGitPath(file);
+  if (!normalized || normalized.endsWith("/")) return false;
+  if (normalized === ".gitignore" || normalized === ".gitattributes") return false;
+  const parts = normalized.split("/");
+  if (parts.some((part) => PROJECT_CONTENT_EXCLUDE_DIRS.has(part))) return false;
+  if (normalized.endsWith(".DS_Store")) return false;
+  return true;
+}
+
+function runGitLines(basePath: string, args: string[]): string[] {
+  try {
+    const output = execFileSync("git", args, {
+      cwd: basePath,
+      stdio: ["ignore", "pipe", "ignore"],
+      encoding: "utf-8",
+    }).trim();
+    return output ? output.split("\n").map((line) => line.trim()).filter(Boolean) : [];
+  } catch {
+    return [];
+  }
+}
+
+function listTrackedProjectFiles(basePath: string): string[] {
+  return runGitLines(basePath, ["ls-files"])
+    .map(normalizeGitPath)
+    .filter(isProjectContentFile);
+}
+
+function listUntrackedProjectFiles(basePath: string): string[] {
+  return runGitLines(basePath, ["ls-files", "--others", "--exclude-standard"])
+    .map(normalizeGitPath)
+    .filter(isProjectContentFile);
+}
+
+function hasKnownProjectMarkers(basePath: string, signals: ProjectSignals): boolean {
+  if (signals.detectedFiles.length > 0) return true;
+  if (signals.xcodePlatforms.length > 0) return true;
+  return false;
+}
+
+/**
+ * Classify repo presence separately from ecosystem/tooling markers.
+ *
+ * Known project files identify tooling. Git-tracked/non-ignored content
+ * identifies whether this is an existing project at all. This keeps small
+ * static or documentation repos from being mislabeled as greenfield.
+ */
+export function classifyProject(basePath: string): ProjectClassification {
+  const signals = detectProjectSignals(basePath);
+  const markers = [...signals.detectedFiles];
+
+  if (!signals.isGitRepo) {
+    return {
+      kind: "invalid-repo",
+      signals,
+      trackedFiles: [],
+      untrackedFiles: [],
+      contentFiles: [],
+      markers,
+      reason: "missing .git",
+    };
+  }
+
+  const trackedFiles = listTrackedProjectFiles(basePath);
+  const untrackedFiles = listUntrackedProjectFiles(basePath);
+  const contentFiles = [...new Set([...trackedFiles, ...untrackedFiles])];
+  const hasMarkers = hasKnownProjectMarkers(basePath, signals);
+
+  if (hasMarkers) {
+    return {
+      kind: "typed-existing",
+      signals,
+      trackedFiles,
+      untrackedFiles,
+      contentFiles,
+      markers,
+      reason: markers.length > 0 ? `detected markers: ${markers.join(", ")}` : "detected project structure",
+    };
+  }
+
+  if (contentFiles.length > 0) {
+    return {
+      kind: "untyped-existing",
+      signals,
+      trackedFiles,
+      untrackedFiles,
+      contentFiles,
+      markers,
+      reason: "project content exists but no recognized tooling markers were found",
+    };
+  }
+
+  return {
+    kind: "greenfield",
+    signals,
+    trackedFiles,
+    untrackedFiles,
+    contentFiles,
+    markers,
+    reason: "no tracked or non-ignored project content",
+  };
+}
+
 // ─── Xcode Platform Detection ───────────────────────────────────────────────────
 
 /** Known SDKROOT values → canonical platform names. */

package/src/resources/extensions/gsd/guided-flow.ts

@@ -30,7 +30,7 @@ import {
   formatInterruptedSessionRunningMessage,
   formatInterruptedSessionSummary,
 } from "./interrupted-session.js";
-import { listUnitRuntimeRecords, clearUnitRuntimeRecord } from "./unit-runtime.js";
+import { listUnitRuntimeRecords, clearUnitRuntimeRecord, isInFlightRuntimePhase } from "./unit-runtime.js";
 import { resolveExpectedArtifactPath } from "./auto.js";
 import { gsdHome } from "./gsd-home.js";
 import {
@@ -118,6 +118,22 @@ export function resolveExpectedArtifactPathForScope(
   return resolveExpectedArtifactPath(unitType, unitId, scope.workspace.projectRoot);
 }
 
+async function runQuickTaskChoice(ctx: ExtensionCommandContext, pi: ExtensionAPI): Promise<void> {
+  if (!ctx.hasUI) {
+    ctx.ui.notify("Run /gsd quick <task> for small bounded work, or /gsd do <task> for natural-language routing.", "info");
+    return;
+  }
+
+  const task = (await ctx.ui.input("Quick task", "Describe the small task to run with /gsd quick"))?.trim();
+  if (!task) {
+    ctx.ui.notify("Quick task cancelled.", "info");
+    return;
+  }
+
+  const { handleQuick } = await import("./quick.js");
+  await handleQuick(task, ctx, pi);
+}
+
 /**
  * Scope-based overload of isGhostMilestone.
  * Binds basePath and milestoneId from the scope, ensuring path resolution
@@ -1786,8 +1802,8 @@ function selfHealRuntimeRecords(basePath: string, ctx: ExtensionContext): { clea
         cleared++;
         continue;
       }
-      // Clear records stuck in dispatched or timeout phase (process died mid-unit)
-      if (phase === "dispatched" || phase === "timeout") {
+      // Clear records stuck in an in-flight phase (process died mid-unit).
+      if (isInFlightRuntimePhase(phase)) {
         clearUnitRuntimeRecord(basePath, unitType, unitId);
         cleared++;
       }
@@ -2134,17 +2150,24 @@ export async function showSmartEntry(
         title: "GSD — Get Shit Done",
         summary: ["No active milestone."],
         actions: [
+          {
+            id: "quick_task",
+            label: "Quick task",
+            description: "For small bounded work, run /gsd quick <task> or /gsd do <task>.",
+            recommended: true,
+          },
           {
             id: "new_milestone",
             label: "Create next milestone",
-            description: "Define what to build next.",
-            recommended: true,
+            description: "Define a larger body of work with planning artifacts.",
           },
         ],
         notYetMessage: "Run /gsd when ready.",
       });
 
-      if (choice === "new_milestone") {
+      if (choice === "quick_task") {
+        await runQuickTaskChoice(ctx, pi);
+      } else if (choice === "new_milestone") {
         setPendingAutoStart(basePath, { ctx, pi, basePath, milestoneId: nextId, step: stepMode });
         await dispatchWorkflow(pi, await prepareAndBuildDiscussPrompt(ctx, pi, nextId,
           `New milestone ${nextId}.`,
@@ -2181,11 +2204,16 @@ export async function showSmartEntry(
       title: `GSD — ${milestoneId}: ${milestoneTitle}`,
       summary: ["All milestones complete."],
       actions: [
+        {
+          id: "quick_task",
+          label: "Quick task",
+          description: "Do a small bounded task without opening a milestone.",
+          recommended: true,
+        },
         {
           id: "new_milestone",
           label: "Start new milestone",
           description: "Define and plan the next milestone.",
-          recommended: true,
         },
         {
           id: "status",
@@ -2196,7 +2224,9 @@ export async function showSmartEntry(
       notYetMessage: "Run /gsd when ready.",
     });
 
-    if (choice === "new_milestone") {
+    if (choice === "quick_task") {
+      await runQuickTaskChoice(ctx, pi);
+    } else if (choice === "new_milestone") {
       const milestoneIds = findMilestoneIds(basePath);
       const uniqueMilestoneIds = !!loadEffectiveGSDPreferences()?.preferences?.unique_milestone_ids;
       const nextId = nextMilestoneIdReserved(milestoneIds, uniqueMilestoneIds, basePath);
@@ -2300,13 +2330,18 @@ export async function showSmartEntry(
       const hasContext = !!(contextFile && await loadFile(contextFile));
 
       const actions = [
+        {
+          id: "quick_task",
+          label: "Quick task instead",
+          description: "Use this when the work is small and should not become a milestone.",
+          recommended: true,
+        },
         {
           id: "plan",
           label: "Create roadmap",
           description: hasContext
             ? "Context captured. Decompose into slices with a boundary map."
             : "Decompose the milestone into slices with a boundary map.",
-          recommended: true,
         },
         ...(!hasContext ? [{
           id: "discuss",
@@ -2332,7 +2367,9 @@ export async function showSmartEntry(
         notYetMessage: "Run /gsd when ready.",
       });
 
-      if (choice === "plan") {
+      if (choice === "quick_task") {
+        await runQuickTaskChoice(ctx, pi);
+      } else if (choice === "plan") {
         setPendingAutoStart(basePath, { ctx, pi, basePath, milestoneId, step: stepMode });
         await dispatchWorkflow(
           pi,

package/src/resources/extensions/gsd/planning-path-scope.ts

@@ -0,0 +1,35 @@
+import { isAbsolute, relative, resolve } from "node:path";
+import { normalizePlannedFileReference } from "./files.js";
+
+export interface PlanningPathScopeField {
+  field: string;
+  values: string[];
+}
+
+function isInsideBase(basePath: string, candidate: string): boolean {
+  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: string,
+  fields: PlanningPathScopeField[],
+): string | null {
+  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/src/resources/extensions/gsd/prompts/complete-milestone.md

@@ -16,15 +16,14 @@ 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}}
 
@@ -33,8 +32,8 @@ Subagents report only; they do not write user source. Fold findings into Decisio
 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**.
+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.

package/src/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/src/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/src/resources/extensions/gsd/safety/evidence-collector.ts

@@ -50,6 +50,15 @@ export interface FileEditEvidence {
 
 export type EvidenceEntry = BashEvidence | FileWriteEvidence | FileEditEvidence;
 
+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: EvidenceEntry[] = [];
@@ -188,11 +197,11 @@ export function clearEvidenceFromDisk(
  * Exit codes and output are filled in by recordToolResult after execution.
  */
 export function recordToolCall(toolCallId: string, toolName: string, input: Record<string, unknown>): void {
-  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/src/resources/extensions/gsd/tests/auto-loop.test.ts

@@ -2556,7 +2556,7 @@ test("autoLoop warns but proceeds for greenfield project (no project files) (#18
     "should not stop with health check failure for greenfield project",
   );
   const greenfieldWarning = notifications.find(
-    (n) => n.includes("no recognized project files") && n.includes("greenfield"),
+    (n) => n.includes("no project content yet") && n.includes("greenfield"),
   );
   assert.ok(
     greenfieldWarning,