gsd-pi 2.80.0-dev.c5f2443b3 → 2.80.0-dev.e146beb20

package/src/resources/extensions/gsd/auto-dispatch.ts

@@ -211,6 +211,23 @@ export function hasPendingDeepStage(prefs: GSDPreferences | undefined, basePath:
   return gate.status === "pending" || gate.status === "blocked";
 }
 
+export function shouldRunDeepProjectSetup(
+  state: Pick<GSDState, "phase">,
+  prefs: GSDPreferences | undefined,
+  basePath: string,
+  options: { hasSurvivorBranch?: boolean } = {},
+): boolean {
+  if (options.hasSurvivorBranch === true) return false;
+  if (
+    state.phase !== "pre-planning" &&
+    state.phase !== "needs-discussion" &&
+    state.phase !== "planning"
+  ) {
+    return false;
+  }
+  return hasPendingDeepStage(prefs, basePath);
+}
+
 function missingSliceStop(mid: string, phase: string): DispatchAction {
   return {
     action: "stop",

package/src/resources/extensions/gsd/auto-post-unit.ts

@@ -43,7 +43,7 @@ import {
 import { regenerateIfMissing } from "./workflow-projections.js";
 import { syncStateToProjectRoot } from "./auto-worktree.js";
 import { normalizeWorktreePathForCompare } from "./worktree-root.js";
-import { isDbAvailable, getTask, getSlice, getMilestone, updateTaskStatus, _getAdapter } from "./gsd-db.js";
+import { isDbAvailable, getTask, getSlice, getMilestone, updateTaskStatus, _getAdapter, getVerificationEvidence } from "./gsd-db.js";
 import { renderPlanCheckboxes } from "./markdown-renderer.js";
 import { consumeSignal } from "./session-status-io.js";
 import {
@@ -852,22 +852,22 @@ export async function postUnitPreVerification(pctx: PostUnitContext, opts?: PreV
         }
 
         // Evidence cross-reference (execute-task only)
-        // Verification evidence is passed via the complete-task tool call and
-        // stored in the SUMMARY.md on disk — not available as structured data
-        // in the DB. The evidence collector tracks actual bash tool calls, so
-        // we can still detect units that claimed success but ran no commands.
+        // Only compare against concrete command evidence persisted by the task
+        // completion tool. A prose Verify field can be satisfied later by the
+        // host verification gate, so it is not enough to accuse the unit.
         if (safetyConfig.evidence_cross_reference && s.currentUnit.type === "execute-task") {
           try {
             const actual = getEvidence();
             const bashCalls = actual.filter(e => e.kind === "bash");
-            // If the task is marked complete but zero bash commands were run,
-            // it's suspicious — the LLM may have fabricated results.
             if (sMid && sSid && sTid && isDbAvailable()) {
               const taskRow = getTask(sMid, sSid, sTid);
-              if (taskRow?.status === "complete" && taskRow.verify && bashCalls.length === 0) {
-                logWarning("safety", "task marked complete with verification commands but no bash calls were executed");
+              const claimedCommands = getVerificationEvidence(sMid, sSid, sTid)
+                .map((row) => row.command)
+                .filter((command): command is string => typeof command === "string" && command.trim().length > 0);
+              if (taskRow?.status === "complete" && claimedCommands.length > 0 && bashCalls.length === 0) {
+                logWarning("safety", "task claimed verification command evidence but no execution tool calls were recorded");
                 ctx.ui.notify(
-                  `Safety: task ${sTid} has verification commands but no bash calls were recorded`,
+                  `Safety: task ${sTid} claimed command evidence but no execution tool calls were recorded`,
                   "warning",
                 );
               }

package/src/resources/extensions/gsd/auto-prompts.ts

@@ -8,7 +8,7 @@
 
 import { loadFile, parseContinue, parseSummary, loadActiveOverrides, formatOverridesSection, parseTaskPlanFile } from "./files.js";
 import type { Override, UatType } from "./files.js";
-import { hasVerdict, getUatType } from "./verdict-parser.js";
+import { hasVerdict, getUatType, extractVerdict } from "./verdict-parser.js";
 import { loadPrompt, inlineTemplate } from "./prompt-loader.js";
 import {
   resolveMilestoneFile, resolveSliceFile, resolveSlicePath,
@@ -39,6 +39,7 @@ import { logWarning } from "./workflow-logger.js";
 import { inlineGraphSubgraph } from "./graph-context.js";
 import { buildExtractionStepsBlock } from "./commands-extract-learnings.js";
 import { resolveSkillManifest, warnIfManifestHasMissingSkills } from "./skill-manifest.js";
+import { classifyProject, type ProjectClassification } from "./detection.js";
 
 // ─── Preamble Cap ─────────────────────────────────────────────────────────────
 
@@ -80,6 +81,108 @@ function resolveSummaryBudgetChars(): number {
   return resolvePromptBudgets().summaryBudgetChars;
 }
 
+function formatProjectClassificationForPlanning(classification: ProjectClassification): string {
+  const sampleFiles = classification.contentFiles.slice(0, 8);
+  const sample = sampleFiles.length > 0 ? sampleFiles.map((file) => `\`${file}\``).join(", ") : "(none)";
+  const lines = [
+    "### Project Classification",
+    "",
+    `- **Kind:** ${classification.kind}`,
+    `- **Content files:** ${classification.contentFiles.length}`,
+    `- **Sample files:** ${sample}`,
+    `- **Reason:** ${classification.reason}`,
+    "",
+  ];
+
+  if (classification.kind === "untyped-existing") {
+    if (classification.contentFiles.length <= 2) {
+      lines.push(
+        "**Workflow sizing:** This is a tiny existing untyped project. Prefer exactly one slice unless the milestone request clearly spans multiple independent user-visible capabilities.",
+      );
+    } else if (classification.contentFiles.length <= 5) {
+      lines.push(
+        "**Workflow sizing:** This is a small existing untyped project. Prefer 1-2 slices unless the milestone request clearly spans multiple independent user-visible capabilities.",
+      );
+    } else {
+      lines.push(
+        "**Workflow sizing:** Existing untyped project. Use generic file-level workflow guidance and size slices by real capability boundaries, not by missing tooling markers.",
+      );
+    }
+  } else if (classification.kind === "greenfield") {
+    lines.push("**Workflow sizing:** No project content exists yet. Use normal greenfield sizing for the requested scope.");
+  } else if (classification.kind === "typed-existing") {
+    lines.push("**Workflow sizing:** Known project markers exist. Use normal ecosystem-aware planning guidance.");
+  } else {
+    lines.push("**Workflow sizing:** Invalid repository state. Planning should surface this as a blocker rather than inventing project structure.");
+  }
+
+  return lines.join("\n");
+}
+
+function normalizeArtifactRef(value: string): string {
+  return value.trim().replace(/^[-\s]+/, "").replace(/^["'`]+|["'`]+$/g, "").replaceAll("\\", "/").replace(/^\.\//, "");
+}
+
+function parseCoveredArtifacts(validationContent: string): Set<string> {
+  const covered = new Set<string>();
+  const lines = validationContent.split(/\r?\n/);
+  let inCoveredArtifacts = false;
+  for (const line of lines) {
+    if (/^\s*covered[-_]?artifacts\s*:/i.test(line)) {
+      inCoveredArtifacts = true;
+      const inline = line.split(/covered[-_]?artifacts\s*:/i)[1]?.trim();
+      if (inline && inline !== "[]") {
+        inline.replace(/^\[|\]$/g, "").split(",").map(normalizeArtifactRef).filter(Boolean).forEach((item) => covered.add(item));
+      }
+      continue;
+    }
+    if (!inCoveredArtifacts) continue;
+    if (/^\S/.test(line) && !/^\s*-/.test(line)) break;
+    const item = line.match(/^\s*-\s*(.+)$/)?.[1];
+    if (item) covered.add(normalizeArtifactRef(item));
+  }
+  return covered;
+}
+
+function isValidationFreshOrApplicable(validationContent: string | null, currentArtifacts: string[]): boolean {
+  if (!validationContent) return false;
+  if (!/validation_metadata:/i.test(validationContent)) return false;
+  const coveredArtifacts = parseCoveredArtifacts(validationContent);
+  if (coveredArtifacts.size === 0) return false;
+  return currentArtifacts
+    .map(normalizeArtifactRef)
+    .filter(Boolean)
+    .every((artifact) => coveredArtifacts.has(artifact));
+}
+
+function formatCloseoutReviewInstructions(validationContent: string | null, validationRel: string, currentArtifacts: string[]): string {
+  const verdict = validationContent ? extractVerdict(validationContent) : null;
+  const validationFresh = isValidationFreshOrApplicable(validationContent, currentArtifacts);
+  if (verdict === "pass" && validationFresh) {
+    return [
+      "### Passing Validation Artifact",
+      "",
+      `A passing validation artifact is present at \`${validationRel}\`. Treat it as authoritative for success criteria, requirement coverage, verification classes, and cross-slice integration.`,
+      "",
+      "Do not delegate fresh reviewer/security/tester audits and do not redo the validation evidence review unless the artifact is internally inconsistent with the inlined summaries. Focus this unit on final milestone narrative, learnings, PROJECT/requirements updates, and `gsd_complete_milestone`.",
+    ].join("\n");
+  }
+
+  if (verdict) {
+    return [
+      "### Validation Requires Attention",
+      "",
+      `A validation artifact is present at \`${validationRel}\` with verdict \`${verdict}\`, but it is missing freshness metadata or does not cover current milestone artifacts. Do not treat the milestone as complete unless the issues are resolved and evidence supports completion.`,
+    ].join("\n");
+  }
+
+  return [
+    "### No Passing Validation Artifact",
+    "",
+    `No passing validation artifact was found at \`${validationRel}\`. Use the full closeout review path before completion.`,
+  ].join("\n");
+}
+
 function capPreamble(preamble: string): string {
   // Cap inlined context at min(historical 30K ceiling, scaled inline budget).
   // The ceiling preserves pre-fix behavior for large-window users; the scaled
@@ -1658,6 +1761,8 @@ export async function buildPlanMilestonePrompt(mid: string, midTitle: string, ba
   const researchAnchor = readPhaseAnchor(base, mid, "research-milestone");
   if (researchAnchor) inlined.push(formatAnchorForPrompt(researchAnchor));
 
+  inlined.push(formatProjectClassificationForPlanning(classifyProject(base)));
+
   inlined.push(await inlineFile(contextPath, contextRel, "Milestone Context"));
   const researchInline = await inlineFileOptional(researchPath, researchRel, "Milestone Research");
   if (researchInline) inlined.push(researchInline);
@@ -2348,6 +2453,9 @@ export async function buildCompleteMilestonePrompt(
   const inlineLevel = level ?? resolveInlineLevel();
   const roadmapPath = resolveMilestoneFile(base, mid, "ROADMAP");
   const roadmapRel = relMilestoneFile(base, mid, "ROADMAP");
+  const validationPath = resolveMilestoneFile(base, mid, "VALIDATION");
+  const validationRel = relMilestoneFile(base, mid, "VALIDATION");
+  const validationContent = validationPath ? await loadFile(validationPath) : null;
 
   const inlined: string[] = [];
   inlined.push(await inlineFile(roadmapPath, roadmapRel, "Milestone Roadmap"));
@@ -2389,6 +2497,13 @@ export async function buildCompleteMilestonePrompt(
       `### On-demand Slice Summaries\n\nExcerpted above. Read the full file for any slice when the excerpt's section heads don't carry enough narrative for the milestone summary you're drafting:\n\n${pathList}`,
     );
   }
+  const validationContext = [
+    formatCloseoutReviewInstructions(validationContent, validationRel, [validationRel, roadmapRel, ...summaryRelPaths]),
+  ];
+  if (validationContent) {
+    validationContext.push(`### Milestone Validation\nSource: \`${validationRel}\`\n\n${validationContent.trim()}`);
+  }
+  inlined.unshift(...validationContext);
 
   // Inline root GSD files (skip for minimal — completion can read these if needed)
   if (inlineLevel !== "minimal") {

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

@@ -14,7 +14,7 @@ import { appendEvent } from "./workflow-events.js";
 import { atomicWriteSync } from "./atomic-write.js";
 import { clearParseCache } from "./files.js";
 import { parseRoadmap as parseLegacyRoadmap, parsePlan as parseLegacyPlan } from "./parsers-legacy.js";
-import { isDbAvailable, getTask, getSlice, getSliceTasks, getPendingGates, updateTaskStatus, updateSliceStatus, insertSlice, getMilestone, refreshOpenDatabaseFromDisk } from "./gsd-db.js";
+import { isDbAvailable, getTask, getSlice, getSliceTasks, getPendingGates, updateTaskStatus, updateSliceStatus, insertSlice, getMilestone, refreshOpenDatabaseFromDisk, getCompletedMilestoneTaskFileHints, getMilestoneCommitAttributionShas, recordMilestoneCommitAttribution } from "./gsd-db.js";
 import { isValidationTerminal } from "./state.js";
 import { getErrorMessage } from "./error-utils.js";
 import { logWarning, logError } from "./workflow-logger.js";
@@ -147,15 +147,29 @@ export function hasImplementationArtifacts(basePath: string, milestoneId?: strin
     // milestone commits instead of treating the self-diff as proof of no work.
     if (changedFiles.length === 0) {
       if (milestoneId && currentBranch === integrationBranch) {
-        const tagged = getChangedFilesFromMilestoneTaggedCommits(basePath, milestoneId);
-        if (!tagged.ok) return "unknown";
-        if (tagged.matched) return classifyImplementationFiles(tagged.files);
+        const milestoneEvidence = getChangedFilesFromMilestoneEvidence(basePath, milestoneId);
+        if (!milestoneEvidence.ok) return "unknown";
+        if (milestoneEvidence.matched) return classifyImplementationFiles(milestoneEvidence.files);
       }
       if (currentBranch && currentBranch !== "HEAD") return "absent";
       return "unknown";
     }
 
-    return classifyImplementationFiles(changedFiles);
+    const branchClassification = classifyImplementationFiles(changedFiles);
+    if (branchClassification === "present") return "present";
+
+    // A completing milestone branch can have a non-empty diff containing only
+    // .gsd/ closeout files after implementation commits already landed on the
+    // recorded integration branch. In that topology, the branch diff alone is
+    // insufficient; use the same milestone-tagged evidence fallback as the
+    // self-diff retry path before declaring the milestone implementation-free.
+    if (milestoneId) {
+      const milestoneEvidence = getChangedFilesFromMilestoneEvidence(basePath, milestoneId);
+      if (!milestoneEvidence.ok) return "unknown";
+      if (milestoneEvidence.matched) return classifyImplementationFiles(milestoneEvidence.files);
+    }
+
+    return "absent";
   } catch (e) {
     // Non-fatal — if git operations fail, return unknown so callers can decide
     logWarning("recovery", `implementation artifact check failed: ${(e as Error).message}`);
@@ -185,6 +199,10 @@ function isImplementationPath(file: string): boolean {
   return !file.startsWith(".gsd/") && !file.startsWith(".gsd\\");
 }
 
+function normalizeRepoPath(file: string): string {
+  return file.trim().replace(/\\/g, "/").replace(/^\.\/+/, "");
+}
+
 /**
  * Detect the main/master branch name.
  */
@@ -263,7 +281,7 @@ function getChangedFilesFromMilestoneTaggedCommits(
     "log", "--format=%H%x1f%B%x1e", "HEAD", "--", `.gsd/milestones/${milestoneId}`,
   ]);
   if (!scoped.ok) return scoped;
-  if (scoped.matched) return scoped;
+  if (scoped.matched && classifyImplementationFiles(scoped.files) === "present") return scoped;
 
   // Fallback (#5033): when .gsd/ is gitignored / external / untracked, the
   // path-scoped scan matches no commits even though GSD-tagged commits
@@ -274,9 +292,137 @@ function getChangedFilesFromMilestoneTaggedCommits(
   // Intentionally unbounded — symmetric with the primary scan, and avoids
   // reintroducing the rolling-depth failure class removed in #4699 where
   // milestone evidence aged out behind unrelated activity.
-  return scanGsdTaggedCommits(basePath, milestoneId, [
+  const unscoped = scanGsdTaggedCommits(basePath, milestoneId, [
     "log", "--format=%H%x1f%B%x1e", "HEAD",
   ]);
+  if (!unscoped.ok) return scoped.matched ? scoped : unscoped;
+  if (!unscoped.matched) return scoped;
+
+  return {
+    ok: true,
+    matched: true,
+    files: [...new Set([...scoped.files, ...unscoped.files])],
+  };
+}
+
+function getChangedFilesFromMilestoneEvidence(
+  basePath: string,
+  milestoneId: string,
+): { ok: boolean; matched: boolean; files: string[] } {
+  const tagged = getChangedFilesFromMilestoneTaggedCommits(basePath, milestoneId);
+  if (!tagged.ok) return tagged;
+  if (tagged.matched && classifyImplementationFiles(tagged.files) === "present") return tagged;
+
+  const attributed = getChangedFilesFromAttributedMilestoneCommits(basePath, milestoneId);
+  if (!attributed.ok) return tagged.matched ? tagged : attributed;
+  if (attributed.matched && classifyImplementationFiles(attributed.files) === "present") return attributed;
+
+  const backfilled = backfillChangedFilesFromUntaggedMilestoneCommits(basePath, milestoneId);
+  if (!backfilled.ok) return tagged.matched ? tagged : attributed.matched ? attributed : backfilled;
+  if (!backfilled.matched) {
+    if (tagged.matched) return tagged;
+    return attributed.matched ? attributed : backfilled;
+  }
+
+  return {
+    ok: true,
+    matched: true,
+    files: [...new Set([...tagged.files, ...attributed.files, ...backfilled.files])],
+  };
+}
+
+function getChangedFilesFromAttributedMilestoneCommits(
+  basePath: string,
+  milestoneId: string,
+): { ok: boolean; matched: boolean; files: string[] } {
+  try {
+    const shas = getMilestoneCommitAttributionShas(milestoneId);
+    if (shas.length === 0) return { ok: true, matched: false, files: [] };
+
+    const files = new Set<string>();
+    let matched = false;
+    for (const sha of shas) {
+      if (!isFullCommitSha(sha)) continue;
+      const commitFiles = getChangedFilesForCommit(basePath, sha);
+      if (commitFiles.length === 0) continue;
+      matched = true;
+      for (const file of commitFiles) files.add(file);
+    }
+    return { ok: true, matched, files: [...files] };
+  } catch (e) {
+    logWarning("recovery", `milestone attribution scan failed: ${(e as Error).message}`);
+    return { ok: false, matched: false, files: [] };
+  }
+}
+
+function backfillChangedFilesFromUntaggedMilestoneCommits(
+  basePath: string,
+  milestoneId: string,
+): { ok: boolean; matched: boolean; files: string[] } {
+  try {
+    const milestone = getMilestone(milestoneId);
+    const milestoneStartedAt = milestone?.created_at ? Math.floor(Date.parse(milestone.created_at) / 1000) * 1000 : NaN;
+    if (!Number.isFinite(milestoneStartedAt)) return { ok: true, matched: false, files: [] };
+
+    const taskFileHints = getCompletedMilestoneTaskFileHints(milestoneId);
+    if (taskFileHints.length === 0) return { ok: true, matched: false, files: [] };
+
+    const hintSet = new Set(taskFileHints.map(normalizeRepoPath).filter(Boolean));
+    if (hintSet.size === 0) return { ok: true, matched: false, files: [] };
+
+    const records = getCommitRecords(basePath);
+    const files = new Set<string>();
+    let matched = false;
+    for (const record of records) {
+      if (!isFullCommitSha(record.hash)) continue;
+      if (Date.parse(record.committedAt) < milestoneStartedAt) continue;
+      if (record.parents.trim().split(/\s+/).filter(Boolean).length > 1) continue;
+      if (commitMessageHasGsdTrailer(record.message)) continue;
+
+      const commitFiles = getChangedFilesForCommit(basePath, record.hash);
+      const implementationFiles = commitFiles.map(normalizeRepoPath).filter(isImplementationPath);
+      if (implementationFiles.length === 0) continue;
+      if (!implementationFiles.some((file) => hintSet.has(file))) continue;
+
+      matched = true;
+      for (const file of implementationFiles) files.add(file);
+      recordMilestoneCommitAttribution({
+        commitSha: record.hash,
+        milestoneId,
+        source: "backfill",
+        confidence: 0.8,
+        files: implementationFiles,
+        createdAt: new Date().toISOString(),
+      });
+    }
+
+    return { ok: true, matched, files: [...files] };
+  } catch (e) {
+    logWarning("recovery", `milestone attribution backfill failed: ${(e as Error).message}`);
+    return { ok: false, matched: false, files: [] };
+  }
+}
+
+function getCommitRecords(basePath: string): Array<{ hash: string; parents: string; committedAt: string; message: string }> {
+  const logOutput = execFileSync("git", ["log", "--format=%H%x1f%P%x1f%cI%x1f%B%x1e", "HEAD"], {
+    cwd: basePath,
+    stdio: ["ignore", "pipe", "pipe"],
+    encoding: "utf-8",
+  });
+  return logOutput
+    .split("\x1e")
+    .map((record) => record.trim())
+    .filter(Boolean)
+    .flatMap((record) => {
+      const parts = record.split("\x1f");
+      if (parts.length < 4) return [];
+      const [hash, parents, committedAt, ...messageParts] = parts;
+      return [{ hash: hash.trim(), parents: parents.trim(), committedAt: committedAt.trim(), message: messageParts.join("\x1f") }];
+    });
+}
+
+function isFullCommitSha(value: string): boolean {
+  return /^[0-9a-f]{40}$/i.test(value);
 }
 
 function scanGsdTaggedCommits(

package/src/resources/extensions/gsd/auto-start.ts

@@ -664,12 +664,13 @@ export async function bootstrapAutoSession(
     }
 
     const effectivePrefs = loadEffectiveGSDPreferences(base)?.preferences;
-    const deepProjectStagePending = !hasSurvivorBranch
-      ? (await import("./auto-dispatch.js")).hasPendingDeepStage(
-          effectivePrefs,
-          base,
-        )
-      : false;
+    const { shouldRunDeepProjectSetup } = await import("./auto-dispatch.js");
+    const deepProjectStagePending = shouldRunDeepProjectSetup(
+      state,
+      effectivePrefs,
+      base,
+      { hasSurvivorBranch },
+    );
 
     if (deepProjectStagePending) {
       // Deep project-level setup runs before the first milestone exists. Let

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

@@ -420,6 +420,17 @@ export function _synthesizePausedSessionRecoveryForTest(
   return synthesizePausedSessionRecovery(basePath, unitType, unitId, sessionFile);
 }
 
+const DETACHED_AUTO_KEEPALIVE_INTERVAL_MS = 30_000;
+
+function withDetachedAutoKeepalive<T>(run: Promise<T>): Promise<T> {
+  const keepAlive = setInterval(() => {}, DETACHED_AUTO_KEEPALIVE_INTERVAL_MS);
+  return run.finally(() => {
+    clearInterval(keepAlive);
+  });
+}
+
+export const _withDetachedAutoKeepaliveForTest = withDetachedAutoKeepalive;
+
 export function startAutoDetached(
   ctx: ExtensionCommandContext,
   pi: ExtensionAPI,
@@ -431,7 +442,7 @@ export function startAutoDetached(
     milestoneLock?: string | null;
   },
 ): void {
-  void startAuto(ctx, pi, base, verboseMode, options).catch((err) => {
+  void withDetachedAutoKeepalive(startAuto(ctx, pi, base, verboseMode, options)).catch((err) => {
     const message = getErrorMessage(err);
     ctx.ui.notify(`Auto-start failed: ${message}`, "error");
     logWarning("engine", `auto start error: ${message}`, { file: "auto.ts" });

package/src/resources/extensions/gsd/bootstrap/agent-end-recovery.ts

@@ -1,3 +1,5 @@
+// GSD-2 + src/resources/extensions/gsd/bootstrap/agent-end-recovery.ts - Handles provider and agent-end recovery for GSD auto-mode.
+
 import type { ExtensionAPI, ExtensionContext } from "@gsd/pi-coding-agent";
 
 import { logWarning } from "../workflow-logger.js";
@@ -12,7 +14,7 @@ import { clearPathCache } from "../paths.js";
 import { getAutoDashboardData, getAutoModeStartModel, isAutoActive, pauseAuto, setCurrentDispatchedModelId } from "../auto.js";
 import { getNextFallbackModel, resolveModelWithFallbacksForUnit } from "../preferences.js";
 import { pauseAutoForProviderError } from "../provider-error-pause.js";
-import { isSessionSwitchInFlight, resolveAgentEnd } from "../auto/resolve.js";
+import { isSessionSwitchInFlight, resolveAgentEnd, resolveAgentEndCancelled } from "../auto/resolve.js";
 import { resolveModelId } from "../auto-model-selection.js";
 import { resolveProjectRoot } from "../worktree.js";
 import { clearDiscussionFlowState } from "./write-gate.js";
@@ -69,6 +71,11 @@ export function _buildAbortedPauseContext(lastMsg: { errorMessage?: unknown }):
   };
 }
 
+export function isUserInitiatedAbortMessage(message: string | undefined | null): boolean {
+  if (!message) return false;
+  return /\b(?:claude code process aborted by user|request aborted by user|process aborted by user)\b/i.test(message);
+}
+
 async function pauseTransientWithBackoff(
   cls: ErrorClass,
   pi: ExtensionAPI,
@@ -180,6 +187,14 @@ export async function handleAgentEnd(
     // is in the assistant message text content. Fall back to content when
     // errorMessage looks uninformative.
     const rawErrorMsg = ("errorMessage" in lastMsg && lastMsg.errorMessage) ? String(lastMsg.errorMessage) : "";
+    if (isUserInitiatedAbortMessage(rawErrorMsg)) {
+      resolveAgentEndCancelled({
+        message: rawErrorMsg,
+        category: "aborted",
+        isTransient: false,
+      });
+      return;
+    }
     const isUseless = !rawErrorMsg || /^(success|ok|true|error|unknown)$/i.test(rawErrorMsg.trim());
     // #3588: When errorMessage is uninformative, extract the real error from
     // the assistant message text content for display purposes only.

package/src/resources/extensions/gsd/bootstrap/register-hooks.ts

@@ -7,7 +7,7 @@ import type { GSDEcosystemBeforeAgentStartHandler } from "../ecosystem/gsd-exten
 import { updateSnapshot } from "../ecosystem/gsd-extension-api.js";
 
 import { buildMilestoneFileName, resolveMilestonePath, resolveSliceFile, resolveSlicePath } from "../paths.js";
-import { canonicalToolName, clearDiscussionFlowState, isDepthConfirmationAnswer, isQueuePhaseActive, markApprovalGateVerified, markDepthVerified, resetWriteGateState, shouldBlockContextWrite, shouldBlockPlanningUnit, shouldBlockQueueExecution, isGateQuestionId, setPendingGate, clearPendingGate, getPendingGate, shouldBlockPendingGate, shouldBlockPendingGateBash, extractDepthVerificationMilestoneId } from "./write-gate.js";
+import { canonicalToolName, clearDiscussionFlowState, isDepthConfirmationAnswer, isQueuePhaseActive, markApprovalGateVerified, markDepthVerified, resetWriteGateState, shouldBlockContextWrite, shouldBlockPlanningUnit, shouldBlockQueueExecution, shouldBlockWorktreeWrite, isGateQuestionId, setPendingGate, clearPendingGate, getPendingGate, shouldBlockPendingGate, shouldBlockPendingGateBash, extractDepthVerificationMilestoneId } from "./write-gate.js";
 import { resolveManifest } from "../unit-context-manifest.js";
 import { isBlockedStateFile, isBashWriteToStateFile, BLOCKED_WRITE_ERROR } from "../write-intercept.js";
 import { loadFile, saveFile, formatContinue } from "../files.js";
@@ -482,6 +482,22 @@ export function registerHooks(
       }
     }
 
+    // ── Worktree-isolation write gate (#5199) ────────────────────────────
+    // Block planning-write tools from landing code at the project root when
+    // git.isolation=worktree but auto-mode hasn't created the milestone
+    // worktree yet. Without this, writes silently orphan outside git history.
+    if (isToolCallEventType("write", event) || isToolCallEventType("edit", event)) {
+      const wtBasePath = resolveWorktreeProjectRoot(dash.basePath ?? discussionBasePath);
+      const wtGuard = shouldBlockWorktreeWrite(
+        event.toolName,
+        event.input.path,
+        wtBasePath,
+        isAutoActive(),
+        dash.currentUnit?.type,
+      );
+      if (wtGuard.block) return wtGuard;
+    }
+
     // ── Single-writer engine: block direct writes to STATE.md ──────────
     // Covers write, edit, and bash tools to prevent bypass vectors.
     if (isToolCallEventType("write", event)) {