gsd-pi 2.66.1-dev.ed243f2 → 2.67.0

package/src/resources/extensions/gsd/parallel-monitor-overlay.ts

@@ -490,6 +490,8 @@ export class ParallelMonitorOverlay {
 
     // Apply scroll — use terminal rows as height estimate
     const termHeight = process.stdout.rows || 40;
+    const maxScroll = Math.max(0, lines.length - termHeight);
+    this.scrollOffset = Math.min(Math.max(this.scrollOffset, 0), maxScroll);
     const visible = lines.slice(this.scrollOffset, this.scrollOffset + termHeight);
     this.cachedLines = visible;
     return visible;

package/src/resources/extensions/gsd/parsers-legacy.ts

@@ -210,7 +210,9 @@ function _parsePlanImpl(content: string): SlicePlan {
     for (const line of lines) {
       const cbMatch = line.match(/^-\s+\[([ xX])\]\s+\*\*([\w.]+):\s+(.+?)\*\*\s*(.*)/);
       // Heading-style: ### T01 -- Title, ### T01: Title, ### T01 — Title
-      const hdMatch = !cbMatch ? line.match(/^#{2,4}\s+([\w.]+)\s*(?:--|—|:)\s*(.+)/) : null;
+      const hdMatch = !cbMatch
+        ? line.match(/^#{2,4}\s+([A-Z]+\d+(?:\.[A-Z]+\d+)*)\s*(?:--|—|:)\s*(.+)/)
+        : null;
       if (cbMatch || hdMatch) {
         const taskId = cbMatch ? cbMatch[2] : hdMatch![1];
         // Skip tasks already found in the Tasks section

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

@@ -200,11 +200,13 @@ function loadPreferencesFile(path: string, scope: "global" | "project"): LoadedG
 }
 
 let _warnedUnrecognizedFormat = false;
+let _warnedSectionParse = false;
 
 /** @internal Reset the warn-once flags — exported for testing only. */
 export function _resetParseWarningFlag(): void {
   _warnedUnrecognizedFormat = false;
   _warnedFrontmatterParse = false;
+  _warnedSectionParse = false;
 }
 
 /** @internal Exported for testing only */
@@ -309,7 +311,10 @@ function parseHeadingListFormat(content: string): GSDPreferences {
 
       typed[targetSection] = value;
     } catch (e) {
-      logWarning("guided", `preferences section parse failed: ${(e as Error).message}`);
+      if (!_warnedSectionParse) {
+        _warnedSectionParse = true;
+        logWarning("guided", `preferences section parse failed: ${(e as Error).message}`);
+      }
     }
   }
 

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

@@ -63,6 +63,6 @@ Then:
 13. Do not commit manually — the system auto-commits your changes after this unit completes.
 - Say: "Milestone {{milestoneId}} complete."
 
-**Important:** Do NOT skip the code change verification, success criteria, or definition of done verification (steps 3-5). The milestone summary must reflect actual verified outcomes, not assumed success. Verification failures BLOCK completion — there is no override. The milestone stays in its current state until issues are resolved and verification is re-run.
+**Important:** Do NOT skip the code change verification, success criteria, or definition of done verification (steps 3-5). The milestone summary must reflect actual verified outcomes, not assumed success. Verification failures BLOCK completion — there is no override. The milestone stays in its current state until issues are resolved and verification is re-run. **If a verification tool itself fails, errors, or returns unexpected output, treat it as a verification failure** — never rationalize past a tool error ("tool didn't respond, assuming success" is forbidden). A tool that cannot verify is a tool that did not verify.
 
 **File system safety:** When scanning milestone directories for evidence, use `ls` or `find` to list directory contents first — never pass a directory path (e.g. `tasks/`, `slices/`) directly to the `read` tool. The `read` tool only accepts file paths, not directories.

package/src/resources/extensions/gsd/prompts/discuss-prepared.md

@@ -109,7 +109,7 @@ Options:
   - "Needs adjustment" — user will clarify, then re-present scope
 ```
 
-**Do NOT proceed to Layer 2 until the user explicitly approves the scope.**
+**CRITICAL — Non-bypassable gate:** Do NOT proceed to Layer 2 until the user explicitly approves the scope. If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block. "Tool not responding, I'll proceed," "auth issues," or "I'll use my recommended scope" are all **forbidden**. The gate exists to protect the user's work; treat a block as an instruction to wait, not an obstacle to work around.
 
 ---
 
@@ -120,7 +120,7 @@ Before presenting Layer 2 findings, use your available web search tools to resea
 1. Search for "[technology] [version] best practices [current year]"
 2. Search for "[technology] [version] known issues"
 
-Summarize findings concisely. If no search tools are available, note this and proceed using your training knowledge — don't block the discussion on missing search results.
+Summarize findings concisely. If search tools fail or are unavailable, note this and proceed using your training knowledge — but do NOT use a search failure as justification to skip any gate.
 
 Present ecosystem findings at the start of Layer 2 alongside your architecture recommendation.
 
@@ -180,7 +180,7 @@ Options:
   - "Want to adjust" — user will clarify, then re-present architecture
 ```
 
-**Do NOT proceed to Layer 3 until the user explicitly approves the architecture.**
+**CRITICAL — Non-bypassable gate:** Do NOT proceed to Layer 3 until the user explicitly approves the architecture. If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block. The gate exists to protect the user's work; treat a block as an instruction to wait, not an obstacle to work around.
 
 ---
 
@@ -243,7 +243,7 @@ Options:
   - "Want to adjust error handling" — user will clarify, then re-present errors
 ```
 
-**Do NOT proceed to Layer 4 until the user explicitly approves error handling.**
+**CRITICAL — Non-bypassable gate:** Do NOT proceed to Layer 4 until the user explicitly approves error handling. If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block. The gate exists to protect the user's work; treat a block as an instruction to wait, not an obstacle to work around.
 
 ---
 
@@ -297,7 +297,7 @@ Options:
   - "Want to adjust the quality bar" — user will clarify, then re-present quality
 ```
 
-**Do NOT proceed to Output Phase until the user explicitly approves the quality bar.**
+**CRITICAL — Non-bypassable gate:** Do NOT proceed to Output Phase until the user explicitly approves the quality bar. If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block. The gate exists to protect the user's work; treat a block as an instruction to wait, not an obstacle to work around.
 
 ---
 
@@ -315,13 +315,13 @@ Before writing a roadmap, produce or update `.gsd/REQUIREMENTS.md`.
 
 Use it as the project's explicit capability contract. Requirements discovered during the 4-layer discussion should be captured here with source `user` or `inferred` as appropriate.
 
-**Print the requirements in chat before writing the roadmap.** Print a markdown table with columns: ID, Title, Status, Owner, Source. Group by status (Active, Deferred, Out of Scope). After the table, ask: "Confirm, adjust, or add?"
+**Print the requirements in chat before writing the roadmap.** Print a markdown table with columns: ID, Title, Status, Owner, Source. Group by status (Active, Deferred, Out of Scope). After the table, ask: "Confirm, adjust, or add?" **Non-bypassable:** If the user does not respond or gives an ambiguous answer, you MUST re-ask — never proceed to roadmap creation without explicit requirement confirmation.
 
 ### Roadmap Preview
 
 Before writing any files, **print the planned roadmap in chat** so the user can see and approve it. Print a markdown table with columns: Slice, Title, Risk, Depends, Demo. One row per slice. Below the table, print the milestone definition of done as a bullet list.
 
-If the user raises a substantive objection, adjust the roadmap. Otherwise, present the roadmap and ask: "Ready to write, or want to adjust?" — one gate, not two.
+If the user raises a substantive objection, adjust the roadmap. Otherwise, present the roadmap and ask: "Ready to write, or want to adjust?" — one gate, not two. **Non-bypassable:** If the user does not respond or gives an ambiguous answer, you MUST re-ask — never write files without explicit approval. A missing response is not a "yes."
 
 ### Naming Convention
 

package/src/resources/extensions/gsd/prompts/discuss.md

@@ -173,7 +173,7 @@ For multi-milestone projects, requirements should span the full vision. Requirem
 
 If the project is new or has no `REQUIREMENTS.md`, surface candidate requirements in chat before writing the roadmap. Ask for correction only on material omissions, wrong ownership, or wrong scope. If the user has already been specific and raises no substantive objection, treat the requirement set as confirmed and continue.
 
-**Print the requirements in chat before writing the roadmap.** Do not say "here are the requirements" and then only write them to a file. The user must see them in the terminal. Print a markdown table with columns: ID, Title, Status, Owner, Source. Group by status (Active, Deferred, Out of Scope). After the table, ask: "Confirm, adjust, or add?"
+**Print the requirements in chat before writing the roadmap.** Do not say "here are the requirements" and then only write them to a file. The user must see them in the terminal. Print a markdown table with columns: ID, Title, Status, Owner, Source. Group by status (Active, Deferred, Out of Scope). After the table, ask: "Confirm, adjust, or add?" **Non-bypassable:** If the user does not respond or gives an ambiguous answer, you MUST re-ask — never proceed to roadmap creation without explicit requirement confirmation.
 
 ## Scope Assessment
 
@@ -185,7 +185,7 @@ Before moving to output, confirm the size estimate from your reflection still ho
 
 Before writing any files, **print the planned roadmap in chat** so the user can see and approve it. Print a markdown table with columns: Slice, Title, Risk, Depends, Demo. One row per slice. Below the table, print the milestone definition of done as a bullet list.
 
-If the user raises a substantive objection, adjust the roadmap. Otherwise, present the roadmap and ask: "Ready to write, or want to adjust?" — one gate, not two.
+If the user raises a substantive objection, adjust the roadmap. Otherwise, present the roadmap and ask: "Ready to write, or want to adjust?" — one gate, not two. **Non-bypassable:** If the user does not respond or gives an ambiguous answer, you MUST re-ask — never write files without explicit approval. A missing response is not a "yes."
 
 ### Naming Convention
 
@@ -242,7 +242,7 @@ If a milestone has no dependencies, omit the frontmatter. The dependency chain f
 
 #### Phase 3: Sequential readiness gate for remaining milestones
 
-For each remaining milestone **one at a time, in sequence**, decide the most likely readiness mode from the evidence you already have, then use `ask_user_questions` to let the user correct that recommendation. Present three options:
+For each remaining milestone **one at a time, in sequence**, decide the most likely readiness mode from the evidence you already have, then use `ask_user_questions` to let the user correct that recommendation. **Non-bypassable:** If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block or auto-select a readiness mode. Present three options:
 
 - **"Discuss now"** — The user wants to conduct a focused discussion for this milestone in the current session, while the context from the broader discussion is still fresh. Proceed with a focused discussion for this milestone (reflection → investigation → questioning → depth verification). When the discussion concludes, write a full `CONTEXT.md`. Then move to the gate for the next milestone.
 - **"Write draft for later"** — This milestone has seed material from the current conversation but needs its own dedicated discussion in a future session. Write a `CONTEXT-DRAFT.md` capturing the seed material (what was discussed, key ideas, provisional scope, open questions). Mark it clearly as a draft, not a finalized context. **What happens downstream:** When auto-mode reaches this milestone, it pauses and notifies the user: "M00x has draft context — needs discussion. Run /gsd." The `/gsd` wizard shows a "Discuss from draft" option that seeds the new discussion with this draft, so nothing from the current conversation is lost. After the dedicated discussion produces a full CONTEXT.md, the draft file is automatically deleted.

package/src/resources/extensions/gsd/prompts/guided-discuss-milestone.md

@@ -92,15 +92,15 @@ Before moving to the wrap-up gate, verify you have covered:
 - header: "Depth Check"
 - question: "Did I capture the depth right?"
 - options: "Yes, you got it (Recommended)", "Not quite — let me clarify"
-- **The question ID must contain `depth_verification`** (e.g. `depth_verification_confirm`) — this enables the write-gate downstream.
+- **The question ID must contain `depth_verification` and the milestone id** (e.g. `depth_verification_{{milestoneId}}_confirm`) — this enables the write-gate downstream and keeps verification scoped to the milestone being discussed.
 
-**If `{{structuredQuestionsAvailable}}` is `false`:** ask in plain text: "Did I capture that correctly? If not, tell me what I missed." Wait for confirmation before proceeding.
+**If `{{structuredQuestionsAvailable}}` is `false`:** ask in plain text: "Did I capture that correctly? If not, tell me what I missed." Wait for explicit confirmation before proceeding. **The same non-bypassable gate applies to the plain-text path** — if the user does not respond, gives an ambiguous answer, or does not explicitly confirm, you MUST re-ask. Never rationalize past a missing confirmation.
 
 If they clarify, absorb the correction and re-verify.
 
 The depth verification is the only required confirmation gate. Do not add a second "ready to proceed?" gate after it.
 
-**CRITICAL — Non-bypassable gate:** The system mechanically blocks CONTEXT.md writes until the user selects the "(Recommended)" option. If the user declines, cancels, or the tool fails, you MUST re-ask — never rationalize past the block ("tool not responding, I'll proceed" is forbidden). The gate exists to protect the user's work; treat a block as an instruction, not an obstacle to work around.
+**CRITICAL — Non-bypassable gate:** The system mechanically blocks CONTEXT.md writes until the user selects the "(Recommended)" option (structured path) or explicitly confirms (plain-text path). If the user declines, cancels, does not respond, or the tool fails, you MUST re-ask — never rationalize past the block ("tool not responding, I'll proceed" is forbidden). The gate exists to protect the user's work; treat a block as an instruction, not an obstacle to work around.
 
 ---
 

package/src/resources/extensions/gsd/prompts/guided-discuss-slice.md

@@ -41,11 +41,13 @@ After each round of answers, decide whether you already have enough signal to wr
 - Ask a single wrap-up question only when you genuinely believe the slice is well understood or the user signals they want to stop.
 - When you do ask it, offer two choices: "Write the context file" *(recommended when the slice is well understood)* or "One more pass". Use `ask_user_questions` if available, otherwise ask in plain text.
 
+**CRITICAL — Non-bypassable gate:** Do NOT write the context file until the user explicitly selects "Write the context file." If `ask_user_questions` fails, errors, returns no response, or the user's response does not match a provided option, you MUST re-ask — never rationalize past the block. "Tool not responding, I'll proceed," "auth issues," or "the slice seems well understood, I'll write it" are all **forbidden**. The gate exists to protect the user's work; treat a block as an instruction to wait, not an obstacle to work around.
+
 ---
 
 ## Output
 
-Once the user is ready to wrap up:
+Once the user has explicitly confirmed they are ready to write the context file:
 
 1. Use the **Slice Context** output template below
 2. `mkdir -p {{sliceDirPath}}`

package/src/resources/extensions/gsd/prompts/rethink.md

@@ -12,7 +12,7 @@ You are a project reorganization assistant for a GSD (Get Shit Done) project. Th
 
 1. Present the current milestone order as a clear numbered list with status indicators (e.g. ✅ complete, ▶ active, ⏳ pending, ⏸ parked)
 2. Ask: **"What would you like to change?"**
-3. Execute changes conversationally, confirming destructive operations before proceeding
+3. Execute changes conversationally, confirming destructive operations before proceeding. **Non-bypassable:** For any destructive operation (discard, skip, reorder that breaks dependencies), you MUST get explicit user confirmation before executing. If the user does not respond, gives an ambiguous answer, or `ask_user_questions` fails, you MUST re-ask — never rationalize past the block. A missing confirmation is a "do not proceed."
 
 ## Supported Operations
 
@@ -53,8 +53,12 @@ gsd_skip_slice({ milestoneId: "M003", sliceId: "S02", reason: "Descoped — feat
 Skipped slices are treated as closed by the state machine (like "complete" but distinct). Use when a slice is no longer needed or has been superseded. The slice data is preserved for reference.
 **Do NOT** just check the slice checkbox in the roadmap — this does not update the DB and auto-mode will resume the slice.
 
+**CRITICAL — Non-bypassable gate:** Skipping a slice is a permanent DB operation. You MUST confirm with the user before calling `gsd_skip_slice`. If the user does not respond or gives an ambiguous answer, you MUST re-ask — never proceed without explicit approval.
+
 ### Discard a milestone
-**Permanently** delete a milestone directory and prune it from QUEUE-ORDER.json. **Always confirm with the user before discarding.** Warn explicitly if the milestone has completed work.
+**Permanently** delete a milestone directory and prune it from QUEUE-ORDER.json.
+
+**CRITICAL — Non-bypassable gate:** Discarding is irreversible. You MUST confirm with the user before discarding. Warn explicitly if the milestone has completed work. If the user does not respond or gives an ambiguous answer, you MUST re-ask — never rationalize past the block. A missing confirmation is a "do not discard."
 
 ### Add a new milestone
 Use the `gsd_milestone_generate_id` tool to get the next ID, then call `gsd_summary_save` with `milestone_id: {ID}`, `artifact_type: "CONTEXT"`, and the scope/goals/success criteria as `content` — the tool writes the context file to disk and persists to DB. Update QUEUE-ORDER.json to place it at the desired position.

package/src/resources/extensions/gsd/prompts/system.md

@@ -38,7 +38,7 @@ GSD ships with bundled skills. Load the relevant skill file with the `read` tool
 - Never print, echo, log, or restate secrets or credentials. Report only key names and applied/skipped status.
 - Never ask the user to edit `.env` files or set secrets manually. Use `secure_env_collect`.
 - In enduring files, write current state only unless the file is explicitly historical.
-- **Never take outward-facing actions on GitHub (or any external service) without explicit user confirmation.** This includes: creating issues, closing issues, merging PRs, approving PRs, posting comments, pushing to remote branches, publishing packages, or any other action that affects state outside the local filesystem. Read-only operations (listing, viewing, diffing) are fine. Always present what you intend to do and get a clear "yes" before executing.
+- **Never take outward-facing actions on GitHub (or any external service) without explicit user confirmation.** This includes: creating issues, closing issues, merging PRs, approving PRs, posting comments, pushing to remote branches, publishing packages, or any other action that affects state outside the local filesystem. Read-only operations (listing, viewing, diffing) are fine. Always present what you intend to do and get a clear "yes" before executing. **Non-bypassable:** If the user does not respond, gives an ambiguous answer, or `ask_user_questions` fails, you MUST re-ask — never rationalize past the block ("tool not responding, I'll proceed" is forbidden). A missing "yes" is a "no."
 
 If a `GSD Skill Preferences` block is present below this contract, treat it as explicit durable guidance for which skills to use, prefer, or avoid during GSD work. Follow it where it does not conflict with required GSD artifact rules, verification requirements, or higher-priority system/developer instructions.
 

package/src/resources/extensions/gsd/prompts/triage-captures.md

@@ -51,7 +51,7 @@ For each capture, classify it as one of:
    
    For captures classified as **note** or **defer**, auto-confirm without asking — these are low-impact.
    For captures classified as **stop** or **backtrack**, auto-confirm without asking — these are urgent user directives that must be honored immediately.
-   For captures classified as **quick-task**, **inject**, or **replan**, ask the user to confirm or choose a different classification.
+   For captures classified as **quick-task**, **inject**, or **replan**, ask the user to confirm or choose a different classification. **Non-bypassable:** If `ask_user_questions` fails, errors, or the user does not respond, you MUST re-ask — never auto-confirm these classifications without explicit user approval.
 
 3. **Update** `.gsd/CAPTURES.md` — for each capture, update its section with the confirmed classification:
    - Change `**Status:** pending` to `**Status:** resolved`

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

@@ -14,7 +14,7 @@ This is remediation round {{remediationRound}}. If this is round 0, this is the
 
 ## Context
 
-All relevant context has been preloaded below — the roadmap, all slice summaries, UAT results, requirements, decisions, and project context are inlined. Start working immediately without re-reading these files.
+All relevant context has been preloaded below — the roadmap, all slice summaries, assessment results, requirements, decisions, and project context are inlined. Start working immediately without re-reading these files.
 
 {{inlinedContext}}
 
@@ -30,8 +30,8 @@ Prompt: "Review milestone {{milestoneId}} requirements coverage. Working directo
 **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, check that the producing slice's SUMMARY confirms it produced the artifact, and the consuming slice's SUMMARY confirms it consumed it. Output a markdown table: Boundary | Producer Summary | Consumer Summary | Status. End with a one-line verdict: PASS if all boundaries honored, NEEDS-ATTENTION if any gaps."
 
-**Reviewer C — UAT & Acceptance Criteria**
-Prompt: "Review milestone {{milestoneId}} UAT and acceptance criteria. Working directory: {{workingDirectory}}. Read `.gsd/{{milestoneId}}/CONTEXT.md` for acceptance criteria. Check for UAT-RESULT files in each slice directory. Verify each acceptance criterion maps to either a passing UAT result or clear SUMMARY evidence. Output a checklist: [ ] Criterion | Evidence. End with a one-line verdict: PASS if all criteria met, NEEDS-ATTENTION if gaps exist."
+**Reviewer C — Assessment & Acceptance Criteria**
+Prompt: "Review milestone {{milestoneId}} assessment evidence and acceptance criteria. Working directory: {{workingDirectory}}. Read `.gsd/{{milestoneId}}/CONTEXT.md` for acceptance criteria. Check for ASSESSMENT files in each slice directory. Verify each acceptance criterion maps to either a passing assessment result or clear SUMMARY evidence. Output a checklist: [ ] Criterion | Evidence. End with a one-line verdict: PASS if all criteria met, NEEDS-ATTENTION if gaps exist."
 
 ### Step 2 — Synthesize Findings
 
@@ -59,7 +59,7 @@ reviewers: 3
 ## Reviewer B — Cross-Slice Integration
 <paste Reviewer B output>
 
-## Reviewer C — UAT & Acceptance Criteria
+## Reviewer C — Assessment & Acceptance Criteria
 <paste Reviewer C output>
 
 ## Synthesis

package/src/resources/extensions/gsd/prompts/worktree-merge.md

@@ -90,9 +90,11 @@ Present a merge plan to the user:
 
 Ask the user to confirm the merge plan before proceeding.
 
+**CRITICAL — Non-bypassable gate:** Do NOT execute any merge commands until the user explicitly approves the merge plan. If `ask_user_questions` fails, errors, returns no response, or the user's response is ambiguous, you MUST re-ask — never rationalize past the block. "No response, I'll proceed with the clean merges," "the plan looks safe, merging," or any other self-authorization is **forbidden**. The gate exists to protect the user's branches; treat a block as an instruction to wait, not an obstacle to work around.
+
 ### Step 4: Execute Merge
 
-Once confirmed, run all commands from `{{mainTreePath}}` (your CWD):
+Once the user has explicitly confirmed, run all commands from `{{mainTreePath}}` (your CWD):
 
 1. Ensure you are on the target branch: `git checkout {{mainBranch}}`
 2. If there are conflicts requiring manual reconciliation, apply the reconciled versions first

package/src/resources/extensions/gsd/safety/file-change-validator.ts

@@ -10,6 +10,7 @@
  */
 
 import { execFileSync } from "node:child_process";
+import { normalizePlannedFileReference } from "../files.js";
 import { logWarning } from "../workflow-logger.js";
 
 // ─── Types ──────────────────────────────────────────────────────────────────
@@ -57,7 +58,9 @@ export function validateFileChanges(
 
   // Normalize expected paths (strip leading ./ or /)
   const normalizedExpected = new Set(
-    [...allExpected].map(f => f.replace(/^\.\//, "").replace(/^\//, "")),
+    [...allExpected].map((f) =>
+      normalizePlannedFileReference(f).replace(/^\.\//, "").replace(/^\//, ""),
+    ),
   );
 
   // Compute symmetric difference

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

@@ -1317,7 +1317,8 @@ export async function _deriveStateImpl(basePath: string): Promise<GSDState> {
       ? `All milestones complete. ${activeReqs} active requirement${activeReqs === 1 ? '' : 's'} in REQUIREMENTS.md ${activeReqs === 1 ? 'has' : 'have'} not been mapped to a milestone.`
       : 'All milestones complete.';
     return {
-      activeMilestone: lastEntry ? { id: lastEntry.id, title: lastEntry.title } : null,
+      activeMilestone: null,
+      lastCompletedMilestone: lastEntry ? { id: lastEntry.id, title: lastEntry.title } : null,
       activeSlice: null,
       activeTask: null,
       phase: 'complete',

package/src/resources/extensions/gsd/tests/auto-dashboard.test.ts

@@ -1,7 +1,8 @@
 import test from "node:test";
 import assert from "node:assert/strict";
-import { readFileSync } from "node:fs";
+import { mkdirSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
+import { tmpdir } from "node:os";
 
 import {
   unitVerb,
@@ -11,11 +12,29 @@ import {
   formatWidgetTokens,
   estimateTimeRemaining,
   extractUatSliceId,
+  getWidgetMode,
+  cycleWidgetMode,
+  _resetWidgetModeForTests,
 } from "../auto-dashboard.ts";
 
 const autoSource = readFileSync(join(process.cwd(), "src", "resources", "extensions", "gsd", "auto.ts"), "utf-8");
 const dashboardSource = readFileSync(join(process.cwd(), "src", "resources", "extensions", "gsd", "auto-dashboard.ts"), "utf-8");
 
+function makeTempDir(prefix: string): string {
+  return join(
+    tmpdir(),
+    `gsd-auto-dashboard-test-${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`,
+  );
+}
+
+function cleanup(dir: string): void {
+  try {
+    rmSync(dir, { recursive: true, force: true });
+  } catch {
+    // best-effort
+  }
+}
+
 // ─── unitVerb ─────────────────────────────────────────────────────────────
 
 test("unitVerb maps known unit types to verbs", () => {
@@ -209,3 +228,35 @@ test("extractUatSliceId returns null for invalid formats", () => {
   assert.equal(extractUatSliceId(""), null);
   assert.equal(extractUatSliceId("M001/T01"), null);
 });
+
+test("widget mode respects project preference precedence and persists there", (t) => {
+  const homeDir = makeTempDir("home");
+  const projectDir = makeTempDir("project");
+  const globalPrefsPath = join(homeDir, ".gsd", "preferences.md");
+  const projectPrefsPath = join(projectDir, ".gsd", "preferences.md");
+
+  mkdirSync(join(homeDir, ".gsd"), { recursive: true });
+  mkdirSync(join(projectDir, ".gsd"), { recursive: true });
+  writeFileSync(globalPrefsPath, "---\nversion: 1\nwidget_mode: off\n---\n", "utf-8");
+  writeFileSync(projectPrefsPath, "---\nversion: 1\nwidget_mode: small\n---\n", "utf-8");
+
+  t.after(() => {
+    cleanup(homeDir);
+    cleanup(projectDir);
+    _resetWidgetModeForTests();
+  });
+
+  _resetWidgetModeForTests();
+
+  assert.equal(getWidgetMode(projectPrefsPath, globalPrefsPath), "small", "project widget_mode overrides global");
+  assert.equal(
+    cycleWidgetMode(projectPrefsPath, globalPrefsPath),
+    "min",
+    "cycling advances from the project-owned mode",
+  );
+
+  const projectPrefs = readFileSync(projectPrefsPath, "utf-8");
+  const globalPrefs = readFileSync(globalPrefsPath, "utf-8");
+  assert.match(projectPrefs, /widget_mode:\s*min/);
+  assert.match(globalPrefs, /widget_mode:\s*off/);
+});

package/src/resources/extensions/gsd/tests/auto-loop.test.ts

@@ -1,4 +1,4 @@
-import test from "node:test";
+import test, { mock } from "node:test";
 import assert from "node:assert/strict";
 import { readFileSync } from "node:fs";
 import { resolve } from "node:path";
@@ -191,6 +191,54 @@ test("runUnit returns cancelled when session creation times out", async () => {
   assert.equal(pi.calls.length, 0);
 });
 
+test("runUnit keeps the session-switch guard across a late newSession settlement", async () => {
+  _resetPendingResolve();
+  mock.timers.enable();
+
+  try {
+    const ctx = makeMockCtx();
+    const pi = makeMockPi();
+    // Use delays longer than NEW_SESSION_TIMEOUT_MS (120s) so the timeout fires
+    const firstSession = makeMockSession({ newSessionDelayMs: 200_000 });
+    const secondSession = makeMockSession({ newSessionDelayMs: 200_000 });
+
+    const firstRun = runUnit(ctx, pi, firstSession, "task", "T01", "prompt");
+
+    // Tick past the 120s session timeout
+    mock.timers.tick(121_000);
+    await Promise.resolve();
+
+    const firstResult = await firstRun;
+    assert.equal(firstResult.status, "cancelled");
+    assert.equal(isSessionSwitchInFlight(), true, "guard should remain set after the timed-out session");
+
+    mock.timers.tick(1);
+    const secondRun = runUnit(ctx, pi, secondSession, "task", "T02", "prompt");
+
+    mock.timers.tick(100_000);
+    await Promise.resolve();
+    assert.equal(
+      isSessionSwitchInFlight(),
+      true,
+      "late settlement from the first session must not clear the newer session guard",
+    );
+
+    // Tick past the second session's timeout (121s total > 120s NEW_SESSION_TIMEOUT_MS)
+    mock.timers.tick(21_001);
+    await Promise.resolve();
+
+    const secondResult = await secondRun;
+    assert.equal(secondResult.status, "cancelled");
+
+    // Tick past the second session's delayed promise (200s) so .finally() fires
+    mock.timers.tick(80_000);
+    await Promise.resolve();
+    assert.equal(isSessionSwitchInFlight(), false, "guard should clear after the newer session settles");
+  } finally {
+    mock.timers.reset();
+  }
+});
+
 test("runUnit returns cancelled when s.active is false before sendMessage", async () => {
   _resetPendingResolve();
 
@@ -412,7 +460,7 @@ function makeMockDeps(
     getCurrentBranch: () => "main",
     autoWorktreeBranch: () => "auto/M001",
     resolveMilestoneFile: () => null,
-    reconcileMergeState: () => false,
+    reconcileMergeState: () => "clean",
     getLedger: () => null,
     getProjectTotals: () => ({ cost: 0 }),
     formatCost: (c: number) => `$${c.toFixed(2)}`,

package/src/resources/extensions/gsd/tests/auto-model-selection.test.ts

@@ -143,17 +143,17 @@ test("resolvePreferredModelConfig keeps explicit phase models as the ceiling", (
 
 // ─── resolveModelId tests ─────────────────────────────────────────────────
 
-test("resolveModelId: bare ID resolves to anthropic over claude-code when session is claude-code (#2905)", () => {
+test("resolveModelId: bare ID resolves to claude-code when session is claude-code (#3772)", () => {
   const availableModels = [
     { id: "claude-sonnet-4-6", provider: "anthropic" },
     { id: "claude-sonnet-4-6", provider: "claude-code" },
   ];
 
-  // Bug: when currentProvider is "claude-code", bare ID "claude-sonnet-4-6"
-  // resolves to claude-code/claude-sonnet-4-6 instead of anthropic/claude-sonnet-4-6
+  // When currentProvider is "claude-code" (set by startup migration for subscription
+  // users), bare IDs must resolve to claude-code to avoid the third-party block (#3772).
   const result = resolveModelId("claude-sonnet-4-6", availableModels, "claude-code");
   assert.ok(result, "should resolve a model");
-  assert.equal(result.provider, "anthropic", "bare ID must resolve to anthropic, not claude-code");
+  assert.equal(result.provider, "claude-code", "bare ID must resolve to claude-code when session provider is claude-code");
 });
 
 test("resolveModelId: bare ID still prefers current provider when it is a first-class API provider", () => {
@@ -227,14 +227,28 @@ test("model change notify in selectAndApplyModel is gated behind verbose flag",
   );
 });
 
-test("resolveModelId: anthropic wins over claude-code regardless of list order", () => {
+test("resolveModelId: anthropic wins over claude-code when session provider is not claude-code", () => {
   const availableModels = [
     { id: "claude-sonnet-4-6", provider: "claude-code" },
     { id: "claude-sonnet-4-6", provider: "anthropic" },
   ];
 
-  // Even when claude-code appears first in the list, anthropic should win
+  // When the session is NOT on claude-code, bare IDs should resolve to
+  // the canonical anthropic provider (original #2905 behavior preserved).
+  const result = resolveModelId("claude-sonnet-4-6", availableModels, undefined);
+  assert.ok(result, "should resolve a model");
+  assert.equal(result.provider, "anthropic", "anthropic must win when session is not claude-code");
+});
+
+test("resolveModelId: claude-code wins when session is claude-code regardless of list order", () => {
+  const availableModels = [
+    { id: "claude-sonnet-4-6", provider: "claude-code" },
+    { id: "claude-sonnet-4-6", provider: "anthropic" },
+  ];
+
+  // When session provider is claude-code (subscription user migration), it must
+  // win regardless of candidate ordering to avoid the third-party block (#3772).
   const result = resolveModelId("claude-sonnet-4-6", availableModels, "claude-code");
   assert.ok(result, "should resolve a model");
-  assert.equal(result.provider, "anthropic", "anthropic must win over claude-code regardless of list order");
+  assert.equal(result.provider, "claude-code", "claude-code must win when it is the session provider");
 });

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

@@ -0,0 +1,48 @@
+import test, { afterEach } from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, mkdirSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+
+import { verifyExpectedArtifact } from "../auto-recovery.ts";
+import { openDatabase, closeDatabase, insertMilestone, insertSlice, insertGateRow } from "../gsd-db.ts";
+
+const tmpDirs: string[] = [];
+
+function makeTmpProject(): string {
+  const dir = mkdtempSync(join(tmpdir(), "auto-recovery-"));
+  mkdirSync(join(dir, ".gsd"), { recursive: true });
+  openDatabase(join(dir, ".gsd", "gsd.db"));
+  insertMilestone({ id: "M001", title: "Test Milestone", status: "active" });
+  insertSlice({
+    milestoneId: "M001",
+    id: "S01",
+    title: "Test Slice",
+    status: "pending",
+    risk: "low",
+    depends: [],
+  });
+  insertGateRow({ milestoneId: "M001", sliceId: "S01", gateId: "Q3", scope: "slice" });
+  tmpDirs.push(dir);
+  return dir;
+}
+
+afterEach(() => {
+  closeDatabase();
+  for (const dir of tmpDirs) {
+    try {
+      rmSync(dir, { recursive: true, force: true });
+    } catch {
+      // Best-effort cleanup only.
+    }
+  }
+  tmpDirs.length = 0;
+});
+
+test("verifyExpectedArtifact checks pending gate-evaluate artifacts without ESM require failures", () => {
+  const base = makeTmpProject();
+
+  const verified = verifyExpectedArtifact("gate-evaluate", "M001/S01/gates+Q3", base);
+
+  assert.equal(verified, false, "pending gates should keep gate-evaluate unverified");
+});

package/src/resources/extensions/gsd/tests/codebase-generator.test.ts

@@ -138,6 +138,28 @@ test("generateCodebaseMap: excludes .gsd/ files", () => {
   }
 });
 
+test("generateCodebaseMap: excludes .claude/ and other tool directories", () => {
+  const base = makeTmpRepo();
+  try {
+    addFile(base, "src/main.ts");
+    addFile(base, ".claude/CLAUDE.md");
+    addFile(base, ".claude/memory/user.md");
+    addFile(base, ".plans/plan.md");
+    addFile(base, ".cursor/settings.json");
+    addFile(base, ".vscode/settings.json");
+
+    const result = generateCodebaseMap(base);
+    assert.ok(result.content.includes("`src/main.ts`"), "should include src/main.ts");
+    assert.ok(!result.content.includes("CLAUDE.md"), "should exclude .claude/ files");
+    assert.ok(!result.content.includes("user.md"), "should exclude .claude/memory/ files");
+    assert.ok(!result.content.includes(".plans"), "should exclude .plans/ files");
+    assert.ok(!result.content.includes(".cursor"), "should exclude .cursor/ files");
+    assert.ok(!result.content.includes(".vscode"), "should exclude .vscode/ files");
+  } finally {
+    cleanup(base);
+  }
+});
+
 test("generateCodebaseMap: excludes binary and lock files", () => {
   const base = makeTmpRepo();
   try {