pi-goal-x 0.16.1 → 0.18.0

package/README.md

@@ -31,6 +31,10 @@ All core features of [@capyup/pi-goal](https://github.com/capyup/pi-goal) are pr
 - **Recursive subtasks** — tasks can have nested sub-tasks via `subtasks?: GoalTask[]` (full recursive type). Subtask depth is controlled globally by `subtaskDepth` in `.pi/pi-goal-x-settings.json` (default: 1 level). Too-deep subtrees are rejected at proposal.
 - **Lightweight subtasks** — each task has an optional `lightweightSubtasks?: boolean` flag. When true, the parent can complete regardless of subtask status. When false/absent (full subtasks), all subtasks must be individually complete before the parent can close.
 - **Per-task completion** — `complete_task` marks individual tasks done with optional evidence/verificationSummary, and `skip_task` marks tasks as skipped with a required reason. Neither stops the turn, so the agent can continue uninterrupted.
+- **Recursive lookup** — `findTaskInTree` and `updateTaskInTree` search and update tasks at any depth. Subtask IDs are valid targets for `complete_task` and `skip_task`.
+- **Subtask gate** — parent tasks with full subtasks require all sub-items to be completed or skipped before the parent can close, enforced by recursive `checkSubtasksComplete`.
+- **Duplicate ID validation** — `validateTaskListProposal` recursively checks all task IDs across the entire tree, preventing collisions between parent/subtask or sibling subtasks.
+- **Agent workflow guidance** — prompts include a `[TASK WORKFLOW]` section directing agents to use tasks as progress trackers, completing subtasks immediately when work finishes (not batch-marking at the end).
 - **Hierarchical display** — task lists with subtasks render with indentation in prompts (`taskListBlock`, `goalPrompt`, `continuationPrompt`) and in the TUI widget (recursive count, BFS next-pending).
 - **Optional `taskList`** — goals without a task list work exactly as before. The feature is entirely opt-in.
 - **Soft `complete_goal` gate** — when `blockCompletion: true` is set, `complete_goal` surfaces a warning if pending tasks remain (prompt-level only; the agent can still complete).
@@ -48,19 +52,20 @@ All core features of [@capyup/pi-goal](https://github.com/capyup/pi-goal) are pr
 ### E2e test infrastructure
 
 - **Deterministic fork tests using `--mode json`**: the e2e suite spawns a real `pi --fork --mode json` session, parses structured `tool_execution_start`/`tool_execution_end` JSON events for field-level assertions — no free-text AI output parsing. Uses `--append-system-prompt` + `--tools` to force deterministic tool calls.
-- **Full coverage**: 281 tests total — function-level integration tests, mock-pi handler tests, file-validity checks, real `pi --fork --mode json` E2E tests, propose_goal_tweak unit/integration/e2e tests, task list policy/round-trip/render tests (including subtasks), and verification contract tests.
+- **Full coverage**: 310 tests total — function-level integration tests, mock-pi handler tests, file-validity checks, real `pi --fork --mode json` E2E tests, propose_goal_tweak unit/integration/e2e tests, task list policy/round-trip/render tests (including subtasks), and verification contract tests.
 
 ### Completion auditor
 
 - **Live progress widget** — when the auditor runs, the TUI shows a spinner, a progress bar (`[████░░░░] 40%`), step labels (`Inspecting files...`, `Verifying success criteria...`), the current tool being executed, and recent output lines. No more wondering if anything is happening.
+- **Per-goal auditor toggle** — during goal confirmation, press `a` to toggle the auditor on/off for that goal. The toggle uses a ●/○ indicator between the goal summary and confirm options. The default position comes from settings; the per-goal override persists within the session.
 - **Escape to skip** — press Escape during an audit to abort it and complete the goal immediately. The skip is recorded in the ledger as `audit_skipped` with reason `user_aborted` and auditor model metadata.
-- **Disable the auditor entirely** — set `disabled: true` in `.pi/pi-goal-x-settings.json` (or toggle it via `/goal-settings`). The agent can still bypass with user confirmation by passing `confirmBypassAuditor: true` to `update_goal`.
+- **Disable the auditor entirely** — set `disabled: true` in `.pi/pi-goal-x-settings.json` (or toggle it via `/goal-settings`). The agent can still bypass with user confirmation by passing `confirmBypassAuditor: true` to `complete_goal`.
 - **Skipped audits are recorded** — every skip (whether disabled or Escape-aborted) is logged to the ledger with the reason, provider, model, and thinking level for full traceability.
 - **Robust abort detection** — the auditor detects aborts both from exceptions *and* from `session.prompt()` returning after an abort signal, preventing stuck goals or ghost states.
 - **Cleaner lifecycle** — `AbortSignal` is properly wired to `session.abort()`, animation timers are cleaned up, and the unsubscribe path is always executed. No more having to kill the session.
 - **Completion report includes full auditor output** — the auditor's full report is included in the goal completion conversation message upon approval, not just a verdict.
 - **Session factory injection** — `runGoalCompletionAuditor` accepts an optional `createSession` parameter for testability, enabling mock auditor sessions in tests.
-- **Structured test evidence** — the executor can pass `testResults` (exit code, suite name, output, timestamp) via `update_goal({testResults})`. The auditor receives a `<test_evidence>` block and is instructed to check it before re-running test suites, skipping redundant re-runs.
+- **Structured test evidence** — the executor can pass `testResults` (exit code, suite name, output, timestamp) via `complete_goal({testResults})`. The auditor receives a `<test_evidence>` block and is instructed to check it before re-running test suites, skipping redundant re-runs.
 
 ### Drafting & UX
 
@@ -232,7 +237,7 @@ The completion result prints a full report into the conversation:
 - the auditor's approval report
 - full current goal details, including objective, status, usage, mode, and file path
 
-Sisyphus goals use the same completion tool as regular goals. The stricter part is the prompt/criteria standard: the agent should only call completion after the whole ordered objective is actually satisfied and likely to survive independent auditing. A paused goal can also be completed directly when the agent already has enough evidence that every requirement is satisfied; it does not need a resume just to call `update_goal`.
+Sisyphus goals use the same completion tool as regular goals. The stricter part is the prompt/criteria standard: the agent should only call completion after the whole ordered objective is actually satisfied and likely to survive independent auditing. A paused goal can also be completed directly when the agent already has enough evidence that every requirement is satisfied; it does not need a resume just to call `complete_goal`.
 
 ## Schema gates
 

package/docs/CHANGELOG.md

@@ -0,0 +1,160 @@
+# Changelog
+
+## 0.18.0 (2026-05-29)
+
+### Features
+
+- **Enriched confirmation dialog** — proposal dialogs now render with full-width box-drawing section headers (`┌─ Section Name ─────┐`), per-status task coloring (`[x]` green, `[ ]` yellow), and goal structure section highlighting (`Objective:`, `Success criteria:`, etc. in accent). The 12-line MAX_CONTEXT_LINES cap is removed — full proposals are always visible.
+- **Hidden TUI debug mode** — Ctrl+Shift+X toggles a debug panel in the goal widget. Ctrl+Shift+N creates/removes test goals (written to `.pi/goals/debug/`), Ctrl+Shift+T injects sample tasks, Ctrl+Shift+R starts a mock audit, Ctrl+Shift+O opens the proposal dialog with realistic data.
+
+### Fixes
+
+- **Text wrapping inside boxes** — pipe-prefixed lines (`│   content`) that wrap now maintain the `│   ` prefix on continuation lines, keeping wrapped text inside the ASCII box. Task checkbox lines embedded in objective text also get the `│   ` prefix so they appear within the box.
+
+### Tests
+
+- 310 total tests (unchanged).
+
+## 0.17.0 (2026-05-29)
+
+### Features
+
+- **Per-goal auditor toggle** — press `a` during the confirmation dialog to toggle the auditor on/off for a specific goal. Default from settings; override persists within session.
+- **Task workflow prompt guidance** — added `[TASK WORKFLOW]` section to both `goalPrompt` and `continuationPrompt`, directing agents to complete subtasks one-by-one as progress trackers (not batch-marking at the end).
+- **Recursive duplicate ID validation** — `validateTaskListProposal` now checks all task IDs across the entire tree, preventing collisions between parent/subtask or sibling subtask IDs.
+- **Escape dialog during audit** — pressing Escape during a completion audit shows a TUI dialog with "Mark complete without audit" or "Continue working" options.
+
+### Fixes
+
+- `validateTaskCompletion` and `validateTaskSkip` now use recursive `findTaskInTree` instead of flat `Array.find()` for nested subtask support.
+- Updated README references from legacy `update_goal` to `complete_goal`.
+
+### Tests
+
+- 310 total tests (up from 308).
+- Added tests for recursive duplicate ID detection across nested subtask trees.
+- Added e2e test for `skipAuditor=true` path.
+
+## 0.16.1 (2026-05-29)
+
+### Features
+
+- **Escape-to-skip audit** — press Escape during an auditor run to abort it and complete the goal immediately. The skip is recorded in the ledger with the reason `user_aborted` and auditor model metadata.
+- **Audit progress widget** — the TUI shows a spinner, progress bar, step labels, current tool, and output lines while the auditor runs.
+- **Audit abort detection** — the auditor detects aborts both from exceptions and from `session.prompt()` returning after an abort signal, preventing stuck goals or ghost states.
+- **Goal status for Sisyphus** — `COMPLETED` status label for completed Sisyphus goals.
+- **Multi-session focus isolation** — goal focus data uses `goalFocusDetails` which includes the goal id and reason but not full balance data, preventing cross-session focus leakage.
+
+### Fixes
+
+- Fixed a merge bug where `propose_task_list` could produce duplicate task list when called during a continuation.
+
+## 0.16.0 (2026-05-29)
+
+### Features
+
+- **`delete_goal` tool** — new lifecycle tool for archiving goals by id. Accepts a required `goalId` and optional `reason`. Agent-facing only; not intended for user use.
+- **`complete_goal` `status` optional** — the `status` parameter on `complete_goal` is now optional. When omitted, defaults to `"complete"`. Explicitly setting an invalid value (anything other than `"complete"`) still produces an error.
+- **SCROLL FIX** — the confirmation dialog no longer scrolls to the bottom when the user is scrolled up and new content arrives. Uses `addContextWrapped()` which suppresses viewport resets.
+- **Task list shown first** — the task list section now appears FIRST in the confirmation dialog context (before the objective), with context capped at 12 lines so tasks don't scroll off-screen.
+- **Audit completion flow** — the completion report card no longer says "Goal audit approved." when the auditor was skipped (now shows "Goal audit skipped." with reason).
+
+### Fixes
+
+- Fixed task completion/skip validation for nested subtasks (uses recursive `findTaskInTree`).
+- All `complete_goal` calls default to `status: "complete"` when no explicit status is provided.
+- Updated prompts and tool descriptions to reflect the `complete_goal` naming.
+
+### Tests
+
+- Updated e2e tests to verify `complete_goal` accepts calls without status.
+- Added e2e test verifying `complete_goal` rejects invalid explicit status.
+
+## 0.15.1 (2026-05-28)
+
+### Fixes
+
+- Fixed settings file reference in storage writes.
+
+### Documentation
+
+- Reorganized README settings documentation for clarity.
+
+## 0.14.0 (2026-05-27)
+
+### Features
+
+- **Subtask hierarchy** — tasks can have nested sub-tasks via `subtasks?: GoalTask[]`. Subtask depth controlled by `subtaskDepth` setting (default: 1). Deep subtrees are rejected at proposal.
+- **Lightweight subtasks** — `lightweightSubtasks?: boolean` on tasks. When true, parent can complete regardless of subtask status. Full subtasks require all sub-items completed first.
+- **Per-task contracts** — `propose_task_list` supports optional `verificationContract` per task. If set, `complete_task` requires a non-empty `verificationSummary`.
+- **Task list block** — tasks are listed in prompts with checkboxes and status indicators.
+
+### Tests
+
+- Added e2e tests for goal creation with task list, scroll fix, and subtask validation.
+
+## 0.13.0 (2026-05-22)
+
+### Features
+
+- **Verification contract system** — goals can include a `Verification contract:` section. Extracted and stored on the goal record. `complete_goal` rejects calls without `verificationSummary` when a contract is set.
+- **Per-goal verification contracts** — the contract is extracted during goal drafting and enforced by tools and prompts.
+- **`complete_goal` `testResults` removed** — replaced with `verificationSummary`. The old structured test results interface is gone.
+- **Auditor integration** — the independent completion auditor receives both the `verificationContract` and `verificationSummary` and cross-checks claims against real artifacts.
+
+### Tests
+
+- Updated verification contract tests.
+
+## 0.12.0 (2026-04-29)
+
+### Features
+
+- **Task list system** — `propose_task_list` tool with confirmation dialog. Tasks stored on goal record, rendered in prompts and widget, serialized to disk.
+- **Unified goal + task acceptance** — `propose_goal_draft` accepts optional `tasks` array. Single dialog shows goal + task list together.
+- **`complete_task` and `skip_task` tools** — per-task completion with evidence/verificationSummary. Neither stops the turn.
+- **`update_goal` renamed to `complete_goal`** — the core completion tool now uses `complete_goal({status: "complete"})` and requires explicit status acceptance.
+- **Completion report heading fix** — the report now shows `Goal complete.` instead of `Goal audit approved.` when no contract or auditor is involved.
+
+### Tests
+
+- Full task lifecycle tests (policy, round-trip, render, edge cases).
+- Verification contract tests for both goal-level and per-task contracts.
+
+## 0.11.0 (2026-04-23)
+
+### Features
+
+- **Deferred archival** — goals are archived at `turn_end`, not inline in the tool handler. Prevents premature archiving before the agent sees the audit result.
+- **`propose_goal_tweak`** — sole mechanism for updating the goal objective during `/goal-tweak`. Uses the same Confirm/Continue Chatting dialog as goal creation.
+- **Focus isolation** — goal focus is stored as a branch-local session entry, not in goal markdown metadata. Multiple sessions can have different focused goals.
+- **Auditor bypass with user confirmation** — `confirmBypassAuditor: true` bypasses the auditor when the user explicitly opts out.
+
+### Fixes
+
+- Cleaned up lifecycle issues with AbortSignal wiring and timer cleanup.
+
+## 0.10.0 (2026-04-15)
+
+### Features
+
+- **Completion audit system** — independent pi auditor agent verifies completion claims before archiving.
+- **Audit progress** — real-time TUI progress widget with spinner, progress bar, and step labels.
+- **Ledger system** — structured event log for all goal lifecycle events.
+
+## 0.9.0 (2026-04-08)
+
+### Features
+
+- **`goal_question` and `goal_questionnaire`** — structured drafting question tools.
+- **`/goal-settings`** — interactive settings configuration.
+- **Sisyphus goal style** — patient ordered execution with prompt/criteria variant.
+
+## 0.8.1 (2026-04-01)
+
+### Features
+
+- Initial fork from @capyup/pi-goal.
+- Pause/resume/abort lifecycle.
+- Multiple open goals.
+- Auto-continue loop.

package/extensions/goal-draft.ts

@@ -85,19 +85,29 @@ export function buildDraftConfirmationText(args: {
 }): string {
 	const lines: string[] = [];
 	const modeLabel = args.focus === "sisyphus" ? "Sisyphus (prompt/criteria style)" : "Normal goal";
-	lines.push("Goal draft ready for confirmation.");
+	lines.push("● Goal draft ready for confirmation.");
 	lines.push("");
-	lines.push("Draft details:");
-	lines.push(`Mode: ${modeLabel}`);
-	lines.push(`Auto-continue: ${args.autoContinue ? "yes" : "no"}`);
+	lines.push("─── Draft Details ───");
+	lines.push(`│   Mode: ${modeLabel}`);
+	lines.push(`│   Auto-continue: ${args.autoContinue ? "yes" : "no"}`);
 	lines.push("");
-	lines.push("Original topic:");
+	lines.push("─── Original Topic ───");
 	lines.push("");
-	lines.push(args.originalTopic.trim());
+	for (const topicLine of args.originalTopic.trim().split("\n")) {
+		if (topicLine.trim()) lines.push(`│   ${topicLine}`);
+	}
 	lines.push("");
-	lines.push("Proposed goal:");
+	lines.push("─── Proposed Goal ───");
 	lines.push("");
-	lines.push(args.objective);
+	for (const objLine of args.objective.split("\n")) {
+		const trimmed = objLine.trim();
+		if (!trimmed) continue;
+		if (trimmed.startsWith("│")) {
+			lines.push(objLine);
+		} else {
+			lines.push(`│   ${objLine}`);
+		}
+	}
 	return lines.join("\n");
 }
 
@@ -109,22 +119,40 @@ export function buildTweakConfirmationText(args: {
 }): string {
 	const lines: string[] = [];
 	const modeLabel = args.sisyphus ? "Sisyphus (prompt/criteria style)" : "Normal goal";
-	lines.push("Goal tweak ready for confirmation.");
+	lines.push("● Goal tweak ready for confirmation.");
 	lines.push("");
-	lines.push("Draft details:");
-	lines.push(`Mode: ${modeLabel}`);
+	lines.push("─── Draft Details ───");
+	lines.push(`│   Mode: ${modeLabel}`);
 	lines.push("");
-	lines.push("Change:");
+	lines.push("─── Change ───");
 	lines.push("");
-	lines.push(args.changeSummary);
+	for (const changeLine of args.changeSummary.split("\n")) {
+		if (changeLine.trim()) lines.push(`│   ${changeLine}`);
+	}
 	lines.push("");
-	lines.push("Current objective:");
+	lines.push("─── Current Objective ───");
 	lines.push("");
-	lines.push(args.currentObjective);
+	for (const curLine of args.currentObjective.split("\n")) {
+		const trimmed = curLine.trim();
+		if (!trimmed) continue;
+		if (trimmed.startsWith("│")) {
+			lines.push(curLine);
+		} else {
+			lines.push(`│   ${curLine}`);
+		}
+	}
 	lines.push("");
-	lines.push("Proposed new objective:");
+	lines.push("─── Proposed New Objective ───");
 	lines.push("");
-	lines.push(args.newObjective);
+	for (const newLine of args.newObjective.split("\n")) {
+		const trimmed = newLine.trim();
+		if (!trimmed) continue;
+		if (trimmed.startsWith("│")) {
+			lines.push(newLine);
+		} else {
+			lines.push(`│   ${newLine}`);
+		}
+	}
 	return lines.join("\n");
 }
 

package/extensions/goal-policy.ts

@@ -185,7 +185,7 @@ export function validateTaskCompletion(args: {
 }): PolicyValidation {
 	if (!args.goal) return { ok: false, message: "No goal is set." };
 	if (!args.goal.taskList) return { ok: false, message: "Goal has no task list." };
-	const task = args.goal.taskList.tasks.find((t) => t.id === args.taskId);
+	const task = findTaskInTree(args.goal.taskList.tasks, args.taskId);
 	if (!task) return { ok: false, message: `Task "${args.taskId}" not found.` };
 	if (task.status === "complete") return { ok: false, message: `Task "${args.taskId}" is already complete.` };
 	if (task.status === "skipped") return { ok: false, message: `Task "${args.taskId}" was already skipped.` };
@@ -199,7 +199,7 @@ export function validateTaskSkip(args: {
 }): PolicyValidation {
 	if (!args.goal) return { ok: false, message: "No goal is set." };
 	if (!args.goal.taskList) return { ok: false, message: "Goal has no task list." };
-	const task = args.goal.taskList.tasks.find((t) => t.id === args.taskId);
+	const task = findTaskInTree(args.goal.taskList.tasks, args.taskId);
 	if (!task) return { ok: false, message: `Task "${args.taskId}" not found.` };
 	if (task.status === "complete") return { ok: false, message: `Task "${args.taskId}" is already complete.` };
 	// Skipped tasks toggle via the executor; reason is only required for first-time skips.
@@ -241,6 +241,20 @@ export function findSubtaskDepthViolation(tasks: GoalTask[], maxDepth: number):
 	return undefined;
 }
 
+function checkDuplicateTaskIds(tasks: GoalTask[], ids: Set<string>): string | undefined {
+	for (const t of tasks) {
+		const id = t.id.trim();
+		if (!id) return "All tasks must have a non-empty id.";
+		if (ids.has(id)) return `Duplicate task id: "${id}".`;
+		ids.add(id);
+		if (t.subtasks) {
+			const childErr = checkDuplicateTaskIds(t.subtasks, ids);
+			if (childErr) return childErr;
+		}
+	}
+	return undefined;
+}
+
 export function validateTaskListProposal(args: {
 	goal: GoalPolicyRecordLike | null;
 	tasks: GoalTask[];
@@ -254,6 +268,11 @@ export function validateTaskListProposal(args: {
 		if (!t.title.trim()) return { ok: false, message: `Task "${t.id}" must have a non-empty title.` };
 		if (ids.has(t.id)) return { ok: false, message: `Duplicate task id: "${t.id}".` };
 		ids.add(t.id);
+		// Recursively check subtask ids against the same global set
+		if (t.subtasks && t.subtasks.length > 0) {
+			const childErr = checkDuplicateTaskIds(t.subtasks, ids);
+			if (childErr) return { ok: false, message: childErr };
+		}
 	}
 	// Check subtask depth limit
 	const maxDepth = args.maxSubtaskDepth ?? 1;

package/extensions/goal-questionnaire.ts

@@ -26,6 +26,7 @@ export interface GoalQuestionnaireResult {
 	questions: GoalQuestionnaireQuestion[];
 	answers: GoalQuestionnaireAnswer[];
 	cancelled: boolean;
+	auditorEnabled?: boolean;
 }
 
 export type ProposalDecision = "confirm" | "continue";
@@ -82,7 +83,7 @@ export function proposalDialogFailureMessage(error: unknown): string {
  * the internal draft-confirm prompt. This keeps pi-goal self-contained and
  * avoids depending on external question/questionnaire packages.
  */
-export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions: GoalQuestionnaireQuestion[]): Promise<GoalQuestionnaireResult> {
+export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions: GoalQuestionnaireQuestion[], auditorToggleInit?: { defaultEnabled: boolean }): Promise<GoalQuestionnaireResult> {
 	if (!ctx.hasUI) {
 		return { questions: [], answers: [], cancelled: true };
 	}
@@ -102,6 +103,7 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 		let inputMode = false;
 		let inputQuestionId: string | null = null;
 		let cachedLines: string[] | undefined;
+		let auditorEnabled = auditorToggleInit?.defaultEnabled ?? true;
 		const answers = new Map<string, GoalQuestionnaireAnswer>();
 		const drafts = new Map<string, string>();
 
@@ -126,7 +128,7 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 			// Restore hardware cursor now that the dialog is closing
 			tui.setShowHardwareCursor(wasHardwareCursorShown);
 			const ordered = questions.map((q) => answers.get(q.id)).filter((a): a is GoalQuestionnaireAnswer => !!a);
-			done({ questions, answers: ordered, cancelled });
+			done({ questions, answers: ordered, cancelled, auditorEnabled: auditorToggleInit ? auditorEnabled : undefined });
 		}
 
 		function currentQuestion(): GoalQuestionnaireQuestion | undefined {
@@ -272,6 +274,13 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 				return;
 			}
 
+			// Auditor toggle hotkey
+			if (matchesKey(data, "a") && auditorToggleInit) {
+				auditorEnabled = !auditorEnabled;
+				refresh();
+				return;
+			}
+
 			if (matchesKey(data, Key.enter) && q) {
 				if (q.options.length === 0 || opts[optionIndex]?.isCustom) {
 					inputMode = true;
@@ -293,7 +302,7 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 			if (matchesKey(data, Key.escape)) submit(true);
 		}
 
-		function render(width: number): string[] {
+			function render(width: number): string[] {
 			if (cachedLines) return cachedLines;
 			const safeWidth = Math.max(20, width);
 			const lines: string[] = [];
@@ -301,6 +310,111 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 			const opts = displayOptions();
 			const add = (s: string) => lines.push(truncateToWidth(s, safeWidth, "…", true));
 			const addWrapped = (s: string) => lines.push(...wrapTextWithAnsi(s, safeWidth));
+			/**
+			 * Wraps a pipe-prefixed line and prepends "│   " to continuation lines
+			 * so wrapped content stays within the ASCII box.
+			 */
+			const addWrappedPipe = (styledLine: string) => {
+				const wrapped = wrapTextWithAnsi(styledLine, safeWidth);
+				for (let i = 0; i < wrapped.length; i++) {
+					lines.push(i === 0 ? wrapped[i] : "│   " + wrapped[i]);
+				}
+			};
+
+			/** Render context lines with per-line styling. No truncation. */
+			const renderContextLines = (context: string): void => {
+				const rawLines = context.split("\n");
+				for (const rawLine of rawLines) {
+					const trimmed = rawLine.trim();
+					// Empty line — preserve as spacing
+					if (!trimmed) {
+						lines.push("");
+						continue;
+					}
+
+					// 1. Announcement header — "● Goal draft/tweak ready for confirmation."
+					if (/^● Goal (draft|tweak) ready for confirmation\.$/.test(trimmed)) {
+						addWrapped(theme.fg("accent", rawLine));
+						continue;
+					}
+
+					// 2. Section marker — "─── Name ───" → full-width box-drawing header
+					const sectionMatch = trimmed.match(/^───\s+(.+?)\s+───$/);
+					if (sectionMatch) {
+						const sectionName = sectionMatch[1];
+						const namePart = ` ${sectionName} `;
+						const left = "┌─";
+						const right = "─┐";
+						const fill = Math.max(0, safeWidth - 2 - visibleWidth(left + namePart + right));
+						add(theme.fg("accent", left + namePart + "─".repeat(fill) + right));
+						continue;
+					}
+
+					// 3. Lines with │ prefix come from buildDraftConfirmationText / buildTweakConfirmationText.
+					if (trimmed.startsWith("│")) {
+						const afterPipe = trimmed.slice(1).trim();
+						// 3a. Task checkbox under │ prefix — detect before key-value to avoid
+						// "[x] t1: ..." being misinterpreted as a key-value pair.
+						const pipeTaskMatch = afterPipe.match(/^(\[.\])(\s+)(.+)$/);
+						if (pipeTaskMatch) {
+							const bracket = pipeTaskMatch[1];
+							const sep = pipeTaskMatch[2];
+							const rest = pipeTaskMatch[3];
+							// Preserve inner whitespace between │ and the task marker (e.g. "   " in "│   [x]...")
+							const pipeContent = trimmed.slice(1);
+							const innerWs = pipeContent.slice(0, pipeContent.length - pipeContent.trimStart().length);
+							const linePrefix = "│" + innerWs;
+							const color = bracket === "[x]" ? "success" : "warning";
+							addWrappedPipe(linePrefix + theme.fg(color, bracket) + sep + theme.fg("muted", rest));
+							continue;
+						}
+						// 3b. Key-value content (e.g. "│   Mode: Normal goal", "│   Auto-continue: yes")
+						if (afterPipe.includes(": ")) {
+							const colonIdx = afterPipe.indexOf(": ");
+							const val = afterPipe.slice(colonIdx + 2).trim();
+							const keyPart = rawLine.slice(0, rawLine.indexOf(afterPipe) + colonIdx + 2);
+							if (val === "yes" || val === "no") {
+								addWrappedPipe(theme.fg("muted", keyPart) + theme.fg(val === "yes" ? "success" : "warning", val));
+								continue;
+							}
+							addWrappedPipe(theme.fg("muted", rawLine));
+							continue;
+						}
+						// 3c. Generic content under │ prefix (topic, goal text, etc.)
+						addWrappedPipe(theme.fg("muted", rawLine));
+						continue;
+					}
+
+					// 4. Goal objective structure lines — detected before task checkboxes
+					// because === Goal could overlap with ─── markers but we already checked those.
+					const GOAL_SECTION_RE = /^(=== (Goal|Sisyphus Goal) ===|Objective:|Success criteria:|Boundaries:|Constraints:|Verification contract:|If blocked:)/;
+					if (GOAL_SECTION_RE.test(trimmed)) {
+						addWrapped(theme.fg("accent", rawLine));
+						continue;
+					}
+
+					// 5. Actual box-drawing borders (┌ └ ├ └ ┐ ┤ ┘ ─) — NOT │ which is handled above
+					if (/^[┌├└┐┤┘─]/.test(trimmed)) {
+						addWrapped(theme.fg("dim", rawLine));
+						continue;
+					}
+
+					// 6. Task checkbox item — "[ ] ...", "[x] ...", or "[~] ..." (with optional indent)
+					const checkMatch = trimmed.match(/^(\[.\])(\s+)(.+)$/);
+					if (checkMatch) {
+						const bracket = checkMatch[1];
+						const sep = checkMatch[2];
+						const rest = checkMatch[3];
+						const indent = rawLine.slice(0, rawLine.length - trimmed.length);
+						const color = bracket === "[x]" ? "success" : "warning";
+						addWrapped(indent + theme.fg(color, bracket) + sep + theme.fg("muted", rest));
+						continue;
+					}
+
+					// 7. Default: any remaining content (fallback)
+					addWrapped(theme.fg("muted", rawLine));
+				}
+			};
 
 			add(theme.fg("accent", "─".repeat(safeWidth)));
 			if (isMulti) {
@@ -331,7 +445,7 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 
 			if (inputMode && q) {
 				addWrapped(theme.fg("text", ` ${q.question}`));
-				if (q.context) addWrapped(theme.fg("muted", ` ${q.context}`));
+				if (q.context) renderContextLines(q.context);
 				lines.push("");
 				if (q.options.length > 0) {
 					renderOptions();
@@ -352,7 +466,15 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 				add(allAnswered() ? theme.fg("success", " Press Enter to submit") : theme.fg("warning", ` Unanswered: ${questions.filter((qq) => !answers.has(qq.id)).map((qq) => qq.id).join(", ")}`));
 			} else if (q) {
 				addWrapped(theme.fg("text", ` ${q.question}`));
-				if (q.context) addWrapped(theme.fg("muted", ` ${q.context}`));
+				if (q.context) renderContextLines(q.context);
+				// Auditor toggle line between context and options
+				if (auditorToggleInit) {
+					const circle = auditorEnabled ? "●" : "○";
+					const label = auditorEnabled ? "Auditor enabled" : "Auditor disabled";
+					const color = auditorEnabled ? "success" : "warning";
+					add(theme.fg(color, ` ${circle} ${label}`) + theme.fg("dim", "  (press 'a' to toggle)"));
+					lines.push("");
+				}
 				const existing = answers.get(q.id);
 				if (existing) add(theme.fg("dim", ` Current: ${existing.wasCustom ? "(wrote) " : ""}${existing.answer}`));
 				lines.push("");
@@ -361,7 +483,10 @@ export async function runGoalQuestionnaire(ctx: ExtensionContext, rawQuestions:
 			}
 
 			lines.push("");
-			if (!inputMode) add(theme.fg("dim", isMulti ? " Tab/←→ navigate • ↑↓ select • Enter confirm • Esc cancel" : " ↑↓ navigate • Enter select • Esc cancel"));
+			if (!inputMode) {
+				const auditorHint = auditorToggleInit ? " • a toggle auditor" : "";
+				add(theme.fg("dim", isMulti ? " Tab/←→ navigate • ↑↓ select • Enter confirm • Esc cancel" + auditorHint : " ↑↓ navigate • Enter select • Esc cancel" + auditorHint));
+			}
 			add(theme.fg("accent", "─".repeat(safeWidth)));
 			cachedLines = lines;
 			return lines;
@@ -379,7 +504,8 @@ export async function showProposalDialog(
 	ctx: ExtensionContext,
 	confirmationText: string,
 	focus: GoalDraftingFocus,
-): Promise<ProposalDecision> {
+	defaultAuditorEnabled?: boolean,
+): Promise<{ decision: ProposalDecision; auditorEnabled: boolean }> {
 	const headerTitle = focus === "sisyphus" ? "Confirm Sisyphus Goal Draft" : "Confirm Goal Draft";
 	const result = await runGoalQuestionnaire(ctx, [{
 		id: "confirm",
@@ -388,11 +514,12 @@ export async function showProposalDialog(
 		options: ["Confirm — create this goal now", "Continue chatting — keep refining"],
 		recommended: 0,
 		allowCustom: false,
-	}]);
-	return proposalDecisionFromQuestionnaireResult({
+	}], defaultAuditorEnabled !== undefined ? { defaultEnabled: defaultAuditorEnabled } : undefined);
+	const decision = proposalDecisionFromQuestionnaireResult({
 		cancelled: result.cancelled,
 		answer: result.answers[0]?.answer,
 	});
+	return { decision, auditorEnabled: result.auditorEnabled ?? true };
 }
 
 export function registerQuestionnaireTools(pi: ExtensionAPI): void {

package/extensions/goal-record.ts

@@ -45,6 +45,7 @@ export interface GoalRecord {
 	// Set by the agent's pause_goal tool. Cleared when the goal becomes active again.
 	pauseReason?: string;
 	pauseSuggestedAction?: string;
+	skipAuditor?: boolean;
 	taskList?: GoalTaskList;
 	/** Plain-text description of what verification evidence is required before completing this goal. */
 	verificationContract?: string;
@@ -247,6 +248,7 @@ export function normalizeGoalRecord(value: unknown): GoalRecord | null {
 		stopReason: raw.stopReason === "agent" || raw.stopReason === "user" ? raw.stopReason : undefined,
 		pauseReason: typeof raw.pauseReason === "string" && raw.pauseReason.trim() ? raw.pauseReason : undefined,
 		pauseSuggestedAction: typeof raw.pauseSuggestedAction === "string" && raw.pauseSuggestedAction.trim() ? raw.pauseSuggestedAction : undefined,
+		skipAuditor: raw.skipAuditor === true ? true : undefined,
 		taskList: normalizeTaskList(raw.taskList),
 		verificationContract: typeof raw.verificationContract === "string" ? raw.verificationContract : undefined,
 	};

package/extensions/goal-settings.ts

@@ -143,6 +143,14 @@ export function loadGoalSettings(cwd: string, env: NodeJS.ProcessEnv = process.e
  * Save settings to the unified settings file on disk.
  * Persists only non-default values using the canonical key names.
  */
+/**
+ * Determine whether the auditor should be enabled by default based on settings.
+ * The auditor is enabled by default unless settings.disabled === true.
+ */
+export function isAuditorEnabledByDefault(settings: GoalSettings): boolean {
+	return settings.disabled !== true;
+}
+
 export function saveGoalSettingsFileConfig(cwd: string, settings: GoalSettings): GoalSettings {
 	const clean: GoalSettings = {};
 	const provider = asNonEmptyString(settings.provider);