commandmate 0.23.0 → 0.25.0

package/dist/server/src/lib/db/migrations/runner.js

@@ -17,7 +17,7 @@ const path_1 = __importDefault(require("path"));
  * Current schema version
  * Increment this when adding new migrations
  */
-exports.CURRENT_SCHEMA_VERSION = 55;
+exports.CURRENT_SCHEMA_VERSION = 56;
 /**
  * Get current schema version from database
  */

package/dist/server/src/lib/db/migrations/v56-gate-result-source.js

@@ -0,0 +1,58 @@
+"use strict";
+/**
+ * Migration v56: record where each verification gate was declared (Issue #1791).
+ *
+ * An execution contract can now carry gate *definitions* of its own, not just a
+ * selection of the repository's (#1756 案 B). That is what stops an orchestrator
+ * from having to append an Issue-specific gate to `.commandmate/verify.yaml` —
+ * a file that stays inside the work-evidence change set, so a worktree carrying
+ * nothing but that append reads as "the agent did work".
+ *
+ * The separation is only real if a reader can see it. Two gates in one report
+ * spell their ids the same way whether the repository declared them or one
+ * delegation did, and the contract's copy is not on disk to be checked against.
+ * Without this column, per-delegation gates are a second verify.yaml that
+ * nothing announces — a run could be green on criteria the repository never
+ * agreed to, and its report would look identical to one that passed the real
+ * ones.
+ *
+ * Nullable, with no backfill and no default. Rows written before this migration
+ * were produced by a runner that had no contract gates at all, so `verify.yaml`
+ * would be *almost* true of them and outright wrong for the built-ins — and
+ * verification history is evidence, which is not rewritten to make a column
+ * look complete. null therefore reads as "written before v56, nobody recorded
+ * this", the same discipline `timingsMeasured` uses for pre-#1625 timestamps.
+ *
+ * The CHECK mirrors VERIFICATION_GATE_SOURCES in verification-db.ts, for the
+ * reason v49's `trigger` CHECK does: a vocabulary that lives only in the writer
+ * lets a typo land as a new bucket nothing queries.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.v56_migrations = void 0;
+exports.v56_migrations = [
+    {
+        version: 56,
+        name: 'add-source-to-verification-gate-results',
+        up: (db) => {
+            // `ADD COLUMN IF NOT EXISTS` does not exist in SQLite, and the rollback
+            // below deliberately leaves the column in place — so a database rolled
+            // back past v56 and migrated forward again reaches this statement with
+            // the column already there. Without the guard that upgrade path dies on
+            // "duplicate column name".
+            const columns = db
+                .prepare('PRAGMA table_info(verification_gate_results)')
+                .all();
+            if (columns.some((column) => column.name === 'source'))
+                return;
+            db.exec(`
+        ALTER TABLE verification_gate_results ADD COLUMN source TEXT
+          CHECK (source IS NULL OR source IN ('builtin', 'verify.yaml', 'contract'));
+      `);
+        },
+        down: () => {
+            // SQLite drops columns only by rebuilding the table, which would rewrite
+            // every historical gate verdict to remove one nullable column. Same
+            // no-op rollback as v35/v36.
+        },
+    },
+];

package/dist/server/src/lib/db/verification-db.js

@@ -20,7 +20,7 @@
  * exactly the failure this table exists to make impossible.
  */
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.MAX_RUN_HISTORY_DAYS = exports.MAX_RUN_HISTORY_LIMIT = exports.DEFAULT_RUN_HISTORY_LIMIT = exports.VERIFICATION_TRIGGERS = void 0;
+exports.MAX_RUN_HISTORY_DAYS = exports.MAX_RUN_HISTORY_LIMIT = exports.DEFAULT_RUN_HISTORY_LIMIT = exports.VERIFICATION_GATE_SOURCES = exports.VERIFICATION_TRIGGERS = void 0;
 exports.createVerificationRun = createVerificationRun;
 exports.finishVerificationRun = finishVerificationRun;
 exports.createGateResult = createGateResult;
@@ -38,11 +38,28 @@ exports.listVerificationRunsForPeriod = listVerificationRunsForPeriod;
  * trigger cannot be accepted by an API route and then rejected by SQLite.
  */
 exports.VERIFICATION_TRIGGERS = ['manual', 'wait', 'api', 'task'];
+/**
+ * Where a gate's definition came from (Issue #1791, migration v56).
+ *
+ * `builtin` = work-evidence / scope / env-clean (and the `config` pseudo-gate),
+ * which are the runner's own. `verify.yaml` = the repository's declared
+ * criterion of passing. `contract` = a gate the execution contract carried for
+ * this delegation alone.
+ *
+ * Recorded rather than inferred from the id, because the whole point of letting
+ * a contract carry gates is that a reader can tell the repository's definition
+ * of "passes" from one Issue's. Without it in the report, per-delegation gates
+ * are a second verify.yaml that nothing announces.
+ *
+ * The runtime tuple mirrors the CHECK constraint in migration v56.
+ */
+exports.VERIFICATION_GATE_SOURCES = ['builtin', 'verify.yaml', 'contract'];
 const RUN_COLUMNS = `
   id, worktree_id, instance_id, task_id, trigger, status, base_ref, started_at, finished_at
 `;
 const GATE_COLUMNS = `
-  id, run_id, gate_id, command, status, exit_code, duration_ms, log_tail, started_at, finished_at
+  id, run_id, gate_id, command, status, exit_code, duration_ms, log_tail, started_at, finished_at,
+  source
 `;
 function mapRunRow(row) {
     return {
@@ -69,6 +86,7 @@ function mapGateRow(row) {
         logTail: row.log_tail,
         startedAt: new Date(row.started_at),
         finishedAt: row.finished_at === null ? null : new Date(row.finished_at),
+        source: row.source ?? null,
         timingsMeasured: row.finished_at !== null &&
             row.duration_ms !== null &&
             row.finished_at - row.started_at === row.duration_ms,
@@ -108,11 +126,12 @@ function createGateResult(db, runId, input) {
     const info = db
         .prepare(`
       INSERT INTO verification_gate_results (
-        run_id, gate_id, command, status, exit_code, duration_ms, log_tail, started_at, finished_at
+        run_id, gate_id, command, status, exit_code, duration_ms, log_tail, started_at,
+        finished_at, source
       )
-      VALUES (?, ?, ?, 'running', NULL, NULL, NULL, ?, NULL)
+      VALUES (?, ?, ?, 'running', NULL, NULL, NULL, ?, NULL, ?)
     `)
-        .run(runId, input.gateId, input.command, now);
+        .run(runId, input.gateId, input.command, now, input.source);
     const row = db
         .prepare(`SELECT ${GATE_COLUMNS} FROM verification_gate_results WHERE id = ?`)
         .get(Number(info.lastInsertRowid));
@@ -266,7 +285,7 @@ function listVerificationRunsForPeriod(db, opts = {}) {
     const placeholders = runRows.map(() => '?').join(', ');
     const gateRows = db
         .prepare(`
-      SELECT run_id, gate_id, status, exit_code, duration_ms
+      SELECT run_id, gate_id, status, exit_code, duration_ms, source
       FROM verification_gate_results
       WHERE run_id IN (${placeholders})
       ORDER BY started_at ASC, id ASC
@@ -279,6 +298,7 @@ function listVerificationRunsForPeriod(db, opts = {}) {
             status: row.status,
             exitCode: row.exit_code,
             durationMs: row.duration_ms,
+            source: row.source ?? null,
         };
         const bucket = byRun.get(row.run_id);
         if (bucket)

package/dist/server/src/lib/detection/cli-patterns.js

@@ -4,11 +4,12 @@
  * Shared between response-poller.ts and API routes
  */
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.CLAUDE_SESSION_ERROR_REGEX_PATTERNS = exports.CLAUDE_SESSION_ERROR_PATTERNS = exports.extractAnsiSequences = exports.stripAnsi = exports.ANTIGRAVITY_SKIP_PATTERNS = exports.ANTIGRAVITY_SELECTION_LIST_PATTERN = exports.ANTIGRAVITY_SEPARATOR_PATTERN = exports.ANTIGRAVITY_THINKING_PATTERN = exports.ANTIGRAVITY_PROMPT_PATTERN = exports.VIBE_LOCAL_THINKING_PATTERN = exports.VIBE_LOCAL_PROMPT_PATTERN = exports.COPILOT_SKIP_PATTERNS = exports.COPILOT_SELECTION_LIST_PATTERN = exports.COPILOT_SEPARATOR_PATTERN = exports.COPILOT_THINKING_PATTERN = exports.COPILOT_PROMPT_PATTERN = exports.OPENCODE_SKIP_PATTERNS = exports.OPENCODE_SEPARATOR_PATTERN = exports.CLAUDE_SELECTION_LIST_FOOTER = exports.CLAUDE_MODEL_OVERLAY_FOOTER_PATTERN = exports.OPENCODE_SELECTION_LIST_PATTERN = exports.OPENCODE_PROCESSING_INDICATOR = exports.OPENCODE_RESPONSE_COMPLETE = exports.OPENCODE_LOADING_PATTERN = exports.OPENCODE_THINKING_PATTERN = exports.OPENCODE_PROMPT_AFTER_RESPONSE = exports.OPENCODE_PROMPT_PATTERN = exports.GEMINI_THINKING_PATTERN = exports.GEMINI_PROMPT_PATTERN = exports.MAX_PASTED_TEXT_RETRIES = exports.PASTED_TEXT_DETECT_DELAY = exports.PASTED_TEXT_PATTERN = exports.CODEX_STATUS_BAR_PATTERN = exports.CODEX_PAGER_FOOTER_PATTERN = exports.CODEX_APPROVAL_FOOTER_PATTERN = exports.CODEX_SELECTION_LIST_PATTERN = exports.CODEX_SEPARATOR_PATTERN = exports.CODEX_DIALOG_PATTERN = exports.CODEX_PROMPT_PATTERN = exports.CLAUDE_TRUST_DIALOG_PATTERN = exports.CLAUDE_SEPARATOR_PATTERN = exports.CLAUDE_PROMPT_PATTERN = exports.CODEX_INTERRUPT_HINT_PATTERN = exports.CODEX_THINKING_PATTERN = exports.CLAUDE_INTERRUPT_HINT_PATTERN = exports.CLAUDE_THINKING_PATTERN = exports.CLAUDE_SPINNER_CHARS = void 0;
+exports.CLAUDE_SESSION_ERROR_REGEX_PATTERNS = exports.CLAUDE_SESSION_ERROR_PATTERNS = exports.extractAnsiSequences = exports.stripAnsi = exports.ANTIGRAVITY_SKIP_PATTERNS = exports.ANTIGRAVITY_SELECTION_LIST_PATTERN = exports.ANTIGRAVITY_SEPARATOR_PATTERN = exports.ANTIGRAVITY_THINKING_PATTERN = exports.ANTIGRAVITY_PROMPT_PATTERN = exports.VIBE_LOCAL_THINKING_PATTERN = exports.VIBE_LOCAL_PROMPT_PATTERN = exports.COPILOT_SKIP_PATTERNS = exports.COPILOT_SELECTION_LIST_PATTERN = exports.COPILOT_SEPARATOR_PATTERN = exports.COPILOT_THINKING_PATTERN = exports.COPILOT_PROMPT_PATTERN = exports.OPENCODE_SKIP_PATTERNS = exports.OPENCODE_SEPARATOR_PATTERN = exports.CLAUDE_SELECTION_LIST_FOOTER = exports.CLAUDE_MODEL_OVERLAY_FOOTER_PATTERN = exports.OPENCODE_SELECTION_LIST_PATTERN = exports.OPENCODE_PROCESSING_INDICATOR = exports.OPENCODE_RESPONSE_COMPLETE = exports.OPENCODE_LOADING_PATTERN = exports.OPENCODE_THINKING_PATTERN = exports.OPENCODE_PROMPT_AFTER_RESPONSE = exports.OPENCODE_PROMPT_PATTERN = exports.GEMINI_THINKING_PATTERN = exports.GEMINI_PROMPT_PATTERN = exports.MAX_PASTED_TEXT_RETRIES = exports.PASTED_TEXT_DETECT_DELAY = exports.PASTED_TEXT_PATTERN = exports.CODEX_STATUS_BAR_PATTERN = exports.CODEX_PAGER_FOOTER_PATTERN = exports.CODEX_APPROVAL_FOOTER_PATTERN = exports.CODEX_SELECTION_LIST_PATTERN = exports.CODEX_SEPARATOR_PATTERN = exports.CODEX_HOOKS_REVIEW_ANCHORS = exports.CODEX_DIALOG_PATTERN = exports.CODEX_PROMPT_PATTERN = exports.CLAUDE_TRUST_DIALOG_PATTERN = exports.CLAUDE_SEPARATOR_PATTERN = exports.CLAUDE_PROMPT_PATTERN = exports.CODEX_INTERRUPT_HINT_PATTERN = exports.CODEX_THINKING_PATTERN = exports.CLAUDE_INTERRUPT_HINT_PATTERN = exports.CLAUDE_THINKING_PATTERN = exports.CLAUDE_SPINNER_CHARS = void 0;
 exports.isCodexTurnActive = isCodexTurnActive;
 exports.findClaudeChromeStart = findClaudeChromeStart;
 exports.isCodexPromptReady = isCodexPromptReady;
 exports.getCodexActiveDialog = getCodexActiveDialog;
+exports.getCodexLifecycleDialog = getCodexLifecycleDialog;
 exports.detectThinking = detectThinking;
 exports.getCliToolPatterns = getCliToolPatterns;
 exports.stripBoxDrawing = stripBoxDrawing;
@@ -330,7 +331,18 @@ function isCodexPromptReady(output) {
  * update dialog wins over its own "Press enter to continue" footer, because Enter
  * on the update dialog could confirm the default "1. Update now" (npm install).
  */
-function getCodexActiveDialog(output) {
+/**
+ * The lines of Codex's ACTIVE region: everything strictly below the bottom-most
+ * genuine input-prompt line, or the whole frame when there is no prompt line
+ * (Issue #892).
+ *
+ * This is the one rule that keeps every Codex dialog classifier honest.
+ * capturePane returns scrollback, so a dialog that was answered minutes ago is
+ * still in the frame; only what sits BELOW the live prompt is still awaiting a
+ * key. Shared by getCodexActiveDialog and getCodexLifecycleDialog so the two
+ * cannot drift into disagreeing about what "active" means.
+ */
+function codexActiveRegionLines(output) {
     const lines = output.split('\n');
     // Index of the bottom-most genuine input-prompt line (-1 if none).
     let promptIdx = -1;
@@ -340,10 +352,12 @@ function getCodexActiveDialog(output) {
             break;
         }
     }
-    // Active region = lines strictly below the genuine prompt (the whole frame when
-    // there is no genuine prompt). Residual dialog text above a live prompt is
-    // excluded, so a dialog lingering in scrollback is never treated as active.
-    const active = lines.slice(promptIdx + 1).join('\n');
+    return lines.slice(promptIdx + 1);
+}
+function getCodexActiveDialog(output) {
+    // Residual dialog text above a live prompt is excluded, so a dialog lingering
+    // in scrollback is never treated as active.
+    const active = codexActiveRegionLines(output).join('\n');
     if (active === '') {
         return null;
     }
@@ -359,6 +373,134 @@ function getCodexActiveDialog(output) {
     }
     return null;
 }
+/**
+ * Anchors of codex's "Hooks need review" launch dialog — screen 1 of the three
+ * it can put in front of a session (Issue #1760, re-measured on codex-cli
+ * 0.148.0 for Issue #1829):
+ *
+ * ```
+ *  Hooks need review
+ *  4 hooks are new or changed.
+ *  Hooks can run outside the sandbox after you trust them.
+ *
+ * > 1. Review hooks
+ *   2. Trust all and continue
+ *   3. Continue without trusting (hooks won't run)
+ *   Press enter to confirm or esc to go back
+ * ```
+ *
+ * The hook COUNT is data — 0.147.0 said 5, 0.148.0 said 4 — so neither anchor
+ * reads it. Both strings are required so a "hooks" mention elsewhere cannot
+ * select an option on a live prompt.
+ */
+exports.CODEX_HOOKS_REVIEW_ANCHORS = ['Hooks need review', 'Continue without trusting'];
+/**
+ * Footer of screen 2, the hooks LIST, new in codex-cli 0.148.0 (Issue #1829):
+ * `Press t to trust all; enter to review hooks; esc to close`.
+ *
+ * The semicolon is what separates it from screen 3's footer — "trust all;" and
+ * "trust;" are disjoint — and matching the footer rather than the table above it
+ * keeps the two screens distinguishable by a single line each.
+ */
+const CODEX_HOOKS_LIST_FOOTER_PATTERN = /press\s+t\s+to\s+trust\s+all\s*;/i;
+/**
+ * Footer of screen 3, the per-hook review DETAIL (Issue #1829):
+ * `Press t to trust; esc to go back`. Where both live sessions in the Issue were
+ * found parked.
+ */
+const CODEX_HOOKS_DETAIL_FOOTER_PATTERN = /press\s+t\s+to\s+trust\s*;/i;
+/**
+ * How much of the active region {@link getCodexLifecycleDialog} judges, in
+ * non-blank lines counted from the bottom (Issue #1829).
+ *
+ * `getCodexActiveDialog` searches the whole active region, which is right for
+ * its caller: `waitForReady` only ever runs during `startSession`, when nothing
+ * else can be on screen. This classifier runs on every Auto-Yes poll for the
+ * life of the session, where "active region" alone is not enough — a codex
+ * approval request renders no `› ` composer line, so an approval that comes up
+ * while a dismissed hooks screen is still inside the capture window would have
+ * the whole frame as its active region and would be mistaken for the dialog.
+ * Requiring the dialog to be in the TAIL is what separates the screen the user
+ * is looking at from the one they have already left.
+ *
+ * 12 lines fits the tallest screen this has to recognise (the review dialog's
+ * two anchors sit 6 lines apart) and none of the shorter frames below it.
+ */
+const CODEX_LIFECYCLE_TAIL_LINES = 12;
+/**
+ * The interactive update dialog, by its option-3 label or its option-1 line.
+ *
+ * Deliberately stricter than `getCodexActiveDialog`'s `Update` AND `Skip`
+ * fallback: that pair can occur in ordinary agent output, and here a false
+ * positive silently stops Auto-Yes answering a real prompt. Both anchors below
+ * are dialog chrome that agent output does not produce.
+ */
+const CODEX_UPDATE_DIALOG_ANCHORS = [
+    /skip until next version/i,
+    /^\s*[›❯]?\s*\d+\.\s*Update now/im,
+];
+/** The directory-trust dialog's question line. */
+const CODEX_TRUST_DIALOG_ANCHOR = /Do you trust/;
+/**
+ * Classify the bottom-most ACTIVE codex lifecycle screen (Issue #1829).
+ *
+ * Position-based, via {@link codexActiveRegionLines}: a dialog left in
+ * scrollback above a live prompt is not active and returns `null`. That is not
+ * a detail — the auto-answer guard in the Auto-Yes poller is built on this
+ * function, and a whole-frame version of it would switch Auto-Yes off for the
+ * rest of a codex session the moment any launch dialog scrolled past.
+ *
+ * The two hooks screens are matched FIRST and bottom-up, because a stuck pane
+ * holds screen 2 above screen 3 and the way out of each differs. The remaining
+ * three are region-level substring tests, which is all their anchors allow:
+ * the review dialog's are on two different lines.
+ *
+ * Deliberately NOT used to decide whether a prompt exists. `detectPrompt` still
+ * reports these screens, so a human still sees them; what this function gates is
+ * only whether a machine may answer on their behalf.
+ *
+ * @param output - ANSI-stripped pane capture
+ * @returns The active lifecycle screen, or null when none is
+ */
+function getCodexLifecycleDialog(output) {
+    const activeLines = codexActiveRegionLines(output);
+    const window = [];
+    for (let i = activeLines.length - 1; i >= 0 && window.length < CODEX_LIFECYCLE_TAIL_LINES; i--) {
+        if (activeLines[i].trim() === '')
+            continue;
+        window.unshift(activeLines[i]);
+    }
+    if (window.length === 0)
+        return null;
+    const text = window.join('\n');
+    // One bottom-up pass, returning on the first line that decides the question --
+    // including the lines that decide it NEGATIVELY. A stuck pane holds screen 2
+    // above screen 3, and an approval request can come up with a hooks screen
+    // still inside the capture window; in both cases the screen the user is
+    // looking at is the lower one.
+    for (let i = window.length - 1; i >= 0; i--) {
+        const line = window[i];
+        if (CODEX_HOOKS_LIST_FOOTER_PATTERN.test(line))
+            return 'hooks-list';
+        if (CODEX_HOOKS_DETAIL_FOOTER_PATTERN.test(line))
+            return 'hooks-detail';
+        // The agent asking the human for permission mid-turn (Issue #1628's
+        // "esc to cancel" footer, which no lifecycle screen wears). This is exactly
+        // the prompt Auto-Yes exists to answer, so whatever lifecycle text is still
+        // above it has been left behind and must not withhold the answer.
+        if (exports.CODEX_APPROVAL_FOOTER_PATTERN.test(line))
+            return null;
+        if (CODEX_UPDATE_DIALOG_ANCHORS.some((pattern) => pattern.test(line)))
+            return 'update';
+        if (CODEX_TRUST_DIALOG_ANCHOR.test(line))
+            return 'trust';
+        // Both anchors required, so a stray "hooks" mention cannot claim the screen.
+        if (line.includes(exports.CODEX_HOOKS_REVIEW_ANCHORS[1]) && text.includes(exports.CODEX_HOOKS_REVIEW_ANCHORS[0])) {
+            return 'hooks-review';
+        }
+    }
+    return null;
+}
 /**
  * Codex separator pattern
  */