Merge pull request #385 from irisitymichaelgrundberg/fix/work-detection-external-clis

Merging with follow-up fixes applied on master: workingLine routed through compileVersionRegex() in both the schema refine and _workingLinePattern(), the Codex footer matched case-insensitively on the E, plus the doc passages that stated the retired Claude-mode-only rule.

src/config/cli-registry/schema.ts

@@ -274,6 +274,26 @@ const capabilitiesSchema = z
     effort: z.boolean(),
     agentSkillInjection: z.boolean(),
     statusLineTelemetry: z.boolean(),
+    workDetect: z
+      .object({
+        promptGlyph: z.string().min(1).max(8),
+        // Compiled per session, so a broken pattern must fail at LOAD time rather than
+        // throw inside the PTY data handler.
+        workingLine: z
+          .string()
+          .min(1)
+          .max(400)
+          .refine((src) => {
+            try {
+              new RegExp(src);
+              return true;
+            } catch {
+              return false;
+            }
+          }, 'workingLine must be a valid regular expression'),
+      })
+      .strict()
+      .optional(),
     model: z
       .object({ source: z.enum(['flag', 'claude-settings-file', 'none']), param: z.string().optional() })
       .strict(),

src/config/cli-registry/stock.ts

@@ -183,6 +183,13 @@ const CLAUDE: CliEntry = {
   },
   capabilities: {
     external: false,
+    // The historical hard-coded pair, now stated as data. `workingLine` matches both the
+    // `✻ Actualizing… (39s · ↓ 2.0k tokens)` status line and the bare `esc to interrupt`
+    // footer, because tmux repaints partially and only one of the two may land in a chunk.
+    workDetect: {
+      promptGlyph: '❯',
+      workingLine: String.raw`…\s*\((?:\d+h\s+)?(?:\d+m\s+)?\d+s\b|esc to interrupt`,
+    },
     requiresMux: false,
     // Claude installs Codeman's own hooks block into every workspace it runs in, so its
     // stop/idle signals are unconditional — no per-session veto, unlike deepseek's bridge.
@@ -418,6 +425,11 @@ const CODEX: CliEntry = {
   },
   capabilities: {
     ...agentDefaults(),
+    // Codex draws `› Ask Codex to do anything` on its composer row and
+    // `Working (2m 49s • esc to interrupt)` above it while a turn runs. It animates no
+    // braille spinner, and it never prints `esc to interrupt` at rest, so that phrase
+    // alone separates a running turn from an idle one.
+    workDetect: { promptGlyph: '›', workingLine: 'esc to interrupt' },
     transcript: 'codex-rollout',
     altScreen: 'strip-full',
     echo: { policy: 'predict', anchor: { kind: 'cursor' }, predictProfile: 'codex' },

src/config/cli-registry/types.ts

@@ -306,6 +306,29 @@ export interface CliCapabilities {
    * independent — see this interface's own doc comment.
    */
   external: boolean;
+  /**
+   * How to read this CLI's own TUI for whether it is mid-turn.
+   *
+   * Codeman infers a working agent from the pane, so the two strings it needs are the
+   * ones that differ per CLI: the glyph on the composer row, and the status line the CLI
+   * draws while a turn runs. Holding them here is what lets a non-Claude CLI report work
+   * at all — `external` used to gate the whole detector, so every external CLI reported
+   * itself permanently idle even mid-turn.
+   *
+   * `promptGlyph` only ARMS the idle confirmation and is never on its own evidence that a
+   * turn ended, because a CLI redraws its composer throughout a turn. `workingLine` is
+   * the evidence, and `_confirmIdle` consults it before believing the pane went quiet.
+   *
+   * An entry that omits this field keeps Codeman's historical behaviour: the Claude glyph
+   * arms the confirmation and the Claude working line answers it. Leave it out for a CLI
+   * whose TUI nobody has characterised, and its sessions report work exactly as before.
+   */
+  workDetect?: {
+    /** The glyph this CLI draws on its composer row, e.g. Claude's `❯`, Codex's `›`. */
+    promptGlyph: string;
+    /** Source of a regex matching the status line this CLI draws while a turn runs. */
+    workingLine: string;
+  };
   /** No direct-PTY fallback: the CLI must run inside tmux (secrets ride tmux setenv). */
   requiresMux: boolean;
   /**

src/session.ts

@@ -481,6 +481,8 @@ export class Session extends EventEmitter {
   private _activityStreak: ActivityStreak | null = null; // Unbroken run of PTY repaints (working detection)
   private _lastPaneProbeAt = 0; // Throttle for the tmux screen probe
   private _lastPaneProbeWorking: boolean | null = null; // Its last verdict (null = could not read)
+  /** Lazily compiled `capabilities.workDetect.workingLine`. See _workingLinePattern(). */
+  private _workingLineRe: RegExp | undefined = undefined;
   private _trustDialogAccepted: boolean = false; // Stops the trust-dialog scan (answered, or given up)
   private _trustDialogAttempts = 0; // Keystrokes sent at the trust dialog
   private _lastTrustDialogScanAt = 0; // Throttle for the trust-dialog screen read
@@ -2388,12 +2390,14 @@ export class Session extends EventEmitter {
    * @param data raw PTY chunk, ANSI included
    */
   private _detectInteractiveActivity(data: string): void {
-    // The prompt line contains "❯" when Claude is waiting for input. It only ARMS
-    // the check and is NOT evidence the turn ended: Claude redraws the composer
-    // about once a second all the way through a turn, which is exactly how a
-    // working session used to flip to idle two seconds in. _confirmIdle() waits
-    // for the pane to actually go quiet before believing it.
-    if (data.includes('❯')) {
+    const workDetect = getCli(this.mode)?.capabilities.workDetect;
+    // The composer row carries this glyph when the CLI is waiting for input. It only
+    // ARMS the check and is NOT evidence the turn ended: a CLI redraws its composer
+    // about once a second all the way through a turn, which is exactly how a working
+    // session used to flip to idle two seconds in. _confirmIdle() waits for the pane to
+    // actually go quiet before believing it. A CLI that declares no glyph keeps Claude's,
+    // which is the glyph every such session has been armed by until now.
+    if (data.includes(workDetect?.promptGlyph ?? '❯')) {
       // Only start a new timeout if we're not already awaiting idle confirmation.
       // This prevents status bar redraws (which include the prompt) from resetting it.
       if (!this._awaitingIdleConfirmation) {
@@ -2412,9 +2416,10 @@ export class Session extends EventEmitter {
     // new status line does not rescue it either (tmux repaints partially, so the
     // complete line reaches the PTY only every few tens of seconds). An unbroken run
     // of repaints is the signal that survives. See session-activity.ts for the
-    // measurement. Claude only: an external CLI's TUI has no ❯, so nothing would
-    // ever arm the idle confirmation and such a session would latch busy forever.
-    if (!isExternalCliMode(this.mode)) {
+    // measurement. This needs a pane Codeman can read: without a glyph to arm the idle
+    // confirmation, a session latches busy forever. A CLI that declares work detection
+    // supplies its own glyph, and the non-external modes keep the run they always had.
+    if (workDetect || !isExternalCliMode(this.mode)) {
       this._activityStreak = trackActivityStreak(this._activityStreak, Date.now());
       // A streak is the TRIGGER to look, not the verdict: typing into the composer
       // also produces a steady stream of repaints. The screen settles it, and only
@@ -2449,10 +2454,32 @@ export class Session extends EventEmitter {
     if (now - this._lastPaneProbeAt < PANE_PROBE_MIN_INTERVAL_MS) return this._lastPaneProbeWorking;
     this._lastPaneProbeAt = now;
     const text = this._mux.capturePaneText?.(this._muxSession.muxName) ?? null;
-    this._lastPaneProbeWorking = text === null ? null : CLAUDE_WORKING_LINE_PATTERN.test(text);
+    this._lastPaneProbeWorking = text === null ? null : this._workingLinePattern().test(text);
     return this._lastPaneProbeWorking;
   }
 
+  /**
+   * The regex matching this CLI's "a turn is running" status line.
+   *
+   * Compiled once per session and cached: `_probePaneWorking` runs it against a whole
+   * pane capture on a timer, and the throttled text detector runs it against every
+   * accumulated chunk. A CLI that declares no pattern falls back to Claude's, which is
+   * the pattern every session used before the registry carried one.
+   */
+  private _workingLinePattern(): RegExp {
+    if (this._workingLineRe === undefined) {
+      const src = getCli(this.mode)?.capabilities.workDetect?.workingLine;
+      // The schema validates `workingLine` at load time, so a throw here would mean a
+      // registry that never loaded. Falling back beats taking the session down.
+      try {
+        this._workingLineRe = src ? new RegExp(src) : CLAUDE_WORKING_LINE_PATTERN;
+      } catch {
+        this._workingLineRe = CLAUDE_WORKING_LINE_PATTERN;
+      }
+    }
+    return this._workingLineRe;
+  }
+
   /**
    * Mark the pane as working. Idempotent: `working` is emitted on the transition
    * only, so the per-chunk detectors can all call it freely.
@@ -2541,10 +2568,6 @@ export class Session extends EventEmitter {
    * PTY data chunk. Receives accumulated raw data to process in one batch.
    */
   private _processExpensiveParsers(rawData: string): void {
-    // Skip Claude-specific parsers for external CLI sessions (Ralph tracker,
-    // BashToolParser, token + CLI-info parsing all depend on Claude's output format).
-    if (isExternalCliMode(this.mode)) return;
-
     // Lazy ANSI strip: only compute cleanData when a consumer actually needs it.
     let _cleanData: string | null = null;
     const getCleanData = (): string => {
@@ -2554,6 +2577,19 @@ export class Session extends EventEmitter {
       return _cleanData;
     };
 
+    // Work detection by status line, ahead of the external-CLI gate below. The pattern
+    // comes from the CLI's own registry entry, so this is the one parser here that is not
+    // Claude-specific — and it sat under that gate, which is why an external CLI reported
+    // itself idle through an entire turn. Guarded on the descriptor so a CLI without one
+    // still skips the ANSI strip the gate used to save it.
+    if (!this._isWorking && getCli(this.mode)?.capabilities.workDetect) {
+      if (this._workingLinePattern().test(getCleanData())) this._markWorking();
+    }
+
+    // Skip Claude-specific parsers for external CLI sessions (Ralph tracker,
+    // BashToolParser, token + CLI-info parsing all depend on Claude's output format).
+    if (isExternalCliMode(this.mode)) return;
+
     // Forward to Ralph tracker to detect Ralph loops and todos
     // (opencode sessions already returned early at line 1209)
     if (this._ralphTracker.enabled || !this._ralphTracker.autoEnableDisabled) {
@@ -2585,16 +2621,13 @@ export class Session extends EventEmitter {
       this.parseTaskDescriptionsFromTerminalData(getCleanData());
     }
 
-    // Work detection (text-based, needs clean data: the status line is coloured,
-    // so raw data has escape sequences between the `…` and the elapsed timer).
-    // Only check if a faster path didn't already trigger working state.
+    // Legacy gerunds, Claude-only. The status-line pattern above already ran for every
+    // CLI that declares one, so this adds only the older wording. Current Claude
+    // randomizes the word ("Actualizing…", "Finagling…"), so these catch a fraction of
+    // turns; the pattern above and the activity streak carry the rest.
     if (!this._isWorking) {
       const cleanData = getCleanData();
       if (
-        CLAUDE_WORKING_LINE_PATTERN.test(cleanData) ||
-        // Legacy gerunds. Current Claude randomizes the word ("Actualizing…",
-        // "Finagling…"), so these catch only a fraction of turns; the pattern
-        // above and the activity streak carry the rest.
         cleanData.includes('Thinking') ||
         cleanData.includes('Writing') ||
         cleanData.includes('Reading') ||

test/session-activity.test.ts

@@ -1,5 +1,5 @@
 /**
- * Working/idle detection for an interactive Claude pane.
+ * Working/idle detection for an interactive agent pane, Claude's and Codex's.
  *
  * The bug this pins: Claude redraws the composer (`❯`) about once a second all
  * the way through a turn, so the old "saw a ❯, wait 2s, call it idle" rule
@@ -7,11 +7,17 @@
  * worker: `GET /api/sessions` reported `idle` for a session that had been
  * running for 17 minutes and was mid-tool-call.
  *
+ * A second bug this pins: work detection read Claude's glyph and Claude's status line
+ * for every CLI, so a Codex session reported itself idle through an entire turn. Each CLI
+ * now names its own pair in `capabilities.workDetect`, and a CLI that names none reports
+ * work exactly as before.
+ *
  * The status-line fixtures below are verbatim captures from live panes
- * (`tmux -L codeman capture-pane -p`) on Claude Code 2.1.220.
+ * (`tmux -L codeman capture-pane -p`) on Claude Code 2.1.220 and Codex CLI 0.152.1.
  */
 import { describe, expect, it, vi, afterEach } from 'vitest';
 import { Session } from '../src/session.js';
+import { getCli } from '../src/config/cli-registry/index.js';
 import { CLAUDE_WORKING_LINE_PATTERN } from '../src/utils/regex-patterns.js';
 import {
   trackActivityStreak,
@@ -38,7 +44,7 @@ function feed(session: Session, data: string): void {
  * A session whose mux reports a fixed (or scripted) screen, so the pane probe has
  * something to read. Only `capturePaneText` is exercised by these paths.
  */
-function withFakePane(screen: string | (() => string)): Session {
+function withFakePane(screen: string | (() => string), mode: 'claude' | 'codex' = 'claude'): Session {
   const read = typeof screen === 'function' ? screen : () => screen;
   const mux = {
     isAvailable: () => true,
@@ -46,12 +52,26 @@ function withFakePane(screen: string | (() => string)): Session {
   } as unknown as NonNullable<Parameters<typeof Session.prototype.constructor>[0]>['mux'];
   return new Session({
     workingDir: '/tmp',
-    mode: 'claude',
+    mode,
     mux,
     muxSession: { muxName: 'codeman-test', sessionId: 'test', createdAt: Date.now() },
   } as ConstructorParameters<typeof Session>[0]);
 }
 
+/**
+ * Codex's pane, verbatim, while a turn runs and once it has finished. Codex draws `›` on
+ * its composer row through the whole turn, exactly as Claude draws `❯`, and prints
+ * `esc to interrupt` only while the turn is live.
+ */
+const CODEX_WORKING =
+  'Working (2m 49s • esc to interrupt)\n› Ask Codex to do anything\n' +
+  '  gpt-5.6-sol high · Context 59% left · ~/innovi/irisplus-ent-2 · main\n';
+const CODEX_FINISHED =
+  '─ Worked for 3m 47s ────────────────────\n› Ask Codex to do anything\n' +
+  '  gpt-5.6-sol high · Context 57% left · ~/innovi/irisplus-ent-2 · main\n';
+/** Codex's own composer repaint, the frame that arms the idle confirmation. */
+const CODEX_COMPOSER_REPAINT = '\x1b[31;1H\x1b[38;5;246m›\xa0\x1b[39m\x1b[0m';
+
 /** A composer repaint: the frame Claude ships roughly once a second while working. */
 const COMPOSER_REPAINT =
   '\x1b[31;1H\x1b[38;5;246m❯\xa0\x1b[39m\x1b[0m\x1b[33;1H  \x1b[38;5;246mOpus 5  in:143,699 out:669  ctx:14%\x1b[39m';
@@ -230,11 +250,13 @@ describe('Session interactive idle detection', () => {
     expect(session.status).toBe('idle');
   });
 
-  it('does not mark an external CLI pane working off raw activity', () => {
+  it('does not mark an uncharacterised CLI working off raw activity', () => {
     vi.useFakeTimers();
-    // Codex/Gemini/OpenCode render their own TUIs and have no ❯, so nothing would
-    // arm the idle confirmation, so a session marked working here would never recover.
-    const session = new Session({ workingDir: '/tmp', mode: 'codex' });
+    // Gemini and OpenCode render their own TUIs, and Codeman knows neither one's glyph,
+    // so nothing would arm the idle confirmation and a session marked working here would
+    // never recover. A CLI that names no glyph therefore reports no work at all.
+    expect(getCli('gemini')?.capabilities.workDetect).toBeUndefined();
+    const session = new Session({ workingDir: '/tmp', mode: 'gemini' });
     const events: string[] = [];
     session.on('working', () => events.push('working'));
 
@@ -245,6 +267,50 @@ describe('Session interactive idle detection', () => {
 
     expect(events).toEqual([]);
   });
+
+  it('marks a Codex pane working, and lets the turn end', () => {
+    vi.useFakeTimers();
+    let screen = CODEX_WORKING;
+    const session = withFakePane(() => screen, 'codex');
+    const events: string[] = [];
+    session.on('working', () => events.push('working'));
+    session.on('idle', () => events.push('idle'));
+
+    for (let i = 0; i < 3; i++) {
+      feed(session, CODEX_COMPOSER_REPAINT);
+      vi.advanceTimersByTime(1000);
+    }
+    vi.advanceTimersByTime(20_000);
+
+    // The old code reported this session idle for the whole turn.
+    expect(events).toEqual(['working']);
+    expect(session.status).toBe('busy');
+
+    // Turn over: the working footer gives way to the finished line, which must NOT
+    // read as work — it sits on screen for the whole idle period afterwards.
+    screen = CODEX_FINISHED;
+    vi.advanceTimersByTime(20_000);
+
+    expect(events).toEqual(['working', 'idle']);
+    expect(session.status).toBe('idle');
+  });
+});
+
+describe("codex's work-detection descriptor", () => {
+  const codex = getCli('codex')?.capabilities.workDetect;
+
+  it('matches the footer Codex prints while a turn runs', () => {
+    expect(new RegExp(codex!.workingLine).test(CODEX_WORKING)).toBe(true);
+  });
+
+  it('does not match the finished line, nor the idle footer', () => {
+    expect(new RegExp(codex!.workingLine).test(CODEX_FINISHED)).toBe(false);
+  });
+
+  it('names the glyph Codex actually draws on its composer row', () => {
+    expect(CODEX_COMPOSER_REPAINT).toContain(codex!.promptGlyph);
+    expect(CODEX_WORKING).toContain(codex!.promptGlyph);
+  });
 });
 
 describe('wire activity stamp across recovery', () => {