Merge pull request #515 from irisitymichaelgrundberg/feat/codex-reasoning-effort

feat(codex): start a codex session at a chosen reasoning effort

docs/architecture-invariants.md

@@ -37,7 +37,7 @@ Pure helpers unit-tested in `test/base-path.test.ts` + `test/webview-proxy.test.
 
 ### External CLI modes (OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek, OMP)
 
-**External CLI modes (OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek, OMP)**: `isExternalCliMode()` in `session.ts` (`mode === 'opencode' || 'codex' || 'gemini' || 'antigravity' || 'pi' || 'grok' || 'deepseek'`) gates Claude-specific behavior — Ralph tracker, BashToolParser, token/CLI-info parsing, and ❯-prompt readiness detection are all skipped (these CLIs render their own TUIs; readiness = output stabilization instead). ⚠️ **Work detection left this gate in #385** and is now per-CLI `capabilities.workDetect` data (`promptGlyph` + `workingLine`), because gating it on the mode left every Codex session reporting `idle` for its entire life; a CLI declaring neither falls back to Claude's pair, which is logic-identical to the pre-registry behaviour. All seven modes **require tmux — no direct PTY fallback** — because secrets are injected via `tmux setenv` (socket-scoped `${this.tmux()} setenv`, never on the spawn command line): OpenCode gets `OPENCODE_CONFIG_CONTENT` etc., Codex gets `OPENAI_API_KEY`/`CODEX_API_KEY`/`CODEX_HOME` (`setCodexEnvVars`), Gemini gets `GEMINI_API_KEY`/`GOOGLE_API_KEY`/`GOOGLE_CLOUD_PROJECT`/`GOOGLE_APPLICATION_CREDENTIALS`/`GOOGLE_GENAI_USE_VERTEXAI` etc. (`setGeminiEnvVars`, all in `tmux-manager.ts`). Codex specifics: command built by `buildCodexCommand()` (`--model`, `resume <id>`, `--dangerously-bypass-approvals-and-sandbox` from the `codexConfig` payload / `codexDangerouslyBypassApprovals` app setting; `renderMode` is schema-coerced to `'hybrid'`, the only supported mode). Gemini specifics: command built by `buildGeminiCommand()` (`--skip-trust` always, `--approval-mode <default|auto_edit|yolo|plan>` defaulting to `yolo` for parity with Claude's `--dangerously-skip-permissions`, `--model`, `--resume` from the `geminiConfig` payload); availability via `GET /api/gemini/status` — session/quick-start routes fail with `OPERATION_FAILED` + install hint (`npm install -g @google/gemini-cli`) when missing. Codex, Gemini, Antigravity, Pi, Grok, DeepSeek and OMP export `COLORTERM=truecolor` and unset `NO_COLOR`; `opencode` unsets `COLORTERM`. **Terminal colour env** under Session launch modes covers Claude and says which panes those declarations actually reach. Gemini joins `isAltScreenStripMode()` (Codex/Claude/Gemini are Ink TUIs that repaint inline → strip alt-screen/`3J` so scrollback survives). Codex availability via `GET /api/codex/status`. Antigravity specifics: command built by `buildAntigravityCommand()` (`--model`, `--conversation <id>` resume, `--dangerously-skip-permissions` from the `antigravityConfig` payload); availability via `GET /api/antigravity/status` — routes fail with `OPERATION_FAILED` + install hint (`curl -fsSL https://antigravity.google/cli/install.sh | bash`) when missing. Unlike the other three it is NOT an npm package (standalone binary, `~/.local/bin/agy`), which is why `docker/agent.Dockerfile` installs it with its own `--dir /usr/local/bin` step rather than in the `npm install -g` line, and why it does NOT join `isAltScreenStripMode()`. Frontend: run-mode dropdown → `runCodex()`/`runGemini()` in `session-ui.js` ("Run CX"/"Run GM" labels), App Settings → Agents & CLIs → Codex; Respawn/Ralph options are Claude-only, so session options open on the Session tab for external CLI sessions. ⚠️ `run*()` MUST unwrap the `{success,data}` envelope (`(await res.json()).data.available` / `data.data.sessionId`) — reading the raw shape silently breaks the run. Tests: `test/run-mode-ui.test.ts` + `test/gemini-mode.test.ts` (vm-sandbox harness, no real DOM). Grok specifics: command built by `buildGrokCommand()` (`--always-approve` from `grokConfig.alwaysApprove` — grok's `bypassPermissions` permission mode, deny rules still apply; `--model`; `--resume <id>` / `--continue`, id-regexed so grok's resume-by-TITLE feature can never put an arbitrary string on the spawn line); availability via `GET /api/grok/status`, which carries `version` because the resolver version-probes candidates (`grok` has npm squatters, e.g. @vibe-kit/grok-cli — `GROK_VERSION_REGEX` is shared with the dependency registry so doctor and run mode agree). Like antigravity it is a standalone binary (xAI installer → `~/.grok/bin`, symlinked into `~/.local/bin`), so `docker/agent.Dockerfile` installs it in its own step (copy to `/usr/local/bin`, drop root's `~/.grok` in the same layer) and it stays OUT of `isAltScreenStripMode()` (fullscreen alt-screen TUI with mouse support — the opencode case, not the Ink case). Env allowlist: `GROK_*` plus the vendor namespace `XAI_*` (`XAI_API_KEY` is grok's documented headless auth var — the same narrow-vendor-namespace reasoning as `GOOGLE_*` for gemini). Docker cred seeding is per-file (`auth.json`, `config.toml`, `pager.toml` from `~/.grok` — the dir also holds `sessions/`, `memory/`, and the ~160MB binary under `downloads/`). Grok tests: `test/grok-mode.test.ts`, `test/grok-cli-resolver.test.ts`.
+**External CLI modes (OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek, OMP)**: `isExternalCliMode()` in `session.ts` (`mode === 'opencode' || 'codex' || 'gemini' || 'antigravity' || 'pi' || 'grok' || 'deepseek'`) gates Claude-specific behavior — Ralph tracker, BashToolParser, token/CLI-info parsing, and ❯-prompt readiness detection are all skipped (these CLIs render their own TUIs; readiness = output stabilization instead). ⚠️ **Work detection left this gate in #385** and is now per-CLI `capabilities.workDetect` data (`promptGlyph` + `workingLine`), because gating it on the mode left every Codex session reporting `idle` for its entire life; a CLI declaring neither falls back to Claude's pair, which is logic-identical to the pre-registry behaviour. All seven modes **require tmux — no direct PTY fallback** — because secrets are injected via `tmux setenv` (socket-scoped `${this.tmux()} setenv`, never on the spawn command line): OpenCode gets `OPENCODE_CONFIG_CONTENT` etc., Codex gets `OPENAI_API_KEY`/`CODEX_API_KEY`/`CODEX_HOME` (`setCodexEnvVars`), Gemini gets `GEMINI_API_KEY`/`GOOGLE_API_KEY`/`GOOGLE_CLOUD_PROJECT`/`GOOGLE_APPLICATION_CREDENTIALS`/`GOOGLE_GENAI_USE_VERTEXAI` etc. (`setGeminiEnvVars`, all in `tmux-manager.ts`). Codex specifics: command built by `buildCodexCommand()` (`--model`, `--config model_reasoning_effort=<level>` from `reasoningEffort`, `--config tui.animations=<bool>` from `animations`, `resume <id>`, `--dangerously-bypass-approvals-and-sandbox` from the `codexConfig` payload / `codexDangerouslyBypassApprovals` app setting; `renderMode` is schema-coerced to `'hybrid'`, the only supported mode). Gemini specifics: command built by `buildGeminiCommand()` (`--skip-trust` always, `--approval-mode <default|auto_edit|yolo|plan>` defaulting to `yolo` for parity with Claude's `--dangerously-skip-permissions`, `--model`, `--resume` from the `geminiConfig` payload); availability via `GET /api/gemini/status` — session/quick-start routes fail with `OPERATION_FAILED` + install hint (`npm install -g @google/gemini-cli`) when missing. Codex, Gemini, Antigravity, Pi, Grok, DeepSeek and OMP export `COLORTERM=truecolor` and unset `NO_COLOR`; `opencode` unsets `COLORTERM`. **Terminal colour env** under Session launch modes covers Claude and says which panes those declarations actually reach. Gemini joins `isAltScreenStripMode()` (Codex/Claude/Gemini are Ink TUIs that repaint inline → strip alt-screen/`3J` so scrollback survives). Codex availability via `GET /api/codex/status`. Antigravity specifics: command built by `buildAntigravityCommand()` (`--model`, `--conversation <id>` resume, `--dangerously-skip-permissions` from the `antigravityConfig` payload); availability via `GET /api/antigravity/status` — routes fail with `OPERATION_FAILED` + install hint (`curl -fsSL https://antigravity.google/cli/install.sh | bash`) when missing. Unlike the other three it is NOT an npm package (standalone binary, `~/.local/bin/agy`), which is why `docker/agent.Dockerfile` installs it with its own `--dir /usr/local/bin` step rather than in the `npm install -g` line, and why it does NOT join `isAltScreenStripMode()`. Frontend: run-mode dropdown → `runCodex()`/`runGemini()` in `session-ui.js` ("Run CX"/"Run GM" labels), App Settings → Agents & CLIs → Codex; Respawn/Ralph options are Claude-only, so session options open on the Session tab for external CLI sessions. ⚠️ `run*()` MUST unwrap the `{success,data}` envelope (`(await res.json()).data.available` / `data.data.sessionId`) — reading the raw shape silently breaks the run. Tests: `test/run-mode-ui.test.ts` + `test/gemini-mode.test.ts` (vm-sandbox harness, no real DOM). Grok specifics: command built by `buildGrokCommand()` (`--always-approve` from `grokConfig.alwaysApprove` — grok's `bypassPermissions` permission mode, deny rules still apply; `--model`; `--resume <id>` / `--continue`, id-regexed so grok's resume-by-TITLE feature can never put an arbitrary string on the spawn line); availability via `GET /api/grok/status`, which carries `version` because the resolver version-probes candidates (`grok` has npm squatters, e.g. @vibe-kit/grok-cli — `GROK_VERSION_REGEX` is shared with the dependency registry so doctor and run mode agree). Like antigravity it is a standalone binary (xAI installer → `~/.grok/bin`, symlinked into `~/.local/bin`), so `docker/agent.Dockerfile` installs it in its own step (copy to `/usr/local/bin`, drop root's `~/.grok` in the same layer) and it stays OUT of `isAltScreenStripMode()` (fullscreen alt-screen TUI with mouse support — the opencode case, not the Ink case). Env allowlist: `GROK_*` plus the vendor namespace `XAI_*` (`XAI_API_KEY` is grok's documented headless auth var — the same narrow-vendor-namespace reasoning as `GOOGLE_*` for gemini). Docker cred seeding is per-file (`auth.json`, `config.toml`, `pager.toml` from `~/.grok` — the dir also holds `sessions/`, `memory/`, and the ~160MB binaryLine truncated
 
 **DeepSeek Harness (`dsh`) specifics** — the mode that breaks three of the assumptions the six above share, so read this before changing anything about it.
 

src/config/cli-registry/stock.ts

@@ -11,6 +11,7 @@
  */
 
 import type { CliEntry } from './types.js';
+import { CODEX_REASONING_EFFORTS } from '../../types/session.js';
 
 const HOME_DIRS = {
   local: '~/.local/bin',
@@ -534,6 +535,7 @@ const CODEX: CliEntry = {
       bypassApprovals: { type: 'bool' },
       animations: { type: 'bool' },
       model: { type: 'token', pattern: 'model' },
+      reasoningEffort: { type: 'enum', values: [...CODEX_REASONING_EFFORTS] },
       resumeId: { type: 'token', pattern: 'id' },
     },
     variants: [
@@ -545,6 +547,14 @@ const CODEX: CliEntry = {
           { flag: '--config', value: 'tui.animations=true', when: { param: 'animations', is: true } },
           { flag: '--config', value: 'tui.animations=false', when: { param: 'animations', is: false } },
           { flag: '--model', valueFrom: 'model', when: { param: 'model', state: 'set' } },
+          // One literal per level: an argv token cannot splice a value into a literal, and
+          // `model_reasoning_effort=<level>` is a single `--config` value. The enum above is
+          // what admits a level, so an unknown one emits nothing.
+          ...CODEX_REASONING_EFFORTS.map((level) => ({
+            flag: '--config',
+            value: `model_reasoning_effort=${level}`,
+            when: { param: 'reasoningEffort', is: level },
+          })),
           { lit: 'resume', when: { param: 'resumeId', state: 'set' } },
           { valueFrom: 'resumeId', when: { param: 'resumeId', state: 'set' } },
         ],

src/types/session.ts

@@ -377,6 +377,16 @@ export function isEffortLevel(value: string | undefined): value is EffortLevel {
   return value !== undefined && (EFFORT_LEVELS as readonly string[]).includes(value);
 }
 
+/**
+ * Reasoning effort levels codex accepts as `model_reasoning_effort` (codex-cli 0.154.0).
+ * Which of them a given model honours is codex's business; Codeman only keeps the value
+ * to a known word, since it lands in the launch argv.
+ */
+export const CODEX_REASONING_EFFORTS = ['none', 'minimal', 'low', 'medium', 'high', 'xhigh', 'max', 'ultra'] as const;
+
+/** Codex reasoning effort for a session, passed as `--config model_reasoning_effort=<level>` */
+export type CodexReasoningEffort = (typeof CODEX_REASONING_EFFORTS)[number];
+
 /** OpenCode session configuration */
 export interface OpenCodeConfig {
   /** Model identifier (e.g., "anthropic/claude-sonnet-4-5", "openai/gpt-5.2", "ollama/codellama") */
@@ -398,6 +408,8 @@ export type CodexRenderMode = 'hybrid';
 export interface CodexConfig {
   /** Model identifier (e.g., "gpt-5", "o4-mini"). Passed via --model. */
   model?: string;
+  /** Reasoning effort for this session. Passed via --config model_reasoning_effort=<level>. */
+  reasoningEffort?: CodexReasoningEffort;
   /** Resume a previous codex conversation by session id (passed via --resume) */
   resumeSessionId?: string;
   /** Bypass approval prompts (passes --dangerously-bypass-approvals-and-sandbox) */

src/web/schemas.ts

@@ -18,6 +18,7 @@ import {
   MIN_TERMINAL_SCROLLBACK_LINES,
 } from '../config/terminal-history.js';
 import { MAX_EDITABLE_BYTES } from '../config/file-editing.js';
+import { CODEX_REASONING_EFFORTS } from '../types/session.js';
 import { MIN_MATCH_LENGTH, MAX_MATCH_LENGTH } from '../config/agent-wait.js';
 import { MAX_WAKE_MACS } from '../config/remote-wake-limits.js';
 import { MAX_INPUT_LENGTH } from '../config/terminal-limits.js';
@@ -298,6 +299,7 @@ const CodexConfigSchema = z
       .max(100)
       .regex(/^[a-zA-Z0-9._\-/]+$/)
       .optional(),
+    reasoningEffort: z.enum(CODEX_REASONING_EFFORTS).optional(),
     resumeSessionId: z
       .string()
       .max(100)

test/cli-registry-spawn-golden.test.ts

@@ -24,6 +24,7 @@
 import { describe, it, expect } from 'vitest';
 import { getCli } from '../src/config/cli-registry/registry.js';
 import { buildSpawnCommandFromRegistry, type SpawnBridgeOptions } from '../src/session-cli-registry-bridge.js';
+import { CODEX_REASONING_EFFORTS } from '../src/types/session.js';
 
 /** A fixed session id, so `--session-id` is stable across runs. */
 const SID = '0f9c2b14-1111-2222-3333-444455556666';
@@ -131,6 +132,18 @@ describe('codex', () => {
   it('resumes with a POSITIONAL subcommand, not a flag', () => {
     expect(cx({ model: 'gpt-5', resumeSessionId: 'roll_42' })).toBe('codex --model gpt-5 resume roll_42');
   });
+
+  it('sends reasoning effort as one model_reasoning_effort config value, for every level', () => {
+    for (const level of CODEX_REASONING_EFFORTS) {
+      expect(cx({ reasoningEffort: level })).toBe(`codex --config model_reasoning_effort=${level}`);
+    }
+  });
+
+  it('keeps reasoning effort ahead of the resume subcommand', () => {
+    expect(cx({ model: 'gpt-5', reasoningEffort: 'high', resumeSessionId: 'roll_42' })).toBe(
+      'codex --model gpt-5 --config model_reasoning_effort=high resume roll_42'
+    );
+  });
 });
 
 describe('gemini', () => {

test/codex-reasoning-effort-schema.test.ts

@@ -0,0 +1,41 @@
+/**
+ * @fileoverview `codexConfig.reasoningEffort` on the create routes.
+ *
+ * The level becomes part of a `--config model_reasoning_effort=<level>` launch token, so the
+ * schema admits only the words codex knows; anything else fails the request rather than
+ * reaching the argv.
+ */
+
+import { describe, it, expect } from 'vitest';
+import { CreateSessionSchema, QuickStartSchema } from '../src/web/schemas.js';
+import { CODEX_REASONING_EFFORTS } from '../src/types/session.js';
+
+describe('codexConfig.reasoningEffort', () => {
+  it('accepts every level codex knows on both create routes', () => {
+    for (const level of CODEX_REASONING_EFFORTS) {
+      const created = CreateSessionSchema.parse({
+        workingDir: '/tmp',
+        mode: 'codex',
+        codexConfig: { reasoningEffort: level },
+      });
+      expect(created.codexConfig?.reasoningEffort).toBe(level);
+      const quick = QuickStartSchema.parse({
+        caseName: 'work',
+        mode: 'codex',
+        codexConfig: { reasoningEffort: level },
+      });
+      expect(quick.codexConfig?.reasoningEffort).toBe(level);
+    }
+  });
+
+  it('rejects a level codex does not know, and anything shaped like shell, on both create routes', () => {
+    for (const reasoningEffort of ['bogus', 'HIGH', 'high; rm -rf /', '']) {
+      expect(() =>
+        CreateSessionSchema.parse({ workingDir: '/tmp', mode: 'codex', codexConfig: { reasoningEffort } })
+      ).toThrow();
+      expect(() =>
+        QuickStartSchema.parse({ caseName: 'work', mode: 'codex', codexConfig: { reasoningEffort } })
+      ).toThrow();
+    }
+  });
+});

test/routes/external-cli-bypass-clamp.test.ts

@@ -104,6 +104,20 @@ describe('clampExternalCliBypassForOwner — multi-user mode', () => {
     expect(out.grokConfig).toEqual({ alwaysApprove: false, model: 'grok-4.5' });
   });
 
+  it("keeps a non-granted owner's codex reasoning effort while forcing bypass off", async () => {
+    // The clamp rewrites one field and must carry the rest; a clamp rebuilt from named
+    // fields would drop the effort here without a word.
+    const out = await _clampExternalCliBypassForOwner(
+      'peon',
+      { dangerouslyBypassApprovals: true, reasoningEffort: 'xhigh' },
+      undefined,
+      undefined,
+      undefined,
+      undefined
+    );
+    expect(out.codexConfig).toEqual({ dangerouslyBypassApprovals: false, reasoningEffort: 'xhigh' });
+  });
+
   it('leaves codex/antigravity/grok absent when nothing was sent (they already spawn safe)', async () => {
     const out = await _clampExternalCliBypassForOwner('peon', undefined, undefined, undefined, undefined, undefined);
     expect(out.codexConfig).toBeUndefined();