app-server.md +344 −38
21Requests include `method`, `params`, and `id`:21Requests include `method`, `params`, and `id`:
22 22
23```json23```json
2424{ "method": "thread/start", "id": 10, "params": { "model": "gpt-5.1-codex" } }{ "method": "thread/start", "id": 10, "params": { "model": "gpt-5.4" } }
25```25```
26 26
27Responses echo the `id` with either `result` or `error`:27Responses echo the `id` with either `result` or `error`:
99 },99 },
100});100});
101send({ method: "initialized", params: {} });101send({ method: "initialized", params: {} });
102102send({ method: "thread/start", id: 1, params: { model: "gpt-5.1-codex" } });send({ method: "thread/start", id: 1, params: { model: "gpt-5.4" } });
103```103```
104 104
105## Core primitives105## Core primitives
116- **Start (or resume) a thread**: Call `thread/start` for a new conversation, `thread/resume` to continue an existing one, or `thread/fork` to branch history into a new thread id.116- **Start (or resume) a thread**: Call `thread/start` for a new conversation, `thread/resume` to continue an existing one, or `thread/fork` to branch history into a new thread id.
117- **Begin a turn**: Call `turn/start` with the target `threadId` and user input. Optional fields override model, personality, `cwd`, sandbox policy, and more.117- **Begin a turn**: Call `turn/start` with the target `threadId` and user input. Optional fields override model, personality, `cwd`, sandbox policy, and more.
118- **Steer an active turn**: Call `turn/steer` to append user input to the currently in-flight turn without creating a new turn.118- **Steer an active turn**: Call `turn/steer` to append user input to the currently in-flight turn without creating a new turn.
119119- **Stream events**: After `turn/start`, keep reading notifications on stdout: `item/started`, `item/completed`, `item/agentMessage/delta`, tool progress, and other updates.- **Stream events**: After `turn/start`, keep reading notifications on stdout: `thread/archived`, `thread/unarchived`, `item/started`, `item/completed`, `item/agentMessage/delta`, tool progress, and other updates.
120- **Finish the turn**: The server emits `turn/completed` with final status when the model finishes or after a `turn/interrupt` cancellation.120- **Finish the turn**: The server emits `turn/completed` with final status when the model finishes or after a `turn/interrupt` cancellation.
121 121
122## Initialization122## Initialization
123 123
124Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.124Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.
125 125
126126The server returns the user agent string it will present to upstream services. Set `clientInfo` to identify your integration.The server returns the user agent string it will present to upstream services plus `platformFamily` and `platformOs` values that describe the runtime target. Set `clientInfo` to identify your integration.
127 127
128`initialize.params.capabilities` also supports per-connection notification opt-out via `optOutNotificationMethods`, which is a list of exact method names to suppress for that connection. Matching is exact (no wildcards/prefixes). Unknown method names are accepted and ignored.128`initialize.params.capabilities` also supports per-connection notification opt-out via `optOutNotificationMethods`, which is a list of exact method names to suppress for that connection. Matching is exact (no wildcards/prefixes). Unknown method names are accepted and ignored.
129 129
159 },159 },
160 "capabilities": {160 "capabilities": {
161 "experimentalApi": true,161 "experimentalApi": true,
162162 "optOutNotificationMethods": [ "optOutNotificationMethods": ["thread/started", "item/agentMessage/delta"]
163 "codex/event/session_configured",
164 "item/agentMessage/delta"
165 ]
166 }163 }
167 }164 }
168}165}
201- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.198- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.
202- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.199- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.
203- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.200- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.
204201- `thread/read` - read a stored thread by id without resuming it; set `includeTurns` to return full turn history.- `thread/read` - read a stored thread by id without resuming it; set `includeTurns` to return full turn history. Returned `thread` objects include runtime `status`.
205202- `thread/list` - page through stored thread logs; supports cursor-based pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filters.- `thread/list` - page through stored thread logs; supports cursor-based pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filters. Returned `thread` objects include runtime `status`.
206- `thread/loaded/list` - list the thread ids currently loaded in memory.203- `thread/loaded/list` - list the thread ids currently loaded in memory.
207204- `thread/archive` - move a thread’s log file into the archived directory; returns `{}` on success.- `thread/name/set` - set or update a thread's user-facing name for a loaded thread or a persisted rollout; emits `thread/name/updated`.
208205- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread`.- `thread/archive` - move a thread's log file into the archived directory; returns `{}` on success and emits `thread/archived`.
206- `thread/unsubscribe` - unsubscribe this connection from thread turn/item events. If this was the last subscriber, the server unloads the thread and emits `thread/closed`.
207- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread` and emits `thread/unarchived`.
208- `thread/status/changed` - notification emitted when a loaded thread's runtime `status` changes.
209- `thread/compact/start` - trigger conversation history compaction for a thread; returns `{}` immediately while progress streams via `turn/*` and `item/*` notifications.209- `thread/compact/start` - trigger conversation history compaction for a thread; returns `{}` immediately while progress streams via `turn/*` and `item/*` notifications.
210- `thread/shellCommand` - run a user-initiated shell command against a thread. This runs outside the sandbox with full access and doesn't inherit the thread sandbox policy.
211- `thread/backgroundTerminals/clean` - stop all running background terminals for a thread (experimental; requires `capabilities.experimentalApi`).
210- `thread/rollback` - drop the last N turns from the in-memory context and persist a rollback marker; returns the updated `thread`.212- `thread/rollback` - drop the last N turns from the in-memory context and persist a rollback marker; returns the updated `thread`.
211- `turn/start` - add user input to a thread and begin Codex generation; responds with the initial `turn` and streams events. For `collaborationMode`, `settings.developer_instructions: null` means "use built-in instructions for the selected mode."213- `turn/start` - add user input to a thread and begin Codex generation; responds with the initial `turn` and streams events. For `collaborationMode`, `settings.developer_instructions: null` means "use built-in instructions for the selected mode."
212- `turn/steer` - append user input to the active in-flight turn for a thread; returns the accepted `turnId`.214- `turn/steer` - append user input to the active in-flight turn for a thread; returns the accepted `turnId`.
213- `turn/interrupt` - request cancellation of an in-flight turn; success is `{}` and the turn ends with `status: "interrupted"`.215- `turn/interrupt` - request cancellation of an in-flight turn; success is `{}` and the turn ends with `status: "interrupted"`.
214- `review/start` - kick off the Codex reviewer for a thread; emits `enteredReviewMode` and `exitedReviewMode` items.216- `review/start` - kick off the Codex reviewer for a thread; emits `enteredReviewMode` and `exitedReviewMode` items.
215- `command/exec` - run a single command under the server sandbox without starting a thread/turn.217- `command/exec` - run a single command under the server sandbox without starting a thread/turn.
218- `command/exec/write` - write `stdin` bytes to a running `command/exec` session or close `stdin`.
219- `command/exec/resize` - resize a running PTY-backed `command/exec` session.
220- `command/exec/terminate` - stop a running `command/exec` session.
216- `model/list` - list available models (set `includeHidden: true` to include entries with `hidden: true`) with effort options, optional `upgrade`, and `inputModalities`.221- `model/list` - list available models (set `includeHidden: true` to include entries with `hidden: true`) with effort options, optional `upgrade`, and `inputModalities`.
217- `experimentalFeature/list` - list feature flags with lifecycle stage metadata and cursor pagination.222- `experimentalFeature/list` - list feature flags with lifecycle stage metadata and cursor pagination.
218- `collaborationMode/list` - list collaboration mode presets (experimental, no pagination).223- `collaborationMode/list` - list collaboration mode presets (experimental, no pagination).
219- `skills/list` - list skills for one or more `cwd` values (supports `forceReload` and optional `perCwdExtraUserRoots`).224- `skills/list` - list skills for one or more `cwd` values (supports `forceReload` and optional `perCwdExtraUserRoots`).
225- `plugin/list` - list discovered plugin marketplaces and plugin state, including install/auth policy metadata, marketplace load errors, featured plugin ids, and local, Git, or remote plugin source metadata.
226- `plugin/read` - read one plugin by marketplace path or remote marketplace name and plugin name, including bundled skills, apps, and MCP server names when those details are available.
227- `plugin/install` - install a plugin from a marketplace path or remote marketplace name.
228- `plugin/uninstall` - uninstall an installed plugin.
220- `app/list` - list available apps (connectors) with pagination plus accessibility/enabled metadata.229- `app/list` - list available apps (connectors) with pagination plus accessibility/enabled metadata.
221- `skills/config/write` - enable or disable skills by path.230- `skills/config/write` - enable or disable skills by path.
222- `mcpServer/oauth/login` - start an OAuth login for a configured MCP server; returns an authorization URL and emits `mcpServer/oauthLogin/completed` on completion.231- `mcpServer/oauth/login` - start an OAuth login for a configured MCP server; returns an authorization URL and emits `mcpServer/oauthLogin/completed` on completion.
223- `tool/requestUserInput` - prompt the user with 1-3 short questions for a tool call (experimental); questions can set `isOther` for a free-form option.232- `tool/requestUserInput` - prompt the user with 1-3 short questions for a tool call (experimental); questions can set `isOther` for a free-form option.
224- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.233- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.
225234- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination).- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination). Use `detail: "full"` for full data or `detail: "toolsAndAuthOnly"` to omit resources.
226235- `feedback/upload` - submit a feedback report (classification + optional reason/logs + conversation id).- `mcpServer/resource/read` - read a single MCP resource through an initialized MCP server.
236- `windowsSandbox/setupStart` - start Windows sandbox setup for `elevated` or `unelevated` mode; returns quickly and later emits `windowsSandbox/setupCompleted`.
237- `feedback/upload` - submit a feedback report (classification + optional reason/logs + conversation id, plus optional `extraLogFiles` attachments).
227- `config/read` - fetch the effective configuration on disk after resolving configuration layering.238- `config/read` - fetch the effective configuration on disk after resolving configuration layering.
239- `externalAgentConfig/detect` - detect external-agent artifacts that can be migrated with `includeHome` and optional `cwds`; each detected item includes `cwd` (`null` for home).
240- `externalAgentConfig/import` - apply selected external-agent migration items by passing explicit `migrationItems` with `cwd` (`null` for home).
228- `config/value/write` - write a single configuration key/value to the user's `config.toml` on disk.241- `config/value/write` - write a single configuration key/value to the user's `config.toml` on disk.
229- `config/batchWrite` - apply configuration edits atomically to the user's `config.toml` on disk.242- `config/batchWrite` - apply configuration edits atomically to the user's `config.toml` on disk.
230243- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists and residency requirements (or `null` if you haven’t set any up).- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists, pinned `featureRequirements`, and residency/network requirements (or `null` if you haven't set any up).
244- `fs/readFile`, `fs/writeFile`, `fs/createDirectory`, `fs/getMetadata`, `fs/readDirectory`, `fs/remove`, and `fs/copy` - operate on absolute filesystem paths through the app-server v2 filesystem API.
245
246Plugin summaries include a `source` union. Local plugins return
247`{ "type": "local", "path": ... }`, Git-backed marketplace entries return
248`{ "type": "git", "url": ..., "path": ..., "refName": ..., "sha": ... }`,
249and remote catalog entries return `{ "type": "remote" }`. For remote-only
250catalog entries, `PluginMarketplaceEntry.path` can be `null`; pass
251`remoteMarketplaceName` instead of `marketplacePath` when reading or installing
252those plugins.
231 253
232## Models254## Models
233 255
239{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }261{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }
240{ "id": 6, "result": {262{ "id": 6, "result": {
241 "data": [{263 "data": [{
242264 "id": "gpt-5.2-codex", "id": "gpt-5.4",
243265 "model": "gpt-5.2-codex", "model": "gpt-5.4",
244266 "upgrade": "gpt-5.3-codex", "displayName": "GPT-5.4",
245 "displayName": "GPT-5.2 Codex",
246 "hidden": false,267 "hidden": false,
247 "defaultReasoningEffort": "medium",268 "defaultReasoningEffort": "medium",
248269 "reasoningEffort": [{ "supportedReasoningEfforts": [{
249270 "effort": "low", "reasoningEffort": "low",
250 "description": "Lower latency"271 "description": "Lower latency"
251 }],272 }],
252 "inputModalities": ["text", "image"],273 "inputModalities": ["text", "image"],
259 280
260Each model entry can include:281Each model entry can include:
261 282
262283- `reasoningEffort` - supported effort options for the model.- `supportedReasoningEfforts` - supported effort options for the model.
263- `defaultReasoningEffort` - suggested default effort for clients.284- `defaultReasoningEffort` - suggested default effort for clients.
264- `upgrade` - optional recommended upgrade model id for migration prompts in clients.285- `upgrade` - optional recommended upgrade model id for migration prompts in clients.
286- `upgradeInfo` - optional upgrade metadata for migration prompts in clients.
265- `hidden` - whether the model is hidden from the default picker list.287- `hidden` - whether the model is hidden from the default picker list.
266- `inputModalities` - supported input types for the model (for example `text`, `image`).288- `inputModalities` - supported input types for the model (for example `text`, `image`).
267- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.289- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.
299- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.321- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.
300- `thread/loaded/list` returns the thread IDs currently in memory.322- `thread/loaded/list` returns the thread IDs currently in memory.
301- `thread/archive` moves the thread's persisted JSONL log into the archived directory.323- `thread/archive` moves the thread's persisted JSONL log into the archived directory.
324- `thread/unsubscribe` unsubscribes the current connection from a loaded thread and can trigger `thread/closed`.
302- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.325- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.
303- `thread/compact/start` triggers compaction and returns `{}` immediately.326- `thread/compact/start` triggers compaction and returns `{}` immediately.
304- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.327- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.
309 332
310```json333```json
311{ "method": "thread/start", "id": 10, "params": {334{ "method": "thread/start", "id": 10, "params": {
312335 "model": "gpt-5.1-codex", "model": "gpt-5.4",
313 "cwd": "/Users/me/project",336 "cwd": "/Users/me/project",
314 "approvalPolicy": "never",337 "approvalPolicy": "never",
315 "sandbox": "workspaceWrite",338 "sandbox": "workspaceWrite",
316339 "personality": "friendly" "personality": "friendly",
340 "serviceName": "my_app_server_client"
317} }341} }
318{ "id": 10, "result": {342{ "id": 10, "result": {
319 "thread": {343 "thread": {
320 "id": "thr_123",344 "id": "thr_123",
321 "preview": "",345 "preview": "",
346 "ephemeral": false,
322 "modelProvider": "openai",347 "modelProvider": "openai",
323 "createdAt": 1730910000348 "createdAt": 1730910000
324 }349 }
326{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }351{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }
327```352```
328 353
354`serviceName` is optional. Set it when you want app-server to tag thread-level metrics with your integration's service name.
355
329To continue a stored session, call `thread/resume` with the `thread.id` you recorded earlier. The response shape matches `thread/start`. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:356To continue a stored session, call `thread/resume` with the `thread.id` you recorded earlier. The response shape matches `thread/start`. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:
330 357
331```json358```json
333 "threadId": "thr_123",360 "threadId": "thr_123",
334 "personality": "friendly"361 "personality": "friendly"
335} }362} }
336363{ "id": 11, "result": { "thread": { "id": "thr_123" } } }{ "id": 11, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false } } }
337```364```
338 365
339Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.366Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.
352{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }379{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }
353```380```
354 381
382When a user-facing thread title has been set, app-server hydrates `thread.name` on `thread/list`, `thread/read`, `thread/resume`, `thread/unarchive`, and `thread/rollback` responses. `thread/start` and `thread/fork` may omit `name` (or return `null`) until a title is set later.
383
355### Read a stored thread (without resuming)384### Read a stored thread (without resuming)
356 385
357Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.386Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.
358 387
359- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.388- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.
389- Returned `thread` objects include runtime `status` (`notLoaded`, `idle`, `systemError`, or `active` with `activeFlags`).
360 390
361```json391```json
362{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }392{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }
363393{ "id": 19, "result": { "thread": { "id": "thr_123", "turns": [] } } }{ "id": 19, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false, "status": { "type": "notLoaded" }, "turns": [] } } }
364```394```
365 395
366Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.396Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.
400} }430} }
401{ "id": 20, "result": {431{ "id": 20, "result": {
402 "data": [432 "data": [
403433 { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111 }, { "id": "thr_a", "preview": "Create a TUI", "ephemeral": false, "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111, "name": "TUI prototype", "status": { "type": "notLoaded" } },
404434 { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000 } { "id": "thr_b", "preview": "Fix tests", "ephemeral": true, "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000, "status": { "type": "notLoaded" } }
405 ],435 ],
406 "nextCursor": "opaque-token-or-null"436 "nextCursor": "opaque-token-or-null"
407} }437} }
409 439
410When `nextCursor` is `null`, you have reached the final page.440When `nextCursor` is `null`, you have reached the final page.
411 441
442### Track thread status changes
443
444`thread/status/changed` is emitted whenever a loaded thread's runtime status changes. The payload includes `threadId` and the new `status`.
445
446```json
447{
448 "method": "thread/status/changed",
449 "params": {
450 "threadId": "thr_123",
451 "status": { "type": "active", "activeFlags": ["waitingOnApproval"] }
452 }
453}
454```
455
412### List loaded threads456### List loaded threads
413 457
414`thread/loaded/list` returns thread IDs currently loaded in memory.458`thread/loaded/list` returns thread IDs currently loaded in memory.
418{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }462{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }
419```463```
420 464
465### Unsubscribe from a loaded thread
466
467`thread/unsubscribe` removes the current connection's subscription to a thread. The response status is one of:
468
469- `unsubscribed` when the connection was subscribed and is now removed.
470- `notSubscribed` when the connection wasn't subscribed to that thread.
471- `notLoaded` when the thread isn't loaded.
472
473If this was the last subscriber, the server unloads the thread and emits a `thread/status/changed` transition to `notLoaded` plus `thread/closed`.
474
475```json
476{ "method": "thread/unsubscribe", "id": 22, "params": { "threadId": "thr_123" } }
477{ "id": 22, "result": { "status": "unsubscribed" } }
478{ "method": "thread/status/changed", "params": {
479 "threadId": "thr_123",
480 "status": { "type": "notLoaded" }
481} }
482{ "method": "thread/closed", "params": { "threadId": "thr_123" } }
483```
484
421### Archive a thread485### Archive a thread
422 486
423Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.487Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.
425```json489```json
426{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }490{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }
427{ "id": 22, "result": {} }491{ "id": 22, "result": {} }
492{ "method": "thread/archived", "params": { "threadId": "thr_b" } }
428```493```
429 494
430Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.495Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.
435 500
436```json501```json
437{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }502{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }
438503{ "id": 24, "result": { "thread": { "id": "thr_b" } } }{ "id": 24, "result": { "thread": { "id": "thr_b", "name": "Bug bash notes" } } }
504{ "method": "thread/unarchived", "params": { "threadId": "thr_b" } }
439```505```
440 506
441### Trigger thread compaction507### Trigger thread compaction
449{ "id": 25, "result": {} }515{ "id": 25, "result": {} }
450```516```
451 517
518### Run a thread shell command
519
520Use `thread/shellCommand` for user-initiated shell commands that belong to a thread. The request returns immediately with `{}` while progress streams through standard `turn/*` and `item/*` notifications.
521
522This API runs outside the sandbox with full access and doesn't inherit the thread sandbox policy. Clients should expose it only for explicit user-initiated commands.
523
524If the thread already has an active turn, the command runs as an auxiliary action on that turn and its formatted output is injected into the turn's message stream. If the thread is idle, app-server starts a standalone turn for the shell command.
525
526```json
527{ "method": "thread/shellCommand", "id": 26, "params": { "threadId": "thr_b", "command": "git status --short" } }
528{ "id": 26, "result": {} }
529```
530
531### Clean background terminals
532
533Use `thread/backgroundTerminals/clean` to stop all running background terminals associated with a thread. This method is experimental and requires `capabilities.experimentalApi = true`.
534
535```json
536{ "method": "thread/backgroundTerminals/clean", "id": 27, "params": { "threadId": "thr_b" } }
537{ "id": 27, "result": {} }
538```
539
540### Roll back recent turns
541
542Use `thread/rollback` to remove the last `numTurns` entries from the in-memory context and persist a rollback marker in the rollout log. The returned `thread` includes `turns` populated after the rollback.
543
544```json
545{ "method": "thread/rollback", "id": 28, "params": { "threadId": "thr_b", "numTurns": 1 } }
546{ "id": 28, "result": { "thread": { "id": "thr_b", "name": "Bug bash notes", "ephemeral": false } } }
547```
548
452## Turns549## Turns
453 550
454The `input` field accepts a list of items:551The `input` field accepts a list of items:
478}575}
479```576```
480 577
578On macOS, `includePlatformDefaults: true` appends a curated platform-default Seatbelt policy for restricted-read sessions. This improves tool compatibility without broadly allowing all of `/System`.
579
481Examples:580Examples:
482 581
483```json582```json
510 "writableRoots": ["/Users/me/project"],609 "writableRoots": ["/Users/me/project"],
511 "networkAccess": true610 "networkAccess": true
512 },611 },
513612 "model": "gpt-5.1-codex", "model": "gpt-5.4",
514 "effort": "medium",613 "effort": "medium",
515 "summary": "concise",614 "summary": "concise",
516 "personality": "friendly",615 "personality": "friendly",
653- The server rejects empty `command` arrays.752- The server rejects empty `command` arrays.
654- `sandboxPolicy` accepts the same shape used by `turn/start` (for example, `dangerFullAccess`, `readOnly`, `workspaceWrite`, `externalSandbox`).753- `sandboxPolicy` accepts the same shape used by `turn/start` (for example, `dangerFullAccess`, `readOnly`, `workspaceWrite`, `externalSandbox`).
655- When omitted, `timeoutMs` falls back to the server default.754- When omitted, `timeoutMs` falls back to the server default.
755- Set `tty: true` for PTY-backed sessions, and use `processId` when you plan to follow up with `command/exec/write`, `command/exec/resize`, or `command/exec/terminate`.
756- Set `streamStdoutStderr: true` to receive `command/exec/outputDelta` notifications while the command is running.
757
758### Read admin requirements (`configRequirements/read`)
759
760Use `configRequirements/read` to inspect the effective admin requirements loaded from `requirements.toml` and/or MDM.
761
762```json
763{ "method": "configRequirements/read", "id": 52, "params": {} }
764{ "id": 52, "result": {
765 "requirements": {
766 "allowedApprovalPolicies": ["onRequest", "unlessTrusted"],
767 "allowedSandboxModes": ["readOnly", "workspaceWrite"],
768 "featureRequirements": {
769 "personality": true,
770 "unified_exec": false
771 },
772 "network": {
773 "enabled": true,
774 "allowedDomains": ["api.openai.com"],
775 "allowUnixSockets": ["/tmp/example.sock"],
776 "dangerouslyAllowAllUnixSockets": false
777 }
778 }
779} }
780```
781
782`result.requirements` is `null` when no requirements are configured. See the docs on [`requirements.toml`](https://developers.openai.com/codex/config-reference#requirementstoml) for details on supported keys and values.
783
784### Windows sandbox setup (`windowsSandbox/setupStart`)
785
786Custom Windows clients can trigger sandbox setup asynchronously instead of blocking on startup checks.
787
788```json
789{ "method": "windowsSandbox/setupStart", "id": 53, "params": { "mode": "elevated" } }
790{ "id": 53, "result": { "started": true } }
791```
792
793App-server starts setup in the background and later emits a completion notification:
794
795```json
796{
797 "method": "windowsSandbox/setupCompleted",
798 "params": { "mode": "elevated", "success": true, "error": null }
799}
800```
801
802Modes:
803
804- `elevated` - run the elevated Windows sandbox setup path.
805- `unelevated` - run the legacy setup/preflight path.
656 806
657## Events807## Events
658 808
659809Event notifications are the server-initiated stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading the active transport stream for `thread/started`, `turn/*`, and `item/*` notifications.Event notifications are the server-initiated stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading the active transport stream for `thread/started`, `thread/archived`, `thread/unarchived`, `thread/closed`, `thread/status/changed`, `turn/*`, `item/*`, and `serverRequest/resolved` notifications.
660 810
661### Notification opt-out811### Notification opt-out
662 812
664 814
665- Exact-match only: `item/agentMessage/delta` suppresses only that method.815- Exact-match only: `item/agentMessage/delta` suppresses only that method.
666- Unknown method names are ignored.816- Unknown method names are ignored.
667817- Applies to both legacy (`codex/event/*`) and v2 (`thread/*`, `turn/*`, `item/*`, etc.) notifications.- Applies to the current `thread/*`, `turn/*`, `item/*`, and related v2 notifications.
668- Doesn't apply to requests, responses, or errors.818- Doesn't apply to requests, responses, or errors.
669 819
670### Fuzzy file search events (experimental)820### Fuzzy file search events (experimental)
674- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.824- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.
675- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.825- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.
676 826
827### Windows sandbox setup events
828
829- `windowsSandbox/setupCompleted` - `{ mode, success, error }` emitted after a `windowsSandbox/setupStart` request finishes.
830
677### Turn events831### Turn events
678 832
679- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.833- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.
689`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:843`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:
690 844
691- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).845- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
692846- `agentMessage` - `{id, text}` containing the accumulated agent reply.- `agentMessage` - `{id, text, phase?}` containing the accumulated agent reply. When present, `phase` uses Responses API wire values (`commentary`, `final_answer`).
693- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.847- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.
694- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.848- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.
695- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.849- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.
696- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.850- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.
697- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.851- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.
852- `dynamicToolCall` - `{id, tool, arguments, status, contentItems?, success?, durationMs?}` for client-executed dynamic tool invocations.
698- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.853- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.
699- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.854- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.
700- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.855- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.
751Order of messages:906Order of messages:
752 907
7531. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.9081. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.
7549092. `item/commandExecution/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, optional `command`, optional `cwd`, optional `commandActions`, and optional `proposedExecpolicyAmendment`.2. `item/commandExecution/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, optional `command`, optional `cwd`, optional `commandActions`, optional `proposedExecpolicyAmendment`, optional `networkApprovalContext`, and optional `availableDecisions`. When `initialize.params.capabilities.experimentalApi = true`, the payload can also include experimental `additionalPermissions` describing requested per-command sandbox access. Any filesystem paths inside `additionalPermissions` are absolute on the wire.
7553. Client responds with one of the command execution approval decisions above.9103. Client responds with one of the command execution approval decisions above.
7569114. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.4. `serverRequest/resolved` confirms that the pending request has been answered or cleared.
9125. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.
913
914When `networkApprovalContext` is present, the prompt is for managed network access (not a general shell-command approval). The current v2 schema exposes the target `host` and `protocol`; clients should render a network-specific prompt and not rely on `command` being a user-meaningful shell command preview.
915
916Codex groups concurrent network approval prompts by destination (`host`, protocol, and port). The app-server may therefore send one prompt that unblocks multiple queued requests to the same destination, while different ports on the same host are treated separately.
757 917
758### File change approvals918### File change approvals
759 919
7621. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.9221. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.
7632. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.9232. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.
7643. Client responds with one of the file change approval decisions above.9243. Client responds with one of the file change approval decisions above.
7659254. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.4. `serverRequest/resolved` confirms that the pending request has been answered or cleared.
9265. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.
927
928### `tool/requestUserInput`
929
930When the client responds to `item/tool/requestUserInput`, app-server emits `serverRequest/resolved` with `{ threadId, requestId }`. If the pending request is cleared by turn start, turn completion, or turn interruption before the client answers, the server emits the same notification for that cleanup.
931
932### Dynamic tool calls (experimental)
933
934`dynamicTools` on `thread/start` and the corresponding `item/tool/call` request or response flow are experimental APIs.
935
936When a dynamic tool is invoked during a turn, app-server emits:
937
9381. `item/started` with `item.type = "dynamicToolCall"`, `status = "inProgress"`, plus `tool` and `arguments`.
9392. `item/tool/call` as a server request to the client.
9403. The client response payload with returned content items.
9414. `item/completed` with `item.type = "dynamicToolCall"`, the final `status`, and any returned `contentItems` or `success` value.
766 942
767### MCP tool-call approvals (apps)943### MCP tool-call approvals (apps)
768 944
769945App (connector) tool calls can also require approval. When an app tool call has side effects, the server may elicit approval with `tool/requestUserInput` and options such as **Accept**, **Decline**, and **Cancel**. If the user declines or cancels, the related `mcpToolCall` item completes with an error instead of running the tool.App (connector) tool calls can also require approval. When an app tool call has side effects, the server may elicit approval with `tool/requestUserInput` and options such as **Accept**, **Decline**, and **Cancel**. Destructive tool annotations always trigger approval even when the tool also advertises less-privileged hints. If the user declines or cancels, the related `mcpToolCall` item completes with an error instead of running the tool.
770 946
771## Skills947## Skills
772 948
863 1039
864## Apps (connectors)1040## Apps (connectors)
865 1041
8661042Use `app/list` to fetch available apps. In the CLI/TUI, `/apps` is the user-facing picker; in custom clients, call `app/list` directly. Each entry includes both `isAccessible` (available to the user) and `isEnabled` (enabled in `config.toml`) so clients can distinguish install/access from local enabled state.Use `app/list` to fetch available apps. In the CLI/TUI, `/apps` is the user-facing picker; in custom clients, call `app/list` directly. Each entry includes both `isAccessible` (available to the user) and `isEnabled` (enabled in `config.toml`) so clients can distinguish install/access from local enabled state. App entries can also include optional `branding`, `appMetadata`, and `labels` fields.
867 1043
868```json1044```json
869{ "method": "app/list", "id": 50, "params": {1045{ "method": "app/list", "id": 50, "params": {
879 "name": "Demo App",1055 "name": "Demo App",
880 "description": "Example connector for documentation.",1056 "description": "Example connector for documentation.",
881 "logoUrl": "https://example.com/demo-app.png",1057 "logoUrl": "https://example.com/demo-app.png",
1058 "logoUrlDark": null,
1059 "distributionChannel": null,
1060 "branding": null,
1061 "appMetadata": null,
1062 "labels": null,
882 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1063 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",
883 "isAccessible": true,1064 "isAccessible": true,
884 "isEnabled": true1065 "isEnabled": true
904 "name": "Demo App",1085 "name": "Demo App",
905 "description": "Example connector for documentation.",1086 "description": "Example connector for documentation.",
906 "logoUrl": "https://example.com/demo-app.png",1087 "logoUrl": "https://example.com/demo-app.png",
1088 "logoUrlDark": null,
1089 "distributionChannel": null,
1090 "branding": null,
1091 "appMetadata": null,
1092 "labels": null,
907 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1093 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",
908 "isAccessible": true,1094 "isAccessible": true,
909 "isEnabled": true1095 "isEnabled": true
936}1122}
937```1123```
938 1124
1125### Config RPC examples for app settings
1126
1127Use `config/read`, `config/value/write`, and `config/batchWrite` to inspect or update app controls in `config.toml`.
1128
1129Read the effective app config shape (including `_default` and per-tool overrides):
1130
1131```json
1132{ "method": "config/read", "id": 60, "params": { "includeLayers": false } }
1133{ "id": 60, "result": {
1134 "config": {
1135 "apps": {
1136 "_default": {
1137 "enabled": true,
1138 "destructive_enabled": true,
1139 "open_world_enabled": true
1140 },
1141 "google_drive": {
1142 "enabled": true,
1143 "destructive_enabled": false,
1144 "default_tools_approval_mode": "prompt",
1145 "tools": {
1146 "files/delete": { "enabled": false, "approval_mode": "approve" }
1147 }
1148 }
1149 }
1150 }
1151} }
1152```
1153
1154Update a single app setting:
1155
1156```json
1157{
1158 "method": "config/value/write",
1159 "id": 61,
1160 "params": {
1161 "keyPath": "apps.google_drive.default_tools_approval_mode",
1162 "value": "prompt",
1163 "mergeStrategy": "replace"
1164 }
1165}
1166```
1167
1168Apply multiple app edits atomically:
1169
1170```json
1171{
1172 "method": "config/batchWrite",
1173 "id": 62,
1174 "params": {
1175 "edits": [
1176 {
1177 "keyPath": "apps._default.destructive_enabled",
1178 "value": false,
1179 "mergeStrategy": "upsert"
1180 },
1181 {
1182 "keyPath": "apps.google_drive.tools.files/delete.approval_mode",
1183 "value": "approve",
1184 "mergeStrategy": "upsert"
1185 }
1186 ]
1187 }
1188}
1189```
1190
1191### Detect and import external agent config
1192
1193Use `externalAgentConfig/detect` to discover external-agent artifacts that can be migrated, then pass the selected entries to `externalAgentConfig/import`.
1194
1195Detection example:
1196
1197```json
1198{ "method": "externalAgentConfig/detect", "id": 63, "params": {
1199 "includeHome": true,
1200 "cwds": ["/Users/me/project"]
1201} }
1202{ "id": 63, "result": {
1203 "items": [
1204 {
1205 "itemType": "AGENTS_MD",
1206 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",
1207 "cwd": "/Users/me/project"
1208 },
1209 {
1210 "itemType": "SKILLS",
1211 "description": "Copy skill folders from /Users/me/.claude/skills to /Users/me/.agents/skills.",
1212 "cwd": null
1213 }
1214 ]
1215} }
1216```
1217
1218Import example:
1219
1220```json
1221{ "method": "externalAgentConfig/import", "id": 64, "params": {
1222 "migrationItems": [
1223 {
1224 "itemType": "AGENTS_MD",
1225 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",
1226 "cwd": "/Users/me/project"
1227 }
1228 ]
1229} }
1230{ "id": 64, "result": {} }
1231```
1232
1233Supported `itemType` values are `AGENTS_MD`, `CONFIG`, `SKILLS`, `PLUGINS`,
1234and `MCP_SERVER_CONFIG`. For `PLUGINS` items, `details.plugins` lists each
1235`marketplaceName` and the `pluginNames` Codex can try to migrate. Detection
1236returns only items that still have work to do. For example, Codex skips AGENTS
1237migration when `AGENTS.md` already exists and is non-empty, and skill imports
1238don't overwrite existing skill directories.
1239
1240When detecting plugins from `.claude/settings.json`, Codex reads configured
1241marketplace sources from `extraKnownMarketplaces`. If `enabledPlugins` contains
1242plugins from `claude-plugins-official` but the marketplace source is missing,
1243Codex infers `anthropics/claude-plugins-official` as the source.
1244
939## Auth endpoints1245## Auth endpoints
940 1246
941The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.1247The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.