77 Commits

• feat: codex exec mapping of collab tools (#9817)

  THIS IS NOT THE FINAL UX

  jif-oai · 2026-01-26 18:01:35 +00:00
  01d7f8095b
• feat: dynamic tools injection (#9539)

  ## Summary
  Add dynamic tool injection to thread startup in API v2, wire dynamic
  tool calls through the app server to clients, and plumb responses back
  into the model tool pipeline.
  
  ### Flow (high level)
  - Thread start injects `dynamic_tools` into the model tool list for that
  thread (validation is done here).
  - When the model emits a tool call for one of those names, core raises a
  `DynamicToolCallRequest` event.
  - The app server forwards it to the client as `item/tool/call`, waits
  for the client’s response, then submits a `DynamicToolResponse` back to
  core.
  - Core turns that into a `function_call_output` in the next model
  request so the model can continue.
  
  ### What changed
  - Added dynamic tool specs to v2 thread start params and protocol types;
  introduced `item/tool/call` (request/response) for dynamic tool
  execution.
  - Core now registers dynamic tool specs at request time and routes those
  calls via a new dynamic tool handler.
  - App server validates tool names/schemas, forwards dynamic tool call
  requests to clients, and publishes tool outputs back into the session.
  - Integration tests

  jif-oai · 2026-01-26 10:06:44 +00:00
  d594693d1a
• Feat: request user input tool (#9472)

  ### Summary
  * Add `requestUserInput` tool that the model can use for gather
  feedback/asking question mid turn.
  
  
  ### Tool input schema
  ```
  {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "title": "requestUserInput input",
    "type": "object",
    "additionalProperties": false,
    "required": ["questions"],
    "properties": {
      "questions": {
        "type": "array",
        "description": "Questions to show the user (1-3). Prefer 1 unless multiple independent decisions block progress.",
        "minItems": 1,
        "maxItems": 3,
        "items": {
          "type": "object",
          "additionalProperties": false,
          "required": ["id", "header", "question"],
          "properties": {
            "id": {
              "type": "string",
              "description": "Stable identifier for mapping answers (snake_case)."
            },
            "header": {
              "type": "string",
              "description": "Short header label shown in the UI (12 or fewer chars)."
            },
            "question": {
              "type": "string",
              "description": "Single-sentence prompt shown to the user."
            },
            "options": {
              "type": "array",
              "description": "Optional 2-3 mutually exclusive choices. Put the recommended option first and suffix its label with \"(Recommended)\". Only include \"Other\" option if we want to include a free form option. If the question is free form in nature, do not include any option.",
              "minItems": 2,
              "maxItems": 3,
              "items": {
                "type": "object",
                "additionalProperties": false,
                "required": ["value", "label", "description"],
                "properties": {
                  "value": {
                    "type": "string",
                    "description": "Machine-readable value (snake_case)."
                  },
                  "label": {
                    "type": "string",
                    "description": "User-facing label (1-5 words)."
                  },
                  "description": {
                    "type": "string",
                    "description": "One short sentence explaining impact/tradeoff if selected."
                  }
                }
              }
            }
          }
        }
      }
    }
  }
  ```
  
  ### Tool output schema
  ```
  {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "title": "requestUserInput output",
    "type": "object",
    "additionalProperties": false,
    "required": ["answers"],
    "properties": {
      "answers": {
        "type": "object",
        "description": "Map of question id to user answer.",
        "additionalProperties": {
          "type": "object",
          "additionalProperties": false,
          "required": ["selected"],
          "properties": {
            "selected": {
              "type": "array",
              "items": { "type": "string" }
            },
            "other": {
              "type": ["string", "null"]
            }
          }
        }
      }
    }
  }
  ```

  Shijie Rao · 2026-01-19 10:17:30 -08:00
  57ec3a8277
• feat: emit events around collab tools (#9095)

  Emit the following events around the collab tools. On the `app-server`
  this will be under `item/started` and `item/completed`
  ```
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabAgentSpawnBeginEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
      /// beginning.
      pub prompt: String,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabAgentSpawnEndEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the newly spawned agent, if it was created.
      pub new_thread_id: Option<ThreadId>,
      /// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
      /// beginning.
      pub prompt: String,
      /// Last known status of the new agent reported to the sender agent.
      pub status: AgentStatus,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabAgentInteractionBeginEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
      /// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
      /// leaking at the beginning.
      pub prompt: String,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabAgentInteractionEndEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
      /// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
      /// leaking at the beginning.
      pub prompt: String,
      /// Last known status of the receiver agent reported to the sender agent.
      pub status: AgentStatus,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabWaitingBeginEvent {
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
      /// ID of the waiting call.
      pub call_id: String,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabWaitingEndEvent {
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
      /// ID of the waiting call.
      pub call_id: String,
      /// Last known status of the receiver agent reported to the sender agent.
      pub status: AgentStatus,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabCloseBeginEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
  }
  
  #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
  pub struct CollabCloseEndEvent {
      /// Identifier for the collab tool call.
      pub call_id: String,
      /// Thread ID of the sender.
      pub sender_thread_id: ThreadId,
      /// Thread ID of the receiver.
      pub receiver_thread_id: ThreadId,
      /// Last known status of the receiver agent reported to the sender agent before
      /// the close.
      pub status: AgentStatus,
  }
  ```

  jif-oai · 2026-01-14 17:55:57 +00:00
  6a939ed7a4
• renaming: task to turn (#8963)
  jif-oai · 2026-01-09 17:31:17 +00:00
  1aed01e99f
• feat(app-server): thread/rollback API (#8454)

  Add `thread/rollback` to app-server to support IDEs undo-ing the last N
  turns of a thread.
  
  For context, an IDE partner will be supporting an "undo" capability
  where the IDE (the app-server client) will be responsible for reverting
  the local changes made during the last turn. To support this well, we
  also need a way to drop the last turn (or more generally, the last N
  turns) from the agent's context. This is what `thread/rollback` does.
  
  **Core idea**: A Thread rollback is represented as a persisted event
  message (EventMsg::ThreadRollback) in the rollout JSONL file, not by
  rewriting history. On resume, both the model's context (core replay) and
  the UI turn list (app-server v2's thread history builder) apply these
  markers so the pruned history is consistent across live conversations
  and `thread/resume`.
  
  Implementation notes:
  - Rollback only affects agent context and appends to the rollout file;
  clients are responsible for reverting files on disk.
  - If a thread rollback is currently in progress, subsequent
  `thread/rollback` calls are rejected.
  - Because we use `CodexConversation::submit` and codex core tracks
  active turns, returning an error on concurrent rollbacks is communicated
  via an `EventMsg::Error` with a new variant
  `CodexErrorInfo::ThreadRollbackFailed`. app-server watches for that and
  sends the BAD_REQUEST RPC response.
  
  Tests cover thread rollbacks in both core and app-server, including when
  `num_turns` > existing turns (which clears all turns).
  
  **Note**: this explicitly does **not** behave like `/undo` which we just
  removed from the CLI, which does the opposite of what `thread/rollback`
  does. `/undo` reverts local changes via ghost commits/snapshots and does
  not modify the agent's context / conversation history.

  Owen Lin · 2026-01-06 21:23:48 +00:00
  8b7ec31ba7
• [chore] add additional_details to StreamErrorEvent + wire through (#8307)

  ### What
  
  Builds on #8293.
  
  Add `additional_details`, which contains the upstream error message, to
  relevant structures used to pass along retryable `StreamError`s.
  
  Uses the new TUI status indicator's `details` field (shows under the
  status header) to display the `additional_details` error to the user on
  retryable `Reconnecting...` errors. This adds clarity for users for
  retryable errors.
  
  Will make corresponding change to VSCode extension to show
  `additional_details` as expandable from the `Reconnecting...` cell.
  
  Examples:
  <img width="1012" height="326" alt="image"
  src="https://github.com/user-attachments/assets/f35e7e6a-8f5e-4a2f-a764-358101776996"
  />
  
  <img width="1526" height="358" alt="image"
  src="https://github.com/user-attachments/assets/0029cbc0-f062-4233-8650-cc216c7808f0"
  />

  sayan-oai · 2025-12-24 10:07:38 -08:00
  bf732600ea
• Add public skills + improve repo skill discovery and error UX (#8098)

  1. Adds SkillScope::Public end-to-end (core + protocol) and loads skills
  from the public cache directory
  2. Improves repo skill discovery by searching upward for the nearest
  .codex/skills within a git repo
  3. Deduplicates skills by name with deterministic ordering to avoid
  duplicates across sources
  4. Fixes garbled “Skill errors” overlay rendering by preventing pending
  history lines from being injected during the modal
  5. Updates the project docs “Skills” intro wording to avoid hardcoded
  paths

  xl-openai · 2025-12-17 01:35:49 -08:00
  4897efcced
• Reimplement skills loading using SkillsManager + skills/list op. (#7914)

  refactor the way we load and manage skills:
  1. Move skill discovery/caching into SkillsManager and reuse it across
  sessions.
  2. Add the skills/list API (Op::ListSkills/SkillsListResponse) to fetch
  skills for one or more cwds. Also update app-server for VSCE/App;
  3. Trigger skills/list during session startup so UIs preload skills and
  handle errors immediately.

  xl-openai · 2025-12-14 09:58:17 -08:00
  5d77d4db6b
• make model optional in config (#7769)

  - Make Config.model optional and centralize default-selection logic in
  ModelsManager, including a default_model helper (with
  codex-auto-balanced when available) so sessions now carry an explicit
  chosen model separate from the base config.
  - Resolve `model` once in `core` and `tui` from config. Then store the
  state of it on other structs.
  - Move refreshing models to be before resolving the default model

  Ahmed Ibrahim · 2025-12-10 11:19:00 -08:00
  cb9a189857
• chore: rework unified exec events (#7775)
  jif-oai · 2025-12-10 10:30:38 +00:00
  0ad54982ae
• Introduce ModelsManager and migrate app-server to use it. (#7552)
  Ahmed Ibrahim · 2025-12-03 17:17:56 -08:00
  00cc00ead8
• Migrate model preset (#7542)

  - Introduce `openai_models` in `/core`
  - Move `PRESETS` under it
  - Move `ModelPreset`, `ModelUpgrade`, `ReasoningEffortPreset`,
  `ReasoningEffortPreset`, and `ReasoningEffortPreset` to `protocol`
  - Introduce `Op::ListModels` and `EventMsg::AvailableModels`
  
  Next steps:
  - migrate `app-server` and `tui` to use the introduced Operation

  Ahmed Ibrahim · 2025-12-03 20:30:43 +00:00
  71504325d3
• feat: add compaction event (#7289)
  jif-oai · 2025-11-25 16:12:14 +00:00
  9ba27cfa0a
• support MCP elicitations (#6947)

  No support for request schema yet, but we'll at least show the message
  and allow accept/decline.
  
  <img width="823" height="551" alt="Screenshot 2025-11-21 at 2 44 05 PM"
  src="https://github.com/user-attachments/assets/6fbb892d-ca12-4765-921e-9ac4b217534d"
  />

  Jeremy Rose · 2025-11-21 14:44:53 -08:00
  7561a6aaf0
• [app-server & core] introduce new codex error code and v2 app-server error events (#6938)

  This PR does two things:
  1. populate a new `codex_error_code` protocol in error events sent from
  core to client;
  2. old v1 core events `codex/event/stream_error` and `codex/event/error`
  will now both become `error`. We also show codex error code for
  turncompleted -> error status.
  
  new events in app server test:
  ```
  < {
  <   "method": "codex/event/stream_error",
  <   "params": {
  <     "conversationId": "019aa34c-0c14-70e0-9706-98520a760d67",
  <     "id": "0",
  <     "msg": {
  <       "codex_error_code": {
  <         "response_stream_disconnected": {
  <           "http_status_code": 401
  <         }
  <       },
  <       "message": "Reconnecting... 2/5",
  <       "type": "stream_error"
  <     }
  <   }
  < }
  
   {
  <   "method": "error",
  <   "params": {
  <     "error": {
  <       "codexErrorCode": {
  <         "responseStreamDisconnected": {
  <           "httpStatusCode": 401
  <         }
  <       },
  <       "message": "Reconnecting... 2/5"
  <     }
  <   }
  < }
  
  < {
  <   "method": "turn/completed",
  <   "params": {
  <     "turn": {
  <       "error": {
  <         "codexErrorCode": {
  <           "responseTooManyFailedAttempts": {
  <             "httpStatusCode": 401
  <           }
  <         },
  <         "message": "exceeded retry limit, last status: 401 Unauthorized, request id: 9a1b495a1a97ed3e-SJC"
  <       },
  <       "id": "0",
  <       "items": [],
  <       "status": "failed"
  <     }
  <   }
  < }
  ```

  Celia Chen · 2025-11-20 23:06:55 +00:00
  9bce050385
• [app-server] feat: v2 apply_patch approval flow (#6760)

  This PR adds the API V2 version of the apply_patch approval flow, which
  centers around `ThreadItem::FileChange`.
  
  This PR wires the new RPC (`item/fileChange/requestApproval`, V2 only)
  and related events (`item/started`, `item/completed` for
  `ThreadItem::FileChange`, which are emitted in both V1 and V2) through
  the app-server
  protocol. The new approval RPC is only sent when the user initiates a
  turn with the new `turn/start` API so we don't break backwards
  compatibility with VSCE.
  
  Similar to https://github.com/openai/codex/pull/6758, the approach I
  took was to make as few changes to the Codex core as possible,
  leveraging existing `EventMsg` core events, and translating those in
  app-server. I did have to add a few additional fields to
  `EventMsg::PatchApplyBegin` and `EventMsg::PatchApplyEnd`, but those
  were fairly lightweight.
  
  However, the `EventMsg`s emitted by core are the following:
  ```
  1) Auto-approved (no request for approval)

  - EventMsg::PatchApplyBegin
  - EventMsg::PatchApplyEnd
  
  2) Approved by user
  - EventMsg::ApplyPatchApprovalRequest
  - EventMsg::PatchApplyBegin
  - EventMsg::PatchApplyEnd
  
  3) Declined by user
  - EventMsg::ApplyPatchApprovalRequest
  - EventMsg::PatchApplyBegin
  - EventMsg::PatchApplyEnd
  ```
  
  For a request triggering an approval, this would result in:
  ```
  item/fileChange/requestApproval
  item/started
  item/completed
  ```
  
  which is different from the `ThreadItem::CommandExecution` flow
  introduced in https://github.com/openai/codex/pull/6758, which does the
  below and is preferable:
  ```
  item/started
  item/commandExecution/requestApproval
  item/completed
  ```
  
  To fix this, we leverage `TurnSummaryStore` on codex_message_processor
  to store a little bit of state, allowing us to fire `item/started` and
  `item/fileChange/requestApproval` whenever we receive the underlying
  `EventMsg::ApplyPatchApprovalRequest`, and no-oping when we receive the
  `EventMsg::PatchApplyBegin` later.
  
  This is much less invasive than modifying the order of EventMsg within
  core (I tried).
  
  The resulting payloads:
  ```
  {
    "method": "item/started",
    "params": {
      "item": {
        "changes": [
          {
            "diff": "Hello from Codex!\n",
            "kind": "add",
            "path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
          }
        ],
        "id": "call_Nxnwj7B3YXigfV6Mwh03d686",
        "status": "inProgress",
        "type": "fileChange"
      }
    }
  }
  ```
  
  ```
  {
    "id": 0,
    "method": "item/fileChange/requestApproval",
    "params": {
      "grantRoot": null,
      "itemId": "call_Nxnwj7B3YXigfV6Mwh03d686",
      "reason": null,
      "threadId": "019a9e11-8295-7883-a283-779e06502c6f",
      "turnId": "1"
    }
  }
  ```
  
  ```
  {
    "id": 0,
    "result": {
      "decision": "accept"
    }
  }
  ```
  
  ```
  {
    "method": "item/completed",
    "params": {
      "item": {
        "changes": [
          {
            "diff": "Hello from Codex!\n",
            "kind": "add",
            "path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
          }
        ],
        "id": "call_Nxnwj7B3YXigfV6Mwh03d686",
        "status": "completed",
        "type": "fileChange"
      }
    }
  }
  ```

  Owen Lin · 2025-11-19 20:13:31 -08:00
  d6c30ed25e
• Revert "[core] add optional status_code to error events (#6865)" (#6955)

  This reverts commit c2ec477d93.
  
  # External (non-OpenAI) Pull Request Requirements
  
  Before opening this Pull Request, please read the dedicated
  "Contributing" markdown file or your PR may be closed:
  https://github.com/openai/codex/blob/main/docs/contributing.md
  
  If your PR conforms to our contribution guidelines, replace this text
  with a detailed and high quality description of your changes.
  
  Include a link to a bug report or enhancement request.

  Celia Chen · 2025-11-20 01:26:14 +00:00
  72a1453ac5
• [core] add optional status_code to error events (#6865)

  We want to better uncover error status code for clients. Add an optional
  status_code to error events (thread error, error, stream error) so app
  server could uncover the status code from the client side later.
  
  in event log:
  ```
  < {
  <   "method": "codex/event/stream_error",
  <   "params": {
  <     "conversationId": "019a9a32-f576-7292-9711-8e57e8063536",
  <     "id": "0",
  <     "msg": {
  <       "message": "Reconnecting... 5/5",
  <       "status_code": 401,
  <       "type": "stream_error"
  <     }
  <   }
  < }
  < {
  <   "method": "codex/event/error",
  <   "params": {
  <     "conversationId": "019a9a32-f576-7292-9711-8e57e8063536",
  <     "id": "0",
  <     "msg": {
  <       "message": "exceeded retry limit, last status: 401 Unauthorized, request id: 9a0cb03a485067f7-SJC",
  <       "status_code": 401,
  <       "type": "error"
  <     }
  <   }
  < }
  ```

  Celia Chen · 2025-11-19 19:51:21 +00:00
  c2ec477d93
• fix: add more fields to ThreadStartResponse and ThreadResumeResponse (#6847)

  This adds the following fields to `ThreadStartResponse` and
  `ThreadResumeResponse`:
  
  ```rust
      pub model: String,
      pub model_provider: String,
      pub cwd: PathBuf,
      pub approval_policy: AskForApproval,
      pub sandbox: SandboxPolicy,
      pub reasoning_effort: Option<ReasoningEffort>,
  ```
  
  This is important because these fields are optional in
  `ThreadStartParams` and `ThreadResumeParams`, so the caller needs to be
  able to determine what values were ultimately used to start/resume the
  conversation. (Though note that any of these could be changed later
  between turns in the conversation.)
  
  Though to get this information reliably, it must be read from the
  internal `SessionConfiguredEvent` that is created in response to the
  start of a conversation. Because `SessionConfiguredEvent` (as defined in
  `codex-rs/protocol/src/protocol.rs`) did not have all of these fields, a
  number of them had to be added as part of this PR.
  
  Because `SessionConfiguredEvent` is referenced in many tests, test
  instances of `SessionConfiguredEvent` had to be updated, as well, which
  is why this PR touches so many files.

  Michael Bolin · 2025-11-18 21:18:43 -08:00
  a75321a64c
• core/tui: non-blocking MCP startup (#6334)

  This makes MCP startup not block TUI startup. Messages sent while MCPs
  are booting will be queued.
  
  
  https://github.com/user-attachments/assets/96e1d234-5d8f-4932-a935-a675d35c05e0
  
  
  Fixes #6317
  
  ---------
  
  Co-authored-by: pakrym-oai <pakrym@openai.com>

  Jeremy Rose · 2025-11-17 11:26:11 -08:00
  03ffe4d595
• Add warning on compact (#6052)

  This PR introduces the ability for `core` to send `warnings` as it can
  send `errors. It also sends a warning on compaction.
  
  <img width="811" height="187" alt="image"
  src="https://github.com/user-attachments/assets/0947a42d-b720-420d-b7fd-115f8a65a46a"
  />

  Ahmed Ibrahim · 2025-10-31 13:27:33 -07:00
  c8ebb2a0dc
• Add item streaming events (#5546)

  Adds AgentMessageContentDelta, ReasoningContentDelta,
  ReasoningRawContentDelta item streaming events while maintaining
  compatibility for old events.
  
  ---------
  
  Co-authored-by: Owen Lin <owen@openai.com>

  pakrym-oai · 2025-10-29 22:33:57 +00:00
  3429e82e45
• feat: deprecation warning (#5825)

  <img width="955" height="311" alt="Screenshot 2025-10-28 at 14 26 25"
  src="https://github.com/user-attachments/assets/99729b3d-3bc9-4503-aab3-8dc919220ab4"
  />

  jif-oai · 2025-10-29 12:29:28 +00:00
  060637b4d4
• chore: undo nits (#5631)
  jif-oai · 2025-10-27 11:48:01 +00:00
  5e8659dcbc
• feat: TUI undo op (#5629)
  jif-oai · 2025-10-27 10:55:29 +00:00
  afc4eaab8b
• Add feedback upload request handling (#5682)
  Ahmed Ibrahim · 2025-10-27 05:53:39 +00:00
  f178805252
• [codex][app-server] introduce codex/event/raw_item events (#5578)
  Anton Panasenko · 2025-10-24 22:41:52 +00:00
  6af83d86ff
• Add ItemStarted/ItemCompleted events for UserInputItem (#5306)

  Adds a new ItemStarted event and delivers UserMessage as the first item
  type (more to come).
  
  
  Renames `InputItem` to `UserInput` considering we're using the `Item`
  suffix for actual items.

  pakrym-oai · 2025-10-20 13:34:44 -07:00
  9c903c4716
• revert /name for now (#4978)

  There was a regression where we'd read entire rollout contents if there
  was no /name present.

  dedrisian-oai · 2025-10-08 17:13:49 -07:00
  4300236681
• feat: Set chat name (#4974)

  Set chat name with `/name` so they appear in the codex resume page:
  
  
  https://github.com/user-attachments/assets/c0252bba-3a53-44c7-a740-f4690a3ad405

  dedrisian-oai · 2025-10-08 16:35:35 -07:00
  ec238a2c39
• feat: codex exec writes only the final message to stdout (#4644)

  This updates `codex exec` so that, by default, most of the agent's
  activity is written to stderr so that only the final agent message is
  written to stdout. This makes it easier to pipe `codex exec` into
  another tool without extra filtering.
  
  I introduced `#![deny(clippy::print_stdout)]` to help enforce this
  change and renamed the `ts_println!()` macro to `ts_msg()` because (1)
  it no longer calls `println!()` and (2), `ts_eprintln!()` seemed too
  long of a name.
  
  While here, this also adds `-o` as an alias for `--output-last-message`.
  
  Fixes https://github.com/openai/codex/issues/1670

  Michael Bolin · 2025-10-03 16:22:12 +00:00
  042d4d55d9
• chore: refactor tool handling (#4510)

  # Tool System Refactor
  
  - Centralizes tool definitions and execution in `core/src/tools/*`:
  specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
  registry/dispatch (`registry.rs`), and shared context (`context.rs`).
  One registry now builds the model-visible tool list and binds handlers.
  - Router converts model responses to tool calls; Registry dispatches
  with consistent telemetry via `codex-rs/otel` and unified error
  handling. Function, Local Shell, MCP, and experimental `unified_exec`
  all flow through this path; legacy shell aliases still work.
  - Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
  make adding tools predictable and testable.
  
  Example: `read_file`
  - Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
  registered by `build_specs`).
  - Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
  1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
  - E2E test: `core/tests/suite/read_file.rs` validates the tool returns
  the requested lines.
  
  ## Next steps:
  - Decompose `handle_container_exec_with_params` 
  - Add parallel tool calls

  jif-oai · 2025-10-03 13:21:06 +01:00
  33d3ecbccc
• Minor cleanup of codex exec output (#4585)

  <img width="850" height="723" alt="image"
  src="https://github.com/user-attachments/assets/2ae067bf-ba6b-47bf-9ffe-d1c3f3aa1870"
  />
  <img width="872" height="547" alt="image"
  src="https://github.com/user-attachments/assets/9058be24-6513-4423-9dae-2d5fd4cbf162"
  />

  pakrym-oai · 2025-10-02 14:17:42 -07:00
  f895d4cbb3
• show "Viewed Image" when the model views an image (#4475)

  <img width="1022" height="339" alt="Screenshot 2025-09-29 at 4 22 00 PM"
  src="https://github.com/user-attachments/assets/12da7358-19be-4010-a71b-496ede6dfbbf"
  />

  Jeremy Rose · 2025-10-02 18:36:03 +00:00
  45936f8fbd
• Add explicit codex exec events (#4177)

  This pull request add a new experimental format of JSON output.
  
  You can try it using `codex exec --experimental-json`.
  
  Design takes a lot of inspiration from Responses API items and stream
  format.
  
  # Session and items
  Each invocation of `codex exec` starts or resumes a session. 
  
  Session contains multiple high-level item types:
  1. Assistant message 
  2. Assistant thinking 
  3. Command execution 
  4. File changes
  5. To-do lists
  6. etc.
  
  # Events 
  Session and items are going through their life cycles which is
  represented by events.
  
  Session is `session.created` or `session.resumed`
  Items are `item.added`, `item.updated`, `item.completed`,
  `item.require_approval` (or other item types like `item.output_delta`
  when we need streaming).
  
  So a typical session can look like:
  
  <details>
  
  ```
  {
    "type": "session.created",
    "session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_0",
      "item_type": "assistant_message",
      "text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_1",
      "item_type": "command_execution",
      "command": "bash -lc ls -la | sed -n '1,200p'",
      "aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@  33 pakrym  staff   1056 Sep 24 14:36 .\ndrwxr-xr-x   41 pakrym  staff   1312 Sep 24 09:17 ..\n-rw-r--r--@   1 pakrym  staff      6 Jul  9 16:16 .codespellignore\n-rw-r--r--@   1 pakrym  staff    258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@   5 pakrym  staff    160 Jul 23 08:26 .devcontainer\n-rw-r--r--@   1 pakrym  staff   6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@  15 pakrym  staff    480 Sep 24 14:38 .git\ndrwxr-xr-x@  12 pakrym  staff    384 Sep  2 16:00 .github\n-rw-r--r--@   1 pakrym  staff    778 Jul  9 16:16 .gitignore\ndrwxr-xr-x@   3 pakrym  staff     96 Aug 11 09:37 .husky\n-rw-r--r--@   1 pakrym  staff    104 Jul  9 16:16 .npmrc\n-rw-r--r--@   1 pakrym  staff     96 Sep  2 08:52 .prettierignore\n-rw-r--r--@   1 pakrym  staff    170 Jul  9 16:16 .prettierrc.toml\ndrwxr-xr-x@   5 pakrym  staff    160 Sep 14 17:43 .vscode\ndrwxr-xr-x@   2 pakrym  staff     64 Sep 11 11:37 2025-09-11\n-rw-r--r--@   1 pakrym  staff   5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@   1 pakrym  staff     92 Sep  2 08:52 CHANGELOG.md\n-rw-r--r--@   1 pakrym  staff   1145 Jul  9 16:16 cliff.toml\ndrwxr-xr-x@  11 pakrym  staff    352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@  38 pakrym  staff   1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@  18 pakrym  staff    576 Sep 23 11:01 docs\n-rw-r--r--@   1 pakrym  staff   2038 Jul  9 16:16 flake.lock\n-rw-r--r--@   1 pakrym  staff   1434 Jul  9 16:16 flake.nix\n-rw-r--r--@   1 pakrym  staff  10926 Jul  9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym  staff  14880 Jul 15 07:36 node_modules\n-rw-r--r--@   1 pakrym  staff    242 Aug  5 08:25 NOTICE\n-rw-r--r--@   1 pakrym  staff    578 Aug 14 12:31 package.json\n-rw-r--r--@   1 pakrym  staff    498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@   1 pakrym  staff     58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@   1 pakrym  staff   2402 Jul  9 16:16 PNPM.md\n-rw-r--r--@   1 pakrym  staff   4393 Sep 12 14:36 README.md\ndrwxr-xr-x@   4 pakrym  staff    128 Sep 18 09:28 scripts\ndrwxr-xr-x@   2 pakrym  staff     64 Sep 11 11:34 tmp\n",
      "exit_code": 0,
      "status": "completed"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_2",
      "item_type": "reasoning",
      "text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_3",
      "item_type": "command_execution",
      "command": "bash -lc sed -n '1,40p' README.md",
      "aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n  <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n  </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
      "exit_code": 0,
      "status": "completed"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_4",
      "item_type": "reasoning",
      "text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_5",
      "item_type": "reasoning",
      "text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_6",
      "item_type": "assistant_message",
      "text": "Applying the change by removing the first line from `README.md`."
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_7",
      "item_type": "file_change",
      "changes": [
        {
          "path": "/Users/pakrym/code/codex/README.md",
          "kind": "update"
        }
      ],
      "status": "completed"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_8",
      "item_type": "reasoning",
      "text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_9",
      "item_type": "command_execution",
      "command": "bash -lc sed -n '1,20p' README.md",
      "aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n  <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n  </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
      "exit_code": 0,
      "status": "completed"
    }
  }
  {
    "type": "item.completed",
    "item": {
      "id": "itm_10",
      "item_type": "assistant_message",
      "text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
    }
  }
  ```
  
  </details>
  
  The idea is to give users fully formatted items they can use directly in
  their rendering/application logic and avoid having them building up
  items manually based on events (unless they want to for streaming).
  
  This PR implements only the `item.completed` payload for some event
  types, more event types and item types to come.
  
  ---------
  
  Co-authored-by: Michael Bolin <mbolin@openai.com>

  pakrym-oai · 2025-09-25 17:47:09 +00:00
  344d4a1d68
• [exec] add include-plan-tool flag and print it nicely (#3461)

  ### Summary
  Sometimes in exec runs, we want to allow the model to use the
  `update_plan` tool, but that's not easily configurable. This change adds
  a feature flag for this, and formats the output so it's human-readable
  
  ## Test Plan
  <img width="1280" height="354" alt="Screenshot 2025-09-11 at 12 39
  44 AM"
  src="https://github.com/user-attachments/assets/72e11070-fb98-47f5-a784-5123ca7333d9"
  />

  Dylan · 2025-09-23 16:50:59 -07:00
  594248f415
• chore: clippy on redundant closure (#4058)

  Add redundant closure clippy rules and let Codex fix it by minimising
  FQP

  jif-oai · 2025-09-22 19:30:16 +00:00
  be366a31ab
• feat: /review (#3774)

  Adds `/review` action in TUI
  
  <img width="637" height="370" alt="Screenshot 2025-09-17 at 12 41 19 AM"
  src="https://github.com/user-attachments/assets/b1979a6e-844a-4b97-ab20-107c185aec1d"
  />

  dedrisian-oai · 2025-09-18 14:14:16 -07:00
  62258df92f
• Review Mode (Core) (#3401)

  ## 📝 Review Mode -- Core
  
  This PR introduces the Core implementation for Review mode:
  
  - New op `Op::Review { prompt: String }:` spawns a child review task
  with isolated context, a review‑specific system prompt, and a
  `Config.review_model`.
  - `EnteredReviewMode`: emitted when the child review session starts.
  Every event from this point onwards reflects the review session.
  - `ExitedReviewMode(Option<ReviewOutputEvent>)`: emitted when the review
  finishes or is interrupted, with optional structured findings:
  
  ```json
  {
    "findings": [
      {
        "title": "<≤ 80 chars, imperative>",
        "body": "<valid Markdown explaining *why* this is a problem; cite files/lines/functions>",
        "confidence_score": <float 0.0-1.0>,
        "priority": <int 0-3>,
        "code_location": {
          "absolute_file_path": "<file path>",
          "line_range": {"start": <int>, "end": <int>}
        }
      }
    ],
    "overall_correctness": "patch is correct" | "patch is incorrect",
    "overall_explanation": "<1-3 sentence explanation justifying the overall_correctness verdict>",
    "overall_confidence_score": <float 0.0-1.0>
  }
  ```
  
  ## Questions
  
  ### Why separate out its own message history?
  
  We want the review thread to match the training of our review models as
  much as possible -- that means using a custom prompt, removing user
  instructions, and starting a clean chat history.
  
  We also want to make sure the review thread doesn't leak into the parent
  thread.
  
  ### Why do this as a mode, vs. sub-agents?
  
  1. We want review to be a synchronous task, so it's fine for now to do a
  bespoke implementation.
  2. We're still unclear about the final structure for sub-agents. We'd
  prefer to land this quickly and then refactor into sub-agents without
  rushing that implementation.

  dedrisian-oai · 2025-09-12 23:25:10 +00:00
  90a0fd342f
• feat: include reasoning_effort in NewConversationResponse (#3506)

  `ClientRequest::NewConversation` picks up the reasoning level from the user's defaults in `config.toml`, so it should be reported in `NewConversationResponse`.

  Michael Bolin · 2025-09-11 21:04:40 -07:00
  9bbeb75361
• chore: enable clippy::redundant_clone (#3489)

  Created this PR by:
  
  - adding `redundant_clone` to `[workspace.lints.clippy]` in
  `cargo-rs/Cargol.toml`
  - running `cargo clippy --tests --fix`
  - running `just fmt`
  
  Though I had to clean up one instance of the following that resulted:
  
  ```rust
  let codex = codex;
  ```

  Michael Bolin · 2025-09-11 11:59:37 -07:00
  bec51f6c05
• Change forking to read the rollout from file (#3440)

  This PR changes get history op to get path. Then, forking will use a
  path. This will help us have one unified codepath for resuming/forking
  conversations. Will also help in having rollout history in order. It
  also fixes a bug where you won't see the UI when resuming after forking.

  Ahmed Ibrahim · 2025-09-10 17:42:54 -07:00
  162e1235a8
• fix: include rollout_path in NewConversationResponse (#3352)

  Adding the `rollout_path` to the `NewConversationResponse` makes it so a
  client can perform subsequent operations on a `(ConversationId,
  PathBuf)` pair. #3353 will introduce support for `ArchiveConversation`.
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/3352).
  * #3353
  * __->__ #3352

  Michael Bolin · 2025-09-09 00:11:48 -07:00
  2a76a08a9e
• Format large numbers in a more readable way. (#2046)

  - In the bottom line of the TUI, print the number of tokens to 3 sigfigs
    with an SI suffix, e.g. "1.23K".
  - Elsewhere where we print a number, I figure it's worthwhile to print
    the exact number, because e.g. it's a summary of your session. Here we print
    the numbers comma-separated.

  Justin Lebar · 2025-09-08 21:48:48 +00:00
  18330c2362
• Use ConversationId instead of raw Uuids (#3282)

  We're trying to migrate from `session_id: Uuid` to `conversation_id:
  ConversationId`. Not only does this give us more type safety but it
  unifies our terminology across Codex and with the implementation of
  session resuming, a conversation (which can span multiple sessions) is
  more appropriate.
  
  I started this impl on https://github.com/openai/codex/pull/3219 as part
  of getting resume working in the extension but it's big enough that it
  should be broken out.

  Gabriel Peal · 2025-09-07 23:22:25 -04:00
  c8fab51372
• Move token usage/context information to session level (#3221)

  Move context information into the main loop so it can be used to
  interrupt the loop or start auto-compaction.

  pakrym-oai · 2025-09-06 15:19:23 +00:00
  0269096229
• Dividing UserMsgs into categories to send it back to the tui (#3127)

  This PR does the following:
  
  - divides user msgs into 3 categories: plain, user instructions, and
  environment context
  - Centralizes adding user instructions and environment context to a
  degree
  - Improve the integration testing
  
  Building on top of #3123
  
  Specifically this
  [comment](https://github.com/openai/codex/pull/3123#discussion_r2319885089).
  We need to send the user message while ignoring the User Instructions
  and Environment Context we attach.

  Ahmed Ibrahim · 2025-09-04 05:34:50 +00:00
  2b96f9f569
• Replay EventMsgs from Response Items when resuming a session with history. (#3123)

  ### Overview
  
  This PR introduces the following changes:
  	1.	Adds a unified mechanism to convert ResponseItem into EventMsg.
  2. Ensures that when a session is initialized with initial history, a
  vector of EventMsg is sent along with the session configuration. This
  allows clients to re-render the UI accordingly.
  	3. 	Added integration testing
  
  ### Caveats
  
  This implementation does not send every EventMsg that was previously
  dispatched to clients. The excluded events fall into two categories:
  	•	“Arguably” rolled-out events
  Examples include tool calls and apply-patch calls. While these events
  are conceptually rolled out, we currently only roll out ResponseItems.
  These events are already being handled elsewhere and transformed into
  EventMsg before being sent.
  	•	Non-rolled-out events
  Certain events such as TurnDiff, Error, and TokenCount are not rolled
  out at all.
  
  ### Future Directions
  
  At present, resuming a session involves maintaining two states:
  	•	UI State
  Clients can replay most of the important UI from the provided EventMsg
  history.
  	•	Model State
  The model receives the complete session history to reconstruct its
  internal state.
  
  This design provides a solid foundation. If, in the future, more precise
  UI reconstruction is needed, we have two potential paths:
  1. Introduce a third data structure that allows us to derive both
  ResponseItems and EventMsgs.
  2. Clearly divide responsibilities: the core system ensures the
  integrity of the model state, while clients are responsible for
  reconstructing the UI.

  Ahmed Ibrahim · 2025-09-04 04:47:00 +00:00
  f2036572b6
• rework message styling (#2877)

  https://github.com/user-attachments/assets/cf07f62b-1895-44bb-b9c3-7a12032eb371

  Jeremy Rose · 2025-09-02 17:29:58 +00:00
  e442ecedab