70 Commits

• Add resume_agent collab tool (#10903)

  Summary
  - add the new resume_agent collab tool path through core, protocol, and
  the app server API, including the resume events
  - update the schema/TypeScript definitions plus docs so resume_agent
  appears in generated artifacts and README
  - note that resumed agents rehydrate rollout history without overwriting
  their base instructions
  
  Testing
  - Not run (not requested)

  jif-oai · 2026-02-07 17:31:45 +01:00
  62605fa471
• feat: add memory tool (#10637)

  Add a tool for memory to retrieve a full memory based on the memory ID

  jif-oai · 2026-02-05 16:16:31 +00:00
  41f3b1ba0b
• feat: land unified_exec (#10641)

  Land `unified_exec` for all non-windows OS

  jif-oai · 2026-02-04 16:39:41 +00:00
  49dd67a260
• Improve Default mode prompt (less confusion with Plan mode) (#10545)

  ## Summary
  
  This PR updates `request_user_input` behavior and Default-mode guidance
  to match current collaboration-mode semantics and reduce model
  confusion.
  
  ## Why
  
  - `request_user_input` should be explicitly documented as **Plan-only**.
  - Tool description and runtime availability checks should be driven by
  the **same centralized mode policy**.
  - Default mode prompt needed stronger execution guidance and explicit
  instruction that `request_user_input` is unavailable.
  - Error messages should report the **actual mode name** (not aliases
  that can read as misleading).
  
  ## What changed
  
  - Centralized `request_user_input` mode policy in `core` handler logic:
    - Added a single allowed-modes config (`Plan` only).
    - Reused that policy for:
      - runtime rejection messaging
      - tool description text
  - Updated tool description to include availability constraint:
    - `"This tool is only available in Plan mode."`
  - Updated runtime rejection behavior:
    - `Default` -> `"request_user_input is unavailable in Default mode"`
    - `Execute` -> `"request_user_input is unavailable in Execute mode"`
  - `PairProgramming` -> `"request_user_input is unavailable in Pair
  Programming mode"`
  - Strengthened Default collaboration prompt:
    - Added explicit execution-first behavior
    - Added assumptions-first guidance
    - Added explicit `request_user_input` unavailability instruction
    - Added concise progress-reporting expectations
  - Simplified formatting implementation:
    - Inlined allowed-mode name collection into `format_allowed_modes()`
  - Kept `format_allowed_modes()` output for 3+ modes as CSV style
  (`modes: a,b,c`)

  Charley Cunningham · 2026-02-03 12:08:38 -08:00
  998eb8f32b
• Enable parallel shell tools (#10505)

  Summary
  - mark the shell-related tools as supporting parallel tool calls so
  exec_command, shell_command, etc. can run concurrently
  - update expectations in tool parallelism tests to reflect the new
  parallel behavior
  - drop the unused serial duration helper from the suite
  
  Testing
  - Not run (not requested)

  jif-oai · 2026-02-03 18:05:02 +00:00
  33dc93e4d2
• chore: nuke chat/completions API (#10157)
  jif-oai · 2026-02-03 11:31:57 +00:00
  d2394a2494
• feat: replace custom mcp-types crate with equivalents from rmcp (#10349)

  We started working with MCP in Codex before
  https://crates.io/crates/rmcp was mature, so we had our own crate for
  MCP types that was generated from the MCP schema:
  
  
  https://github.com/openai/codex/blob/8b95d3e082376f4cb23e92641705a22afb28a9da/codex-rs/mcp-types/README.md
  
  Now that `rmcp` is more mature, it makes more sense to use their MCP
  types in Rust, as they handle details (like the `_meta` field) that our
  custom version ignored. Though one advantage that our custom types had
  is that our generated types implemented `JsonSchema` and `ts_rs::TS`,
  whereas the types in `rmcp` do not. As such, part of the work of this PR
  is leveraging the adapters between `rmcp` types and the serializable
  types that are API for us (app server and MCP) introduced in #10356.
  
  Note this PR results in a number of changes to
  `codex-rs/app-server-protocol/schema`, which merit special attention
  during review. We must ensure that these changes are still
  backwards-compatible, which is possible because we have:
  
  ```diff
  - export type CallToolResult = { content: Array<ContentBlock>, isError?: boolean, structuredContent?: JsonValue, };
  + export type CallToolResult = { content: Array<JsonValue>, structuredContent?: JsonValue, isError?: boolean, _meta?: JsonValue, };
  ```
  
  so `ContentBlock` has been replaced with the more general `JsonValue`.
  Note that `ContentBlock` was defined as:
  
  ```typescript
  export type ContentBlock = TextContent | ImageContent | AudioContent | ResourceLink | EmbeddedResource;
  ```
  
  so the deletion of those individual variants should not be a cause of
  great concern.
  
  Similarly, we have the following change in
  `codex-rs/app-server-protocol/schema/typescript/Tool.ts`:
  
  ```
  - export type Tool = { annotations?: ToolAnnotations, description?: string, inputSchema: ToolInputSchema, name: string, outputSchema?: ToolOutputSchema, title?: string, };
  + export type Tool = { name: string, title?: string, description?: string, inputSchema: JsonValue, outputSchema?: JsonValue, annotations?: JsonValue, icons?: Array<JsonValue>, _meta?: JsonValue, };
  ```
  
  so:
  
  - `annotations?: ToolAnnotations` ➡️ `JsonValue`
  - `inputSchema: ToolInputSchema` ➡️ `JsonValue`
  - `outputSchema?: ToolOutputSchema` ➡️ `JsonValue`
  
  and two new fields: `icons?: Array<JsonValue>, _meta?: JsonValue`
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10349).
  * #10357
  * __->__ #10349
  * #10356

  Michael Bolin · 2026-02-02 17:41:55 -08:00
  66447d5d2c
• feat(core) Smart approvals on (#10286)

  ## Summary
  Turn on Smart Approvals by default
  
  ## Testing
   - [x] Updated unit tests

  Dylan Hurd · 2026-01-30 23:12:25 -07:00
  a8c9e386e7
• Chore: plan mode do not include free form question and always include isOther (#10210)

  We should never ask a freeform question when planning and we should
  always include isOther as an escape hatch.

  Shijie Rao · 2026-01-30 01:19:24 -08:00
  a0ccef9d5c
• feat(core) RequestRule (#9489)

  ## Summary
  Instead of trying to derive the prefix_rule for a command mechanically,
  let's let the model decide for us.
  
  ## Testing
  - [x] tested locally

  Dylan Hurd · 2026-01-28 08:43:17 +00:00
  996e09ca24
• fix: enable per-turn updates to web search mode (#10040)

  web_search can now be updated per-turn, for things like changes to
  sandbox policy.
  
  `SandboxPolicy::DangerFullAccess` now sets web_search to `live`, and the
  default is still `cached`.
  
  Added integration tests.

  sayan-oai · 2026-01-27 18:09:29 -08:00
  a90ab789c2
• nit: better tool description (#9988)
  jif-oai · 2026-01-27 12:46:51 +00:00
  742f086ee6
• make cached web_search client-side default (#9974)

  [Experiment](https://console.statsig.com/50aWbk2p4R76rNX9lN5VUw/experiments/codex_web_search_rollout/summary)
  for default cached `web_search` completed; cached chosen as default.
  
  Update client to reflect that.

  sayan-oai · 2026-01-26 21:25:40 -08:00
  0adcd8aa86
• fix: attempt to reduce high cpu usage when using collab (#9776)

  Reproduce with a prompt like this with collab enabled:
  ```
  Examine the code at <some subdirectory with a deeply nested project>.  Find the most urgent issue to resolve and describe it to me.
  ```
  
  Existing behavior causes the top-level agent to busy wait on subagents.

  Gene Oden · 2026-01-26 10:07:25 -08:00
  375a5ef051
• Feat: add isOther to question returned by request user input tool (#9890)

  ### Summary
  Add `isOther` to question object from request_user_input tool input and
  remove `other` option from the tool prompt to better handle tool input.

  Shijie Rao · 2026-01-26 09:52:38 -08:00
  3ba702c5b6
• 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: collab wait multiple IDs (#9294)
  jif-oai · 2026-01-16 12:05:04 +01:00
  c576756c81
• [search] allow explicitly disabling web search (#9249)

  moving `web_search` rollout serverside, so need a way to explicitly
  disable search + signal eligibility from the client.
  
  - Add `x‑oai‑web‑search‑eligible` header that signifies whether the
  request can have web search.
  - Only attach the `web_search` tool when the resolved `WebSearchMode` is
  `Live` or `Cached`.

  sayan-oai · 2026-01-15 11:28:57 -08:00
  169201b1b5
• feat: add interrupt capabilities to send_input (#9276)
  jif-oai · 2026-01-15 14:59:07 +00:00
  faeb08c1e1
• feat: add agent roles to collab tools (#9275)

  Add `agent_type` parameter to the collab tool `spawn_agent` that
  contains a preset to apply on the config when spawning this agent

  jif-oai · 2026-01-15 13:33:52 +00:00
  05b960671d
• add WebSearchMode enum (#9216)

  ### What
  Add `WebSearchMode` enum (disabled, cached live, defaults to cached) to
  config + V2 protocol. This enum takes precedence over legacy flags:
  `web_search_cached`, `web_search_request`, and `tools.web_search`.
  
  Keep `--search` as live.
  
  ### Tests
  Added tests

  sayan-oai · 2026-01-14 12:51:42 -08:00
  5e426ac270
• feat: adding piped process to replace PTY when needed (#8797)
  jif-oai · 2026-01-14 18:44:04 +00:00
  577e1fd1b2
• chore: clarify default shell for unified_exec (#8997)

  The description of the `shell` arg for `exec_command` states the default
  is `/bin/bash`, but AFAICT it's the user's default shell.
  
  Default logic
  [here](https://github.com/openai/codex/blob/2a06d64bc996e4d848b95285700b195c2852a42f/codex-rs/core/src/tools/handlers/unified_exec.rs#L123).
  
  EDIT: #9004 has an alternative where we inform the model of the default
  shell itself.

  sayan-oai · 2026-01-13 21:37:41 -08:00
  5675af5190
• Label attached images so agent can understand in-message labels (#8950)

  Agent wouldn't "see" attached images and would instead try to use the
  view_file tool:
  <img width="1516" height="504" alt="image"
  src="https://github.com/user-attachments/assets/68a705bb-f962-4fc1-9087-e932a6859b12"
  />
  
  In this PR, we wrap image content items in XML tags with the name of
  each image (now just a numbered name like `[Image #1]`), so that the
  model can understand inline image references (based on name). We also
  put the image content items above the user message which the model seems
  to prefer (maybe it's more used to definitions being before references).
  
  We also tweak the view_file tool description which seemed to help a bit
  
  Results on a simple eval set of images:
  
  Before
  <img width="980" height="310" alt="image"
  src="https://github.com/user-attachments/assets/ba838651-2565-4684-a12e-81a36641bf86"
  />
  
  After
  <img width="918" height="322" alt="image"
  src="https://github.com/user-attachments/assets/10a81951-7ee6-415e-a27e-e7a3fd0aee6f"
  />
  
  ```json
  [
    {
      "id": "single_describe",
      "prompt": "Describe the attached image in one sentence.",
      "images": ["image_a.png"]
    },
    {
      "id": "single_color",
      "prompt": "What is the dominant color in the image? Answer with a single color word.",
      "images": ["image_b.png"]
    },
    {
      "id": "orientation_check",
      "prompt": "Is the image portrait or landscape? Answer in one sentence.",
      "images": ["image_c.png"]
    },
    {
      "id": "detail_request",
      "prompt": "Look closely at the image and call out any small details you notice.",
      "images": ["image_d.png"]
    },
    {
      "id": "two_images_compare",
      "prompt": "I attached two images. Are they the same or different? Briefly explain.",
      "images": ["image_a.png", "image_b.png"]
    },
    {
      "id": "two_images_captions",
      "prompt": "Provide a short caption for each image (Image 1, Image 2).",
      "images": ["image_c.png", "image_d.png"]
    },
    {
      "id": "multi_image_rank",
      "prompt": "Rank the attached images from most colorful to least colorful.",
      "images": ["image_a.png", "image_b.png", "image_c.png"]
    },
    {
      "id": "multi_image_choice",
      "prompt": "Which image looks more vibrant? Answer with 'Image 1' or 'Image 2'.",
      "images": ["image_b.png", "image_d.png"]
    }
  ]
  ```

  charley-oai · 2026-01-09 21:33:45 -08:00
  6709ad8975
• chore: non mutable btree when building specs (#8969)
  jif-oai · 2026-01-09 12:21:55 +00:00
  e9c548c65e
• feat: first pass on clb tool (#8930)
  jif-oai · 2026-01-09 11:54:05 +00:00
  568b938c80
• chore: drop useless feature flags (#8850)
  jif-oai · 2026-01-07 19:54:32 +00:00
  1253d19641
• Merge Modelfamily into modelinfo (#8763)

  - Merge ModelFamily into ModelInfo
  - Remove logic for adding instructions to apply patch
  - Add compaction limit and visible context window to `ModelInfo`

  Ahmed Ibrahim · 2026-01-07 10:35:09 -08:00
  9179c9deac
• chore: unify conversation with thread name (#8830)

  Done and verified by Codex + refactor feature of RustRover

  jif-oai · 2026-01-07 17:04:53 +00:00
  116059c3a0
• add web_search_cached flag (#8795)

  Add `web_search_cached` feature to config. Enables `web_search` tool
  with access only to cached/indexed results (see
  [docs](https://platform.openai.com/docs/guides/tools-web-search#live-internet-access)).
  
  This takes precedence over the existing `web_search_request`, which
  continues to enable `web_search` over live results as it did before.
  
  `web_search_cached` is disabled for review mode, as `web_search_request`
  is.

  sayan-oai · 2026-01-06 14:53:59 -08:00
  54ded1a3c0
• Rename OpenAI models to models manager (#8346)

  # 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.

  Ahmed Ibrahim · 2025-12-19 16:20:05 -08:00
  f0dc6fd3c7
• nit: doc (#8186)
  jif-oai · 2025-12-17 15:29:29 +00:00
  45c164a982
• feat: fallback unified_exec to shell_command (#8075)
  jif-oai · 2025-12-17 10:29:45 +00:00
  813bdb9010
• Update Model Info (#7853)
  Ahmed Ibrahim · 2025-12-11 14:06:07 -08:00
  b7fa7ca8e9
• Chore: limit find family visability (#7891)

  a little bit more code quality of life

  Ahmed Ibrahim · 2025-12-11 13:30:56 -08:00
  b9fb3b81e5
• feat: add shell snapshot for shell command (#7786)
  jif-oai · 2025-12-11 13:46:43 +00:00
  29381ba5c2
• refactoring with_escalated_permissions to use SandboxPermissions instead (#7750)

  helpful in the future if we want more granularity for requesting
  escalated permissions:
  e.g when running in readonly sandbox, model can request to escalate to a
  sandbox that allows writes

  zhao-oai · 2025-12-10 17:18:48 +00:00
  e0fb3ca1db
• Fixed regression for chat endpoint; missing tools name caused litellm proxy to crash (#7724)

  This PR addresses https://github.com/openai/codex/issues/7051

  Eric Traut · 2025-12-08 00:49:51 -08:00
  acb8ed493f
• feat(core) Add login to shell_command tool (#6846)

  ## Summary
  Adds the `login` parameter to the `shell_command` tool - optional,
  defaults to true.
  
  ## Testing
  - [x] Tested locally

  Dylan Hurd · 2025-12-05 11:03:25 -08:00
  a8cbbdbc6e
• Call models endpoint in models manager (#7616)

  - Introduce `with_remote_overrides` and update
  `refresh_available_models`
  - Put `auth_manager` instead of `auth_mode` on `models_manager`
  - Remove `ShellType` and `ReasoningLevel` to use already existing
  structs

  Ahmed Ibrahim · 2025-12-04 18:28:03 -08:00
  7b359c9c8e
• Migrate model family to models manager (#7565)

  This PR moves `ModelsFamily` to `openai_models`. It also propagates
  `ModelsManager` to session services and use it to drive model family. We
  also make `derive_default_model_family` private because it's a step
  towards what we want: one place that gives model configuration.
  
  This is a second step at having one source of truth for models
  information and config: `ModelsManager`.
  
  Next steps would be to remove `ModelsFamily` from config. That's massive
  because it's being used in 41 occasions mostly pre launching `codex`.
  Also, we need to make `find_family_for_model` private. It's also big
  because it's being used in 21 occasions ~ all tests.

  Ahmed Ibrahim · 2025-12-03 18:49:47 -08:00
  cee37a32b2
• enable unified exec for experiments (#7118)
  Ahmed Ibrahim · 2025-11-21 13:10:01 -08:00
  d5f661c91d
• Delete shell_command feature (#7024)
  pakrym-oai · 2025-11-20 14:14:56 -08:00
  856f97f449
• shell_command returns freeform output (#6860)

  Instead of returning structured out and then re-formatting it into
  freeform, return the freeform output from shell_command tool.
  
  Keep `shell` as the default tool for GPT-5.

  pakrym-oai · 2025-11-18 23:38:43 -08:00
  ee0484a98c
• chore(config) enable shell_command (#6843)

  ## Summary
  Enables shell_command as default for `gpt-5*` and `codex-*` models.
  
  ## Testing
  - [x] Updated unit tests

  Dylan Hurd · 2025-11-18 12:46:02 -08:00
  29ca89c414
• fix(windows) shell_command on windows, minor parsing (#6811)

  ## Summary
  Enables shell_command for windows users, and starts adding some basic
  command parsing here, to at least remove powershell prefixes. We'll
  follow this up with command parsing but I wanted to land this change
  separately with some basic UX.
  
  **NOTE**: This implementation parses bash and powershell on both
  platforms. In theory this is possible, since you can use git bash on
  windows or powershell on linux. In practice, this may not be worth the
  complexity of supporting, so I don't feel strongly about the current
  approach vs. platform-specific branching.
  
  ## Testing
  - [x] Added a bunch of tests 
  - [x] Ran on both windows and os x

  Dylan Hurd · 2025-11-17 22:23:53 -08:00
  28ebe1c97a
• core: add a feature to disable the shell tool (#6481)

  `--disable shell_tool` disables the built-in shell tool. This is useful
  for MCP-only operation.
  
  ---------
  
  Co-authored-by: Michael Bolin <mbolin@openai.com>

  Jeremy Rose · 2025-11-17 22:56:19 +00:00
  ab2e7499f8
• chore(core) Update shell instructions (#6679)

  ## Summary
  Consolidates `shell` and `shell_command` tool instructions.
  ## Testing 
  - [x] Updated tests, tested locally

  Dylan Hurd · 2025-11-17 13:05:15 -08:00
  daf77b8452
• remove porcupine model slug (#6580)
  Ahmed Ibrahim · 2025-11-13 04:43:31 +00:00
  b1979b70a8