3718 Commits

This Branch

This Branch

All Branches

• 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
• fix(app-server): fix approval events in review mode (#10416)

  One of our partners flagged that they were seeing the wrong order of
  events when running `review/start` with command exec approvals:
  ```
  {"method":"item/commandExecution/requestApproval","id":0,"params":{"threadId":"019c0b6b-6a42-7c02-99c4-98c80e88ac27","turnId":"0","itemId":"0","reason":"`/bin/zsh -lc 'git show b7a92b4eacf262c575f26b1e1ed621a357642e55 --stat'` requires approval: Xcode-required approval: Require explicit user confirmation for all commands.","proposedExecpolicyAmendment":null}}
  
  {"method":"item/started","params":{"item":{"type":"commandExecution","id":"call_AEjlbHqLYNM7kbU3N6uw1CNi","command":"/bin/zsh -lc 'git show b7a92b4eacf262c575f26b1e1ed621a357642e55 --stat'","cwd":"/Users/devingreen/Desktop/SampleProject","processId":null,"status":"inProgress","commandActions":[{"type":"unknown","command":"git show b7a92b4eacf262c575f26b1e1ed621a357642e55 --stat"}],"aggregatedOutput":null,"exitCode":null,"durationMs":null},"threadId":"019c0b6b-6a42-7c02-99c4-98c80e88ac27","turnId":"0"}}
  ```
  
  **Key fix**: In the review sub‑agent delegate we were forwarding exec
  (and patch) approvals using the parent turn id (`parent_ctx.sub_id`) as
  the approval call_id. That made
  `item/commandExecution/requestApproval.itemId` differ from the actual
  `item/started` id. We now forward the sub‑agent’s `call_id` from the
  approval event instead, so the approval item id matches the
  commandExecution item id in review flows.
  
  Here’s the expected event order for an inline `review/start` that
  triggers an exec approval after this fix:
  1. Response to review/start (JSON‑RPC response)
  - Includes `turn` (status inProgress) and `review_thread_id` (same as
  parent thread for inline).
  2. `turn/started` notification
    - turnId is the review turn id (e.g., "0").
  3. `item/started` → EnteredReviewMode
    - item.id == turnId, marks entry into review mode.
  4. `item/started` → commandExecution
    - item.id == <call_id> (e.g., "review-call-1"), status: inProgress.
  5. `item/commandExecution/requestApproval` request
    - JSON‑RPC request (not a notification).
    - params.itemId == <call_id> and params.turnId == turnId.
  6. Client replies to approval request (Approved / Declined / etc).
  7. If approved:
    - Optional `item/commandExecution/outputDelta` notifications.
    - `item/completed` → commandExecution with status and exitCode.
  8. Review finishes:
    - `item/started` → ExitedReviewMode
    - `item/completed` → ExitedReviewMode
    - (Agent message items may also appear, depending on review output.)
  9. `turn/completed` notification
  
  The key being #4 and #5 are now in the proper order with the correct
  item id.

  Owen Lin · 2026-02-03 12:08:17 -08:00
  d9ad5c3c49
• fix(app-server): fix TS annotations for optional fields on requests (#10412)

  This updates our generated TypeScript types to be more correct with how
  the server actually behaves, **specifically for JSON-RPC requests**.
  
  Before this PR, we'd generate `field: T | null`. After this PR, we will
  have `field?: T | null`. The latter matches how the server actually
  works, in that if an optional field is omitted, the server will treat it
  as null. This also makes it less annoying in theory for clients to
  upgrade to newer versions of Codex, since adding a new optional field to
  a JSON-RPC request should not require a client change.
  
  NOTE: This only applies to JSON-RPC requests. All other payloads (i.e.
  responses, notifications) will return `field: T | null` as usual.

  Owen Lin · 2026-02-03 11:51:37 -08:00
  efd96c46c7
• Revert "Load untrusted rules" (#10536)

  Reverts openai/codex#9791

  viyatb-oai · 2026-02-03 19:38:44 +00:00
  1dcce204fc
• Inject CODEX_THREAD_ID into the terminal environment (#10096)

  Inject CODEX_THREAD_ID (when applicable) into the terminal environment
  so that the agent (and skills) can refer to the current thread / session
  ID.
  
  Discussion:
  https://openai.slack.com/archives/C095U48JNL9/p1769542492067109

  Max Johnson · 2026-02-03 11:31:12 -08:00
  66b196a725
• fix: make $PWD/.agents read-only like $PWD/.codex (#10524)

  In light of https://github.com/openai/codex/pull/10317, because
  `.agents` can include resources that Codex can run in a privileged way,
  it should be read-only by default just as `.codex` is.

  Michael Bolin · 2026-02-03 11:26:34 -08:00
  9a487f9c18
• feat: find_thread_path_by_id_str_in_subdir from DB (#10532)
  jif-oai · 2026-02-03 19:09:04 +00:00
  c38a5958d7
• 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
• Cleanup collaboration mode variants (#10404)

  ## Summary
  
  This PR simplifies collaboration modes to the visible set `default |
  plan`, while preserving backward compatibility for older partners that
  may still send legacy mode
  names.
  
  Specifically:
  - Renames the old Code behavior to **Default**.
  - Keeps **Plan** as-is.
  - Removes **Custom** mode behavior (fallbacks now resolve to Default).
  - Keeps `PairProgramming` and `Execute` internally for compatibility
  plumbing, while removing them from schema/API and UI visibility.
  - Adds legacy input aliasing so older clients can still send old mode
  names.
  
  ## What Changed
  
  1. Mode enum and compatibility
  - `ModeKind` now uses `Plan` + `Default` as active/public modes.
  - `ModeKind::Default` deserialization accepts legacy values:
    - `code`
    - `pair_programming`
    - `execute`
    - `custom`
  - `PairProgramming` and `Execute` variants remain in code but are hidden
  from protocol/schema generation.
  - `Custom` variant is removed; previous custom fallbacks now map to
  `Default`.
  
  2. Collaboration presets and templates
  - Built-in presets now return only:
    - `Plan`
    - `Default`
  - Template rename:
    - `core/templates/collaboration_mode/code.md` -> `default.md`
  - `execute.md` and `pair_programming.md` remain on disk but are not
  surfaced in visible preset lists.
  
  3. TUI updates
  - Updated user-facing naming and prompts from “Code” to “Default”.
  - Updated mode-cycle and indicator behavior to reflect only visible
  `Plan` and `Default`.
  - Updated corresponding tests and snapshots.
  
  4. request_user_input behavior
  - `request_user_input` remains allowed only in `Plan` mode.
  - Rejection messaging now consistently treats non-plan modes as
  `Default`.
  
  5. Schemas
  - Regenerated config and app-server schemas.
  - Public schema types now advertise mode values as:
    - `plan`
    - `default`
  
  ## Backward Compatibility Notes
  
  - Incoming legacy mode names (`code`, `pair_programming`, `execute`,
  `custom`) are accepted and coerced to `default`.
  - Outgoing/public schema surfaces intentionally expose only `plan |
  default`.
  - This allows tolerant ingestion of older partner payloads while
  standardizing new integrations on the reduced mode set.
  
  ## Codex author
  `codex fork 019c1fae-693b-7840-b16e-9ad38ea0bd00`

  Charley Cunningham · 2026-02-03 09:23:53 -08:00
  d509df676b
• fix WebSearchAction type clash between v1 and v2 (#10408)

  type clash; app-server generated types were still using the v1
  snake_case `WebSearchAction`, so there was a mismatch between the
  camelCase emitted types and the snake_case types we were trying to
  parse.
  
  Updated v2 `WebSearchAction` to export into the `v2/` type set and
  updated `ThreadItem` to use that.
  
  ### Tests
  Ran new `just write-app-server-schema` to surface changes to schema, the
  import looks correct now.

  sayan-oai · 2026-02-03 17:12:37 +00:00
  aea38f0f88
• chore: update bytes crate in response to security advisory (#10525)

  While here, remove one advisory from `deny.toml` that has been addressed
  (it was showing up as a warning).

  Michael Bolin · 2026-02-03 17:08:04 +00:00
  1634db6677
• Avoid redundant transactional check before inserting dynamic tools (#10521)

  Summary
  - remove the extra transaction guard that checked for existing dynamic
  tools per thread before inserting new ones
  - insert each tool record with `ON CONFLICT(thread_id, position) DO
  NOTHING` to ignore duplicates instead of pre-querying
  - simplify execution to use the shared pool directly and avoid unneeded
  commits
  
  Testing
  - Not run (not requested)

  jif-oai · 2026-02-03 15:34:28 +00:00
  ed778f9017
• Add more detail to 401 error (#10508)

  Add the error.message if it exists, the body otherwise. Truncate body to
  1k characters. Print the cf-ray and the requestId.
  
  **Before:**
  <img width="860" height="305" alt="Screenshot 2026-02-03 at 13 15 28"
  src="https://github.com/user-attachments/assets/949d5a4d-2b51-488c-a723-c6deffde0353"
  />
  
  **After:**
  <img width="1523" height="373" alt="Screenshot 2026-02-03 at 13 15 38"
  src="https://github.com/user-attachments/assets/f96a747e-e596-4a7a-aae9-64210d805b26"
  />

  gt-oai · 2026-02-03 14:58:33 +00:00
  944541e936
• feat: clean codex-api part 1 (#10501)
  jif-oai · 2026-02-03 14:08:09 +00:00
  d5e7248958
• feat: drop wire_api from clients (#10498)
  jif-oai · 2026-02-03 12:43:09 +00:00
  88598b9402
• chore: nuke chat/completions API (#10157)
  jif-oai · 2026-02-03 11:31:57 +00:00
  d2394a2494
• feat(secrets): add codex-secrets crate (#10142)

  ## Summary
  This introduces the first working foundation for Codex managed secrets:
  a small Rust crate that can securely store and retrieve secrets locally.
  
  Concretely, it adds a `codex-secrets` crate that:
  - encrypts a local secrets file using `age`
  - generates a high-entropy encryption key
  - stores that key in the OS keyring
  
  ## What this enables
  - A secure local persistence model for secrets
  - A clean, isolated place for future provider backends
  - A clear boundary: Codex can become a credential broker without putting
  plaintext secrets in config files
  
  ## Implementation details
  - New crate: `codex-rs/secrets/`
  - Encryption: `age` with scrypt recipient/identity
  - Key generation: `OsRng` (32 random bytes)
  - Key storage: OS keyring via `codex-keyring-store`
  
  ## Testing
  - `cd codex-rs && just fmt`
  - `cd codex-rs && cargo test -p codex-secrets`

  viyatb-oai · 2026-02-03 08:14:39 +00:00
  9257d8451c
• feat(linux-sandbox): vendor bubblewrap and wire it with FFI (#10413)

  ## Summary
  
  Vendor Bubblewrap into the repo and add minimal build plumbing in
  `codex-linux-sandbox` to compile/link it.
  
  ## Why
  
  We want to move Linux sandboxing toward Bubblewrap, but in a safe
  two-step rollout:
  1) vendoring/build setup (this PR),  
  2) runtime integration (follow-up PR).
  
  ## Included
  
  - Add `codex-rs/vendor/bubblewrap` sources.
  - Add build-time FFI path in `codex-rs/linux-sandbox`.
  - Update `build.rs` rerun tracking for vendored files.
  - Small vendored compile warning fix (`sockaddr_nl` full init).
  
  follow up in https://github.com/openai/codex/pull/9938

  viyatb-oai · 2026-02-02 23:33:46 -08:00
  f956cc2a02
• Ignore remote_compact_trims_function_call_history_to_fit_context_window on windows (#10474)
  pakrym-oai · 2026-02-02 22:47:38 -08:00
  53d8474061
• fix: clarify deprecation message for features.web_search (#10406)

  clarify that the new `web_search` is not a feature flag under
  `[features]` in the deprecation CTA

  sayan-oai · 2026-02-02 21:17:01 -08:00
  59707da857
• Restore status after preamble (#10465)
  pakrym-oai · 2026-02-02 20:35:50 -08:00
  bf87468c2b
• Updated bug and feature templates (#10453)

  The current bug template uses CLI-specific instructions for getting the
  version.
  
  The current feature template doesn't ask the user to provide the Codex
  variant (surface) they are using.
  
  This PR addresses these problems.

  Eric Traut · 2026-02-02 20:08:08 -08:00
  8b280367b1
• Trim compaction input (#10374)

  Two fixes:
  
  1. Include trailing tool output in the total context size calculation.
  Otherwise when checking whether compaction should run we ignore newly
  added outputs.
  2. Trim trailing tool output/tool calls until we can fit the request
  into the model context size. Otherwise the compaction endpoint will fail
  to compact. We only trim items that can be reproduced again by the model
  (tool calls, tool call outputs).

  pakrym-oai · 2026-02-02 19:03:11 -08:00
  cbfd2a37cc
• [Codex][CLI] Gate image inputs by model modalities (#10271)

  ###### Summary
  
  - Add input_modalities to model metadata so clients can determine
  supported input types.
  - Gate image paste/attach in TUI when the selected model does not
  support images.
  - Block submits that include images for unsupported models and show a
  clear warning.
  - Propagate modality metadata through app-server protocol/model-list
  responses.
    - Update related tests/fixtures.
  
    ###### Rationale
  
    - Models support different input modalities.
  - Clients need an explicit capability signal to prevent unsupported
  requests.
  - Backward-compatible defaults preserve existing behavior when modality
  metadata is absent.
  
    ###### Scope
  
    - codex-rs/protocol, codex-rs/core, codex-rs/tui
    - codex-rs/app-server-protocol, codex-rs/app-server
    - Generated app-server types / schema fixtures
  
    ###### Trade-offs
  
  - Default behavior assumes text + image when field is absent for
  compatibility.
    - Server-side validation remains the source of truth.
  
    ###### Follow-up
  
  - Non-TUI clients should consume input_modalities to disable unsupported
  attachments.
  - Model catalogs should explicitly set input_modalities for text-only
  models.
  
    ###### Testing
  
    - cargo fmt --all
    - cargo test -p codex-tui
    - env -u GITHUB_APP_KEY cargo test -p codex-core --lib
    - just write-app-server-schema
  - cargo run -p codex-cli --bin codex -- app-server generate-ts --out
  app-server-types
    - test against local backend
    
  <img width="695" height="199" alt="image"
  src="https://github.com/user-attachments/assets/d22dd04f-5eba-4db9-a7c5-a2506f60ec44"
  />
  
  ---------
  
  Co-authored-by: Josh McKinney <joshka@openai.com>

  Colin Young · 2026-02-02 18:56:39 -08:00
  7e07ec8f73
• Require models refresh on cli version mismatch (#10414)
  Ahmed Ibrahim · 2026-02-02 18:55:25 -08:00
  b8addcddb9
• chore: add phase to message responseitem (#10455)

  ### What
  
  add wiring for `phase` field on `ResponseItem::Message` to lay
  groundwork for differentiating model preambles and final messages.
  currently optional.
  
  follows pattern in #9698.
  
  updated schemas with `just write-app-server-schema` so we can see type
  changes.
  
  ### Tests
  Updated existing tests for SSE parsing and hydrating from history

  sayan-oai · 2026-02-03 02:52:26 +00:00
  fc05374344
• app tool tip (#10454)

  # 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 · 2026-02-03 02:37:01 +00:00
  0999fd82b9
• chore: remove deprecated mcp-types crate (#10357)

  https://github.com/openai/codex/pull/10349 migrated us off of
  `mcp-types`, so this PR deletes the code.
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10357).
  * __->__ #10357
  * #10349
  * #10356

  Michael Bolin · 2026-02-03 02:33:16 +00:00
  891ed87409
• Hide short worked-for label in final separator (#10452)

  - Hide the "Worked for" label in the final message separator unless
  elapsed time is over one minute.\n- Update/add tests to cover both
  hidden (<60s) and shown (>=61s) behavior.

  Ahmed Ibrahim · 2026-02-03 02:29:20 +00:00
  97ff090104
• Fixed sandbox mode inconsistency if untrusted is selected (#10415)

  This PR addresses #10395
  
  When a user is asked to pick the trust level of a project, the code
  currently reloads the config if they select "trusted". It doesn't reload
  the config in the "untrusted" case but should. This causes the sandbox
  mode to be reported incorrectly in `/status` during the first run (it's
  displayed as `read-only` even though it acts as though it's
  `workspace-write`).

  Eric Traut · 2026-02-03 02:00:35 +00:00
  8dd41e229b
• 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
• TUI: Render request_user_input results in history and simplify interrupt handling (#10064)

  ## Summary
  This PR improves the TUI experience for `request_user_input` by
  rendering submitted question/answer sets directly in conversation
  history with clear, structured formatting.
  
  It also intentionally simplifies interrupt behavior for now: on `Esc` /
  `Ctrl+C`, the questions overlay interrupts the turn without attempting
  to submit partial answers.
  
  <img width="1344" height="573" alt="Screenshot 2026-02-02 at 4 51 40 PM"
  src="https://github.com/user-attachments/assets/ff752131-7060-44c1-9ded-af061969a533"
  />
  
  ## Scope
  - TUI-only changes.
  - No core/protocol/app-server behavior changes in this PR.
  - Resume reconstruction of interrupted question sets is out of scope for
  this PR.
  
  ## What Changed
  - Added a new history cell: `RequestUserInputResultCell` in
  `codex-rs/tui/src/history_cell.rs`.
  - On normal `request_user_input` submission, TUI now inserts that
  history cell immediately after sending `Op::UserInputAnswer`.
  - Rendering includes a `Questions` header with `answered/total` count.
  - Rendering shows each question as a bullet item.
  - Rendering styles submitted answer lines in cyan.
  - Rendering styles notes (for option questions) as `note:` lines in
  cyan.
  - Rendering styles freeform text (for no-option questions) as `answer:`
  lines in cyan.
  - Rendering dims only the `(unanswered)` suffix.
  - Rendering can include an interrupted suffix and summary text when the
  cell is marked interrupted.
  - Rendering redacts secret questions as `••••••` instead of showing raw
  values.
  - Added `wrap_with_prefix(...)` in `history_cell.rs` for wrapped
  prefixed lines.
  - Added `split_request_user_input_answer(...)` in `history_cell.rs` for
  decoding `"user_note: ..."` entries.
  
  ## Interrupt Behavior (Intentional for this PR)
  - `Esc` / `Ctrl+C` in the questions overlay now performs `Op::Interrupt`
  and exits the overlay.
  - It does **not** submit partial/committed answers on interrupt.
  - Added TODO comments in `request_user_input` overlay interrupt paths
  indicating where interrupted partial result emission should be
  reintroduced once core support is finalized.
  - Queued `request_user_input` overlays are discarded on interrupt in the
  current behavior.
  
  ## Tests Updated
  - Updated/added overlay tests in
  `codex-rs/tui/src/bottom_pane/request_user_input/mod.rs` to reflect
  interrupt-only behavior.
  - Added helper assertion for interrupt-only event expectation.
  - Existing submission-path tests now validate history insertion behavior
  and expected answer maps.
  
  ## Behavior Notes
  - Completed question flows now produce a readable `Questions` block in
  transcript history.
  - Interrupted flows currently do not persist partial answers to
  model-visible tool output.
  
  ## Follow-ups
  - Reintroduce partial-answer-on-interrupt semantics once core can
  persist/sequence interrupted `request_user_input` outputs safely.
  - Optionally add replay/resume rendering for interrupted question sets
  as a separate PR.
  
  ## Codex author
  `codex fork 019bfb8d-2a65-7313-9be2-ea7100d19a61`

  Charley Cunningham · 2026-02-02 17:41:30 -08:00
  8f5edddf71
• Fix plan implementation prompt reappearing after /agent thread switch (#10447)

  ## Summary
  
  This fixes a UX bug (https://github.com/openai/codex/issues/10442) where
  the **"Implement this plan?"** prompt could reappear after switching
  agents with `/agent` and then switching back to the original agent
  during plan execution.
  
  ## Root Cause
  
  On thread switch, the TUI rebuilds `ChatWidget`, replays buffered thread
  events, then drains any queued live events.
  
  In this flow, a `TurnComplete` can be handled twice for the same logical
  turn:
  1. replayed (`from_replay = true`)
  2. then live (`from_replay = false`)
  
  `ChatWidget` used `saw_plan_item_this_turn` to decide whether to show
  the plan implementation prompt, but that flag was only reset on
  `TurnStarted`.
  If duplicate completion events occurred, stale `saw_plan_item_this_turn
  = true` could cause the prompt to re-trigger unexpectedly.
  
  ## Fix
  
  - Clear `saw_plan_item_this_turn` at the end of `on_task_complete`,
  after prompt gating runs.
  - This keeps the flag truly turn-scoped and prevents duplicate
  `TurnComplete` handling from reopening the prompt.

  Charley Cunningham · 2026-02-02 17:40:05 -08:00
  1096d6453c
• Add codex app macOS launcher (#10418)

  - Add `codex app <path>` to launch the Codex Desktop app.
  - On macOS, auto-downloads the DMG if missing; non-macOS prints a link
  to chatgpt.com/codex.

  Ahmed Ibrahim · 2026-02-02 17:37:04 -08:00
  d02db8b43d
• make codex better at git (#10145)

  adds basic git context to the session prefix so the model can anchor git
  actions and be a bit more version-aware. structured it in a
  multiroot-friendly shape even though we only have one root today

  pash-openai · 2026-02-02 16:57:29 -08:00
  019d89ff86
• feat: Read personal skills from .agents/skills (#10437)

  - Issue: https://github.com/agentskills/agentskills/issues/15
  - Follow-up to https://github.com/openai/codex/pull/10317 (for team/repo
  skills)
  - This change now also loads personal/user skills from
  `$HOME/.agents/skills` (or `~/.agents/skills`) in addition to loading
  from `.agents/skills` inside of git repos.
  - The location of `.system` skills remains unchanged.
  - Keeping backwards compatibility with `~/.codex/skills` for now until
  we fully deprecate.
  
  With skills in both personal folders:
  <img width="831" height="421" alt="image"
  src="https://github.com/user-attachments/assets/ad8ac918-bfe6-4a2d-8a8e-d608c9d3d701"
  />
  
  We load from both places:
  <img width="607" height="236" alt="image"
  src="https://github.com/user-attachments/assets/480f4db0-ae64-4dc1-bdf5-c5de98c16f5c"
  />

  Gav Verma · 2026-02-02 16:49:23 -08:00
  e24058b7a8
• [feat] persist thread_dynamic_tools in db (#10252)

  Persist thread_dynamic_tools in sqlite and read first from it. Fall back
  to rollout files if it's not found. Persist dynamic tools to both sqlite
  and rollout files.
  
  Saw that new sessions get populated to db correctly & old sessions get
  backfilled correctly at startup:
  ```
  celia@com-92114 codex-rs % sqlite3 ~/.codex/state.sqlite \      "select thread_id, position,name,description,input_schema from thread_dynamic_tools;"
  019c0cad-ec0d-74b2-a787-e8b33a349117|0|geo_lookup|lookup a city|{"properties":{"city":{"type":"string"}},"required":["city"],"type":"object"}
  ....
  019c10ca-aa4b-7620-ae40-c0919fbd7ea7|0|geo_lookup|lookup a city|{"properties":{"city":{"type":"string"}},"required":["city"],"type":"object"}
  ```

  Celia Chen · 2026-02-03 00:06:44 +00:00
  fb2df99cf1
• chore(tui) /personalities tip (#10377)

  ## Summary
  We have /personality now.
  
  ## Testing
  - [x] tested locally

  Dylan Hurd · 2026-02-02 15:35:37 -08:00
  98debeda8a
• emit a separate metric when the user cancels UAT during elevated setup (#10399)

  Currently this shows up as elevated setup failure, which isn't quite
  accurate.

  iceweasel-oai · 2026-02-02 15:31:08 -08:00
  a5066bef78
• Updated labeler workflow prompt to include "app" label (#10411)

  Support for desktop app issues

  Eric Traut · 2026-02-02 13:13:14 -08:00
  0f15ed4325
• fix: unsafe auto-approval of git commands (#10258)

  fixes https://github.com/openai/codex/issues/10160 and some more.
  
  ## Description
  
  Hardens Git command safety to prevent approval bypasses for destructive
  or write-capable invocations (branch delete, risky push forms,
  output/config-override flags), so these commands no longer auto-run as
  “safe.”
  
  - `git branch -d` variants (especially in worktrees / with global
  options like -C / -c)
  - `git show|diff|log --output` ... style file-write flags
  - risky Git config override flags (-c, --config-env) that can trigger
  external execution
  - dangerous push forms that weren’t fully caught (`--force*`,
  `--delete`, `+refspec`, `:refspec`)
  - grouped short-flag delete forms (e.g. stacked branch flags containing
  `d/D`)
  
  will fast follow with a common git policy to bring windows to parity.
  
  ---------
  
  Co-authored-by: Eric Traut <etraut@openai.com>

  viyatb-oai · 2026-02-02 12:30:17 -08:00
  f50c8b2f81
• feat: add --experimental to generate-ts (#10402)

  Adding a `--experimental` flag to the `generate-ts` fct in the
  app-sever.
  
  It can be called through one of those 2 command
  ```
  just write-app-server-schema --experimental
  codex app-server generate-ts --experimental
  ```

  jif-oai · 2026-02-02 20:30:01 +00:00
  059d386f03
• Select experimental features with space (#10281)
  pakrym-oai · 2026-02-02 11:35:11 -08:00
  74327fa59c
• feat: drop sqlx logging (#10398)
  jif-oai · 2026-02-02 19:26:58 +00:00
  34c0534f6e
• chore: ignore synthetic messages (#10394)

  This will be fixed once this is settled:
  https://www.notion.so/openai/Artificial-context-management-2fb8e50b62b080db8b8ed93b3b19d1a2#2fb8e50b62b080d2bffce2dd1e60972b

  jif-oai · 2026-02-02 18:13:48 +00:00
  0b460eda32
• Add credits tooltip (#10274)
  pakrym-oai · 2026-02-02 10:06:43 -08:00
  9d976962ec
• Nicer highlighting of slash commands, /plan accepts prompt args and pasted images (#10269)

  ## Summary
  - Make typed slash commands become text elements when the user hits
  space, including paste‑burst spaces.
  - Enable `/plan` to accept inline args and submit them in plan mode,
  mirroring `/review` behavior and blocking submission while a task is
  running.
  - Preserve text elements/attachments for slash commands that take args.
  
  <img width="1510" height="500" alt="image"
  src="https://github.com/user-attachments/assets/446024df-b69a-4249-85db-1a85110e07f1"
  />
  
  ## Changes
  - Add safe helper to insert element ranges in the textarea.
  - Extend command‑with‑args pipeline to carry text elements and reuse
  submission prep.
  - Update `/plan` dispatch to switch to plan mode then submit prompt +
  elements.
  - Document new composer behavior and add tests.
  
  ## Notes
  - `/plan` is blocked during active tasks (same as `/review`).
  - Slash‑command elementization recognizes built‑ins and `/prompts:`
  custom commands only.
  
  ## Codex author
  `codex fork 019c16d3-4520-7bb0-9b9d-48720d40a8ab`

  Charley Cunningham · 2026-02-02 09:53:29 -08:00
  3392c5af24
• feat: add MCP protocol types and rmcp adapters (#10356)

  Currently, types from our custom `mcp-types` crate are part of some of
  our APIs:
  
  
  https://github.com/openai/codex/blob/03fcd12e77fedf4fa327af27e2e476e1ebc5f651/codex-rs/app-server-protocol/src/protocol/v2.rs#L43-L46
  
  To eliminate this crate in #10349 by switching to `rmcp`, we need our
  own wrappers for the `rmcp` types that we can use in our API, which is
  what this PR does.
  
  Note this PR introduces the new API types, but we do not make use of
  them until #10349.
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10356).
  * #10357
  * #10349
  * __->__ #10356

  Michael Bolin · 2026-02-02 08:41:02 -08:00
  d1e71cd202
• fix: Rfc3339 casting (#10386)
  jif-oai · 2026-02-02 13:33:28 +00:00
  4f1cfaf892
• fix: thread listing (#10383)
  jif-oai · 2026-02-02 12:52:49 +00:00
  e9a774e7ae