39 Commits

• docs: require insta snapshot coverage for UI changes (#10669)

  Adds an explicit requirement in AGENTS.md that any user-visible UI
  change includes corresponding insta snapshot coverage and that snapshots
  are reviewed/accepted in the PR.
  
  Tests: N/A (docs only)

  Josh McKinney · 2026-02-12 22:47:09 +00:00
  75e79cf09a
• feat(app-server): experimental flag to persist extended history (#11227)

  This PR adds an experimental `persist_extended_history` bool flag to
  app-server thread APIs so rollout logs can retain a richer set of
  EventMsgs for non-lossy Thread > Turn > ThreadItems reconstruction (i.e.
  on `thread/resume`).
  
  ### Motivation
  Today, our rollout recorder only persists a small subset (e.g. user
  message, reasoning, assistant message) of `EventMsg` types, dropping a
  good number (like command exec, file change, etc.) that are important
  for reconstructing full item history for `thread/resume`, `thread/read`,
  and `thread/fork`.
  
  Some clients want to be able to resume a thread without lossiness. This
  lossiness is primarily a UI thing, since what the model sees are
  `ResponseItem` and not `EventMsg`.
  
  ### Approach
  This change introduces an opt-in `persist_full_history` flag to preserve
  those events when you start/resume/fork a thread (defaults to `false`).
  
  This is done by adding an `EventPersistenceMode` to the rollout
  recorder:
  - `Limited` (existing behavior, default)
  - `Extended` (new opt-in behavior)
  
  In `Extended` mode, persist additional `EventMsg` variants needed for
  non-lossy app-server `ThreadItem` reconstruction. We now store the
  following ThreadItems that we didn't before:
  - web search
  - command execution
  - patch/file changes
  - MCP tool calls
  - image view calls
  - collab tool outcomes
  - context compaction
  - review mode enter/exit
  
  For **command executions** in particular, we truncate the output using
  the existing `truncate_text` from core to store an upper bound of 10,000
  bytes, which is also the default value for truncating tool outputs shown
  to the model. This keeps the size of the rollout file and command
  execution items returned over the wire reasonable.
  
  And we also persist `EventMsg::Error` which we can now map back to the
  Turn's status and populates the Turn's error metadata.
  
  #### Updates to EventMsgs
  To truly make `thread/resume` non-lossy, we also needed to persist the
  `status` on `EventMsg::CommandExecutionEndEvent` and
  `EventMsg::PatchApplyEndEvent`. Previously it was not obvious whether a
  command failed or was declined (similar for apply_patch). These
  EventMsgs were never persisted before so I made it a required field.

  Owen Lin · 2026-02-12 19:34:22 +00:00
  efc8d45750
• Try to stop small helper methods (#11203)
  pakrym-oai · 2026-02-09 20:01:30 +00:00
  086d02fb14
• chore(app-server): update AGENTS.md for config + optional collection guidance (#10914)

  Based on recent app-server PRs

  Owen Lin · 2026-02-06 12:45:27 -08:00
  731f0f384a
• 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
• Reject request_user_input outside Plan/Pair (#9955)

  ## Context
  
  Previous work in https://github.com/openai/codex/pull/9560 only rejected
  `request_user_input` in Execute and Custom modes. Since then, additional
  modes
  (e.g., Code) were added, so the guard should be mode-agnostic.
  
  ## What changed
  
  - Switch the handler to an allowlist: only Plan and PairProgramming are
  allowed
  - Return the same error for any other mode (including Code)
  - Add a Code-mode rejection test alongside the existing Execute/Custom
  tests
  
  ## Why
  
  This prevents `request_user_input` from being used in modes where it is
  not
  intended, even as new modes are introduced.

  Charley Cunningham · 2026-01-26 17:12:17 -08:00
  47aa1f3b6a
• chore: tweak AGENTS.md (#9650)

  ## Summary
  Update AGENTS.md to improve testing flow
  
  ## Testing
  - [x] Tested locally, much faster

  Dylan Hurd · 2026-01-21 20:20:45 -08:00
  e520592bcf
• don't ask for approval for just fix (#9586)

  It blocks all my skills from executing because it asks to run just fmt.
  It's quick command that doesn't need approval.
  
  
  <img width="967" height="120" alt="image"
  src="https://github.com/user-attachments/assets/f8e6ca76-a650-49e9-beb2-ce98ba48d310"
  />

  Ahmed Ibrahim · 2026-01-21 04:56:11 +00:00
  ebc88f29f8
• add generated jsonschema for config.toml (#8956)

  ### What
  Add JSON Schema generation for `config.toml`, with checked‑in
  `docs/config.schema.json`. We can move the schema elsewhere if preferred
  (and host it if there's demand).
  
  Add fixture test to prevent drift and `just write-config-schema` to
  regenerate on schema changes.
  
  Generate MCP config schema from `RawMcpServerConfig` instead of
  `McpServerConfig` because that is the runtime type used for
  deserialization.
  
  Populate feature flag values into generated schema so they can be
  autocompleted.
  
  ### Tests
  Added tests + regenerate script to prevent drift. Tested autocompletions
  using generated jsonschema locally with Even Better TOML.
  
  
  
  https://github.com/user-attachments/assets/5aa7cd39-520c-4a63-96fb-63798183d0bc

  sayan-oai · 2026-01-13 10:22:51 -08:00
  40e2405998
• feat: introduce find_resource! macro that works with Cargo or Bazel (#8879)

  To support Bazelification in https://github.com/openai/codex/pull/8875,
  this PR introduces a new `find_resource!` macro that we use in place of
  our existing logic in tests that looks for resources relative to the
  compile-time `CARGO_MANIFEST_DIR` env var.
  
  To make this work, we plan to add the following to all `rust_library()`
  and `rust_test()` Bazel rules in the project:
  
  ```
  rustc_env = {
      "BAZEL_PACKAGE": native.package_name(),
  },
  ```
  
  Our new `find_resource!` macro reads this value via
  `option_env!("BAZEL_PACKAGE")` so that the Bazel package _of the code
  using `find_resource!`_ is injected into the code expanded from the
  macro. (If `find_resource()` were a function, then
  `option_env!("BAZEL_PACKAGE")` would always be
  `codex-rs/utils/cargo-bin`, which is not what we want.)
  
  Note we only consider the `BAZEL_PACKAGE` value when the `RUNFILES_DIR`
  environment variable is set at runtime, indicating that the test is
  being run by Bazel. In this case, we have to concatenate the runtime
  `RUNFILES_DIR` with the compile-time `BAZEL_PACKAGE` value to build the
  path to the resource.
  
  In testing this change, I discovered one funky edge case in
  `codex-rs/exec-server/tests/common/lib.rs` where we have to _normalize_
  (but not canonicalize!) the result from `find_resource!` because the
  path contains a `common/..` component that does not exist on disk when
  the test is run under Bazel, so it must be semantically normalized using
  the [`path-absolutize`](https://crates.io/crates/path-absolutize) crate
  before it is passed to `dotslash fetch`.
  
  Because this new behavior may be non-obvious, this PR also updates
  `AGENTS.md` to make humans/Codex aware that this API is preferred.

  Michael Bolin · 2026-01-07 18:06:08 -08:00
  f6b563ec64
• feat: introduce codex-utils-cargo-bin as an alternative to assert_cmd::Command (#8496)

  This PR introduces a `codex-utils-cargo-bin` utility crate that
  wraps/replaces our use of `assert_cmd::Command` and
  `escargot::CargoBuild`.
  
  As you can infer from the introduction of `buck_project_root()` in this
  PR, I am attempting to make it possible to build Codex under
  [Buck2](https://buck2.build) as well as `cargo`. With Buck2, I hope to
  achieve faster incremental local builds (largely due to Buck2's
  [dice](https://buck2.build/docs/insights_and_knowledge/modern_dice/)
  build strategy, as well as benefits from its local build daemon) as well
  as faster CI builds if we invest in remote execution and caching.
  
  See
  https://buck2.build/docs/getting_started/what_is_buck2/#why-use-buck2-key-advantages
  for more details about the performance advantages of Buck2.
  
  Buck2 enforces stronger requirements in terms of build and test
  isolation. It discourages assumptions about absolute paths (which is key
  to enabling remote execution). Because the `CARGO_BIN_EXE_*` environment
  variables that Cargo provides are absolute paths (which
  `assert_cmd::Command` reads), this is a problem for Buck2, which is why
  we need this `codex-utils-cargo-bin` utility.
  
  My WIP-Buck2 setup sets the `CARGO_BIN_EXE_*` environment variables
  passed to a `rust_test()` build rule as relative paths.
  `codex-utils-cargo-bin` will resolve these values to absolute paths,
  when necessary.
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/8496).
  * #8498
  * __->__ #8496

  Michael Bolin · 2025-12-23 19:29:32 -08:00
  e61bae12e3
• Fixed resume matching to respect case insensitivity when using WSL mount points (#8000)

  This fixes #7995

  Eric Traut · 2025-12-16 16:27:38 -08:00
  42b8f28ee8
• docs: remove blanket ban on unsigned integers (#7957)

  Drop the AGENTS.md rule that forbids unsigned ints. The blanket guidance
  causes unnecessary complexity in cases where values are naturally
  unsigned, leading to extra clamping/conversion code instead of using
  checked or saturating arithmetic where needed.

  Josh McKinney · 2025-12-12 17:01:56 -08:00
  596fcd040f
• 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
• tests: replace mount_sse_once_match with mount_sse_once for SSE mocking (#6640)
  pakrym-oai · 2025-11-13 18:04:05 -08:00
  6c384eb9c6
• Prefer wait_for_event over wait_for_event_with_timeout. (#6346)

  No need to specify the timeout in most cases.

  pakrym-oai · 2025-11-06 16:14:43 -08:00
  f8b30af6dc
• Auto compact at ~90% (#5292)

  Users now hit a window exceeded limit and they usually don't know what
  to do. This starts auto compact at ~90% of the window.

  Ahmed Ibrahim · 2025-10-20 11:29:49 -07:00
  049a61bcfc
• [MCP] Add support for resources (#5239)

  This PR adds support for [MCP
  resources](https://modelcontextprotocol.io/specification/2025-06-18/server/resources)
  by adding three new tools for the model:
  1. `list_resources`
  2. `list_resource_templates`
  3. `read_resource`
  
  These 3 tools correspond to the [three primary MCP resource protocol
  messages](https://modelcontextprotocol.io/specification/2025-06-18/server/resources#protocol-messages).
  
  Example of listing and reading a GitHub resource tempalte
  <img width="2984" height="804" alt="CleanShot 2025-10-15 at 17 31 10"
  src="https://github.com/user-attachments/assets/89b7f215-2e2a-41c5-90dd-b932ac84a585"
  />
  
  `/mcp` with Figma configured
  <img width="2984" height="442" alt="CleanShot 2025-10-15 at 18 29 35"
  src="https://github.com/user-attachments/assets/a7578080-2ed2-4c59-b9b4-d8461f90d8ee"
  />
  
  Fixes #4956

  Gabriel Peal · 2025-10-17 01:05:15 -04:00
  40fba1bb4c
• Simplify request body assertions (#4845)

  We'll have a lot more test like these

  pakrym-oai · 2025-10-07 09:56:39 +01:00
  35a770e871
• chore: subject docs/*.md to Prettier checks (#4645)

  Apparently we were not running our `pnpm run prettier` check in CI, so
  many files that were covered by the existing Prettier check were not
  well-formatted.
  
  This updates CI and formats the files.

  Michael Bolin · 2025-10-03 11:35:48 -07:00
  c32e9cfe86
• [MCP] Add support for MCP Oauth credentials (#4517)

  This PR adds oauth login support to streamable http servers when
  `experimental_use_rmcp_client` is enabled.
  
  This PR is large but represents the minimal amount of work required for
  this to work. To keep this PR smaller, login can only be done with
  `codex mcp login` and `codex mcp logout` but it doesn't appear in `/mcp`
  or `codex mcp list` yet. Fingers crossed that this is the last large MCP
  PR and that subsequent PRs can be smaller.
  
  Under the hood, credentials are stored using platform credential
  managers using the [keyring crate](https://crates.io/crates/keyring).
  When the keyring isn't available, it falls back to storing credentials
  in `CODEX_HOME/.credentials.json` which is consistent with how other
  coding agents handle authentication.
  
  I tested this on macOS, Windows, WSL (ubuntu), and Linux. I wasn't able
  to test the dbus store on linux but did verify that the fallback works.
  
  One quirk is that if you have credentials, during development, every
  build will have its own ad-hoc binary so the keyring won't recognize the
  reader as being the same as the write so it may ask for the user's
  password. I may add an override to disable this or allow
  users/enterprises to opt-out of the keyring storage if it causes issues.
  
  <img width="5064" height="686" alt="CleanShot 2025-09-30 at 19 31 40"
  src="https://github.com/user-attachments/assets/9573f9b4-07f1-4160-83b8-2920db287e2d"
  />
  <img width="745" height="486" alt="image"
  src="https://github.com/user-attachments/assets/9562649b-ea5f-4f22-ace2-d0cb438b143e"
  />

  Gabriel Peal · 2025-10-03 13:43:12 -04:00
  1d17ca1fa3
• AGENTS.md: Add instruction to install missing commands (#3807)

  This change instructs the model to install any missing command. Else
  tokens are wasted when it tries to run
  commands that aren't available multiple times before installing them.

  Abhishek Bhardwaj · 2025-09-17 11:06:59 -07:00
  208089e58e
• syntax-highlight bash lines (#3142)

  i'm not yet convinced i have the best heuristics for what to highlight,
  but this feels like a useful step towards something a bit easier to
  read, esp. when the model is producing large commands.
  
  <img width="669" height="589" alt="Screenshot 2025-09-03 at 8 21 56 PM"
  src="https://github.com/user-attachments/assets/b9cbcc43-80e8-4d41-93c8-daa74b84b331"
  />
  
  also a fairly significant refactor of our line wrapping logic.

  Jeremy Rose · 2025-09-05 14:10:32 +00:00
  d6182becbe
• AGENTS.md: clarify test approvals for codex-rs (#3132)

  Clarifies codex-rs testing approvals in AGENTS.md:
  
  - Allow running project-specific or individual tests without asking.
  - Require asking before running the complete test suite.
  - Keep `just fmt` always allowed without approval.

  Jeremy Rose · 2025-09-04 13:36:12 -07:00
  1c04e1314d
• core: correct sandboxed shell tool description (reads allowed anywhere) (#3069)

  Correct the `shell` tool description for sandboxed runs and add targeted
  tests.
  
  - Fix the WorkspaceWrite description to clearly state that writes
  outside the writable roots require escalated permissions; reads are not
  restricted. The previous wording/formatting could be read as restricting
  reads outside the workspace.
  - Render the writable roots list on its own lines under a newline after
  "writable roots:" for clarity.
  - Show the "Commands that require network access" note only in
  WorkspaceWrite when network is disabled.
  - Add focused tests that call `create_shell_tool_for_sandbox` directly
  and assert the exact description text for WorkspaceWrite, ReadOnly, and
  DangerFullAccess.
  - Update AGENTS.md to note that `just fmt` can be run automatically
  without asking.

  Jeremy Rose · 2025-09-03 10:02:34 -07:00
  97000c6e6d
• prefer ratatui Stylized for constructing lines/spans (#3068)

  no functional change, just simplifying ratatui styling and adding
  guidance in AGENTS.md for future.

  Jeremy Rose · 2025-09-02 23:19:54 +00:00
  578ff09e17
• suggest just fix -p in agents.md (#2881)
  Jeremy Rose · 2025-08-28 22:32:53 -07:00
  7d734bff65
• [chore] Tweak AGENTS.md so agent doesn't always have to test (#2706)
  ae · 2025-08-26 00:27:19 -07:00
  8192cf147e
• Fix typo in AGENTS.md (#2518)

  - Change `examole` to `example`

  wkrettek · 2025-08-22 16:05:39 -07:00
  85099017fd
• tui: tab-completing a command moves the cursor to the end (#2362)

  also tweak agents.md for faster `just fix`

  Jeremy Rose · 2025-08-20 09:57:55 -07:00
  8481eb4c6e
• fix: clean up styles & colors and define in styles.md (#2401)

  New style guide:
  
    # Headers, primary, and secondary text
    
  - **Headers:** Use `bold`. For markdown with various header levels,
  leave in the `#` signs.
    - **Primary text:** Default.
    - **Secondary text:** Use `dim`.
    
    # Foreground colors
    
  - **Default:** Most of the time, just use the default foreground color.
  `reset` can help get it back.
  - **Selection:** Use ANSI `blue`. (Ed & AE want to make this cyan too,
  but we'll do that in a followup since it's riskier in different themes.)
    - **User input tips and status indicators:** Use ANSI `cyan`.
    - **Success and additions:** Use ANSI `green`.
    - **Errors, failures and deletions:** Use ANSI `red`.
    - **Codex:** Use ANSI `magenta`.
    
    # Avoid
    
  - Avoid custom colors because there's no guarantee that they'll contrast
  well or look good on various terminal color themes.
  - Avoid ANSI `black`, `white`, `yellow` as foreground colors because the
  terminal theme will do a better job. (Use `reset` if you need to in
  order to get those.) The exception is if you need contrast rendering
  over a manually colored background.
    
    (There are some rules to try to catch this in `clippy.toml`.)
  
  # Testing
  
  Tested in a variety of light and dark color themes in Terminal, iTerm2, and Ghostty.

  ae · 2025-08-18 08:26:29 -07:00
  5bce369c4d
• color the status letter in apply patch summary (#2337)

  <img width="440" height="77" alt="Screenshot 2025-08-14 at 8 30 30 PM"
  src="https://github.com/user-attachments/assets/c6169a3a-2e98-4ace-b7ee-918cf4368b7a"
  />

  Jeremy Rose · 2025-08-15 20:25:48 +00:00
  1ad8ae2579
• tui: align diff display by always showing sign char and keeping fixed gutter (#2353)

  diff lines without a sign char were misaligned.

  Jeremy Rose · 2025-08-15 09:32:45 -07:00
  45d6c74682
• AGENTS.md more strongly suggests running targeted tests first (#2306)
  Jeremy Rose · 2025-08-15 00:51:32 +00:00
  8bdb4521c9
• [1/3] Parse exec commands and format them more nicely in the UI (#2095)

  # Note for reviewers
  The bulk of this PR is in in the new file, `parse_command.rs`. This file
  is designed to be written TDD and implemented with Codex. Do not worry
  about reviewing the code, just review the unit tests (if you want). If
  any cases are missing, we'll add more tests and have Codex fix them.
  
  I think the best approach will be to land and iterate. I have some
  follow-ups I want to do after this lands. The next PR after this will
  let us merge (and dedupe) multiple sequential cells of the same such as
  multiple read commands. The deduping will also be important because the
  model often reads the same file multiple times in a row in chunks
  
  ===
  
  This PR formats common commands like reading, formatting, testing, etc
  more nicely:
  
  It tries to extract things like file names, tests and falls back to the
  cmd if it doesn't. It also only shows stdout/err if the command failed.
  
  <img width="770" height="238" alt="CleanShot 2025-08-09 at 16 05 15"
  src="https://github.com/user-attachments/assets/0ead179a-8910-486b-aa3d-7d26264d751e"
  />
  <img width="348" height="158" alt="CleanShot 2025-08-09 at 16 05 32"
  src="https://github.com/user-attachments/assets/4302681b-5e87-4ff3-85b4-0252c6c485a9"
  />
  <img width="834" height="324" alt="CleanShot 2025-08-09 at 16 05 56 2"
  src="https://github.com/user-attachments/assets/09fb3517-7bd6-40f6-a126-4172106b700f"
  />
  
  Part 2: https://github.com/openai/codex/pull/2097
  Part 3: https://github.com/openai/codex/pull/2110

  Gabriel Peal · 2025-08-11 14:26:15 -04:00
  7f6408720b
• feat: make .git read-only within a writable root when using Seatbelt (#1765)

  To make `--full-auto` safer, this PR updates the Seatbelt policy so that
  a `SandboxPolicy` with a `writable_root` that contains a `.git/`
  _directory_ will make `.git/` _read-only_ (though as a follow-up, we
  should also consider the case where `.git` is a _file_ with a `gitdir:
  /path/to/actual/repo/.git` entry that should also be protected).
  
  The two major changes in this PR:
  
  - Updating `SandboxPolicy::get_writable_roots_with_cwd()` to return a
  `Vec<WritableRoot>` instead of a `Vec<PathBuf>` where a `WritableRoot`
  can specify a list of read-only subpaths.
  - Updating `create_seatbelt_command_args()` to honor the read-only
  subpaths in `WritableRoot`.
  
  The logic to update the policy is a fairly straightforward update to
  `create_seatbelt_command_args()`, but perhaps the more interesting part
  of this PR is the introduction of an integration test in
  `tests/sandbox.rs`. Leveraging the new API in #1785, we test
  `SandboxPolicy` under various conditions, including ones where `$TMPDIR`
  is not readable, which is critical for verifying the new behavior.
  
  To ensure that Codex can run its own tests, e.g.:
  
  ```
  just codex debug seatbelt --full-auto -- cargo test if_git_repo_is_writable_root_then_dot_git_folder_is_read_only
  ```
  
  I had to introduce the use of `CODEX_SANDBOX=sandbox`, which is
  comparable to how `CODEX_SANDBOX_NETWORK_DISABLED=1` was already being
  used.
  
  Adding a comparable change for Landlock will be done in a subsequent PR.

  Michael Bolin · 2025-08-01 16:11:24 -07:00
  80555d4ff2
• chore: rename toolchain file (#1604)

  Rename toolchain file so older versions of cargo can pick it up.

  pakrym-oai · 2025-07-17 15:36:15 -07:00
  327e2254f6
• chore: auto format code on save and add more details to AGENTS.md (#1582)

  Adds a default vscode config with generally applicable settings.
  Adds more entrypoints to justfile both  for environment setup and to help
  agents better verify changes.

  pakrym-oai · 2025-07-17 11:40:00 -07:00
  6949329a7f
• feat: add support for AGENTS.md in Rust CLI (#885)

  The TypeScript CLI already has support for including the contents of
  `AGENTS.md` in the instructions sent with the first turn of a
  conversation. This PR brings this functionality to the Rust CLI.
  
  To be considered, `AGENTS.md` must be in the `cwd` of the session, or in
  one of the parent folders up to a Git/filesystem root (whichever is
  encountered first).
  
  By default, a maximum of 32 KiB of `AGENTS.md` will be included, though
  this is configurable using the new-in-this-PR `project_doc_max_bytes`
  option in `config.toml`.

  Michael Bolin · 2025-05-10 17:52:59 -07:00
  2b122da087