169 Commits

• feat: introduce ExternalSandbox policy (#8290)

  ## Description
  
  Introduced `ExternalSandbox` policy to cover use case when sandbox
  defined by outside environment, effectively it translates to
  `SandboxMode#DangerFullAccess` for file system (since sandbox configured
  on container level) and configurable `network_access` (either Restricted
  or Enabled by outside environment).
  
  as example you can configure `ExternalSandbox` policy as part of
  `sendUserTurn` v1 app_server API:
  
  ```
   {
              "conversationId": <id>,
              "cwd": <cwd>,
              "approvalPolicy": "never",
              "sandboxPolicy": {
                    "type": ""external-sandbox",
                    "network_access": "enabled"/"restricted"
              },
              "model": <model>,
              "effort": <effort>,
              ....
          }
  ```

  Anton Panasenko · 2025-12-18 17:02:03 -08:00
  3429de21b3
• Support skills shortDescription. (#8278)

  Allow SKILL.md to specify a more human-readable short description as
  skill metadata.

  xl-openai · 2025-12-18 23:13:18 +00:00
  358a5baba0
• feat(app-server): add v2 deprecation notice (#8285)

  Add a v2 event for deprecation notices so we can get rid of
  `codex/event/deprecation_notice`.

  Owen Lin · 2025-12-18 21:45:36 +00:00
  d7ae342ff4
• feat: migrate to new constraint-based loading strategy (#8251)

  This is a significant change to how layers of configuration are applied.
  In particular, the `ConfigLayerStack` now has two important fields:
  
  - `layers: Vec<ConfigLayerEntry>`
  - `requirements: ConfigRequirements`
  
  We merge `TomlValue`s across the layers, but they are subject to
  `ConfigRequirements` before creating a `Config`.
  
  How I would review this PR:
  
  - start with `codex-rs/app-server-protocol/src/protocol/v2.rs` and note
  the new variants added to the `ConfigLayerSource` enum:
  `LegacyManagedConfigTomlFromFile` and `LegacyManagedConfigTomlFromMdm`
  - note that `ConfigLayerSource` now has a `precedence()` method and
  implements `PartialOrd`
  - `codex-rs/core/src/config_loader/layer_io.rs` is responsible for
  loading "admin" preferences from `/etc/codex/managed_config.toml` and
  MDM. Because `/etc/codex/managed_config.toml` is now deprecated in favor
  of `/etc/codex/requirements.toml` and `/etc/codex/config.toml`, we now
  include some extra information on the `LoadedConfigLayers` returned in
  `layer_io.rs`.
  - `codex-rs/core/src/config_loader/mod.rs` has major changes to
  `load_config_layers_state()`, which is what produces `ConfigLayerStack`.
  The docstring has the new specification and describes the various layers
  that will be loaded and the precedence order.
  - It uses the information from `LoaderOverrides` "twice," both in the
  spirit of legacy support:
  - We use one instances to derive an instance of `ConfigRequirements`.
  Currently, the only field in `managed_config.toml` that contributes to
  `ConfigRequirements` is `approval_policy`. This PR introduces
  `Constrained::allow_only()` to support this.
  - We use a clone of `LoaderOverrides` to derive
  `ConfigLayerSource::LegacyManagedConfigTomlFromFile` and
  `ConfigLayerSource::LegacyManagedConfigTomlFromMdm` layers, as
  appropriate. As before, this ends up being a "best effort" at enterprise
  controls, but is enforcement is not guaranteed like it is for
  `ConfigRequirements`.
  - Now we only create a "user" layer if `$CODEX_HOME/config.toml` exists.
  (Previously, a user layer was always created for `ConfigLayerStack`.)
  - Similarly, we only add a "session flags" layer if there are CLI
  overrides.
  - `config_loader/state.rs` contains the updated implementation for
  `ConfigLayerStack`. Note the public API is largely the same as before,
  but the implementation is quite different. We leverage the fact that
  `ConfigLayerSource` is now `PartialOrd` to ensure layers are in the
  correct order.
  - A `Config` constructed via `ConfigBuilder.build()` will use
  `load_config_layers_state()` to create the `ConfigLayerStack` and use
  the associated `ConfigRequirements` when constructing the `Config`
  object.
  - That said, a `Config` constructed via
  `Config::load_from_base_config_with_overrides()` does _not_ yet use
  `ConfigBuilder`, so it creates a `ConfigRequirements::default()` instead
  of loading a proper `ConfigRequirements`. I will fix this in a
  subsequent PR.
  
  Then the following files are mostly test changes:
  
  ```
  codex-rs/app-server/tests/suite/v2/config_rpc.rs
  codex-rs/core/src/config/service.rs
  codex-rs/core/src/config_loader/tests.rs
  ```
  
  Again, because we do not always include "user" and "session flags"
  layers when the contents are empty, `ConfigLayerStack` sometimes has
  fewer layers than before (and the precedence order changed slightly),
  which is the main reason integration tests changed.

  Michael Bolin · 2025-12-18 10:06:05 -08:00
  b903285746
• caribou (#8265)

  Welcome caribou
  
  <img width="1536" height="1024" alt="image"
  src="https://github.com/user-attachments/assets/2a67b21f-40cf-4518-aee4-691af331ab50"
  />

  Ahmed Ibrahim · 2025-12-18 08:58:44 -08:00
  f084e5264b
• chores: clean picker (#8232)

  # 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 · 2025-12-18 08:41:34 -08:00
  374d591311
• Support SYSTEM skills. (#8220)

  1. Remove PUBLIC skills and introduce SYSTEM skills embedded in the
  binary and installed into $CODEX_HOME/skills/.system at startup.
  2. Skills are now always enabled (feature flag removed).
  3. Update skills/list to accept forceReload and plumb it through (not
  used by clients yet).

  xl-openai · 2025-12-17 18:48:28 -08:00
  da3869eeb6
• chore: cleanup Config instantiation codepaths (#8226)

  This PR does various types of cleanup before I can proceed with more
  ambitious changes to config loading.
  
  First, I noticed duplicated code across these two methods:
  
  
  https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L314-L324
  
  
  https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L334-L344
  
  This has now been consolidated in
  `load_config_as_toml_with_cli_overrides()`.
  
  Further, I noticed that `Config::load_with_cli_overrides()` took two
  similar arguments:
  
  
  https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L308-L311
  
  The difference between `cli_overrides` and `overrides` was not
  immediately obvious to me. At first glance, it appears that one should
  be able to be expressed in terms of the other, but it turns out that
  some fields of `ConfigOverrides` (such as `cwd` and
  `codex_linux_sandbox_exe`) are, by design, not configurable via a
  `.toml` file or a command-line `--config` flag.
  
  That said, I discovered that many callers of
  `Config::load_with_cli_overrides()` were passing
  `ConfigOverrides::default()` for `overrides`, so I created two separate
  methods:
  
  - `Config::load_with_cli_overrides(cli_overrides: Vec<(String,
  TomlValue)>)`
  - `Config::load_with_cli_overrides_and_harness_overrides(cli_overrides:
  Vec<(String, TomlValue)>, harness_overrides: ConfigOverrides)`
  
  The latter has a long name, as it is _not_ what should be used in the
  common case, so the extra typing is designed to draw attention to this
  fact. I tried to update the existing callsites to use the shorter name,
  where possible.
  
  Further, in the cases where `ConfigOverrides` is used, usually only a
  limited subset of fields are actually set, so I updated the declarations
  to leverage `..Default::default()` where possible.

  Michael Bolin · 2025-12-17 18:01:17 -08:00
  a8797019a1
• feat: model picker (#8209)

  # 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 · 2025-12-17 16:12:35 -08:00
  774bd9e432
• Load models from static file (#8153)

  - Load models from static file as a fallback
  - Make API users use this file directly
  - Add tests to make sure updates to the file always serialize

  Ahmed Ibrahim · 2025-12-17 14:34:13 -08:00
  927a6acbea
• feat: make list_models non-blocking (#8198)

  ### Summary
  * Make `app_server.list_models` to be non-blocking and consumers (i.e.
  extension) can manage the flow themselves.
  * Force config to use remote models and therefore fetch codex-auto model
  list.

  Shijie Rao · 2025-12-17 12:13:16 -08:00
  df35189366
• chore: update listMcpServerStatus to be non-blocking (#8151)

  ### Summary
  * Update `listMcpServerStatus` to be non-blocking by wrapping it with
  tokio:spawn.

  Shijie Rao · 2025-12-17 10:11:02 -08:00
  3702793882
• feat: change ConfigLayerName into a disjoint union rather than a simple enum (#8095)

  This attempts to tighten up the types related to "config layers."
  Currently, `ConfigLayerEntry` is defined as follows:
  
  
  https://github.com/openai/codex/blob/bef36f4ae765f471d7cd69372fcf1b92c8f0367a/codex-rs/core/src/config_loader/state.rs#L19-L25
  
  but the `source` field is a bit of a lie, as:
  
  - for `ConfigLayerName::Mdm`, it is
  `"com.openai.codex/config_toml_base64"`
  - for `ConfigLayerName::SessionFlags`, it is `"--config"`
  - for `ConfigLayerName::User`, it is `"config.toml"` (just the file
  name, not the path to the `config.toml` on disk that was read)
  - for `ConfigLayerName::System`, it seems like it is usually
  `/etc/codex/managed_config.toml` in practice, though on Windows, it is
  `%CODEX_HOME%/managed_config.toml`:
  
  
  https://github.com/openai/codex/blob/bef36f4ae765f471d7cd69372fcf1b92c8f0367a/codex-rs/core/src/config_loader/layer_io.rs#L84-L101
  
  All that is to say, in three out of the four `ConfigLayerName`, `source`
  is a `PathBuf` that is not an absolute path (or even a true path).
  
  This PR tries to uplevel things by eliminating `source` from
  `ConfigLayerEntry` and turning `ConfigLayerName` into a disjoint union
  named `ConfigLayerSource` that has the appropriate metadata for each
  variant, favoring the use of `AbsolutePathBuf` where appropriate:
  
  ```rust
  pub enum ConfigLayerSource {
      /// Managed preferences layer delivered by MDM (macOS only).
      #[serde(rename_all = "camelCase")]
      #[ts(rename_all = "camelCase")]
      Mdm { domain: String, key: String },
      /// Managed config layer from a file (usually `managed_config.toml`).
      #[serde(rename_all = "camelCase")]
      #[ts(rename_all = "camelCase")]
      System { file: AbsolutePathBuf },
      /// Session-layer overrides supplied via `-c`/`--config`.
      SessionFlags,
      /// User config layer from a file (usually `config.toml`).
      #[serde(rename_all = "camelCase")]
      #[ts(rename_all = "camelCase")]
      User { file: AbsolutePathBuf },
  }
  ```

  Michael Bolin · 2025-12-17 08:13:59 -08:00
  de3fa03e1c
• [app-server] add new RawResponseItem v2 event (#8152)

  ``codex/event/raw_response_item` (v1) -> `rawResponseItem/completed`
  (v1).
  
  test client log:
  ````
  < {
  <   "method": "codex/event/raw_response_item",
  <   "params": {
  <     "conversationId": "019b29f7-b089-7140-a535-3fe681562c15",
  <     "id": "0",
  <     "msg": {
  <       "item": {
  <         "arguments": "{\"command\":\"sed -n '1,160p' Cargo.toml\",\"workdir\":\"/Users/celia/code/codex/codex-rs\"}",
  <         "call_id": "call_DrqbdB2jPxezPWc19YVEEt3h",
  <         "name": "shell_command",
  <         "type": "function_call"
  <       },
  <       "type": "raw_response_item"
  <     }
  <   }
  < }
  < {
  <   "method": "rawResponseItem/completed",
  <   "params": {
  <     "item": {
  <       "arguments": "{\"command\":\"sed -n '1,160p' Cargo.toml\",\"workdir\":\"/Users/celia/code/codex/codex-rs\"}",
  <       "call_id": "call_DrqbdB2jPxezPWc19YVEEt3h",
  <       "name": "shell_command",
  <       "type": "function_call"
  <     },
  <     "threadId": "019b29f7-b089-7140-a535-3fe681562c15",
  <     "turnId": "0"
  <   }
  < }
  ```

  Celia Chen · 2025-12-17 02:19:30 +00:00
  70913effc3
• chore: update listMcpServers to listMcpServerStatus (#8114)

  ### Summary
  * rename app server `listMcpServers` to `listMcpServerStatuses`.

  Shijie Rao · 2025-12-16 15:28:45 -08:00
  600d01b33a
• chore(app-server): remove stubbed thread/compact API (#8086)

  We want to rely on server-side auto-compaction instead of having the
  client trigger context compaction manually. This API was stubbed as a
  placeholder and never implemented.

  Owen Lin · 2025-12-16 01:11:01 +00:00
  412dd37956
• better name for windows sandbox features (#8077)

  `--enable enable...` is a bad look

  iceweasel-oai · 2025-12-15 10:15:40 -08:00
  b4635ccc07
• 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
• [codex] add otel tracing (#7844)
  Anton Panasenko · 2025-12-12 17:07:17 -08:00
  ad7b9d63c3
• fix: added test helpers for platform-specific paths (#7954)

  This addresses post-merge feedback from
  https://github.com/openai/codex/pull/7856.

  Michael Bolin · 2025-12-13 00:14:12 +00:00
  b1905d3754
• fix: introduce AbsolutePathBuf as part of sandbox config (#7856)

  Changes the `writable_roots` field of the `WorkspaceWrite` variant of
  the `SandboxPolicy` enum from `Vec<PathBuf>` to `Vec<AbsolutePathBuf>`.
  This is helpful because now callers can be sure the value is an absolute
  path rather than a relative one. (Though when using an absolute path in
  a Seatbelt config policy, we still have to _canonicalize_ it first.)
  
  Because `writable_roots` can be read from a config file, it is important
  that we are able to resolve relative paths properly using the parent
  folder of the config file as the base path.

  Michael Bolin · 2025-12-12 15:25:22 -08:00
  642b7566df
• feat: clean config loading and config api (#7924)

  Check the README of the `config_loader` for details

  jif-oai · 2025-12-12 12:01:24 -08:00
  92098d36e8
• chores: models manager (#7937)
  Ahmed Ibrahim · 2025-12-12 18:59:39 +00:00
  149696d959
• feat: use latest disk value for mcp servers status (#7907)

  ### Summary
  Instead of stale in memory config value for listing mcp server statuses,
  we pull the latest disk value.

  Shijie Rao · 2025-12-11 18:56:55 -08:00
  163a7e317e
• Fix misleading 'maximize' high effort description on xhigh models (#7874)

  ## Notes
  - switch misleading High reasoning effort descriptions from "Maximizes
  reasoning depth" to "Higher reasoning depth" across models with xhigh
  reasoning. Affects GPT-5.1 Codex Max and Robin
  - refresh model list fixtures and chatwidget snapshots to match new copy
  
  ## Revision
  - R2: Change 'Higher' to 'Greater'
  - R1: Initial
  
  ## Testing
  
  <img width="583" height="142" alt="image"
  src="https://github.com/user-attachments/assets/1ddd8971-7841-4cb3-b9ba-91095a7435d2"
  />
  
  <img width="838" height="142" alt="image"
  src="https://github.com/user-attachments/assets/79aaedbf-7624-4695-b822-93dea7d6a800"
  />

  Victor Vannara · 2025-12-11 16:38:52 -08:00
  95f7d37ec6
• Update Model Info (#7853)
  Ahmed Ibrahim · 2025-12-11 14:06:07 -08:00
  b7fa7ca8e9
• feat: robin (#7882)

  <img width="554" height="554" alt="image"
  src="https://github.com/user-attachments/assets/aa86f4c8-fb34-4b0e-8b03-3a9980dfdb08"
  />
  
  ---------
  
  Co-authored-by: Dylan Hurd <dylan.hurd@openai.com>

  Ahmed Ibrahim · 2025-12-11 09:04:08 -08:00
  238ce7dfad
• feat: add shell snapshot for shell command (#7786)
  jif-oai · 2025-12-11 13:46:43 +00:00
  29381ba5c2
• fix(stuff) (#7855)

  Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>

  Dylan Hurd · 2025-12-11 00:39:47 -08:00
  dca7f4cb60
• [app-server] Update readme to include mcp endpoints (#7850)

  n/a

  Celia Chen · 2025-12-11 01:08:31 +00:00
  ce19dbbb22
• [app-server] make app server not throw error when login id is not found (#7831)

  Our previous design of cancellation endpoint is not idempotent, which
  caused a bunch of flaky tests. Make app server just returned a not_found
  status instead of throwing an error if the login id is not found. Keep
  V1 endpoint behavior the same.

  Celia Chen · 2025-12-10 16:19:40 -08:00
  7cabe54fc7
• fix: thread/list returning fewer than the requested amount due to filtering CXA-293 (#7509)

  This caused some conversations to not appear when they otherwise should.
  
  Prior to this change, `thread/list`/`list_conversations_common` would:
  - Fetch N conversations from `RolloutRecorder::list_conversations`
  - Then it would filter those (like by the provided `model_providers`)
  - This would make it potentially return less than N items.
  
  With this change:
  - `list_conversations_common` now continues fetching more conversations
  from `RolloutRecorder::list_conversations` until it "fills up" the
  `requested_page_size`.
  - Ultimately this means that clients can rely on getting eg 20
  conversations if they request 20 conversations.

  Javi · 2025-12-10 23:06:32 +00:00
  e2559ab28d
• [app-server-protocol] Add types for config (#7658)

  Currently the config returned by `config/read` in untyped. Add types so
  it's easier for client to parse the config. Since currently configs are
  all defined in snake case we'll keep that instead of using camel case
  like the rest of V2.
  
  Sample output by testing using the app server test client:
  ```
  {
  <   "id": "f28449f4-b015-459b-b07b-eef06980165d",
  <   "result": {
  <     "config": {
  <       "approvalPolicy": null,
  <       "compactPrompt": null,
  <       "developerInstructions": null,
  <       "features": {
  <         "experimental_use_rmcp_client": true
  <       },
  <       "forcedChatgptWorkspaceId": null,
  <       "forcedLoginMethod": null,
  <       "instructions": null,
  <       "model": "gpt-5.1-codex-max",
  <       "modelAutoCompactTokenLimit": null,
  <       "modelContextWindow": null,
  <       "modelProvider": null,
  <       "modelReasoningEffort": null,
  <       "modelReasoningSummary": null,
  <       "modelVerbosity": null,
  <       "model_providers": {
  <         "local": {
  <           "base_url": "http://localhost:8061/api/codex",
  <           "env_http_headers": {
  <             "ChatGPT-Account-ID": "OPENAI_ACCOUNT_ID"
  <           },
  <           "env_key": "CHATGPT_TOKEN_STAGING",
  <           "name": "local",
  <           "wire_api": "responses"
  <         }
  <       },
  <       "model_reasoning_effort": "medium",
  <       "notice": {
  <         "hide_gpt-5.1-codex-max_migration_prompt": true,
  <         "hide_gpt5_1_migration_prompt": true
  <       },
  <       "profile": null,
  <       "profiles": {},
  <       "projects": {
  <         "/Users/celia/code": {
  <           "trust_level": "trusted"
  <         },
  <         "/Users/celia/code/codex": {
  <           "trust_level": "trusted"
  <         },
  <         "/Users/celia/code/openai": {
  <           "trust_level": "trusted"
  <         }
  <       },
  <       "reviewModel": null,
  <       "sandboxMode": null,
  <       "sandboxWorkspaceWrite": null,
  <       "tools": {
  <         "viewImage": null,
  <         "webSearch": null
  <       }
  <     },
  <     "origins": {
  <       "features.experimental_use_rmcp_client": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_providers.local.base_url": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_providers.local.env_http_headers.ChatGPT-Account-ID": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_providers.local.env_key": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_providers.local.name": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_providers.local.wire_api": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "model_reasoning_effort": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "notice.hide_gpt-5.1-codex-max_migration_prompt": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "notice.hide_gpt5_1_migration_prompt": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "projects./Users/celia/code.trust_level": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "projects./Users/celia/code/codex.trust_level": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "projects./Users/celia/code/openai.trust_level": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       },
  <       "tools.web_search": {
  <         "name": "user",
  <         "source": "/Users/celia/.codex/config.toml",
  <         "version": "sha256:a1d8eaedb5d9db5dfdfa69f30fa9df2efec66bb4dd46aa67f149fcc67cd0711c"
  <       }
  <     }
  <   }
  < }
  ```

  Celia Chen · 2025-12-10 21:35:31 +00:00
  bfb4d5710b
• 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
• [app-server] Make sure that config writes preserve comments & order or configs (#7789)

  Make sure that config writes preserve comments and order of configs by
  utilizing the ConfigEditsBuilder in core.
  
  Tested by running a real example and made sure that nothing in the
  config file changes other than the configs to edit.

  Celia Chen · 2025-12-10 19:14:27 +00:00
  8a71f8b634
• Removed experimental "command risk assessment" feature (#7799)

  This experimental feature received lukewarm reception during internal
  testing. Removing from the code base.

  Eric Traut · 2025-12-10 09:48:11 -08:00
  c4af707e09
• 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
• chore: rework unified exec events (#7775)
  jif-oai · 2025-12-10 10:30:38 +00:00
  0ad54982ae
• feat: support mcp in-session login (#7751)

  ### Summary
  * Added `mcpServer/oauthLogin` in app server for supporting in session
  MCP server login
  * Added `McpServerOauthLoginParams` and `McpServerOauthLoginResponse` to
  support above method with response returning the auth URL for consumer
  to open browser or display accordingly.
  * Added `McpServerOauthLoginCompletedNotification` which the app server
  would emit on MCP server login success or failure (i.e. timeout).
  * Refactored rmcp-client oath_login to have the ability on starting a
  auth server which the codex_message_processor uses for in-session auth.

  Shijie Rao · 2025-12-09 17:43:53 -08:00
  893f5261eb
• updating app server types to support execpoilcy amendment (#7747)

  also includes minor refactor merging `ApprovalDecision` with
  `CommandExecutionRequestAcceptSettings`

  zhao-oai · 2025-12-08 13:56:22 -08:00
  0a32acaa2d
• fix: taking plan type from usage endpoint instead of thru auth token (#7610)

  pull plan type from the usage endpoint, persist it in session state /
  tui state, and propagate through rate limit snapshots

  zhao-oai · 2025-12-04 23:34:13 -08:00
  b8eab7ce90
• fix(app-server): add will_retry to ErrorNotification (#7611)

  VSCE renders `codex/event/stream_error` (automatically retried, e.g.
  `"Reconnecting... 1/n"`) and `codex/event/error` (terminal errors)
  differently, so add `will_retry` on ErrorNotification to indicate this.

  Owen Lin · 2025-12-04 21:48:37 +00:00
  e8f6d65899
• fix(app-server): add duration_ms to McpToolCallItem (#7605)

  Seems like a nice field to have, and also VSCE does render this one.

  Owen Lin · 2025-12-04 13:45:07 -08:00
  342c084cc3
• Refactor execpolicy fallback evaluation (#7544)

  ## Refactor of the `execpolicy` crate
  
  To illustrate why we need this refactor, consider an agent attempting to
  run `apple | rm -rf ./`. Suppose `apple` is allowed by `execpolicy`.
  Before this PR, `execpolicy` would consider `apple` and `pear` and only
  render one rule match: `Allow`. We would skip any heuristics checks on
  `rm -rf ./` and immediately approve `apple | rm -rf ./` to run.
  
  To fix this, we now thread a `fallback` evaluation function into
  `execpolicy` that runs when no `execpolicy` rules match a given command.
  In our example, we would run `fallback` on `rm -rf ./` and prevent
  `apple | rm -rf ./` from being run without approval.

  zhao-oai · 2025-12-03 23:39:48 -08:00
  3d35cb4619
• whitelist command prefix integration in core and tui (#7033)

  this PR enables TUI to approve commands and add their prefixes to an
  allowlist:
  <img width="708" height="605" alt="Screenshot 2025-11-21 at 4 18 07 PM"
  src="https://github.com/user-attachments/assets/56a19893-4553-4770-a881-becf79eeda32"
  />
  
  note: we only show the option to whitelist the command when 
  1) command is not multi-part (e.g `git add -A && git commit -m 'hello
  world'`)
  2) command is not already matched by an existing rule

  zhao-oai · 2025-12-03 23:17:02 -08:00
  e925a380dc
• [app-server] make file_path for config optional (#7560)

  When we are writing to config using `config/value/write` or
  `config/batchWrite`, it always require a `config/read` before it right
  now in order to get the correct file path to write to. make this
  optional so we read from the default user config file if this is not
  passed in.

  Celia Chen · 2025-12-04 03:08:18 +00:00
  3e6cd5660c
• Introduce ModelsManager and migrate app-server to use it. (#7552)
  Ahmed Ibrahim · 2025-12-03 17:17:56 -08:00
  00cc00ead8
• [app-server] fix: add thread_id to turn/plan/updated (#7553)

  Realized we're missing this while migrating VSCE.

  Owen Lin · 2025-12-03 15:00:07 -08:00
  231ff19ca2
• 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
• chore: conversation_id -> thread_id in app-server feedback/upload (#7538)

  Use `thread_id: Option<String>` instead of `conversation_id:
  Option<ConversationId>` to be consistent with the rest of app-server v2
  APIs.

  Owen Lin · 2025-12-03 18:47:35 +00:00
  3ef76ff29d