Commit Graph
54 Commits
Author SHA1 Message Date
Ahmed Ibrahim 7e33ac7eb6 clean models manager (#9168)
Have only the following Methods:
- `list_models`: getting current available models
- `try_list_models`: sync version no refresh for tui use
- `get_default_model`: get the default model (should be tightened to
core and received on session configuration)
- `get_model_info`: get `ModelInfo` for a specific model (should be
tightened to core but used in tests)
- `refresh_if_new_etag`: trigger refresh on different etags

Also move the cache to its own struct
2026-01-13 16:55:33 -08:00
Ahmed Ibrahim 87f7226cca Assemble sandbox/approval/network prompts dynamically (#8961)
- Add a single builder for developer permissions messaging that accepts
SandboxPolicy and approval policy. This builder now drives the developer
“permissions” message that’s injected at session start and any time
sandbox/approval settings change.
- Trim EnvironmentContext to only include cwd, writable roots, and
shell; removed sandbox/approval/network duplication and adjusted XML
serialization and tests accordingly.

Follow-up: adding a config value to replace the developer permissions
message for custom sandboxes.
2026-01-12 23:12:59 +00:00
jif-oai 1aed01e99f renaming: task to turn (#8963) 2026-01-09 17:31:17 +00:00
Michael Bolin 59d6937550 fix: reduce duplicate include_str!() calls (#8914) 2026-01-08 17:20:41 +00:00
Michael Bolin 7520d8ba58 fix: leverage find_resource! macro in load_sse_fixture_with_id (#8888)
This helps prepare us for Bazel builds:
https://github.com/openai/codex/pull/8875.
2026-01-08 09:34:05 -05:00
Ahmed Ibrahim 9179c9deac 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`
2026-01-07 10:35:09 -08:00
jif-oai 116059c3a0 chore: unify conversation with thread name (#8830)
Done and verified by Codex + refactor feature of RustRover
2026-01-07 17:04:53 +00:00
Anton Panasenko 807f8a43c2 feat: expose outputSchema to user_turn/turn_start app_server API (#8377)
What changed
- Added `outputSchema` support to the app-server APIs, mirroring `codex
exec --output-schema` behavior.
- V1 `sendUserTurn` now accepts `outputSchema` and constrains the final
assistant message for that turn.
- V2 `turn/start` now accepts `outputSchema` and constrains the final
assistant message for that turn (explicitly per-turn only).

Core behavior
- `Op::UserTurn` already supported `final_output_json_schema`; now V1
`sendUserTurn` forwards `outputSchema` into that field.
- `Op::UserInput` now carries `final_output_json_schema` for per-turn
settings updates; core maps it into
`SessionSettingsUpdate.final_output_json_schema` so it applies to the
created turn context.
- V2 `turn/start` does NOT persist the schema via `OverrideTurnContext`
(it’s applied only for the current turn). Other overrides
(cwd/model/etc) keep their existing persistent behavior.

API / docs
- `codex-rs/app-server-protocol/src/protocol/v1.rs`: add `output_schema:
Option<serde_json::Value>` to `SendUserTurnParams` (serialized as
`outputSchema`).
- `codex-rs/app-server-protocol/src/protocol/v2.rs`: add `output_schema:
Option<JsonValue>` to `TurnStartParams` (serialized as `outputSchema`).
- `codex-rs/app-server/README.md`: document `outputSchema` for
`turn/start` and clarify it applies only to the current turn.
- `codex-rs/docs/codex_mcp_interface.md`: document `outputSchema` for v1
`sendUserTurn` and v2 `turn/start`.

Tests added/updated
- New app-server integration tests asserting `outputSchema` is forwarded
into outbound `/responses` requests as `text.format`:
  - `codex-rs/app-server/tests/suite/output_schema.rs`
  - `codex-rs/app-server/tests/suite/v2/output_schema.rs`
- Added per-turn semantics tests (schema does not leak to the next
turn):
  - `send_user_turn_output_schema_is_per_turn_v1`
  - `turn_start_output_schema_is_per_turn_v2`
- Added protocol wire-compat tests for the merged op:
  - serialize omits `final_output_json_schema` when `None`
  - deserialize works when field is missing
  - serialize includes `final_output_json_schema` when `Some(schema)`

Call site updates (high level)
- Updated all `Op::UserInput { .. }` constructions to include
`final_output_json_schema`:
  - `codex-rs/app-server/src/codex_message_processor.rs`
  - `codex-rs/core/src/codex_delegate.rs`
  - `codex-rs/mcp-server/src/codex_tool_runner.rs`
  - `codex-rs/tui/src/chatwidget.rs`
  - `codex-rs/tui2/src/chatwidget.rs`
  - plus impacted core tests.

Validation
- `just fmt`
- `cargo test -p codex-core`
- `cargo test -p codex-app-server`
- `cargo test -p codex-mcp-server`
- `cargo test -p codex-tui`
- `cargo test -p codex-tui2`
- `cargo test -p codex-protocol`
- `cargo clippy --all-features --tests --profile dev --fix -- -D
warnings`
2026-01-05 10:27:00 -08:00
Michael Bolin dc61fc5f50 feat: support allowed_sandbox_modes in requirements.toml (#8298)
This adds support for `allowed_sandbox_modes` in `requirements.toml` and
provides legacy support for constraining sandbox modes in
`managed_config.toml`. This is converted to `Constrained<SandboxPolicy>`
in `ConfigRequirements` and applied to `Config` such that constraints
are enforced throughout the harness.

Note that, because `managed_config.toml` is deprecated, we do not add
support for the new `external-sandbox` variant recently introduced in
https://github.com/openai/codex/pull/8290. As noted, that variant is not
supported in `config.toml` today, but can be configured programmatically
via app server.
2025-12-19 21:09:20 +00:00
xl-openai da3869eeb6 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).
2025-12-17 18:48:28 -08:00
Ahmed Ibrahim 927a6acbea 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
2025-12-17 14:34:13 -08:00
gt-oai 9352c6b235 feat: Constrain values for approval_policy (#7778)
Constrain `approval_policy` through new `admin_policy` config.

This PR will:
1. Add a `admin_policy` section to config, with a single field (for now)
`allowed_approval_policies`. This list constrains the set of
user-settable `approval_policy`s.
2. Introduce a new `Constrained<T>` type, which combines a current value
and a validator function. The validator function ensures disallowed
values are not set.
3. Change the type of `approval_policy` on `Config` and
`SessionConfiguration` from `AskForApproval` to
`Constrained<AskForApproval>`. The validator function is set by the
values passed into `allowed_approval_policies`.
4. `GenericDisplayRow`: add a `disabled_reason: Option<String>`. When
set, it disables selection of the value and indicates as such in the
menu. This also makes it unselectable with arrow keys or numbers. This
is used in the `/approvals` menu.

Follow ups are:
1. Do the same thing to `sandbox_policy`.
2. Propagate the allowed set of values through app-server for the
extension (though already this should prevent app-server from setting
this values, it's just that we want to disable UI elements that are
unsettable).

Happy to split this PR up if you prefer, into the logical numbered areas
above. Especially if there are parts we want to gavel on separately
(e.g. admin_policy).

Disabled full access:
<img width="1680" height="380" alt="image"
src="https://github.com/user-attachments/assets/1fb61c8c-1fcb-4dc4-8355-2293edb52ba0"
/>

Disabled `--yolo` on startup:
<img width="749" height="76" alt="image"
src="https://github.com/user-attachments/assets/0a1211a0-6eb1-40d6-a1d7-439c41e94ddb"
/>

CODEX-4087
2025-12-17 16:19:27 +00:00
Michael Bolin 642b7566df 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.
2025-12-12 15:25:22 -08:00
Ahmed Ibrahim cb9a189857 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
2025-12-10 11:19:00 -08:00
Ahmed Ibrahim d08efb1743 Wire with_remote_overrides to construct model families (#7621)
- This PR wires `with_remote_overrides` and make the
`construct_model_families` an async function
- Moves getting model family a level above to keep the function `sync`
- Updates the tests to local, offline, and `sync` helper for model
families
2025-12-05 10:40:15 -08:00
Ahmed Ibrahim 9b2055586d remove model_family from `config (#7571)
- Remove `model_family` from `config`
- Make sure to still override config elements related to `model_family`
like supporting reasoning
2025-12-04 11:57:58 -08:00
Ahmed Ibrahim cee37a32b2 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.
2025-12-03 18:49:47 -08:00
Ahmed Ibrahim 71504325d3 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
2025-12-03 20:30:43 +00:00
pakrym-oai 30ca89424c Always fallback to real shell (#6953)
Either cmd.exe or `/bin/sh`.
2025-11-20 10:58:46 -08:00
Dylan Hurd 15b5eb30ed fix(core) Support changing /approvals before conversation (#6836)
## Summary
Setting `/approvals` before the start of a conversation was not updating
the environment_context for a conversation. Not sure exactly when this
problem was introduced, but this should reduce model confusion
dramatically.

## Testing
- [x] Added unit test to reproduce bug, confirmed fix with update
- [x] Tested locally
2025-11-19 11:32:48 +00:00
pakrym-oai ee0484a98c 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.
2025-11-18 23:38:43 -08:00
Ahmed Ibrahim 793063070b fix: typos in model picker (#6859)
# 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.
2025-11-19 06:29:02 +00:00
Dylan Hurd 29ca89c414 chore(config) enable shell_command (#6843)
## Summary
Enables shell_command as default for `gpt-5*` and `codex-*` models.

## Testing
- [x] Updated unit tests
2025-11-18 12:46:02 -08:00
Ahmed Ibrahim ddcc60a085 Update defaults to gpt-5.1 (#6652)
## Summary
- update documentation, example configs, and automation defaults to
reference gpt-5.1 / gpt-5.1-codex
- bump the CLI and core configuration defaults, model presets, and error
messaging to the new models while keeping the model-family/tool coverage
for legacy slugs
- refresh tests, fixtures, and TUI snapshots so they expect the upgraded
defaults

## Testing
- `cargo test -p codex-core
config::tests::test_precedence_fixture_with_gpt5_profile`


------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6916c5b3c2b08321ace04ee38604fc6b)
2025-11-17 17:40:11 -08:00
pakrym-oai 6c384eb9c6 tests: replace mount_sse_once_match with mount_sse_once for SSE mocking (#6640) 2025-11-13 18:04:05 -08:00
pakrym-oai 041d6ad902 Migrate prompt caching tests to test_codex (#6605)
To hopefully fix the flakiness
2025-11-13 09:19:38 -08:00
Owen Lin 964220ac94 [app-server] feat: thread/resume supports history, path, and overrides (#6483)
This updates `thread/resume` to be at parity with v1's
`ResumeConversationParams`. Turns out history is useful for codex cloud
and path is useful for the VSCode extension. And config overrides are
always useful.
2025-11-12 22:02:43 +00:00
pakrym-oai ec69a4a810 Add gpt-5.1 model definitions (#6551) 2025-11-12 12:44:36 -08:00
pakrym-oai 2371d771cc Update user instruction message format (#6010) 2025-10-30 18:44:02 -07:00
Ahmed Ibrahim a3d3719481 Remove last turn reasoning filtering (#5986) 2025-10-30 23:20:32 +00:00
pakrym-oai 1b8f2543ac Filter out reasoning items from previous turns (#5857)
Reduces request size and prevents 400 errors when switching between API
orgs.

Based on Responses API behavior described in
https://cookbook.openai.com/examples/responses_api/reasoning_items#caching
2025-10-28 11:39:34 -07:00
pakrym-oai 1b10a3a1b2 Enable plan tool by default (#5384)
## Summary
- make the plan tool available by default by removing the feature flag
and always registering the handler
- drop plan-tool CLI and API toggles across the exec, TUI, MCP server,
and app server code paths
- update tests and configs to reflect the always-on plan tool and guard
workspace restriction tests against env leakage

## Testing
Manually tested the extension. 
------
https://chatgpt.com/codex/tasks/task_i_68f67a3ff2d083209562a773f814c1f9
2025-10-21 16:25:05 +00:00
pakrym-oai 9c903c4716 Add ItemStarted/ItemCompleted events for UserInputItem (#5306)
Adds a new ItemStarted event and delivers UserMessage as the first item
type (more to come).


Renames `InputItem` to `UserInput` considering we're using the `Item`
suffix for actual items.
2025-10-20 13:34:44 -07:00
pakrym-oai 2287d2afde Create independent TurnContexts (#5308)
The goal of this change:
1. Unify user input and user turn implementation.
2. Have a single place where turn/session setting overrides are applied.
3. Have a single place where turn context is created.
4. Create TurnContext only for actual turn and have a separate structure
for current session settings (reuse ConfigureSession)
2025-10-18 17:43:08 -07:00
Gabriel Peal 40fba1bb4c [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
2025-10-17 01:05:15 -04:00
jif-oai f7b4e29609 feat: feature flag (#4948)
Add proper feature flag instead of having custom flags for everything.
This is just for experimental/wip part of the code
It can be used through CLI:
```bash
codex --enable unified_exec --disable view_image_tool
```

Or in the `config.toml`
```toml
# Global toggles applied to every profile unless overridden.
[features]
apply_patch_freeform = true
view_image_tool = false
```

Follow-up:
In a following PR, the goal is to have a default have `bundles` of
features that we can associate to a model
2025-10-14 17:50:00 +00:00
Dylan 3203862167 chore: update tool config (#4755)
## Summary
Updates tool config for gpt-5-codex

## Test Plan
- [x] Ran locally
- [x]  Updated unit tests
2025-10-04 22:47:26 -07:00
iceweasel-oai de8d77274a set gpt-5 as default model for Windows users (#4676)
Codex isn’t great yet on Windows outside of WSL, and while we’ve merged
https://github.com/openai/codex/pull/4269 to reduce the repetitive
manual approvals on readonly commands, we’ve noticed that users seem to
have more issues with GPT-5-Codex than with GPT-5 on Windows.

This change makes GPT-5 the default for Windows users while we continue
to improve the CLI harness and model for GPT-5-Codex on Windows.
2025-10-03 14:00:03 -07:00
jif-oai 33d3ecbccc chore: refactor tool handling (#4510)
# Tool System Refactor

- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.

Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.

## Next steps:
- Decompose `handle_container_exec_with_params` 
- Add parallel tool calls
2025-10-03 13:21:06 +01:00
Jeremy Rose 4a5f05c136 make tests pass cleanly in sandbox (#4067)
This changes the reqwest client used in tests to be sandbox-friendly,
and skips a bunch of other tests that don't work inside the
sandbox/without network.
2025-09-25 13:11:14 -07:00
pakrym-oai fdb8dadcae Add exec output-schema parameter (#4079)
Adds structured output to `exec` via the `--structured-output`
parameter.
2025-09-23 13:59:16 -07:00
Thibault Sottiaux c93e77b68b feat: update default (#4076)
Changes:
- Default model and docs now use gpt-5-codex. 
- Disables the GPT-5 Codex NUX by default.
- Keeps presets available for API key users.
2025-09-22 20:10:52 -07:00
Dylan 11285655c4 fix: Record EnvironmentContext in SendUserTurn (#3678)
## Summary
SendUserTurn has not been correctly handling updates to policies. While
the tui protocol handles this in `Op::OverrideTurnContext`, the
SendUserTurn should be appending `EnvironmentContext` messages when the
sandbox settings change. MCP client behavior should match the cli
behavior, so we update `SendUserTurn` message to match.

## Testing
- [x] Added prompt caching tests
2025-09-16 11:32:20 -07:00
jif-oai c6fd056aa6 feat: reasoning effort as optional (#3527)
Allow the reasoning effort to be optional
2025-09-12 12:06:33 -07:00
jif-oai 114ce9ff4d NIT unified exec (#3479)
Fix the default value of the experimental flag of unified_exec
2025-09-11 16:19:12 +00:00
jif-oai c09ed74a16 Unified execution (#3288)
## Unified PTY-Based Exec Tool

Note: this requires to have this flag in the config:
`use_experimental_unified_exec_tool=true`

- Adds a PTY-backed interactive exec feature (“unified_exec”) with
session reuse via
  session_id, bounded output (128 KiB), and timeout clamping (≤ 60 s).
- Protocol: introduces ResponseItem::UnifiedExec { session_id,
arguments, timeout_ms }.
- Tools: exposes unified_exec as a function tool (Responses API);
excluded from Chat
  Completions payload while still supported in tool lists.
- Path handling: resolves commands via PATH (or explicit paths), with
UTF‑8/newline‑aware
  truncation (truncate_middle).
- Tests: cover command parsing, path resolution, session
persistence/cleanup, multi‑session
  isolation, timeouts, and truncation behavior.
2025-09-10 17:38:11 -07:00
Jeremy Rose f69f07b028 put workspace roots in the environment context (#3375)
to keep the tool description constant when the writable roots change.
2025-09-10 15:10:52 -07:00
Michael Bolin 51d9e05de7 Back out "feat: POSIX unification and snapshot sessions (#3179)" (#3430)
This reverts https://github.com/openai/codex/pull/3179.

#3179 appears to introduce a regression where sourcing dotfiles causes a
bunch of activity in the title bar (and potentially slows things down?)


https://github.com/user-attachments/assets/a68f7fb3-0749-4e0e-a321-2aa6993e01da

Verified this no longer happens after backing out #3179.

Original commit changeset: 62bd0e3d9d
2025-09-10 12:40:24 -07:00
jif-oaiandMichael Bolin 62bd0e3d9d feat: POSIX unification and snapshot sessions (#3179)
## Session snapshot
For POSIX shell, the goal is to take a snapshot of the interactive shell
environment, store it in a session file located in `.codex/` and only
source this file for every command that is run.
As a result, if a snapshot files exist, `bash -lc <CALL>` get replaced
by `bash -c <CALL>`.

This also fixes the issue that `bash -lc` does not source `.bashrc`,
resulting in missing env variables and aliases in the codex session.
## POSIX unification
Unify `bash` and `zsh` shell into a POSIX shell. The rational is that
the tool will not use any `zsh` specific capabilities.

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-09-08 18:09:45 -07:00
pakrym-oai 5775174ec2 Never store requests (#3212)
When item ids are sent to Responses API it will load them from the
database ignoring the provided values. This adds extra latency.

Not having the mode to store requests also allows us to simplify the
code.

## Breaking change

The `disable_response_storage` configuration option is removed.
2025-09-05 10:41:47 -07:00