Tightened the CLI integration tests to stop relying on wall-clock
sleeps—new fs watcher helper waits for session files instead of timing
out, and SSE mocks/fixtures make the flows deterministic.
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
1. You can now add streamable http servers via the CLI
2. As part of this, I'm also changing the existing bearer_token plain
text config field with ane env var
```
mcp add github --url https://api.githubcopilot.com/mcp/ --bearer-token-env-var=GITHUB_PAT
```
We use to put the review prompt in the first user message as well to
bypass statsig overrides, but now that's been resolved and instructions
are being respected, so we're duplicating the review instructions.
## Summary
- replace manual wiremock SSE mounts in the compact suite with the
shared response helpers
- simplify the exec auth_env integration test by using the
mount_sse_once_match helper
- rely on mount_sse_sequence plus server request collection to replace
the bespoke SeqResponder utility in tests
## Testing
- just fmt
------
https://chatgpt.com/codex/tasks/task_i_68e2e238f2a88320a337f0b9e4098093
## Summary
- add a reusable `ev_response_created` helper that builds
`response.created` SSE events for integration tests
- update the exec and core integration suites to use the new helper
instead of repeating manual JSON literals
- keep the streaming fixtures consistent by relying on the shared helper
in every touched test
## Testing
- `just fmt`
------
https://chatgpt.com/codex/tasks/task_i_68e1fe885bb883208aafffb94218da61
## Summary
- replace manual event polling loops in several core test suites with
the shared wait_for_event helpers
- keep prior assertions intact by using closure captures for stateful
expectations, including plan updates, patch lifecycles, and review flow
checks
- rely on wait_for_event_with_timeout where longer waits are required,
simplifying timeout handling
## Testing
- just fmt
------
https://chatgpt.com/codex/tasks/task_i_68e1d58582d483208febadc5f90dd95e
## Summary
This PR is an alternative approach to #4711, but instead of changing our
storage, parses out shell calls in the client and reserializes them on
the fly before we send them out as part of the request.
What this changes:
1. Adds additional serialization logic when the
ApplyPatchToolType::Freeform is in use.
2. Adds a --custom-apply-patch flag to enable this setting on a
session-by-session basis.
This change is delicate, but is not meant to be permanent. It is meant
to be the first step in a migration:
1. (This PR) Add in-flight serialization with config
2. Update model_family default
3. Update serialization logic to store turn outputs in a structured
format, with logic to serialize based on model_family setting.
4. Remove this rewrite in-flight logic.
## Test Plan
- [x] Additional unit tests added
- [x] Integration tests added
- [x] Tested locally
In the past, we were treating `input exceeded context window` as a
streaming error and retrying on it. Retrying on it has no point because
it won't change the behavior. In this PR, we surface the error to the
client without retry and also send a token count event to indicate that
the context window is full.
<img width="650" height="125" alt="image"
src="https://github.com/user-attachments/assets/c26b1213-4c27-4bfc-90f4-51a270a3efd5"
/>
We truncate the output of exec commands to not blow the context window.
However, some cases we weren't doing that. This caused reports of people
with 76% context window left facing `input exceeded context window`
which is weird.
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.
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"
/>
This issue was due to the fact that the timeout is not always sufficient
to have enough character for truncation + a race between synthetic
timeout and process kill
# 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
# Extract and Centralize Sandboxing
- Goal: Improve safety and clarity by centralizing sandbox planning and
execution.
- Approach:
- Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
with run_with_plan.
- Refactor codex.rs to plan-then-execute; handle failures/escalation via
the plan.
- Delegate apply_patch to the codex binary and run it with an empty env
for determinism.
We continue the separation between `codex app-server` and `codex
mcp-server`.
In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.
Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.
We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.
Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
### Title
## otel
Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.
```toml
[otel]
environment = "staging" # defaults to "dev"
exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled
```
Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.
### Event catalog
Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.
With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):
- `codex.api_request`
- `cf_ray` (optional)
- `attempt`
- `duration_ms`
- `http.response.status_code` (optional)
- `error.message` (failures)
- `codex.sse_event`
- `event.kind`
- `duration_ms`
- `error.message` (failures)
- `input_token_count` (completion only)
- `output_token_count` (completion only)
- `cached_token_count` (completion only, optional)
- `reasoning_token_count` (completion only, optional)
- `tool_token_count` (completion only)
- `codex.user_prompt`
- `prompt_length`
- `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
- `tool_name`
- `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
- `source` (`config` or `user`)
- `codex.tool_result`
- `tool_name`
- `call_id`
- `arguments`
- `duration_ms` (execution time for the tool)
- `success` (`"true"` or `"false"`)
- `output`
### Choosing an exporter
Set `otel.exporter` to control where events go:
- `none` – leaves instrumentation active but skips exporting. This is
the
default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
endpoint, protocol, and headers your collector expects:
```toml
[otel]
exporter = { otlp-http = {
endpoint = "https://otel.example.com/v1/logs",
protocol = "binary",
headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
}}
```
- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
metadata headers:
```toml
[otel]
exporter = { otlp-grpc = {
endpoint = "https://otel.example.com:4317",
headers = { "x-otlp-meta" = "abc123" }
}}
```
If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.
If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.
---------
Co-authored-by: Anton Panasenko <apanasenko@openai.com>
This PR adds support for streamable HTTP MCP servers when the
`experimental_use_rmcp_client` is enabled.
To set one up, simply add a new mcp server config with the url:
```
[mcp_servers.figma]
url = "http://127.0.0.1:3845/mcp"
```
It also supports an optional `bearer_token` which will be provided in an
authorization header. The full oauth flow is not supported yet.
The config parsing will throw if it detects that the user mixed and
matched config fields (like command + bearer token or url + env).
The best way to review it is to review `core/src` and then
`rmcp-client/src/rmcp_client.rs` first. The rest is tests and
propagating the `Transport` struct around the codebase.
Example with the Figma MCP:
<img width="5084" height="1614" alt="CleanShot 2025-09-26 at 13 35 40"
src="https://github.com/user-attachments/assets/eaf2771e-df3e-4300-816b-184d7dec5a28"
/>
The [official Rust
SDK](57fc428c57)
has come a long way since we first started our mcp client implementation
5 months ago and, today, it is much more complete than our own
stdio-only implementation.
This PR introduces a new config flag `experimental_use_rmcp_client`
which will use a new mcp client powered by the sdk instead of our own.
To keep this PR simple, I've only implemented the same stdio MCP
functionality that we had but will expand on it with future PRs.
---------
Co-authored-by: pakrym-oai <pakrym@openai.com>
Extracting tasks in a module and start abstraction behind a Trait (more
to come on this but each task will be tackled in a dedicated PR)
The goal was to drop the ActiveTask and to have a (potentially) set of
tasks during each turn
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.
