we are seeing [reports](https://github.com/openai/codex/issues/6004) of
users having verbosity in their config.toml and facing issues.
gpt-5-codex doesn't accept other values rather than medium for
verbosity.
Adds AgentMessageContentDelta, ReasoningContentDelta,
ReasoningRawContentDelta item streaming events while maintaining
compatibility for old events.
---------
Co-authored-by: Owen Lin <owen@openai.com>
In this PR, I am exploring migrating task kind to an invocation of
Codex. The main reason would be getting rid off multiple
`ConversationHistory` state and streamlining our context/history
management.
This approach depends on opening a channel between the sub-codex and
codex. This channel is responsible for forwarding `interactive`
(`approvals`) and `non-interactive` events. The `task` is responsible
for handling those events.
This opens the door for implementing `codex as a tool`, replacing
`compact` and `review`, and potentially subagents.
One consideration is this code is very similar to `app-server` specially
in the approval part. If in the future we wanted an interactive
`sub-codex` we should consider using `codex-mcp`
This PR does the following:
1. Changes `try_refresh_token` to handle the case where the endpoint
returns a response without an `id_token`. The OpenID spec indicates that
this field is optional and clients should not assume it's present.
2. Changes the `attempt_stream_responses` to propagate token refresh
errors rather than silently ignoring them.
3. Fixes a typo in a couple of error messages (unrelated to the above,
but something I noticed in passing) - "reconnect" should be spelled
without a hyphen.
This PR does not implement the additional suggestion from @pakrym-oai
that we should sign out when receiving `refresh_token_expired` from the
refresh endpoint. Leaving this as a follow-on because I'm undecided on
whether this should be implemented in `try_refresh_token` or its
callers.
This PR adds support for a model-based summary and risk assessment for
commands that violate the sandbox policy and require user approval. This
aids the user in evaluating whether the command should be approved.
The feature works by taking a failed command and passing it back to the
model and asking it to summarize the command, give it a risk level (low,
medium, high) and a risk category (e.g. "data deletion" or "data
exfiltration"). It uses a new conversation thread so the context in the
existing thread doesn't influence the answer. If the call to the model
fails or takes longer than 5 seconds, it falls back to the current
behavior.
For now, this is an experimental feature and is gated by a config key
`experimental_sandbox_command_assessment`.
Here is a screen shot of the approval prompt showing the risk assessment
and summary.
<img width="723" height="282" alt="image"
src="https://github.com/user-attachments/assets/4597dd7c-d5a0-4e9f-9d13-414bd082fd6b"
/>
## Summary
- wrap the default reqwest::Client inside a new
CodexHttpClient/CodexRequestBuilder pair and log the HTTP method, URL,
and status for each request
- update the auth/model/provider plumbing to use the new builder helpers
so headers and bearer auth continue to be applied consistently
- add the shared `http` dependency that backs the header conversion
helpers
## Testing
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-core`
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-chatgpt`
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-tui`
------
https://chatgpt.com/codex/tasks/task_i_68fa5038c17483208b1148661c5873be
While we do not want to encourage users to hardcode secrets in their
`config.toml` file, it should be possible to pass an API key
programmatically. For example, when using `codex app-server`, it is
possible to pass a "bag of configuration" as part of the
`NewConversationParams`:
682d05512f/codex-rs/app-server-protocol/src/protocol.rs (L248-L251)
When using `codex app-server`, it's not practical to change env vars of
the `codex app-server` process on the fly (which is how we usually read
API key values), so this helps with that.
Adds a `GET account/rateLimits/read` API to app-server. This calls the
codex backend to fetch the user's current rate limits.
This would be helpful in checking rate limits without having to send a
message.
For calling the codex backend usage API, I generated the types and
manually copied the relevant ones into `codex-backend-openapi-types`.
It'll be nice to extend our internal openapi generator to support Rust
so we don't have to run these manual steps.
# 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.
The backend will be returning unix timestamps (seconds since epoch)
instead of RFC 3339 strings. This will make it more ergonomic for
developers to integrate against - no string parsing.
This change ensures that we store the absolute time instead of relative
offsets of when the primary and secondary rate limits will reset.
Previously these got recalculated relative to current time, which leads
to the displayed reset times to change over time, including after doing
a codex resume.
For previously changed sessions, this will cause the reset times to not
show due to this being a breaking change:
<img width="524" height="55" alt="Screenshot 2025-10-17 at 5 14 18 PM"
src="https://github.com/user-attachments/assets/53ebd43e-da25-4fef-9c47-94a529d40265"
/>
Fixes https://github.com/openai/codex/issues/4761
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 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>
- Render `send a message to load usage data` in the beginning of the
session
- Render `data not available yet` if received no rate limits
- nit case
- Deleted stall snapshots that were moved to
`codex-rs/tui/src/status/snapshots`
# 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.
I would like to be able to swap in a different way to resolve model
sampling requests, so this refactoring consolidates things behind
`attempt_stream_responses()` to make that easier. Ideally, we would
support an in-memory backend that we can use in our integration tests,
for example.
We currently get information about rate limits in the response headers.
We want to forward them to the clients to have better transparency.
UI/UX plans have been discussed and this information is needed.
Azure Responses API doesn't work well with store:false and response
items.
If store = false and id is sent an error is thrown that ID is not found
If store = false and id is not sent an error is thrown that ID is
required
Add detection for Azure urls and add a workaround to preserve reasoning
item IDs and send store:true
## Compact feature:
1. Stops the model when the context window become too large
2. Add a user turn, asking for the model to summarize
3. Build a bridge that contains all the previous user message + the
summary. Rendered from a template
4. Start sampling again from a clean conversation with only that bridge
The previous config approach had a few issues:
1. It is part of the config but not designed to be used externally
2. It had to be wired through many places (look at the +/- on this PR
3. It wasn't guaranteed to be set consistently everywhere because we
don't have a super well defined way that configs stack. For example, the
extension would configure during newConversation but anything that
happened outside of that (like login) wouldn't get it.
This env var approach is cleaner and also creates one less thing we have
to deal with when coming up with a better holistic story around configs.
One downside is that I removed the unit test testing for the override
because I don't want to deal with setting the global env or spawning
child processes and figuring out how to introspect their originator
header. The new code is sufficiently simple and I tested it e2e that I
feel as if this is still worth it.
We're trying to migrate from `session_id: Uuid` to `conversation_id:
ConversationId`. Not only does this give us more type safety but it
unifies our terminology across Codex and with the implementation of
session resuming, a conversation (which can span multiple sessions) is
more appropriate.
I started this impl on https://github.com/openai/codex/pull/3219 as part
of getting resume working in the extension but it's big enough that it
should be broken out.
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.
