## Summary
- add realtime websocket client transport in codex-api
- send session.create on connect with backend prompt and optional
conversation_id
- keep session.update for prompt changes after connect
- switch inbound event parsing to a tagged enum (typed variants instead
of optional field bag)
- add a websocket e2e integration test in
codex-rs/codex-api/tests/realtime_websocket_e2e.rs
## Why
This moves the realtime transport to an explicit session-create
handshake and improves protocol safety with typed inbound events.
## Testing
- Added e2e integration test coverage for session create + event flow in
the API crate.
### Summary
Ensure that we use the model value from the response header only so that
we are guaranteed with the correct slug name. We are no longer checking
against the model value from response so that we are less likely to have
false positive.
There are two different treatments - for SSE we use the header from the
response and for websocket we check top-level events.
Add per-turn notice when a request is downgraded to a fallback model due
to cyber safety checks.
**Changes**
- codex-api: Emit a ServerModel event based on the openai-model response
header and/or response payload (SSE + WebSocket), including when the
model changes mid-stream.
- core: When the server-reported model differs from the requested model,
emit a single per-turn warning explaining the reroute to gpt-5.2 and
directing users to Trusted
Access verification and the cyber safety explainer.
- app-server (v2): Surface these cyber model-routing warnings as
synthetic userMessage items with text prefixed by Warning: (and document
this behavior).
# 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.
Added multi-limit support end-to-end by carrying limit_name in
rate-limit snapshots and handling multiple buckets instead of only
codex.
Extended /usage client parsing to consume additional_rate_limits
Updated TUI /status and in-memory state to store/render per-limit
snapshots
Extended app-server rate-limit read response: kept rate_limits and added
rate_limits_by_name.
Adjusted usage-limit error messaging for non-default codex limit buckets
When communicating over websockets, we can't rely on headers to deliver
rate limit information. This PR adds a `codex.rate_limits` event that
the server can pass to the client to inform them about rate limit usage.
The client parses this data the same way we parse rate limit headers in
HTTP mode.
This PR also wires up the etag and reasoning headers for websockets
### What
add wiring for `phase` field on `ResponseItem::Message` to lay
groundwork for differentiating model preambles and final messages.
currently optional.
follows pattern in #9698.
updated schemas with `just write-app-server-schema` so we can see type
changes.
### Tests
Updated existing tests for SSE parsing and hydrating from history
Summary
- expose websocket telemetry hooks through the responses client so
request durations and event processing can be reported
- record websocket request/event metrics and emit runtime telemetry
events that the history UI now surfaces
- improve tests to cover websocket telemetry reporting and guard runtime
summary updates
<img width="824" height="79" alt="Screenshot 2026-01-31 at 5 28 12 PM"
src="https://github.com/user-attachments/assets/ea9a7965-d8b4-4e3c-a984-ef4fdc44c81d"
/>
seeing issues with azure after default-enabling web search: #10071,
#10257.
need to work with azure to fix api-side, for now turning off
default-enable of web_search for azure.
diff is big because i moved logic to reuse
### Summary
- Parse all `web_search` tool actions (`search`, `find_in_page`,
`open_page`).
- Previously we only parsed + displayed `search`, which made the TUI
appear to pause when the other actions were being used.
- Show in progress `web_search` calls as `Searching the web`
- Previously we only showed completed tool calls
<img width="308" height="149" alt="image"
src="https://github.com/user-attachments/assets/90a4e8ff-b06a-48ff-a282-b57b31121845"
/>
### Tests
Added + updated tests, tested locally
### Follow ups
Update VSCode extension to display these as well
**Goal**: Prevent response.failed events with `invalid_prompt` from
being treated as retryable errors so the UI shows the actual error
message instead of continually retrying.
**Before**: Codex would continue to retry despite the prompt being
marked as disallowed
**After**: Codex will stop retrying once prompt is marked disallowed
- capture the header from SSE/WS handshakes, store it per
ModelClientSession using `Oncelock`, echo it on turn-scoped requests,
and add SSE+WS integration tests for within-turn persistence +
cross-turn reset.
- keep `x-codex-turn-state` sticky within a user turn to maintain
routing continuity for retries/tool follow-ups.
Adds a new feature
`enable_request_compression` that will compress using zstd requests to
the codex-backend. Currently only enabled for codex-backend so only enabled for openai providers when using chatgpt::auth even when the feature is enabled
Added a new info log line too for evaluating the compression ratio and
overhead off compressing before requesting. You can enable with
`RUST_LOG=$RUST_LOG,codex_client::transport=info`
```
2026-01-06T00:09:48.272113Z INFO codex_client::transport: Compressed request body with zstd pre_compression_bytes=28914 post_compression_bytes=11485 compression_duration_ms=0
```
- Merge ModelFamily into ModelInfo
- Remove logic for adding instructions to apply patch
- Add compaction limit and visible context window to `ModelInfo`
Context
- This code parses Server-Sent Events (SSE) from the legacy Chat
Completions streaming API (wire_api = "chat").
- The upstream protocol terminates a stream with a final sentinel event:
data: [DONE].
- Some of our test stubs/helpers historically end the stream with data:
DONE (no brackets).
How this was found
- GitHub Actions on Windows failed in codex-app-server integration tests
with wiremock verification errors (expected multiple POSTs, got 1).
Diagnosis
- The job logs included: codex_api::sse::chat: Failed to parse
ChatCompletions SSE event ... data: DONE.
- eventsource_stream surfaces the sentinel as a normal SSE event; it
does not automatically close the stream.
- The parser previously attempted to JSON-decode every data: payload.
The sentinel is not JSON, so we logged and skipped it, then continued
polling.
- On servers that keep the HTTP connection open after emitting the
sentinel (notably wiremock on Windows), skipping the sentinel meant we
never emitted ResponseEvent::Completed.
- Higher layers wait for completion before progressing (emitting
approval requests and issuing follow-up model calls), so the test never
reached the subsequent requests and wiremock panicked when its
expected-call count was not met.
Fix
- Treat both data: [DONE] and data: DONE as explicit end-of-stream
sentinels.
- When a sentinel is seen, flush any pending assistant/reasoning items
and emit ResponseEvent::Completed once.
Tests
- Add a regression unit test asserting we complete on the sentinel even
if the underlying connection is not closed.
