32 Commits

• [codex] Add response.processed websocket request (#21284)

  ## Summary
  
  - Add a `response.processed` websocket request payload and sender for
  Responses API websockets.
  - Send `response.processed` from `try_run_sampling_request` after a
  response completes, local turn processing succeeds, and the
  session-owned feature flag is enabled.
  - Add websocket coverage for both enabled and disabled feature-flag
  behavior.
  
  ## Validation
  
  - `just fmt`
  - `cargo test -p codex-core response_processed`
  - `cargo test -p codex-api responses_websocket`
  - `cargo test -p codex-features
  responses_websocket_response_processed_is_under_development`
  - `git diff --check`
  - `just fix -p codex-api -p codex-core -p codex-features`
  - `git diff --check origin/main...HEAD`

  pakrym-oai · 2026-05-06 09:58:46 -07:00
  2070d5bfd3
• Propagate cache key and service tiers in compact (#21249)

  ## Why
  
  `/responses/compact` should preserve the request-affinity fields that
  apply to the active auth mode. ChatGPT-auth compact requests need the
  effective `service_tier`, and compact requests for every auth mode need
  the stable `prompt_cache_key`, so compaction does not quietly lose
  routing or cache behavior that normal sampling already has.
  
  This follows the request-parity direction from #20719, but keeps the net
  change focused on the compact payload fields needed here.
  
  ## What changed
  
  - Add `service_tier` and `prompt_cache_key` to the compact endpoint
  input payload.
  - Build the remote compact payload from the existing responses request
  builder output so `Fast` still maps to `priority` when compact sends a
  service tier.
  - Pass the turn service tier into remote compaction, but only include it
  in compact payloads for ChatGPT-backed auth.
  - Keep `prompt_cache_key` on compact payloads for all auth modes.
  - Add request-body diff snapshot coverage in
  `core/tests/suite/compact_remote.rs` for:
  - API-key auth reusing `prompt_cache_key` while omitting `service_tier`
  even when `Fast` is configured.
    - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`.
  - Drive the snapshot coverage through five varied turns: plain text,
  multi-part text, tool-call continuation, image+text input, local-shell
  continuation, and final-turn reasoning output.
  
  ## Verification
  
  - Added insta snapshots for compact request-body parity against the last
  normal `/responses` request after five varied turns.
  - Not run locally per repo guidance; relying on GitHub CI for test
  execution.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-05-06 13:38:43 +03:00
  5d6f23a27b
• [rollout-trace] Include x-request-id in rollout trace. (#20066)

  ## Why
  
  Rollout traces need an identifier that can be used to correlate a Codex
  inference with upstream Responses API, proxy, and engine logs. The
  reduced trace model already exposed `upstream_request_id`, but it was
  being populated from the Responses API `response.id`. That value is
  useful for `previous_response_id` chaining, but it is not the transport
  request id that upstream systems key on.
  
  This PR separates those concepts so trace consumers can reliably answer
  both questions:
  
  - which Responses API response did this inference produce?
  - which upstream request handled it?
  
  ## Structure
  
  The change keeps the upstream request id at the same lifecycle level as
  the provider stream:
  
  - `codex-api` captures the `x-request-id` HTTP response header when the
  SSE stream is created and exposes it on `ResponseStream`. Fixture and
  websocket streams set the field to `None` because they do not have that
  HTTP response header.
  - `codex-core` carries that stream-level id into `InferenceTraceAttempt`
  when recording terminal stream outcomes. Completed, failed, cancelled,
  dropped-stream, and pre-response error paths all record the id when it
  is available.
  - `rollout-trace` now records both identifiers in raw terminal inference
  events and response payloads: `response_id` for the Responses API
  `response.id`, and `upstream_request_id` for `x-request-id`.
  - The reducer stores both fields on `InferenceCall`. It also uses
  `response_id` for `previous_response_id` conversation linking, which
  removes the old accidental dependency on the misnamed
  `upstream_request_id` field.
  - Terminal inference reduction now consumes the full terminal payload
  (`InferenceCompleted`, `InferenceFailed`, or `InferenceCancelled`) in
  one place. That keeps status, partial payloads, response ids, and
  upstream request ids consistent across success, failure, cancellation,
  and late stream-mapper events.
  
  ## Why This Shape
  
  `x-request-id` is a property of the HTTP/provider response envelope, not
  an SSE event. Capturing it once in `codex-api` and plumbing it through
  terminal trace recording avoids trying to infer the value from stream
  contents, and it preserves the id even when the stream fails or is
  cancelled after only partial output.
  
  Keeping `response_id` separate from `upstream_request_id` also makes the
  reduced trace model less surprising: `response_id` remains the
  conversation-continuation id, while `upstream_request_id` is the
  operational correlation id for upstream debugging.
  
  ## Validation
  
  The PR updates trace and reducer coverage for:
  
  - reading `x-request-id` from SSE response headers;
  - storing the true upstream request id on completed inference calls;
  - preserving upstream request ids for cancelled and late-cancelled
  inference streams;
  - keeping `previous_response_id` reconstruction tied to `response_id`
  rather than transport request ids.

  cassirer-openai · 2026-04-28 21:11:17 +00:00
  89698ad1c3
• Support end_turn in response.completed (#19610)

  Some providers of Responses API forward a model-defined `end_turn`
  boolean indicating explicitly the model's indication of whether it would
  like to end the turn or to be inferenced again. In this PR, we update
  the sampling loop to use this field correctly if it's set. If the field
  is not set by the provider, we fall back to the existing sampling logic.

  Andrey Mishchenko · 2026-04-25 21:57:42 -07:00
  355c40ad7e
• Add safety check notification and error handling (#19055)

  Adds a new app-server notification that fires when a user account has
  been flagged for potential safety reasons.

  Eric Traut · 2026-04-22 22:24:12 -07:00
  bbff4ee61a
• Allow guardian bare allow output (#18797)

  ## Summary
  
  Allow guardian to skip other fields and output only
  `{"outcome":"allow"}` when the command is low risk.
  This change lets guardian reviews use a non-strict text format while
  keeping the JSON schema itself as plain user-visible schema data, so
  transport strictness is carried out-of-band instead of through a schema
  marker key.
  
  ## What changed
  
  - Add an explicit `output_schema_strict` flag to model prompts and pass
  it into `codex-api` text formatting.
  - Set guardian reviewer prompts to non-strict schema validation while
  preserving strict-by-default behavior for normal callers.
  - Update the guardian output contract so definitely-low-risk decisions
  may return only `{"outcome":"allow"}`.
  - Treat bare allow responses as low-risk approvals in the guardian
  parser.
  - Add tests and snapshots covering the non-strict guardian request and
  optional guardian output fields.
  
  ## Verification
  
  - `cargo test -p codex-core guardian::tests::guardian`
  - `cargo test -p codex-core guardian::tests::`
  - `cargo test -p codex-core client_common::tests::`
  - `cargo test -p codex-protocol
  user_input_serialization_includes_final_output_json_schema`
  - `cargo test -p codex-api`
  - `git diff --check`
  
  Note: `cargo test -p codex-core` was also attempted, but this desktop
  environment injects ambient config/proxy state that causes unrelated
  config/session tests expecting pristine defaults to fail.
  
  ---------
  
  Co-authored-by: Dylan Hurd <dylan.hurd@openai.com>
  Co-authored-by: Codex <noreply@openai.com>

  maja-openai · 2026-04-21 15:37:12 -07:00
  ef00014a46
• Stream apply_patch changes (#17862)

  Adds new events for streaming apply_patch changes from responses api.
  This is to enable clients to show progress during file writes.
  
  Caveat: This does not work with apply_patch in function call mode, since
  that required adding streaming json parsing.

  Akshay Nathan · 2026-04-16 18:12:19 -07:00
  7995c66032
• Omit empty app-server instruction overrides (#17258)

  ## Summary
  - omit serialized Responses instructions when an app-server base
  instruction override is empty
  - skip empty developer instruction messages and add v2 coverage for the
  empty-override request shape
  
  ## Validation
  - just fmt
  - git diff --check

  Ahmed Ibrahim · 2026-04-09 15:29:35 -07:00
  ecca34209d
• fix(app-server) revert null instructions changes (#17047)
  Dylan Hurd · 2026-04-07 15:18:34 -07:00
  6c36e7d688
• feat(analytics): generate an installation_id and pass it in responsesapi client_metadata (#16912)

  ## Summary
  
  This adds a stable Codex installation ID and includes it on Responses
  API requests via `x-codex-installation-id` passed in via the
  `client_metadata` field for analytics/debugging.
  
  The main pieces are:
  - persist a UUID in `$CODEX_HOME/installation_id`
  - thread the installation ID into `ModelClient`
  - send it in `client_metadata` on Responses requests so it works
  consistently across HTTP and WebSocket transports

  Owen Lin · 2026-04-07 09:52:17 -07:00
  5d1671ca70
• Honor null thread instructions (#16964)

  - Treat explicit null thread instructions as a blank-slate override
  while preserving omitted-field fallback behavior.
  - Preserve null through rollout resume/fork and keep explicit empty
  strings distinct.
  - Add app-server v2 start/fork coverage for the tri-state instruction
  params.

  Ahmed Ibrahim · 2026-04-07 04:10:19 +00:00
  24c598e8a9
• feat(core, tracing): create turn spans over websockets (#14632)

  ## Description
  
  Dependent on:
  - [responsesapi] https://github.com/openai/openai/pull/760991 
  - [codex-backend] https://github.com/openai/openai/pull/760985
  
  `codex app-server -> codex-backend -> responsesapi` now reuses a
  persistent websocket connection across many turns. This PR updates
  tracing when using websockets so that each `response.create` websocket
  request propagates the current tracing context, so we can get a holistic
  end-to-end trace for each turn.
  
  Tracing is propagated via special keys (`ws_request_header_traceparent`,
  `ws_request_header_tracestate`) set in the `client_metadata` param in
  Responses API.
  
  Currently tracing on websockets is a bit broken because we only set
  tracing context on ws connection time, so it's detached from a
  `turn/start` request.

  Owen Lin · 2026-03-19 03:41:06 +00:00
  20f2a216df
• Reapply "Pass more params to compaction" (#14298) (#14521)

  This reverts commit 8af97ce4b08fdedadc6037851b5e20cc653e9536.
  
  Confirmed that this runs locally without the previous issues with tool
  use

  Rasmus Rygaard · 2026-03-12 23:27:21 +00:00
  53d5972226
• Revert "Pass more params to compaction" (#14298)
  Rasmus Rygaard · 2026-03-11 12:33:10 -07:00
  7f22329389
• Pass more params to compaction (#14247)

  Pass more params to /compact. This should give us parity with the
  /responses endpoint to improve caching.
  
  I'm torn about the MCP await. Blocking will give us parity but it seems
  like we explicitly don't block on MCPs. Happy either way

  Rasmus Rygaard · 2026-03-11 12:33:09 -07:00
  2621ba17e3
• Remove Responses V1 websocket implementation (#13364)

  V2 is the way to go!

  pakrym-oai · 2026-03-03 11:32:53 -07:00
  69df12efb3
• add fast mode toggle (#13212)

  - add a local Fast mode setting in codex-core (similar to how model id
  is currently stored on disk locally)
  - send `service_tier=priority` on requests when Fast is enabled
  - add `/fast` in the TUI and persist it locally
  - feature flag

  pash-openai · 2026-03-02 20:29:33 -08:00
  2f5b01abd6
• Send warmup request (#11258)

  Send a request with `generate: falls` but a full set of tools and
  instructions to pre-warm inference.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  pakrym-oai · 2026-02-24 08:15:47 -08:00
  97d0068658
• ws turn metadata via client_metadata (#11953)
  pash-openai · 2026-02-19 12:28:15 -08:00
  429cc4860e
• add(core): safety check downgrade warning (#11964)

  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).

  Fouad Matin · 2026-02-16 22:13:36 -08:00
  02e9006547
• Do not attempt to append after response.completed (#11402)

  Completed responses are fully done, and new response must be created.

  pakrym-oai · 2026-02-11 07:45:17 -08:00
  eac5473114
• Compare full request for websockets incrementality (#11343)

  Tools can dynamically change mid-turn now. We need to be more thorough
  about reusing incremental connections.

  pakrym-oai · 2026-02-10 19:14:36 +00:00
  0639c33892
• Remove ApiPrompt (#11265)

  Keep things simple and build a full Responses API request request right
  in the model client

  pakrym-oai · 2026-02-10 16:12:31 +00:00
  3322b99900
• memories: add extraction and prompt module foundation (#11200)

  ## Summary
  - add the new `core/src/memories` module (phase-one parsing, rollout
  filtering, storage, selection, prompts)
  - add Askama-backed memory templates for stage-one input/system and
  consolidation prompts
  - add module tests for parsing, filtering, path bucketing, and summary
  maintenance
  
  ## Testing
  - just fmt
  - cargo test -p codex-core --lib memories::

  jif-oai · 2026-02-10 10:10:24 +00:00
  6049ff02a0
• Support alternative websocket API (#10861)

  **Test plan**
  
  ```
  cargo build -p codex-cli && RUST_LOG='codex_api::endpoint::responses_websocket=trace,codex_core::client=debug,codex_core::codex=debug' \
    ./target/debug/codex \
      --enable responses_websockets_v2 \
      --profile byok \
      --full-auto
  ```

  Brian Yu · 2026-02-06 14:40:50 -08:00
  1fbf5ed06f
• feat: add phase 1 mem client (#10629)

  Adding a client on top of https://github.com/openai/openai/pull/672176

  jif-oai · 2026-02-04 17:59:36 +00:00
  e9335374b9
• chore: nuke chat/completions API (#10157)
  jif-oai · 2026-02-03 11:31:57 +00:00
  d2394a2494
• Act on reasoning-included per turn (#9402)

  - Reset reasoning-included flag each turn and update compaction test

  Ahmed Ibrahim · 2026-01-19 11:23:25 -08:00
  b11e96fb04
• Websocket append support (#9128)

  Support an incremental append request in websocket transport.

  pakrym-oai · 2026-01-13 06:07:13 +00:00
  e726a82c8a
• Refresh on models etag mismatch (#8491)

  - Send models etag
  - Refresh models on 412
  - This wires `ModelsManager` to `ModelFamily` so we don't mutate it
  mid-turn

  Ahmed Ibrahim · 2026-01-01 11:41:16 -08:00
  66b7c673e9
• 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: proper client extraction (#6996)
  jif-oai · 2025-11-25 18:06:12 +00:00
  4502b1b263