Commit Graph
28 Commits
Author SHA1 Message Date
Ahmed IbrahimandCodex af8a9d2d2b remove temporary ownership re-exports (#16626)
Stacked on #16508.

This removes the temporary `codex-core` / `codex-login` re-export shims
from the ownership split and rewrites callsites to import directly from
`codex-model-provider-info`, `codex-models-manager`, `codex-api`,
`codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.

No behavior change intended; this is the mechanical import cleanup layer
split out from the ownership move.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-03 00:33:34 -07:00
Michael Bolin aa2403e2eb core: remove cross-crate re-exports from lib.rs (#16512)
## Why

`codex-core` was re-exporting APIs owned by sibling `codex-*` crates,
which made downstream crates depend on `codex-core` as a proxy module
instead of the actual owner crate.

Removing those forwards makes crate boundaries explicit and lets leaf
crates drop unnecessary `codex-core` dependencies. In this PR, this
reduces the dependency on `codex-core` to `codex-login` in the following
files:

```
codex-rs/backend-client/Cargo.toml
codex-rs/mcp-server/tests/common/Cargo.toml
```

## What

- Remove `codex-rs/core/src/lib.rs` re-exports for symbols owned by
`codex-login`, `codex-mcp`, `codex-rollout`, `codex-analytics`,
`codex-protocol`, `codex-shell-command`, `codex-sandboxing`,
`codex-tools`, and `codex-utils-path`.
- Delete the `default_client` forwarding shim in `codex-rs/core`.
- Update in-crate and downstream callsites to import directly from the
owning `codex-*` crate.
- Add direct Cargo dependencies where callsites now target the owner
crate, and remove `codex-core` from `codex-rs/backend-client`.
2026-04-01 23:06:24 -07:00
Michael Bolin 20f43c1e05 core: support dynamic auth tokens for model providers (#16288)
## Summary

Fixes #15189.

Custom model providers that set `requires_openai_auth = false` could
only use static credentials via `env_key` or
`experimental_bearer_token`. That is not enough for providers that mint
short-lived bearer tokens, because Codex had no way to run a command to
obtain a bearer token, cache it briefly in memory, and retry with a
refreshed token after a `401`.

This PR adds that provider config and wires it through the existing auth
design: request paths still go through `AuthManager.auth()` and
`UnauthorizedRecovery`, with `core` only choosing when to use a
provider-backed bearer-only `AuthManager`.

## Scope

To keep this PR reviewable, `/models` only uses provider auth for the
initial request in this change. It does **not** add a dedicated `401`
retry path for `/models`; that can be follow-up work if we still need it
after landing the main provider-token support.

## Example Usage

```toml
model_provider = "corp-openai"

[model_providers.corp-openai]
name = "Corp OpenAI"
base_url = "https://gateway.example.com/openai"
requires_openai_auth = false

[model_providers.corp-openai.auth]
command = "gcloud"
args = ["auth", "print-access-token"]
timeout_ms = 5000
refresh_interval_ms = 300000
```

The command contract is intentionally small:

- write the bearer token to `stdout`
- exit `0`
- any leading or trailing whitespace is trimmed before the token is used

## What Changed

- add `model_providers.<id>.auth` to the config model and generated
schema
- validate that command-backed provider auth is mutually exclusive with
`env_key`, `experimental_bearer_token`, and `requires_openai_auth`
- build a bearer-only `AuthManager` for `ModelClient` and
`ModelsManager` when a provider configures `auth`
- let normal Responses requests and realtime websocket connects use the
provider-backed bearer source through the same `AuthManager.auth()` path
- allow `/models` online refresh for command-auth providers and attach
the provider token to the initial `/models` request
- keep `auth.cwd` available as an advanced escape hatch and include it
in the generated config schema

## Testing

- `cargo test -p codex-core provider_auth_command`
- `cargo test -p codex-core
refresh_available_models_uses_provider_auth_token`
- `cargo test -p codex-core
test_deserialize_provider_auth_config_defaults`

## Docs

- `developers.openai.com/codex` should document the new
`[model_providers.<id>.auth]` block and the token-command contract
2026-03-31 01:37:27 -07:00
3ce879c646 Handle realtime conversation end in the TUI (#14903)
- close live realtime sessions on errors, ctrl-c, and active meter
removal
- centralize TUI realtime cleanup and avoid duplicate follow-up close
info

---------

Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
2026-03-17 21:04:58 -07:00
98be562fd3 Unify realtime shutdown in core (#14902)
- route realtime startup, input, and transport failures through a single
shutdown path
- emit one realtime error/closed lifecycle while clearing session state
once

---------

Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
2026-03-17 15:58:52 -07:00
Ahmed Ibrahim c6ab4ee537 Gate realtime audio interruption logic to v2 (#14984)
- thread the realtime version into conversation start and app-server
notifications
- keep playback-aware mic gating and playback interruption behavior on
v2 only, leaving v1 on the legacy path
2026-03-17 15:24:37 -07:00
Ahmed IbrahimandCodex fbd7f9b986 [stack 2/4] Align main realtime v2 wire and runtime flow (#14830)
## Stack Position
2/4. Built on top of #14828.

## Base
- #14828

## Unblocks
- #14829
- #14827

## Scope
- Port the realtime v2 wire parsing, session, app-server, and
conversation runtime behavior onto the split websocket-method base.
- Branch runtime behavior directly on the current realtime session kind
instead of parser-derived flow flags.
- Keep regression coverage in the existing e2e suites.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-16 21:38:07 -07:00
Ahmed IbrahimandCodex 3aabce9e0a Unify realtime v1/v2 session config (#14606)
## Summary
- unify realtime websocket settings under `[realtime]` (`version` and
`type`)
- remove `realtime_conversation_v2` and select parser/session mode from
config

## Testing
- not run (per request)

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-13 11:35:38 -07:00
Ahmed IbrahimandCodex 2253a9d1d7 Add realtime transcription mode for websocket sessions (#14556)
- add experimental_realtime_ws_mode (conversational/transcription) and
plumb it into realtime conversation session config
- switch realtime websocket intent and session.update payload shape
based on mode
- update config schema and realtime/config tests

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-12 23:50:30 -07:00
Ahmed IbrahimandCodex 3e8f47169e Add realtime v2 event parser behind feature flag (#14537)
- Add a feature-flagged realtime v2 parser on the existing
websocket/session pipeline.
- Wire parser selection from core feature flags and map the codex
handoff tool-call path into existing handoff events.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-12 21:12:40 -07:00
Michael Bolin 0c8a36676a fix: move inline codex-rs/core unit tests into sibling files (#14444)
## Why
PR #13783 moved the `codex.rs` unit tests into `codex_tests.rs`. This
applies the same extraction pattern across the rest of `codex-rs/core`
so the production modules stay focused on runtime code instead of large
inline test blocks.

Keeping the tests in sibling files also makes follow-up edits easier to
review because product changes no longer have to share a file with
hundreds or thousands of lines of test scaffolding.

## What changed
- replaced each inline `mod tests { ... }` in `codex-rs/core/src/**`
with a path-based module declaration
- moved each extracted unit test module into a sibling `*_tests.rs`
file, using `mod_tests.rs` for `mod.rs` modules
- preserved the existing `cfg(...)` guards and module-local structure so
the refactor remains structural rather than behavioral

## Testing
- `cargo test -p codex-core --lib` (`1653 passed; 0 failed; 5 ignored`)
- `just fix -p codex-core`
- `cargo fmt --check`
- `cargo shear`
2026-03-12 08:16:36 -07:00
Ahmed Ibrahim 2e24be2134 Use realtime transcript for handoff context (#14132)
- collect input/output transcript deltas into active handoff transcript
state
- attach and clear that transcript on each handoff, and regenerate
schema/tests
2026-03-09 22:30:03 -07:00
Ahmed Ibrahim a11c59f634 Add realtime startup context override (#13796)
- add experimental_realtime_ws_startup_context to override or disable
realtime websocket startup context
- preserve generated startup context when unset and cover the new
override paths in tests
2026-03-06 16:00:30 -08:00
Ahmed Ibrahim 6cf0ed4e79 Refine realtime startup context formatting (#13560)
## Summary
- group recent work by git repo when available, otherwise by directory
- render recent work as bounded user asks with per-thread cwd context
- exclude hidden files and directories from workspace trees
2026-03-05 16:31:20 -08:00
Ahmed Ibrahim 7b088901c2 Log non-audio realtime events (#13516)
Improve observability of realtime conversation event handling by logging
non-audio events with payload details in the event loop, while skipping
audio-out events to reduce noise.
2026-03-04 16:30:18 -08:00
Ahmed Ibrahim 294079b0b1 Prefix handoff messages with role (#13505)
Format handoff context by prefixing each message with its role (for
example "user:" and "assistant:") before forwarding to the agent.
2026-03-04 15:37:31 -08:00
Ahmed Ibrahim 6bee02a346 Build delegated realtime handoff text from all messages (#13395)
## Summary
- Route delegated realtime handoff turns from all handoff message texts,
preserving order
- Fallback to input_transcript only when no messages are present
- Add regression coverage for multi-message handoff requests
2026-03-03 14:07:51 -08:00
Ahmed IbrahimandCodex b20b6aa46f Update realtime websocket API (#13265)
- migrate the realtime websocket transport to the new session and
handoff flow
- make the realtime model configurable in config.toml and use API-key
auth for the websocket

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-02 16:05:40 -08:00
0aeb55bf08 Record realtime close marker on replacement (#13058)
## Summary
- record a realtime close developer message when a new realtime session
replaces an active one
- assert the replacement marker through the mocked responses request
path

---------

Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Charles Cunningham <ccunningham@openai.com>
2026-03-01 13:54:12 -08:00
Ahmed Ibrahim 53e28f18cf Add realtime websocket tracing (#12981)
- add transport and conversation logs around connect, close, and parse
flow
- log realtime transport failures as errors for easier debugging
2026-02-26 22:15:18 -08:00
Ahmed Ibrahim 3f30746237 Add simple realtime text logs (#12807)
Update realtime debug logs to include the actual text payloads in both
input and output paths.

- In `core/src/realtime_conversation.rs`:
- `handle_start`: add extracted assistant text output to the
`[realtime-text]` debug log.
- `handle_text`: add incoming text input (`params.text`) to the
`[realtime-text]` debug log.

No tests were run (per request).
2026-02-25 12:01:48 -08:00
Ahmed Ibrahim 10a3adad8e Handle realtime spawn_transcript delegation (#12619) 2026-02-23 14:39:07 -08:00
Ahmed IbrahimandCodex e00fa19328 Revert "Revert "Route inbound realtime text into turn start or steer"" (#12480)
With working tests this time

---------

Co-authored-by: Codex <noreply@openai.com>
2026-02-22 11:54:16 -08:00
Ahmed Ibrahim 5e505ff877 Revert "Route inbound realtime text into turn start or steer" (#12479)
Reverts openai/codex#12469
2026-02-21 15:46:03 -08:00
Ahmed Ibrahim 031d701705 Route inbound realtime text into turn start or steer (#12469)
- Route inbound realtime websocket text into normal user input handling
so it steers an active turn or starts a new one
2026-02-21 15:45:27 -08:00
Ahmed Ibrahim b237f7cbb1 Add experimental realtime websocket backend prompt override (#12418)
- add top-level `experimental_realtime_ws_backend_prompt` config key
(experimental / do not use) and include it in config schema
- apply the override only to `Op::RealtimeConversation` websocket
`backend_prompt`, with config + realtime tests
2026-02-20 20:10:51 -08:00
Ahmed Ibrahim 7ae5d88016 Add experimental realtime websocket URL override (#12416)
- add top-level `experimental_realtime_ws_base_url` config key
(experimental / do not use) and include it in config schema
- apply the override only to `Op::RealtimeConversation` websocket
transport, with config + realtime tests
2026-02-20 19:51:20 -08:00
Ahmed Ibrahim 6817f0be8a Wire realtime api to core (#12268)
- Introduce `RealtimeConversationManager` for realtime API management 
- Add `op::conversation` to start conversation, insert audio, insert
text, and close conversation.
- emit conversation lifecycle and realtime events.
- Move shared realtime payload types into codex-protocol and add core
e2e websocket tests for start/replace/transport-close paths.

Things to consider:
- Should we use the same `op::` and `Events` channel to carry audio? I
think we should try this simple approach and later we can create
separate one if the channels got congested.
- Sending text updates to the client: we can start simple and later
restrict that.
- Provider auth isn't wired for now intentionally
2026-02-20 19:06:35 -08:00