Commit Graph
33 Commits
Author SHA1 Message Date
Michael Bolin 2f8beb9f4e feat: add support for allowed_web_search_modes in requirements.toml
Example:

```toml
# This means that "live" is not allowed; "disabled" is allowed even though not listed explicitly.
allowed_web_search_modes = ["cached"]
```

### Why
- Support admin/MDM/requirements.toml constraints over web-search behavior, independent of user config or sandbox defaults.
- Ensure per-turn config resolution and review-mode overrides can never crash when constraints are present.
- Note that `allowed_web_search_modes = ["cached"]` denies `"live"`, even if `--yolo` is used. See `resolve_web_search_mode_for_turn()`.

### What
- Add `allowed_web_search_modes` to requirements parsing and app-server v2 `ConfigRequirements` (`allowedWebSearchModes`), with schema/TS fixture updates.
- Introduce TOML-only `WebSearchModeRequirement` for requirements allowlists; accept `disabled|cached|live`, and treat an empty list as `[disabled]`.
- Convert the allowlist to a `ConstrainedWithSource<Option<WebSearchMode>>`, always permitting `Disabled` while enforcing membership for other values.
- Make `Config.web_search_mode` a constrained field, update call sites/tests, and surface constraint violations via warnings/fallback.
- Extend TUI `/debug-config` output to display `allowed_web_search_modes`.

### Safety
- Avoid `expect()` on constrained `web_search_mode` mutation in session per-turn config and review-thread setup; warn and keep the constrained value instead.
2026-02-06 18:02:36 -08:00
pakrym-oai 7f20357611 Stop client from being state carrier (#10595)
I'd like to make client session wide. This requires shedding all random
state it has to carry.
2026-02-04 09:05:37 -08:00
sayan-oai fc05374344 chore: add phase to message responseitem (#10455)
### 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
2026-02-03 02:52:26 +00:00
sayan-oai a90ab789c2 fix: enable per-turn updates to web search mode (#10040)
web_search can now be updated per-turn, for things like changes to
sandbox policy.

`SandboxPolicy::DangerFullAccess` now sets web_search to `live`, and the
default is still `cached`.

Added integration tests.
2026-01-27 18:09:29 -08:00
sayan-oai 0adcd8aa86 make cached web_search client-side default (#9974)
[Experiment](https://console.statsig.com/50aWbk2p4R76rNX9lN5VUw/experiments/codex_web_search_rollout/summary)
for default cached `web_search` completed; cached chosen as default.

Update client to reflect that.
2026-01-26 21:25:40 -08:00
pakrym-oai b511c38ddb Support end_turn flag (#9698)
Experimental flag that signals the end of the turn.
2026-01-22 17:27:48 +00:00
Eric Traut 264d40efdc Fix invalid input error on Azure endpoint (#9387)
Users of Azure endpoints are reporting that when they use `/review`,
they sometimes see an error "Invalid 'input[3].id". I suspect this is
specific to the Azure implementation of the `responses` API. The Azure
team generally copies the OpenAI code for this endpoint, but they do
have minor differences and sometimes lag in rolling out bug fixes or
updates.

The error appears to be triggered because the `/review` implementation
is using a user ID with a colon in it.

Addresses #9360
2026-01-19 08:21:27 -08:00
sayan-oai 169201b1b5 [search] allow explicitly disabling web search (#9249)
moving `web_search` rollout serverside, so need a way to explicitly
disable search + signal eligibility from the client.

- Add `x‑oai‑web‑search‑eligible` header that signifies whether the
request can have web search.
- Only attach the `web_search` tool when the resolved `WebSearchMode` is
`Live` or `Cached`.
2026-01-15 11:28:57 -08:00
sayan-oai 5e426ac270 add WebSearchMode enum (#9216)
### What
Add `WebSearchMode` enum (disabled, cached live, defaults to cached) to
config + V2 protocol. This enum takes precedence over legacy flags:
`web_search_cached`, `web_search_request`, and `tools.web_search`.

Keep `--search` as live.

### Tests
Added tests
2026-01-14 12:51:42 -08:00
pakrym-oai 92472e7baa Use current model for review (#9179)
Instead of having a hard-coded default review model, use the current
model for running `/review` unless one is specified in the config.

Also inherit current reasoning effort
2026-01-14 08:59:41 -08:00
jif-oai 1aed01e99f renaming: task to turn (#8963) 2026-01-09 17:31:17 +00:00
Thibault Sottiaux be212db0c8 fix: include project instructions in /review subagent (#8899)
Include project-level AGENTS.md and skills in /review sessions so the
review sub-agent uses the same instruction pipeline as standard runs,
keeping reviewer context aligned with normal sessions.
2026-01-08 13:31:01 +00:00
jif-oai 634650dd25 feat: metrics capabilities (#8318)
Add metrics capabilities to Codex. The `README.md` is up to date.

This will not be merged with the metrics before this PR of course:
https://github.com/openai/codex/pull/8350
2026-01-08 11:47:36 +00:00
jif-oai 1253d19641 chore: drop useless feature flags (#8850) 2026-01-07 19:54:32 +00:00
jif-oai 116059c3a0 chore: unify conversation with thread name (#8830)
Done and verified by Codex + refactor feature of RustRover
2026-01-07 17:04:53 +00:00
Eric Traut bbc5675974 Revert "chore: review in read-only (#7593)" (#8127)
This reverts commit 291b54a762.

This commit was intended to prevent the model from making code changes
during `/review`, which is sometimes does. Unfortunately, it has other
unintended side effects that cause `/review` to fail in a variety of
ways. See #8115 and #7815. We've therefore decided to revert this
change.
2025-12-16 12:01:54 -08:00
Ahmed Ibrahim cb9a189857 make model optional in config (#7769)
- Make Config.model optional and centralize default-selection logic in
ModelsManager, including a default_model helper (with
codex-auto-balanced when available) so sessions now carry an explicit
chosen model separate from the base config.
- Resolve `model` once in `core` and `tui` from config. Then store the
state of it on other structs.
- Move refreshing models to be before resolving the default model
2025-12-10 11:19:00 -08:00
jif-oai 291b54a762 chore: review in read-only (#7593) 2025-12-04 10:01:12 -08:00
Ahmed Ibrahim cee37a32b2 Migrate model family to models manager (#7565)
This PR moves `ModelsFamily` to `openai_models`. It also propagates
`ModelsManager` to session services and use it to drive model family. We
also make `derive_default_model_family` private because it's a step
towards what we want: one place that gives model configuration.

This is a second step at having one source of truth for models
information and config: `ModelsManager`.

Next steps would be to remove `ModelsFamily` from config. That's massive
because it's being used in 41 occasions mostly pre launching `codex`.
Also, we need to make `find_family_for_model` private. It's also big
because it's being used in 21 occasions ~ all tests.
2025-12-03 18:49:47 -08:00
jif-oai aaec8abf58 feat: detached review (#7292) 2025-11-28 11:34:57 +00:00
jif-oai 8ddae8cde3 feat: review in app server (#6613) 2025-11-18 21:58:54 +00:00
pakrym-oai c368c6aeea Remove shell tool when unified exec is enabled (#6345)
Also drop streameable shell that's just an alias for unified exec.
2025-11-06 15:46:24 -08:00
Ahmed Ibrahim fe54c216a3 ignore deltas in codex_delegate (#6208)
ignore legacy deltas in codex-delegate to avoid this
[issue](https://github.com/openai/codex/pull/6202).
2025-11-04 19:21:35 +00:00
Ahmed Ibrahim 7e068e1094 fix: ignore reasoning deltas because we send it with turn item (#6202)
should fix this:

<img width="2418" height="242" alt="image"
src="https://github.com/user-attachments/assets/f818d00b-ed3a-479b-94a7-e4bc5db6326e"
/>
2025-11-04 08:27:16 -08:00
Ahmed Ibrahim 5fcc380bd9 Pass initial history as an optional to codex delegate (#5950)
This will give us more freedom on controlling the delegation. i.e we can
fork our history and run `compact`.
2025-10-30 07:22:42 -07:00
Ahmed Ibrahim 7aa46ab5fc ignore agent message deltas for the review mode (#5937)
The deltas produce the whole json output. ignore them.
2025-10-30 00:47:55 +00:00
pakrym-oaiandOwen Lin 3429e82e45 Add item streaming events (#5546)
Adds AgentMessageContentDelta, ReasoningContentDelta,
ReasoningRawContentDelta item streaming events while maintaining
compatibility for old events.

---------

Co-authored-by: Owen Lin <owen@openai.com>
2025-10-29 22:33:57 +00:00
Ahmed Ibrahim 13e1d0362d Delegate review to codex instance (#5572)
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`
2025-10-29 21:04:25 +00:00
pakrym-oai 789e65b9d2 Pass TurnContext around instead of sub_id (#5421)
Today `sub_id` is an ID of a single incoming Codex Op submition. We then
associate all events triggered by this operation using the same
`sub_id`.

At the same time we are also creating a TurnContext per submission and
we'd like to start associating some events (item added/item completed)
with an entire turn instead of just the operation that started it.

Using turn context when sending events give us flexibility to change
notification scheme.
2025-10-21 08:04:16 -07:00
pakrym-oai 9c903c4716 Add ItemStarted/ItemCompleted events for UserInputItem (#5306)
Adds a new ItemStarted event and delivers UserMessage as the first item
type (more to come).


Renames `InputItem` to `UserInput` considering we're using the `Item`
suffix for actual items.
2025-10-20 13:34:44 -07:00
pakrym-oai c03e31ecf5 Support graceful agent interruption (#5287) 2025-10-17 18:52:57 +00:00
jif-oai 268a10f917 feat: add header for task kind (#5142)
Add a header in the responses API request for the task kind (compact,
review, ...) for observability purpose
The header name is `codex-task-type`
2025-10-14 15:17:00 +00:00
jif-oai 1fc3413a46 ref: state - 2 (#4229)
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
2025-09-26 13:49:08 +00:00