Commit Graph

9 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
gt-oai
1f47e08d66 Cloud Requirements: increase timeout and retries (#10631)
Add retries and an increased-length timeout for loading Cloud
Requirements.

Co-authored-by: alexsong-oai <alexsong@openai.com>
2026-02-05 01:52:12 +00:00
gt-oai
95269ce88b Increase cloud req timeout (#10659)
5s -> 15s
2026-02-04 18:57:39 +00:00
Ruyut
9327e99b28 Fix minor typos in comments and documentation (#10287)
## Summary

I have read the contribution guidelines.  
All changes in this PR are limited to text corrections and do not modify
any business logic, runtime behavior, or user-facing functionality.

## Details

This PR fixes several minor typos, including:

- `create` -> `crate`
- `analagous` -> `analogous`
- `apply-patch` -> `apply_patch`
- `codecs` -> `codex`
- ` '/" ` -> ` '/' `
- `Respesent` -> `Represent`
2026-01-30 22:11:02 -08:00
gt-oai
47faa1594c Turn on cloud requirements for business too (#10283)
Need to check "enterprise" and "business"
2026-01-31 02:57:42 +00:00
gt-oai
149f3aa27a Add enforce_residency to requirements (#10263)
Add `enforce_residency` to requirements.toml and thread it through to a
header on `default_client`.
2026-01-31 00:26:25 +00:00
Michael Bolin
40bf11bd52 chore: fix the build breakage that came from a merge race (#10239)
I think I needed to rebase on top of
https://github.com/openai/codex/pull/10167 before merging
https://github.com/openai/codex/pull/10208.
2026-01-30 10:29:54 -08:00
gt-oai
5662eb8b75 Load exec policy rules from requirements (#10190)
`requirements.toml` should be able to specify rules which always run. 

My intention here was that these rules could only ever be restrictive,
which means the decision can be "prompt" or "forbidden" but never
"allow". A requirement of "you must always allow this command" didn't
make sense to me, but happy to be gaveled otherwise.

Rules already applies the most restrictive decision, so we can safely
merge these with rules found in other config folders.
2026-01-30 18:04:09 +00:00
gt-oai
e85d019daa Fetch Requirements from cloud (#10167)
Load requirements from Codex Backend. It only does this for enterprise
customers signed in with ChatGPT.

Todo in follow-up PRs:
* Add to app-server and exec too
* Switch from fail-open to fail-closed on failure
2026-01-30 12:03:29 +00:00