Commit Graph

449 Commits

Author SHA1 Message Date
Jeremy Rose
19f46439ae timeouts for mcp tool calls (#3959)
defaults to 60sec, overridable with MCP_TOOL_TIMEOUT or on a per-server
basis in the config.
2025-09-22 10:30:59 -07:00
jif-oai
e258ca61b4 chore: more clippy rules 2 (#4057)
The only file to watch is the cargo.toml
All the others come from just fix + a few manual small fix

The set of rules have been taken from the list of clippy rules
arbitrarily while trying to optimise the learning and style of the code
while limiting the loss of productivity
2025-09-22 17:16:02 +00:00
jif-oai
e5fe50d3ce chore: unify cargo versions (#4044)
Unify cargo versions at root
2025-09-22 16:47:01 +00:00
pakrym-oai
14a115d488 Add non_sandbox_test helper (#3880)
Makes tests shorter
2025-09-22 14:50:41 +00:00
dedrisian-oai
5996ee0e5f feat: Add more /review options (#3961)
Adds the following options:

1. Review current changes
2. Review a specific commit
3. Review against a base branch (PR style)
4. Custom instructions

<img width="487" height="330" alt="Screenshot 2025-09-20 at 2 11 36 PM"
src="https://github.com/user-attachments/assets/edb0aaa5-5747-47fa-881f-cc4c4f7fe8bc"
/>

---

\+ Adds the following UI helpers:

1. Makes list selection searchable
2. Adds navigation to the bottom pane, so you could add a stack of
popups
3. Basic custom prompt view
2025-09-21 20:18:35 -07:00
Ahmed Ibrahim
04504d8218 Forward Rate limits to the UI (#3965)
We currently get information about rate limits in the response headers.
We want to forward them to the clients to have better transparency.
UI/UX plans have been discussed and this information is needed.
2025-09-20 21:26:16 -07:00
pakrym-oai
9b18875a42 Use helpers instead of fixtures (#3888)
Move to using test helper method everywhere.
2025-09-19 06:46:25 -07:00
pakrym-oai
881c7978f1 Move responses mocking helpers to a shared lib (#3878)
These are generally useful
2025-09-18 17:53:14 -07:00
Ahmed Ibrahim
a7fda70053 Use a unified shell tell to not break cache (#3814)
Currently, we change the tool description according to the sandbox
policy and approval policy. This breaks the cache when the user hits
`/approvals`. This PR does the following:
- Always use the shell with escalation parameter:
- removes `create_shell_tool_for_sandbox` and always uses unified tool
via `create_shell_tool`
- Reject the func call when the model uses escalation parameter when it
cannot.
2025-09-19 00:08:28 +00:00
Michael Bolin
de64f5f007 fix: update try_parse_word_only_commands_sequence() to return commands in order (#3881)
Incidentally, we had a test for this in
`accepts_multiple_commands_with_allowed_operators()`, but it was
verifying the bad behavior. Oops!
2025-09-18 16:07:38 -07:00
Michael Bolin
8595237505 fix: ensure cwd for conversation and sandbox are separate concerns (#3874)
Previous to this PR, both of these functions take a single `cwd`:


71038381aa/codex-rs/core/src/seatbelt.rs (L19-L25)


71038381aa/codex-rs/core/src/landlock.rs (L16-L23)

whereas `cwd` and `sandbox_cwd` should be set independently (fixed in
this PR).

Added `sandbox_distinguishes_command_and_policy_cwds()` to
`codex-rs/exec/tests/suite/sandbox.rs` to verify this.
2025-09-18 14:37:06 -07:00
dedrisian-oai
62258df92f feat: /review (#3774)
Adds `/review` action in TUI

<img width="637" height="370" alt="Screenshot 2025-09-17 at 12 41 19 AM"
src="https://github.com/user-attachments/assets/b1979a6e-844a-4b97-ab20-107c185aec1d"
/>
2025-09-18 14:14:16 -07:00
Jeremy Rose
b34e906396 Reland "refactor transcript view to handle HistoryCells" (#3753)
Reland of #3538
2025-09-18 20:55:53 +00:00
Jeremy Rose
71038381aa fix error on missing notifications in [tui] (#3867)
Fixes #3811.
2025-09-18 11:25:09 -07:00
jif-oai
277fc6254e chore: use tokio mutex and async function to prevent blocking a worker (#3850)
### Why Use `tokio::sync::Mutex`

`std::sync::Mutex` are not _async-aware_. As a result, they will block
the entire thread instead of just yielding the task. Furthermore they
can be poisoned which is not the case of `tokio` Mutex.
This allows the Tokio runtime to continue running other tasks while
waiting for the lock, preventing deadlocks and performance bottlenecks.

In general, this is preferred in async environment
2025-09-18 18:21:52 +01:00
jif-oai
992b531180 fix: some nit Rust reference issues (#3849)
Fix some small references issue. No behavioural change. Just making the
code cleaner
2025-09-18 18:18:06 +01:00
jif-oai
4a5d6f7c71 Make ESC button work when auto-compaction (#3857)
Only emit a task finished when the compaction comes from a `/compact`
2025-09-18 15:34:16 +00:00
pakrym-oai
d4aba772cb Switch to uuid_v7 and tighten ConversationId usage (#3819)
Make sure conversations have a timestamp.
2025-09-18 14:37:03 +00:00
jif-oai
4c97eeb32a bug: Ignore tests for now (#3777)
Ignore flaky / long tests for now
2025-09-18 10:43:45 +01:00
Thibault Sottiaux
c9505488a1 chore: update "Codex CLI harness, sandboxing, and approvals" section (#3822) 2025-09-17 16:48:20 -07:00
dedrisian-oai
72733e34c4 Add dev message upon review out (#3758)
Proposal: We want to record a dev message like so:

```
{
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "<user_action>
  <context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
  <action>review</action>
  <results>
  {findings_str}
  </results>
</user_action>"
        }
      ]
    },
```

Without showing in the chat transcript.

Rough idea, but it fixes issue where the user finishes a review thread,
and asks the parent "fix the rest of the review issues" thinking that
the parent knows about it.

### Question: Why not a tool call?

Because the agent didn't make the call, it was a human. + we haven't
implemented sub-agents yet, and we'll need to think about the way we
represent these human-led tool calls for the agent.
2025-09-16 18:43:32 -07:00
dedrisian-oai
7fe4021f95 Review mode core updates (#3701)
1. Adds the environment prompt (including cwd) to review thread
2. Prepends the review prompt as a user message (temporary fix so the
instructions are not replaced on backend)
3. Sets reasoning to low
4. Sets default review model to `gpt-5-codex`
2025-09-16 13:36:51 -07:00
Dylan
11285655c4 fix: Record EnvironmentContext in SendUserTurn (#3678)
## Summary
SendUserTurn has not been correctly handling updates to policies. While
the tui protocol handles this in `Op::OverrideTurnContext`, the
SendUserTurn should be appending `EnvironmentContext` messages when the
sandbox settings change. MCP client behavior should match the cli
behavior, so we update `SendUserTurn` message to match.

## Testing
- [x] Added prompt caching tests
2025-09-16 11:32:20 -07:00
Ahmed Ibrahim
244687303b Persist search items (#3745)
Let's record the search items because they are part of the history.
2025-09-16 18:02:15 +00:00
Dylan
a8026d3846 fix: read-only escalations (#3673)
## Summary
Splitting out this smaller fix from #2694 - fixes the sandbox
permissions so Chat / read-only mode tool definition matches
expectations

## Testing 
- [x] Tested locally

<img width="1271" height="629" alt="Screenshot 2025-09-15 at 2 51 19 PM"
src="https://github.com/user-attachments/assets/fcb247e4-30b6-4199-80d7-a2876d79ad7d"
/>
2025-09-15 19:01:10 -07:00
dependabot[bot]
404c126fc3 chore(deps): bump wildmatch from 2.4.0 to 2.5.0 in /codex-rs (#3619)
Bumps [wildmatch](https://github.com/becheran/wildmatch) from 2.4.0 to
2.5.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/becheran/wildmatch/releases">wildmatch's
releases</a>.</em></p>
<blockquote>
<h2>v2.5.0</h2>
<p><a
href="https://redirect.github.com/becheran/wildmatch/pull/27">becheran/wildmatch#27</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b39902c120"><code>b39902c</code></a>
chore: Release wildmatch version 2.5.0</li>
<li><a
href="87a8cf4c80"><code>87a8cf4</code></a>
Merge pull request <a
href="https://redirect.github.com/becheran/wildmatch/issues/28">#28</a>
from smichaku/micha/fix-unicode-case-insensitive-matching</li>
<li><a
href="a3ab4903f5"><code>a3ab490</code></a>
fix: Fix unicode matching for non-ASCII characters</li>
<li>See full diff in <a
href="https://github.com/becheran/wildmatch/compare/v2.4.0...v2.5.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=wildmatch&package-manager=cargo&previous-version=2.4.0&new-version=2.5.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-09-15 12:57:17 -07:00
Jeremy Rose
0560079c41 notifications on approvals and turn end (#3329)
uses OSC 9 to notify when a turn ends or approval is required. won't
work in vs code or terminal.app but iterm2/kitty/wezterm supports it :)
2025-09-15 10:22:02 -07:00
ae
5c583fe89b feat: tweak onboarding strings (#3650) 2025-09-15 08:49:37 -07:00
pakrym-oai
b1c291e2bb Add file reference guidelines to gpt-5 prompt (#3651) 2025-09-15 08:35:30 -07:00
Michael Bolin
f037b2fd56 chore: rename (#3648) 2025-09-15 08:17:13 -07:00
Thibault Sottiaux
d60cbed691 fix: add references (#3633) 2025-09-15 07:48:22 -07:00
jimmyfraiture2
d555b68469 fix: race condition unified exec (#3644)
Fix race condition without storing an rx in the session
2025-09-15 06:52:39 -07:00
Thibault Sottiaux
6039f8a126 feat: tighten preset filter, tame storage load logs, enable rollout prompt by default (#3628)
Summary
- common: use exact equality for Swiftfox exclusion to avoid hiding
future slugs that merely contain the substring
- core: treat missing internal_storage.json as expected (debug), warn
only on real IO/parse errors
- tui: drop DEBUG_HIGH gate; always consider showing rollout prompt, but
suppress under ApiKey auth mode
2025-09-14 23:05:41 -07:00
Ahmed Ibrahim
50262a44ce Show abort in the resume (#3629)
Show abort error when resuming a session
2025-09-15 05:24:30 +00:00
easong-openai
6a8e743d57 initial mcp add interface (#3543)
Adds `codex mcp add`, `codex mcp list`, `codex mcp remove`. Currently writes to global config.
2025-09-15 04:30:56 +00:00
Thibault Sottiaux
a797051921 chore: update swiftfox_prompt.md (#3624) 2025-09-15 04:10:35 +00:00
Ahmed Ibrahim
26f1246a89 Revert "refactor transcript view to handle HistoryCells" (#3614)
Reverts openai/codex#3538
It panics on forking first message. It also calculates the index in a
wrong way.
2025-09-15 03:39:36 +00:00
Eric Traut
900bb01486 When logging in using ChatGPT, make sure to overwrite API key (#3611)
When logging in using ChatGPT using the `codex login` command, a
successful login should write a new `auth.json` file with the ChatGPT
token information. The old code attempted to retain the API key and
merge the token information into the existing `auth.json` file. With the
new simplified login mechanism, `auth.json` should have auth information
for only ChatGPT or API Key, not both.

The `codex login --api-key <key>` code path was already doing the right
thing here, but the `codex login` command was incorrect. This PR fixes
the problem and adds test cases for both commands.
2025-09-14 19:48:18 -07:00
Dylan
b6673838e8 fix: model family and apply_patch consistency (#3603)
## Summary
Resolves a merge conflict between #3597 and #3560, and adds tests to
double check our apply_patch configuration.

## Testing
- [x] Added unit tests

---------

Co-authored-by: dedrisian-oai <dedrisian@openai.com>
2025-09-14 18:20:37 -07:00
Fouad Matin
5185d69f13 fix(core): flaky test completed_commands_do_not_persist_sessions (#3596)
Fix flaky test:
```
        FAIL [   2.641s] codex-core unified_exec::tests::completed_commands_do_not_persist_sessions
  stdout ───

    running 1 test
    test unified_exec::tests::completed_commands_do_not_persist_sessions ... FAILED

    failures:

    failures:
        unified_exec::tests::completed_commands_do_not_persist_sessions

    test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 235 filtered out; finished in 2.63s
    
  stderr ───

    thread 'unified_exec::tests::completed_commands_do_not_persist_sessions' panicked at core/src/unified_exec/mod.rs:582:9:
    assertion failed: result.output.contains("codex")
```
2025-09-14 18:04:05 -07:00
dedrisian-oai
2aa84b8891 Fix EventMsg Optional (#3604) 2025-09-15 00:34:33 +00:00
pakrym-oai
9177bdae5e Only one branch for swiftfox (#3601)
Make each model family have a single branch.
2025-09-14 16:56:22 -07:00
Ahmed Ibrahim
a30e5e40ee enable-resume (#3537)
Adding the ability to resume conversations.
we have one verb `resume`. 

Behavior:

`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`

`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`

Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
2025-09-14 19:33:19 -04:00
dedrisian-oai
b2f6fc3b9a Fix flaky windows test (#3564)
There are exactly 4 types of flaky tests in Windows x86 right now:

1. `review_input_isolated_from_parent_history` => Times out waiting for
closing events
2. `review_does_not_emit_agent_message_on_structured_output` => Times
out waiting for closing events
3. `auto_compact_runs_after_token_limit_hit` => Times out waiting for
closing events
4. `auto_compact_runs_after_token_limit_hit` => Also has a problem where
auto compact should add a third request, but receives 4 requests.

1, 2, and 3 seem to be solved with increasing threads on windows runner
from 2 -> 4.

Don't know yet why # 4 is happening, but probably also because of
WireMock issues on windows causing races.
2025-09-14 23:20:25 +00:00
pakrym-oai
51f88fd04a Fix swiftfox model selector (#3598)
The model shouldn't be saved with a suffix. The effort is a separate
field.
2025-09-14 23:12:21 +00:00
pakrym-oai
916fdc2a37 Add per-model-family prompts (#3597)
Allows more flexibility in defining prompts.
2025-09-14 22:45:15 +00:00
pakrym-oai
863d9c237e Include command output when sending timeout to model (#3576)
Being able to see the output helps the model decide how to handle the
timeout.
2025-09-14 14:38:26 -07:00
Ahmed Ibrahim
bbea6bbf7e Handle resuming/forking after compact (#3533)
We need to construct the history different when compact happens. For
this, we need to just consider the history after compact and convert
compact to a response item.

This needs to change and use `build_compact_history` when this #3446 is
merged.
2025-09-14 13:23:31 +00:00
Jeremy Rose
4891ee29c5 refactor transcript view to handle HistoryCells (#3538)
No (intended) functional change.

This refactors the transcript view to hold a list of HistoryCells
instead of a list of Lines. This simplifies and makes much of the logic
more robust, as well as laying the groundwork for future changes, e.g.
live-updating history cells in the transcript.

Similar to #2879 in goal. Fixes #2755.
2025-09-13 19:23:14 -07:00
Thibault Sottiaux
bac8a427f3 chore: default swiftfox models to experimental reasoning summaries (#3560) 2025-09-13 23:40:54 +00:00