## Summary
In #1939 we overhauled a lot of our prompt. This was largely good, but
we're seeing some specific points of confusion from the model! This
prompt update attempts to address 3 of them:
- Enforcing the use of `ripgrep`, which is bundled as a dependency when
installed with homebrew. We should do the same on node (in progress)
- Explicit guidance on reading files in chunks.
- Slight adjustment to networking sandbox language. `enabled` /
`restricted` is anecdotally less confusing to the model and requires
less reasoning to escalate for approval.
We are going to continue iterating on shell usage and tools, but this
restores us to best practices for current model snapshots.
## Testing
- [x] evals
- [x] local testing
Bumps [clap_complete](https://github.com/clap-rs/clap) from 4.5.55 to
4.5.56.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="9cec1007ac"><code>9cec100</code></a>
chore: Release</li>
<li><a
href="00e72e06f4"><code>00e72e0</code></a>
docs: Update changelog</li>
<li><a
href="c7848ff6fc"><code>c7848ff</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/6094">#6094</a>
from epage/home</li>
<li><a
href="60184fb76a"><code>60184fb</code></a>
feat(complete): Expand ~ in native completions</li>
<li><a
href="09969d3c1a"><code>09969d3</code></a>
chore(deps): Update Rust Stable to v1.89 (<a
href="https://redirect.github.com/clap-rs/clap/issues/6093">#6093</a>)</li>
<li><a
href="520beb5ec2"><code>520beb5</code></a>
chore: Release</li>
<li><a
href="2bd8ab3c00"><code>2bd8ab3</code></a>
docs: Update changelog</li>
<li><a
href="220875b585"><code>220875b</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/6091">#6091</a>
from epage/possible</li>
<li><a
href="e5eb6c9d84"><code>e5eb6c9</code></a>
fix(help): Integrate 'Possible Values:' into 'Arg::help'</li>
<li><a
href="594a771030"><code>594a771</code></a>
refactor(help): Make empty tracking more consistent</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.55...clap_complete-v4.5.56">compare
view</a></li>
</ul>
</details>
<br />
[](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>
[//]: # (dependabot-start)
⚠️ **Dependabot is rebasing this PR** ⚠️
Rebasing might not happen immediately, so don't worry if this takes some
time.
Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.
---
[//]: # (dependabot-end)
Bumps [clap](https://github.com/clap-rs/clap) from 4.5.41 to 4.5.43.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/releases">clap's
releases</a>.</em></p>
<blockquote>
<h2>v4.5.43</h2>
<h2>[4.5.43] - 2025-08-06</h2>
<h3>Fixes</h3>
<ul>
<li><em>(help)</em> In long help, list Possible Values before defaults,
rather than after, for a more consistent look</li>
</ul>
<h2>v4.5.42</h2>
<h2>[4.5.42] - 2025-07-30</h2>
<h3>Fixes</h3>
<ul>
<li>Include subcommand visible long aliases in <code>--help</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/blob/master/CHANGELOG.md">clap's
changelog</a>.</em></p>
<blockquote>
<h2>[4.5.43] - 2025-08-06</h2>
<h3>Fixes</h3>
<ul>
<li><em>(help)</em> In long help, list Possible Values before defaults,
rather than after, for a more consistent look</li>
</ul>
<h2>[4.5.42] - 2025-07-30</h2>
<h3>Fixes</h3>
<ul>
<li>Include subcommand visible long aliases in <code>--help</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c4105bd90c"><code>c4105bd</code></a>
chore: Release</li>
<li><a
href="a029b20be6"><code>a029b20</code></a>
docs: Update changelog</li>
<li><a
href="cf15d48b59"><code>cf15d48</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5893">#5893</a>
from 8LWXpg/patch-2</li>
<li><a
href="7e54542de9"><code>7e54542</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5892">#5892</a>
from 8LWXpg/patch-1</li>
<li><a
href="6ffc88f8c9"><code>6ffc88f</code></a>
fix(complete): Check if help string is empty</li>
<li><a
href="7d8470ed9c"><code>7d8470e</code></a>
fix(complete): Fix single quote escaping in PowerShell</li>
<li><a
href="eadcc8f66c"><code>eadcc8f</code></a>
chore: Release</li>
<li><a
href="7ce0f7bea3"><code>7ce0f7b</code></a>
docs: Update changelog</li>
<li><a
href="fea7c5487b"><code>fea7c54</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5888">#5888</a>
from epage/tut</li>
<li><a
href="c297ddd56e"><code>c297ddd</code></a>
docs(tutorial): Experiment with a flat layout</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.41...clap_complete-v4.5.43">compare
view</a></li>
</ul>
</details>
<br />
[](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>
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.4 to 0.9.5.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="bd21148c49"><code>bd21148</code></a>
chore: Release</li>
<li><a
href="ff1cb9a263"><code>ff1cb9a</code></a>
docs: Update changelog</li>
<li><a
href="39dd8b6422"><code>39dd8b6</code></a>
fix(parser): Improve bad quote error messages (<a
href="https://redirect.github.com/toml-rs/toml/issues/1014">#1014</a>)</li>
<li><a
href="137338eb26"><code>137338e</code></a>
chore(deps): Update Rust crate serde_json to v1.0.142 (<a
href="https://redirect.github.com/toml-rs/toml/issues/1022">#1022</a>)</li>
<li><a
href="d5b8c8a94e"><code>d5b8c8a</code></a>
fix(parser): Improve missing-open-quote errors</li>
<li><a
href="ce91354fc7"><code>ce91354</code></a>
fix(parser): Don't treat trailing quotes as separate items</li>
<li><a
href="8f424edd08"><code>8f424ed</code></a>
fix(parser): Conjoin more values in unquoted string errors</li>
<li><a
href="2b9a81ae79"><code>2b9a81a</code></a>
fix(parser): Reduce float false positives</li>
<li><a
href="f6538413bb"><code>f653841</code></a>
fix(parser): Reduce float/bool false positives</li>
<li><a
href="f4864ef34b"><code>f4864ef</code></a>
test(parser): Add case for missing start quote</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.4...toml-v0.9.5">compare
view</a></li>
</ul>
</details>
<br />
[](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>
Moves `use codex_core::protocol::EventMsg` inside the block annotated
with `#[cfg(debug_assertions)]` since that was the only place in the
file that was using it.
This eliminates the `warning: unused import:` when building with `cargo
build --release` in `cargo-rs/tui`.
Note this was not breaking CI because we do not build release builds on
CI since we're impatient :P
## Summary
Our current approach to prompt caching is fragile! The current approach
works, but we are planning to update to a more resilient system (storing
them in the rollout file). Let's start adding some integration tests to
ensure stability while we migrate it.
## Testing
- [x] These are the tests 😎
## Summary
GPT-OSS and `gpt-5-mini` have training artifacts that cause the models
to occasionally use `applypatch` instead of `apply_patch`. I think
long-term we'll want to provide `apply_patch` as a first class tool, but
for now let's silently handle this case to avoid hurting model
performance
## Testing
- [x] Added unit test
Right now, every time an exec ends, we emit it to history which makes it
immutable. In order to be able to update or merge successive tool calls
(which will be useful after https://github.com/openai/codex/pull/2095),
we need to retain it as the active cell.
This also changes the cell to contain the metadata necessary to render
it so it can be updated rather than baking in the final text lines when
the cell is created.
Part 1: https://github.com/openai/codex/pull/2095
Part 3: https://github.com/openai/codex/pull/2110
## Summary
#1865 added `AskForApproval::OnRequest`, but missed adding it to our
custom struct in `mcp-server`. This adds the missing configuration
## Testing
- [x] confirmed locally
# Note for reviewers
The bulk of this PR is in in the new file, `parse_command.rs`. This file
is designed to be written TDD and implemented with Codex. Do not worry
about reviewing the code, just review the unit tests (if you want). If
any cases are missing, we'll add more tests and have Codex fix them.
I think the best approach will be to land and iterate. I have some
follow-ups I want to do after this lands. The next PR after this will
let us merge (and dedupe) multiple sequential cells of the same such as
multiple read commands. The deduping will also be important because the
model often reads the same file multiple times in a row in chunks
===
This PR formats common commands like reading, formatting, testing, etc
more nicely:
It tries to extract things like file names, tests and falls back to the
cmd if it doesn't. It also only shows stdout/err if the command failed.
<img width="770" height="238" alt="CleanShot 2025-08-09 at 16 05 15"
src="https://github.com/user-attachments/assets/0ead179a-8910-486b-aa3d-7d26264d751e"
/>
<img width="348" height="158" alt="CleanShot 2025-08-09 at 16 05 32"
src="https://github.com/user-attachments/assets/4302681b-5e87-4ff3-85b4-0252c6c485a9"
/>
<img width="834" height="324" alt="CleanShot 2025-08-09 at 16 05 56 2"
src="https://github.com/user-attachments/assets/09fb3517-7bd6-40f6-a126-4172106b700f"
/>
Part 2: https://github.com/openai/codex/pull/2097
Part 3: https://github.com/openai/codex/pull/2110
This PR updates ChatWidget to ensure that when AgentMessage,
AgentReasoning, or AgentReasoningRawContent events arrive without any
streamed deltas, the final text from the event is rendered before the
stream is finalized. Previously, these handlers ignored the event text
in such cases, relying solely on prior deltas.
<img width="603" height="189" alt="image"
src="https://github.com/user-attachments/assets/868516f2-7963-4603-9af4-adb1b1eda61e"
/>
Bumps [tokio-util](https://github.com/tokio-rs/tokio) from 0.7.15 to
0.7.16.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="cf6b50a3fd"><code>cf6b50a</code></a>
chore: prepare tokio-util v0.7.16 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7507">#7507</a>)</li>
<li><a
href="416e36b0df"><code>416e36b</code></a>
task: stabilise <code>JoinMap</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7075">#7075</a>)</li>
<li><a
href="9741c90f9f"><code>9741c90</code></a>
sync: document cancel safety on <code>SetOnce::wait</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7506">#7506</a>)</li>
<li><a
href="4e3f17bce3"><code>4e3f17b</code></a>
codec: also apply capacity to read buffer in
<code>Framed::with_capacity</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7500">#7500</a>)</li>
<li><a
href="86cbf81e15"><code>86cbf81</code></a>
Merge 'tokio-1.47.1' into 'master'</li>
<li><a
href="be8ee45b3f"><code>be8ee45</code></a>
chore: prepare Tokio v1.47.1 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7504">#7504</a>)</li>
<li><a
href="d9b19166cd"><code>d9b1916</code></a>
Merge 'tokio-1.43.2' into 'tokio-1.47.x' (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7503">#7503</a>)</li>
<li><a
href="db8edc620f"><code>db8edc6</code></a>
chore: prepare Tokio v1.43.2 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7502">#7502</a>)</li>
<li><a
href="e47565b086"><code>e47565b</code></a>
blocking: clarify that spawn_blocking is aborted if not yet started (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7501">#7501</a>)</li>
<li><a
href="4730984d66"><code>4730984</code></a>
readme: add 1.47 as LTS release (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7497">#7497</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/tokio-rs/tokio/compare/tokio-util-0.7.15...tokio-util-0.7.16">compare
view</a></li>
</ul>
</details>
<br />
[](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>
- I had a recent conversation where the one-liner showed using 11M
tokens! But looking into it 10M were cached. So I looked into it and I
think we had a regression here. ->
- Use blended total tokens for chat composer usage display
- Compute remaining context using tokens_in_context_window helper
------
https://chatgpt.com/codex/tasks/task_i_68981a16c0a4832cbf416017390930e5
## Summary
- allow Esc to interrupt the current session when a task is running
- document Esc as an interrupt key in status indicator
## Testing
- `just fmt`
- `just fix` *(fails: E0658 `let` expressions in this position are
unstable)*
- `cargo test --all-features` *(fails: E0658 `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689698cf605883208f57b0317ff6a303
## Summary
Allow tui conversations to resume after the client fails out of retries.
I tested this with exec / mocked api failures as well, and it appears to
be fine. But happy to add an exec integration test as well!
## Testing
- [x] Added integration test
- [x] Tested locally
## Summary
From codex-cli 😁
`-s/--sandbox` now correctly affects sandbox mode.
What changed
- In `codex-rs/exec/src/cli.rs`:
- Added `value_enum` to the `--sandbox` flag so Clap parses enum values
into `
SandboxModeCliArg`.
- This ensures values like `-s read-only`, `-s workspace-write`, and `-s
dange
r-full-access` are recognized and propagated.
Why this fixes it
- The enum already derives `ValueEnum`, but without `#[arg(value_enum)]`
Clap ma
y not map the string into the enum, leaving the option ineffective at
runtime. W
ith `value_enum`, `sandbox_mode` is parsed and then converted to
`SandboxMode` i
n `run_main`, which feeds into `ConfigOverrides` and ultimately into the
effecti
ve `sandbox_policy`.
This pull request implements a fix from #2000, as well as fixed an
additional problem with path lengths on windows that prevents the login
from displaying.
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Summary
- fix typo in usage limit banner text
- update error message tests
## Testing
- `just fmt`
- `RUSTC_BOOTSTRAP=1 just fix` *(fails: `let` expressions in this
position are unstable)*
- `RUSTC_BOOTSTRAP=1 cargo test --all-features` *(fails: `let`
expressions in this position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689610fc1fe4832081bdd1118779b60b
We wait until we have an entire newline, then format it with markdown and stream in to the UI. This reduces time to first token but is the right thing to do with our current rendering model IMO. Also lets us add word wrapping!
Uses this rough strategy for authentication:
```
if auth.json
if auth.json.API_KEY is NULL # new auth
CHAT
else # old auth
if plus or pro or team
CHAT
else
API_KEY
else OPENAI_API_KEY
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1970).
* __->__ #1971
* #1970
* #1966
* #1965
* #1962
There are two valid ways to create an instance of `CodexAuth`:
`from_api_key()` and `from_codex_home()`. Now both are static methods of
`CodexAuth` and are listed first in the implementation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1966).
* #1971
* #1970
* __->__ #1966
* #1965
* #1962
`CodexAuth::new()` was the first method listed in `CodexAuth`, but it is
only meant to be used by tests. Rename it to
`create_dummy_chatgpt_auth_for_testing()` and move it to the end of the
implementation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1962).
* #1971
* #1970
* #1966
* #1965
* __->__ #1962
