mirror of
https://github.com/openai/codex.git
synced 2026-04-28 16:45:54 +00:00
b4e9baaaff468ba1c18c8039b0f60a73895d2142
214 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
jif-oai
|
f304b2ef62 | feat: bind package manager (#13571) | ||
|
dependabot[bot]
|
95aad8719f |
chore(deps): bump serde_with from 3.16.1 to 3.17.0 in /codex-rs (#13209)
Bumps [serde_with](https://github.com/jonasbb/serde_with) from 3.16.1 to 3.17.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/jonasbb/serde_with/releases">serde_with's releases</a>.</em></p> <blockquote> <h2>serde_with v3.17.0</h2> <h3>Added</h3> <ul> <li>Support <code>OneOrMany</code> with <code>smallvec</code> v1 (<a href="https://redirect.github.com/jonasbb/serde_with/issues/920">#920</a>, <a href="https://redirect.github.com/jonasbb/serde_with/issues/922">#922</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Switch to <code>yaml_serde</code> for a maintained yaml dependency by <a href="https://github.com/kazan417"><code>@kazan417</code></a> (<a href="https://redirect.github.com/jonasbb/serde_with/issues/921">#921</a>)</li> <li>Bump MSRV to 1.82, since that is required for <code>yaml_serde</code> dev-dependency.</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
14ac823aef |
chore(deps): bump strum_macros from 0.27.2 to 0.28.0 in /codex-rs (#13210)
Bumps [strum_macros](https://github.com/Peternator7/strum) from 0.27.2 to 0.28.0. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/Peternator7/strum/blob/master/CHANGELOG.md">strum_macros's changelog</a>.</em></p> <blockquote> <h2>0.28.0</h2> <ul> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/461">#461</a>: Allow any kind of passthrough attributes on <code>EnumDiscriminants</code>.</p> <ul> <li>Previously only list-style attributes (e.g. <code>#[strum_discriminants(derive(...))]</code>) were supported. Now path-only (e.g. <code>#[strum_discriminants(non_exhaustive)]</code>) and name/value (e.g. <code>#[strum_discriminants(doc = "foo")]</code>) attributes are also supported.</li> </ul> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/462">#462</a>: Add missing <code>#[automatically_derived]</code> to generated impls not covered by <a href="https://redirect.github.com/Peternator7/strum/pull/444">#444</a>.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/466">#466</a>: Bump MSRV to 1.71, required to keep up with updated <code>syn</code> and <code>windows-sys</code> dependencies. This is a breaking change if you're on an old version of rust.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/469">#469</a>: Use absolute paths in generated proc macro code to avoid potential name conflicts.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/465">#465</a>: Upgrade <code>phf</code> dependency to v0.13.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/473">#473</a>: Fix <code>cargo fmt</code> / <code>clippy</code> issues and add GitHub Actions CI.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/477">#477</a>: <code>strum::ParseError</code> now implements <code>core::fmt::Display</code> instead <code>std::fmt::Display</code> to make it <code>#[no_std]</code> compatible. Note the <code>Error</code> trait wasn't available in core until <code>1.81</code> so <code>strum::ParseError</code> still only implements that in std.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/476">#476</a>: <strong>Breaking Change</strong> - <code>EnumString</code> now implements <code>From<&str></code> (infallible) instead of <code>TryFrom<&str></code> when the enum has a <code>#[strum(default)]</code> variant. This more accurately reflects that parsing cannot fail in that case. If you need the old <code>TryFrom</code> behavior, you can opt back in using <code>parse_error_ty</code> and <code>parse_error_fn</code>:</p> <pre lang="rust"><code>#[derive(EnumString)] #[strum(parse_error_ty = strum::ParseError, parse_error_fn = make_error)] pub enum Color { Red, #[strum(default)] Other(String), } <p>fn make_error(x: &str) -> strum::ParseError { strum::ParseError::VariantNotFound } </code></pre></p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/431">#431</a>: Fix bug where <code>EnumString</code> ignored the <code>parse_err_ty</code> attribute when the enum had a <code>#[strum(default)]</code> variant.</p> </li> <li> <p><a href="https://redirect.github.com/Peternator7/strum/pull/474">#474</a>: EnumDiscriminants will now copy <code>default</code> over from the original enum to the Discriminant enum.</p> <pre lang="rust"><code>#[derive(Debug, Default, EnumDiscriminants)] #[strum_discriminants(derive(Default))] // <- Remove this in 0.28. enum MyEnum { #[default] // <- Will be the #[default] on the MyEnumDiscriminant #[strum_discriminants(default)] // <- Remove this in 0.28 Variant0, Variant1 { a: NonDefault }, } </code></pre> </li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
jif-oai
|
2322e49549 |
feat: external artifacts builder (#13485)
This PR reverts the built-in artifact render while a decision is being reached. No impact expected on any features |
||
|
jif-oai
|
8c5e50ef39 | feat: spreadsheet artifact (#13345) | ||
|
jif-oai
|
4874b9291a |
feat: presentation artifact p1 (#13341)
Part 1 of presentation tool artifact |
||
|
Celia Chen
|
90cc4e79a2 |
feat: add local date/timezone to turn environment context (#12947)
## Summary
This PR includes the session's local date and timezone in the
model-visible environment context and persists that data in
`TurnContextItem`.
## What changed
- captures the current local date and IANA timezone when building a turn
context, with a UTC fallback if the timezone lookup fails
- includes current_date and timezone in the serialized
<environment_context> payload
- stores those fields on TurnContextItem so they survive rollout/history
handling, subagent review threads, and resume flows
- treats date/timezone changes as environment updates, so prompt caching
and context refresh logic do not silently reuse stale time context
- updates tests to validate the new environment fields without depending
on a single hardcoded environment-context string
## test
built a local build and saw it in the rollout file:
```
{"timestamp":"2026-02-26T21:39:50.737Z","type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"<environment_context>\n <shell>zsh</shell>\n <current_date>2026-02-26</current_date>\n <timezone>America/Los_Angeles</timezone>\n</environment_context>"}]}}
```
|
||
|
pakrym-oai
|
1503a8dad7 |
split-debuginfo (#12871)
Attempt to reduce disk usage in mac ci. >off - This is the default for platforms with ELF binaries and windows-gnu (not Windows MSVC and not macOS). This typically means that DWARF debug information can be found in the final artifact in sections of the executable. This option is not supported on Windows MSVC. On macOS this options prevents the final execution of dsymutil to generate debuginfo. |
||
|
jif-oai
|
7b39e76a66 |
Revert "fix(bazel): replace askama templates with include_str! in memories" (#12795)
Reverts openai/codex#11778 |
||
|
mcgrew-oai
|
bccce0d75f |
otel: add host.name resource attribute to logs/traces via gethostname (#12352)
**PR Summary**
This PR adds the OpenTelemetry `host.name` resource attribute to Codex
OTEL exports so every OTEL log (and trace, via the shared resource)
carries the machine hostname.
**What changed**
- Added `host.name` to the shared OTEL `Resource` in
`/Users/michael.mcgrew/code/codex/codex-rs/otel/src/otel_provider.rs`
- This applies to both:
- OTEL logs (`SdkLoggerProvider`)
- OTEL traces (`SdkTracerProvider`)
- Hostname is now resolved via `gethostname::gethostname()`
(best-effort)
- Value is trimmed
- Empty values are omitted (non-fatal)
- Added focused unit tests for:
- including `host.name` when present
- omitting `host.name` when missing/empty
**Why**
- `host.name` is host/process metadata and belongs on the OTEL
`resource`, not per-event attributes.
- Attaching it in the shared resource is the smallest change that
guarantees coverage across all exported OTEL logs/traces.
**Scope / Non-goals**
- No public API changes
- No changes to metrics behavior (this PR only updates log/trace
resource metadata)
**Dependency updates**
- Added `gethostname` as a workspace dependency and `codex-otel`
dependency
- `Cargo.lock` updated accordingly
- `MODULE.bazel.lock` unchanged after refresh/check
**Validation**
- `just fmt`
- `cargo test -p codex-otel`
- `just bazel-lock-update`
- `just bazel-lock-check`
|
||
|
jif-oai
|
5441130e0a |
feat: adding stream parser (#12666)
Add a stream parser to extract citations (and others) from a stream. This support cases where markers are split in differen tokens. Codex never manage to make this code work so everything was done manually. Please review correctly and do not touch this part of the code without a very clear understanding of it |
||
|
jif-oai
|
5a9a5b51b2 |
feat: add large stack test macro (#12768)
This PR adds the macro `#[large_stack_test]` This spawns the tests in a dedicated tokio runtime with a larger stack. It is useful for tests that needs the full recursion on the harness (which is now too deep for windows for example) |
||
|
daveaitel-openai
|
dcab40123f |
Agent jobs (spawn_agents_on_csv) + progress UI (#10935)
## Summary - Add agent job support: spawn a batch of sub-agents from CSV, auto-run, auto-export, and store results in SQLite. - Simplify workflow: remove run/resume/get-status/export tools; spawn is deterministic and completes in one call. - Improve exec UX: stable, single-line progress bar with ETA; suppress sub-agent chatter in exec. ## Why Enables map-reduce style workflows over arbitrarily large repos using the existing Codex orchestrator. This addresses review feedback about overly complex job controls and non-deterministic monitoring. ## Demo (progress bar) ``` ./codex-rs/target/debug/codex exec \ --enable collab \ --enable sqlite \ --full-auto \ --progress-cursor \ -c agents.max_threads=16 \ -C /Users/daveaitel/code/codex \ - <<'PROMPT' Create /tmp/agent_job_progress_demo.csv with columns: path,area and 30 rows: path = item-01..item-30, area = test. Then call spawn_agents_on_csv with: - csv_path: /tmp/agent_job_progress_demo.csv - instruction: "Run `python - <<'PY'` to sleep a random 0.3–1.2s, then output JSON with keys: path, score (int). Set score = 1." - output_csv_path: /tmp/agent_job_progress_demo_out.csv PROMPT ``` ## Review feedback addressed - Auto-start jobs on spawn; removed run/resume/status/export tools. - Auto-export on success. - More descriptive tool spec + clearer prompts. - Avoid deadlocks on spawn failure; pending/running handled safely. - Progress bar no longer scrolls; stable single-line redraw. ## Tests - `cd codex-rs && cargo test -p codex-exec` - `cd codex-rs && cargo build -p codex-cli` |
||
|
Michael Bolin
|
3ca0e7673b |
feat: run zsh fork shell tool via shell-escalation (#12649)
## Why This PR switches the `shell_command` zsh-fork path over to `codex-shell-escalation` so the new shell tool can use the shared exec-wrapper/escalation protocol instead of the `zsh_exec_bridge` implementation that was introduced in https://github.com/openai/codex/pull/12052. `zsh_exec_bridge` relied on UNIX domain sockets, which is not as tamper-proof as the FD-based approach in `codex-shell-escalation`. ## What Changed - Added a Unix zsh-fork runtime adapter in `core` (`core/src/tools/runtimes/shell/unix_escalation.rs`) that: - runs zsh-fork commands through `codex_shell_escalation::run_escalate_server` - bridges exec-policy / approval decisions into `ShellActionProvider` - executes escalated commands via a `ShellCommandExecutor` that calls `process_exec_tool_call` - Updated `ShellRuntime` / `ShellCommandHandler` / tool spec wiring to select a `shell_command` backend (`classic` vs `zsh-fork`) while leaving the generic `shell` tool path unchanged. - Removed the `zsh_exec_bridge`-based session service and deleted `core/src/zsh_exec_bridge/mod.rs`. - Moved exec-wrapper entrypoint dispatch to `arg0` by handling the `codex-execve-wrapper` arg0 alias there, and removed the old `codex_core::maybe_run_zsh_exec_wrapper_mode()` hooks from `cli` and `app-server` mains. - Added the needed `codex-shell-escalation` dependencies for `core` and `arg0`. ## Tests - `cargo test -p codex-core shell_zsh_fork_prefers_shell_command_over_unified_exec` - `cargo test -p codex-app-server turn_start_shell_zsh_fork -- --nocapture` - verifies zsh-fork command execution and approval flows through the new backend - includes subcommand approve/decline coverage using the shared zsh DotSlash fixture in `app-server/tests/suite/zsh` - To test manually, I added the following to `~/.codex/config.toml`: ```toml zsh_path = "/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh" [features] shell_zsh_fork = true ``` Then I ran `just c` to run the dev build of Codex with these changes and sent it the message: ``` run `echo $0` ``` And it replied with: ``` echo $0 printed: /Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh In this tool context, $0 reflects the script path used to invoke the shell, not just zsh. ``` so the tool appears to be wired up correctly. ## Notes - The zsh subcommand-decline integration test now uses `rm` under a `WorkspaceWrite` sandbox. The previous `/usr/bin/true` scenario is auto-allowed by the new `shell-escalation` policy path, which no longer produces subcommand approval prompts. |
||
|
sayan-oai
|
7e46e5b9c2 |
chore: rm hardcoded PRESETS list (#12650)
rm `PRESETS` list harcoded in `model_presets` as we now have bundled `models.json` with equivalent info. update logic to rely on bundled models instead, update tests. |
||
|
Michael Bolin
|
38f84b6b29 |
refactor: delete exec-server and move execve wrapper into shell-escalation (#12632)
## Why We already plan to remove the shell-tool MCP path, and doing that cleanup first makes the follow-on `shell-escalation` work much simpler. This change removes the last remaining reason to keep `codex-rs/exec-server` around by moving the `codex-execve-wrapper` binary and shared shell test fixtures to the crates/tests that now own that functionality. ## What Changed ### Delete `codex-rs/exec-server` - Remove the `exec-server` crate, including the MCP server binary, MCP-specific modules, and its test support/test suite - Remove `exec-server` from the `codex-rs` workspace and update `Cargo.lock` ### Move `codex-execve-wrapper` into `codex-rs/shell-escalation` - Move the wrapper implementation into `shell-escalation` (`src/unix/execve_wrapper.rs`) - Add the `codex-execve-wrapper` binary entrypoint under `shell-escalation/src/bin/` - Update `shell-escalation` exports/module layout so the wrapper entrypoint is hosted there - Move the wrapper README content from `exec-server` to `shell-escalation/README.md` ### Move shared shell test fixtures to `app-server` - Move the DotSlash `bash`/`zsh` test fixtures from `exec-server/tests/suite/` to `app-server/tests/suite/` - Update `app-server` zsh-fork tests to reference the new fixture paths ### Keep `shell-tool-mcp` as a shell-assets package - Update `.github/workflows/shell-tool-mcp.yml` packaging so the npm artifact contains only patched Bash/Zsh payloads (no Rust binaries) - Update `shell-tool-mcp/package.json`, `shell-tool-mcp/src/index.ts`, and docs to reflect the shell-assets-only package shape - `shell-tool-mcp-ci.yml` does not need changes because it is already JS-only ## Verification - `cargo shear` - `cargo clippy -p codex-shell-escalation --tests` - `just clippy` |
||
|
dependabot[bot]
|
cd5acf6af7 |
chore(deps): bump owo-colors from 4.2.3 to 4.3.0 in /codex-rs (#12530)
Bumps [owo-colors](https://github.com/owo-colors/owo-colors) from 4.2.3 to 4.3.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/owo-colors/owo-colors/releases">owo-colors's releases</a>.</em></p> <blockquote> <h2>owo-colors 4.3.0</h2> <h3>Fixed</h3> <ul> <li>Scripts in the <code>scripts/</code> directory are no longer published in the crate package. Thanks <a href="https://redirect.github.com/owo-colors/owo-colors/pull/152">weiznich</a> for your first contribution!</li> </ul> <h3>Changed</h3> <ul> <li> <p>Mark methods with <code>#[rust_analyzer::completions(ignore_flyimport)]</code> and the <code>OwoColorize</code> trait with <code>#[rust_analyzer::completions(ignore_flyimport_methods)]</code>. This prevents owo-colors methods from being completed with rust-analyzer unless the <code>OwoColorize</code> trait is included.</p> <p>Unfortunately, this also breaks explicit autocomplete commands such as Ctrl-Space in many editors. (The language server protocol doesn't appear to have a way to differentiate between implicit and explicit autocomplete commands.) On balance we believe this is the right approach, but please do provide feedback on [PR <a href="https://redirect.github.com/owo-colors/owo-colors/issues/141">#141</a>](<a href="https://redirect.github.com/owo-colors/owo-colors/pull/141">owo-colors/owo-colors#141</a>) if it negatively affects you.</p> </li> <li> <p>Updated MSRV to Rust 1.81.</p> </li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/owo-colors/owo-colors/blob/main/CHANGELOG.md">owo-colors's changelog</a>.</em></p> <blockquote> <h2>[4.3.0] - 2026-02-22</h2> <h3>Fixed</h3> <ul> <li>Scripts in the <code>scripts/</code> directory are no longer published in the crate package. Thanks <a href="https://redirect.github.com/owo-colors/owo-colors/pull/152">weiznich</a> for your first contribution!</li> </ul> <h3>Changed</h3> <ul> <li> <p>Mark methods with <code>#[rust_analyzer::completions(ignore_flyimport)]</code> and the <code>OwoColorize</code> trait with <code>#[rust_analyzer::completions(ignore_flyimport_methods)]</code>. This prevents owo-colors methods from being completed with rust-analyzer unless the <code>OwoColorize</code> trait is included.</p> <p>Unfortunately, this also breaks explicit autocomplete commands such as Ctrl-Space in many editors. (The language server protocol doesn't appear to have a way to differentiate between implicit and explicit autocomplete commands.) On balance we believe this is the right approach, but please do provide feedback on [PR <a href="https://redirect.github.com/owo-colors/owo-colors/issues/141">#141</a>](<a href="https://redirect.github.com/owo-colors/owo-colors/pull/141">owo-colors/owo-colors#141</a>) if it negatively affects you.</p> </li> <li> <p>Updated MSRV to Rust 1.81.</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
5c52ef8e60 |
chore(deps): bump libc from 0.2.180 to 0.2.182 in /codex-rs (#12528)
Bumps [libc](https://github.com/rust-lang/libc) from 0.2.180 to 0.2.182. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/rust-lang/libc/releases">libc's releases</a>.</em></p> <blockquote> <h2>0.2.182</h2> <h3>Added</h3> <ul> <li>Android, Linux: Add <code>tgkill</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4970">#4970</a>)</li> <li>Redox: Add <code>RENAME_NOREPLACE</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4968">#4968</a>)</li> <li>Redox: Add <code>renameat2</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4968">#4968</a>)</li> </ul> <h2>0.2.181</h2> <h3>Added</h3> <ul> <li>Apple: Add <code>MADV_ZERO</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4924">#4924</a>)</li> <li>Redox: Add <code>makedev</code>, <code>major</code>, and <code>minor</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4928">#4928</a>)</li> <li>GLibc: Add <code>PTRACE_SET_SYSCALL_INFO</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4933">#4933</a>)</li> <li>OpenBSD: Add more kqueue related constants for (<a href="https://redirect.github.com/rust-lang/libc/pull/4945">#4945</a>)</li> <li>Linux: add CAN error types (<a href="https://redirect.github.com/rust-lang/libc/pull/4944">#4944</a>)</li> <li>OpenBSD: Add siginfo_t::si_status (<a href="https://redirect.github.com/rust-lang/libc/pull/4946">#4946</a>)</li> <li>QNX NTO: Add <code>max_align_t</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4927">#4927</a>)</li> <li>Illumos: Add <code>_CS_PATH</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4956">#4956</a>)</li> <li>OpenBSD: add <code>ppoll</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4957">#4957</a>)</li> </ul> <h3>Fixed</h3> <ul> <li><strong>Breaking</strong>: Redox: Fix the type of <code>dev_t</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4928">#4928</a>)</li> <li>AIX: Change 'tv_nsec' of 'struct timespec' to type 'c_long' (<a href="https://redirect.github.com/rust-lang/libc/pull/4931">#4931</a>)</li> <li>AIX: Use 'struct st_timespec' in 'struct stat{,64}' (<a href="https://redirect.github.com/rust-lang/libc/pull/4931">#4931</a>)</li> <li>Glibc: Link old version of <code>tc{g,s}etattr</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4938">#4938</a>)</li> <li>Glibc: Link the correct version of <code>cf{g,s}et{i,o}speed</code> on mips{32,64}r6 (<a href="https://redirect.github.com/rust-lang/libc/pull/4938">#4938</a>)</li> <li>OpenBSD: Fix constness of tm.tm_zone (<a href="https://redirect.github.com/rust-lang/libc/pull/4948">#4948</a>)</li> <li>OpenBSD: Fix the definition of <code>ptrace_thread_state</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4947">#4947</a>)</li> <li>QuRT: Fix type visibility and defs (<a href="https://redirect.github.com/rust-lang/libc/pull/4932">#4932</a>)</li> <li>Redox: Fix values for <code>PTHREAD_MUTEX_{NORMAL, RECURSIVE}</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4943">#4943</a>)</li> <li>Various: Mark additional fields as private padding (<a href="https://redirect.github.com/rust-lang/libc/pull/4922">#4922</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Fuchsia: Update <code>SO_*</code> constants (<a href="https://redirect.github.com/rust-lang/libc/pull/4937">#4937</a>)</li> <li>Revert "musl: convert inline timespecs to timespec" (resolves build issues on targets only supported by Musl 1.2.3+ ) (<a href="https://redirect.github.com/rust-lang/libc/pull/4958">#4958</a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/rust-lang/libc/blob/0.2.182/CHANGELOG.md">libc's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/rust-lang/libc/compare/0.2.181...0.2.182">0.2.182</a> - 2026-02-13</h2> <h3>Added</h3> <ul> <li>Android, Linux: Add <code>tgkill</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4970">#4970</a>)</li> <li>Redox: Add <code>RENAME_NOREPLACE</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4968">#4968</a>)</li> <li>Redox: Add <code>renameat2</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4968">#4968</a>)</li> </ul> <h2><a href="https://github.com/rust-lang/libc/compare/0.2.180...0.2.181">0.2.181</a> - 2026-02-09</h2> <h3>Added</h3> <ul> <li>Apple: Add <code>MADV_ZERO</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4924">#4924</a>)</li> <li>Redox: Add <code>makedev</code>, <code>major</code>, and <code>minor</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4928">#4928</a>)</li> <li>GLibc: Add <code>PTRACE_SET_SYSCALL_INFO</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4933">#4933</a>)</li> <li>OpenBSD: Add more kqueue related constants for (<a href="https://redirect.github.com/rust-lang/libc/pull/4945">#4945</a>)</li> <li>Linux: add CAN error types (<a href="https://redirect.github.com/rust-lang/libc/pull/4944">#4944</a>)</li> <li>OpenBSD: Add siginfo_t::si_status (<a href="https://redirect.github.com/rust-lang/libc/pull/4946">#4946</a>)</li> <li>QNX NTO: Add <code>max_align_t</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4927">#4927</a>)</li> <li>Illumos: Add <code>_CS_PATH</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4956">#4956</a>)</li> <li>OpenBSD: add <code>ppoll</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4957">#4957</a>)</li> </ul> <h3>Fixed</h3> <ul> <li><strong>breaking</strong>: Redox: Fix the type of dev_t (<a href="https://redirect.github.com/rust-lang/libc/pull/4928">#4928</a>)</li> <li>AIX: Change 'tv_nsec' of 'struct timespec' to type 'c_long' (<a href="https://redirect.github.com/rust-lang/libc/pull/4931">#4931</a>)</li> <li>AIX: Use 'struct st_timespec' in 'struct stat{,64}' (<a href="https://redirect.github.com/rust-lang/libc/pull/4931">#4931</a>)</li> <li>Glibc: Link old version of <code>tc{g,s}etattr</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4938">#4938</a>)</li> <li>Glibc: Link the correct version of <code>cf{g,s}et{i,o}speed</code> on mips{32,64}r6 (<a href="https://redirect.github.com/rust-lang/libc/pull/4938">#4938</a>)</li> <li>OpenBSD: Fix constness of tm.tm_zone (<a href="https://redirect.github.com/rust-lang/libc/pull/4948">#4948</a>)</li> <li>OpenBSD: Fix the definition of <code>ptrace_thread_state</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4947">#4947</a>)</li> <li>QuRT: Fix type visibility and defs (<a href="https://redirect.github.com/rust-lang/libc/pull/4932">#4932</a>)</li> <li>Redox: Fix values for <code>PTHREAD_MUTEX_{NORMAL, RECURSIVE}</code> (<a href="https://redirect.github.com/rust-lang/libc/pull/4943">#4943</a>)</li> <li>Various: Mark additional fields as private padding (<a href="https://redirect.github.com/rust-lang/libc/pull/4922">#4922</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Fuchsia: Update <code>SO_*</code> constants (<a href="https://redirect.github.com/rust-lang/libc/pull/4937">#4937</a>)</li> <li>Revert "musl: convert inline timespecs to timespec" (resolves build issues on targets only supported by Musl 1.2.3+ ) (<a href="https://redirect.github.com/rust-lang/libc/pull/4958">#4958</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Michael Bolin
|
5221575f23 |
refactor: normalize unix module layout for exec-server and shell-escalation (#12556)
## Why Shell execution refactoring in `exec-server` had become split between duplicated code paths, which blocked a clean introduction of the new reusable shell escalation flow. This commit creates a dedicated foundation crate so later shell tooling changes can share one implementation. ## What changed - Added the `codex-shell-escalation` crate and moved the core escalation pieces (`mcp` protocol/socket/session flow, policy glue) that were previously in `exec-server` into it. - Normalized `exec-server` Unix structure under a dedicated `unix` module layout and kept non-Unix builds narrow. - Wired crate/build metadata so `shell-escalation` is a first-class workspace dependency for follow-on integration work. ## Verification - Built and linted the stack at this commit point with `just clippy`. [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/openai/codex/pull/12556). * #12584 * #12583 * __->__ #12556 |
||
|
Felipe Coury
|
c4f1af7a86 |
feat(tui): syntax highlighting via syntect with theme picker (#11447)
## Summary Adds syntax highlighting to the TUI for fenced code blocks in markdown responses and file diffs, plus a `/theme` command with live preview and persistent theme selection. Uses syntect (~250 grammars, 32 bundled themes, ~1 MB binary cost) — the same engine behind `bat`, `delta`, and `xi-editor`. Includes guardrails for large inputs, graceful fallback to plain text, and SSH-aware clipboard integration for the `/copy` command. <img width="1554" height="1014" alt="image" src="https://github.com/user-attachments/assets/38737a79-8717-4715-b857-94cf1ba59b85" /> <img width="2354" height="1374" alt="image" src="https://github.com/user-attachments/assets/25d30a00-c487-4af8-9cb6-63b0695a4be7" /> ## Problem Code blocks in the TUI (markdown responses and file diffs) render without syntax highlighting, making it hard to scan code at a glance. Users also have no way to pick a color theme that matches their terminal aesthetic. ## Mental model The highlighting system has three layers: 1. **Syntax engine** (`render::highlight`) -- a thin wrapper around syntect + two-face. It owns a process-global `SyntaxSet` (~250 grammars) and a `RwLock<Theme>` that can be swapped at runtime. All public entry points accept `(code, lang)` and return ratatui `Span`/`Line` vectors or `None` when the language is unrecognized or the input exceeds safety guardrails. 2. **Rendering consumers** -- `markdown_render` feeds fenced code blocks through the engine; `diff_render` highlights Add/Delete content as a whole file and Update hunks per-hunk (preserving parser state across hunk lines). Both callers fall back to plain unstyled text when the engine returns `None`. 3. **Theme lifecycle** -- at startup the config's `tui.theme` is resolved to a syntect `Theme` via `set_theme_override`. At runtime the `/theme` picker calls `set_syntax_theme` to swap themes live; on cancel it restores the snapshot taken at open. On confirm it persists `[tui] theme = "..."` to config.toml. ## Non-goals - Inline diff highlighting (word-level change detection within a line). - Semantic / LSP-backed highlighting. - Theme authoring tooling; users supply standard `.tmTheme` files. ## Tradeoffs | Decision | Upside | Downside | | ------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | syntect over tree-sitter / arborium | ~1 MB binary increase for ~250 grammars + 32 themes; battle-tested crate powering widely-used tools (`bat`, `delta`, `xi-editor`). tree-sitter would add ~12 MB for 20-30 languages or ~35 MB for full coverage. | Regex-based; less structurally accurate than tree-sitter for some languages (e.g. language injections like JS-in-HTML). | | Global `RwLock<Theme>` | Enables live `/theme` preview without threading Theme through every call site | Lock contention risk (mitigated: reads vastly outnumber writes, single UI thread) | | Skip background / italic / underline from themes | Terminal BG preserved, avoids ugly rendering on some themes | Themes that rely on these properties lose fidelity | | Guardrails: 512 KB / 10k lines | Prevents pathological stalls on huge diffs or pastes | Very large files render without color | ## Architecture ``` config.toml ─[tui.theme]─> set_theme_override() ─> THEME (RwLock) │ ┌───────────────────────────────────────────┘ │ markdown_render ─── highlight_code_to_lines(code, lang) ─> Vec<Line> diff_render ─── highlight_code_to_styled_spans(code, lang) ─> Option<Vec<Vec<Span>>> │ │ (None ⇒ plain text fallback) │ /theme picker ─── set_syntax_theme(theme) // live preview swap ─── current_syntax_theme() // snapshot for cancel ─── resolve_theme_by_name(name) // lookup by kebab-case ``` Key files: - `tui/src/render/highlight.rs` -- engine, theme management, guardrails - `tui/src/diff_render.rs` -- syntax-aware diff line wrapping - `tui/src/theme_picker.rs` -- `/theme` command builder - `tui/src/bottom_pane/list_selection_view.rs` -- side content panel, callbacks - `core/src/config/types.rs` -- `Tui::theme` field - `core/src/config/edit.rs` -- `syntax_theme_edit()` helper ## Observability - `tracing::warn` when a configured theme name cannot be resolved. - `Config::startup_warnings` surfaces the same message as a TUI banner. - `tracing::error` when persisting theme selection fails. ## Tests - Unit tests in `highlight.rs`: language coverage, fallback behavior, CRLF stripping, style conversion, guardrail enforcement, theme name mapping exhaustiveness. - Unit tests in `diff_render.rs`: snapshot gallery at multiple terminal sizes (80x24, 94x35, 120x40), syntax-highlighted wrapping, large-diff guardrail, rename-to-different-extension highlighting, parser state preservation across hunk lines. - Unit tests in `theme_picker.rs`: preview rendering (wide + narrow), dim overlay on deletions, subtitle truncation, cancel-restore, fallback for unavailable configured theme. - Unit tests in `list_selection_view.rs`: side layout geometry, stacked fallback, buffer clearing, cancel/selection-changed callbacks. - Integration test in `lib.rs`: theme warning uses the final (post-resume) config. ## Cargo Deny: Unmaintained Dependency Exceptions This PR adds two `cargo deny` advisory exceptions for transitive dependencies pulled in by `syntect v5.3.0`: | Advisory | Crate | Status | |----------|-------|--------| | RUSTSEC-2024-0320 | `yaml-rust` | Unmaintained (maintainer unreachable) | | RUSTSEC-2025-0141 | `bincode` | Unmaintained (development ceased; v1.3.3 considered complete) | **Why this is safe in our usage:** - Neither advisory describes a known security vulnerability. Both are "unmaintained" notices only. - `bincode` is used by syntect to deserialize pre-compiled syntax sets. Again, these are **static vendored artifacts** baked into the binary at build time. No user-supplied bincode data is ever deserialized. - Attack surface is zero for both crates; exploitation would require a supply-chain compromise of our own build artifacts. - These exceptions can be removed when syntect migrates to `yaml-rust2` and drops `bincode`, or when alternative crates are available upstream. |
||
|
Michael Bolin
|
85ce91a5b3 |
refactor(core): move embedded system skills into codex-skills crate (#12435)
## Why `codex-core` was carrying the embedded system-skill sample assets (and a `build.rs` that walks those files to register rerun triggers). Those assets change infrequently, but any change under `codex-core` still ties them to `codex-core`'s build/cache lifecycle. This change moves the embedded system-skills packaging into a dedicated `codex-skills` crate so it can be cached independently. That reduces unnecessary invalidation/rebuild pressure on `codex-core` when the skills bundle is the only thing that changes. ## What Changed - Added a new `codex-rs/skills` crate (`codex-skills`) with: - `Cargo.toml` - `BUILD.bazel` - `build.rs` to track skill asset file changes for Cargo rebuilds - `src/lib.rs` containing the embedded system-skills install/cache logic previously in `codex-core` - Moved the embedded sample skill assets from `codex-rs/core/src/skills/assets/samples` to `codex-rs/skills/src/assets/samples`. - Updated `codex-rs/core/Cargo.toml` to depend on `codex-skills` and removed `codex-core`'s direct `include_dir` dependency. - Removed `codex-core`'s `build.rs`. - Replaced `codex-rs/core/src/skills/system.rs` implementation with a thin re-export wrapper to keep existing `codex-core` call sites unchanged. - Updated workspace manifests/lockfile (`codex-rs/Cargo.toml`, `codex-rs/Cargo.lock`) for the new crate. |
||
|
viyatb-oai
|
64f3827d10 |
Move sanitizer into codex-secrets (#12306)
## Summary - move the sanitizer implementation into `codex-secrets` (`secrets/src/sanitizer.rs`) and re-export `redact_secrets` - switch `codex-core` to depend on/import `codex-secrets` for sanitizer usage - remove the old `utils/sanitizer` crate wiring and refresh lockfiles ## Testing - `just fmt` - `cargo test -p codex-secrets` - `cargo test -p codex-core --no-run` - `cargo clippy -p codex-secrets -p codex-core --all-targets --all-features -- -D warnings` - `just bazel-lock-update` - `just bazel-lock-check` ## Notes - not run: `cargo test --all-features` (full workspace suite) |
||
|
Alex Kwiatkowski
|
fe7054a346 |
fix(bazel): replace askama templates with include_str! in memories (#11778)
## Summary
- The experimental Bazel CI builds fail on all platforms because askama
resolves template paths relative to `CARGO_MANIFEST_DIR`, which points
outside the Bazel sandbox. This produces errors like:
```
error: couldn't read
`codex-rs/core/src/memories/../../../../../../../../../../../work/codex/codex/codex-rs/core/templates/memories/consolidation.md`:
No such file or directory
```
- Replaced `#[derive(Template)]` + `#[template(path = "...")]` with
`include_str!` + `str::replace()` for the three affected templates
(`consolidation.md`, `stage_one_input.md`, `read_path.md`).
`include_str!` resolves paths relative to the source file, which works
correctly in both Cargo and Bazel builds.
- The templates only use simple `{{ variable }}` substitution with no
control flow or filters, so no askama functionality is lost.
- Removes the `askama` dependency from `codex-core` since it was the
only crate using it. The workspace-level dependency definition is left
in place.
- This matches the existing pattern used throughout the codebase — e.g.
`codex-rs/core/src/memories/mod.rs` already uses
`include_str!("../../templates/memories/stage_one_system.md")` for the
fourth template file.
## Test plan
- [ ] Verify Bazel (experimental) CI passes on all platforms
- [ ] Verify rust-ci (Cargo) builds and tests continue to pass
- [ ] Verify `cargo test -p codex-core` passes locally
|
||
|
dependabot[bot]
|
4c4255fcfc |
chore(deps): bump env_logger from 0.11.8 to 0.11.9 in /codex-rs (#11889)
Bumps [env_logger](https://github.com/rust-cli/env_logger) from 0.11.8 to 0.11.9. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/rust-cli/env_logger/releases">env_logger's releases</a>.</em></p> <blockquote> <h2>v0.11.9</h2> <h2>[0.11.9] - 2026-02-11</h2> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/rust-cli/env_logger/blob/main/CHANGELOG.md">env_logger's changelog</a>.</em></p> <blockquote> <h2>[0.11.9] - 2026-02-11</h2> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Yaroslav Volovich
|
32da5eb358 |
feat(tui): prevent macOS idle sleep while turns run (#11711)
## Summary - add a shared `codex-core` sleep inhibitor that uses native macOS IOKit assertions (`IOPMAssertionCreateWithName` / `IOPMAssertionRelease`) instead of spawning `caffeinate` - wire sleep inhibition to turn lifecycle in `tui` (`TurnStarted` enables; `TurnComplete` and abort/error finalization disable) - gate this behavior behind a `/experimental` feature toggle (`[features].prevent_idle_sleep`) instead of a dedicated `[tui]` config flag - expose the toggle in `/experimental` on macOS; keep it under development on other platforms - keep behavior no-op on non-macOS targets <img width="1326" height="577" alt="image" src="https://github.com/user-attachments/assets/73fac06b-97ae-46a2-800a-30f9516cf8a3" /> ## Testing - `cargo check -p codex-core -p codex-tui` - `cargo test -p codex-core sleep_inhibitor::tests -- --nocapture` - `cargo test -p codex-core tui_config_missing_notifications_field_defaults_to_enabled -- --nocapture` - `cargo test -p codex-core prevent_idle_sleep_is_ -- --nocapture` ## Semantics and API references - This PR targets `caffeinate -i` semantics: prevent *idle system sleep* while allowing display idle sleep. - `caffeinate -i` mapping in Apple open source (`assertionMap`): - `kIdleAssertionFlag -> kIOPMAssertionTypePreventUserIdleSystemSleep` - Source: https://github.com/apple-oss-distributions/PowerManagement/blob/PowerManagement-1846.60.12/caffeinate/caffeinate.c#L52-L54 - Apple IOKit docs for assertion types and API: - https://developer.apple.com/documentation/iokit/iopmlib_h/iopmassertiontypes - https://developer.apple.com/documentation/iokit/1557092-iopmassertioncreatewithname - https://developer.apple.com/library/archive/qa/qa1340/_index.html ## Codex Electron vs this PR (full stack path) - Codex Electron app requests sleep blocking with `powerSaveBlocker.start("prevent-app-suspension")`: - https://github.com/openai/codex/blob/main/codex/codex-vscode/electron/src/electron-message-handler.ts - Electron maps that string to Chromium wake lock type `kPreventAppSuspension`: - https://github.com/electron/electron/blob/main/shell/browser/api/electron_api_power_save_blocker.cc - Chromium macOS backend maps wake lock types to IOKit assertion constants and calls IOKit: - `kPreventAppSuspension -> kIOPMAssertionTypeNoIdleSleep` - `kPreventDisplaySleep / kPreventDisplaySleepAllowDimming -> kIOPMAssertionTypeNoDisplaySleep` - https://github.com/chromium/chromium/blob/main/services/device/wake_lock/power_save_blocker/power_save_blocker_mac.cc ## Why this PR uses a different macOS constant name - This PR uses `"PreventUserIdleSystemSleep"` directly, via `IOPMAssertionCreateWithName`, in `codex-rs/core/src/sleep_inhibitor.rs`. - Apple’s IOKit header documents `kIOPMAssertionTypeNoIdleSleep` as deprecated and recommends `kIOPMAssertPreventUserIdleSystemSleep` / `kIOPMAssertionTypePreventUserIdleSystemSleep`: - https://github.com/apple-oss-distributions/IOKitUser/blob/IOKitUser-100222.60.2/pwr_mgt.subproj/IOPMLib.h#L1000-L1030 - So Chromium and this PR are using different constant names, but semantically equivalent idle-system-sleep prevention behavior. ## Future platform support The architecture is intentionally set up for multi-platform extensions: - UI code (`tui`) only calls `SleepInhibitor::set_turn_running(...)` on turn lifecycle boundaries. - Platform-specific behavior is isolated in `codex-rs/core/src/sleep_inhibitor.rs` behind `cfg(...)` blocks. - Feature exposure is centralized in `core/src/features.rs` and surfaced via `/experimental`. - Adding new OS backends should not require additional TUI wiring; only the backend internals and feature stage metadata need to change. Potential follow-up implementations: - Windows: - Add a backend using Win32 power APIs (`SetThreadExecutionState(ES_CONTINUOUS | ES_SYSTEM_REQUIRED)` as baseline). - Optionally move to `PowerCreateRequest` / `PowerSetRequest` / `PowerClearRequest` for richer assertion semantics. - Linux: - Add a backend using logind inhibitors over D-Bus (`org.freedesktop.login1.Manager.Inhibit` with `what="sleep"`). - Keep a no-op fallback where logind/D-Bus is unavailable. This PR keeps the cross-platform API surface minimal so future PRs can add Windows/Linux support incrementally with low churn. --------- Co-authored-by: jif-oai <jif@openai.com> |
||
|
jif-oai
|
f741fad5c0 |
chore: drop and clean from phase 1 (#11605)
This PR is mostly cleaning and simplifying phase 1 of memories |
||
|
jif-oai
|
cf4ef84b52 |
feat: add sanitizer to redact secrets (#11600)
Adding a sanitizer crate that can redact API keys and other secret with known pattern from a String |
||
|
Gabriel Peal
|
bd3ce98190 |
Bump rmcp to 0.15 (#11539)
https://github.com/modelcontextprotocol/rust-sdk/pull/598 in 0.14 broke some MCP oauth (like Linear) and https://github.com/modelcontextprotocol/rust-sdk/pull/641 fixed it in 0.15 |
||
|
Michael Bolin
|
577a416f9a |
Extract codex-config from codex-core (#11389)
`codex-core` had accumulated config loading, requirements parsing, constraint logic, and config-layer state handling in a single crate. This change extracts that subsystem into `codex-config` to reduce `codex-core` rebuild/test surface area and isolate future config work. ## What Changed ### Added `codex-config` - Added new workspace crate `codex-rs/config` (`codex-config`). - Added workspace/build wiring in: - `codex-rs/Cargo.toml` - `codex-rs/config/Cargo.toml` - `codex-rs/config/BUILD.bazel` - Updated lockfiles (`codex-rs/Cargo.lock`, `MODULE.bazel.lock`). - Added `codex-core` -> `codex-config` dependency in `codex-rs/core/Cargo.toml`. ### Moved config internals from `core` into `config` Moved modules to `codex-rs/config/src/`: - `core/src/config/constraint.rs` -> `config/src/constraint.rs` - `core/src/config_loader/cloud_requirements.rs` -> `config/src/cloud_requirements.rs` - `core/src/config_loader/config_requirements.rs` -> `config/src/config_requirements.rs` - `core/src/config_loader/fingerprint.rs` -> `config/src/fingerprint.rs` - `core/src/config_loader/merge.rs` -> `config/src/merge.rs` - `core/src/config_loader/overrides.rs` -> `config/src/overrides.rs` - `core/src/config_loader/requirements_exec_policy.rs` -> `config/src/requirements_exec_policy.rs` - `core/src/config_loader/state.rs` -> `config/src/state.rs` `codex-config` now re-exports this surface from `config/src/lib.rs` at the crate top level. ### Updated `core` to consume/re-export `codex-config` - `core/src/config_loader/mod.rs` now imports/re-exports config-loader types/functions from top-level `codex_config::*`. - Local moved modules were removed from `core/src/config_loader/`. - `core/src/config/mod.rs` now re-exports constraint types from `codex_config`. |
||
|
Michael Bolin
|
8b7f8af343 |
feat: split codex-common into smaller utils crates (#11422)
We are removing feature-gated shared crates from the `codex-rs` workspace. `codex-common` grouped several unrelated utilities behind `[features]`, which made dependency boundaries harder to reason about and worked against the ongoing effort to eliminate feature flags from workspace crates. Splitting these utilities into dedicated crates under `utils/` aligns this area with existing workspace structure and keeps each dependency explicit at the crate boundary. ## What changed - Removed `codex-rs/common` (`codex-common`) from workspace members and workspace dependencies. - Added six new utility crates under `codex-rs/utils/`: - `codex-utils-cli` - `codex-utils-elapsed` - `codex-utils-sandbox-summary` - `codex-utils-approval-presets` - `codex-utils-oss` - `codex-utils-fuzzy-match` - Migrated the corresponding modules out of `codex-common` into these crates (with tests), and added matching `BUILD.bazel` targets. - Updated direct consumers to use the new crates instead of `codex-common`: - `codex-rs/cli` - `codex-rs/tui` - `codex-rs/exec` - `codex-rs/app-server` - `codex-rs/mcp-server` - `codex-rs/chatgpt` - `codex-rs/cloud-tasks` - Updated workspace lockfile entries to reflect the new dependency graph and removal of `codex-common`. |
||
|
Michael Bolin
|
d44f4205fb |
chore: rename codex-command to codex-shell-command (#11378)
This addresses some post-merge feedback on https://github.com/openai/codex/pull/11361: - crate rename - reuse `detect_shell_type()` utility |
||
|
Michael Bolin
|
d8f9bb65e2 |
# Split command parsing/safety out of codex-core into new codex-command (#11361)
`codex-core` had accumulated command parsing and command safety logic (`bash`, `powershell`, `parse_command`, and `command_safety`) that is logically cohesive but orthogonal to most core session/runtime logic. Keeping this code in `codex-core` made the crate increasingly monolithic and raised iteration cost for unrelated core changes. This change extracts that surface into a dedicated crate, `codex-command`, while preserving existing `codex_core::...` call sites via re-exports. ## Why this refactor During analysis, command parsing/safety stood out as a good first split because it has: - a clear domain boundary (shell parsing + safety classification) - relatively self-contained dependencies (notably `tree-sitter` / `tree-sitter-bash`) - a meaningful standalone test surface (`134` tests moved with the crate) - many downstream uses that benefit from independent compilation and caching The practical problem was build latency from a large `codex-core` compile/test graph. Clean-build timings before and after this split showed measurable wins: - `cargo check -p codex-core`: `57.08s` -> `53.54s` (~`6.2%` faster) - `cargo test -p codex-core --no-run`: `2m39.9s` -> `2m20s` (~`12.4%` faster) - `codex-core lib` compile unit: `57.18s` -> `49.67s` (~`13.1%` faster) - `codex-core lib(test)` compile unit: `60.87s` -> `53.21s` (~`12.6%` faster) This gives a concrete reduction in core build overhead without changing behavior. ## What changed ### New crate - Added `codex-rs/command` as workspace crate `codex-command`. - Added: - `command/src/lib.rs` - `command/src/bash.rs` - `command/src/powershell.rs` - `command/src/parse_command.rs` - `command/src/command_safety/*` - `command/src/shell_detect.rs` - `command/BUILD.bazel` ### Code moved out of `codex-core` - Moved modules from `core/src` into `command/src`: - `bash.rs` - `powershell.rs` - `parse_command.rs` - `command_safety/*` ### Dependency graph updates - Added workspace member/dependency entries for `codex-command` in `codex-rs/Cargo.toml`. - Added `codex-command` dependency to `codex-rs/core/Cargo.toml`. - Removed `tree-sitter` and `tree-sitter-bash` from `codex-core` direct deps (now owned by `codex-command`). ### API compatibility for callers To avoid immediate downstream churn, `codex-core` now re-exports the moved modules/functions: - `codex_command::bash` - `codex_command::powershell` - `codex_command::parse_command` - `codex_command::is_safe_command` - `codex_command::is_dangerous_command` This keeps existing `codex_core::...` paths working while enabling gradual migration to direct `codex-command` usage. ### Internal decoupling detail - Added `command::shell_detect` so moved `bash`/`powershell` logic no longer depends on core shell internals. - Adjusted PowerShell helper visibility in `codex-command` for existing core test usage (`UTF8` prefix helper + executable discovery functions). ## Validation - `just fmt` - `just fix -p codex-command -p codex-core` - `cargo test -p codex-command` (`134` passed) - `cargo test -p codex-core --no-run` - `cargo test -p codex-core shell_command_handler` ## Notes / follow-up This commit intentionally prioritizes boundary extraction and compatibility. A follow-up can migrate downstream crates to depend directly on `codex-command` (instead of through `codex-core` re-exports) to realize additional incremental build wins. |
||
|
jif-oai
|
d735df1f50 |
Extract hooks into dedicated crate (#11311)
Summary - move `core/src/hooks` implementation into a new `codex-hooks` crate with its own manifest - update `codex-rs` workspace and `codex-core` crate to depend on the extracted `hooks` crate and wire up the shared APIs - ensure references, modules, and lockfile reflect the new crate layout Testing - Not run (not requested) |
||
|
jif-oai
|
6049ff02a0 |
memories: add extraction and prompt module foundation (#11200)
## Summary - add the new `core/src/memories` module (phase-one parsing, rollout filtering, storage, selection, prompts) - add Askama-backed memory templates for stage-one input/system and consolidation prompts - add module tests for parsing, filtering, path bucketing, and summary maintenance ## Testing - just fmt - cargo test -p codex-core --lib memories:: |
||
|
Michael Bolin
|
8e240a13be |
chore: put crypto provider logic in a shared crate (#11294)
Ensures a process-wide rustls crypto provider is installed. Both the `codex-network-proxy` and `codex-api` crates need this. |
||
|
dependabot[bot]
|
c0994b363d |
chore(deps): bump regex from 1.12.2 to 1.12.3 in /codex-rs (#11138)
Bumps [regex](https://github.com/rust-lang/regex) from 1.12.2 to 1.12.3. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/rust-lang/regex/blob/master/CHANGELOG.md">regex's changelog</a>.</em></p> <blockquote> <h1>1.12.3 (2025-02-03)</h1> <p>This release excludes some unnecessary things from the archive published to crates.io. Specifically, fuzzing data and various shell scripts are now excluded. If you run into problems, please file an issue.</p> <p>Improvements:</p> <ul> <li><a href="https://redirect.github.com/rust-lang/regex/pull/1319">#1319</a>: Switch from a Cargo <code>exclude</code> list to an <code>include</code> list, and exclude some unnecessary stuff.</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
10b1214606 |
chore(deps): bump insta from 1.46.2 to 1.46.3 in /codex-rs (#11140)
Bumps [insta](https://github.com/mitsuhiko/insta) from 1.46.2 to 1.46.3. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/mitsuhiko/insta/releases">insta's releases</a>.</em></p> <blockquote> <h2>1.46.3</h2> <h2>Release Notes</h2> <ul> <li>Fix inline escaped snapshots incorrectly stripping leading newlines when content contains control characters like carriage returns. The escaped format (used for snapshots with control chars) now correctly preserves the original content without stripping a non-existent formatting newline. <a href="https://redirect.github.com/mitsuhiko/insta/issues/865">#865</a></li> </ul> <h2>Install cargo-insta 1.46.3</h2> <h3>Install prebuilt binaries via shell script</h3> <pre lang="sh"><code>curl --proto '=https' --tlsv1.2 -LsSf https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-installer.sh | sh </code></pre> <h3>Install prebuilt binaries via powershell script</h3> <pre lang="sh"><code>powershell -ExecutionPolicy Bypass -c "irm https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-installer.ps1 | iex" </code></pre> <h2>Download cargo-insta 1.46.3</h2> <table> <thead> <tr> <th>File</th> <th>Platform</th> <th>Checksum</th> </tr> </thead> <tbody> <tr> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-aarch64-apple-darwin.tar.xz">cargo-insta-aarch64-apple-darwin.tar.xz</a></td> <td>Apple Silicon macOS</td> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-aarch64-apple-darwin.tar.xz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-apple-darwin.tar.xz">cargo-insta-x86_64-apple-darwin.tar.xz</a></td> <td>Intel macOS</td> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-apple-darwin.tar.xz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-pc-windows-msvc.zip">cargo-insta-x86_64-pc-windows-msvc.zip</a></td> <td>x64 Windows</td> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-pc-windows-msvc.zip.sha256">checksum</a></td> </tr> <tr> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-unknown-linux-gnu.tar.xz">cargo-insta-x86_64-unknown-linux-gnu.tar.xz</a></td> <td>x64 Linux</td> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-unknown-linux-gnu.tar.xz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-unknown-linux-musl.tar.xz">cargo-insta-x86_64-unknown-linux-musl.tar.xz</a></td> <td>x64 MUSL Linux</td> <td><a href="https://github.com/mitsuhiko/insta/releases/download/1.46.3/cargo-insta-x86_64-unknown-linux-musl.tar.xz.sha256">checksum</a></td> </tr> </tbody> </table> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/mitsuhiko/insta/blob/master/CHANGELOG.md">insta's changelog</a>.</em></p> <blockquote> <h2>1.46.3</h2> <ul> <li>Fix inline escaped snapshots incorrectly stripping leading newlines when content contains control characters like carriage returns. The escaped format (used for snapshots with control chars) now correctly preserves the original content without stripping a non-existent formatting newline. <a href="https://redirect.github.com/mitsuhiko/insta/issues/865">#865</a></li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Anton Panasenko
|
becc3a0424 |
feat: search_tool (#10657)
**Why We Did This** - The goal is to reduce MCP tool context pollution by not exposing the full MCP tool list up front - It forces an explicit discovery step (`search_tool_bm25`) so the model narrows tool scope before making MCP calls, which helps relevance and lowers prompt/tool clutter. **What It Changed** - Added a new experimental feature flag `search_tool` in `core/src/features.rs:90` and `core/src/features.rs:430`. - Added config/schema support for that flag in `core/config.schema.json:214` and `core/config.schema.json:1235`. - Added BM25 dependency (`bm25`) in `Cargo.toml:129` and `core/Cargo.toml:23`. - Added new tool handler `search_tool_bm25` in `core/src/tools/handlers/search_tool_bm25.rs:18`. - Registered the handler and tool spec in `core/src/tools/handlers/mod.rs:11` and `core/src/tools/spec.rs:780` and `core/src/tools/spec.rs:1344`. - Extended `ToolsConfig` to carry `search_tool` enablement in `core/src/tools/spec.rs:32` and `core/src/tools/spec.rs:56`. - Injected dedicated developer instructions for tool-discovery workflow in `core/src/codex.rs:483` and `core/src/codex.rs:1976`, using `core/templates/search_tool/developer_instructions.md:1`. - Added session state to store one-shot selected MCP tools in `core/src/state/session.rs:27` and `core/src/state/session.rs:131`. - Added filtering so when feature is enabled, only selected MCP tools are exposed on the next request (then consumed) in `core/src/codex.rs:3800` and `core/src/codex.rs:3843`. - Added E2E suite coverage for enablement/instructions/hide-until-search/one-turn-selection in `core/tests/suite/search_tool.rs:72`, `core/tests/suite/search_tool.rs:109`, `core/tests/suite/search_tool.rs:147`, and `core/tests/suite/search_tool.rs:218`. - Refactored test helper utilities to support config-driven tool collection in `core/tests/suite/tools.rs:281`. **Net Behavioral Effect** - With `search_tool` **off**: existing MCP behavior (tools exposed normally). - With `search_tool` **on**: MCP tools start hidden, model must call `search_tool_bm25`, and only returned `selected_tools` are available for the next model call. |
||
|
viyatb-oai
|
c2c6bc90f8 |
chore: remove network-proxy-cli crate (#11158)
## Summary - remove `network-proxy-cli` from the Rust workspace members - delete the dedicated `codex-network-proxy-cli` crate files - remove the stale `codex-network-proxy-cli` package entry from `Cargo.lock` ## Testing - just fmt - cargo test -p codex-network-proxy |
||
|
Michael Bolin
|
383b45279e |
feat: include NetworkConfig through ExecParams (#11105)
This PR adds the following field to `Config`: ```rust pub network: Option<NetworkProxy>, ``` Though for the moment, it will always be initialized as `None` (this will be addressed in a subsequent PR). This PR does the work to thread `network` through to `execute_exec_env()`, `process_exec_tool_call()`, and `UnifiedExecRuntime.run()` to ensure it is available whenever we span a process. |
||
|
Michael Bolin
|
ff74aaae21 | chore: reverse the codex-network-proxy -> codex-core dependency (#11121) | ||
|
Matthew Zeng
|
9f1009540b |
Upgrade rmcp to 0.14 (#10718)
- [x] Upgrade rmcp to 0.14 |
||
|
Anton Panasenko
|
a94505a92a |
feat: enable premessage-deflate for websockets (#10966)
note:
unfortunately, tokio-tungstenite / tungstenite upgrade triggers some
problems with linker of rama-tls-boring with openssl:
```
error: linking with `/Users/apanasenko/Library/Caches/cargo-zigbuild/0.20.1/zigcc-x86_64-unknown-linux-musl-ff6a.sh` failed: exit status: 1
|
= note: "/Users/apanasenko/Library/Caches/cargo-zigbuild/0.20.1/zigcc-x86_64-unknown-linux-musl-ff6a.sh" "-m64" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained/rcrt1.o" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained/crti.o" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained/crtbeginS.o" "<1 object files omitted>" "-Wl,--as-needed" "-Wl,-Bstatic" "/var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/{liblzma_sys-662a82316f96ec30,libbzip2_sys-bf78a2d58d5cbce6,liblibsqlite3_sys-6c004987fd67a36a,libtree_sitter_bash-220b99a97d331ab7,libtree_sitter-858f0a1dbfea58bd,libzstd_sys-6eb237deec748c5b,libring-2a87376483bf916f,libopenssl_sys-7c189e68b37fe2bb,liblibz_sys-4344eef4345520b1,librama_boring_sys-0414e98115015ee0}.rlib" "-lc++" "-lc++abi" "-lunwind" "-lc" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/libcompiler_builtins-*.rlib" "-L" "/var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/raw-dylibs" "-Wl,-Bdynamic" "-Wl,--eh-frame-hdr" "-Wl,-z,noexecstack" "-nostartfiles" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/libz-sys-ff5ea50d88c28ffb/out/lib" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/ring-bdec3dddc19f5a5e/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/openssl-sys-96e0870de3ca22bc/out/openssl-build/install/lib" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/zstd-sys-0cc37a5da1481740/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/tree-sitter-72d2418073317c0f/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/tree-sitter-bash-bfd293a9f333ce6a/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/libsqlite3-sys-b78b2cfb81a330fc/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/bzip2-sys-69a145cc859ef275/out/lib" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/lzma-sys-07e92d0b6baa6fd4/out" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/build/crypto/" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/build/ssl/" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/build/" "-L" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/build" "-L" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained" "-L" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib" "-o" "/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/deps/codex_network_proxy-d08268b863517761" "-Wl,--gc-sections" "-static-pie" "-Wl,-z,relro,-z,now" "-Wl,-O1" "-Wl,--strip-all" "-nodefaultlibs" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained/crtendS.o" "<sysroot>/lib/rustlib/x86_64-unknown-linux-musl/lib/self-contained/crtn.o"
= note: some arguments are omitted. use `--verbose` to show all linker arguments
= note: warning: ignoring deprecated linker optimization setting '1'
warning: unable to open library directory '/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/build/crypto/': FileNotFound
ld.lld: error: duplicate symbol: SSL_export_keying_material
>>> defined at ssl_lib.c:3816 (ssl/ssl_lib.c:3816)
>>> libssl-lib-ssl_lib.o:(SSL_export_keying_material) in archive /var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/libopenssl_sys-7c189e68b37fe2bb.rlib
>>> defined at t1_enc.cc:205 (/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/boringssl/ssl/t1_enc.cc:205)
>>> t1_enc.cc.o:(.text.SSL_export_keying_material+0x0) in archive /var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/librama_boring_sys-0414e98115015ee0.rlib
ld.lld: error: duplicate symbol: d2i_ASN1_TIME
>>> defined at a_time.c:27 (crypto/asn1/a_time.c:27)
>>> libcrypto-lib-a_time.o:(d2i_ASN1_TIME) in archive /var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/libopenssl_sys-7c189e68b37fe2bb.rlib
>>> defined at a_time.cc:34 (/Users/apanasenko/code/codex/codex-rs/target/x86_64-unknown-linux-musl/release/build/rama-boring-sys-0bc2dfbf669addc4/out/boringssl/crypto/asn1/a_time.cc:34)
>>> a_time.cc.o:(.text.d2i_ASN1_TIME+0x0) in archive /var/folders/kt/52y_g75x3ng8ktvk3rfwm6400000gp/T/rustcyGQdYm/librama_boring_sys-0414e98115015ee0.rlib
```
that force me to migrate away from rama-tls-boring to rama-tls-rustls
and pin `ring` for rustls.
|
||
|
jif-oai
|
66554abfb9 |
sec: fix version of time to prevent vulnerability (#10876)
RUSTSEC-2026-0009 |
||
|
Celia Chen
|
16647b188b |
chore: add codex debug app-server tooling (#10367)
codex debug app-server <user message> forwards the message through
codex-app-server-test-client’s send_message_v2 library entry point,
using std::env::current_exe() to resolve the codex binary.
for how it looks like, see:
```
celia@com-92114 codex-rs % cargo build -p codex-cli && target/debug/codex debug app-server --help
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.34s
Tooling: helps debug the app server
Usage: codex debug app-server [OPTIONS] <COMMAND>
Commands:
send-message-v2
help Print this message or the help of the given subcommand(s)
````
and
```
celia@com-92114 codex-rs % cargo build -p codex-cli && target/debug/codex debug app-server send-message-v2 "hello world"
Compiling codex-cli v0.0.0 (/Users/celia/code/codex/codex-rs/cli)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 1.38s
> {
> "method": "initialize",
> "id": "f8ba9f60-3a49-4ea9-81d6-4ab6853e3954",
> "params": {
> "clientInfo": {
> "name": "codex-toy-app-server",
> "title": "Codex Toy App Server",
> "version": "0.0.0"
> },
> "capabilities": {
> "experimentalApi": true
> }
> }
> }
< {
< "id": "f8ba9f60-3a49-4ea9-81d6-4ab6853e3954",
< "result": {
< "userAgent": "codex-toy-app-server/0.0.0 (Mac OS 26.2.0; arm64) vscode/2.4.27 (codex-toy-app-server; 0.0.0)"
< }
< }
< initialize response: InitializeResponse { user_agent: "codex-toy-app-server/0.0.0 (Mac OS 26.2.0; arm64) vscode/2.4.27 (codex-toy-app-server; 0.0.0)" }
> {
> "method": "thread/start",
> "id": "203f1630-beee-4e60-b17b-9eff16b1638b",
> "params": {
> "model": null,
> "modelProvider": null,
> "cwd": null,
> "approvalPolicy": null,
> "sandbox": null,
> "config": null,
> "baseInstructions": null,
> "developerInstructions": null,
> "personality": null,
> "ephemeral": null,
> "dynamicTools": null,
> "mockExperimentalField": null,
> "experimentalRawEvents": false
> }
> }
...
```
|
||
|
xl-openai
|
f38d181795 |
feat: add APIs to list and download public remote skills (#10448)
Add API to list / download from remote public skills |
||
|
viyatb-oai
|
9257d8451c |
feat(secrets): add codex-secrets crate (#10142)
## Summary This introduces the first working foundation for Codex managed secrets: a small Rust crate that can securely store and retrieve secrets locally. Concretely, it adds a `codex-secrets` crate that: - encrypts a local secrets file using `age` - generates a high-entropy encryption key - stores that key in the OS keyring ## What this enables - A secure local persistence model for secrets - A clean, isolated place for future provider backends - A clear boundary: Codex can become a credential broker without putting plaintext secrets in config files ## Implementation details - New crate: `codex-rs/secrets/` - Encryption: `age` with scrypt recipient/identity - Key generation: `OsRng` (32 random bytes) - Key storage: OS keyring via `codex-keyring-store` ## Testing - `cd codex-rs && just fmt` - `cd codex-rs && cargo test -p codex-secrets` |
||
|
Michael Bolin
|
891ed87409 |
chore: remove deprecated mcp-types crate (#10357)
https://github.com/openai/codex/pull/10349 migrated us off of `mcp-types`, so this PR deletes the code. --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10357). * __->__ #10357 * #10349 * #10356 |
||
|
Michael Bolin
|
66447d5d2c |
feat: replace custom mcp-types crate with equivalents from rmcp (#10349)
We started working with MCP in Codex before
https://crates.io/crates/rmcp was mature, so we had our own crate for
MCP types that was generated from the MCP schema:
|
||
|
jif-oai
|
3cc9122ee2 |
feat: experimental flags (#10231)
## Problem being solved
- We need a single, reliable way to mark app-server API surface as
experimental so that:
1. the runtime can reject experimental usage unless the client opts in
2. generated TS/JSON schemas can exclude experimental methods/fields for
stable clients.
Right now that’s easy to drift or miss when done ad-hoc.
## How to declare experimental methods and fields
- **Experimental method**: add `#[experimental("method/name")]` to the
`ClientRequest` variant in `client_request_definitions!`.
- **Experimental field**: on the params struct, derive `ExperimentalApi`
and annotate the field with `#[experimental("method/name.field")]` + set
`inspect_params: true` for the method variant so
`ClientRequest::experimental_reason()` inspects params for experimental
fields.
## How the macro solves it
- The new derive macro lives in
`codex-rs/codex-experimental-api-macros/src/lib.rs` and is used via
`#[derive(ExperimentalApi)]` plus `#[experimental("reason")]`
attributes.
- **Structs**:
- Generates `ExperimentalApi::experimental_reason(&self)` that checks
only annotated fields.
- The “presence” check is type-aware:
- `Option<T>`: `is_some_and(...)` recursively checks inner.
- `Vec`/`HashMap`/`BTreeMap`: must be non-empty.
- `bool`: must be `true`.
- Other types: considered present (returns `true`).
- Registers each experimental field in an `inventory` with `(type_name,
serialized field name, reason)` and exposes `EXPERIMENTAL_FIELDS` for
that type. Field names are converted from `snake_case` to `camelCase`
for schema/TS filtering.
- **Enums**:
- Generates an exhaustive `match` returning `Some(reason)` for annotated
variants and `None` otherwise (no wildcard arm).
- **Wiring**:
- Runtime gating uses `ExperimentalApi::experimental_reason()` in
`codex-rs/app-server/src/message_processor.rs` to reject requests unless
`InitializeParams.capabilities.experimental_api == true`.
- Schema/TS export filters use the inventory list and
`EXPERIMENTAL_CLIENT_METHODS` from `client_request_definitions!` to
strip experimental methods/fields when `experimental_api` is false.
|