## Why
`parse_tool_input_schema` and the supporting `JsonSchema` model were
living in `core/src/tools/spec.rs`, but they already serve callers
outside `codex-core`.
Keeping that shared schema parsing logic inside `codex-core` makes the
crate boundary harder to reason about and works against the guidance in
`AGENTS.md` to avoid growing `codex-core` when reusable code can live
elsewhere.
This change takes the first extraction step by moving the schema parsing
primitive into its own crate while keeping the rest of the tool-spec
assembly in `codex-core`.
## What changed
- added a new `codex-tools` crate under `codex-rs/tools`
- moved the shared tool input schema model and sanitizer/parser into
`tools/src/json_schema.rs`
- kept `tools/src/lib.rs` exports-only, with the module-level unit tests
split into `json_schema_tests.rs`
- updated `codex-core` to use `codex-tools::JsonSchema` and re-export
`parse_tool_input_schema`
- updated `codex-app-server` dynamic tool validation to depend on
`codex-tools` directly instead of reaching through `codex-core`
- wired the new crate into the Cargo workspace and Bazel build graph
## Why
`#[large_stack_test]` made the `apply_patch_cli` tests pass by giving
them more stack, but it did not address why those tests needed the extra
stack in the first place.
The real problem is the async state built by the `apply_patch_cli`
harness path. Those tests await three helper boundaries directly:
harness construction, turn submission, and apply-patch output
collection. If those helpers inline their full child futures, the test
future grows to include the whole harness startup and request/response
path.
This change replaces the workaround from #12768 with the same basic
approach used in #13429, but keeps the fix narrower: only the helper
boundaries awaited directly by `apply_patch_cli` stay boxed.
## What Changed
- removed `#[large_stack_test]` from
`core/tests/suite/apply_patch_cli.rs`
- restored ordinary `#[tokio::test(flavor = "multi_thread",
worker_threads = 2)]` annotations in that suite
- deleted the now-unused `codex-test-macros` crate and removed its
workspace wiring
- boxed only the three helper boundaries that the suite awaits directly:
- `apply_patch_harness_with(...)`
- `TestCodexHarness::submit(...)`
- `TestCodexHarness::apply_patch_output(...)`
- added comments at those boxed boundaries explaining why they remain
boxed
## Testing
- `cargo test -p codex-core --test all suite::apply_patch_cli --
--nocapture`
## References
- #12768
- #13429
This PR partially rebase `unified_exec` on the `exec-server` and adapt
the `exec-server` accordingly.
## What changed in `exec-server`
1. Replaced the old "broadcast-driven; process-global" event model with
process-scoped session events. The goal is to be able to have dedicated
handler for each process.
2. Add to protocol contract to support explicit lifecycle status and
stream ordering:
- `WriteResponse` now returns `WriteStatus` (Accepted, UnknownProcess,
StdinClosed, Starting) instead of a bool.
- Added seq fields to output/exited notifications.
- Added terminal process/closed notification.
3. Demultiplexed remote notifications into per-process channels. Same as
for the event sys
4. Local and remote backends now both implement ExecBackend.
5. Local backend wraps internal process ID/operations into per-process
ExecProcess objects.
6. Remote backend registers a session channel before launch and
unregisters on failed launch.
## What changed in `unified_exec`
1. Added unified process-state model and backend-neutral process
wrapper. This will probably disappear in the future, but it makes it
easier to keep the work flowing on both side.
- `UnifiedExecProcess` now handles both local PTY sessions and remote
exec-server processes through a shared `ProcessHandle`.
- Added `ProcessState` to track has_exited, exit_code, and terminal
failure message consistently across backends.
2. Routed write and lifecycle handling through process-level methods.
## Some rationals
1. The change centralizes execution transport in exec-server while
preserving policy and orchestration ownership in core, avoiding
duplicated launch approval logic. This comes from internal discussion.
2. Session-scoped events remove coupling/cross-talk between processes
and make stream ordering and terminal state explicit (seq, closed,
failed).
3. The failure-path surfacing (remote launch failures, write failures,
transport disconnects) makes command tool output and cleanup behavior
deterministic
## Follow-ups:
* Unify the concept of thread ID behind an obfuscated struct
* FD handling
* Full zsh-fork compatibility
* Full network sandboxing compatibility
* Handle ws disconnection
## Summary
- move skill loading and management into codex-core-skills
- leave codex-core with the thin integration layer and shared wiring
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- move the analytics events client into codex-analytics
- update codex-core and app-server callsites to use the new crate
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- extract plugin identifiers and load-outcome types into codex-plugin
- update codex-core to consume the new plugin crate
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- extract instruction fragment and user-instruction types into
codex-instructions
- update codex-core to consume the new crate
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
- move the shared byte-based middle truncation logic from `core` into
`codex-utils-string`
- keep token-specific truncation in `codex-core` so rollout can reuse
the shared helper in the next stacked PR
---------
Co-authored-by: Codex <noreply@openai.com>
- create `codex-git-utils` and move the shared git helpers into it with
file moves preserved for diff readability
- move the `GitInfo` helpers out of `core` so stacked rollout work can
depend on the shared crate without carrying its own git info module
---------
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
## Summary
- add a new `codex-sandboxing` crate for sandboxing extraction work
- move the pure Linux sandbox argv builders and their unit tests out of
`codex-core`
- keep `core::landlock` as the spawn wrapper and update direct callers
to use `codex_sandboxing::landlock`
## Testing
- `cargo test -p codex-sandboxing`
- `cargo test -p codex-core landlock`
- `cargo test -p codex-cli debug_sandbox`
- `just argument-comment-lint`
## Notes
- this is step 1 of the move plan aimed at minimizing per-PR diffs
- no re-exports or no-op proxy methods were added
Moves Code Mode to a new crate with no dependencies on codex. This
create encodes the code mode semantics that we want for lifetime,
mounting, tool calling.
The model-facing surface is mostly unchanged. `exec` still runs raw
JavaScript, `wait` still resumes or terminates a `cell_id`, nested tools
are still available through `tools.*`, and helpers like `text`, `image`,
`store`, `load`, `notify`, `yield_control`, and `exit` still exist.
The major change is underneath that surface:
- Old code mode was an external Node runtime.
- New code mode is an in-process V8 runtime embedded directly in Rust.
- Old code mode managed cells inside a long-lived Node runner process.
- New code mode manages cells in Rust, with one V8 runtime thread per
active `exec`.
- Old code mode used JSON protocol messages over child stdin/stdout plus
Node worker-thread messages.
- New code mode uses Rust channels and direct V8 callbacks/events.
This PR also fixes the two migration regressions that fell out of that
substrate change:
- `wait { terminate: true }` now waits for the V8 runtime to actually
stop before reporting termination.
- synchronous top-level `exit()` now succeeds again instead of surfacing
as a script error.
---
- `core/src/tools/code_mode/*` is now mostly an adapter layer for the
public `exec` / `wait` tools.
- `code-mode/src/service.rs` owns cell sessions and async control flow
in Rust.
- `code-mode/src/runtime/*.rs` owns the embedded V8 isolate and
JavaScript execution.
- each `exec` spawns a dedicated runtime thread plus a Rust
session-control task.
- helper globals are installed directly into the V8 context instead of
being injected through a source prelude.
- helper modules like `tools.js` and `@openai/code_mode` are synthesized
through V8 module resolution callbacks in Rust.
---
Also added a benchmark for showing the speed of init and use of a code
mode env:
```
$ cargo bench -p codex-code-mode --bench exec_overhead -- --samples 30 --warm-iterations 25 --tool-counts 0,32,128
Finished [`bench` profile [optimized]](https://doc.rust-lang.org/cargo/reference/profiles.html#default-profiles) target(s) in 0.18s
Running benches/exec_overhead.rs (target/release/deps/exec_overhead-008c440d800545ae)
exec_overhead: samples=30, warm_iterations=25, tool_counts=[0, 32, 128]
scenario tools samples warmups iters mean/exec p95/exec rssΔ p50 rssΔ max
cold_exec 0 30 0 1 1.13ms 1.20ms 8.05MiB 8.06MiB
warm_exec 0 30 1 25 473.43us 512.49us 912.00KiB 1.33MiB
cold_exec 32 30 0 1 1.03ms 1.15ms 8.08MiB 8.11MiB
warm_exec 32 30 1 25 509.73us 545.76us 960.00KiB 1.30MiB
cold_exec 128 30 0 1 1.14ms 1.19ms 8.30MiB 8.34MiB
warm_exec 128 30 1 25 575.08us 591.03us 736.00KiB 864.00KiB
memory uses a fresh-process max RSS delta for each scenario
```
---------
Co-authored-by: Codex <noreply@openai.com>
- Split the feature system into a new `codex-features` crate.
- Cut `codex-core` and workspace consumers over to the new config and
warning APIs.
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
- Move the auth implementation and token data into codex-login.
- Keep codex-core re-exporting that surface from codex-login for
existing callers.
---------
Co-authored-by: Codex <noreply@openai.com>
- Move core/src/terminal.rs and its tests into a standalone
terminal-detection workspace crate.
- Update direct consumers to depend on codex-terminal-detection and
import terminal APIs directly.
---------
Co-authored-by: Codex <noreply@openai.com>
The idea is that codex-exec exposes an Environment struct with services
on it. Each of those is a trait.
Depending on construction parameters passed to Environment they are
either backed by local or remote server but core doesn't see these
differences.
Adds an environment crate and environment + file system abstraction.
Environment is a combination of attributes and services specific to
environment the agent is connected to:
File system, process management, OS, default shell.
The goal is to move most of agent logic that assumes environment to work
through the environment abstraction.
### Summary
Propagate trace context originating at app-server RPC method handlers ->
codex core submission loop (so this includes spans such as `run_turn`!).
This implements PR 2 of the app-server tracing rollout.
This also removes the old lower-level env-based reparenting in core so
explicit request/submission ancestry wins instead of being overridden by
ambient `TRACEPARENT` state.
### What changed
- Added `trace: Option<W3cTraceContext>` to codex_protocol::Submission
- Taught `Codex::submit()` / `submit_with_id()` to automatically capture
the current span context when constructing or forwarding a submission
- Wrapped the core submission loop in a submission_dispatch span
parented from Submission.trace
- Warn on invalid submission trace carriers and ignore them cleanly
- Removed the old env-based downstream reparenting path in core task
execution
- Stopped OTEL provider init from implicitly attaching env trace context
process-wide
- Updated mcp-server Submission call sites for the new field
Added focused unit tests for:
- capturing trace context into Submission
- preferring `Submission.trace` when building the core dispatch span
### Why
PR 1 gave us consistent inbound request spans in app-server, but that
only covered the transport boundary. For long-running work like turns
and reviews, the important missing piece was preserving ancestry after
the request handler returns and core continues work on a different async
path.
This change makes that handoff explicit and keeps the parentage rules
simple:
- app-server request span sets the current context
- `Submission.trace` snapshots that context
- core restores it once, at the submission boundary
- deeper core spans inherit naturally
That also lets us stop relying on env-based reparenting for this path,
which was too ambient and could override explicit ancestry.
## Summary
Add original-resolution support for `view_image` behind the
under-development `view_image_original_resolution` feature flag.
When the flag is enabled and the target model is `gpt-5.3-codex` or
newer, `view_image` now preserves original PNG/JPEG/WebP bytes and sends
`detail: "original"` to the Responses API instead of using the legacy
resize/compress path.
## What changed
- Added `view_image_original_resolution` as an under-development feature
flag.
- Added `ImageDetail` to the protocol models and support for serializing
`detail: "original"` on tool-returned images.
- Added `PromptImageMode::Original` to `codex-utils-image`.
- Preserves original PNG/JPEG/WebP bytes.
- Keeps legacy behavior for the resize path.
- Updated `view_image` to:
- use the shared `local_image_content_items_with_label_number(...)`
helper in both code paths
- select original-resolution mode only when:
- the feature flag is enabled, and
- the model slug parses as `gpt-5.3-codex` or newer
- Kept local user image attachments on the existing resize path; this
change is specific to `view_image`.
- Updated history/image accounting so only `detail: "original"` images
use the docs-based GPT-5 image cost calculation; legacy images still use
the old fixed estimate.
- Added JS REPL guidance, gated on the same feature flag, to prefer JPEG
at 85% quality unless lossless is required, while still allowing other
formats when explicitly requested.
- Updated tests and helper code that construct
`FunctionCallOutputContentItem::InputImage` to carry the new `detail`
field.
## Behavior
### Feature off
- `view_image` keeps the existing resize/re-encode behavior.
- History estimation keeps the existing fixed-cost heuristic.
### Feature on + `gpt-5.3-codex+`
- `view_image` sends original-resolution images with `detail:
"original"`.
- PNG/JPEG/WebP source bytes are preserved when possible.
- History estimation uses the GPT-5 docs-based image-cost calculation
for those `detail: "original"` images.
#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/13050
- ⏳ `2` https://github.com/openai/codex/pull/13331
- ⏳ `3` https://github.com/openai/codex/pull/13049
## 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>"}]}}
```
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
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)
## 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.
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.
## 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.
## Why
Compiling `codex-rs/core` is a bottleneck for local iteration, so this
change continues the ongoing extraction of config-related functionality
out of `codex-core` and into `codex-config`.
The goal is not just to move code, but to reduce `codex-core` ownership
and indirection so more code depends on `codex-config` directly.
## What Changed
- Moved config diagnostics logic from
`core/src/config_loader/diagnostics.rs` into
`config/src/diagnostics.rs`.
- Updated `codex-core` to use `codex-config` diagnostics types/functions
directly where possible.
- Removed the `core/src/config_loader/diagnostics.rs` shim module
entirely; the remaining `ConfigToml`-specific calls are in
`core/src/config_loader/mod.rs`.
- Moved `CONFIG_TOML_FILE` into `codex-config` and updated existing
references to use `codex_config::CONFIG_TOML_FILE` directly.
- Added a direct `codex-config` dependency to `codex-cli` for its
`CONFIG_TOML_FILE` use.
## 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
Bumps [arc-swap](https://github.com/vorner/arc-swap) from 1.8.0 to
1.8.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/vorner/arc-swap/blob/master/CHANGELOG.md">arc-swap's
changelog</a>.</em></p>
<blockquote>
<h1>1.8.2</h1>
<ul>
<li>Proper gate of <code>Pin</code> (since 1.39 - we are not using only
<code>Pin</code>, but also
<code>Pin::into_inner</code>, <a
href="https://redirect.github.com/vorner/arc-swap/issues/197">#197</a>).</li>
</ul>
<h1>1.8.1</h1>
<ul>
<li>Some more careful orderings (<a
href="https://redirect.github.com/vorner/arc-swap/issues/195">#195</a>).</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="19f0d661a2"><code>19f0d66</code></a>
Version 1.8.2</li>
<li><a
href="c222a22864"><code>c222a22</code></a>
Release 1.8.1</li>
<li><a
href="cccf3548a8"><code>cccf354</code></a>
Upgrade the other ordering too, for transitivity</li>
<li><a
href="e94df5511a"><code>e94df55</code></a>
Merge pull request <a
href="https://redirect.github.com/vorner/arc-swap/issues/195">#195</a>
from 0xfMel/master</li>
<li><a
href="bd5d3276e4"><code>bd5d327</code></a>
Fix Debt::pay failure ordering</li>
<li><a
href="22431daf64"><code>22431da</code></a>
Merge pull request <a
href="https://redirect.github.com/vorner/arc-swap/issues/189">#189</a>
from atouchet/rdm</li>
<li><a
href="b142bd81da"><code>b142bd8</code></a>
Update Readme</li>
<li>See full diff in <a
href="https://github.com/vorner/arc-swap/compare/v1.8.0...v1.8.2">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 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>
This PR keeps compaction context-layout test coverage separate from
runtime compaction behavior changes, so runtime logic review can stay
focused.
## Included
- Adds reusable context snapshot helpers in
`core/tests/common/context_snapshot.rs` for rendering model-visible
request/history shapes.
- Standardizes helper naming for readability:
- `format_request_input_snapshot`
- `format_response_items_snapshot`
- `format_labeled_requests_snapshot`
- `format_labeled_items_snapshot`
- Expands snapshot coverage for both local and remote compaction flows:
- pre-turn auto-compaction
- pre-turn failure/context-window-exceeded paths
- mid-turn continuation compaction
- manual `/compact` with and without prior user turns
- Captures both sides where relevant:
- compaction request shape
- post-compaction history layout shape
- Adds/uses shared request-inspection helpers so assertions target
structured request content instead of ad-hoc JSON string parsing.
- Aligns snapshots/assertions to current behavior and leaves explicit
`TODO(ccunningham)` notes where behavior is known and intentionally
deferred.
## Not Included
- No runtime compaction logic changes.
- No model-visible context/state behavior changes.
`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`.
## Why
`codex-core` was being built in multiple feature-resolved permutations
because test-only behavior was modeled as crate features. For a large
crate, those permutations increase compile cost and reduce cache reuse.
## Net Change
- Removed the `test-support` crate feature and related feature wiring so
`codex-core` no longer needs separate feature shapes for test consumers.
- Standardized cross-crate test-only access behind
`codex_core::test_support`.
- External test code now imports helpers from
`codex_core::test_support`.
- Underlying implementation hooks are kept internal (`pub(crate)`)
instead of broadly public.
## Outcome
- Fewer `codex-core` build permutations.
- Better incremental cache reuse across test targets.
- No intended production behavior change.
## Why
`codex-core` enabled `deterministic_process_ids` through a self
dev-dependency.
That forced a second feature-resolved build of the same crate, which
increased
compile time and test latency.
## What Changed
- Removed the `deterministic_process_ids` feature from
`codex-rs/core/Cargo.toml`.
- Removed the self dev-dependency on `codex-core` that enabled that
feature.
- Removed the Bazel `deterministic_process_ids` crate feature for
`codex-core`.
- Added a test-only `AtomicBool` override in unified exec process-id
allocation.
- Added a test-support setter for that override and re-exported it from
`codex-core`.
- Enabled deterministic process IDs in integration tests via
`core_test_support` ctor.
## Behavior
- Production behavior remains random process IDs.
- Unit tests remain deterministic via `cfg(test)`.
- Integration tests remain deterministic via explicit test-support
initialization.
## Validation
- `just fmt`
- `cargo test -p codex-core unified_exec::`
- `cargo test -p codex-core --test all unified_exec -- --test-threads=1`
- `cargo tree -p codex-core -e features` (verified the removed feature
path)
`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.
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)
**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.
We support requirements on Unix, loading from
`/etc/codex/requirements.toml`. On MacOS, we also support MDM.
Now, on Windows, we'll load requirements from
`%ProgramData%\OpenAI\Codex\requirements.toml`
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.
