## Why
Now that workspace crate features have been removed and
`.github/scripts/verify_cargo_workspace_manifests.py` hard-bans new
ones, Rust CI should stop building and testing with `--all-features`.
Keeping `--all-features` in CI no longer buys us meaningful coverage for
`codex-rs`, but it still makes the workflow look like we rely on Cargo
feature permutations that we are explicitly trying to eliminate. It also
leaves stale examples in the repo that suggest `--all-features` is a
normal or recommended way to run the workspace.
## What changed
- removed `--all-features` from the Rust CI `cargo chef cook`, `cargo
clippy`, and `cargo nextest` invocations in
`.github/workflows/rust-ci-full.yml`
- updated the `just test` guidance in `justfile` to reflect that
workspace crate features are banned and there should be no need to add
`--all-features`
- updated the multiline command example and snapshot in
`codex-rs/tui/src/history_cell.rs` to stop rendering `cargo test
--all-features --quiet`
- tightened the verifier docstring in
`.github/scripts/verify_cargo_workspace_manifests.py` so it no longer
talks about temporary remaining exceptions
## How tested
- `python3 .github/scripts/verify_cargo_workspace_manifests.py`
- `cargo test -p codex-tui`
## Why
Follow-up to #16379.
`codex-rs/core/src/tools/spec.rs` and the corresponding handlers still
owned several pure tool-definition helpers even though they do not need
`codex-core` runtime state. Keeping that spec-only logic in `codex-core`
keeps the crate boundary blurry and works against the guidance in
`AGENTS.md` to keep shared tooling out of `codex-core` when possible.
This change takes another step toward a dedicated `codex-tools` crate by
moving more metadata and schema-building code behind the `codex-tools`
API while leaving the actual tool execution paths in `codex-core`.
## What Changed
- Added `codex-rs/tools/src/apply_patch_tool.rs` to own
`ApplyPatchToolArgs`, the freeform/json `apply_patch` tool specs, and
the moved `tool_apply_patch.lark` grammar.
- Updated `codex-rs/tools/BUILD.bazel` so Bazel exposes the moved
grammar file to `codex-tools`.
- Moved the `request_user_input` availability and description helpers
into `codex-rs/tools/src/request_user_input_tool.rs`, with the related
unit tests moved alongside that business logic.
- Moved `request_permissions_tool_description()` into
`codex-rs/tools/src/local_tool.rs`.
- Rewired `codex-rs/core/src/tools/spec.rs`,
`codex-rs/core/src/tools/handlers/apply_patch.rs`, and
`codex-rs/core/src/tools/handlers/request_user_input.rs` to consume the
new `codex-tools` exports instead of local helper code.
- Removed the now-redundant helper implementations and tests from
`codex-core`, plus a couple of stale `client_common` re-exports that
became unused after the move.
## Testing
- `cargo test -p codex-tools`
- `cargo test -p codex-core tools::spec::tests`
- `cargo test -p codex-core tools::handlers::apply_patch::tests`
## Why
`codex-otel` still carried `disable-default-metrics-exporter`, which was
the last remaining workspace crate feature.
We are removing workspace crate features because they do not fit our
current build model well:
- our Bazel setup does not honor crate features today, which can let
feature-gated issues go unnoticed
- they create extra crate build permutations that we want to avoid
For this case, the feature was only being used to keep the built-in
Statsig metrics exporter off in test and debug-oriented contexts. This
repo already treats `debug_assertions` as the practical proxy for that
class of behavior, so OTEL should follow the same convention instead of
keeping a dedicated crate feature alive.
## What changed
- removed `disable-default-metrics-exporter` from
`codex-rs/otel/Cargo.toml`
- removed the `codex-otel` dev-dependency feature activation from
`codex-rs/core/Cargo.toml`
- changed `codex-rs/otel/src/config.rs` so the built-in
`OtelExporter::Statsig` default resolves to `None` when
`debug_assertions` is enabled, with a focused unit test covering that
behavior
- removed the final feature exceptions from
`.github/scripts/verify_cargo_workspace_manifests.py`, so workspace
crate features are now hard-banned instead of temporarily allowlisted
- expanded the verifier error message to explain the Bazel mismatch and
build-permutation cost behind that policy
## How tested
- `python3 .github/scripts/verify_cargo_workspace_manifests.py`
- `cargo test -p codex-otel`
- `cargo test -p codex-core
metrics_exporter_defaults_to_statsig_when_missing`
- `cargo test -p codex-app-server app_server_default_analytics_`
- `just bazel-lock-check`
## Why
`codex-core` already owns too much of the tool stack, and `AGENTS.md`
explicitly pushes us to move shared code out of `codex-core` instead of
letting it keep growing. This PR takes the next incremental step in
moving `core/src/tools` toward `codex-rs/tools` by extracting
low-coupling tool configuration and image-detail gating logic into
`codex-tools`.
That gives later extraction work a cleaner boundary to build on without
trying to move the entire tools subtree in one shot.
## What changed
- moved `ToolsConfig`, `ToolsConfigParams`, shell backend config, and
unified-exec session selection from `core/src/tools/spec.rs` into
`codex-tools`
- moved original image-detail gating and normalization into
`codex-tools`
- updated `codex-core` to consume the new `codex-tools` exports and pass
a rendered agent-type description instead of raw role config
- kept `codex-rs/tools/src/lib.rs` exports-only, with extracted unit
tests living in sibling `*_tests.rs` modules
## Testing
- `cargo test -p codex-tools`
- `cargo test -p codex-core --lib tools::spec::`
## Why
`voice-input` is the only remaining TUI crate feature, but it is also a
default feature and nothing in the workspace selects it explicitly. In
practice it is just acting as a proxy for platform support, which is
better expressed with target-specific dependencies and cfgs.
## What changed
- remove the `voice-input` feature from `codex-tui`
- make `cpal` a normal non-Linux target dependency
- replace the feature-based voice and audio cfgs with pure
Linux-vs-non-Linux cfgs
- shrink the workspace-manifest verifier allowlist to remove the
remaining `codex-tui` exception
## How tested
- `python3 .github/scripts/verify_cargo_workspace_manifests.py`
- `cargo test -p codex-tui`
- `just bazel-lock-check`
- `just argument-comment-lint -p codex-tui`
## Why
`voice-input` is the only remaining TUI crate feature, but it is also a default feature and nothing in the workspace selects it explicitly. In practice it is just acting as a proxy for platform support, which is better expressed with target-specific dependencies and cfgs.
## What changed
- remove the `voice-input` feature from `codex-tui`
- make `cpal` a normal non-Linux target dependency
- replace the feature-based voice/audio cfgs with pure Linux-vs-non-Linux cfgs
- shrink the workspace-manifest verifier allowlist to remove the remaining `codex-tui` exception
## Why
`voice-input` is the only remaining TUI crate feature, but it is also a default feature and nothing in the workspace selects it explicitly. In practice it is just acting as a proxy for platform support, which is better expressed with target-specific dependencies and cfgs.
## What changed
- remove the `voice-input` feature from `codex-tui`
- make `cpal` a normal non-Linux target dependency
- replace the feature-based voice/audio cfgs with pure Linux-vs-non-Linux cfgs
- shrink the workspace-manifest verifier allowlist to remove the remaining `codex-tui` exception
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui`
were only gating test-only and debug-only behavior. Those feature
toggles add Cargo and Bazel permutations without buying anything, and
they make it easier for more crate features to linger in the workspace.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- always compile the VT100 integration tests in the TUI test target
instead of hiding them behind a Cargo feature
- remove the unused textarea debug logging branch instead of replacing
it with another gate
- add the required argument-comment annotations in the VT100 tests now
that Bazel sees those callsites during linting
- shrink the manifest verifier allowlist again so only the remaining
real feature exceptions stay permitted
## How tested
- `cargo test -p codex-tui`
- `just argument-comment-lint -p codex-tui`
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was mixing two different roles: the real HTTP
client and the mock implementation used by tests and local mock mode.
Keeping both in the same crate forced Cargo feature toggles and Bazel
`crate_features` just to pick an implementation.
This change keeps `codex-cloud-tasks-client` focused on the shared API
surface and real backend client, and moves the mock implementation into
its own crate so we can remove those feature permutations cleanly.
## What changed
- add a new `codex-cloud-tasks-mock-client` crate that owns `MockClient`
- remove the `mock` and `online` features from
`codex-cloud-tasks-client`
- make `codex-cloud-tasks-client` unconditionally depend on
`codex-backend-client` and export `HttpClient` directly
- gate the mock-mode path in `codex-cloud-tasks` behind
`#[cfg(debug_assertions)]`, so release builds always initialize the real
HTTP client
- update `codex-cloud-tasks` and its tests to use
`codex-cloud-tasks-mock-client::MockClient` wherever mock behavior is
needed
- remove the matching Bazel `crate_features` override and shrink the
manifest verifier allowlist accordingly
## How tested
- `cargo test -p codex-cloud-tasks-client`
- `cargo test -p codex-cloud-tasks-mock-client`
- `cargo test -p codex-cloud-tasks`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16456).
* #16457
* __->__ #16456
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was still using Cargo features to select its HTTP and mock implementations. That leaks feature permutations into both Cargo and Bazel for a crate that does not need them.
## What changed
- delete the `online` and `mock` crate features from `codex-cloud-tasks-client`
- make `codex-backend-client` unconditional and always export both `HttpClient` and `MockClient`
- remove the internal `features = ["mock", "online"]` activation from `codex-cloud-tasks`
- remove the matching Bazel `crate_features` override
- shrink the manifest verifier allowlist to match the remaining exceptions
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was still using Cargo features to select its HTTP and mock implementations. That leaks feature permutations into both Cargo and Bazel for a crate that does not need them.
## What changed
- delete the `online` and `mock` crate features from `codex-cloud-tasks-client`
- make `codex-backend-client` unconditional and always export both `HttpClient` and `MockClient`
- remove the internal `features = ["mock", "online"]` activation from `codex-cloud-tasks`
- remove the matching Bazel `crate_features` override
- shrink the manifest verifier allowlist to match the remaining exceptions
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was still using Cargo features to select its HTTP and mock implementations. That leaks feature permutations into both Cargo and Bazel for a crate that does not need them.
## What changed
- delete the `online` and `mock` crate features from `codex-cloud-tasks-client`
- make `codex-backend-client` unconditional and always export both `HttpClient` and `MockClient`
- remove the internal `features = ["mock", "online"]` activation from `codex-cloud-tasks`
- remove the matching Bazel `crate_features` override
- shrink the manifest verifier allowlist to match the remaining exceptions
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was still using Cargo features to select its HTTP and mock implementations. That leaks feature permutations into both Cargo and Bazel for a crate that does not need them.
## What changed
- delete the `online` and `mock` crate features from `codex-cloud-tasks-client`
- make `codex-backend-client` unconditional and always export both `HttpClient` and `MockClient`
- remove the internal `features = ["mock", "online"]` activation from `codex-cloud-tasks`
- remove the matching Bazel `crate_features` override
- shrink the manifest verifier allowlist to match the remaining exceptions
## Why
We already enforce workspace metadata and lint inheritance for
`codex-rs` manifests, but we still allow new crate features to slip into
the workspace. That makes it too easy to add more Cargo-only feature
permutations while we are trying to eliminate them.
## What changed
- extend `verify_cargo_workspace_manifests.py` to reject new
`[features]` tables in workspace crates
- reject new optional dependencies that create implicit crate features
- reject new workspace-to-workspace `features = [...]` activations and
`default-features = false`
- add a narrow temporary allowlist for the existing feature-bearing
manifests and internal feature activations
- make the allowlist self-shrinking so a follow-up removal has to delete
its corresponding exception
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16455).
* #16457
* #16456
* __->__ #16455
Makes fuzzy file search use case-insensitive matching instead of
smart-case in `codex-file-search`. I find smart-case to be a poor user
experience -using the wrong case for a letter drops its match so
significantly, it often drops off the results list, effectively making a
search case-sensitive.
## Why
The remaining `vt100-tests` and `debug-logs` features in `codex-tui` were only selecting debug and test-only behavior. Those are exactly the cases where this repo already accepts `#[cfg(debug_assertions)]` as the Cargo-free substitute.
## What changed
- delete `vt100-tests` and `debug-logs` from `codex-tui`
- gate the VT100 integration tests with `debug_assertions` instead of a Cargo feature
- gate the textarea debug log site with `debug_assertions`
- shrink the manifest verifier allowlist again so only the remaining real feature exceptions stay permitted
## Why
`codex-cloud-tasks-client` was still using Cargo features to select its HTTP and mock implementations. That leaks feature permutations into both Cargo and Bazel for a crate that does not need them.
## What changed
- delete the `online` and `mock` crate features from `codex-cloud-tasks-client`
- make `codex-backend-client` unconditional and always export both `HttpClient` and `MockClient`
- remove the internal `features = ["mock", "online"]` activation from `codex-cloud-tasks`
- remove the matching Bazel `crate_features` override
- shrink the manifest verifier allowlist to match the remaining exceptions
## Why
We already enforce workspace metadata and lint inheritance for `codex-rs` manifests, but we still allow new crate features to slip into the workspace. That makes it too easy to add more Cargo-only feature permutations while we are trying to eliminate them.
## What changed
- extend `verify_cargo_workspace_manifests.py` to reject new `[features]` tables in workspace crates
- reject new optional dependencies that create implicit crate features
- reject new workspace-to-workspace `features = [...]` activations and `default-features = false`
- add a narrow temporary allowlist for the existing feature-bearing manifests and internal feature activations
- make the allowlist self-shrinking so a follow-up removal has to delete its corresponding exception
