## Why
We were seeing failures in the following tests as part of trying to get
all the tests running under Bazel on Windows in CI
(https://github.com/openai/codex/pull/16528):
```
suite::shell_command::unicode_output::with_login
suite::shell_command::unicode_output::without_login
```
Certainly `PATHEXT` should have been included in the extra `CORE_VARS`
list, so we fix that up here, but also take things a step further for
now by forcibly ensuring it is set on Windows in the return value of
`create_env()`. Once we get the Windows Bazel build working reliably
(i.e., after #16528 is merged), we should come back to this and confirm
we can remove the special case in `create_env()`.
## What
- Split core env inheritance into `COMMON_CORE_VARS` plus
platform-specific allowlists for Windows and Unix in
[`exec_env.rs`](https://github.com/openai/codex/blob/1b55c88fbf585b32cd553cb9d02ec817f2ad6ebc/codex-rs/core/src/exec_env.rs#L45-L81).
- Preserve `PATHEXT`, `USERNAME`, and `USERPROFILE` on Windows, and
`HOME` / locale vars on Unix.
- Backfill a default `PATHEXT` in `create_env()` on Windows if the
parent env does not provide one, so child process launch still works in
stripped-down Bazel environments.
- Extend the Windows exec-env test to assert mixed-case `PathExt`
survives case-insensitive core filtering, and document why the
shell-command Unicode test goes through a child process.
## Verification
- `cargo test -p codex-core exec_env::tests`
Addresses #16124
Problem: `codex --remote --cd <path>` canonicalized the path locally and
then omitted it from remote thread lifecycle requests, so remote-only
working directories failed or were ignored.
Solution: Keep remote startup on the local cwd, forward explicit `--cd`
values verbatim to `thread/start`, `thread/resume`, and `thread/fork`,
and cover the behavior with `codex-tui` tests.
Testing: I manually tested `--remote --cd` with both absolute and
relative paths and validated correct behavior.
---
Update based on code review feedback:
Problem: Remote `--cd` was forwarded to `thread/resume` and
`thread/fork`, but not to `thread/list` lookups, so `--resume --last`
and picker flows could select a session from the wrong cwd; relative cwd
filters also failed against stored absolute paths.
Solution: Apply explicit remote `--cd` to `thread/list` lookups for
`--last` and picker flows, normalize relative cwd filters on the
app-server before exact matching, and document/test the behavior.
Addresses #11555
Problem: macOS malloc stack-logging diagnostics could leak into the TUI
composer and get misclassified as pasted user input.
Solution: Strip `MallocStackLogging*` and `MallocLogFile*` during macOS
pre-main hardening and document the additional env cleanup.
Addresses #15640
Problem: `codex exec` panicked on macOS when sandboxed proxy discovery
hit a NULL `SCDynamicStore` handle in `system-configuration`.
Solution: Bump `hyper-util` and `system-configuration` to versions that
handle denied `configd` lookups safely, and refresh the Bazel lockfile.
Testing: Verified using the manual `printf '(version 1) (allow default)
(deny mach-lookup (global-name
"com.apple.SystemConfiguration.configd"))' > /tmp/deny-configd.sb
sandbox-exec -f /tmp/deny-configd.sb codex exec -s danger-full-access
"echo test"`. Prior to the fix, this caused a panic.
Addresses #15282
Problem: Codex warned about missing system bubblewrap even when
sandboxing was disabled.
Solution: Gate the bwrap warning on the active sandbox policy and skip
it for danger-full-access and external-sandbox modes.
Addresses #16671 and #14927
Problem: `mcpServerStatus/list` rebuilt MCP tool groups from sanitized
tool prefixes but looked them up by unsanitized server names, so
hyphenated servers rendered as having no tools in `/mcp`. This was
reported as a regression when the TUI switched to use the app server.
Solution: Build each server's tool map using the original server name's
sanitized prefix, include effective runtime MCP servers in the status
response, and add a regression test for hyphenated server names.
Addresses #16454
Problem: `/copy` could keep stale output after a turn with
commentary-only assistant text.
Solution: Cache the latest non-empty agent message during a turn and
promote it on turn completion.
Stacked on #16508.
This removes the temporary `codex-core` / `codex-login` re-export shims
from the ownership split and rewrites callsites to import directly from
`codex-model-provider-info`, `codex-models-manager`, `codex-api`,
`codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.
No behavior change intended; this is the mechanical import cleanup layer
split out from the ownership move.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
This is a follow-up to #16665. The Windows `unicode_output` test should
still exercise a child process so it verifies PowerShell's UTF-8 output
configuration, but `$env:COMSPEC` depends on that environment variable
surviving the curated Bazel test environment.
Using `cmd.exe` keeps the child-process coverage while avoiding both
bare `cmd` + `PATHEXT` lookup and `$env:COMSPEC` env passthrough
assumptions.
## What
- Run `cmd.exe /c echo naïve_café` in the Windows branch of
`unicode_output`.
## Verification
- `cargo test -p codex-core unicode_output`
## Why
Windows Bazel shell tests launch PowerShell with a curated environment,
so `PATHEXT` may be absent. The existing `unicode_output` test invokes
bare `cmd`, which can fail before the test exercises UTF-8 child-process
output.
## What
- Use `$env:COMSPEC /c echo naïve_café` in the Windows branch of
`unicode_output`.
- Preserve the external child-process path instead of switching the test
to a PowerShell builtin.
## Verification
- `cargo test -p codex-core unicode_output`
https://github.com/openai/codex/pull/16460 was a large PR created by
Codex to try to get the tests to pass under Bazel on Windows. Indeed, it
successfully ran all of the tests under `//codex-rs/core:` with its
changes to `codex-rs/core/`, though the full set of changes seems to be
too broad.
This PR tries to port the key changes, which are:
- Under Bazel, the `USERNAME` environment variable is not guaranteed to
be set on Windows, so for tests that need a non-empty env var as a
convenient substitute for an env var containing an API key, just use
`PATH`. Note that `PATH` is unlikely to contain characters that are not
allowed in an HTTP header value.
- Specify `"powershell.exe"` instead of just `"powershell"` in case the
`PATHEXT` env var gets lost in the shuffle.
## Summary
- split `models-manager` out of `core` and add `ModelsManagerConfig`
plus `Config::to_models_manager_config()` so model metadata paths stop
depending on `core::Config`
- move login-owned/auth-owned code out of `core` into `codex-login`,
move model provider config into `codex-model-provider-info`, move API
bridge mapping into `codex-api`, move protocol-owned types/impls into
`codex-protocol`, and move response debug helpers into a dedicated
`response-debug-context` crate
- move feedback tag emission into `codex-feedback`, relocate tests to
the crates that now own the code, and keep broad temporary re-exports so
this PR avoids a giant import-only rewrite
## Major moves and decisions
- created `codex-models-manager` as the owner for model
cache/catalog/config/model info logic, including the new
`ModelsManagerConfig` struct
- created `codex-model-provider-info` as the owner for provider config
parsing/defaults and kept temporary `codex-login`/`codex-core`
re-exports for old import paths
- moved `api_bridge` error mapping + `CoreAuthProvider` into
`codex-api`, while `codex-login::api_bridge` temporarily re-exports
those symbols and keeps the `auth_provider_from_auth` wrapper
- moved `auth_env_telemetry` and `provider_auth` ownership to
`codex-login`
- moved `CodexErr` ownership to `codex-protocol::error`, plus
`StreamOutput`, `bytes_to_string_smart`, and network policy helpers to
protocol-owned modules
- created `codex-response-debug-context` for
`extract_response_debug_context`, `telemetry_transport_error_message`,
and related response-debug plumbing instead of leaving that behavior in
`core`
- moved `FeedbackRequestTags`, `emit_feedback_request_tags`, and
`emit_feedback_request_tags_with_auth_env` to `codex-feedback`
- deferred removal of temporary re-exports and the mechanical import
rewrites to a stacked follow-up PR so this PR stays reviewable
## Test moves
- moved auth refresh coverage from `core/tests/suite/auth_refresh.rs` to
`login/tests/suite/auth_refresh.rs`
- moved text encoding coverage from
`core/tests/suite/text_encoding_fix.rs` to
`protocol/src/exec_output_tests.rs`
- moved model info override coverage from
`core/tests/suite/model_info_overrides.rs` to
`models-manager/src/model_info_overrides_tests.rs`
---------
Co-authored-by: Codex <noreply@openai.com>
Addresses #16655
Problem: `codex login --api-key` failed in Clap before Codex could show
the deprecation guidance.
Solution: Allow the hidden `--api-key` flag to parse with zero or one
values so both forms reach the `--with-api-key` message.
## Why
The Windows `ProviderAuthScript` test helpers do not need PowerShell.
Running them through `cmd.exe` is enough to emit the next fixture token
and rotate `tokens.txt`, and it avoids a PowerShell-specific dependency
in these tests.
## What changed
- Replaced the Windows `print-token.ps1` fixtures with `print-token.cmd`
in `codex-rs/core/src/models_manager/manager_tests.rs` and
`codex-rs/login/src/auth/auth_tests.rs`.
- Switched the failing external-auth helper in
`codex-rs/login/src/auth/auth_tests.rs` from `powershell.exe -Command
'exit 1'` to `cmd.exe /d /s /c 'exit /b 1'`.
- Updated Windows timeout comments so they no longer call out PowerShell
specifically.
## Verification
- `cargo test -p codex-login`
- `cargo test -p codex-core` (fails in unrelated
`core/src/config/config_tests.rs` assertions in this checkout)
## Why
`thread/shellCommand` executes the raw command string through the
current user shell, which is PowerShell on Windows. The two v2
app-server tests in `app-server/tests/suite/v2/thread_shell_command.rs`
used POSIX `printf`, so Bazel CI on Windows failed with `printf` not
being recognized as a PowerShell command.
For reference, the user-shell task wraps commands with the active shell
before execution:
[`core/src/tasks/user_shell.rs`](https://github.com/openai/codex/blob/7a3eec6fdb356bd71f80582119eb829179ff0da1/codex-rs/core/src/tasks/user_shell.rs#L120-L126).
## What Changed
Added a test-local helper that builds a shell-appropriate output command
and expected newline sequence from `default_user_shell()`:
- PowerShell: `Write-Output '...'` with `\r\n`
- Cmd: `echo ...` with `\r\n`
- POSIX shells: `printf '%s\n' ...` with `\n`
Both `thread_shell_command_runs_as_standalone_turn_and_persists_history`
and `thread_shell_command_uses_existing_active_turn` now use that
helper.
## Verification
- `cargo test -p codex-app-server thread_shell_command`
- Persist trusted cwd state during thread/start when the resolved
sandbox is elevated.
- Add app-server coverage for trusted root resolution and confirm
turn/start does not mutate trust.
## Why
This continues the compile-time cleanup from #16630. `SessionTask`
implementations are monomorphized, but `Session` stores the task behind
a `dyn` boundary so it can drive and abort heterogenous turn tasks
uniformly. That means we can move the `#[async_trait]` expansion off the
implementation trait, keep a small boxed adapter only at the storage
boundary, and preserve the existing task lifecycle semantics while
reducing the amount of generated async-trait glue in `codex-core`.
One measurement caveat showed up while exploring this: a warm
incremental benchmark based on `touch core/src/tasks/mod.rs && cargo
check -p codex-core --lib` was basically flat, but that was the wrong
benchmark for this change. Using package-clean `codex-core` rebuilds,
like #16630, shows the real win.
Relevant pre-change code:
- [`SessionTask` with
`#[async_trait]`](https://github.com/openai/codex/blob/3c7f013f9735e67796c70d95f75f436b7f97e3ec/codex-rs/core/src/tasks/mod.rs#L129-L182)
- [`RunningTask` storing `Arc<dyn
SessionTask>`](https://github.com/openai/codex/blob/3c7f013f9735e67796c70d95f75f436b7f97e3ec/codex-rs/core/src/state/turn.rs#L69-L77)
## What changed
- Switched `SessionTask::{run, abort}` to native RPITIT futures with
explicit `Send` bounds.
- Added a private `AnySessionTask` adapter that boxes those futures only
at the `Arc<dyn ...>` storage boundary.
- Updated `RunningTask` to store `Arc<dyn AnySessionTask>` and removed
`#[async_trait]` from the concrete task impls plus test-only
`SessionTask` impls.
## Timing
Benchmarked package-clean `codex-core` rebuilds with dependencies left
warm:
```shell
cargo check -p codex-core --lib >/dev/null
cargo clean -p codex-core >/dev/null
/usr/bin/time -p cargo +nightly rustc -p codex-core --lib -- \
-Z time-passes \
-Z time-passes-format=json >/dev/null
```
| revision | rustc `total` | process `real` | `generate_crate_metadata`
| `MIR_borrow_checking` | `monomorphization_collector_graph_walk` |
| --- | ---: | ---: | ---: | ---: | ---: |
| parent `3c7f013f9735` | 67.21s | 67.71s | 24.61s | 23.43s | 22.43s |
| this PR `2cafd783ac22` | 35.08s | 35.60s | 8.01s | 7.25s | 7.15s |
| delta | -47.8% | -47.4% | -67.5% | -69.1% | -68.1% |
For completeness, the warm touched-file benchmark stayed flat (`1.96s`
parent vs `1.97s` this PR), which is why that benchmark should not be
used to evaluate this refactor.
## Verification
- Ran `cargo test -p codex-core`; this change compiled and task-related
tests passed before hitting the same unrelated 5
`config::tests::*guardian*` failures already present on the parent
stack.
## TL;DR
Fixes the issues when using Codex CLI with Zellij multiplexer. Before
this PR there would be no scrollback when using it inside a zellij
terminal.
## Problem
Addresses #2558
Zellij does not support ANSI scroll-region manipulation (`DECSTBM` /
Reverse Index) or the alternate screen buffer in the way traditional
terminals do. When codex's TUI runs inside Zellij, two things break: (1)
inline history insertion corrupts the display because the scroll-region
escape sequences are silently dropped or mishandled, and (2) the
composer textarea renders with inherited background/foreground styles
that produce unreadable text against Zellij's pane chrome.
## Mental model
The fix introduces a **Zellij mode** — a runtime boolean detected once
at startup via `codex_terminal_detection::terminal_info().is_zellij()` —
that gates two subsystems onto Zellij-safe terminal strategies:
- **History insertion** (`insert_history.rs`): Instead of using
`DECSTBM` scroll regions and Reverse Index (`ESC M`) to slide content
above the viewport, Zellij mode scrolls the screen by emitting `\n` at
the bottom row and then writes history lines at absolute positions. This
avoids every escape sequence Zellij mishandles.
- **Viewport expansion** (`tui.rs`): When the viewport grows taller than
available space, the standard path uses `scroll_region_up` on the
backend. Zellij mode instead emits newlines at the screen bottom to push
content up, then invalidates the ratatui diff buffer so the next draw is
a full repaint.
- **Composer rendering** (`chat_composer.rs`, `textarea.rs`): All text
rendering in the input area uses an explicit `base_style` with
`Color::Reset` foreground, preventing Zellij's pane styling from
bleeding into the textarea. The prompt chevron (`›`) and placeholder
text use explicit color constants instead of relying on `.bold()` /
`.dim()` modifiers that render inconsistently under Zellij.
## Non-goals
- This change does not fix or improve Zellij's terminal emulation
itself.
- It does not rearchitect the inline viewport model; it adds a parallel
code path gated on detection.
- It does not touch the alternate-screen disable logic (that already
existed and continues to use `is_zellij` via the same detection).
## Tradeoffs
- **Code duplication in `insert_history.rs`**: The Zellij and Standard
branches share the line-rendering loop (color setup, span merging,
`write_spans`) but differ in the scrolling preamble. The duplication is
intentional — merging them would force a complex conditional state
machine that's harder to reason about than two flat sequences.
- **`invalidate_viewport` after every Zellij history flush or viewport
expansion**: This forces a full repaint on every draw cycle in Zellij,
which is more expensive than ratatui's normal diff-based rendering. This
is necessary because Zellij's lack of scroll-region support means the
diff buffer's assumptions about what's on screen are invalid after we
manually move content.
- **Explicit colors vs semantic modifiers**: Replacing `.bold()` /
`.dim()` with `Color::Cyan` / `Color::DarkGray` / `Color::White` in the
Zellij branch sacrifices theme-awareness for correctness. If the project
ever adopts a theming system, Zellij styling will need to participate.
## Architecture
The Zellij detection flag flows through three layers:
1. **`codex_terminal_detection`** — `TerminalInfo::is_zellij()` (new
convenience method) reads the already-detected `Multiplexer` variant.
2. **`Tui` struct** — caches `is_zellij` at construction; passes it into
`update_inline_viewport`, `flush_pending_history_lines`, and
`insert_history_lines_with_mode`.
3. **`ChatComposer` struct** — independently caches `is_zellij` at
construction; uses it in `render_textarea` for style decisions.
The two caches (`Tui.is_zellij` and `ChatComposer.is_zellij`) are read
from the same global `OnceLock<TerminalInfo>`, so they always agree.
## Observability
No new logging, metrics, or tracing is introduced. Diagnosis depends on:
- Whether `ZELLIJ` or `ZELLIJ_SESSION_NAME` env vars are set (the
detection heuristic).
- Visual inspection of the rendered TUI inside Zellij vs a standard
terminal.
- The insta snapshot `zellij_empty_composer` captures the Zellij-mode
render path.
## Tests
- `terminal_info_reports_is_zellij` — unit test in `terminal-detection`
confirming the convenience method.
- `zellij_empty_composer_snapshot` — insta snapshot in `chat_composer`
validating the Zellij render path for an empty composer.
- `vt100_zellij_mode_inserts_history_and_updates_viewport` — integration
test in `insert_history` verifying that Zellij-mode history insertion
writes content and shifts the viewport.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Addresses #16560
Problem: `/status` stopped showing the source thread id in forked TUI
sessions after the app-server migration.
Solution: Carry fork source ids through app-server v2 thread data and
the TUI session adapter, and update TUI fixtures so `/status` matches
the old TUI behavior.
Recently, I merged a number of PRs to increase startup timeouts for
scripts that ran under PowerShell, but in the failure for
`suite::codex_tool::test_shell_command_approval_triggers_elicitation`, I
found this in the error logs when running on Bazel with BuildBuddy:
```
[mcp stderr] 2026-04-02T19:54:10.758951Z ERROR codex_core::tools::router: error=Exit code: 1
[mcp stderr] Wall time: 0.2 seconds
[mcp stderr] Output:
[mcp stderr] 'New-Item' is not recognized as an internal or external command,
[mcp stderr] operable program or batch file.
[mcp stderr]
```
This error implies that the command was run under `cmd.exe` instead of
`pwsh.exe`. Under GitHub Actions, I suspect that the `%PATH%` that is
passed to our Bazel builder is scrubbed such that our tests cannot find
PowerShell where GitHub installs it. Having these explicit fallback
paths should help.
While we could enable these only for tests, I don't see any harm in
keeping them in production, as well.
Addresses #16389
Problem: `/review` follow-ups can crash when app-server TUI steers with
a stale active turn id; #14717 introduced the client-side race, and
#15714 only handled the “no active turn” half.
Solution: Treat turn-id mismatch as stale cached state too, sync to the
server’s current turn id, retry once, and let review turns fall into the
existing queue path.
Addresses #16562
Problem: Resume picker could keep a stale backend-provided thread title
instead of the latest name from session_index.jsonl.
Solution: Always backfill/override picker row names from local
session_index.jsonl and cover stale-name replacement with a regression
test.
Addresses #16514
Problem: Resume picker could show “No sessions yet” before the initial
session fetch finished.
Solution: Render a loading message while the first page is pending, and
keep the empty state for truly empty results.
In https://github.com/openai/codex/pull/16528, I am trying to get tests
running under Bazel on Windows, but currently I see:
```
thread 'suite::user_shell_cmd::user_shell_command_does_not_set_network_sandbox_env_var' (10220) panicked at core/tests\suite\user_shell_cmd.rs:358:5:
assertion failed: `(left == right)`
Diff < left / right > :
<1
>0
```
This PR updates the `assert_eq!()` to provide more information to help
diagnose the failure.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16606).
* #16608
* __->__ #16606
## Why
`external_bearer_only_auth_manager_uses_cached_provider_token` can fail
on Windows when cold `powershell.exe` startup exceeds the provider-auth
helper's 1s timeout. When that happens,
`AuthManager::resolve_external_api_key_auth()` [logs the resolver error
and returns
`None`](https://github.com/openai/codex/blob/024b08b411fe/codex-rs/login/src/auth/manager.rs#L1449-L1455),
which is exactly the assertion failure from the flake.
## What
- Invoke `powershell.exe` explicitly in the Windows provider-auth test
helpers in `login/src/auth/auth_tests.rs`.
- Increase the helper timeout to `10_000` ms and document why that slack
exists.
## Verification
- `cargo test -p codex-login`
Running multiple builds with no changes causes some differences, we see
that
https://app.buildbuddy.io/compare/a9719629-1660-4735-a477-d66357f234fb...df85310b-eb5c-4c10-8b79-4d0449ba6cdd#file
shows the file-differences between two Bazel builds.
These differences are caused by a non-deterministic `.git` entry in the
rules_rs crates that are created with `crate_git_repository`.
As a way to make these deterministic, we can remove this entry after we
download the git source, so that the input to the compile action is
deterministic.
### CLA
I have read the CLA Document and I hereby sign the CLA
## Why
`codex-rs/exec/src/lib.rs` already keeps unit tests in a sibling
`lib_tests.rs` module so the implementation stays top-heavy and easier
to read. This applies that same layout to the rest of
`codex-rs/exec/src` so each production file keeps its entry points and
helpers ahead of test code.
## What
- Move inline unit tests out of `cli.rs`, `main.rs`,
`event_processor_with_human_output.rs`, and
`event_processor_with_jsonl_output.rs` into sibling `*_tests.rs` files.
- Keep test modules wired through `#[cfg(test)]` plus `#[path = "..."]
mod tests;`, matching the `lib.rs` pattern.
- Preserve the existing test coverage and assertions while making this a
source-layout-only refactor.
## Verification
- `cargo test -p codex-exec`
## Why
The main Bazel CI lanes need compact execution logs to investigate cache
misses and unexpected rebuilds, but local users of the shared wrapper
should not pay that log-generation cost by default.
## What Changed
-
[`.github/scripts/run-bazel-ci.sh`](https://github.com/openai/codex/blob/a6ec239a24fd21507bb75a28f17277653f52e3a2/.github/scripts/run-bazel-ci.sh#L149-L153)
now appends `--execution_log_compact_file=...` only when
`CODEX_BAZEL_EXECUTION_LOG_COMPACT_DIR` is set; the caller owns creating
that directory.
-
[`.github/workflows/bazel.yml`](https://github.com/openai/codex/blob/a6ec239a24fd21507bb75a28f17277653f52e3a2/.github/workflows/bazel.yml#L66-L174)
enables that env var only for the main `test` and `clippy` jobs, creates
the temp log directory in each job, and uploads the resulting `*.zst`
files from `runner.temp`.
## Verification
- `bash -n .github/scripts/run-bazel-ci.sh`
- Parsed `.github/workflows/bazel.yml` as YAML.
- Ran a local opt-in wrapper smoke test and confirmed it writes
`execution-log-cquery-local-*.zst` when the caller pre-creates
`CODEX_BAZEL_EXECUTION_LOG_COMPACT_DIR`.
## Why
This finishes the config-type move out of `codex-core` by removing the
temporary compatibility shim in `codex_core::config::types`. Callers now
depend on `codex-config` directly, which keeps these config model types
owned by the config crate instead of re-expanding `codex-core` as a
transitive API surface.
## What Changed
- Removed the `codex-rs/core/src/config/types.rs` re-export shim and the
`core::config::ApprovalsReviewer` re-export.
- Updated `codex-core`, `codex-cli`, `codex-tui`, `codex-app-server`,
`codex-mcp-server`, and `codex-linux-sandbox` call sites to import
`codex_config::types` directly.
- Added explicit `codex-config` dependencies to downstream crates that
previously relied on the `codex-core` re-export.
- Regenerated `codex-rs/core/config.schema.json` after updating the
config docs path reference.
## Why
`codex-rs/core/src/config/types.rs` is a plain config-type module with
no dependency on `codex-core`. Moving it into `codex-config` shrinks the
core crate and gives config-only consumers a more natural dependency
boundary.
## What Changed
- Added `codex_config::types` with the moved structs, enums, constants,
and unit tests.
- Kept `codex_core::config::types` as a compatibility re-export to avoid
a broad call-site migration in this PR.
- Switched notice-table writes in `core/src/config/edit.rs` to a local
`NOTICE_TABLE_KEY` constant.
- Added the `wildmatch` runtime dependency and `tempfile` test
dependency to `codex-config`.
## Why
#16513 moved pure tool-registry planning into `codex-tools`, but much of
the corresponding spec/feature-gating coverage still lived in
`codex-core`. That leaves the tests for planner behavior in the crate
that no longer owns that logic and makes the next extraction steps
harder to review.
## What
Move the planner-only `spec_tests.rs` coverage into
`codex-rs/tools/src/tool_registry_plan_tests.rs` and wire it up from
`codex-rs/tools/src/tool_registry_plan.rs` using the crate-local `#[path
= "tool_registry_plan_tests.rs"] mod tests;` pattern.
The `codex-core` test file now keeps the core-side integration checks:
router-visible model tool lists, namespaced handler alias registration,
shell adapter behavior, and MCP schema edge cases that still exercise
the `core` binding layer.
## Verification
- `cargo test -p codex-tools`
- `cargo test -p codex-core tools::spec::tests`
## Why
This is a larger step in the `codex-core` -> `codex-tools` migration
called out in `AGENTS.md`.
`codex-rs/core/src/tools/spec.rs` had become mostly pure tool-spec
assembly plus handler registration. That made it hard to move more of
the tool-definition layer into `codex-tools`, because the runtime
binding and the crate-independent planning logic were still interleaved
in one function.
Splitting those concerns gives `codex-tools` ownership of the
declarative registry plan while keeping `codex-core` responsible for
instantiating concrete handlers.
## What Changed
- Add a `codex-tools` registry-plan layer in
`codex-rs/tools/src/tool_registry_plan.rs` and
`codex-rs/tools/src/tool_registry_plan_types.rs`.
- Move feature-gated tool-spec assembly, MCP/dynamic tool conversion,
tool-search aliases, and code-mode nested-plan expansion into
`codex-tools`.
- Keep `codex-rs/core/src/tools/spec.rs` as the core-side adapter that
maps each planned handler kind to concrete runtime handler instances.
- Update `spec_tests.rs` to import the moved `codex_tools` symbols
directly instead of relying on top-level `spec.rs` re-exports.
This is intended to be a straight refactor with no behavior change and
no new test surface.
## Verification
- `cargo test -p codex-tools`
- `cargo test -p codex-core tools::spec::tests`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16513).
* #16521
* __->__ #16513
This PR updates `Cargo.lock` to remove `codex-core` from
`mcp_test_support`, which corresponds to
`codex-rs/mcp-server/tests/common/Cargo.toml`. As noted in #16512, it
updated that crate to drop its `codex-core` dependency.
## Why
`codex-core` was re-exporting APIs owned by sibling `codex-*` crates,
which made downstream crates depend on `codex-core` as a proxy module
instead of the actual owner crate.
Removing those forwards makes crate boundaries explicit and lets leaf
crates drop unnecessary `codex-core` dependencies. In this PR, this
reduces the dependency on `codex-core` to `codex-login` in the following
files:
```
codex-rs/backend-client/Cargo.toml
codex-rs/mcp-server/tests/common/Cargo.toml
```
## What
- Remove `codex-rs/core/src/lib.rs` re-exports for symbols owned by
`codex-login`, `codex-mcp`, `codex-rollout`, `codex-analytics`,
`codex-protocol`, `codex-shell-command`, `codex-sandboxing`,
`codex-tools`, and `codex-utils-path`.
- Delete the `default_client` forwarding shim in `codex-rs/core`.
- Update in-crate and downstream callsites to import directly from the
owning `codex-*` crate.
- Add direct Cargo dependencies where callsites now target the owner
crate, and remove `codex-core` from `codex-rs/backend-client`.
## Why
This is another small step in the `codex-core` -> `codex-tools`
migration described in `AGENTS.md`.
`core/src/tools/spec.rs` and `core/src/tools/code_mode/mod.rs` were both
hand-rolling the same pure transformation: convert visible `ToolSpec`s
into code-mode nested tool definitions, then sort and deduplicate by
tool name. That logic does not depend on core runtime state or handlers,
so keeping it in `codex-core` makes `spec.rs` harder to peel out later
than it needs to be.
## What Changed
- Add `collect_code_mode_tool_definitions()` to
`codex-rs/tools/src/code_mode.rs`.
- Reuse that helper from `codex-rs/core/src/tools/spec.rs` when
assembling the `exec` tool description.
- Reuse the same helper from `codex-rs/core/src/tools/code_mode/mod.rs`
when exposing nested tool metadata to the code-mode runtime.
This is intended to be a straight refactor with no behavior change and
no new test surface.
## Verification
- `cargo test -p codex-tools`
- `cargo test -p codex-core tools::spec::tests`
- `cargo test -p codex-core code_mode_only_`
Michael Bolin ·
Eric Traut ·
Ahmed Ibrahim ·
starr-openai ·
fcoury-oai ·
Tyler French ·
jif-oai ·