## 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>"}]}}
```
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.
**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`
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
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`
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="baf10f9a74"><code>baf10f9</code></a>
[owo-colors] version 4.3.0</li>
<li><a
href="6abe2026c5"><code>6abe202</code></a>
[meta] prepare changelog</li>
<li><a
href="ca81447041"><code>ca81447</code></a>
[RFC] add ignore_flyimport and ignore_flyimport_methods (<a
href="https://redirect.github.com/owo-colors/owo-colors/issues/141">#141</a>)</li>
<li><a
href="61de72e7f9"><code>61de72e</code></a>
Exclude development script from published package (<a
href="https://redirect.github.com/owo-colors/owo-colors/issues/152">#152</a>)</li>
<li><a
href="b2ad6bcd41"><code>b2ad6bc</code></a>
update MSRV to Rust 1.81 (<a
href="https://redirect.github.com/owo-colors/owo-colors/issues/156">#156</a>)</li>
<li>See full diff in <a
href="https://github.com/owo-colors/owo-colors/compare/v4.2.3...v4.3.0">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>
## 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
## 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.
## 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.
## 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 [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="2f06b4c7cf"><code>2f06b4c</code></a>
chore: Release</li>
<li><a
href="57e13acb42"><code>57e13ac</code></a>
chore: Release</li>
<li><a
href="4f9066d8af"><code>4f9066d</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-cli/env_logger/issues/393">#393</a>
from rust-cli/renovate/crate-ci-typos-1.x</li>
<li><a
href="3e4709a266"><code>3e4709a</code></a>
chore(deps): Update Rust crate snapbox to v0.6.24 (<a
href="https://redirect.github.com/rust-cli/env_logger/issues/394">#394</a>)</li>
<li><a
href="80ff83adba"><code>80ff83a</code></a>
chore(deps): Update pre-commit hook crate-ci/typos to v1.42.3</li>
<li><a
href="76891b9e32"><code>76891b9</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-cli/env_logger/issues/392">#392</a>
from epage/template</li>
<li><a
href="14cda4a666"><code>14cda4a</code></a>
chore: Update from _rust template</li>
<li><a
href="e4f2b351a3"><code>e4f2b35</code></a>
chore(ci): Update action</li>
<li><a
href="6d0d36b072"><code>6d0d36b</code></a>
chore(ci): Clean up previous branch in case it was leaked</li>
<li><a
href="30b3b14bd6"><code>30b3b14</code></a>
chore(ci): Fix how rustfmt jobs run</li>
<li>Additional commits viewable in <a
href="https://github.com/rust-cli/env_logger/compare/v0.11.8...v0.11.9">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>
Co-authored-by: Eric Traut <etraut@openai.com>
## 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>
`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`.
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`.
`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)
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="b028e4f40e"><code>b028e4f</code></a>
1.12.3</li>
<li><a
href="5e195de266"><code>5e195de</code></a>
regex-automata-0.4.14</li>
<li><a
href="a3433f6918"><code>a3433f6</code></a>
regex-syntax-0.8.9</li>
<li><a
href="0c07fae444"><code>0c07fae</code></a>
regex-lite-0.1.9</li>
<li><a
href="6a810068f0"><code>6a81006</code></a>
cargo: exclude development scripts and fuzzing data</li>
<li><a
href="4733e28ba4"><code>4733e28</code></a>
automata: fix <code>onepass::DFA::try_search_slots</code> panic when too
many slots are ...</li>
<li>See full diff in <a
href="https://github.com/rust-lang/regex/compare/1.12.2...1.12.3">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>
**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.
## 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
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.
## 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`
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:
8b95d3e082/codex-rs/mcp-types/README.md
Now that `rmcp` is more mature, it makes more sense to use their MCP
types in Rust, as they handle details (like the `_meta` field) that our
custom version ignored. Though one advantage that our custom types had
is that our generated types implemented `JsonSchema` and `ts_rs::TS`,
whereas the types in `rmcp` do not. As such, part of the work of this PR
is leveraging the adapters between `rmcp` types and the serializable
types that are API for us (app server and MCP) introduced in #10356.
Note this PR results in a number of changes to
`codex-rs/app-server-protocol/schema`, which merit special attention
during review. We must ensure that these changes are still
backwards-compatible, which is possible because we have:
```diff
- export type CallToolResult = { content: Array<ContentBlock>, isError?: boolean, structuredContent?: JsonValue, };
+ export type CallToolResult = { content: Array<JsonValue>, structuredContent?: JsonValue, isError?: boolean, _meta?: JsonValue, };
```
so `ContentBlock` has been replaced with the more general `JsonValue`.
Note that `ContentBlock` was defined as:
```typescript
export type ContentBlock = TextContent | ImageContent | AudioContent | ResourceLink | EmbeddedResource;
```
so the deletion of those individual variants should not be a cause of
great concern.
Similarly, we have the following change in
`codex-rs/app-server-protocol/schema/typescript/Tool.ts`:
```
- export type Tool = { annotations?: ToolAnnotations, description?: string, inputSchema: ToolInputSchema, name: string, outputSchema?: ToolOutputSchema, title?: string, };
+ export type Tool = { name: string, title?: string, description?: string, inputSchema: JsonValue, outputSchema?: JsonValue, annotations?: JsonValue, icons?: Array<JsonValue>, _meta?: JsonValue, };
```
so:
- `annotations?: ToolAnnotations` ➡️ `JsonValue`
- `inputSchema: ToolInputSchema` ➡️ `JsonValue`
- `outputSchema?: ToolOutputSchema` ➡️ `JsonValue`
and two new fields: `icons?: Array<JsonValue>, _meta?: JsonValue`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10349).
* #10357
* __->__ #10349
* #10356
## 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.
Summary
- require `CODEX_HOME` to point to an existing directory before
canonicalizing and surface clear errors otherwise
- share the same helper logic in both `core` and `rmcp-client` and add
unit tests that cover missing, non-directory, valid, and default paths
This addresses #9222
Load requirements from Codex Backend. It only does this for enterprise
customers signed in with ChatGPT.
Todo in follow-up PRs:
* Add to app-server and exec too
* Switch from fail-open to fail-closed on failure
we can't use runfiles directory on Windows due to path lengths, so swap
to manifest strategy. Parsing the manifest is a bit complex and the
format is changing in Bazel upstream, so pull in the official Rust
library (via a small hack to make it importable...) and cleanup all the
associated logic to work cleanly in both bazel and cargo without extra
confusion
