## 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
Once the repo-local lint exists, `codex-rs` needs to follow the
checked-in convention and CI needs to keep it from drifting. This commit
applies the fallback `/*param*/` style consistently across existing
positional literal call sites without changing those APIs.
The longer-term preference is still to avoid APIs that require comments
by choosing clearer parameter types and call shapes. This PR is
intentionally the mechanical follow-through for the places where the
existing signatures stay in place.
After rebasing onto newer `main`, the rollout also had to cover newly
introduced `tui_app_server` call sites. That made it clear the first cut
of the CI job was too expensive for the common path: it was spending
almost as much time installing `cargo-dylint` and re-testing the lint
crate as a representative test job spends running product tests. The CI
update keeps the full workspace enforcement but trims that extra
overhead from ordinary `codex-rs` PRs.
## What changed
- keep a dedicated `argument_comment_lint` job in `rust-ci`
- mechanically annotate remaining opaque positional literals across
`codex-rs` with exact `/*param*/` comments, including the rebased
`tui_app_server` call sites that now fall under the lint
- keep the checked-in style aligned with the lint policy by using
`/*param*/` and leaving string and char literals uncommented
- cache `cargo-dylint`, `dylint-link`, and the relevant Cargo
registry/git metadata in the lint job
- split changed-path detection so the lint crate's own `cargo test` step
runs only when `tools/argument-comment-lint/*` or `rust-ci.yml` changes
- continue to run the repo wrapper over the `codex-rs` workspace, so
product-code enforcement is unchanged
Most of the code changes in this commit are intentionally mechanical
comment rewrites or insertions driven by the lint itself.
## Verification
- `./tools/argument-comment-lint/run.sh --workspace`
- `cargo test -p codex-tui-app-server -p codex-tui`
- parsed `.github/workflows/rust-ci.yml` locally with PyYAML
---
* -> #14652
* #14651
Proposal: We want to record a dev message like so:
```
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "<user_action>
<context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
<action>review</action>
<results>
{findings_str}
</results>
</user_action>"
}
]
},
```
Without showing in the chat transcript.
Rough idea, but it fixes issue where the user finishes a review thread,
and asks the parent "fix the rest of the review issues" thinking that
the parent knows about it.
### Question: Why not a tool call?
Because the agent didn't make the call, it was a human. + we haven't
implemented sub-agents yet, and we'll need to think about the way we
represent these human-led tool calls for the agent.
Michael BolinandGitHub
jif-oaiandGitHub
dedrisian-oaiandGitHub