feat: add claude code and codex plugins#224
Conversation
Signed-off-by: Will Killian <wkillian@nvidia.com>
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughAdds CLI plugin install/uninstall/doctor surfaces and implementation, generates local marketplace/plugin manifests, orchestrates host registration and rollback, implements plugin-shim sidecar lifecycle and hook forwarding (Codex/Claude), adds idle-shutdown tracking, and updates tests, docs, CI, and release automation. ChangesPlugin System Implementation
Estimated code review effort: ✨ Finishing Touches🧪 Generate unit tests (beta)
|
github-actions
Bot
added
size:XXL
…e-and-codex-plugins # Conflicts: # crates/cli/src/config.rs # crates/cli/src/main.rs
Signed-off-by: Will Killian <wkillian@nvidia.com>
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 10
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/cli/src/plugin_install/mod.rs`:
- Around line 74-92: The doctor function is ignoring the json parameter and
always sets skip_doctor to true; update the PluginInstallOptions creation in
doctor (and the other affected call site) to carry the _json flag (rename or use
the json param) through (e.g., add a json field to PluginInstallOptions or pass
a separate flag) and propagate that flag into run_for_hosts so doctor_host
receives it; then modify doctor_host (the doctor_host function that prints the
host-specific diagnostics) to branch on the JSON flag and emit structured JSON
output instead of plain-text fields (the plain prints around the current lines
~267-270) when json is true. Ensure unique symbols updated: doctor,
PluginInstallOptions, run_for_hosts invocation, and doctor_host.
- Around line 238-245: The uninstall path currently aborts if require_relay or
validate_relay_plugin_shim fail; instead, make relay validation best-effort
during uninstall: in run_plugin_uninstall remove the early error return from
require_relay/validate_relay_plugin_shim (or call them inside a match and treat
Err(_) as a logged warning) so state mutation and run_host_unregistration(host,
&mut state, ...) always run even if nemo-relay is missing; keep
require_relay/validate_relay_plugin_shim behavior strict for install/doctor code
paths but change the uninstall caller to catch errors and continue (log
diagnostics) rather than propagate them.
- Around line 171-173: The install_host flow currently writes the marketplace
then writes state, but if write_state(...) fails the marketplace tree is left
orphaned; update install_host so that after calling
write_plugin_marketplace(host, &layout, options) you attempt
write_state(&layout, options) and on any Err you synchronously remove the
generated marketplace (e.g. remove_dir_all(layout.marketplace_root) or
equivalent) before returning the error; reference the write_plugin_marketplace,
write_state, install_host function and layout.marketplace_root (and
HostRegistrationProgress if used) so the cleanup happens in the same error-path
to avoid leaving an install tree invisible to uninstall.
In `@crates/cli/src/plugin_install/state.rs`:
- Around line 146-178: In write_state, replace the silent fallback on
layout.state_path.parent().unwrap_or_else(|| Path::new(".")) with an explicit
expect call so construction bugs surface: call
layout.state_path.parent().expect("state_path should have a parent directory")
and pass that to write_state_for_host; mention the same descriptive message so
failures when computing the parent for write_state (which delegates to
write_state_for_host) are caught immediately.
In `@crates/cli/src/plugin_shim/claude.rs`:
- Around line 57-73: The branch that handles when json_env_string(&settings,
"ANTHROPIC_BASE_URL") != Some(gateway_url) erroneously deletes the backup via
remove_backup(&path) even though the file was left unchanged; update this branch
in the function handling restore (the block that reads settings with
read_json_object and compares via json_env_string) to NOT call
remove_backup(&path) when the current ANTHROPIC_BASE_URL is not
Relay-managed—keep the backup file intact so a future restore is possible; leave
the existing println message indicating the file was left unchanged but remove
the call to remove_backup(&path) in that else branch.
In `@crates/cli/src/plugin_shim/codex.rs`:
- Around line 154-191: The no-backup branch currently calls
remove_table_item_if_bool(&mut doc, "features", "hooks", true) whenever
preserve_hooks is false, which can clear users' pre-existing hooks; change this
so the removal is only performed if Relay actually owns the flag (minimum:
require provider_is_managed). In practice update the else-block to guard the
remove_table_item_if_bool call with provider_is_managed (or another explicit
ownership check such as feature_hooks_enabled(&doc) == Some(true) combined with
provider_is_managed) so remove_table_item_if_bool is only invoked when
provider_is_managed is true.
In `@crates/cli/src/plugin_shim/shared.rs`:
- Around line 22-46: The lock currently uses agent.as_arg() (in ensure_sidecar)
which causes different agents sharing the same resolved gateway URL to race;
change the lock naming to be derived from the resolved host:port for the
provided url instead of agent.as_arg(). Parse the url (e.g., with
url::Url::parse) to extract host_str() and port_or_known_default(), combine into
a filesystem-safe string (replace ':'/slashes as needed) and use that value in
the runtime.join(format!("{}-sidecar.lock", host_port)) creation; leave the rest
of ensure_sidecar (runtime_dir(), lock acquisition loop,
repair_stale_lock(&lock), start_sidecar(...), and lock removal) unchanged.
Ensure any parsing errors fall back to using the raw url string sanitized so
lock name always exists.
- Around line 516-523: runtime_dir currently falls back to a global temp path
causing cross-user collisions; update the function (runtime_dir) so that when
XDG_RUNTIME_DIR/TMPDIR/TEMP are absent you append a per-user segment (e.g. UID
or username) to the temp_dir path before joining "nemo-relay-plugin". Use
available env vars ("USER" or "USERNAME") or the platform UID as the user
identifier and ensure the same identifier is used on all platforms so
locks/logs/pids live under a user-scoped subdirectory.
In `@integrations/coding-agents/codex/README.md`:
- Around line 307-310: The README notes a race where Codex may send the provider
request before hooks like SessionStart or UserPromptSubmit run, causing missed
first-request capture; update the Codex lazy-start logic so the agent waits for
hook registration or a readiness signal before allowing the first provider
request: implement a simple readiness probe/handshake in the Codex startup flow
(e.g., block or buffer the first provider request until a
SessionStart/UserPromptSubmit hook handler is registered or a short timeout
elapses), or add an explicit Relay readiness API that Codex calls to confirm
hooks are active; mention the new readiness behavior and configuration
(timeout/backoff) in the docs for clarity.
In `@integrations/coding-agents/README.md`:
- Around line 25-26: The sentence is ambiguous about who performs the
installation; change the line describing `claude-code/` so the actor is
explicit—replace the pronoun "It" with a clear subject such as the command
`nemo-relay install claude-code` (e.g., "The `nemo-relay install claude-code`
command installs hook entries targeting `POST /hooks/claude-code` through
`nemo-relay` on `PATH`"), and keep references to `claude-code/`, `nemo-relay`,
`POST /hooks/claude-code`, and `PATH`.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: d8fff306-dd5a-46c4-a213-cb3633978e09
📒 Files selected for processing (42)
.agents/plugins/marketplace.json.claude-plugin/marketplace.json.github/ci-path-filters.yml.github/workflows/ci.yamlRELEASING.mdcrates/cli/src/config.rscrates/cli/src/gateway.rscrates/cli/src/main.rscrates/cli/src/plugin_install/host.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_install/mod.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/state.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/tests/coverage/server_tests.rsdocs/getting-started/installation.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/nemo-relay-cli/codex.mdxdocs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/plugin-installation.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/.claude-plugin/plugin.jsonintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/claude-code/hooks/hooks.jsonintegrations/coding-agents/codex/.codex-plugin/plugin.jsonintegrations/coding-agents/codex/README.mdintegrations/coding-agents/codex/hooks/hooks.jsonjustfile
📜 Review details
🧰 Additional context used
📓 Path-based instructions (33)
{docs/**,README.md,CONTRIBUTING.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
{docs/**,README.md,CONTRIBUTING.md}: For docs-only changes, run targeted checks only if commands, package names, or examples changed. Usejust docsfor docs-site builds andjust docs-linkcheckwhen links changed
Run docs site build withjust docs
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,CONTRIBUTING.md,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Run docs link validation with
just docs-linkcheckwhen links change
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
{docs/**,README.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Verify README and docs entry points still match current package names and paths for large or public-facing changes
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,examples/**,README.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Verify examples still run with documented commands for large or public-facing changes
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,**/Cargo.toml,**/package.json,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Ensure renamed public surfaces are reflected consistently in manifests and docs for large or public-facing changes
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.{md,mdx,py,sh,yaml,yml,toml,json}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repo references, and build commands current
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/claude-code/hooks/hooks.jsonintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/hooks/hooks.jsonintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.mdx
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
In MDX files, top-of-file comments must use JSX comment delimiters: {/* to open and */} to close. Do not use HTML comments for MDX SPDX headers.
MDX top-of-file SPDX comments must use {/* ... */} delimiters instead of HTML comment delimiters (Must-Fix)
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
**/*.{html,md,mdx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license header in HTML and Markdown files using HTML comment syntax
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
docs/**/*.{md,mdx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update embedded documentation snippets, patch docs, and binding-support notes if examples or supported bindings changed
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
docs/**
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run
just docsor./scripts/build-docs.sh htmlto regenerate ignored Fern API reference pages before validation for documentation site changes
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}
⚙️ CodeRabbit configuration file
{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}: Review documentation for technical accuracy against the current API, command correctness, and consistency across language bindings.
Flag stale examples, missing SPDX headers where required, and instructions that no longer match CI or pre-commit behavior.
Files:
docs/nemo-relay-cli/cursor.mdxdocs/nemo-relay-cli/about.mdxdocs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/basic-usage.mdxdocs/nemo-relay-cli/hermes.mdxdocs/nemo-relay-cli/claude-code.mdxdocs/getting-started/installation.mdxdocs/nemo-relay-cli/codex.mdxRELEASING.md
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Use
snake_casenaming convention for Rust identifiers (e.g.,nemo_relay_tool_call)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node work
**/*.rs: Runcargo fmt --allto format all Rust code
Runcargo clippy --workspace --all-targets -- -D warningsto enforce all clippy lints as errors
**/*.rs: Runcargo fmt --allwhen Rust files changed as part of WebAssembly work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files changed as part of WebAssembly work
**/*.rs: If any Rust code changed, always runjust test-rust
If any Rust code changed, also runcargo fmt --all
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings
Run Rust formatting withcargo fmt --all
Run Rust linting withcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Usecargo fmtfor Rust code formatting
Runcargo clippy -- -D warningsto lint Rust code and treat all warnings as errors
Use Rust snake_case naming convention for Rust identifiers
Include SPDX license header in all Rust source files using double-slash comment syntax
Validate Rust code withuv run pre-commit run --all-filesto enforce cargo fmt formatting check, cargo clippy lints, and cargo deny aud...
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
**/{Cargo.toml,**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Maintain consistency between Rust package names in
Cargo.tomland their actual usage across the codebase
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
**/*.{h,hpp,c,cpp,rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Ensure FFI header and library naming follows consistent conventions across platform-specific builds
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
**/*.{rs,toml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update Rust crate names and module prefixes during coordinated rename operations
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
**/*.{rs,py,js,ts,tsx,jsx,go,sh,toml,yaml,yml,md}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rsintegrations/coding-agents/README.mdcrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rsintegrations/coding-agents/claude-code/README.mdcrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rsintegrations/coding-agents/codex/README.mdcrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rsRELEASING.mdcrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions: Rust and Python use
snake_case, C FFI exports prefixednemo_relay_, Go usesPascalCasefor public APIs, Node.js usescamelCase.
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
crates/**/*.rs
📄 CodeRabbit inference engine (AGENTS.md)
crates/**/*.rs: Keep async behavior on the existing tokio-based model. Bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
UseJson = serde_json::Valuein Rust-facing runtime APIs for JSON payload handling.
Files:
crates/cli/src/main.rscrates/cli/src/gateway.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/plugin_install/marketplace.rscrates/cli/src/plugin_shim/command.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/host.rscrates/cli/src/server.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/shared.rscrates/cli/src/plugin_install/state.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/config.rs
.github/workflows/*.{yml,yaml}
📄 CodeRabbit inference engine (.agents/skills/maintain-ci/SKILL.md)
.github/workflows/*.{yml,yaml}: Putpermissions:on each job that needs token access in GitHub Actions workflows
Avoid workflow-level permissions unless the repository intentionally centralizes them and the inheritance tradeoff is documented
Keep third-party actions pinned to full commit SHAs and preserve the readable version comment after the SHA
Prefer action-native or ecosystem-native caching over genericactions/cache
Use lockfiles or dependency manifests to drive cache invalidation in GitHub Actions workflows
Keep deploy and publish permissions isolated to the jobs that need them in GitHub Actions
Read both caller and callee when a workflow usesworkflow_callin GitHub Actions
Put release-tag validation in the earliest practical caller job when the pipeline has tag-based publish behavior
Keep release-tag policy aligned withRELEASING.md: raw SemVer tags only, no leadingv
contents: readis the default minimum permission for checkout-based build, test, docs, and packaging jobs
pull-requests: readis required for PR metadata lookup jobs in GitHub Actions workflows
pages: writeandid-token: writeshould be limited to Pages deployment jobs and callers that invoke them through reusable workflows
For reusable workflows, the caller must grant every permission the called jobs require; the callee cannot elevate beyond what the caller provides
Preferastral-sh/setup-uvcache support withcache-dependency-globanchored touv.lock
PreferSwatinem/rust-cachewith explicitshared-keyandworkspacesinstead of ad hoc target-directory caching
Avoid caching generated outputs that can hide stale behavior unless the repo already relies on them deliberately
Files:
.github/workflows/ci.yaml
.{github/workflows/*.{yml,yaml},gitlab-ci.yml}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Ensure CI workflows reference the same package names, install commands, and build commands as local development workflows
Files:
.github/workflows/ci.yaml
{.github/**,.gitlab-ci.yml,.pre-commit-config.yaml,justfile,scripts/**}
⚙️ CodeRabbit configuration file
{.github/**,.gitlab-ci.yml,.pre-commit-config.yaml,justfile,scripts/**}: Review automation changes for reproducibility, pinned versions where appropriate, secret handling, and consistency with the documented validation matrix.
Pay attention to commands that need generated native artifacts, FFI libraries, or platform-specific environment variables.
Files:
.github/workflows/ci.yaml.github/ci-path-filters.ymljustfile
{crates/adaptive/**/*.rs,**/*test*.{rs,py,go,ts,js},**/*adaptive*test*.{rs,py,go,ts,js},docs/plugins/adaptive/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Maintain documented and tested validation and report behavior for adaptive surfaces
Files:
crates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rs
**/*.{md,rst,html,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
**/*.{md,rst,html,txt}: Always spellNVIDIAin all caps. Do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company.
Use trademark symbols with product names only when the document type or legal guidance requires them.
Verify official capitalization, spacing, and hyphenation for product names.
Precede NVIDIA product names withNVIDIAon first mention when it is natural and accurate.
Do not rewrite product names for grammar or title-case rules.
Preserve third-party product names according to the owner's spelling.
Include the company name and full model qualifier on first use when it helps identify the model.
Preserve the official capitalization and punctuation of model names.
Use shorter family names only after the full name is established.
Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience.
Use the acronym on later mentions after it has been defined.
For long documents, reintroduce the full term if readers might lose context.
Form plurals of acronyms withs, not an apostrophe, such asGPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such asCPU,GPU,PC,API, andUIusually do not need to be spelled out for developer audiences.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.{md,rst,html}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
Link the first mention of a product name when the destination helps the reader.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.md
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Documentation must be updated if activation or usage changed
**/*.md: Use title case consistently in technical documentation headings
Avoid quotation marks, ampersands, and exclamation marks in headings
Keep product, event, research, and whitepaper names in their official title case
Use title case for table headers
Do not force social-media sentence case into technical docs
Format code elements, commands, parameters, package names, and expressions in monospace
Format directories, file names, and paths in monospace using backticks
Use angle brackets inside monospace for variables inside paths, such as/home/<username>/.login
Format error messages and strings in quotation marks, keeping literal code strings in code formatting when clearer
Format UI buttons, menus, fields, and labels in bold
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use, sparingly and only when introducing the term
Use italics for publication titles
Format keyboard shortcuts in plain text, such as Press Ctrl+Alt+Delete
Use owner/repo link text for GitHub repositories, preferring[NVIDIA/NeMo](link)over prose references like 'the GitHub repo'
Introduce every code block with a complete sentence
Do not make a code block complete the grammar of the previous sentence
Do not continue a sentence after a code block
Use syntax highlighting when the format supports it for code blocks
Avoid the word 'snippet' unless the surrounding docs already use it as a term of art
Keep inline method, function, and class references consistent with nearby docs, omitting empty parentheses for prose readability when no call is shown
Use descriptive anchor text that matches the destination title when possible for links
Avoid raw URLs in running text
Avoid generic anchor text such as 'here,' 'this page,' and 'read more'
Include acronyms in link text when a linked term includes an acronym
Do not link long sentences or multiple sentences
Avoid links ...
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/{docs,examples,**/*.md,*.patch,*.diff,.github,*.sh,*.yaml,*.yml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update documentation, examples, CI configuration, and patch artifacts when performing rename operations
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.{md,rst,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
Spell
NVIDIAin all caps. Do not useNvidia,nvidia, orNV.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/*.{md,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,rst}: Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as "here" or "read more."
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce.
Preferrefer tooverseewhen the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical docs.
Spell out months in body text, avoid ordinal dates, and use clear time zones.
Spell out whole numbers from zero through nine unless they are technical values, parameters, versions, or UI values.
Use numerals for 10 or greater and include commas in thousands.
Do not add trademark symbols to learning-oriented docs unless the source, platform, or legal guidance explicitly requires them.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdRELEASING.md
**/README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant crate or package README when that surface changed
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.md
RELEASING.md
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Ensure public packaging changes are reflected in release-facing documentation and RELEASING.md
Files:
RELEASING.md
{CHANGELOG.md,RELEASING.md,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Release history and release notes must reference GitHub Releases, not CHANGELOG.md or docs pages
Files:
RELEASING.md
**/*config*.{rs,ts,py,go,js,json,yaml,yml}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Ensure dynamic config shape still matches the documented canonical model
Files:
crates/cli/src/config.rs
🔇 Additional comments (63)
.github/ci-path-filters.yml (1)
112-113: LGTM!Also applies to: 134-135
.github/workflows/ci.yaml (1)
285-287: LGTM!RELEASING.md (1)
36-36: LGTM!Also applies to: 239-240, 254-256, 283-285, 300-301
justfile (1)
391-416: LGTM!Also applies to: 557-557
crates/cli/src/config.rs (4)
14-14: LGTM!Also applies to: 84-86, 100-102
108-122: LGTM!
124-146: LGTM!
419-426: LGTM!crates/cli/src/main.rs (3)
17-18: LGTM!
60-62: LGTM!
99-105: LGTM!crates/cli/src/plugin_install/state.rs (6)
17-42: LGTM!
43-85: LGTM!
87-104: LGTM!
106-144: LGTM!
180-228: LGTM!
230-265: LGTM!crates/cli/src/plugin_install/marketplace.rs (4)
16-48: LGTM!
50-88: LGTM!
90-130: LGTM!
132-151: LGTM!.agents/plugins/marketplace.json (1)
1-20: LGTM!.claude-plugin/marketplace.json (1)
1-16: LGTM!crates/cli/src/plugin_install/host.rs (6)
15-109: LGTM!
111-156: LGTM!
158-224: LGTM!
226-280: LGTM!
282-307: LGTM!
309-330: LGTM!crates/cli/src/plugin_shim/command.rs (6)
10-24: LGTM!
26-30: LGTM!
32-38: LGTM!
40-54: LGTM!
56-72: LGTM!
74-80: LGTM!crates/cli/src/plugin_install/mod.rs (1)
1-2: Run the repository-required Rust validation matrix.The PR notes
cargo test,cargo clippy, andcargo fmt check, but the Rust validation policy here is stricter. Please runjust test-rust,cargo fmt --all, andcargo clippy --workspace --all-targets -- -D warningsbefore merge.
As per coding guidelines, "Any Rust change must runjust test-rust", "Runcargo fmt --allto format all Rust code", and "Runcargo clippy --workspace --all-targets -- -D warningsto enforce all clippy lints as errors."Source: Coding guidelines
crates/cli/src/plugin_install/setup.rs (1)
12-103: LGTM!docs/getting-started/installation.mdx (1)
26-35: LGTM!docs/nemo-relay-cli/about.mdx (1)
27-28: LGTM!Also applies to: 58-59
docs/nemo-relay-cli/basic-usage.mdx (3)
96-120: LGTM!
350-352: LGTM!
373-373: LGTM!docs/nemo-relay-cli/claude-code.mdx (1)
43-65: LGTM!docs/nemo-relay-cli/codex.mdx (1)
60-88: LGTM!docs/nemo-relay-cli/cursor.mdx (1)
4-4: LGTM!docs/nemo-relay-cli/hermes.mdx (1)
4-4: LGTM!docs/nemo-relay-cli/plugin-installation.mdx (1)
1-137: LGTM!integrations/coding-agents/README.md (2)
71-126: LGTM!
167-180: LGTM!crates/cli/tests/coverage/plugin_install_tests.rs (2)
1-3: Confirm the Required Rust Validation Matrix Ran for This PR.Please provide run evidence for
just test-rust,cargo fmt --all, andcargo clippy --workspace --all-targets -- -D warningsfor this Rust change set.As per coding guidelines, "Any Rust change must run
just test-rust", "Any Rust change must runcargo fmt --all", and "Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings."Source: Coding guidelines
13-838: LGTM!crates/cli/tests/coverage/plugin_shim_tests.rs (1)
16-1310: LGTM!crates/cli/tests/coverage/installer_tests.rs (1)
162-279: LGTM!crates/cli/tests/cli_tests.rs (1)
325-392: LGTM!crates/cli/tests/coverage/gateway_tests.rs (1)
725-730: LGTM!Also applies to: 752-757
crates/cli/tests/coverage/server_tests.rs (2)
213-317: LGTM!
38-63: Serialize process-env mutation inEnvVarGuard(global lock + preserveOsString)
EnvVarGuardmutates the process-wide environment (set_var/remove_var) without a shared, module-wide lock, so concurrently running tests can race and become flaky. Also, storing/restoring viaString(var) can drop non-UTF8 values; prefervar_os/OsString. Finally, theunsafe { ... }blocks aroundset_var/remove_varare unnecessary unless there’s a separate justification.Suggested fix
+use std::ffi::OsString; +use std::sync::{Mutex, OnceLock}; + +fn env_lock() -> &'static Mutex<()> { + static LOCK: OnceLock<Mutex<()>> = OnceLock::new(); + LOCK.get_or_init(|| Mutex::new(())) +} + -struct EnvVarGuard { +struct EnvVarGuard<'a> { + _guard: std::sync::MutexGuard<'a, ()>, key: &'static str, - old: Option<String>, + old: Option<OsString>, } -impl EnvVarGuard { +impl<'a> EnvVarGuard<'a> { fn set(key: &'static str, value: &str) -> Self { - let old = std::env::var(key).ok(); + let guard = env_lock().lock().unwrap_or_else(|e| e.into_inner()); + let old = std::env::var_os(key); unsafe { std::env::set_var(key, value); } - Self { key, old } + Self { _guard: guard, key, old } } } -impl Drop for EnvVarGuard { +impl Drop for EnvVarGuard<'_> { fn drop(&mut self) { unsafe { if let Some(old) = self.old.take() { std::env::set_var(self.key, old); } else { std::env::remove_var(self.key); } } } }integrations/coding-agents/claude-code/hooks/hooks.json (1)
8-8: Ensure CLI aliasclaudemaps toCodingAgent::ClaudeCode
- hooks.json packages
nemo-relay plugin-shim hook claude; if the CLI argument/alias layer doesn’t parseclaudeto the sameCodingAgentvariant that the shim matches on (theClaudeCodespecial-case), the hook will fail before reaching the Claude implementation.integrations/coding-agents/claude-code/.claude-plugin/plugin.json (1)
2-4: LGTM!integrations/coding-agents/codex/hooks/hooks.json (1)
9-145: LGTM!integrations/coding-agents/codex/README.md (1)
219-242: Verify the Codexmarketplace.jsonschema in the README matches the generator code.The README example (
integrations/coding-agents/codex/README.md, lines 219-242) usesinterface.displayName, nestedsource.source/source.path, andpolicy.installation/policy.authentication; confirm this matches the actualmarketplace.jsonschema produced bycrates/cli/src/plugin_install/marketplace.rs.integrations/coding-agents/claude-code/README.md (1)
208-227: Confirmmarketplace.jsonmatches the Claude Code plugin marketplace schemaIn
integrations/coding-agents/claude-code/README.md(lines 208-227), validate that themarketplace.jsonexample uses the exact Claude Code schema and field nesting:metadata.description,owner.name/owner.email, andplugins[]entries (name,description,source,category). Pay special attention to whetherplugins[].sourcemust be a relative path like./plugins/nemo-relay-pluginversus an expected marketplace identifier.integrations/coding-agents/codex/.codex-plugin/plugin.json (1)
27-29: ValidatedefaultPromptagainst Codexplugin.jsonschema (placement + constraints)
- In OpenAI Codex plugin manifests,
defaultPromptis a supported field (defined as an array of strings) under theinterfaceobject for UI starter prompts.- Ensure the
defaultPromptyou added atintegrations/coding-agents/codex/.codex-plugin/plugin.json(lines 27-29) is nested underinterfaceand respects Codex validator limits (strings ≤ 128 chars; up to 3 entries).- The fact it doesn’t exist in Claude Code’s
.claude-plugin/plugin.jsonis not a relevant schema check (Codex and Claude Code use different manifest formats).
Signed-off-by: Will Killian <wkillian@nvidia.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/cli/src/plugin_install/mod.rs`:
- Around line 315-323: The JSON branch inside doctor_host is unreachable because
doctor() already routes json=true to doctor_json(), so when run_for_hosts calls
doctor_host options.json is always false; remove the dead code block that checks
options.json and its print_json/with_schema/doctor_host_json_value call (i.e.,
delete the if options.json { ... } early-return) and any helper references that
only served that branch (doctor_host_json_value), leaving doctor_host to only
handle the non-JSON path called by run_for_hosts/doctor().
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: efd087b1-22c5-4768-8836-9094d01d954c
📒 Files selected for processing (12)
crates/cli/src/config.rscrates/cli/src/plugin_install/mod.rscrates/cli/src/plugin_install/setup.rscrates/cli/src/plugin_install/state.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_shim/shared.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rsintegrations/coding-agents/README.md
💤 Files with no reviewable changes (1)
- crates/cli/src/plugin_shim/claude.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (22)
**/*.{md,rst,html,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
**/*.{md,rst,html,txt}: Always spellNVIDIAin all caps. Do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company.
Use trademark symbols with product names only when the document type or legal guidance requires them.
Verify official capitalization, spacing, and hyphenation for product names.
Precede NVIDIA product names withNVIDIAon first mention when it is natural and accurate.
Do not rewrite product names for grammar or title-case rules.
Preserve third-party product names according to the owner's spelling.
Include the company name and full model qualifier on first use when it helps identify the model.
Preserve the official capitalization and punctuation of model names.
Use shorter family names only after the full name is established.
Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience.
Use the acronym on later mentions after it has been defined.
For long documents, reintroduce the full term if readers might lose context.
Form plurals of acronyms withs, not an apostrophe, such asGPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such asCPU,GPU,PC,API, andUIusually do not need to be spelled out for developer audiences.
Files:
integrations/coding-agents/README.md
**/*.{md,rst,html}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
Link the first mention of a product name when the destination helps the reader.
Files:
integrations/coding-agents/README.md
**/*.md
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Documentation must be updated if activation or usage changed
**/*.md: Use title case consistently in technical documentation headings
Avoid quotation marks, ampersands, and exclamation marks in headings
Keep product, event, research, and whitepaper names in their official title case
Use title case for table headers
Do not force social-media sentence case into technical docs
Format code elements, commands, parameters, package names, and expressions in monospace
Format directories, file names, and paths in monospace using backticks
Use angle brackets inside monospace for variables inside paths, such as/home/<username>/.login
Format error messages and strings in quotation marks, keeping literal code strings in code formatting when clearer
Format UI buttons, menus, fields, and labels in bold
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use, sparingly and only when introducing the term
Use italics for publication titles
Format keyboard shortcuts in plain text, such as Press Ctrl+Alt+Delete
Use owner/repo link text for GitHub repositories, preferring[NVIDIA/NeMo](link)over prose references like 'the GitHub repo'
Introduce every code block with a complete sentence
Do not make a code block complete the grammar of the previous sentence
Do not continue a sentence after a code block
Use syntax highlighting when the format supports it for code blocks
Avoid the word 'snippet' unless the surrounding docs already use it as a term of art
Keep inline method, function, and class references consistent with nearby docs, omitting empty parentheses for prose readability when no call is shown
Use descriptive anchor text that matches the destination title when possible for links
Avoid raw URLs in running text
Avoid generic anchor text such as 'here,' 'this page,' and 'read more'
Include acronyms in link text when a linked term includes an acronym
Do not link long sentences or multiple sentences
Avoid links ...
Files:
integrations/coding-agents/README.md
**/{docs,examples,**/*.md,*.patch,*.diff,.github,*.sh,*.yaml,*.yml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update documentation, examples, CI configuration, and patch artifacts when performing rename operations
Files:
integrations/coding-agents/README.md
**/*.{md,rst,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
Spell
NVIDIAin all caps. Do not useNvidia,nvidia, orNV.
Files:
integrations/coding-agents/README.md
**/*.{md,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,rst}: Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as "here" or "read more."
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce.
Preferrefer tooverseewhen the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical docs.
Spell out months in body text, avoid ordinal dates, and use clear time zones.
Spell out whole numbers from zero through nine unless they are technical values, parameters, versions, or UI values.
Use numerals for 10 or greater and include commas in thousands.
Do not add trademark symbols to learning-oriented docs unless the source, platform, or legal guidance explicitly requires them.
Files:
integrations/coding-agents/README.md
{docs/**,README.md,CONTRIBUTING.md,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Run docs link validation with
just docs-linkcheckwhen links change
Files:
integrations/coding-agents/README.md
{docs/**,README.md,**/Cargo.toml,**/package.json,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Ensure renamed public surfaces are reflected consistently in manifests and docs for large or public-facing changes
Files:
integrations/coding-agents/README.md
**/*.{md,mdx,py,sh,yaml,yml,toml,json}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repo references, and build commands current
Files:
integrations/coding-agents/README.md
**/*.{html,md,mdx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license header in HTML and Markdown files using HTML comment syntax
Files:
integrations/coding-agents/README.md
**/README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant crate or package README when that surface changed
Files:
integrations/coding-agents/README.md
**/*.{rs,py,js,ts,tsx,jsx,go,sh,toml,yaml,yml,md}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.
Files:
integrations/coding-agents/README.mdcrates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**
⚙️ CodeRabbit configuration file
**:AGENTS.md
This file provides guidance to agents, including Claude Code and OpenAI Codex, when working in this repository.
Project Overview
NeMo Relay is a multi-language agent runtime framework for execution scopes, lifecycle events, middleware, plugins, and observability around tool and LLM calls. The core runtime is Rust. Primary supported bindings are Rust, Python, and Node.js. Go, WebAssembly, and the raw C FFI are experimental and source-first.
The shared runtime model is:
- Scope stacks decide where work belongs and which scope-local behavior is visible.
- Middleware registries decide what guardrails and intercepts run around managed calls.
- Plugins install reusable runtime behavior from configuration.
- Events record runtime behavior in ATOF form.
- Subscribers and exporters consume events in-process or export them to ATIF, OpenTelemetry, OpenInference, or other backends.
Repository Structure
The repository layout separates the Rust runtime, language bindings, documentation,
integration patches, and agent-facing skills.crates/ core/ # Rust core runtime crate, published as nemo-relay adaptive/ # Adaptive runtime primitives and plugin components python/ # PyO3 native extension for the Python package ffi/ # Raw C ABI layer used by downstream bindings such as Go node/ # NAPI Node.js binding and JavaScript/TypeScript entry points wasm/ # wasm-bindgen WebAssembly binding and JS wrappers python/ nemo_relay/ # Python wrapper package: scopes, tools, LLM, middleware, typed helpers, plugins, adaptive helpers tests/ # Python tests go/ nemo_relay/ # Experimental Go CGo binding and tests fern/ # Fern documentation site scripts/ # Stable wrappers and helper scripts; build/test/docs entry points live in justfile third_party/ # P...
Files:
integrations/coding-agents/README.mdcrates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Use
snake_casenaming convention for Rust identifiers (e.g.,nemo_relay_tool_call)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node work
**/*.rs: Runcargo fmt --allto format all Rust code
Runcargo clippy --workspace --all-targets -- -D warningsto enforce all clippy lints as errors
**/*.rs: Runcargo fmt --allwhen Rust files changed as part of WebAssembly work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files changed as part of WebAssembly work
**/*.rs: If any Rust code changed, always runjust test-rust
If any Rust code changed, also runcargo fmt --all
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings
Run Rust formatting withcargo fmt --all
Run Rust linting withcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Usecargo fmtfor Rust code formatting
Runcargo clippy -- -D warningsto lint Rust code and treat all warnings as errors
Use Rust snake_case naming convention for Rust identifiers
Include SPDX license header in all Rust source files using double-slash comment syntax
Validate Rust code withuv run pre-commit run --all-filesto enforce cargo fmt formatting check, cargo clippy lints, and cargo deny aud...
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**/{Cargo.toml,**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Maintain consistency between Rust package names in
Cargo.tomland their actual usage across the codebase
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**/*.{h,hpp,c,cpp,rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Ensure FFI header and library naming follows consistent conventions across platform-specific builds
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**/*.{rs,toml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update Rust crate names and module prefixes during coordinated rename operations
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions: Rust and Python use
snake_case, C FFI exports prefixednemo_relay_, Go usesPascalCasefor public APIs, Node.js usescamelCase.
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
crates/**/*.rs
📄 CodeRabbit inference engine (AGENTS.md)
crates/**/*.rs: Keep async behavior on the existing tokio-based model. Bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
UseJson = serde_json::Valuein Rust-facing runtime APIs for JSON payload handling.
Files:
crates/cli/src/plugin_install/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/src/plugin_shim/mod.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/state.rscrates/cli/src/config.rscrates/cli/src/plugin_shim/codex.rscrates/cli/src/plugin_shim/shared.rs
{crates/adaptive/**/*.rs,**/*test*.{rs,py,go,ts,js},**/*adaptive*test*.{rs,py,go,ts,js},docs/plugins/adaptive/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Maintain documented and tested validation and report behavior for adaptive surfaces
Files:
crates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/cli_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rs
**/*config*.{rs,ts,py,go,js,json,yaml,yml}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Ensure dynamic config shape still matches the documented canonical model
Files:
crates/cli/src/config.rs
🔇 Additional comments (25)
integrations/coding-agents/README.md (1)
25-222: LGTM!crates/cli/src/config.rs (3)
113-136: LGTM!
138-146: LGTM!
419-426: LGTM!crates/cli/src/plugin_shim/mod.rs (1)
17-18: LGTM!Also applies to: 150-194
crates/cli/src/plugin_shim/shared.rs (2)
15-15: LGTM!Also applies to: 23-51
517-583: LGTM!crates/cli/src/plugin_shim/codex.rs (1)
183-185: LGTM!crates/cli/tests/coverage/plugin_shim_tests.rs (3)
538-557: LGTM!
849-860: LGTM!Also applies to: 862-896
788-788: LGTM!crates/cli/tests/cli_tests.rs (1)
382-396: LGTM!crates/cli/src/plugin_install/state.rs (2)
23-23: LGTM!
160-163: LGTM!crates/cli/src/plugin_install/mod.rs (6)
14-15: LGTM!Also applies to: 26-27, 49-49, 68-68
78-101: LGTM!
139-166: LGTM!
209-217: LGTM!
283-287: LGTM!
331-349: LGTM!Also applies to: 450-461
crates/cli/src/plugin_install/setup.rs (1)
8-8: LGTM!Also applies to: 49-54, 81-81, 112-121
crates/cli/tests/coverage/plugin_install_tests.rs (4)
115-127: LGTM!Also applies to: 146-146
591-614: LGTM!
739-763: LGTM!
765-784: LGTM!
Signed-off-by: Will Killian <wkillian@nvidia.com>
There was a problem hiding this comment.
Update after af66400: I re-tested the two remaining nitpicks from this review and both are addressed now.
- Claude provider stale-backup repro: fixed. After reinstall and restore, the final
ANTHROPIC_BASE_URLstays at the user-ownedhttps://custom.examplevalue instead of reverting to the stale original backup. doctor --plugin claude-codehost-registration false positive: fixed. After manually removing the host plugin and marketplace, doctor now exits non-zero withclaude plugin host registration is incomplete: missing nemo-relay-plugin@nemo-relay-local host plugin, nemo-relay-local host marketplace.
I also ran cargo test -p nemo-relay-cli -- --test-threads=1 successfully on the latest PR head. No remaining action needed from my prior review comments.
|
@willkill07 , one UX gap I noticed in the Codex/Claude plugin install flow: That is technically composable, but I don't think it matches the end-user install story. For coding-agent plugins, the user mental model is probably "install Relay for Codex/Claude and get traces," not "install the plugin, then know to configure an observability component separately." This matters more for global installs. If someone installs Codex once on their machine, they'll likely expect exporters to apply across repos. Today they need to know to run something like I’d treat this as a UX follow-up, not a blocker for the PR. Possible fixes:
My preference: keep plugin install and exporter config separate internally, but make exporter setup first-class in the CLI. The one-time install flow should not require users to discover |
|
Update after I reran the end-user flow against the PR binary with the user OpenInference exporter pointing at Phoenix: nemo-relay doctor --plugin claude-code
nemo-relay plugin-shim doctor claude
jq .env.ANTHROPIC_BASE_URL ~/.claude/settings.json
claude -p "hi from direct installed nemo relay test at 2026-06-10T20:33:11Z" --output-format jsonPhoenix trace So the earlier direct-mode symptom no longer reproduces: the root |
Signed-off-by: Will Killian <wkillian@nvidia.com>
|
Plugin setup still separate step. Everything else has been addressed @AjayThorve |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/cli/tests/coverage/session_tests.rs`:
- Around line 3804-3817: The prompt_submitted handling records a "prompt_mark"
regardless of session, so unrelated parallel events can satisfy the assertion;
update the logic in the prompt_submitted branch (the if checking event.name() ==
"prompt_submitted" and pushing to captured.lock().unwrap().push(...)) to also
check that event_session_id == Some("claude-direct-race") (i.e., scope the
capture to the target session) before pushing; you can either add the session
check inside that branch or move the existing event_session_id check above it so
the "prompt_mark" is only recorded for the intended session (apply the same
change to the other occurrence around lines 3895-3898).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: daa38465-7d84-4490-a523-ccbb433f900e
📒 Files selected for processing (11)
crates/cli/src/alignment/claude_code.rscrates/cli/src/alignment/mod.rscrates/cli/src/plugin_install/host.rscrates/cli/src/plugin_install/mod.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/session.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/plugin_install_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/session_tests.rs
👮 Files not reviewed due to content moderation or server errors (5)
- crates/cli/src/alignment/claude_code.rs
- crates/cli/src/alignment/mod.rs
- crates/cli/src/session.rs
- crates/cli/tests/coverage/alignment_claude_code_tests.rs
- crates/cli/tests/coverage/server_tests.rs
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: Check / Run
- GitHub Check: Preview docs
🧰 Additional context used
📓 Path-based instructions (10)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Use
snake_casenaming convention for Rust identifiers (e.g.,nemo_relay_tool_call)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node work
**/*.rs: Runcargo fmt --allto format all Rust code
Runcargo clippy --workspace --all-targets -- -D warningsto enforce all clippy lints as errors
**/*.rs: Runcargo fmt --allwhen Rust files changed as part of WebAssembly work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files changed as part of WebAssembly work
**/*.rs: If any Rust code changed, always runjust test-rust
If any Rust code changed, also runcargo fmt --all
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings
Run Rust formatting withcargo fmt --all
Run Rust linting withcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Usecargo fmtfor Rust code formatting
Runcargo clippy -- -D warningsto lint Rust code and treat all warnings as errors
Use Rust snake_case naming convention for Rust identifiers
Include SPDX license header in all Rust source files using double-slash comment syntax
Validate Rust code withuv run pre-commit run --all-filesto enforce cargo fmt formatting check, cargo clippy lints, and cargo deny aud...
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**/{Cargo.toml,**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Maintain consistency between Rust package names in
Cargo.tomland their actual usage across the codebase
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**/*.{h,hpp,c,cpp,rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Ensure FFI header and library naming follows consistent conventions across platform-specific builds
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**/*.{rs,toml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update Rust crate names and module prefixes during coordinated rename operations
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**/*.{rs,py,js,ts,tsx,jsx,go,sh,toml,yaml,yml,md}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions: Rust and Python use
snake_case, C FFI exports prefixednemo_relay_, Go usesPascalCasefor public APIs, Node.js usescamelCase.
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
crates/**/*.rs
📄 CodeRabbit inference engine (AGENTS.md)
crates/**/*.rs: Keep async behavior on the existing tokio-based model. Bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
UseJson = serde_json::Valuein Rust-facing runtime APIs for JSON payload handling.
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
**
⚙️ CodeRabbit configuration file
**:AGENTS.md
This file provides guidance to agents, including Claude Code and OpenAI Codex, when working in this repository.
Project Overview
NeMo Relay is a multi-language agent runtime framework for execution scopes, lifecycle events, middleware, plugins, and observability around tool and LLM calls. The core runtime is Rust. Primary supported bindings are Rust, Python, and Node.js. Go, WebAssembly, and the raw C FFI are experimental and source-first.
The shared runtime model is:
- Scope stacks decide where work belongs and which scope-local behavior is visible.
- Middleware registries decide what guardrails and intercepts run around managed calls.
- Plugins install reusable runtime behavior from configuration.
- Events record runtime behavior in ATOF form.
- Subscribers and exporters consume events in-process or export them to ATIF, OpenTelemetry, OpenInference, or other backends.
Repository Structure
The repository layout separates the Rust runtime, language bindings, documentation,
integration patches, and agent-facing skills.crates/ core/ # Rust core runtime crate, published as nemo-relay adaptive/ # Adaptive runtime primitives and plugin components python/ # PyO3 native extension for the Python package ffi/ # Raw C ABI layer used by downstream bindings such as Go node/ # NAPI Node.js binding and JavaScript/TypeScript entry points wasm/ # wasm-bindgen WebAssembly binding and JS wrappers python/ nemo_relay/ # Python wrapper package: scopes, tools, LLM, middleware, typed helpers, plugins, adaptive helpers tests/ # Python tests go/ nemo_relay/ # Experimental Go CGo binding and tests fern/ # Fern documentation site scripts/ # Stable wrappers and helper scripts; build/test/docs entry points live in justfile third_party/ # P...
Files:
crates/cli/src/alignment/mod.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/src/alignment/claude_code.rscrates/cli/src/session.rscrates/cli/src/plugin_shim/claude.rscrates/cli/src/plugin_install/host.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/src/plugin_install/mod.rscrates/cli/tests/coverage/plugin_install_tests.rs
{crates/adaptive/**/*.rs,**/*test*.{rs,py,go,ts,js},**/*adaptive*test*.{rs,py,go,ts,js},docs/plugins/adaptive/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Maintain documented and tested validation and report behavior for adaptive surfaces
Files:
crates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/tests/coverage/plugin_install_tests.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/alignment_claude_code_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/plugin_shim_tests.rscrates/cli/tests/coverage/plugin_install_tests.rs
🔇 Additional comments (5)
crates/cli/src/plugin_install/host.rs (1)
1-571: LGTM!crates/cli/src/plugin_install/mod.rs (1)
19-23: LGTM!Also applies to: 316-319, 332-342
crates/cli/tests/coverage/plugin_install_tests.rs (1)
11-11: LGTM!Also applies to: 19-20, 32-48, 98-114, 795-924
crates/cli/src/plugin_shim/claude.rs (1)
30-35: LGTM!Also applies to: 141-164
crates/cli/tests/coverage/plugin_shim_tests.rs (1)
791-838: LGTM!
AjayThorve
left a comment
AjayThorve
left a comment
There was a problem hiding this comment.
Looks good to me after af66400
Co-authored-by: lvojtku <lvojtku@nvidia.com> Signed-off-by: lvojtku <lvojtku@nvidia.com>
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
integrations/coding-agents/codex/README.md (1)
37-38: 🧹 Nitpick | 🔵 Trivial | ⚡ Quick winClarify what "v1" refers to.
The reference to "v1 does not depend on Codex exposing those broader events" is ambiguous. Consider replacing "v1" with a clearer term such as "the minimum hook set," "the base integration," or "NeMo Relay's initial Codex support" to help readers understand what scope or version is being referenced.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@integrations/coding-agents/codex/README.md` around lines 37 - 38, The phrase "v1 does not depend on Codex exposing those broader events" is ambiguous; update that sentence to replace "v1" with a clearer term such as "the base integration," "NeMo Relay's initial Codex support," or "the minimum hook set" to clarify scope. Locate the exact phrase "v1 does not depend on Codex exposing those broader events" in the README and change "v1" to one of the suggested clearer terms (pick the one that best fits the project tone) so readers understand which scope/version is referenced.Source: Coding guidelines
♻️ Duplicate comments (1)
integrations/coding-agents/codex/README.md (1)
252-252:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winFix spacing before inline code.
Missing space between "using" and the backtick for the inline code element.
📝 Suggested fix
-For end-to-end installation, we recommend using`nemo-relay install codex`; it performs the +For end-to-end installation, we recommend using `nemo-relay install codex`; it performs the🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@integrations/coding-agents/codex/README.md` at line 252, The inline code in the sentence "For end-to-end installation, we recommend using`nemo-relay install codex`; it performs the" is missing a space before the backtick; update the text so there is a space between "using" and the inline code (i.e., change "using`nemo-relay install codex`" to "using `nemo-relay install codex`") to fix spacing in the README.md content.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/nemo-relay-cli/codex.mdx`:
- Line 71: Replace the plain URL with a monospace-formatted one in the line
referencing the nemo-relay-openai provider alias; find the occurrence of
http://127.0.0.1:47632 (near the "nemo-relay-openai provider alias" text) and
wrap it in backticks so it appears as `http://127.0.0.1:47632` to follow docs
guidelines for paths and URLs.
---
Outside diff comments:
In `@integrations/coding-agents/codex/README.md`:
- Around line 37-38: The phrase "v1 does not depend on Codex exposing those
broader events" is ambiguous; update that sentence to replace "v1" with a
clearer term such as "the base integration," "NeMo Relay's initial Codex
support," or "the minimum hook set" to clarify scope. Locate the exact phrase
"v1 does not depend on Codex exposing those broader events" in the README and
change "v1" to one of the suggested clearer terms (pick the one that best fits
the project tone) so readers understand which scope/version is referenced.
---
Duplicate comments:
In `@integrations/coding-agents/codex/README.md`:
- Line 252: The inline code in the sentence "For end-to-end installation, we
recommend using`nemo-relay install codex`; it performs the" is missing a space
before the backtick; update the text so there is a space between "using" and the
inline code (i.e., change "using`nemo-relay install codex`" to "using
`nemo-relay install codex`") to fix spacing in the README.md content.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: 887a3ce2-d0c6-4f47-8e3e-bad12336ecaf
📒 Files selected for processing (4)
docs/nemo-relay-cli/codex.mdxdocs/nemo-relay-cli/plugin-installation.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: Check / Run
- GitHub Check: Preview docs
🧰 Additional context used
📓 Path-based instructions (20)
{docs/**,README.md,CONTRIBUTING.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
{docs/**,README.md,CONTRIBUTING.md}: For docs-only changes, run targeted checks only if commands, package names, or examples changed. Usejust docsfor docs-site builds andjust docs-linkcheckwhen links changed
Run docs site build withjust docs
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,CONTRIBUTING.md,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Run docs link validation with
just docs-linkcheckwhen links change
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
{docs/**,README.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Verify README and docs entry points still match current package names and paths for large or public-facing changes
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,examples/**,README.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Verify examples still run with documented commands for large or public-facing changes
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,**/Cargo.toml,**/package.json,**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Ensure renamed public surfaces are reflected consistently in manifests and docs for large or public-facing changes
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,mdx,py,sh,yaml,yml,toml,json}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repo references, and build commands current
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.mdx
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
In MDX files, top-of-file comments must use JSX comment delimiters: {/* to open and */} to close. Do not use HTML comments for MDX SPDX headers.
MDX top-of-file SPDX comments must use {/* ... */} delimiters instead of HTML comment delimiters (Must-Fix)
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
**/*.{html,md,mdx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license header in HTML and Markdown files using HTML comment syntax
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
docs/**/*.{md,mdx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update embedded documentation snippets, patch docs, and binding-support notes if examples or supported bindings changed
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
docs/**
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run
just docsor./scripts/build-docs.sh htmlto regenerate ignored Fern API reference pages before validation for documentation site changes
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}
⚙️ CodeRabbit configuration file
{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}: Review documentation for technical accuracy against the current API, command correctness, and consistency across language bindings.
Flag stale examples, missing SPDX headers where required, and instructions that no longer match CI or pre-commit behavior.
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdx
**
⚙️ CodeRabbit configuration file
**:AGENTS.md
This file provides guidance to agents, including Claude Code and OpenAI Codex, when working in this repository.
Project Overview
NeMo Relay is a multi-language agent runtime framework for execution scopes, lifecycle events, middleware, plugins, and observability around tool and LLM calls. The core runtime is Rust. Primary supported bindings are Rust, Python, and Node.js. Go, WebAssembly, and the raw C FFI are experimental and source-first.
The shared runtime model is:
- Scope stacks decide where work belongs and which scope-local behavior is visible.
- Middleware registries decide what guardrails and intercepts run around managed calls.
- Plugins install reusable runtime behavior from configuration.
- Events record runtime behavior in ATOF form.
- Subscribers and exporters consume events in-process or export them to ATIF, OpenTelemetry, OpenInference, or other backends.
Repository Structure
The repository layout separates the Rust runtime, language bindings, documentation,
integration patches, and agent-facing skills.crates/ core/ # Rust core runtime crate, published as nemo-relay adaptive/ # Adaptive runtime primitives and plugin components python/ # PyO3 native extension for the Python package ffi/ # Raw C ABI layer used by downstream bindings such as Go node/ # NAPI Node.js binding and JavaScript/TypeScript entry points wasm/ # wasm-bindgen WebAssembly binding and JS wrappers python/ nemo_relay/ # Python wrapper package: scopes, tools, LLM, middleware, typed helpers, plugins, adaptive helpers tests/ # Python tests go/ nemo_relay/ # Experimental Go CGo binding and tests fern/ # Fern documentation site scripts/ # Stable wrappers and helper scripts; build/test/docs entry points live in justfile third_party/ # P...
Files:
docs/nemo-relay-cli/plugin-installation.mdxdocs/nemo-relay-cli/codex.mdxintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,rst,html,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
**/*.{md,rst,html,txt}: Always spellNVIDIAin all caps. Do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company.
Use trademark symbols with product names only when the document type or legal guidance requires them.
Verify official capitalization, spacing, and hyphenation for product names.
Precede NVIDIA product names withNVIDIAon first mention when it is natural and accurate.
Do not rewrite product names for grammar or title-case rules.
Preserve third-party product names according to the owner's spelling.
Include the company name and full model qualifier on first use when it helps identify the model.
Preserve the official capitalization and punctuation of model names.
Use shorter family names only after the full name is established.
Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience.
Use the acronym on later mentions after it has been defined.
For long documents, reintroduce the full term if readers might lose context.
Form plurals of acronyms withs, not an apostrophe, such asGPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such asCPU,GPU,PC,API, andUIusually do not need to be spelled out for developer audiences.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,rst,html}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
Link the first mention of a product name when the destination helps the reader.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.md
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Documentation must be updated if activation or usage changed
**/*.md: Use title case consistently in technical documentation headings
Avoid quotation marks, ampersands, and exclamation marks in headings
Keep product, event, research, and whitepaper names in their official title case
Use title case for table headers
Do not force social-media sentence case into technical docs
Format code elements, commands, parameters, package names, and expressions in monospace
Format directories, file names, and paths in monospace using backticks
Use angle brackets inside monospace for variables inside paths, such as/home/<username>/.login
Format error messages and strings in quotation marks, keeping literal code strings in code formatting when clearer
Format UI buttons, menus, fields, and labels in bold
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use, sparingly and only when introducing the term
Use italics for publication titles
Format keyboard shortcuts in plain text, such as Press Ctrl+Alt+Delete
Use owner/repo link text for GitHub repositories, preferring[NVIDIA/NeMo](link)over prose references like 'the GitHub repo'
Introduce every code block with a complete sentence
Do not make a code block complete the grammar of the previous sentence
Do not continue a sentence after a code block
Use syntax highlighting when the format supports it for code blocks
Avoid the word 'snippet' unless the surrounding docs already use it as a term of art
Keep inline method, function, and class references consistent with nearby docs, omitting empty parentheses for prose readability when no call is shown
Use descriptive anchor text that matches the destination title when possible for links
Avoid raw URLs in running text
Avoid generic anchor text such as 'here,' 'this page,' and 'read more'
Include acronyms in link text when a linked term includes an acronym
Do not link long sentences or multiple sentences
Avoid links ...
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/{docs,examples,**/*.md,*.patch,*.diff,.github,*.sh,*.yaml,*.yml}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update documentation, examples, CI configuration, and patch artifacts when performing rename operations
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,rst,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
Spell
NVIDIAin all caps. Do not useNvidia,nvidia, orNV.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,rst}: Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as "here" or "read more."
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce.
Preferrefer tooverseewhen the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical docs.
Spell out months in body text, avoid ordinal dates, and use clear time zones.
Spell out whole numbers from zero through nine unless they are technical values, parameters, versions, or UI values.
Use numerals for 10 or greater and include commas in thousands.
Do not add trademark symbols to learning-oriented docs unless the source, platform, or legal guidance explicitly requires them.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant crate or package README when that surface changed
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{rs,py,js,ts,tsx,jsx,go,sh,toml,yaml,yml,md}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
🔇 Additional comments (2)
docs/nemo-relay-cli/plugin-installation.mdx (1)
1-137: LGTM!integrations/coding-agents/README.md (1)
1-222: LGTM!
Signed-off-by: Will Killian <wkillian@nvidia.com>
|
/merge |
3 participants
Overview
Add NeMo Relay plugin installation and runtime support for Claude Code and Codex. The change adds host plugin manifests, marketplace generation, CLI install/uninstall/doctor commands, hook-supervised Codex startup, and Claude provider routing setup.
Details
nemo-relay install,nemo-relay uninstall, andnemo-relay doctor --pluginflows for Codex, Claude Code, and all supported hosts.plugin-shimsupport for Codex hooks, lazy sidecar startup, Claude provider enable/restore, and hook forwarding.Validation run locally:
Where should the reviewer start?
Start with
crates/cli/src/plugin_install/mod.rsfor install orchestration andcrates/cli/src/plugin_shim/mod.rsfor host-specific setup and hook handling. The Codex lazy-start path is incrates/cli/src/plugin_shim/codex.rs, and the generated marketplace/plugin files are covered bycrates/cli/tests/coverage/plugin_install_tests.rs.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
New Features
nemo-relay install [<host>|all],nemo-relay doctor --plugin, andnemo-relay uninstall.Documentation
Tests
Chores