The Responses route now resolves openrouter alongside openai. The OpenRouter config reuses the OpenAI request and response transforms and owns only its bearer credential (OPENROUTER_API_KEY, then OR_API_KEY) and base URL (OPENROUTER_API_BASE). Wire model ids follow Python's get_llm_provider, including the openrouter/auto native id with an explicit provider. The Python route host no longer hands litellm.openai_key to OpenRouter. The OpenRouter live test lives in tests/live/openrouter.rs and returns early when the provider key is not exported, so cargo test stays offline by default instead of hiding it behind --ignored. Co-authored-by: nate-berri <nate@berri.ai> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
4.4 KiB
Rust workspace rules
For diagnostic tracing changes, follow .agents/skills/rust-tracing/SKILL.md
For string-valued enums and their Serde conversions, follow .agents/skills/rust-string-enums/SKILL.md
For fieldless enums, derive strum::VariantArray and use VARIANTS instead of a hand-listed ALL array. Derive Strum string conversions instead of hand-written variant-to-string matches
Use the derived conversions directly (<&'static str>::from(x) / .into(), str::parse) with no as_str/parse wrapper that only delegates, and spell each variant with explicit #[strum(serialize = "...")] instead of serialize_all
Test placement
- Never create a
tests.rs(ortest.rs) file undersrc/, and never#[path = "tests.rs"] mod tests; - Tests live inline by default, in a
#[cfg(test)] mod tests { ... }at the bottom of the file that owns the code under test, whether or not they touch private items crates/<crate>/tests/is only for tests that drive several modules together end to end, such as a full request through a route. A test of one type or function never goes there- A helper shared by several inline test modules goes in a
#[cfg(test)] mod test_support;at the crate root, and only once a second module needs it - A test for another crate's item belongs in that crate, not in a downstream one
- Tests that call a real provider go in
crates/<crate>/tests/live/<provider>.rsbehind atests/live/main.rs. Each reads the provider's key from the environment through anOptionfixture and returns early when it is unset, never#[ignore], socargo teststays offline until the key is exported - Never set
autotests = falseor hand-list[[test]]targets. Every file directly undertests/is discovered by cargo, and a shared helper goes intests/<name>/mod.rsortests/<subject>/support.rsso it is not picked up as a test crate of its own
Test fixtures and cases
Use #[rstest] for new and updated tests and #[fixture] for reusable setup, injected through typed test arguments. Express input variations as named #[case::name(...)] cases instead of loops or duplicated tests so each failure identifies its case. Keep behavior assertions in the test body and fixtures focused on setup. Use the workspace rstest dependency
- Never loop over inputs (
for,.iter().for_each,.all) inside a test body. Give each input its own#[case::name(...)], or use#[values(...)]for a cross product - Exception: a test pinning a Rust table against a repo-owned data file (for example
include_str!of a JSON config) may iterate that file's entries
Error definitions
- A crate's errors live in
src/error.rs, defined withthiserror, and re-exported fromlib.rs - Put message templates in the variant's
#[error(...)]declaration. Callers pass only the small typed arguments needed to fill them, neverError::Variant(format!(...))or a preformatted message. Keep the smallest set of neutral variants that callers need to distinguish. Different wording or providers do not justify new variants - Default to one top-level
Errorenum per crate, with one variant per failure mode and a#[error(...)]message on each. A failure mode is something a caller handles differently (phase, status code, retry, a message Python parity pins exactly). Failures no caller tells apart share one variant and differ only in its message - Keep shared error enums minimal and provider-neutral. Provider names, credential types, configuration fields, and setup guidance belong in caller-supplied data, not dedicated variants or hardcoded shared messages. Reuse a variant for the same failure mode across providers, such as
MissingApiBase { provider: "Azure", guidance: "..." }. An exact parity message does not justify a provider-specific variant when caller-supplied context can preserve it - Wrap a lower-level error as a variant with
#[from]or#[source]instead of flattening it to a string - Exception: split into separate types when different functions fail in disjoint ways, especially when different callers see them. A shared enum would force every caller to match variants its function can never return
- Name a split type after what went wrong (a unit struct is fine for a single failure mode), not after the function that returns it