Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Rust
docs: fix reasoning_effort docs (#1274)
Greg Clark0203ac603d85
diff --git a/docs/routing_algorithms/model_selection.md b/docs/routing_algorithms/model_selection.mdindex 578633c95..c465451ac 100644--- a/docs/routing_algorithms/model_selection.md+++ b/docs/routing_algorithms/model_selection.md@@ -274,26 +274,15 @@ Record it with every result. Three rules apply:`reasoning_effort` key instead. It writes `reasoning.effort` on`openai_responses` and `reasoning_effort` on `openai_chat`, replacing the valuethe client sent. The DeepSWE profiles above use it to run both tiers at `max`.-- `reasoning_effort` is rejected on `anthropic_messages` clients. The server does- not start:-- ```text- target weak reasoning_effort is only supported on openai_chat and openai_responses clients- ```-- For those targets the effort the client sends is passed through in- Anthropic's form.--- One route cannot hold the same model at two efforts. Two targets with the same- model ID on one client but different `reasoning_effort` or `extra_body` fail- to load:-- ```text- targets strong and strong_max both name model openai/gpt-4o on llm client openrouter but with different reasoning_effort, extra_body, or omit_body_fields; one target per model id is kept, so give each its own model id or llm client- ```-- Separate routes can use separate `llm_clients` entries for the same- endpoint. See the [target keys](../reference/toml_schema.md#targetsname).+- On `anthropic_messages`, the target's `reasoning_effort` writes+ `output_config.effort`, replacing the value the caller sent. Switchyard accepts+ `low`, `medium`, `high`, `xhigh`, and `max` for this format. Choose an effort+ supported by the upstream provider and model. When the target leaves+ `reasoning_effort` unset, the caller's effort is passed through.+- One route can use multiple target names with the same provider model ID and+ `llm_client` at different efforts. Each target keeps its own `reasoning_effort`,+ `extra_body`, and `omit_body_fields`. See the+ [target keys](../reference/toml_schema.md#targetsname) for an example.## Related