mesh-llm skippy-server
Use this skill for skippy serving, embedded runtime lifecycle, and binary stage-to-stage transport.
Current Repo Shape
The mesh integration embeds skippy-server through Rust APIs instead of
launching it as mesh's public OpenAI surface. Public OpenAI compatibility
belongs in openai-frontend; skippy-server should remain the backend stage
runtime.
Important crates:
crates/skippy-server
crates/skippy-protocol
crates/skippy-runtime
crates/mesh-llm/src/inference/skippy
Validation
Run cargo commands serially:
cargo check -p mesh-llm
cargo test -p skippy-server --lib
cargo test -p skippy-protocol --lib
cargo test -p mesh-llm-host-runtime --lib inference::skippy
For lifecycle/status changes, also run:
cargo test -p mesh-llm-host-runtime --lib
Rules
Do not reintroduce standalone kv-server or ngram-pool dependencies into
mesh. Keep structured outputs, tools, logprobs, and /v1/responses
compatibility in openai-frontend.
Stage status exposed by mesh should be backend-neutral at the API boundary. Backend-specific details can remain in internal skippy structs.