Coder
99b63abde6
Extend the openRouterCost projection with a per-step priced-cost map keyed by turn:step so surfaces can render spend without re-pricing, and have the Trajectory view read it through the framework useProjection seat: each priced assistant step shows its USD cost on the request boundary chip and in the inspector summary, while unpriced steps stay blank. Also fix a pre-existing exactOptionalPropertyTypes error in extractCacheRates that the host typecheck surfaced.
llm/ — LLM capability family
English | 中文
The LLM seam and its provider adapters. The llm package owns both the Service Definition and Consumer roles: the abstract service, content-block vocabulary, and stream-chunk assembler. Provider adapters register on ctx.llm. All product packages.
| Package | Role | ctx key |
|---|---|---|
llm/ |
LLM service and shared streaming vocabulary | ctx.llm |
token-meter/ |
Replay-aware token measurement | ctx.tokenMeter |
llm-retry/ |
Provider-scoped retry policy | listens to agent/request-error |
llm-deepseek/ |
Direct DeepSeek adapter | registers on ctx.llm |
llm-pi-ai/ |
Multi-provider pi-ai adapter | registers on ctx.llm |
Adapters register provider routes on the seam; retry and token measurement remain separate consumers. The child READMEs own routing, metadata, replay, and provider-wire details; the LLM architecture decisions own the rationale.
The subsystem reference — messages and blocks, the model request, the StreamChunk protocol, the adapter contract — is docs/subsystems/llm-streaming.md (token measurement: token-meter.md); see the twin adapters, replay token meter, and routed model context Agent Notes.