94289d057e
A model the installed pi-ai catalog does not describe was reported as text-only with no way to say otherwise, so a vision model added through the custom-provider form was refused at every image admission point. The justification in the source described the DeepSeek chat-completions serializer, which does reject image blocks; the pi-ai request converter and every wire protocol it speaks carry images. Modalities now resolve entry `input` -> installed catalog entry -> route `defaultInput`, the chain the two capacity fallbacks already use, so the route value is a fallback and never narrows a catalog model. Its default stays `[text]`: nothing can interrogate a gateway for its modalities, and over-claiming admits an image the provider rejects mid-turn, after prompt admission has already committed the message.
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.