creatixchu
30704dc1df
Master dimensions move from a 2048 long-edge rule to a total-pixel budget (normalizedImageMaxPixels, default 2048x2048) with an 8192 long-edge cap, so extreme aspect ratios keep short-edge resolution. The shared quality ladder and lazy execution move to encoding.ts, review-round doc fixes land across attachment and llm packages, and the superseded facts in the unified-image-pipeline note now describe the shipped routing.
llm/ — LLM capability family
English | 中文
The LLM seam, provider adapters, and provider-specific request metadata plugins. 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 |
deepseek-llm-api-extensions/ |
Official DeepSeek request-field registry | ctx.deepseekLlmApiExtensions |
plugin-package-inventory-deepseek/ |
Active package metadata for official DeepSeek requests | contributes dsh_plugin_packages |
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.