mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
ec9a08bdde
# Conflicts: # .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/module-graph.md # packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx # packages/client/ui-conversation/src/client/index.ts # packages/compact/compact-basic/README.i18n.yaml
llm/ — LLM capability family
English | 中文
The LLM seam and its provider adapters. The interface package (llm) owns the abstract service, the content-block vocabulary, and the stream-chunk assembler; the adapters are concrete implementations that 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.