mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
aa0ca6c836
core.md read as a type grab-bag: LLM wire vocabulary up front, the agent/loop story buried, and no correspondence to packages/core. It now opens on the packages/core control spine — the package-by-package loop map with a Page column into session/system-prompt/tools/scope — and keeps only what the spine group declares plus the repo-wide patterns: the Agent handle with its delivery/cancellation/interception contracts, the SessionEvent envelope, branded ids, the …Map pattern. The conversation vocabulary (Message/ContentBlock, the model request, adapters — 17 type-equiv blocks) moves to llm-streaming.md, which now declares packages/llm end-to-end; the duplicate ContentBlockMap paste near its seam section folds into the moved section, and the manifest, LINK_MAP, README table rows, website label (Core data structures → Core), and inbound anchors follow. Every packages/<group>/README pair is now a thin front door in one shape: a why-first intro (bash's seam-pattern-first paragraph rewritten as 'shell execution for the agent'), the package table, and a closing pointer to the owning docs/subsystems page — the bash-style table stays the load-bearing middle. Load-bearing trailing paragraphs relocate rather than vanish: the fs no-timeout rationale becomes a filesystem.md section (both languages), session's four sectioned tables merge into one 12-row table, examples' legacy-bin H2 collapses to a pointer at jsonrpc-demo's README, and design rationale that already lives in an Agent Note or subsystem page is now linked instead of restated. All 40 pair records re-recorded.
1.6 KiB
1.6 KiB
llm/ — LLM 能力家族
English | 中文
LLM（大语言模型）seam 及其提供方适配器。接口包（llm）负责抽象服务、内容块词汇和流式分片组装器；适配器是注册到 ctx.llm 的具体实现。这些全是产品包。
| 包 | 职责 | ctx key |
|---|---|---|
llm/ |
LLM 服务和共享流式词汇 | ctx.llm |
token-meter/ |
可感知回放的 token 测量 | ctx.tokenMeter |
llm-retry/ |
提供方作用域的重试策略 | 监听 agent/request-error |
llm-deepseek/ |
直接 DeepSeek 适配器 | 注册到 ctx.llm |
llm-pi-ai/ |
多提供方 pi-ai 适配器 | 注册到 ctx.llm |
适配器在 seam 上注册提供方路由；重试与 token 测量仍是独立消费方。子 README 负责路由、元数据、回放和提供方协议细节；LLM 架构决策负责设计原理。
子系统参考——消息与内容块、模型请求、StreamChunk 协议、适配器契约——见 docs/subsystems/llm-streaming.md（token 计量：token-meter.md）；另见孪生适配器、回放 token 计量与按路由模型上下文 Agent Note。