mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
b0d1d9445e
# Conflicts: # apps/web/tests/snapshots/queue-actions/preserved.expected.md # docs/cordis-catalog/services.md # docs/core-data-structures/session.i18n.yaml # packages/client/runtime/src/client/session-history/history-fold.ts # packages/client/ui-conversation/README.i18n.yaml # packages/core/session/src/index.ts
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.