2nd dokployH
The first real LlmAdapter implementations, shipped as a deliberate pair:
same models and wire protocol, completely different internals, so the
StreamChunk protocol is verified across independent implementations.
- dsh-llm-deepseek: hand-rolled fetch + SSE parser + chunk-translation
state machine against the official chat-completions format (thinking
mode via top-level thinking/reasoning_effort; the empty-string
reasoning_content first chunk; usage attached to the finish chunk or
trailing; reasoning_content passback on tool-call turns; disjoint
cache-token accounting).
- dsh-llm-pi-ai: the same endpoint through @earendil-works/pi-ai,
mapping its event vocabulary (parsed tool arguments, in-stream error
events, folded reasoning tokens) onto the same chunks.
The agent loop now honors the in-band error path: an adapter that ends
its stream with finish {kind:error|aborted} (the only option for
adapters that can't throw mid-stream, like pi-ai) is translated into a
step error, so the turn ends error/aborted with a logged error event
instead of a normal completed assistant message. This makes the
StreamChunk error contract real for both adapters; docs/architecture.md
and the StreamChunk doc are updated accordingly.
New yarn test:e2e (vitest.e2e.config.ts, *.e2e.ts) runs key-gated
real-API matrices for both adapters across V4 Flash/Pro and all
thinking/effort levels; it self-skips without DEEPSEEK_API_KEY. Unit
suites run against local node:http mock SSE servers at 100% per-file
coverage.
|
||
|---|---|---|
| .github/workflows | ||
| docs | ||
| examples | ||
| packages | ||
| scripts | ||
| vendor | ||
| .gitignore | ||
| .yarnrc.yml | ||
| AGENTS.md | ||
| CLAUDE.md | ||
| eslint.config.mjs | ||
| knip.json | ||
| lefthook.yml | ||
| LICENSE | ||
| package.json | ||
| README.md | ||
| tsconfig.base.json | ||
| tsconfig.build.json | ||
| tsconfig.json | ||
| tsconfig.test.json | ||
| tsconfig.typecheck.json | ||
| tsdown.config.ts | ||
| vitest.config.ts | ||
| vitest.e2e.config.ts | ||
| yarn.config.cjs | ||
| yarn.lock | ||
DeepSeek Harness
Monorepo for the DeepSeek Harness group.
Projects
- DeepSeek Code — DeepSeek's coding agent product.
Development
This monorepo is built on the Cordis framework (vendored as source under vendor/), microkernel-style: everything is a plugin.
yarn install
yarn test # vitest
yarn demo # runnable echo-agent example
For agent instructions see AGENTS.md. For the architecture design see docs/architecture.md. Each subdirectory has its own README.md with local context: packages/, vendor/.