a0268d2509
Automatic compaction fires mid-conversation, right after the loop warmed the provider's KV cache with the last routed request. The default summarizer then issued a separate request whose prefix shared nothing with that warm request — a bespoke summarizer system prompt followed by the older history flattened to one rendered transcript string — so a differing first token invalidated the entire cached prefix and every compaction re-processed the whole replayed history twice. Move the compaction directive from the FRONT (a fresh system prompt) to the END (a trailing user message), and replay the last routed request's own system prompt, tools, message prefix, and shadowed-region messages verbatim via session.requestHeader() + deriveEventMessage. The auxiliary call is now a genuine prefix-extension of the warm request, so the provider reuses the cached tokens up to the trailing instruction. SummarizationInput carries the replayed prefix instead of a flat string; the now-unused renderTranscript/renderContentBlocks path is removed with its spec. Cache reuse is best-effort (head compaction guarantees a hit; a mid-range compaction or a differently-routed summarizer forgoes it), correctness is not.
DeepSeek Harness
English | 中文
The DeepSeek Harness SDK is a plugin-based SDK for building agent harnesses.
Development
This monorepo is built on the Cordis framework (vendored as source under vendor/), microkernel-style: everything is a plugin.
pnpm install
pnpm run test # vitest
# Agent demos require DEEPSEEK_API_KEY.
pnpm run demo:tui # full-screen TUI coding agent
pnpm run demo:headless "task" # one-shot coding agent
pnpm run demo:cordis # self-referential agent demo
pnpm run demo:acp # ACP server agent demo
For humans, start with the development guide for local setup, hooks, environment variables, and quality gates, then read the architecture design and documentation graph index before package work. Local context lives in packages/ and vendor/.
For agents, follow AGENTS.md.