Tianyi Cui
2745879132
ImageBlock had no production producer and every consumer dropped it: the deepseek serializer skipped it, the pi-ai converter skipped it as unrepresentable, the ACP bridge neither advertises image prompt capability nor forwards image blocks, and compact-basic charged a flat 85-token estimate and rendered an [image] placeholder. A block constructed today would silently vanish from the wire — the vocabulary advertised a capability no path honors, the silent-data-loss shape the defensive patterns warn against. The only constructors were tests pinning the skip/estimate branches. Remove ImageBlock and its ContentBlockMap entry (its cache?: CacheHint field leaves with it; CacheHint itself and the other two cache? fields are out of scope). compact-basic loses its explicit image estimate and placeholder arms (the merge-extensible default arms absorb the case); the deepseek serializer, pi-ai converter, and ACP codec already handled image in their default arms, so only their image-naming comments change. The codec's inbound rejection of ACP-protocol image prompt content stays — that guards wire content a client can send regardless of our vocabulary. Tests that constructed harness image blocks to pin the removed branches are dropped (the 85-token estimate pin) or retargeted onto plugin-added block types / other non-text blocks, which the surviving default arms own. Docs, the type-equiv pastes, and the content-block vocabulary RFC's block list and multimodal-home consequence are updated in the same change; the RFC moves to implemented/ and the index is regenerated. A real multimodal feature reintroduces image via declaration merging together with the adapter mapping, ACP advertisement, and compaction pricing that honor it.
@deepseek-ai/dsh-llm-pi-ai
DeepSeek adapter for the harness LLM seam backed by @earendil-works/pi-ai (the LLM library behind the pi agent).
Why a second adapter exists
@deepseek-ai/dsh-llm-deepseek already talks to the same endpoint. This package is its design-verification twin: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness StreamChunk protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose:
- pi-ai hands tool-call
argumentsaround as parsed objects; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls atblock-end. - pi-ai reports failures as in-stream error events (it never throws mid-stream); these map to
finish {kind:'error'|'aborted'}chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). - pi-ai folds reasoning tokens into
usage.output; there is no separate reasoning count to map. - pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its
onPayloadhook to preserve the harness contract (stop, per-toolstrict, omitted reasoning effort, raw replayed tool arguments).
Config
Same shape as llm-deepseek (one-line swap in cordis.yml), with pi-ai's thinking-level vocabulary:
- id: llm
name: '@deepseek-ai/dsh-llm-pi-ai'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY
baseURL: !!js process.env.DEEPSEEK_BASE_URL
models: [deepseek-v4-flash, deepseek-v4-pro]
reasoning: high # off | high | xhigh (xhigh → wire 'max')
Dependency weight
pi-ai declares the openai/anthropic/google/mistral/AWS SDKs as install-time dependencies. They are lazy-loaded — only the openai SDK actually loads for this adapter — but they do land in node_modules. Accepted for a package whose purpose is design verification.
Limitations
Same MVP contract as llm-deepseek: prefill throws UNSUPPORTED, tool_choice is not mapped.
Testing
Unit suites run against a local node:http mock SSE server (pi-ai's openai SDK happily talks to any base URL). Real-API coverage in tests/adapter.e2e.ts (pnpm run test:e2e, key-gated): V4 Flash + V4 Pro across all exposed reasoning levels (off/high/xhigh), the thinking+tools round trip, and a cross-adapter structural-equivalence check against llm-deepseek.