0ebb86e70f
dsh-llm owns the vocabulary (attribution.ts): AppIdentity with the version
read from the package manifest, userAgent(), and attributionHeaders(target,
identity) over a closed AttributionTarget union ('generic' | 'openrouter').
Both adapters send the headers on every provider request — llm-deepseek in
its fetch headers, llm-pi-ai through pi-ai's StreamOptions.headers — behind
an explicit attributionTarget config (never inferred from baseURL), with
mock-server tests asserting exact wire arrival and the absence of the
OpenRouter set by default.
The RFC moves to implemented/ amended with the settled identity (the
deepseek-harness token, the DeepSeek Harness title, the planned
deepseek-ai/deepseek-harness-sdk URL behind a FIXME until that repo exists)
and the explicit-config OpenRouter decision.
@deepseek-ai/dsh-llm-deepseek
DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled fetch + SSE translation from the official wire format (source of truth: the API docs — guides/thinking_mode, guides/tool_calls, api/create-chat-completion) into the StreamChunk protocol.
A second, independent implementation of the same seam exists in @deepseek-ai/dsh-llm-pi-ai (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design).
Config
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY # or rely on the env fallback
baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com
models: [deepseek-v4-flash, deepseek-v4-pro] # one adapter, registered for each name
thinking: enabled # optional; provider default is enabled
reasoningEffort: high # optional; high | max — omitted ⇒ not sent
attributionTarget: openrouter # optional; generic | openrouter — omitted ⇒ generic
models lists every model name this one adapter instance serves: the adapter registers itself for each (the harness model name IS the wire model string), so a generate/stream call routes to it whenever options.model is any of them. Registering a second adapter for a name already taken throws LlmError('DUPLICATE_ADAPTER') (the LLM service enforces one adapter per model, all-or-nothing).
reasoningEffort is omitted by default — when unset, the reasoning_effort wire field is not sent and the server applies its own default for the model. The only accepted values are high and max (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default).
thinking/reasoningEffort are adapter-level request defaults serialized as the official top-level thinking: {type} / reasoning_effort wire fields. They live in adapter config (not GenerateOptions) to keep the core vocabulary provider-neutral.
App attribution
Every request carries the shared attribution headers from dsh-llm's attributionHeaders() — the mandatory User-Agent baseline identifying the harness (see dsh-llm § App attribution). Direct DeepSeek requests get no provider-specific headers. Set attributionTarget: openrouter only when baseURL points at OpenRouter: it adds OpenRouter's documented app-attribution set (HTTP-Referer, X-OpenRouter-Title, X-OpenRouter-Categories). The target is explicit config by design — the adapter never infers it from the URL.
Wire-format notes (verified live + against the official docs)
- Streaming only (
stream_options.include_usagealways on).usagemay arrive attached to the finish chunk or as a trailing usage-only chunk — the translator defers both to[DONE], sousagealways precedesfinishand nothing followsfinish. - The first thinking-mode chunk carries
reasoning_content: ""— handled (no spurious reasoning block). - Reasoning passback rule: on assistant turns that carried tool calls,
reasoning_contentis serialized back in history (required by the API in thinking mode); on tool-call-free turns it is dropped (ignored anyway — saves tokens). stricton tool schemas passes through (officially Beta; the public API wants the/betabase URL for it, the internal endpoint accepts it directly).- Cache accounting:
cacheReadTokens←prompt_cache_hit_tokens/prompt_tokens_details.cached_tokens; DeepSeek reports no cache-write metric.
Limitations (MVP, documented deliberately)
prefillthrowsLlmError('UNSUPPORTED')— DeepSeek's chat-prefix completion is a Beta feature on the/betabase URL; future work.imageblocks are skipped (no vision support on these models).tool_choiceis not mapped (not part of the core vocabulary).
Errors
Non-2xx responses throw LlmError with stable codes: AUTH (401/403), RATE_LIMIT (429), INVALID_REQUEST (400), SERVER (5xx), HTTP_<status> otherwise. Protocol violations throw STREAM_CLOSED (no [DONE]) or MALFORMED_RESPONSE (bad JSON payload). Unknown wire finish_reasons (e.g. content_filter, insufficient_system_resource) become finish {kind: 'error', code: <REASON>} chunks.
Testing
Unit suites run against a local node:http mock SSE server (no network). Real-API coverage lives in tests/adapter.e2e.ts (pnpm run test:e2e, key-gated): V4 Flash + V4 Pro across thinking enabled/disabled and both official effort levels, including the thinking+tools round trip with reasoning passback.