dsh-llm-gateway-compat
适用于 DeepSeek Harness 的 OpenAI 兼容网关适配器和方言修复
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-llm-gateway-compat@0.5.0Llm Gateway Compat 以 dsh-llm-gateway-compat 发布，当前版本为 0.5.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文
A community bundle compatible with DeepSeek Harness (DSH) 0.2.1-alpha.2 or later. It stops empty streamed tool-call identity from wiping the call, turns the two most common request 400s into an llm-pi-ai compat write plus one retry, and can own Chat Completions routes that default to system / max_tokens.
This is not an official DeepSeek package. It is not endorsed by DeepSeek.
0.5.0 follows the 0.2.1 configuration and message model. It will not load on 0.1.x.
Wraps llm/stream so later SSE fragments with empty id / name cannot overwrite a nonempty value. Synthesizes compat_call_<index> when no id ever arrives. Official DeepSeek streams stay unchanged when identity is already stable.
On agent/request-error, classifies developer-role and max_completion_tokens refusals, writes the matching field into official llm-pi-ai settings, retries the same step once, and injects a logged plugin notice. Generic 400s are not retried.
Optional routes under llm-gateway-compat.providers. Each route is a direct POST {baseURL}/chat/completions adapter with gateway-safe defaults:
role: systemmax_tokensextraBody for fields the harness vocabulary does not own (user, prompt_cache_key)Authorization: Bearer or DashScope api-keyreasoning_content (default), thinking, think-tags, or noneRoute ids must not collide with llm-deepseek or llm-pi-ai. Pick a new id such as dashscope-compat.
From GitHub (ships built lib/, no install-time TypeScript build):
dsh plugin --profile web add github:snowshadow/dsh-llm-gateway-compat
Restart dsh web. Pin a commit (github:snowshadow/dsh-llm-gateway-compat#<sha>) so a later push cannot change what runs. Only add packages whose source you trust.
From a local checkout:
dsh plugin --profile web add /absolute/path/to/dsh-llm-gateway-compat
Plugin switches live on the llm-gateway-compat profile entry. Volatile fields update the running plugin; the settings forms edit those same fields.
| key | default | meaning |
|---|---|---|
enabled | true | master switch for stream wrapping and 400 recovery |
diagnose | true | classify known gateway 400s and inject a YAML snippet |
autoApplyCompat | true | persist the matching llm-pi-ai compat field and retry once |
providers | {} | Chat Completions routes this plugin owns |
One gateway route:
# llm-gateway-compat entry config
providers:
dashscope-compat:
displayName: DashScope
baseURL: https://dashscope.aliyuncs.com/compatible-mode/v1
apiKeyEnv: DASHSCOPE_API_KEY
authHeader: bearer
thinkingFormat: reasoning_content
extraBody:
user: harness
models:
- id: deepseek-v4-flash
name: DeepSeek V4 Flash
Store DASHSCOPE_API_KEY on the Models page or in $DSH_HOME/.credentials.yaml, or export it in the environment that launches dsh. Include /v1 (or /compatible-mode/v1) in baseURL when the gateway requires it. Then select the dashscope-compat / deepseek-v4-flash route in the model picker.
Provider fields:
| key | default | meaning |
|---|---|---|
baseURL | required | origin plus path prefix; /chat/completions is appended |
apiKeyEnv | required | credential reference: Models page / $DSH_HOME/.credentials.yaml, then that environment variable |
authHeader | bearer | bearer or api-key |
models | [] | advisory catalog; unlisted ids still resolve as text-only |
extraBody | — | merged under harness-owned fields; max_completion_tokens is stripped |
headers | — | extra request headers; User-Agent still comes from harness attribution |
thinkingFormat | reasoning_content | history + stream reasoning dialect |
includeUsage | true | send stream_options.include_usage |
Typecheck and tests expect a sibling deepseek-harness checkout at ../deepseek-harness, or DSH_HARNESS, at 0.2.1-alpha.2. pnpm test / pnpm run build link @deepseek-ai/dsh-llm, cordis, and schemastery to that checkout. The checkout must already be built (lib/ present).
pnpm install
pnpm test
pnpm run build
UNSUPPORTED_CONTENT).think-tags is applied on replayed assistant history, not on partial streamed tags.AbortSignal is honored.supportsDeveloperRole: false and maxTokensField: max_tokens on llm-pi-ai routes, through the profile configuration editor.developer messages (tool additions and removals) are not sent. The request still carries the current tools list.MIT