dsh-llm-gateway-compat
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.
What it does
Streamed tool-call identity (v0.1)
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.
Request dialect 400s (v0.2)
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.
Chat Completions adapter (v0.3)
Optional routes under llm-gateway-compat.providers. Each route is a direct POST {baseURL}/chat/completions adapter with gateway-safe defaults:
- system prompt is always
role: system
- output cap is always
max_tokens
- empty tool-call id/name never overwrite, even if stream sanitizing is off
extraBody for fields the harness vocabulary does not own (user, prompt_cache_key)- extra headers,
Authorization: Bearer or DashScope api-key
- thinking dialect:
reasoning_content (default), thinking, think-tags, or none
Route ids must not collide with llm-deepseek or llm-pi-ai. Pick a new id such as dashscope-compat.
Install
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
Config
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 |
Develop
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
Known limitations
- Cannot recover a tool name the gateway never emitted.
- Image input is refused (
UNSUPPORTED_CONTENT).
think-tags is applied on replayed assistant history, not on partial streamed tags.- No idle-stream watchdog; caller
AbortSignal is honored.
- Auto-apply only writes
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.- Volatile fields are editable from the settings forms. Other edits belong in the profile patch.
License
MIT
