DSH Plugins Marketplace

DSH Plugins

Plugins

/

dsh-endpoint

w

dsh-endpoint

Manifest valid

OpenAI-compatible HTTP endpoint that forwards model calls through a running DeepSeek Harness

UI (client)hasBundlePatch

dsh-endpoint

npm license ci

Expose the model providers and models already configured in DeepSeek Harness as an OpenAI-compatible HTTP endpoint.

The endpoint only forwards. It holds no provider credentials and never talks to a provider directly: every model call goes through ctx.llm.stream(), so DSH's provider adapters (credentials, protocol differences, retries, image handling, token usage) keep owning the real request.

中文

Architecture

OpenAI-compatible client
   │  POST /v1/chat/completions
   ▼
┌────────────────────── DSH host process ───────────────────────┐
│  dsh-endpoint (Cordis plugin)                                 │
│   HTTP listener → OpenAI mapping → SessionMirror → ctx.llm     │
│                                          │                     │
│                        dsh-llm-pi-ai / dsh-llm-deepseek-*      │
└──────────────────────────────────────────┼─────────────────────┘
                                           ▼
                                   provider API
  • Plugin only. No second process, no second credential store.
  • Sessions are real. Each conversation is mirrored into a DSH session, so it shows up in the sidebar and can be inspected.
  • Read-only mirrors. The mirrored session holds the persistence write handle, so the GUI refuses to resume it (already owned by an active write handle).

Install

Requires DeepSeek Harness Desktop (web profile) 0.2.1-rc.x.

From npm:

dsh plugin --profile web add dsh-endpoint

From a checkout (useful while developing):

dsh plugin --profile web add /absolute/path/to/dsh-endpoint

In the Desktop app you can also use Settings → Plugins and install it from the market once the package is listed.

No authentication, no rate limiting. The endpoint spends your configured model quota for anyone who can reach it. Keep it on 127.0.0.1 unless you put it behind a proxy you control, and disable the plugin to switch it off.

Restart the app after installing: host plugins are ESM modules, and reinstalling does not replace the module already loaded in the running process.

Settings page

Settings → Model Endpoint (a custom section, same level as plugin pages).

dsh-endpoint settings page

FieldMeaning
Listen address127.0.0.1 (local only) or 0.0.0.0 (all interfaces)
Portdefault 43130; the GUI owns 43129
Default modelused when a request omits model
Model aliasesJSON map, e.g. {"gpt-4o": "opencode-go/deepseek-v4.1-flash"}
Session mirrorwrite each API conversation into a DSH session
Mapping retentiondays an external conversation id keeps its session after last use
Workspace directoryworkspace that groups mirrored sessions

Saving applies immediately: changing the listen address or port rebinds the listener in place (the old listener closes, the new one binds, and a failed bind rolls back to the previous address). Switching 127.0.0.1 ↔ 0.0.0.0 takes the same path. Toggling the mirror or changing the workspace directory still needs a plugin reload, because those are built at startup.

In-flight streaming responses are dropped when the listener moves.

The page reads and writes two loopback-only routes: GET /dsh-endpoint/state and GET|PUT /dsh-endpoint/config. Saves go to the user layer $DSH_HOME/dsh-endpoint/config.json, which is merged over the plugin config at startup.

HTTP API

MethodPathNotes
GET/healthzliveness + registered providers
GET/v1/modelsprovider/model ids plus aliases
GET/v1/models/{id}one model
POST/v1/chat/completionsstreaming and non-streaming

Model ids are provider/model, e.g. opencode-go/deepseek-v4.1-flash.

Supported: messages (system/user/assistant/tool), tools and tool_calls pass-through, temperature, max_tokens / max_completion_tokens, stream, stream_options.include_usage, stop (truncated endpoint-side because not every adapter accepts it).

Rejected explicitly: n > 1, tool_choice other than "auto", remote (http(s)) media URLs, file_id references, and binary documents (PDF/DOCX).

Attachments

Inline base64 only — the endpoint never fetches remote URLs on a client's behalf.

InputHandling
image_url with data:image/{png,jpeg,webp,gif};base64,…decoded → ctx.attachments.saveImages → ImageBlock; the adapter resizes per route
image_url with http(s)://…400: send a data URL instead
file part with file_data of text/*, JSON, YAML, XML, JS, SQLinlined as a text block (512 KiB cap, filename preserved)
file part with a binary document (PDF, DOCX, …)400: text extraction is not implemented
file part with file_id400: the Files API is not implemented

Attachments live in DSH's attachment store, so the mirrored session keeps a compact reference instead of megabytes of base64.

Limits

LimitValueSource
Request body20 MiB, max 300 MiBlimits.maxBodyBytes, a plugin default. DSH's own /api limit is 300 MiB (314572800); higher values are rejected
One inline text file8 MiB, never above the body caplimits.maxTextFileBytes, a plugin default. DSH sets no file-size limit
One image20 MiBDSH attachment service (not this plugin)
Images per message20DSH attachment service
Total image bytes per message200 MiBDSH attachment service
Image pixels / longest side64 MP / 8192 pxDSH attachment service

The text-file cap is a prompt-size guard, not a protocol limit: the body is already bounded by maxBodyBytes, and a file near the cap is far past most models' context windows. Truncation is announced in the inlined text, so the model knows it is partial.

Ignored on purpose: every other unknown field (top_p, seed, service_tier, metadata, …). Real clients send fields this build does not model; rejecting them would break more than it protects, so they are logged and dropped rather than silently applied.

Session identity

Resolution order, first hit wins:

  1. x-dsh-session-id (this plugin's own header)
  2. known agent headers: x-session-id, x-conversation-id, x-chat-id, x-thread-id, x-agent-session-id, x-claude-code-session-id, x-codex-session-id
  3. body fields: session_id, conversation_id, chat_id, thread_id, metadata.session_id, metadata.conversation_id, user
  4. content fingerprint: sha256(model + first user message) — deterministic across requests and restarts
  5. only when there is no user message at all, a fresh id is minted

x-request-id, x-correlation-id and x-trace-id are never treated as session ids.

Every response echoes back the key the request used — the client's own header/body value, or the derived/minted key when the client sent none — so a client can store it and replay it on the next call. The internal mirror id is exposed separately as x-dsh-mirror-session for debugging; never send that one back.

Keys that cannot be written into a header (non-ASCII body values) are echoed in the endpoint's own ep-<32 hex> reference form, which resolves to the same conversation.

Only new user/tool messages are appended to the mirrored session (assistant messages are always the ones this endpoint produced), so logs grow per turn instead of quadratically. If the client's user history diverges from what was recorded, a new DSH session is started and the divergence is logged.

Supported clients

Any client that can point an OpenAI-compatible provider at a custom base URL:

export OPENAI_BASE_URL=http://127.0.0.1:43130/v1
export OPENAI_API_KEY=anything          # there is no auth; any placeholder works
ClientHow to configureStatus
curl / any HTTP clientPOST the body directlyverified
OpenAI Python SDKOpenAI(base_url="http://127.0.0.1:43130/v1", api_key="any")request shape verified
OpenAI Node SDKnew OpenAI({ baseURL: "http://127.0.0.1:43130/v1", apiKey: "any" })request shape verified
Cline (VS Code)Provider: OpenAI Compatible → Base URL + any keyexpected; not yet end-to-end tested
Roo Code (VS Code)Provider: OpenAI Compatibleexpected; not yet end-to-end tested
Continue (VS Code / JetBrains)provider: openai, apiBase: http://127.0.0.1:43130/v1expected; not yet end-to-end tested
OpenCode (CLI)custom provider in opencode.json, see belowverified, tool loop included
Cherry StudioAdd provider → OpenAI → API Hostexpected
ChatboxModel provider → OpenAI API → API Hostexpected
LobeChatOpenAI provider → proxy/base URLexpected
Open WebUIConnections → OpenAI → Base URLexpected

OpenCode

Model ids contain a slash, which breaks provider/model parsing on the client, so add a slash-free alias first (Settings → Model Endpoint → Model aliases), e.g. {"flash": "opencode-go/deepseek-v4.1-flash"}. Then point a project opencode.json at the endpoint:

{
  "provider": {
    "dsh": {
      "name": "DSH Endpoint",
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "http://127.0.0.1:43130/v1", "apiKey": "anything" },
      "models": { "flash": { "name": "DeepSeek via DSH" } }
    }
  }
}
opencode run -m dsh/flash "list the files here and tell me which is largest"

A ready-to-copy file lives at examples/opencode.json.

OpenCode sends x-session-id, which the endpoint already treats as the conversation key, so a whole multi-step tool loop lands in one mirrored session.

Tool calls are forwarded both ways (tools in, tool_calls out); OpenCode's shell/read tool loop has been verified end to end.

Limitations

  • No authentication and no rate limiting. The stop switch is disabling the plugin. Keep it on 127.0.0.1; binding 0.0.0.0 lets anyone who can reach the port spend your quota.
  • Inline images and text files only; remote media URLs and binary documents are refused.
  • n > 1, tool_choice other than auto, logprobs, top_p, seed are not applied.
  • Mirrored sessions cannot be continued in the GUI by design.
  • Pinned to DSH internal packages (0.2.1-rc.x); API changes there can break this plugin.

Development

pnpm install
node --test                              # 47 cases, no DSH required
node spike/mock-provider.mjs 44001       # local fake provider

spike/ also contains the P0 harness that creates a session in a throwaway DSH_HOME, persists it, restores it, and checks that GUI takeover is refused (spike/run.sh).

Verified / not verified

Verified on a real Desktop install:

  • /v1/models (31 models across opencode-go, deepseek-official, deepseek-account)
  • non-streaming and streaming chat with usage
  • the same conversation twice → the same x-dsh-session-id
  • mirrored session persists with turn/start → step/start → user → assistant → step/end → turn/end, second turn appends only the new user message
  • mirrored sessions appear in the sidebar workspace
  • agentLoop.resume refused while the write handle is held
  • settings page: section registered, config read/write round-trip
  • live listener rebind (43130 → 43131 → 43130) without restarting the app
  • inline image input (a 1152×883 screenshot was described correctly)
  • OpenCode driving a full tool loop (two shell calls in one turn, mirrored with tool results)

Not verified yet:

  • other IDE agents (Cline, Roo Code, Continue)
  • multiple concurrent conversations against one provider quota

Comments

Loading…

Similar plugins

dsh-openai-gateway

by pigman18

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.

Models & ProvidersManifest valid

★ 0

MIT

JavaScript

Nov 13, 2026

dsh plugin --profile web add dsh-openai-gateway

by paulalesius

OpenAI-compatible /v1/chat/completions (streaming and non-streaming) and /v1/models endpoint on the DSH web server.

Manifest valid

★ 0

TypeScript

Aug 24, 2026

dsh plugin --profile web add dsh-plugin-openai-api

by Fast-Editor

DeepSeek Harness (dsh) plugin: registers Lynkr as a custom OpenAI-compatible provider

Manifest valid

★ 0

MIT

TypeScript

Aug 28, 2026

dsh plugin --profile web add lynkr-dsh-plugin

by Jyjays

Configurable OpenAI Responses-compatible native web search provider for DeepSeek Harness, with a Settings UI to configure endpoint, model, and API key.

Manifest valid

★ 0

MIT

TypeScript

Aug 21, 2026

dsh plugin --profile web add dsh-websearch-custom

by wenzetan

NewAPI (OpenAI-compatible gateway) LLM provider plugin for DeepSeek Harness (dsh): chat-only model discovery + Web settings section. Zero dsh modifications.

Models & ProvidersManifest valid

★ 6

↓ 35/wk

MIT

TypeScript

Sep 24, 2026

dsh plugin --profile web add dsh-llm-newapi

by puciguala

Use configured DSH model providers and credentials for OpenAI Responses web search.

Manifest valid

★ 0

Apache-2.0

JavaScript

Oct 19, 2026

dsh plugin --profile web add dsh-web-search-custom