dsh-mercury-diffusion

dsh-mercury-diffusion

Watch a diffusion LLM think — live, inside your DeepSeek Harness chat.

A [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (dsh) plugin that streams the real denoising frames of [Inception Mercury](https://docs.inceptionlabs.ai) and plays them in the answer bubble, from noise to finished text.

English · [简体中文](README.zh-CN.md)

---

Promo video

Highlights

• Real frames, not a fake animation. Every frame is a denoising state returned by the Mercury API (diffusing: true), replayed at a readable pace.
• Works with the provider route you already have. The plugin registers no provider and no settings page of its own; it adds a diffusion layer under the route you add on dsh's Models page.
• Zero-cost capability probe. Whether a route/model honors diffusing is measured with a request that is rejected before any token is generated. No model-name guessing, no billed tokens.
• Never breaks a conversation. Attachments, auxiliary calls, unwatched sessions, routes without a credential, or a gateway that rejects the field all fall back to the original adapter untouched.
• Clean session logs. Intermediate frames travel on a side channel; only the converged text is written to the log and shown to the model.
• One-click toggle per model. A small floating button appears for capable models; your choice is stored in dsh user settings (plugin config key diffusion.::) and survives restarts.

Quick start

Requirements: dsh >=0.2.1-rc.2 <0.3.0, Node ^22.19 || >=24, and [pnpm](https://pnpm.io) on your PATH (dsh plugin uses it to manage profile plugins).

1. Install

dsh plugin --profile web add dsh-mercury-diffusion
dsh web

Install from source instead

git clone https://github.com/TonyWu2333/dsh-mercury-diffusion.git
cd dsh-mercury-diffusion
npm install
npm pack
dsh plugin --profile web add ./dsh-mercury-diffusion-0.2.1.tgz
dsh web

2. Add an Inception route

Open Settings → Models → Add model provider → Custom model API and fill in:

| Field | Value |

|---|---|

| Provider ID | inception |

| Display name | Inception |

| Base URL | https://api.inceptionlabs.ai/v1 (must include /v1) |

| API protocol | OpenAI Chat Completions |

| API key | your Inception API key |

| Models | Add model → mercury-3 (or mercury-2.5, mercury-2) |

Then click Create provider.

> [!WARNING]

> Don't point the built-in DeepSeek card at Inception. That adapter speaks a different protocol, and requests fail with 404.

Prefer config files? Add the route to cordis.patch.yml

# ~/.dsh/profiles/web/cordis.patch.yml
- id: llm-pi-ai
  name: "@deepseek-ai/dsh-llm-pi-ai"
  config:
    providers:
      inception:
        displayName: Inception
        api: openai-completions
        baseURL: https://api.inceptionlabs.ai/v1
        apiKeyEnv: INCEPTION_API_KEY   # a credential reference, not the key itself
        models:
          - id: mercury-3
            name: Mercury 3
            contextWindow: 1000000
            maxTokens: 131072

Use the bare model id (mercury-3) when calling Inception directly. Gateways that aggregate providers usually expect the prefixed form (inception/mercury-3).

3. Turn it on

Pick the Mercury model from the model selector next to the send button and start a new conversation. A floating button appears on the right edge; switch diffusion on and send a message.

How it works