Skip to main content

dsh-claude-provider

38Stars0Forks0Issues0Watchers

Add an independent Claude provider type for DSH model settings, with gear levels based on model configuration, and support for Anthropic native model detection with pre-filled known model capacities.

Evidence5/5methodologySourceInstallMaintenanceDSH versionSecurity scan
Machine-auditedInstall commandRepo verifieddsh-plugin topicLicenseREADMEAI wiki
Language
JavaScript
License
MIT
Branch
main
anthropicclaudedeepseek-harnessdsh-plugin

Install

cmdweb profile
$ dsh plugin --profile web add @mofeng2223/dsh-claude-provider

Run the command above in your terminal to install this plugin via the dsh CLI. You can switch Profile in the top-right corner. New to dsh? Read the beginner tutorial

Install via your agent

Install the DeepSeek Harness plugin MoFeng2223/dsh-claude-provider for me: review the repository at https://github.com/MoFeng2223/dsh-claude-provider first, then run the install command and verify the plugin loads successfully.

Paste this instruction to the DSH Web GUI assistant — it will install and verify for you.

One-Sentence Description

Adds a standalone Claude provider type to DeepSeek Harness's model settings page, automatically writes RC8 native configuration, and supplements Anthropic native model detection with capacity pre-filling for common Claude models.

Core Capabilities

  • Adds "Claude Provider" entry on the model settings page, managed separately from regular custom providers, allowing creation of multiple Provider IDs
  • Separate thinking effort presets per model: five levels (low/medium/high/xhigh/max), four levels (low/medium/high/max), or toggle (off/high)
  • Detects model list via Anthropic's native GET /v1/models interface, supports cursor pagination, can point to any compatible gateway
  • When detected model ID matches a recorded Claude model ID, automatically fills context window, max output length, and effort preset
  • Only affects Provider IDs explicitly registered as Claude provider, does not modify built-in providers or other anthropic-messages custom routes

Technical Implementation

  • Language: JavaScript (ESM, "type": "module")
  • Key Dependencies: @deepseek-ai/dsh-settings (injects settings and llm services), @deepseek-ai/schemastery (declares settings schema), @deepseek-ai/dsh-client-ui-settings-models (devDependency only, used for building frontend patch client)
  • Architecture Pattern: Backend registers namespace to ctx.settings and configurable provider to ctx.llm via apply(ctx), wraps llm.discoverModels to route Claude provider through native Anthropic detection; frontend uses cordis.patch.yml to disable built-in ui-settings-models, replacing it with lib/client.js (compiled from scripts/build-client.mjs which performs AST text replacement on upstream dsh-client-ui-settings-models)
  • Entry Files: src/index.js (backend apply/export), lib/client.js (frontend bundled artifact), scripts/build-client.mjs (build script)

Use Cases

Use this plugin when users want to manage Anthropic Claude series models (including those accessed via self-hosted or third-party Anthropic-compatible gateways) as a "dedicated provider" in DSH, and select thinking intensity per model. It replaces manual editing of settings.yaml and fills in the gaps where DSH's built-in UI doesn't yet provide Anthropic native model detection and capacity defaults for known models.

Prerequisites and Compatibility

DependencyMinimum VersionNotes
Node.js>=22.19Declared in engines.node
DSH0.1.0-rc.8+Depends on @deepseek-ai/[email protected]; frontend patch based on [email protected], dsh version lower bound not explicitly specified in manifest
PlatformCross-platformInjects web client via cordis, no platform restrictions
Native ModulesNoneNo node-pty, node:sqlite, or other native modules introduced

Installation

dsh plugin --profile web add github:MoFeng2223/dsh-claude-provider

Configuration

No additional configuration required. Recorded Claude models and their default capacities are hardcoded in the source code (CLAUDE_KNOWN_MODELS, including Fable 5, Opus 5/4.8/4.7/4.6, Sonnet 5/4.6, Haiku 4.5, etc.), and are automatically applied when creating new providers and models.

FAQ

Q: Do I need to manually edit settings.yaml after installation?

A: No. When saving the Claude provider in the frontend, the plugin calls DSH's native configuration write interface to persist fields like reasoning, reasoningEfforts, and compat.forceAdaptiveThinking to settings.yaml.

Q: Will it affect DSH's built-in Anthropic provider or regular custom providers?

A: No. The plugin does routing in the llm.discoverModels wrapper: only when a Provider ID is explicitly registered as claude-adaptive type under the dsh-claude-provider namespace does it use native Anthropic detection; the built-in anthropic route continues to use the upstream directory, and other anthropic-messages custom routes are not rewritten.

Q: Can I use self-hosted or third-party Anthropic-compatible gateways?

A: Yes. Model detection derives the /v1/models endpoint from the Messages API baseURL you provide, supporting any HTTP(S) address; API key is passed directly in the request or resolved from credential reference. Responses over 4 MiB are automatically aborted, with a maximum of 100 pages.

Q: Which thinking effort levels are available for each model?

A: Three preset options are provided: five levels (low/medium/high/xhigh/max), four levels (low/medium/high/max), and toggle (off/high). New models default to five levels, and Claude providers default to reasoning: high.

Q: Will uninstalling the plugin cause data loss?

A: No. Uninstalling does not delete ~/.dsh/settings.yaml or saved credentials. Existing Claude providers are downgraded to regular anthropic-messages routes, and native fields continue to work; only the dedicated Claude UI, model detection, and capacity pre-filling are lost.

Q: Can it work in CLI mode (without Web interface)?

A: The plugin supports --profile headless as well, but model detection and the dedicated UI depend on the Web client; frontend capabilities won't take effect in headless mode.

Q: What if I don't see the "Add Claude Provider" button after installation?

A: The cordis patch simultaneously sets the built-in ui-settings-models to disabled: true, replaced by this plugin's bundled lib/client.js. If the button is missing, please confirm the frontend client has been replaced and restart the DSH process.

Difficulty

Beginner — Installation immediately shows a new entry on the settings page. Usage only requires filling in baseURL, API key, and selecting a model; no need to understand schema details.

Known Issues and Limitations

  • Model detection has a 4 MiB size limit on single responses and a 100-page hard limit on pagination (src/index.js:18-19); exceeding these will throw an error
  • Only takes effect for Provider IDs explicitly registered as claude-adaptive; users checking anthropic-messages protocol in regular custom providers won't get effort presets or capacity pre-filling
  • Built-in anthropic provider doesn't go through this plugin's detection, still uses the upstream directory (src/index.js:217)
  • Frontend capabilities are only enabled in the Web client; headless installation only retains backend schema registration and intercept points

Read the usage guide →

Install steps, key points, FAQ and compatibility for this plugin — auto-derived from indexed fields.

Listing badge

Listed on deepseek-plugin.org
[![Listed on deepseek-plugin.org](https://img.shields.io/badge/listed_on-deepseek--plugin.org-007EC6)](https://deepseek-plugin.org/plugins/MoFeng2223/dsh-claude-provider)

Paste this markdown into your GitHub README to link back to this listing. The badge only states the listing — not a security endorsement.

← Back to plugin directory