dsh-codearts
Connect Huawei Cloud CodeArts models to DeepSeek Harness with OAuth2 auth and multi-account rotation.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- One-click browser OAuth2 login (PKCE + DPoP) with automatic background token renewal
- Multi-account pool rotation to bypass upstream concurrent session slot constraints
- Dynamic upstream model discovery with selective model filtering in UI settings
- Local usage ledger tracking tokens, requests, and slot status by account and model
- Support for multimodal image inputs on vision-compatible models
- Secure local loopback shim handling HMAC-SHA256 signing and STS token injection
- CLI utility providing status, models, usage, identity, doctor, and logout commands
Useful For
- Using models provided by Huawei Cloud CodeArts (such as DeepSeek, GLM, Qwen, and Pangu) directly inside DeepSeek Harness chat sessions
- Managing multiple CodeArts accounts to distribute concurrent request load seamlessly without waiting for upstream session lock timeouts
- Diagnosing and monitoring local token consumption and active model availability on headless environments via CLI
Who It Fits
- DeepSeek Harness users with Huawei Cloud CodeArts accounts or quotas
- Developers seeking diverse model provider endpoints integrated into DSH
- Teams looking to rotate multiple CodeArts developer accounts for AI chat sessions
Documented Limitations
- Subject to upstream CodeArts concurrency limits (3 concurrent sessions per account, occupied for ~1 minute each)
- Usage ledger only tracks requests originating locally through the plugin, not the remote official account balance
- Credentials expire after approximately 2 hours and require re-authentication if automated refresh fails
- Effective max_tokens ceiling depends on upstream gateway constraints
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 26 development, 11 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- elegant01/dsh-codearts
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 3dee999 · 2026-10-23
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 4GitHub stars
- Forks
- 0
- Open issues
- 2
- Last commit
- 2026-10-22
- Last release
- 2026-10-22
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Command Code LLM provider bundle for DeepSeek Harness with model catalog, quota tracking, and multi-account rotation.
View plugin →Free frontier LLM provider plugin for DeepSeek Harness with upstream probing and local OpenAI-compatible gateway.
View plugin →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →Connects local WorkBuddy and WorkBuddy AI desktop models to DeepSeek Harness with zero configuration.
View plugin →