dsh-model-probe
Audits and corrects llm-pi-ai model capability declarations in DeepSeek Harness by directly probing provider endpoints.
Install
$ dsh plugin --profile web add dsh-model-probePlugin 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
- Measures contextWindow, maxTokens limits, reasoningEfforts, and image input capabilities directly from endpoints
- Uses constraint elicitation to extract parameter boundaries with 0 output tokens generated
- Synthesizes test images in-process to verify multimodal vision support
- Provides a dedicated settings UI (模型配置实测) with scan diffs, per-provider toggles, and safe mutate-backed write operations
- Exposes agent tools (model_probe_status, model_probe_scan, model_probe_apply) for automated inspection and updates
- Supports openai-completions and anthropic-messages protocols
Useful For
- Preventing HTTP 400 errors caused by configuring maxTokens beyond a provider gateway's actual maximum limit
- Auditing newly added llm-pi-ai endpoints to ensure declared context windows and reasoning levels match reality
- Verifying whether a newly released model gateway supports vision inputs before routing multimodal tasks
Who It Fits
- DeepSeek Harness users configuring custom or third-party LLM gateways
- Developers needing accurate model metadata and token boundary verification
- AI operators debugging silent model configuration failures
Documented Limitations
- Supports openai-completions and anthropic-messages protocols only
- Endpoints returning unparseable error messages for illegal values fall back to unknown without writing
- Settings UI labels are currently provided in Chinese only
- CLI installation requires selecting the matching active DSH profile
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, 3 development, 3 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
- xiaomao49/dsh-model-probe
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- c5bc8d9 · 2026-09-14
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-14
- Last release
- 2026-09-14
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →Command Code LLM provider bundle for DeepSeek Harness with model catalog, quota tracking, and multi-account rotation.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Skill manager UI for DeepSeek Harness to discover, toggle, import, and update agent skills.
View plugin →