model-catalog
A DeepSeek Harness plugin that discovers and normalizes model catalogs from OpenAI-compatible and local API hosts.
Install
$ dsh plugin --profile demo add github:JohnXu22786/model-catalogPlugin 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
- Detects OpenAI-compatible, augmented-metadata, quota, capability-flag, Ollama, and vLLM hosts.
- Fetches and normalizes model IDs, context windows, output limits, pricing, capabilities, and provenance.
- Converts supported pricing representations to USD per million tokens and represents per-call pricing separately.
- Uses a documented pricing and metadata fallback chain: host, overrides, external mirror, built-in table, then unknown.
- Optionally probes tool calling, structured output, and streaming when metadata is incomplete.
- Provides five DSH tools: catalog.discover, catalog.list, catalog.refresh, catalog.select, and catalog.probe.
- Generates a full catalog JSON file, a DSH model configuration fragment, and a Markdown report.
- Caches detection, probing, and mirror results with TTLs and uses file locking and atomic writes.
Useful For
- Generate DSH-ready model configuration from a DeepSeek, OpenAI-compatible, gateway, Ollama, or vLLM endpoint.
- Compare discovered models, prices, and available capabilities before selecting a model.
- Fill incomplete host metadata with configured overrides, a price mirror, or built-in DeepSeek fallback data.
- Interactively select models and create a DSH configuration fragment.
Who It Fits
- DeepSeek Harness users configuring model providers.
- Developers operating OpenAI-compatible gateways or local inference endpoints.
- Teams that need normalized model metadata and pricing for DSH configuration.
Documented Limitations
- Vision and parallel-tool capabilities are metadata-only and are unknown when metadata does not provide them.
- Capability probes can consume tokens; in auto mode, keyless standard hosts are not probed.
- Pricing may remain unknown when no host data, override, external mirror, or built-in fallback applies.
- A multiplier gateway group-ratio map without a default group is treated as 1 unless corrected through overrides.
- Requires Node.js 21 or later.
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, 2 development, 0 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
- JohnXu22786/model-catalog
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- f9ec6c7 · 2026-09-19
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-16
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.
View plugin →DeepSeek Harness-native vision toolkit for image Q&A, OCR, grounding, UI restoration, pixel comparison, and visual artifacts.
View plugin →