dsh-models-radar
Model capability radar and benchmark dashboard for the DeepSeek Harness Web GUI.
Install
$ dsh plugin --profile web add github:hi-fangj/dsh-models-radarPlugin 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
- Adds a dedicated Model Radar section under Web GUI Settings via settings.section
- Displays a live DeepSWE capability capsule and popover beside the conversation composer model selector
- Provides multi-channel benchmark visualizations for DeepSWE code-repair and Pompeii visual reconstruction
- Charts 24-hour and 7-day IQ trends with capability band coloring and summary statistics
- Visualizes Cost vs IQ tradeoffs across composite cost, time cost, and token pricing
- Presents 7-day and 24-hour rolling community experience ratings
- Proxies upstream requests through the host with local snapshot caching and freshness windows
Useful For
- Comparing benchmark intelligence and cost efficiency across different model tiers before selecting a session model
- Tracking hourly and weekly model capability shifts and leaderboard rankings directly within DeepSeek Harness
- Inspecting task-level repair performance, majority votes, and language breakdowns
Who It Fits
- DeepSeek Harness Web GUI users selecting optimal models for development tasks
- Developers seeking model benchmarking and cost-performance analytics inside their workspace
Documented Limitations
- Requires DeepSeek Harness Web GUI and Node.js 22 or newer
- Dependent on upstream reachability of api.codexradar.com for live metric refreshes (falls back to local snapshots when offline)
- Composer capability readout is hidden for models absent from the benchmark leaderboard
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 1 runtime, 1 development, 9 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
- hi-fangj/dsh-models-radar
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 33dad59 · 2026-10-20
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
- 3GitHub stars
- Forks
- 2
- Open issues
- 0
- Last commit
- 2026-09-28
- Last release
- 2026-09-28
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Context insight and lifecycle management plugin for DeepSeek Harness with visual dashboards, trends, and agent network views.
View plugin →Generative UI plugin for DeepSeek Harness that renders interactive cards, charts, forms, and panels inline from dsh-ui code fences.
View plugin →Skill manager UI for DeepSeek Harness to discover, toggle, import, and update agent skills.
View plugin →Wallpaper Engine backgrounds and iOS-style liquid glass theme customization for the DeepSeek Harness web GUI.
View plugin →