dsh-llm-auto
DeepSeek Harness host plugin registering an auto model router with ordered fallback chains, transient retries, and compaction window alignment.
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
- Registers a virtual 'auto' model routing layer within DeepSeek Harness
- Ordered multi-provider fallback chains with transient error retry policies
- Compaction window calculation and alignment (compactWindow) to steer DSH auto-compaction
- Sanitization of reasoning blocks across route transitions to prevent thought-text leakage
- Appends model change notifications on silent route switches without modifying persistent session logs
- Includes a browser client slot rendering settings forms and a read-only fallback chain inspector
- Provides an HTTP diagnostic endpoint (/api/llm-auto/routes) for inspecting routing rings and attempts
Useful For
- Aggregating multiple LLM provider subscriptions into a single resilient model endpoint
- Preventing chat workflow disruptions caused by provider rate limits, 502 server errors, or outages
- Maintaining stable context compaction thresholds across variable upstream model windows
- Debugging and tracking multi-provider routing fallbacks through the DSH web interface
Who It Fits
- DeepSeek Harness users requiring multi-provider failover and high availability
- Developers configuring custom Cordis patches with automated model routing
- Power users managing multiple LLM API quotas and endpoints
Documented Limitations
- Does not dynamically route requests based on token pricing, prompt content, or modal routing
- Once output streaming begins (content deltas), failures cannot be retried or routed to fallback models
- Routing call histories are stored in volatile host memory and reset upon DSH restart
- Compaction window recalculations assume standard compaction-basic engine constants
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, 0 development, 7 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
- liuyun847/dsh-llm-auto
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 450f918 · 2026-10-25
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
- 2026-10-12
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Free frontier LLM provider plugin for DeepSeek Harness with upstream probing and local OpenAI-compatible gateway.
View plugin →Free and multi-engine web search provider for DeepSeek Harness with automatic fallback and web settings UI.
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 →