dsh-llm-fallbacks
Role-based LLM retry, time-slot routing, and fallback chains for DeepSeek Harness agents.
Install
$ dsh plugin --profile web add dsh-llm-fallbacks # web profile (Settings → Fallbacks card)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
- Automatic model failover across provider chains on failure codes (AUTH, QUOTA, RATE_LIMIT, CONTEXT_WINDOW_EXCEEDED)
- Configurable recovery policies including cooldown expiry and half-open recovery modes
- Time-slot based routing presets (peak and valley hours) to rotate effective root chains
- Role-based subagent model routing and persona assignment via dispatch headers
- Support for both Web UI settings cards and dsh-tui command diagnostics (/fallbacks, /settings)
Useful For
- Preventing workflow interruptions during LLM API rate limits or service outages
- Handling context-window overflow by dynamically failing over to larger context models
- Routing requests to cost-effective models during peak/valley pricing windows
- Assigning specialized models and personas to subagents and teammates automatically
Who It Fits
- DeepSeek Harness developers and power users needing resilient LLM provider failover
- Teams managing multi-agent setups with specialized subagent model requirements
- Developers seeking automated rate-limit and quota mitigation
Documented Limitations
- Requires DeepSeek Harness runtime environment with Node.js >=22
- All-day root chain must terminate with an official DeepSeek model
- Subagent model selection is constrained by the host dsh subagent-model-selection allowlist
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, 33 development, 26 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.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- omdsh-dev/dsh-llm-fallbacks
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- cba0c87 · 2026-10-26
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
- 23GitHub stars
- Forks
- 2
- Open issues
- 0
- Last commit
- 2026-10-25
- Last release
- 2026-10-25
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 →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 →