dsh-llm-fallbacks
Role-based LLM retry and fallback strategy plugin 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 provider and model fallback chains for root and subagents
- Time-slot based chain rotation by wall-clock windows (peak/valley presets)
- Dispatch-time role resolution and role persona injection for subagents
- Context-window-aware fallback skipping models that cannot fit large prompts
- Configurable cooldown, revert policies, and half-open circuit recovery
- Support for both Web settings card and dsh-tui terminal configuration surfaces
Useful For
- Preventing task interruption when upstream LLM providers hit rate limits or downtime
- Optimizing model routing across peak and off-peak hours using time-slot presets
- Assigning specialized subagents to dedicated model chains based on roles
Who It Fits
- DeepSeek Harness users and agent developers needing resilient LLM provider failover
Documented Limitations
- Requires Node >= 22
- The tail of the root chain must be an official model (deepseek-flash or deepseek-v4-pro)
- Session log repair utility requires running directly from the repository source
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, 25 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
- 2980e52 · 2026-10-12
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
- 22GitHub stars
- Forks
- 2
- Open issues
- 0
- Last commit
- 2026-09-29
- Last release
- 2026-09-29
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 model provider plugin for DeepSeek Harness with live model catalog, multi-account rotation, and web search integration.
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 →