circuit-breaker 13
Thinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects two per-call shapes (reasoning-only calls, restated-material calls) and re-fires instead of latching; plus two mid-stream breakers that en
dsh plugin add @mrweicodes/dsh-loop-guardTwo-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback
dsh plugin add dsh-model-failoverProvider-level web search+fetch pool for DeepSeek Harness: bypass the official LLM search channel (0 model tokens), failover/rotate across Exa/Tavily/Jina/Firecrawl/Serper/SerpApi/SearXNG/DDG/Brave with quota-aware circuit breaking, multi-key rotation, an
dsh plugin add dsh-search-failoverCircuit breaker for pure-thinking idle loops in DSH agent turns: triple fusing on timeout, reasoning volume, and degenerate repetition.
dsh plugin add @ethanwong-hk/dsh-thinking-guard确定性步数治理——agent/pre-step reject 步级熔断与 tools/pre-execute deny 支线熔断(shadow 先行,fail-open)
dsh plugin add dsh-step-governorDeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
dsh plugin add @raphelutumn/dsh-change-budgetProgress-gated exploration brake for DeepSeek Harness: counts agent-loop steps since the last task-node advance and denies tool calls when the model keeps exploring without moving the task list or goal; optionally reshapes full-file reads into an outline,
dsh plugin add dsh-exploration-guardLocal tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.
dsh plugin add dsh-plugin-vajraclawThinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects three per-call shapes (reasoning-only calls, restated-material calls, self-repeating low-entropy reasoning) and re-fires instead of latchi
dsh plugin add @argszero/cordis-plugin-thinking-loop-guardThinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects two per-call shapes (reasoning-only calls, restated-material calls) and re-fires instead of latching; plus two mid-stream breakers that en
dsh plugin add @logictan/dsh-loop-guardStream ceiling for dsh: an absolute bound on one model call, mounted on the llm/stream waterfall. The harness's streamIdleTimeoutMs is re-armed by every SSE keep-alive comment (comments never enter the payload stream), so it bounds keep-alive silence rath
dsh plugin add @argszero/cordis-plugin-stream-ceilingSame-args circuit breaker for DeepSeek Harness: blocks identical tool calls repeated in a sliding window via ctx.tools.guard (agent loop prevention)
dsh plugin add dsh-loop-breaker模型故障转移队列:P1 限额/限流/不可用时自动切到队列下一个模型继续,全部图形界面配置 | Model fallback queue for DeepSeek Harness: auto-switch to the next model when the current one hits quota or rate limits
dsh plugin add dsh-model-fallback-queue