dsh-retry-plugin
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
10 results
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
DSH web plugin: manage how other plugins' sections appear in the global Settings dialog — show/hide, reorder, rename — without touching upstream. Every settings.section registration passes through the manager policy (registration-time + read-path interception).
Offline content-addressed proof that a canary decision follows explicit evidence policy
Experimental Dream-RSI exploration-policy plugin for DeepSeek Harness
dsh plugin: bounded retry for transient gateway network failures the stock retry policy cannot classify (finish_reason: network_error, unexpected EOF, TLS alerts, stream read errors)
Exact-model sampling policy bundle for DeepSeek Harness