dsh-trilogy
Per-project memory for DeepSeek Harness: auto-creates memory/PROJECT.md, DECISIONS.md and SESSIONS.md per project, loads them into every session, and records durable outcomes by classification.
40 results
Per-project memory for DeepSeek Harness: auto-creates memory/PROJECT.md, DECISIONS.md and SESSIONS.md per project, loads them into every session, and records durable outcomes by classification.
Content-addressed proof that recorded DSH authorization decisions and effects agree
Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.
Deterministic regression tests for DSH policy decisions, evaluated without invoking the protected tool body.
文档与架构决策记录:记录为什么而非只是什么,ADR 格式与文档策略。受 addyosmani/agent-skills(88k★ MIT)启发。
Track human decisions for related DeepSeek Harness conversation branches.
DeepSeek Harness 插件 / DeepSeek Harness plugin: Wayfinder decision-map dashboard. Every question stays visible; dependencies gate execution only.
开眼看世界:DSH 决策层插件——让 agent 在「该上网搜索」的时候先搜再答(fresh-info-first / 联网优先)。判定『何时搜索』(决策层),不自带搜索引擎(能力层)。
Multi-agent orchestration for DeepSeek Harness: delegate, adversarial review, diverse explore, background runs + converge. One prompt. A team of agents.
Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client
DeepSeek Harness shopping decision plugin for candidate ranking, realizable price, merchant/review evidence and source-quality risk.
Offline content-addressed proof that a canary decision follows explicit evidence policy
Multi-channel decision & remote-control bridge for DeepSeek Harness: pushes any workspace's approval/question cards to IM channels (WeChat iLink first) and answers them from chat, with a session console, per-channel security, and an open push service.
Research lab for DeepSeek Harness: AutoSci-style wiki (experiments/literature/decisions), ASI-Bench-grade eval rigor ledger, arXiv digest, adversarial paper review, and academic writing checks.
Session health for DeepSeek Harness: real token-meter data, configurable continue-vs-new decision model. Reactive header badge (compaction-aware), /compass command, context_compass tool.
Independent second-model reviews for DeepSeek Harness assistant decisions