EveGoodEvening/dsh-autoresearch

README 摘要

dsh-autoresearch Bounded, metric-driven autoresearch plugin for DeepSeek Harness. dsh-autoresearch gives a DeepSeek Harness agent a single tool — autoresearch — that runs a baseline-first, keep/reject optimization loop inside an isolated Git worktree. The design is inspired by Karpathy's autoresearch : an autonomous propose → edit → run → measure → keep/revert loop where a coding agent performs the search and a fixed mechanical metric acts as the source of truth. What makes that loop trustworthy is discipline — the agent proposes candidate changes; trusted host code owns evaluation, metric decisions, persistence, cancellation, and recovery. The model never touches the evaluator, the metric, or the database. - One scalar metric. Strict minimize / maximize improvement against a measured baseline; no vibes. - Shell-free evaluator. Immutable { command, args, cwd? } argv, final-line JSON scalar parsing, frozen provenance hashes. - Narrow mutable surface. Only mutable globs paths may change; everything else is protected. - Durable SQLite evidence. Every run, experiment, attempt, and artifact is recorded with transition-checked state and SHA-256 provenance. - Background jobs by default. R…

分类