prime-radiant-inc/serf

tool-fluency

Use when designing, running, or diagnosing Serf tool-fluency experiments for a real built-in, plugin, or newly added tool. Covers probe manifests, model comparisons, semantic oracles, and interpreting fluency failures without ad-hoc transcript parsing.

原文语言：英语

doctoring-serf

Use when diagnosing a serf session, job, watch, or the session tree — investigating watch runaways (self-influence depth + runaway-fuse drops), dropped/coalesced deliveries, "how many times did X actually get called", stuck turns, or parent↔delegate↔observer…

原文语言：英语

fuzzing-an-api-surface

Use when a surface parses untrusted or model-generated input — a wire protocol, tool-call JSON, upstream SSE, an HTTP body — or after a parser/dispatch bug, to fuzz that surface and turn any deterministic failure into a permanent, flake-guarded regression…

原文语言：英语