瀏覽代碼

docs(repeat-guard): trim module orientation

Tianyi Cui 2 月之前
父節點
當前提交
042d752fd2
共有 1 個文件被更改,包括 4 次插入 和 33 次删除
  1. 4 33
      packages/guard/repeat-tool-guard/src/index.ts

+ 4 - 33
packages/guard/repeat-tool-guard/src/index.ts

@@ -1,37 +1,8 @@
 /**
 /**
- * Repeat-tool-call guard: advisory loop-breaker for agents stuck re-issuing
- * the same tool call with identical arguments.
- *
- * Not a model-facing tool — it registers no tool, never vetoes or rewrites a
- * call, and adds exactly one behavior: watch each agent's stream of tool calls
- * through the `tools/post-execute` waterfall, count runs of consecutive calls
- * to the same tool with identical canonicalized arguments, and at configured
- * run lengths fold an escalating advisory reminder onto the decision's
- * `additionalContext`. The loop appends that context as a logged
- * `context/message` after the step's tool results, so the reminder is
- * model-visible, source-attributed, and reconstructable from the session log
- * with no new session event. Decision record:
- * docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md.
- *
- * ```yaml
- * - id: repeat-tool-guard
- *   name: '@deepseek-ai/dsh-repeat-tool-guard'
- *   config:
- *     thresholds: [3, 5, 8]   # consecutive counts that trigger a reminder
- *     include: []             # tool-name patterns to track; empty = all tools
- *     exclude: [todo_write]   # tool-name patterns transparent to the chain
- * ```
- *
- * Chain state is keyed by the live agent object — the tool registry is a
- * context-level singleton whose waterfalls interleave every agent's calls, so
- * a shared counter would let one agent's repetition trip another's reminder.
- * State is in-memory only: a session resumed from persistence starts with a
- * fresh chain (the guard is a heuristic nudge, not a logged invariant).
- *
- * Plugin export shape: named exports, NO default. The cordis Loader's
- * `unwrapExports` does `exports.default ?? exports`, so a stray default would
- * collapse the module to the bare `apply` (see docs/postmortem/0001).
- *
+ * Advisory per-agent repeat-call detector. It enriches post-execute decisions
+ * with logged model context without vetoing or rewriting calls. Configuration
+ * and chain semantics live in the package README; rationale lives in the
+ * repeat-tool-guard RFC.
  * @module @deepseek-ai/dsh-repeat-tool-guard
  * @module @deepseek-ai/dsh-repeat-tool-guard
  */
  */