UNPKG

@blundergoat/goat-flow

Version:

AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot - setup audits, guardrails, structured skills, deny hooks, and persistent learning loops.

23 lines 1.27 kB
/** * Builds the compact, ranked list of learning-loop entries (footguns, lessons, * patterns, decisions) used for bounded prompt retrieval - each bucket file is * split into sections, summarized into a small fact with a byte-capped excerpt, * and tagged with reference-validation results. * * The final ordering is deterministic by design (kind, then newest-first by * updated/created date, then path, then discovery order) so prompt context is * stable across runs and machines. The per-kind order offsets (0, 10k, 20k, 30k) * are tiebreak seeds that keep entries from different buckets from interleaving * unpredictably; they are not limits on entry count. */ import type { LearningLoopEntryFact, ReadonlyFS } from "../../types.js"; import type { LoadedConfig } from "../../config/types.js"; /** * Extract compact learning-loop entries for bounded prompt retrieval. * * @param fs - filesystem adapter for the target project * @param configState - loaded config with footgun, lesson, and decision paths * @returns ordered compact entries suitable for prompt context selection */ export declare function extractLearningLoopEntries(fs: ReadonlyFS, configState: LoadedConfig): LearningLoopEntryFact[]; //# sourceMappingURL=learning-loop-entries.d.ts.map