/**
 * Shared claim-extraction contract for knowledge ingestion. Both summarizer paths
 * use this so they produce identical, reviewable output:
 *   - the LLM fallback (`dim knowledge sync`) feeds these instructions to a model;
 *   - the MCP `knowledge_ingest` prompt feeds them to the connected agent.
 *
 * The extractor turns a project document into typed, scoped, FALSIFIABLE claims —
 * never a single blob. Claims become proposals (source `knowledge:<doc>`) and, once
 * approved with `dim review`, PINNED memories.
 */
import type { GuardrailLevel, MemoryKind } from "../types.js";
export interface ExtractedClaim {
    kind: MemoryKind;
    claim: string;
    paths?: string[];
    symbols?: string[];
    /** only for kind === "GUARDRAIL" */
    guardrailLevel?: GuardrailLevel;
    /** only for kind === "FAILED_APPROACH": conditions under which the failure applies */
    appliesWhen?: string[];
    /** short note on why this is durable / where in the doc it came from */
    rationale?: string;
    /** optional STATIC_CHECK shell command that passes iff the claim holds */
    staticCheck?: string;
}
export declare const KNOWLEDGE_EXTRACT_INSTRUCTIONS = "You are extracting durable, project-specific knowledge from a document a developer dropped into the knowledge inbox (a design doc, ADR, style guide, runbook, or notes).\n\nTurn it into a small set of FALSIFIABLE claims. Rules:\n\n1. BE SPECIFIC. Every claim must name concrete files, modules, functions, config keys, or commands. Bad: \"The project uses a specific tool for code completion\" (useless). Good: \"The UI is a single-page app generated from src/ui/page.ts which inlines all CSS and JS into one HTML file served by the Express server in src/ui/server.ts\". Bad: \"The project uses a specific file format for README files\" (which format? why?).\n2. REJECT generic statements. If a claim could apply to any repo, discard it. \"Uses TypeScript\" is useless. \"All API handlers in src/api/ must extend BaseHandler and register via src/api/registry.ts\" is useful.\n3. Only DURABLE, NON-OBVIOUS facts about THIS project \u2014 rules, decisions, architecture, invariants, guardrails, procedures. Skip generic advice, tutorials, and anything a quick file read already shows.\n4. Write each claim as a checkable statement. Bad: \"auth is complex\". Good: \"JWT refresh in src/auth/refresh.ts must run before the middleware chain; reordering breaks session renewal\".\n5. Pick the right kind:\n   - DECISION: a choice + the rejected alternative\n   - CONVENTION: a rule the repo follows\n   - GOTCHA: surprising behavior that costs time\n   - FAILED_APPROACH: something tried that did NOT work\n   - ARCHITECTURE: how components fit together\n   - INVARIANT: something that must always/never hold\n   - GUARDRAIL: a behavioral rule for future agents \u2014 set guardrail_level to \"never\" (refuse), \"ask-first\" (confirm), or \"always\" (do automatically)\n   - SKILL: a reusable step-by-step procedure (write the steps as \"1) ... 2) ...\")\n   - TODO_CONTEXT: unfinished work + the context to resume it\n6. Scope each claim with paths/symbols it applies to when the document names them; otherwise leave them empty (repo-wide).\n7. Extract 0\u201312 claims. Zero is fine. Do NOT pad, and do NOT invent rules the document doesn't support.\n\nRespond with ONLY a JSON object of this exact shape:\n{\"claims\":[{\"kind\":\"CONVENTION\",\"claim\":\"All API handlers in src/api/ must extend BaseHandler and register via src/api/registry.ts\",\"paths\":[\"src/api/registry.ts\"],\"symbols\":[\"BaseHandler\"],\"guardrail_level\":null,\"applies_when\":[],\"rationale\":\"from ADR-003: API handler registration pattern\"}]}";
/** Build the user message for the LLM: instructions + the document. */
export declare function buildExtractionUser(filename: string, content: string): string;
/**
 * Tolerantly parse a model/agent response into validated claims. Accepts a bare
 * array or an object with a `claims` array, and ignores anything malformed rather
 * than throwing — a bad doc should never crash ingestion.
 */
export declare function parseClaims(raw: string): ExtractedClaim[];
/** Collapse claims repeated across chunks (normalized text match). */
export declare function dedupeClaims(claims: ExtractedClaim[]): ExtractedClaim[];