kirograph 0.28.0 → 1.0.0

package/dist/core/pipeline.d.ts

@@ -1,40 +0,0 @@
-/**
- * IndexPipeline — full-index and incremental-sync pipelines.
- *
- * Owns the two heavy workflows:
- *   - indexAll(): scan all files, extract, store, resolve, detect frameworks,
- *                 generate embeddings, analyze architecture.
- *   - sync():     detect changed files via git (or full scan fallback),
- *                 re-extract only what changed, then run the same tail pipeline.
- *
- * Everything that touches the filesystem or sub-systems is injected via the
- * constructor, keeping this class testable and free of global state.
- */
-import { GraphDatabase } from '../db/database';
-import { ReferenceResolver } from '../resolution/index';
-import { VectorManager } from '../vectors/index';
-import { ArchitectureAnalyzer } from '../architecture/index';
-import type { KiroGraphConfig } from '../config';
-import type { IndexResult, IndexProgress, SyncResult } from '../types';
-import { LockManager } from './lock-manager';
-export declare class IndexPipeline {
-    private readonly db;
-    private readonly vectors;
-    private readonly resolver;
-    private readonly arch;
-    private readonly lock;
-    private readonly config;
-    private readonly projectRoot;
-    private readonly mutex;
-    constructor(db: GraphDatabase, vectors: VectorManager, resolver: ReferenceResolver, arch: ArchitectureAnalyzer, lock: LockManager, config: KiroGraphConfig, projectRoot: string);
-    indexAll(opts?: {
-        onProgress?: (p: IndexProgress) => void;
-        force?: boolean;
-        signal?: AbortSignal;
-    }): Promise<IndexResult>;
-    sync(opts?: {
-        changedFiles?: string[];
-        onProgress?: (p: IndexProgress) => void;
-    }): Promise<SyncResult>;
-}
-//# sourceMappingURL=pipeline.d.ts.map

package/dist/core/pipeline.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../../src/core/pipeline.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAIH,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAK/C,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AACxD,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AACjD,OAAO,EAAE,oBAAoB,EAAE,MAAM,uBAAuB,CAAC;AAC7D,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AACjD,OAAO,KAAK,EAAE,WAAW,EAAE,aAAa,EAAE,UAAU,EAAE,MAAM,UAAU,CAAC;AACvE,OAAO,EAAE,WAAW,EAAE,MAAM,gBAAgB,CAAC;AAK7C,qBAAa,aAAa;IAItB,OAAO,CAAC,QAAQ,CAAC,EAAE;IACnB,OAAO,CAAC,QAAQ,CAAC,OAAO;IACxB,OAAO,CAAC,QAAQ,CAAC,QAAQ;IACzB,OAAO,CAAC,QAAQ,CAAC,IAAI;IACrB,OAAO,CAAC,QAAQ,CAAC,IAAI;IACrB,OAAO,CAAC,QAAQ,CAAC,MAAM;IACvB,OAAO,CAAC,QAAQ,CAAC,WAAW;IAT9B,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAe;gBAGlB,EAAE,EAAE,aAAa,EACjB,OAAO,EAAE,aAAa,EACtB,QAAQ,EAAE,iBAAiB,EAC3B,IAAI,EAAE,oBAAoB,EAC1B,IAAI,EAAE,WAAW,EACjB,MAAM,EAAE,eAAe,EACvB,WAAW,EAAE,MAAM;IAGhC,QAAQ,CAAC,IAAI,CAAC,EAAE;QACpB,UAAU,CAAC,EAAE,CAAC,CAAC,EAAE,aAAa,KAAK,IAAI,CAAC;QACxC,KAAK,CAAC,EAAE,OAAO,CAAC;QAChB,MAAM,CAAC,EAAE,WAAW,CAAC;KACtB,GAAG,OAAO,CAAC,WAAW,CAAC;IAqQlB,IAAI,CAAC,IAAI,CAAC,EAAE;QAChB,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;QACxB,UAAU,CAAC,EAAE,CAAC,CAAC,EAAE,aAAa,KAAK,IAAI,CAAC;KACzC,GAAG,OAAO,CAAC,UAAU,CAAC;CA+QxB"}

package/dist/core/snapshot.d.ts

@@ -1,58 +0,0 @@
-/**
- * KiroGraph Snapshot Manager
- *
- * Saves lightweight graph snapshots (node IDs + edge tuples) to
- * .kirograph/snapshots/ and computes structural diffs between them.
- */
-import type { GraphDatabase } from '../db/database';
-export interface SnapshotNode {
-    id: string;
-    name: string;
-    kind: string;
-    filePath: string;
-}
-export interface SnapshotEdge {
-    source: string;
-    target: string;
-    kind: string;
-}
-export interface GraphSnapshot {
-    label: string;
-    timestamp: number;
-    nodeCount: number;
-    edgeCount: number;
-    nodes: SnapshotNode[];
-    edges: SnapshotEdge[];
-}
-export interface GraphDiff {
-    from: {
-        label: string;
-        timestamp: number;
-    };
-    to: {
-        label: string;
-        timestamp: number;
-    };
-    addedNodes: SnapshotNode[];
-    removedNodes: SnapshotNode[];
-    addedEdges: SnapshotEdge[];
-    removedEdges: SnapshotEdge[];
-}
-export declare class SnapshotManager {
-    private readonly db;
-    private readonly snapshotsDir;
-    constructor(db: GraphDatabase, projectRoot: string);
-    private ensureDir;
-    save(label?: string): GraphSnapshot;
-    list(): Array<{
-        label: string;
-        timestamp: number;
-        nodeCount: number;
-        edgeCount: number;
-    }>;
-    load(label: string): GraphSnapshot | null;
-    loadLatest(): GraphSnapshot | null;
-    currentSnapshot(): GraphSnapshot;
-    diff(from: GraphSnapshot, to: GraphSnapshot): GraphDiff;
-}
-//# sourceMappingURL=snapshot.d.ts.map

package/dist/core/snapshot.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"snapshot.d.ts","sourceRoot":"","sources":["../../src/core/snapshot.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAIH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAEpD,MAAM,WAAW,YAAY;IAC3B,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;CACd;AAED,MAAM,WAAW,aAAa;IAC5B,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,YAAY,EAAE,CAAC;IACtB,KAAK,EAAE,YAAY,EAAE,CAAC;CACvB;AAED,MAAM,WAAW,SAAS;IACxB,IAAI,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;IAC3C,EAAE,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;IACzC,UAAU,EAAE,YAAY,EAAE,CAAC;IAC3B,YAAY,EAAE,YAAY,EAAE,CAAC;IAC7B,UAAU,EAAE,YAAY,EAAE,CAAC;IAC3B,YAAY,EAAE,YAAY,EAAE,CAAC;CAC9B;AAID,qBAAa,eAAe;IAGd,OAAO,CAAC,QAAQ,CAAC,EAAE;IAF/B,OAAO,CAAC,QAAQ,CAAC,YAAY,CAAS;gBAET,EAAE,EAAE,aAAa,EAAE,WAAW,EAAE,MAAM;IAInE,OAAO,CAAC,SAAS;IAIjB,IAAI,CAAC,KAAK,CAAC,EAAE,MAAM,GAAG,aAAa;IA+BnC,IAAI,IAAI,KAAK,CAAC;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;IAazF,IAAI,CAAC,KAAK,EAAE,MAAM,GAAG,aAAa,GAAG,IAAI;IAazC,UAAU,IAAI,aAAa,GAAG,IAAI;IAKlC,eAAe,IAAI,aAAa;IAUhC,IAAI,CAAC,IAAI,EAAE,aAAa,EAAE,EAAE,EAAE,aAAa,GAAG,SAAS;CAuBxD"}

package/dist/data/filters.d.ts

@@ -1,23 +0,0 @@
-/**
- * Structured Filter → SQL WHERE Clause Builder
- *
- * Converts QueryFilter objects into parameterized SQL.
- * Zero injection surface — column names are validated against schema,
- * values are always parameterized.
- */
-import type { QueryFilter } from './types';
-interface SQLClause {
-    where: string;
-    params: any[];
-}
-/**
- * Build a parameterized WHERE clause from structured filters.
- * All filters are ANDed together.
- *
- * @param filters - Array of QueryFilter objects
- * @param validColumns - Set of valid column names (from schema)
- * @returns SQL WHERE clause and parameter array
- */
-export declare function buildWhereClause(filters: QueryFilter[], validColumns: Set<string>): SQLClause;
-export {};
-//# sourceMappingURL=filters.d.ts.map

package/dist/data/filters.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"filters.d.ts","sourceRoot":"","sources":["../../src/data/filters.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,SAAS,CAAC;AAE3C,UAAU,SAAS;IACjB,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,GAAG,EAAE,CAAC;CACf;AAcD;;;;;;;GAOG;AACH,wBAAgB,gBAAgB,CAAC,OAAO,EAAE,WAAW,EAAE,EAAE,YAAY,EAAE,GAAG,CAAC,MAAM,CAAC,GAAG,SAAS,CAoF7F"}

package/dist/data/indexer.d.ts

@@ -1,25 +0,0 @@
-/**
- * Data Indexer
- *
- * Orchestrates: scan data files → parse → profile columns → persist rows to SQLite.
- * Supports incremental re-indexing via content hashes.
- */
-import type { KiroGraphConfig } from '../config';
-import type { DataIndexResult } from './types';
-export declare class DataIndexer {
-    private readonly db;
-    private readonly config;
-    private readonly projectRoot;
-    constructor(db: any, config: KiroGraphConfig, projectRoot: string);
-    indexAll(opts?: {
-        force?: boolean;
-        onProgress?: (msg: string) => void;
-    }): Promise<DataIndexResult>;
-    indexFile(relPath: string, force?: boolean): Promise<{
-        rows: number;
-        columns: number;
-    } | null>;
-    private scanDataFiles;
-    private removeDeletedDatasets;
-}
-//# sourceMappingURL=indexer.d.ts.map

package/dist/data/indexer.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"indexer.d.ts","sourceRoot":"","sources":["../../src/data/indexer.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAMH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AACjD,OAAO,KAAK,EAAuB,eAAe,EAAa,MAAM,SAAS,CAAC;AAkB/E,qBAAa,WAAW;IACtB,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAM;IACzB,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAkB;IACzC,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAS;gBAEzB,EAAE,EAAE,GAAG,EAAE,MAAM,EAAE,eAAe,EAAE,WAAW,EAAE,MAAM;IAM3D,QAAQ,CAAC,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,OAAO,CAAC;QAAC,UAAU,CAAC,EAAE,CAAC,GAAG,EAAE,MAAM,KAAK,IAAI,CAAA;KAAE,GAAG,OAAO,CAAC,eAAe,CAAC;IAyClG,SAAS,CAAC,OAAO,EAAE,MAAM,EAAE,KAAK,UAAQ,GAAG,OAAO,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,GAAG,IAAI,CAAC;IA8GlG,OAAO,CAAC,aAAa;IAkCrB,OAAO,CAAC,qBAAqB;CAc9B"}

package/dist/data/linker.d.ts

@@ -1,37 +0,0 @@
-/**
- * Data ↔ Code Linker
- *
- * Detects references to data files in source code and populates data_code_refs.
- * Patterns detected:
- *   - readFileSync('data/users.csv'), readFile('path/to/file.csv')
- *   - pd.read_csv('data/file.csv'), pd.read_excel(...)
- *   - open('data/file.csv'), csv.reader(open(...))
- *   - COPY FROM 'file.csv', \copy ... from 'file.csv'
- *   - require('./data/file.json'), import ... from './data/file.json'
- *   - fs.createReadStream('data/file.csv')
- *   - String literals matching known data file paths
- */
-/**
- * Scan source code content for references to data files.
- * Returns matched file paths with their reference type.
- */
-export declare function detectDataReferences(sourceContent: string, knownDataPaths: Set<string>): Array<{
-    filePath: string;
-    refType: 'reads' | 'writes';
-    confidence: number;
-}>;
-/**
- * Link data files to code symbols.
- * Scans all indexed source files for references to known data file paths.
- */
-export declare class DataCodeLinker {
-    private readonly db;
-    private readonly projectRoot;
-    constructor(db: any, projectRoot: string);
-    /**
-     * Populate data_code_refs by scanning source files for data file references.
-     * Returns the number of refs created.
-     */
-    linkAll(): number;
-}
-//# sourceMappingURL=linker.d.ts.map

package/dist/data/linker.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"linker.d.ts","sourceRoot":"","sources":["../../src/data/linker.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAqCH;;;GAGG;AACH,wBAAgB,oBAAoB,CAClC,aAAa,EAAE,MAAM,EACrB,cAAc,EAAE,GAAG,CAAC,MAAM,CAAC,GAC1B,KAAK,CAAC;IAAE,QAAQ,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,OAAO,GAAG,QAAQ,CAAC;IAAC,UAAU,EAAE,MAAM,CAAA;CAAE,CAAC,CAoC9E;AAiCD;;;GAGG;AACH,qBAAa,cAAc;IACzB,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAM;IACzB,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAS;gBAEzB,EAAE,EAAE,GAAG,EAAE,WAAW,EAAE,MAAM;IAKxC;;;OAGG;IACH,OAAO,IAAI,MAAM;CAuDlB"}

package/dist/data/linker.test.js

@@ -1,60 +0,0 @@
-"use strict";
-var import_vitest = require("vitest");
-var import_linker = require("./linker");
-const KNOWN_PATHS = /* @__PURE__ */ new Set([
-  "data/report.pdf",
-  "docs/manual.pdf",
-  "data/users.csv"
-]);
-(0, import_vitest.describe)("detectDataReferences \u2014 PDF patterns", () => {
-  (0, import_vitest.it)("detects readFileSync with .pdf path", () => {
-    const src = `const buf = readFileSync('data/report.pdf')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/report.pdf" && r.refType === "reads")).toBe(true);
-  });
-  (0, import_vitest.it)("detects createReadStream with .pdf path", () => {
-    const src = `fs.createReadStream('data/report.pdf')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/report.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("detects Python open() with .pdf extension", () => {
-    const src = `f = open('docs/manual.pdf', 'rb')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "docs/manual.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("detects PdfReader() call", () => {
-    const src = `reader = PdfReader('data/report.pdf')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/report.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("detects pdfplumber.open() call", () => {
-    const src = `with pdfplumber.open('data/report.pdf') as pdf:`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/report.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("detects fitz.open() call", () => {
-    const src = `doc = fitz.open('docs/manual.pdf')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "docs/manual.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("detects generic string literal with .pdf extension", () => {
-    const src = `const path = 'data/report.pdf';`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/report.pdf")).toBe(true);
-  });
-  (0, import_vitest.it)("gives confidence 1.0 for known paths, lower for unknown", () => {
-    const src = `readFileSync('data/report.pdf'); readFileSync('other/unknown.pdf')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    const known = refs.find((r) => r.filePath === "data/report.pdf");
-    const unknown = refs.find((r) => r.filePath === "other/unknown.pdf");
-    (0, import_vitest.expect)(known?.confidence).toBe(1);
-    (0, import_vitest.expect)(unknown?.confidence).toBeLessThan(1);
-  });
-  (0, import_vitest.it)("does not confuse .pdf with .csv patterns", () => {
-    const src = `readFileSync('data/users.csv')`;
-    const refs = (0, import_linker.detectDataReferences)(src, KNOWN_PATHS);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath === "data/users.csv")).toBe(true);
-    (0, import_vitest.expect)(refs.some((r) => r.filePath?.endsWith(".pdf"))).toBe(false);
-  });
-});
-//# sourceMappingURL=linker.test.js.map

package/dist/data/linker.test.js.map

@@ -1,7 +0,0 @@
-{
-  "version": 3,
-  "sources": ["../../src/data/linker.test.ts"],
-  "sourcesContent": ["import { describe, it, expect } from 'vitest';\nimport { detectDataReferences } from './linker';\n\nconst KNOWN_PATHS = new Set([\n  'data/report.pdf',\n  'docs/manual.pdf',\n  'data/users.csv',\n]);\n\ndescribe('detectDataReferences \u2014 PDF patterns', () => {\n  it('detects readFileSync with .pdf path', () => {\n    const src = `const buf = readFileSync('data/report.pdf')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/report.pdf' && r.refType === 'reads')).toBe(true);\n  });\n\n  it('detects createReadStream with .pdf path', () => {\n    const src = `fs.createReadStream('data/report.pdf')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/report.pdf')).toBe(true);\n  });\n\n  it('detects Python open() with .pdf extension', () => {\n    const src = `f = open('docs/manual.pdf', 'rb')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'docs/manual.pdf')).toBe(true);\n  });\n\n  it('detects PdfReader() call', () => {\n    const src = `reader = PdfReader('data/report.pdf')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/report.pdf')).toBe(true);\n  });\n\n  it('detects pdfplumber.open() call', () => {\n    const src = `with pdfplumber.open('data/report.pdf') as pdf:`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/report.pdf')).toBe(true);\n  });\n\n  it('detects fitz.open() call', () => {\n    const src = `doc = fitz.open('docs/manual.pdf')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'docs/manual.pdf')).toBe(true);\n  });\n\n  it('detects generic string literal with .pdf extension', () => {\n    const src = `const path = 'data/report.pdf';`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/report.pdf')).toBe(true);\n  });\n\n  it('gives confidence 1.0 for known paths, lower for unknown', () => {\n    const src = `readFileSync('data/report.pdf'); readFileSync('other/unknown.pdf')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    const known = refs.find(r => r.filePath === 'data/report.pdf');\n    const unknown = refs.find(r => r.filePath === 'other/unknown.pdf');\n    expect(known?.confidence).toBe(1.0);\n    expect(unknown?.confidence).toBeLessThan(1.0);\n  });\n\n  it('does not confuse .pdf with .csv patterns', () => {\n    const src = `readFileSync('data/users.csv')`;\n    const refs = detectDataReferences(src, KNOWN_PATHS);\n    expect(refs.some(r => r.filePath === 'data/users.csv')).toBe(true);\n    expect(refs.some(r => r.filePath?.endsWith('.pdf'))).toBe(false);\n  });\n});\n"],
-  "mappings": ";AAAA,oBAAqC;AACrC,oBAAqC;AAErC,MAAM,cAAc,oBAAI,IAAI;AAAA,EAC1B;AAAA,EACA;AAAA,EACA;AACF,CAAC;AAAA,IAED,wBAAS,4CAAuC,MAAM;AACpD,wBAAG,uCAAuC,MAAM;AAC9C,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,qBAAqB,EAAE,YAAY,OAAO,CAAC,EAAE,KAAK,IAAI;AAAA,EAC7F,CAAC;AAED,wBAAG,2CAA2C,MAAM;AAClD,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,6CAA6C,MAAM;AACpD,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,4BAA4B,MAAM;AACnC,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,kCAAkC,MAAM;AACzC,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,4BAA4B,MAAM;AACnC,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,sDAAsD,MAAM;AAC7D,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB,CAAC,EAAE,KAAK,IAAI;AAAA,EACpE,CAAC;AAED,wBAAG,2DAA2D,MAAM;AAClE,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,UAAM,QAAQ,KAAK,KAAK,OAAK,EAAE,aAAa,iBAAiB;AAC7D,UAAM,UAAU,KAAK,KAAK,OAAK,EAAE,aAAa,mBAAmB;AACjE,8BAAO,OAAO,UAAU,EAAE,KAAK,CAAG;AAClC,8BAAO,SAAS,UAAU,EAAE,aAAa,CAAG;AAAA,EAC9C,CAAC;AAED,wBAAG,4CAA4C,MAAM;AACnD,UAAM,MAAM;AACZ,UAAM,WAAO,oCAAqB,KAAK,WAAW;AAClD,8BAAO,KAAK,KAAK,OAAK,EAAE,aAAa,gBAAgB,CAAC,EAAE,KAAK,IAAI;AACjE,8BAAO,KAAK,KAAK,OAAK,EAAE,UAAU,SAAS,MAAM,CAAC,CAAC,EAAE,KAAK,KAAK;AAAA,EACjE,CAAC;AACH,CAAC;",
-  "names": []
-}

package/dist/data/lint.d.ts

@@ -1,27 +0,0 @@
-/**
- * Data Lint
- *
- * Integrity checks for the data index:
- * - Row count mismatch (stored vs actual table rows)
- * - Schema consistency (columns in profile vs actual table)
- * - Stale datasets (source file deleted or changed)
- * - Missing optional deps (files skipped due to missing xlsx/parquetjs-lite)
- * - Orphan code refs (refs pointing to deleted datasets)
- */
-export interface LintIssue {
-    severity: 'error' | 'warning' | 'info';
-    dataset?: string;
-    message: string;
-}
-export interface LintResult {
-    issues: LintIssue[];
-    datasetsChecked: number;
-    healthy: number;
-}
-export declare class DataLinter {
-    private readonly db;
-    private readonly projectRoot;
-    constructor(db: any, projectRoot: string);
-    lint(): LintResult;
-}
-//# sourceMappingURL=lint.d.ts.map

package/dist/data/lint.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"lint.d.ts","sourceRoot":"","sources":["../../src/data/lint.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAMH,MAAM,WAAW,SAAS;IACxB,QAAQ,EAAE,OAAO,GAAG,SAAS,GAAG,MAAM,CAAC;IACvC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,UAAU;IACzB,MAAM,EAAE,SAAS,EAAE,CAAC;IACpB,eAAe,EAAE,MAAM,CAAC;IACxB,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,qBAAa,UAAU;IACrB,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAM;IACzB,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAS;gBAEzB,EAAE,EAAE,GAAG,EAAE,WAAW,EAAE,MAAM;IAKxC,IAAI,IAAI,UAAU;CAgFnB"}

package/dist/data/parsers/__fixtures__/pdf-inspector-stub.js

@@ -1,41 +0,0 @@
-"use strict";
-var __defProp = Object.defineProperty;
-var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
-var __getOwnPropNames = Object.getOwnPropertyNames;
-var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __export = (target, all) => {
-  for (var name in all)
-    __defProp(target, name, { get: all[name], enumerable: true });
-};
-var __copyProps = (to, from, except, desc) => {
-  if (from && typeof from === "object" || typeof from === "function") {
-    for (let key of __getOwnPropNames(from))
-      if (!__hasOwnProp.call(to, key) && key !== except)
-        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
-  }
-  return to;
-};
-var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
-var pdf_inspector_stub_exports = {};
-__export(pdf_inspector_stub_exports, {
-  classifyPdf: () => classifyPdf,
-  extractPagesMarkdown: () => extractPagesMarkdown,
-  processPdf: () => processPdf
-});
-module.exports = __toCommonJS(pdf_inspector_stub_exports);
-function extractPagesMarkdown(_buf) {
-  throw new Error("@firecrawl/pdf-inspector is not installed");
-}
-function processPdf(_buf) {
-  throw new Error("@firecrawl/pdf-inspector is not installed");
-}
-function classifyPdf(_buf) {
-  throw new Error("@firecrawl/pdf-inspector is not installed");
-}
-// Annotate the CommonJS export names for ESM import in node:
-0 && (module.exports = {
-  classifyPdf,
-  extractPagesMarkdown,
-  processPdf
-});
-//# sourceMappingURL=pdf-inspector-stub.js.map

package/dist/data/parsers/__fixtures__/pdf-inspector-stub.js.map

@@ -1,7 +0,0 @@
-{
-  "version": 3,
-  "sources": ["../../../../src/data/parsers/__fixtures__/pdf-inspector-stub.ts"],
-  "sourcesContent": ["// Stub for @firecrawl/pdf-inspector used in tests.\n// Real package not installed \u2014 this stub allows require() to resolve.\n// vi.mock('@firecrawl/pdf-inspector', factory) overrides this in individual tests.\nexport function extractPagesMarkdown(_buf: Buffer): never {\n  throw new Error('@firecrawl/pdf-inspector is not installed');\n}\nexport function processPdf(_buf: Buffer): never {\n  throw new Error('@firecrawl/pdf-inspector is not installed');\n}\nexport function classifyPdf(_buf: Buffer): never {\n  throw new Error('@firecrawl/pdf-inspector is not installed');\n}\n"],
-  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAGO,SAAS,qBAAqB,MAAqB;AACxD,QAAM,IAAI,MAAM,2CAA2C;AAC7D;AACO,SAAS,WAAW,MAAqB;AAC9C,QAAM,IAAI,MAAM,2CAA2C;AAC7D;AACO,SAAS,YAAY,MAAqB;AAC/C,QAAM,IAAI,MAAM,2CAA2C;AAC7D;",
-  "names": []
-}

package/dist/data/parsers/csv.d.ts

@@ -1,11 +0,0 @@
-/**
- * CSV/TSV Streaming Parser
- *
- * Handles: .csv, .tsv
- * Parses line-by-line without loading the full file into memory.
- * Handles quoted fields, newlines within quotes, and various delimiters.
- */
-import type { DataFormatParser } from '../types';
-export declare const csvParser: DataFormatParser;
-export declare const tsvParser: DataFormatParser;
-//# sourceMappingURL=csv.d.ts.map

package/dist/data/parsers/csv.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"csv.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/csv.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAIH,OAAO,KAAK,EAAE,gBAAgB,EAAa,MAAM,UAAU,CAAC;AAwG5D,eAAO,MAAM,SAAS,EAAE,gBAKvB,CAAC;AAEF,eAAO,MAAM,SAAS,EAAE,gBAKvB,CAAC"}

package/dist/data/parsers/excel.d.ts

@@ -1,10 +0,0 @@
-/**
- * Excel Parser (Optional Dependency)
- *
- * Handles: .xlsx, .xls
- * Requires: xlsx package (optional dependency)
- * Gracefully returns isAvailable()=false if not installed.
- */
-import type { DataFormatParser } from '../types';
-export declare const excelParser: DataFormatParser;
-//# sourceMappingURL=excel.d.ts.map

package/dist/data/parsers/excel.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"excel.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/excel.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,KAAK,EAAE,gBAAgB,EAAa,MAAM,UAAU,CAAC;AAkB5D,eAAO,MAAM,WAAW,EAAE,gBA0DzB,CAAC"}

package/dist/data/parsers/index.d.ts

@@ -1,28 +0,0 @@
-/**
- * Data Format Registry
- *
- * Maps file extensions to their appropriate parser.
- * Gracefully skips formats whose optional dependencies are not installed.
- */
-import type { DataFormatParser } from '../types';
-/**
- * Get the parser for a given file extension.
- * Returns null if no parser is registered or the optional dep is missing.
- */
-export declare function getDataParser(filePath: string): DataFormatParser | null;
-/**
- * Check if a file extension is supported for data parsing.
- */
-export declare function isSupportedDataFormat(filePath: string): boolean;
-/**
- * Get all supported extensions (only those with available deps).
- */
-export declare function getAvailableExtensions(): string[];
-/**
- * Get extensions that are registered but have missing optional deps.
- */
-export declare function getUnavailableExtensions(): Array<{
-    ext: string;
-    parser: string;
-}>;
-//# sourceMappingURL=index.d.ts.map

package/dist/data/parsers/index.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/index.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,UAAU,CAAC;AA4BjD;;;GAGG;AACH,wBAAgB,aAAa,CAAC,QAAQ,EAAE,MAAM,GAAG,gBAAgB,GAAG,IAAI,CAMvE;AAED;;GAEG;AACH,wBAAgB,qBAAqB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAE/D;AAED;;GAEG;AACH,wBAAgB,sBAAsB,IAAI,MAAM,EAAE,CAMjD;AAED;;GAEG;AACH,wBAAgB,wBAAwB,IAAI,KAAK,CAAC;IAAE,GAAG,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC,CAQjF"}

package/dist/data/parsers/json-array.d.ts

@@ -1,9 +0,0 @@
-/**
- * JSON Array Parser
- *
- * Handles: .json files that contain an array of objects
- * For files in data/ directories (not package.json, tsconfig.json, etc.)
- */
-import type { DataFormatParser } from '../types';
-export declare const jsonArrayParser: DataFormatParser;
-//# sourceMappingURL=json-array.d.ts.map

package/dist/data/parsers/json-array.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"json-array.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/json-array.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAGH,OAAO,KAAK,EAAE,gBAAgB,EAAa,MAAM,UAAU,CAAC;AAI5D,eAAO,MAAM,eAAe,EAAE,gBA6D7B,CAAC"}

package/dist/data/parsers/jsonl.d.ts

@@ -1,9 +0,0 @@
-/**
- * JSONL/NDJSON Streaming Parser
- *
- * Handles: .jsonl, .ndjson
- * Parses one JSON object per line without loading the full file.
- */
-import type { DataFormatParser } from '../types';
-export declare const jsonlParser: DataFormatParser;
-//# sourceMappingURL=jsonl.d.ts.map

package/dist/data/parsers/jsonl.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"jsonl.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/jsonl.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAIH,OAAO,KAAK,EAAE,gBAAgB,EAAa,MAAM,UAAU,CAAC;AAI5D,eAAO,MAAM,WAAW,EAAE,gBAoDzB,CAAC"}

package/dist/data/parsers/parquet.d.ts

@@ -1,10 +0,0 @@
-/**
- * Parquet Parser (Optional Dependency)
- *
- * Handles: .parquet
- * Requires: parquetjs-lite package (optional dependency)
- * Gracefully returns isAvailable()=false if not installed.
- */
-import type { DataFormatParser } from '../types';
-export declare const parquetParser: DataFormatParser;
-//# sourceMappingURL=parquet.d.ts.map

package/dist/data/parsers/parquet.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"parquet.d.ts","sourceRoot":"","sources":["../../../src/data/parsers/parquet.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,KAAK,EAAE,gBAAgB,EAAa,MAAM,UAAU,CAAC;AAuB5D,eAAO,MAAM,aAAa,EAAE,gBAyD3B,CAAC"}

package/dist/data/parsers/pdf.test.js

@@ -1,125 +0,0 @@
-"use strict";
-var import_vitest = require("vitest");
-var import_pdf = require("./pdf");
-import_vitest.vi.mock("fs", async (importOriginal) => {
-  const actual = await importOriginal();
-  return { ...actual, readFileSync: import_vitest.vi.fn().mockReturnValue(Buffer.from("fake-pdf")) };
-});
-const mockExtractPages = import_vitest.vi.fn();
-const mockProcessPdf = import_vitest.vi.fn();
-function makeMockResult(pages, opts) {
-  return {
-    pages,
-    pagesWithTables: opts?.pagesWithTables ?? [],
-    pagesWithColumns: opts?.pagesWithColumns ?? []
-  };
-}
-(0, import_vitest.describe)("pdfParser", () => {
-  (0, import_vitest.beforeEach)(() => {
-    import_vitest.vi.clearAllMocks();
-    (0, import_pdf._setPdfInspectorForTesting)({ extractPagesMarkdown: mockExtractPages, processPdf: mockProcessPdf });
-  });
-  (0, import_vitest.afterEach)(() => {
-    (0, import_pdf._resetPdfInspectorForTesting)();
-  });
-  (0, import_vitest.it)("isAvailable returns true when module is injected", () => {
-    (0, import_vitest.expect)(import_pdf.pdfParser.isAvailable()).toBe(true);
-  });
-  (0, import_vitest.it)("isAvailable returns false when module is not available", () => {
-    (0, import_pdf._resetPdfInspectorForTesting)();
-    (0, import_vitest.expect)(import_pdf.pdfParser.isAvailable()).toBe(false);
-  });
-  (0, import_vitest.it)("parse returns empty result when library is unavailable", async () => {
-    (0, import_pdf._resetPdfInspectorForTesting)();
-    const batches = [];
-    const result = await import_pdf.pdfParser.parse("/fake/doc.pdf", {
-      maxRows: 1e3,
-      onBatch: (rows, cols) => batches.push({ rows, cols })
-    });
-    (0, import_vitest.expect)(result.columns).toEqual([]);
-    (0, import_vitest.expect)(result.totalRows).toBe(0);
-    (0, import_vitest.expect)(batches).toHaveLength(0);
-  });
-  (0, import_vitest.it)("happy path: text-based PDF produces correct rows and metadata", async () => {
-    mockExtractPages.mockReturnValue(makeMockResult([
-      { page: 0, markdown: "# Title\n\nSome content here.", needsOcr: false },
-      { page: 1, markdown: "Page two content.", needsOcr: false }
-    ], { pagesWithTables: [1], pagesWithColumns: [] }));
-    mockProcessPdf.mockReturnValue({
-      pdfType: "TextBased",
-      confidence: 0.97,
-      title: "Test Doc",
-      hasEncodingIssues: false,
-      isComplexLayout: false
-    });
-    const batches = [];
-    const result = await import_pdf.pdfParser.parse("/fake/report.pdf", {
-      maxRows: 1e3,
-      onBatch: (rows, cols) => batches.push({ rows, cols })
-    });
-    (0, import_vitest.expect)(result.columns).toEqual(["page", "content", "needs_ocr", "has_tables", "has_columns"]);
-    (0, import_vitest.expect)(result.totalRows).toBe(2);
-    (0, import_vitest.expect)(batches).toHaveLength(1);
-    (0, import_vitest.expect)(batches[0].rows[0]).toMatchObject({ page: "0", needs_ocr: "false", has_tables: "false" });
-    (0, import_vitest.expect)(batches[0].rows[1]).toMatchObject({ page: "1", needs_ocr: "false", has_tables: "true" });
-    (0, import_vitest.expect)(result.metadataJson).toBeTruthy();
-    const meta = JSON.parse(result.metadataJson);
-    (0, import_vitest.expect)(meta.pdfType).toBe("TextBased");
-    (0, import_vitest.expect)(meta.confidence).toBe(0.97);
-    (0, import_vitest.expect)(meta.hasEncodingIssues).toBe(false);
-  });
-  (0, import_vitest.it)("mixed PDF: text pages indexed normally, scanned pages flagged", async () => {
-    mockExtractPages.mockReturnValue(makeMockResult([
-      { page: 0, markdown: "Text content", needsOcr: false },
-      { page: 1, markdown: "", needsOcr: true },
-      { page: 2, markdown: "More text", needsOcr: false },
-      { page: 3, markdown: "", needsOcr: true }
-    ]));
-    mockProcessPdf.mockReturnValue({ pdfType: "Mixed", confidence: 0.85, hasEncodingIssues: false, isComplexLayout: false });
-    const batches = [];
-    await import_pdf.pdfParser.parse("/fake/mixed.pdf", {
-      maxRows: 1e3,
-      onBatch: (rows2) => batches.push({ rows: rows2 })
-    });
-    (0, import_vitest.expect)(batches).toHaveLength(1);
-    const rows = batches[0].rows;
-    (0, import_vitest.expect)(rows).toHaveLength(4);
-    (0, import_vitest.expect)(rows.filter((r) => r.needs_ocr === "true")).toHaveLength(2);
-    (0, import_vitest.expect)(rows.filter((r) => r.needs_ocr === "false")).toHaveLength(2);
-  });
-  (0, import_vitest.it)("hasEncodingIssues is captured in metadataJson", async () => {
-    mockExtractPages.mockReturnValue(makeMockResult([{ page: 0, markdown: "garbled", needsOcr: false }]));
-    mockProcessPdf.mockReturnValue({ pdfType: "TextBased", confidence: 0.4, hasEncodingIssues: true, isComplexLayout: false });
-    const result = await import_pdf.pdfParser.parse("/fake/garbled.pdf", { maxRows: 1e3, onBatch: () => {
-    } });
-    (0, import_vitest.expect)(result.metadataJson).toBeTruthy();
-    const meta = JSON.parse(result.metadataJson);
-    (0, import_vitest.expect)(meta.hasEncodingIssues).toBe(true);
-  });
-  (0, import_vitest.it)("empty PDF returns no rows and no batch", async () => {
-    mockExtractPages.mockReturnValue({ pages: [], pagesWithTables: [], pagesWithColumns: [] });
-    mockProcessPdf.mockReturnValue({ pdfType: "TextBased", confidence: 1, hasEncodingIssues: false, isComplexLayout: false });
-    const batches = [];
-    const result = await import_pdf.pdfParser.parse("/fake/empty.pdf", {
-      maxRows: 1e3,
-      onBatch: (rows, cols) => batches.push({ rows, cols })
-    });
-    (0, import_vitest.expect)(result.totalRows).toBe(0);
-    (0, import_vitest.expect)(batches).toHaveLength(0);
-  });
-  (0, import_vitest.it)("gracefully handles processPdf failure \u2014 still returns rows", async () => {
-    mockExtractPages.mockReturnValue(makeMockResult([{ page: 0, markdown: "content", needsOcr: false }]));
-    mockProcessPdf.mockImplementation(() => {
-      throw new Error("processPdf failed");
-    });
-    const batches = [];
-    const result = await import_pdf.pdfParser.parse("/fake/broken-meta.pdf", {
-      maxRows: 1e3,
-      onBatch: (rows, cols) => batches.push({ rows, cols })
-    });
-    (0, import_vitest.expect)(result.totalRows).toBe(1);
-    (0, import_vitest.expect)(batches).toHaveLength(1);
-    (0, import_vitest.expect)(result.metadataJson).toBeNull();
-  });
-});
-//# sourceMappingURL=pdf.test.js.map

package/dist/data/parsers/pdf.test.js.map

@@ -1,7 +0,0 @@
-{
-  "version": 3,
-  "sources": ["../../../src/data/parsers/pdf.test.ts"],
-  "sourcesContent": ["import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';\nimport { pdfParser, _setPdfInspectorForTesting, _resetPdfInspectorForTesting } from './pdf';\n\n// \u2500\u2500 Mock fs.readFileSync so tests never touch the filesystem \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n\nvi.mock('fs', async (importOriginal) => {\n  const actual = await importOriginal<typeof import('fs')>();\n  return { ...actual, readFileSync: vi.fn().mockReturnValue(Buffer.from('fake-pdf')) };\n});\n\n// \u2500\u2500 Helpers \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n\nconst mockExtractPages = vi.fn();\nconst mockProcessPdf = vi.fn();\n\nfunction makeMockResult(\n  pages: Array<{ page: number; markdown: string; needsOcr: boolean }>,\n  opts?: { pagesWithTables?: number[]; pagesWithColumns?: number[] },\n) {\n  return {\n    pages,\n    pagesWithTables: opts?.pagesWithTables ?? [],\n    pagesWithColumns: opts?.pagesWithColumns ?? [],\n  };\n}\n\n// \u2500\u2500 Tests \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n\ndescribe('pdfParser', () => {\n  beforeEach(() => {\n    vi.clearAllMocks();\n    _setPdfInspectorForTesting({ extractPagesMarkdown: mockExtractPages, processPdf: mockProcessPdf });\n  });\n\n  afterEach(() => {\n    _resetPdfInspectorForTesting();\n  });\n\n  it('isAvailable returns true when module is injected', () => {\n    expect(pdfParser.isAvailable()).toBe(true);\n  });\n\n  it('isAvailable returns false when module is not available', () => {\n    _resetPdfInspectorForTesting(); // clears pdfModule\n    // Simulate require() failure by resetting the module\n    expect(pdfParser.isAvailable()).toBe(false);\n  });\n\n  it('parse returns empty result when library is unavailable', async () => {\n    _resetPdfInspectorForTesting();\n    const batches: any[] = [];\n    const result = await pdfParser.parse('/fake/doc.pdf', {\n      maxRows: 1000,\n      onBatch: (rows, cols) => batches.push({ rows, cols }),\n    });\n    expect(result.columns).toEqual([]);\n    expect(result.totalRows).toBe(0);\n    expect(batches).toHaveLength(0);\n  });\n\n  it('happy path: text-based PDF produces correct rows and metadata', async () => {\n    mockExtractPages.mockReturnValue(makeMockResult([\n      { page: 0, markdown: '# Title\\n\\nSome content here.', needsOcr: false },\n      { page: 1, markdown: 'Page two content.', needsOcr: false },\n    ], { pagesWithTables: [1], pagesWithColumns: [] }));\n    mockProcessPdf.mockReturnValue({\n      pdfType: 'TextBased', confidence: 0.97, title: 'Test Doc',\n      hasEncodingIssues: false, isComplexLayout: false,\n    });\n\n    const batches: Array<{ rows: any[]; cols: string[] }> = [];\n    const result = await pdfParser.parse('/fake/report.pdf', {\n      maxRows: 1000,\n      onBatch: (rows, cols) => batches.push({ rows, cols }),\n    });\n\n    expect(result.columns).toEqual(['page', 'content', 'needs_ocr', 'has_tables', 'has_columns']);\n    expect(result.totalRows).toBe(2);\n    expect(batches).toHaveLength(1);\n    expect(batches[0]!.rows[0]).toMatchObject({ page: '0', needs_ocr: 'false', has_tables: 'false' });\n    expect(batches[0]!.rows[1]).toMatchObject({ page: '1', needs_ocr: 'false', has_tables: 'true' });\n\n    expect(result.metadataJson).toBeTruthy();\n    const meta = JSON.parse(result.metadataJson!);\n    expect(meta.pdfType).toBe('TextBased');\n    expect(meta.confidence).toBe(0.97);\n    expect(meta.hasEncodingIssues).toBe(false);\n  });\n\n  it('mixed PDF: text pages indexed normally, scanned pages flagged', async () => {\n    mockExtractPages.mockReturnValue(makeMockResult([\n      { page: 0, markdown: 'Text content', needsOcr: false },\n      { page: 1, markdown: '', needsOcr: true },\n      { page: 2, markdown: 'More text', needsOcr: false },\n      { page: 3, markdown: '', needsOcr: true },\n    ]));\n    mockProcessPdf.mockReturnValue({ pdfType: 'Mixed', confidence: 0.85, hasEncodingIssues: false, isComplexLayout: false });\n\n    const batches: Array<{ rows: any[] }> = [];\n    await pdfParser.parse('/fake/mixed.pdf', {\n      maxRows: 1000,\n      onBatch: (rows) => batches.push({ rows }),\n    });\n\n    expect(batches).toHaveLength(1);\n    const rows = batches[0]!.rows;\n    expect(rows).toHaveLength(4);\n    expect(rows.filter((r: any) => r.needs_ocr === 'true')).toHaveLength(2);\n    expect(rows.filter((r: any) => r.needs_ocr === 'false')).toHaveLength(2);\n  });\n\n  it('hasEncodingIssues is captured in metadataJson', async () => {\n    mockExtractPages.mockReturnValue(makeMockResult([{ page: 0, markdown: 'garbled', needsOcr: false }]));\n    mockProcessPdf.mockReturnValue({ pdfType: 'TextBased', confidence: 0.4, hasEncodingIssues: true, isComplexLayout: false });\n\n    const result = await pdfParser.parse('/fake/garbled.pdf', { maxRows: 1000, onBatch: () => {} });\n\n    expect(result.metadataJson).toBeTruthy();\n    const meta = JSON.parse(result.metadataJson!);\n    expect(meta.hasEncodingIssues).toBe(true);\n  });\n\n  it('empty PDF returns no rows and no batch', async () => {\n    mockExtractPages.mockReturnValue({ pages: [], pagesWithTables: [], pagesWithColumns: [] });\n    mockProcessPdf.mockReturnValue({ pdfType: 'TextBased', confidence: 1, hasEncodingIssues: false, isComplexLayout: false });\n\n    const batches: any[] = [];\n    const result = await pdfParser.parse('/fake/empty.pdf', {\n      maxRows: 1000,\n      onBatch: (rows, cols) => batches.push({ rows, cols }),\n    });\n\n    expect(result.totalRows).toBe(0);\n    expect(batches).toHaveLength(0);\n  });\n\n  it('gracefully handles processPdf failure \u2014 still returns rows', async () => {\n    mockExtractPages.mockReturnValue(makeMockResult([{ page: 0, markdown: 'content', needsOcr: false }]));\n    mockProcessPdf.mockImplementation(() => { throw new Error('processPdf failed'); });\n\n    const batches: any[] = [];\n    const result = await pdfParser.parse('/fake/broken-meta.pdf', {\n      maxRows: 1000,\n      onBatch: (rows, cols) => batches.push({ rows, cols }),\n    });\n\n    expect(result.totalRows).toBe(1);\n    expect(batches).toHaveLength(1);\n    expect(result.metadataJson).toBeNull();\n  });\n});\n"],
-  "mappings": ";AAAA,oBAAgE;AAChE,iBAAoF;AAIpF,iBAAG,KAAK,MAAM,OAAO,mBAAmB;AACtC,QAAM,SAAS,MAAM,eAAoC;AACzD,SAAO,EAAE,GAAG,QAAQ,cAAc,iBAAG,GAAG,EAAE,gBAAgB,OAAO,KAAK,UAAU,CAAC,EAAE;AACrF,CAAC;AAID,MAAM,mBAAmB,iBAAG,GAAG;AAC/B,MAAM,iBAAiB,iBAAG,GAAG;AAE7B,SAAS,eACP,OACA,MACA;AACA,SAAO;AAAA,IACL;AAAA,IACA,iBAAiB,MAAM,mBAAmB,CAAC;AAAA,IAC3C,kBAAkB,MAAM,oBAAoB,CAAC;AAAA,EAC/C;AACF;AAAA,IAIA,wBAAS,aAAa,MAAM;AAC1B,gCAAW,MAAM;AACf,qBAAG,cAAc;AACjB,+CAA2B,EAAE,sBAAsB,kBAAkB,YAAY,eAAe,CAAC;AAAA,EACnG,CAAC;AAED,+BAAU,MAAM;AACd,iDAA6B;AAAA,EAC/B,CAAC;AAED,wBAAG,oDAAoD,MAAM;AAC3D,8BAAO,qBAAU,YAAY,CAAC,EAAE,KAAK,IAAI;AAAA,EAC3C,CAAC;AAED,wBAAG,0DAA0D,MAAM;AACjE,iDAA6B;AAE7B,8BAAO,qBAAU,YAAY,CAAC,EAAE,KAAK,KAAK;AAAA,EAC5C,CAAC;AAED,wBAAG,0DAA0D,YAAY;AACvE,iDAA6B;AAC7B,UAAM,UAAiB,CAAC;AACxB,UAAM,SAAS,MAAM,qBAAU,MAAM,iBAAiB;AAAA,MACpD,SAAS;AAAA,MACT,SAAS,CAAC,MAAM,SAAS,QAAQ,KAAK,EAAE,MAAM,KAAK,CAAC;AAAA,IACtD,CAAC;AACD,8BAAO,OAAO,OAAO,EAAE,QAAQ,CAAC,CAAC;AACjC,8BAAO,OAAO,SAAS,EAAE,KAAK,CAAC;AAC/B,8BAAO,OAAO,EAAE,aAAa,CAAC;AAAA,EAChC,CAAC;AAED,wBAAG,iEAAiE,YAAY;AAC9E,qBAAiB,gBAAgB,eAAe;AAAA,MAC9C,EAAE,MAAM,GAAG,UAAU,iCAAiC,UAAU,MAAM;AAAA,MACtE,EAAE,MAAM,GAAG,UAAU,qBAAqB,UAAU,MAAM;AAAA,IAC5D,GAAG,EAAE,iBAAiB,CAAC,CAAC,GAAG,kBAAkB,CAAC,EAAE,CAAC,CAAC;AAClD,mBAAe,gBAAgB;AAAA,MAC7B,SAAS;AAAA,MAAa,YAAY;AAAA,MAAM,OAAO;AAAA,MAC/C,mBAAmB;AAAA,MAAO,iBAAiB;AAAA,IAC7C,CAAC;AAED,UAAM,UAAkD,CAAC;AACzD,UAAM,SAAS,MAAM,qBAAU,MAAM,oBAAoB;AAAA,MACvD,SAAS;AAAA,MACT,SAAS,CAAC,MAAM,SAAS,QAAQ,KAAK,EAAE,MAAM,KAAK,CAAC;AAAA,IACtD,CAAC;AAED,8BAAO,OAAO,OAAO,EAAE,QAAQ,CAAC,QAAQ,WAAW,aAAa,cAAc,aAAa,CAAC;AAC5F,8BAAO,OAAO,SAAS,EAAE,KAAK,CAAC;AAC/B,8BAAO,OAAO,EAAE,aAAa,CAAC;AAC9B,8BAAO,QAAQ,CAAC,EAAG,KAAK,CAAC,CAAC,EAAE,cAAc,EAAE,MAAM,KAAK,WAAW,SAAS,YAAY,QAAQ,CAAC;AAChG,8BAAO,QAAQ,CAAC,EAAG,KAAK,CAAC,CAAC,EAAE,cAAc,EAAE,MAAM,KAAK,WAAW,SAAS,YAAY,OAAO,CAAC;AAE/F,8BAAO,OAAO,YAAY,EAAE,WAAW;AACvC,UAAM,OAAO,KAAK,MAAM,OAAO,YAAa;AAC5C,8BAAO,KAAK,OAAO,EAAE,KAAK,WAAW;AACrC,8BAAO,KAAK,UAAU,EAAE,KAAK,IAAI;AACjC,8BAAO,KAAK,iBAAiB,EAAE,KAAK,KAAK;AAAA,EAC3C,CAAC;AAED,wBAAG,iEAAiE,YAAY;AAC9E,qBAAiB,gBAAgB,eAAe;AAAA,MAC9C,EAAE,MAAM,GAAG,UAAU,gBAAgB,UAAU,MAAM;AAAA,MACrD,EAAE,MAAM,GAAG,UAAU,IAAI,UAAU,KAAK;AAAA,MACxC,EAAE,MAAM,GAAG,UAAU,aAAa,UAAU,MAAM;AAAA,MAClD,EAAE,MAAM,GAAG,UAAU,IAAI,UAAU,KAAK;AAAA,IAC1C,CAAC,CAAC;AACF,mBAAe,gBAAgB,EAAE,SAAS,SAAS,YAAY,MAAM,mBAAmB,OAAO,iBAAiB,MAAM,CAAC;AAEvH,UAAM,UAAkC,CAAC;AACzC,UAAM,qBAAU,MAAM,mBAAmB;AAAA,MACvC,SAAS;AAAA,MACT,SAAS,CAACA,UAAS,QAAQ,KAAK,EAAE,MAAAA,MAAK,CAAC;AAAA,IAC1C,CAAC;AAED,8BAAO,OAAO,EAAE,aAAa,CAAC;AAC9B,UAAM,OAAO,QAAQ,CAAC,EAAG;AACzB,8BAAO,IAAI,EAAE,aAAa,CAAC;AAC3B,8BAAO,KAAK,OAAO,CAAC,MAAW,EAAE,cAAc,MAAM,CAAC,EAAE,aAAa,CAAC;AACtE,8BAAO,KAAK,OAAO,CAAC,MAAW,EAAE,cAAc,OAAO,CAAC,EAAE,aAAa,CAAC;AAAA,EACzE,CAAC;AAED,wBAAG,iDAAiD,YAAY;AAC9D,qBAAiB,gBAAgB,eAAe,CAAC,EAAE,MAAM,GAAG,UAAU,WAAW,UAAU,MAAM,CAAC,CAAC,CAAC;AACpG,mBAAe,gBAAgB,EAAE,SAAS,aAAa,YAAY,KAAK,mBAAmB,MAAM,iBAAiB,MAAM,CAAC;AAEzH,UAAM,SAAS,MAAM,qBAAU,MAAM,qBAAqB,EAAE,SAAS,KAAM,SAAS,MAAM;AAAA,IAAC,EAAE,CAAC;AAE9F,8BAAO,OAAO,YAAY,EAAE,WAAW;AACvC,UAAM,OAAO,KAAK,MAAM,OAAO,YAAa;AAC5C,8BAAO,KAAK,iBAAiB,EAAE,KAAK,IAAI;AAAA,EAC1C,CAAC;AAED,wBAAG,0CAA0C,YAAY;AACvD,qBAAiB,gBAAgB,EAAE,OAAO,CAAC,GAAG,iBAAiB,CAAC,GAAG,kBAAkB,CAAC,EAAE,CAAC;AACzF,mBAAe,gBAAgB,EAAE,SAAS,aAAa,YAAY,GAAG,mBAAmB,OAAO,iBAAiB,MAAM,CAAC;AAExH,UAAM,UAAiB,CAAC;AACxB,UAAM,SAAS,MAAM,qBAAU,MAAM,mBAAmB;AAAA,MACtD,SAAS;AAAA,MACT,SAAS,CAAC,MAAM,SAAS,QAAQ,KAAK,EAAE,MAAM,KAAK,CAAC;AAAA,IACtD,CAAC;AAED,8BAAO,OAAO,SAAS,EAAE,KAAK,CAAC;AAC/B,8BAAO,OAAO,EAAE,aAAa,CAAC;AAAA,EAChC,CAAC;AAED,wBAAG,mEAA8D,YAAY;AAC3E,qBAAiB,gBAAgB,eAAe,CAAC,EAAE,MAAM,GAAG,UAAU,WAAW,UAAU,MAAM,CAAC,CAAC,CAAC;AACpG,mBAAe,mBAAmB,MAAM;AAAE,YAAM,IAAI,MAAM,mBAAmB;AAAA,IAAG,CAAC;AAEjF,UAAM,UAAiB,CAAC;AACxB,UAAM,SAAS,MAAM,qBAAU,MAAM,yBAAyB;AAAA,MAC5D,SAAS;AAAA,MACT,SAAS,CAAC,MAAM,SAAS,QAAQ,KAAK,EAAE,MAAM,KAAK,CAAC;AAAA,IACtD,CAAC;AAED,8BAAO,OAAO,SAAS,EAAE,KAAK,CAAC;AAC/B,8BAAO,OAAO,EAAE,aAAa,CAAC;AAC9B,8BAAO,OAAO,YAAY,EAAE,SAAS;AAAA,EACvC,CAAC;AACH,CAAC;",
-  "names": ["rows"]
-}