@hasna/knowledge 0.2.26 → 0.2.28

package/src/knowledge-db.ts

@@ -1,354 +0,0 @@
-import { Database } from 'bun:sqlite';
-import { ensureParentDir } from './workspace';
-
-export const CURRENT_SCHEMA_VERSION = 5;
-
-export interface KnowledgeDbStats {
-  schema_version: number;
-  sources: number;
-  source_revisions: number;
-  chunks: number;
-  wiki_pages: number;
-  citations: number;
-  indexes: number;
-  runs: number;
-  run_events: number;
-  redaction_findings: number;
-  audit_events: number;
-  approval_gates: number;
-  storage_objects: number;
-  embeddings: number;
-  vector_entries: number;
-  reindex_queue: number;
-}
-
-const MIGRATION_1 = `
-PRAGMA journal_mode = WAL;
-PRAGMA foreign_keys = ON;
-
-CREATE TABLE IF NOT EXISTS schema_versions (
-  version INTEGER PRIMARY KEY,
-  applied_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS sources (
-  id TEXT PRIMARY KEY,
-  uri TEXT NOT NULL UNIQUE,
-  kind TEXT NOT NULL,
-  title TEXT,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  acl_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS source_revisions (
-  id TEXT PRIMARY KEY,
-  source_id TEXT NOT NULL REFERENCES sources(id) ON DELETE CASCADE,
-  revision TEXT NOT NULL,
-  hash TEXT,
-  extracted_text_uri TEXT,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  UNIQUE(source_id, revision)
-);
-
-CREATE TABLE IF NOT EXISTS chunks (
-  id TEXT PRIMARY KEY,
-  source_revision_id TEXT REFERENCES source_revisions(id) ON DELETE CASCADE,
-  wiki_page_id TEXT,
-  kind TEXT NOT NULL,
-  ordinal INTEGER NOT NULL,
-  text TEXT NOT NULL,
-  token_count INTEGER,
-  start_offset INTEGER,
-  end_offset INTEGER,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS chunk_embeddings (
-  id TEXT PRIMARY KEY,
-  chunk_id TEXT NOT NULL REFERENCES chunks(id) ON DELETE CASCADE,
-  provider TEXT NOT NULL,
-  model TEXT NOT NULL,
-  dimensions INTEGER NOT NULL,
-  vector_json TEXT NOT NULL,
-  created_at TEXT NOT NULL,
-  UNIQUE(chunk_id, provider, model)
-);
-
-CREATE TABLE IF NOT EXISTS wiki_pages (
-  id TEXT PRIMARY KEY,
-  path TEXT NOT NULL UNIQUE,
-  title TEXT NOT NULL,
-  artifact_uri TEXT,
-  content_hash TEXT,
-  status TEXT NOT NULL DEFAULT 'active',
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS wiki_backlinks (
-  from_page_id TEXT NOT NULL REFERENCES wiki_pages(id) ON DELETE CASCADE,
-  to_page_id TEXT NOT NULL REFERENCES wiki_pages(id) ON DELETE CASCADE,
-  label TEXT,
-  created_at TEXT NOT NULL,
-  PRIMARY KEY(from_page_id, to_page_id)
-);
-
-CREATE TABLE IF NOT EXISTS citations (
-  id TEXT PRIMARY KEY,
-  wiki_page_id TEXT REFERENCES wiki_pages(id) ON DELETE CASCADE,
-  chunk_id TEXT REFERENCES chunks(id) ON DELETE SET NULL,
-  source_uri TEXT NOT NULL,
-  quote TEXT,
-  start_offset INTEGER,
-  end_offset INTEGER,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS knowledge_indexes (
-  id TEXT PRIMARY KEY,
-  kind TEXT NOT NULL,
-  name TEXT NOT NULL,
-  artifact_uri TEXT,
-  shard_key TEXT,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL,
-  UNIQUE(kind, name, shard_key)
-);
-
-CREATE TABLE IF NOT EXISTS runs (
-  id TEXT PRIMARY KEY,
-  type TEXT NOT NULL,
-  prompt TEXT,
-  status TEXT NOT NULL,
-  provider TEXT,
-  model TEXT,
-  cost_tokens INTEGER NOT NULL DEFAULT 0,
-  cost_usd REAL NOT NULL DEFAULT 0,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS run_events (
-  id TEXT PRIMARY KEY,
-  run_id TEXT NOT NULL REFERENCES runs(id) ON DELETE CASCADE,
-  level TEXT NOT NULL,
-  event TEXT NOT NULL,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS provider_usage (
-  id TEXT PRIMARY KEY,
-  run_id TEXT REFERENCES runs(id) ON DELETE SET NULL,
-  provider TEXT NOT NULL,
-  model TEXT NOT NULL,
-  input_tokens INTEGER NOT NULL DEFAULT 0,
-  output_tokens INTEGER NOT NULL DEFAULT 0,
-  cost_usd REAL NOT NULL DEFAULT 0,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS redaction_findings (
-  id TEXT PRIMARY KEY,
-  source_uri TEXT,
-  run_id TEXT REFERENCES runs(id) ON DELETE SET NULL,
-  severity TEXT NOT NULL,
-  finding_type TEXT NOT NULL,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS storage_objects (
-  id TEXT PRIMARY KEY,
-  artifact_uri TEXT NOT NULL UNIQUE,
-  kind TEXT NOT NULL,
-  content_type TEXT,
-  hash TEXT,
-  size_bytes INTEGER,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL
-);
-
-CREATE VIRTUAL TABLE IF NOT EXISTS chunks_fts USING fts5(
-  text,
-  title,
-  source_uri,
-  content='',
-  tokenize='porter unicode61'
-);
-
-INSERT OR IGNORE INTO schema_versions(version, applied_at)
-VALUES (1, datetime('now'));
-`;
-
-const MIGRATION_2 = `
-DROP TABLE IF EXISTS chunks_fts;
-
-CREATE VIRTUAL TABLE IF NOT EXISTS chunks_fts USING fts5(
-  chunk_id UNINDEXED,
-  text,
-  title,
-  source_uri,
-  tokenize='porter unicode61'
-);
-
-INSERT OR IGNORE INTO schema_versions(version, applied_at)
-VALUES (2, datetime('now'));
-`;
-
-const MIGRATION_3 = `
-CREATE TABLE IF NOT EXISTS audit_events (
-  id TEXT PRIMARY KEY,
-  event_type TEXT NOT NULL,
-  action TEXT NOT NULL,
-  target_uri TEXT,
-  decision TEXT NOT NULL,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL
-);
-
-CREATE TABLE IF NOT EXISTS approval_gates (
-  id TEXT PRIMARY KEY,
-  action TEXT NOT NULL,
-  target_uri TEXT,
-  status TEXT NOT NULL,
-  reason TEXT,
-  approved_by TEXT,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL
-);
-
-CREATE INDEX IF NOT EXISTS idx_audit_events_action ON audit_events(action);
-CREATE INDEX IF NOT EXISTS idx_audit_events_target ON audit_events(target_uri);
-CREATE INDEX IF NOT EXISTS idx_audit_events_created ON audit_events(created_at);
-CREATE INDEX IF NOT EXISTS idx_approval_gates_action ON approval_gates(action);
-CREATE INDEX IF NOT EXISTS idx_approval_gates_status ON approval_gates(status);
-
-INSERT OR IGNORE INTO schema_versions(version, applied_at)
-VALUES (3, datetime('now'));
-`;
-
-const MIGRATION_4 = `
-CREATE TABLE IF NOT EXISTS vector_index_entries (
-  id TEXT PRIMARY KEY,
-  chunk_id TEXT NOT NULL REFERENCES chunks(id) ON DELETE CASCADE,
-  source_revision_id TEXT REFERENCES source_revisions(id) ON DELETE CASCADE,
-  provider TEXT NOT NULL,
-  model TEXT NOT NULL,
-  dimensions INTEGER NOT NULL,
-  vector_json TEXT NOT NULL,
-  vector_norm REAL NOT NULL,
-  source_uri TEXT,
-  source_ref TEXT,
-  revision TEXT,
-  hash TEXT,
-  start_offset INTEGER,
-  end_offset INTEGER,
-  token_count INTEGER,
-  status TEXT NOT NULL DEFAULT 'active',
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL,
-  UNIQUE(chunk_id, provider, model)
-);
-
-CREATE INDEX IF NOT EXISTS idx_vector_index_provider_model ON vector_index_entries(provider, model);
-CREATE INDEX IF NOT EXISTS idx_vector_index_source_revision ON vector_index_entries(source_revision_id);
-CREATE INDEX IF NOT EXISTS idx_vector_index_source_uri ON vector_index_entries(source_uri);
-CREATE INDEX IF NOT EXISTS idx_vector_index_status ON vector_index_entries(status);
-
-INSERT OR IGNORE INTO schema_versions(version, applied_at)
-VALUES (4, datetime('now'));
-`;
-
-const MIGRATION_5 = `
-CREATE TABLE IF NOT EXISTS reindex_queue (
-  id TEXT PRIMARY KEY,
-  kind TEXT NOT NULL,
-  target_id TEXT NOT NULL,
-  source_uri TEXT,
-  reason TEXT NOT NULL,
-  status TEXT NOT NULL DEFAULT 'pending',
-  attempts INTEGER NOT NULL DEFAULT 0,
-  metadata_json TEXT NOT NULL DEFAULT '{}',
-  created_at TEXT NOT NULL,
-  updated_at TEXT NOT NULL,
-  UNIQUE(kind, target_id, reason)
-);
-
-CREATE INDEX IF NOT EXISTS idx_reindex_queue_status ON reindex_queue(status);
-CREATE INDEX IF NOT EXISTS idx_reindex_queue_kind_target ON reindex_queue(kind, target_id);
-CREATE INDEX IF NOT EXISTS idx_reindex_queue_source_uri ON reindex_queue(source_uri);
-
-INSERT OR IGNORE INTO schema_versions(version, applied_at)
-VALUES (5, datetime('now'));
-`;
-
-export function openKnowledgeDb(path: string): Database {
-  ensureParentDir(path);
-  const db = new Database(path);
-  db.exec('PRAGMA foreign_keys = ON;');
-  db.exec('PRAGMA busy_timeout = 5000;');
-  return db;
-}
-
-export function migrateKnowledgeDb(path: string): { path: string; schema_version: number } {
-  const db = openKnowledgeDb(path);
-  try {
-    db.exec(MIGRATION_1);
-    if (getSchemaVersion(db) < 2) db.exec(MIGRATION_2);
-    if (getSchemaVersion(db) < 3) db.exec(MIGRATION_3);
-    if (getSchemaVersion(db) < 4) db.exec(MIGRATION_4);
-    if (getSchemaVersion(db) < 5) db.exec(MIGRATION_5);
-    return { path, schema_version: getSchemaVersion(db) };
-  } finally {
-    db.close();
-  }
-}
-
-export function getSchemaVersion(db: Database): number {
-  const row = db.query<{ version: number }, []>('SELECT MAX(version) AS version FROM schema_versions').get();
-  return row?.version ?? 0;
-}
-
-function count(db: Database, table: string): number {
-  const row = db.query<{ n: number }, []>(`SELECT COUNT(*) AS n FROM ${table}`).get();
-  return row?.n ?? 0;
-}
-
-export function getKnowledgeDbStats(path: string): KnowledgeDbStats {
-  const db = openKnowledgeDb(path);
-  try {
-    return {
-      schema_version: getSchemaVersion(db),
-      sources: count(db, 'sources'),
-      source_revisions: count(db, 'source_revisions'),
-      chunks: count(db, 'chunks'),
-      wiki_pages: count(db, 'wiki_pages'),
-      citations: count(db, 'citations'),
-      indexes: count(db, 'knowledge_indexes'),
-      runs: count(db, 'runs'),
-      run_events: count(db, 'run_events'),
-      redaction_findings: count(db, 'redaction_findings'),
-      audit_events: count(db, 'audit_events'),
-      approval_gates: count(db, 'approval_gates'),
-      storage_objects: count(db, 'storage_objects'),
-      embeddings: count(db, 'chunk_embeddings'),
-      vector_entries: count(db, 'vector_index_entries'),
-      reindex_queue: count(db, 'reindex_queue'),
-    };
-  } finally {
-    db.close();
-  }
-}