sync: migrate ai-operator to Gitea (2026-08-10)

migrations/001_init_kb.sql

@@ -0,0 +1,77 @@
+CREATE EXTENSION IF NOT EXISTS vector;
+
+CREATE TABLE IF NOT EXISTS schema_migrations (
+    version text PRIMARY KEY,
+    applied_at timestamptz NOT NULL DEFAULT now()
+);
+
+CREATE TABLE IF NOT EXISTS knowledge_documents (
+    id uuid PRIMARY KEY,
+    external_id text NOT NULL UNIQUE,
+    title text NOT NULL,
+    language text NOT NULL CHECK (language IN ('ru','kk')),
+    region_code text NOT NULL DEFAULT 'global' CHECK (length(region_code) > 0),
+    category text NOT NULL DEFAULT 'general',
+    source_type text NOT NULL,
+    source_uri text,
+    source_hash text NOT NULL,
+    status text NOT NULL DEFAULT 'published' CHECK (status IN ('draft','published','archived')),
+    content text NOT NULL,
+    question text,
+    short_answer text,
+    full_answer text,
+    keywords text[] NOT NULL DEFAULT '{}',
+    source text,
+    metadata jsonb NOT NULL DEFAULT '{}',
+    valid_from timestamptz,
+    valid_to timestamptz,
+    priority int NOT NULL DEFAULT 0,
+    created_at timestamptz NOT NULL DEFAULT now(),
+    updated_at timestamptz NOT NULL DEFAULT now()
+);
+
+CREATE TABLE IF NOT EXISTS knowledge_chunks (
+    id uuid PRIMARY KEY,
+    document_id uuid NOT NULL REFERENCES knowledge_documents(id) ON DELETE CASCADE,
+    chunk_index int NOT NULL,
+    language text NOT NULL CHECK (language IN ('ru','kk')),
+    region_code text NOT NULL,
+    title text NOT NULL,
+    content text NOT NULL,
+    content_hash text NOT NULL,
+    token_estimate int NOT NULL DEFAULT 0,
+    char_count int NOT NULL DEFAULT 0,
+    embedding vector(1536),
+    embedding_model text NOT NULL DEFAULT 'fake',
+    embedding_provider text NOT NULL DEFAULT 'fake',
+    metadata jsonb NOT NULL DEFAULT '{}',
+    tsv tsvector,
+    created_at timestamptz NOT NULL DEFAULT now(),
+    updated_at timestamptz NOT NULL DEFAULT now(),
+    UNIQUE(document_id, chunk_index)
+);
+
+CREATE TABLE IF NOT EXISTS knowledge_ingest_runs (
+    id uuid PRIMARY KEY,
+    source_path text NOT NULL,
+    status text NOT NULL,
+    documents_seen int NOT NULL DEFAULT 0,
+    documents_ingested int NOT NULL DEFAULT 0,
+    chunks_created int NOT NULL DEFAULT 0,
+    skipped int NOT NULL DEFAULT 0,
+    error text,
+    started_at timestamptz NOT NULL DEFAULT now(),
+    finished_at timestamptz
+);
+
+CREATE TABLE IF NOT EXISTS knowledge_search_logs (
+    id uuid PRIMARY KEY,
+    call_id text,
+    query text NOT NULL,
+    language text NOT NULL,
+    region_code text NOT NULL,
+    result_count int NOT NULL,
+    top_score double precision,
+    cross_language_fallback_used boolean NOT NULL DEFAULT false,
+    created_at timestamptz NOT NULL DEFAULT now()
+);