MVP stage 1: extract -> Postgres + atom_versions (web) + Qdrant

db/schema.sql

@@ -0,0 +1,100 @@
+-- content-atom: schema для MVP stage 1
+-- Postgres (atom-db) + pgvector (расширение "vector")
+
+CREATE EXTENSION IF NOT EXISTS vector;
+CREATE EXTENSION IF NOT EXISTS pg_trgm;
+CREATE EXTENSION IF NOT EXISTS btree_gin;
+
+-- Проекты (домены)
+CREATE TABLE projects (
+  id        UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  slug      TEXT UNIQUE NOT NULL,
+  name      TEXT NOT NULL,
+  kind      TEXT NOT NULL,          -- site | service | social | podcast
+  niche     TEXT,
+  role      TEXT NOT NULL DEFAULT 'satellite',  -- flagship | satellite | experiment | service
+  locale    TEXT DEFAULT 'ru',
+  settings  JSONB DEFAULT '{}',
+  status    TEXT DEFAULT 'active',  -- active | paused | archived
+  created_at TIMESTAMPTZ DEFAULT now()
+);
+CREATE INDEX ON projects (role, niche);
+
+-- Атомы
+CREATE TABLE atoms (
+  id             UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  project_id     UUID REFERENCES projects(id) ON DELETE CASCADE,
+  type           TEXT NOT NULL,      -- claim | fact | stat | quote | definition | instruction | case | comparison | qa | opinion | hook | transition | cta | media_ref
+  status         TEXT NOT NULL DEFAULT 'draft',
+  title          TEXT,
+  summary        TEXT,
+  body           JSONB NOT NULL,
+  plain_text     TEXT,
+  language       TEXT DEFAULT 'ru',
+  entities       JSONB DEFAULT '[]',
+  topics         TEXT[] DEFAULT '{}',
+  intent         TEXT,
+  audience       TEXT,
+  confidence     NUMERIC(3,2),
+  quality_score  NUMERIC(4,2),
+  word_count     INT,
+  source_refs    JSONB DEFAULT '[]',
+  embedding      VECTOR(1024),
+  generator      JSONB,
+  cost           JSONB,
+  pipeline_stage TEXT,
+  parent_atom_id UUID,
+  lineage_root_id UUID,
+  created_at     TIMESTAMPTZ DEFAULT now(),
+  updated_at     TIMESTAMPTZ DEFAULT now()
+);
+CREATE INDEX ON atoms (project_id, type, status);
+CREATE INDEX ON atoms USING gin (plain_text gin_trgm_ops);
+CREATE INDEX ON atoms USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100);
+
+-- Версии под каналы
+CREATE TABLE atom_versions (
+  id            UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  atom_id       UUID REFERENCES atoms(id) ON DELETE CASCADE,
+  channel       TEXT NOT NULL,       -- web_article | telegram | youtube_script | podcast | newsletter | service_card
+  format        TEXT NOT NULL,       -- markdown | html | plain | srt | ssml | json
+  content       TEXT NOT NULL,
+  meta          JSONB DEFAULT '{}',
+  quality_score NUMERIC(4,2),
+  created_at    TIMESTAMPTZ DEFAULT now(),
+  UNIQUE (atom_id, channel, format)
+);
+CREATE INDEX ON atom_versions (channel, created_at DESC);
+
+-- Задачи пайплайна + стоимость
+CREATE TABLE jobs (
+  id           UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  kind         TEXT NOT NULL,        -- generate | edit | adapt | publish | index
+  atom_id      UUID REFERENCES atoms(id),
+  status       TEXT DEFAULT 'queued',
+  attempts     INT DEFAULT 0,
+  max_attempts INT DEFAULT 3,
+  payload      JSONB DEFAULT '{}',
+  error        TEXT,
+  scheduled_at TIMESTAMPTZ DEFAULT now(),
+  started_at   TIMESTAMPTZ,
+  finished_at  TIMESTAMPTZ,
+  created_at   TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE runs (
+  id          BIGSERIAL PRIMARY KEY,
+  job_id      UUID REFERENCES jobs(id) ON DELETE CASCADE,
+  stage       TEXT NOT NULL,
+  model       TEXT,
+  tokens_in   INT,
+  tokens_out  INT,
+  seconds     NUMERIC,
+  cost_usd    NUMERIC DEFAULT 0,
+  quality     NUMERIC(4,2),
+  created_at  TIMESTAMPTZ DEFAULT now()
+);
+
+-- Индексы
+CREATE INDEX ON jobs (status, scheduled_at);
+CREATE INDEX ON runs (stage, created_at DESC);