feat: brain service — self-contained second brain knowledge manager

Full backend service with:
- FastAPI REST API with CRUD, search, reprocess endpoints
- PostgreSQL + pgvector for items and semantic search
- Redis + RQ for background job processing
- Meilisearch for fast keyword/filter search
- Browserless/Chrome for JS rendering and screenshots
- OpenAI structured output for AI classification
- Local file storage with S3-ready abstraction
- Gateway auth via X-Gateway-User-Id header
- Own docker-compose stack (6 containers)

Classification: fixed folders (Home/Family/Work/Travel/Knowledge/Faith/Projects)
and fixed tags (28 predefined). AI assigns exactly 1 folder, 2-3 tags, title,
summary, and confidence score per item.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

services/brain/app/models/schema.py

@@ -0,0 +1,109 @@
+"""Pydantic schemas for API request/response."""
+
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+# ── Request schemas ──
+
+class ItemCreate(BaseModel):
+    type: str = "link"
+    url: Optional[str] = None
+    raw_content: Optional[str] = None
+    title: Optional[str] = None
+    folder: Optional[str] = None
+    tags: Optional[list[str]] = None
+
+
+class ItemUpdate(BaseModel):
+    title: Optional[str] = None
+    folder: Optional[str] = None
+    tags: Optional[list[str]] = None
+    raw_content: Optional[str] = None
+
+
+class SearchQuery(BaseModel):
+    q: str
+    folder: Optional[str] = None
+    tags: Optional[list[str]] = None
+    type: Optional[str] = None
+    limit: int = Field(default=20, le=100)
+    offset: int = 0
+
+
+class SemanticSearchQuery(BaseModel):
+    q: str
+    folder: Optional[str] = None
+    type: Optional[str] = None
+    limit: int = Field(default=20, le=100)
+
+
+class HybridSearchQuery(BaseModel):
+    q: str
+    folder: Optional[str] = None
+    tags: Optional[list[str]] = None
+    type: Optional[str] = None
+    limit: int = Field(default=20, le=100)
+
+
+# ── Response schemas ──
+
+class AssetOut(BaseModel):
+    id: str
+    asset_type: str
+    filename: str
+    content_type: Optional[str] = None
+    size_bytes: Optional[int] = None
+    created_at: datetime
+
+    model_config = {"from_attributes": True}
+
+
+class ItemOut(BaseModel):
+    id: str
+    type: str
+    title: Optional[str] = None
+    url: Optional[str] = None
+    folder: Optional[str] = None
+    tags: Optional[list[str]] = None
+    summary: Optional[str] = None
+    confidence: Optional[float] = None
+    processing_status: str
+    processing_error: Optional[str] = None
+    metadata_json: Optional[dict] = None
+    created_at: datetime
+    updated_at: datetime
+    assets: list[AssetOut] = []
+
+    model_config = {"from_attributes": True}
+
+
+class ItemList(BaseModel):
+    items: list[ItemOut]
+    total: int
+
+
+class SearchResult(BaseModel):
+    items: list[ItemOut]
+    total: int
+    query: str
+
+
+class ConfigOut(BaseModel):
+    folders: list[str]
+    tags: list[str]
+
+
+# ── OpenAI classification schema ──
+
+class ClassificationResult(BaseModel):
+    """What the AI returns for each item."""
+    folder: str
+    tags: list[str] = Field(min_length=2, max_length=3)
+    title: str
+    summary: str
+    confidence: float = Field(ge=0.0, le=1.0)