chore: initial commit — existing single-user document scanner codebase

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/services/classifier.py

@@ -0,0 +1,59 @@
+"""
+Classification orchestrator.
+Loads settings, selects AI provider, classifies document, auto-creates suggested topics.
+"""
+from services import storage
+from ai import get_provider
+
+MAX_AI_CHARS = 8_000
+
+
+async def classify_document(doc_id: str, topic_names: list[str] | None = None) -> list[str]:
+    """
+    Classify a document by its ID. Returns the list of assigned topic names.
+    If topic_names is provided, restrict classification to those topics.
+    Auto-creates any newly suggested topics.
+    """
+    meta = storage.get_metadata(doc_id)
+    if meta is None:
+        raise ValueError(f"Document {doc_id} not found")
+
+    settings = storage.load_settings()
+    system_prompt = settings.get("system_prompt", "")
+    provider = get_provider(settings)
+
+    # Use all known topics if not specified
+    if topic_names is None:
+        all_topics = storage.load_topics()
+        topic_names = [t["name"] for t in all_topics]
+
+    text = meta.get("extracted_text", "")
+    result = await provider.classify(text[:MAX_AI_CHARS], topic_names, system_prompt)
+
+    # Collect all topic names to persist (assigned + suggested)
+    all_new_names = set(result.suggested_new_topics) | set(result.topics)
+
+    # Auto-create any topic not already in the registry
+    existing_names = {t.lower() for t in topic_names}
+    for name in all_new_names:
+        if name.strip() and name.lower() not in existing_names:
+            storage.create_topic(name.strip())
+
+    # Final list: everything the AI assigned or suggested
+    final_topics = [t for t in list(set(result.topics + result.suggested_new_topics)) if t.strip()]
+
+    storage.update_document_topics(doc_id, final_topics)
+    return final_topics
+
+
+async def suggest_topics_for_document(doc_id: str) -> list[str]:
+    """Return AI-suggested topic names without modifying the document."""
+    meta = storage.get_metadata(doc_id)
+    if meta is None:
+        raise ValueError(f"Document {doc_id} not found")
+
+    settings = storage.load_settings()
+    system_prompt = settings.get("system_prompt", "")
+    provider = get_provider(settings)
+    text = meta.get("extracted_text", "")
+    return await provider.suggest_topics(text[:MAX_AI_CHARS], system_prompt)