2 Commits

Author	SHA1	Message	Date
Roberto Musso	c6c4578f9a	fix(tests): migrate eval tests to Langfuse V3 API ... lf.trace() and lf.score(trace_id=...) are V2 API removed in V3. V3 pattern: lf.start_as_current_observation(name=...) as context manager → obs obs.score(name=..., value=...) contextlib.nullcontext() when lf is None so structure stays the same Updated tests 2.1–2.7 in test_agent_runner_v2.py accordingly. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-07 23:04:24 +02:00
Roberto Musso	fa231a3642	feat(local-agent-v2): step 2+3 — unified runner + AgentConfig schema ... Step 3 (prerequisite): - app/schemas.py: add ContentTypeConfig + AgentConfig Pydantic models - app/models.py: add agent_config (JSON, nullable) to LocalAgentConfig - alembic migration a3b9c0d1e2f3: ADD COLUMN agent_config Step 2 (runner refactor): - Remove _classify_file() and _BATCH_FILE_CLASSIFIER_PROMPT (LLM classification step) - Add Phase A: detect_content_type + preprocess (zero LLM, per file) - Add _UNIFIED_PROCESSING_PROMPT (hot-swappable via Langfuse "unified_processing") - Add helper functions: _format_projects, _format_metadata, _get_extraction_rules, _get_no_match_behavior - Single LLM call per file with tools (classify + extract + create) - Fix items_created: count create_* tool calls via _tool_calls_out param - test_agent_runner_v2.py: 10 cases (2.1-2.10) with Langfuse eval scoring Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-07 15:00:32 +02:00