api/core at fa231a3642c864c0f8abd043a922c7d08fe3912f - api

Files

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

preprocessors

feat: add preprocessor system (Step 1 — Local Agent V2)

2026-04-07 10:19:02 +02:00

__init__.py

step 1 complete: runnable FastAPI skeleton

2026-03-01 23:51:37 +01:00

agent_registry.py

feat: migrate chat orchestration to deep langgraph workers

2026-03-12 22:25:36 +01:00

agent_runner.py

feat(local-agent-v2): step 2+3 — unified runner + AgentConfig schema