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>

alembic/versions/a3b9c0d1e2f3_add_agent_config_to_local_agents.py

@@ -0,0 +1,31 @@
+"""add agent_config to local_agent_configs
+
+Revision ID: a3b9c0d1e2f3
+Revises: 9a1f2d0b6c7e
+Create Date: 2026-04-07 00:00:00.000000
+
+"""
+from __future__ import annotations
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "a3b9c0d1e2f3"
+down_revision: Union[str, None] = "9a1f2d0b6c7e"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "local_agent_configs",
+        sa.Column("agent_config", sa.JSON(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("local_agent_configs", "agent_config")