fix(langfuse): remove invalid user_id/session_id kwargs from start_as_current_observation

Langfuse V3 does not accept user_id/session_id on observation-level calls.
Moved to metadata dict in agent_runner, deep_agent, and agent_setup.

refactor(tests): fixture-based pattern for agent_runner_v2 eval tests

- cases.yaml + data/ fixtures under tests/fixtures/agent_runner_v2/
- pytest_generate_tests parametrizes test_eval_runner from YAML
- _resolve_projects() handles symbolic names and inline dicts
- _evaluate_case() centralizes all assertion logic
- --runner-dir CLI option for custom fixture folders

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

app/core/deep_agent.py

@@ -615,8 +615,7 @@ async def _run_single_agent(
         lf.start_as_current_observation(
             as_type="span",
             name=agent_name,
-            user_id=user_id,
-            session_id=trace_id,
+            metadata={"user_id": user_id, "session_id": trace_id},
             input=message,
         )
         if lf else None
@@ -740,8 +739,7 @@ async def _run_single_agent_stream(
         lf.start_as_current_observation(
             as_type="span",
             name=f"{agent_name}-stream",
-            user_id=user_id,
-            session_id=trace_id,
+            metadata={"user_id": user_id, "session_id": trace_id},
             input=message,
         )
         if lf else None