Roberto Musso c0aef71141 refactor(tests): remove non-deterministic journey eval cases 4.2–4.5 ...

Keep only 4.1 (first reply contains question) as automated eval.
Multi-turn cases (4.2–4.5) are non-deterministic and tested manually
with results tracked in Langfuse.

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

2026-04-08 09:41:43 +02:00

..

fixtures

refactor(tests): remove non-deterministic journey eval cases 4.2–4.5

2026-04-08 09:41:43 +02:00

__init__.py

step 1 complete: runnable FastAPI skeleton

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

conftest.py

feat(local-agent-v2): step 4 — journey produces structured AgentConfig JSON

2026-04-08 00:23:58 +02:00

test_agent_runner_v2.py

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

2026-04-08 00:45:15 +02:00

test_agent_runner.py

refactor agents to client-owned config flow

2026-03-16 22:35:46 +01:00

test_agent_setup.py

step 3.5 complete: chatbot journey endpoint

2026-03-05 17:35:37 +01:00

test_auth.py

Remove unused imports across multiple files to clean up the codebase

2026-03-03 17:21:40 +01:00

test_classify_file.py

Fix project creation: code-based in runner, not delegated to Step 2 LLM

2026-03-21 23:40:38 +01:00

test_deep_agent.py

fix floating stream empty responses with sanitizer-safe fallbacks

2026-03-13 16:57:30 +01:00

test_device_ws.py

step 3.3 complete: device WS endpoint + DeviceConnectionManager

2026-03-05 15:51:58 +01:00

test_integrations.py

feat(step-3.6): cloud provider integrations (Gmail, Outlook, Teams)

2026-03-05 18:05:07 +01:00

test_journey_v2.py

refactor(tests): remove non-deterministic journey eval cases 4.2–4.5

2026-04-08 09:41:43 +02:00

test_memory_middleware.py

scope episodic memory enrichment by session_id

2026-03-16 00:33:11 +01:00

test_memory_models.py

step-6: add memory models and migration (models.py, alembic)

2026-03-08 22:05:58 +01:00

test_middleware.py

feat: migrate chat orchestration to deep langgraph workers

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

test_output_formatter.py

refactor floating_domain to structured object-only payload

2026-03-13 16:09:24 +01:00

test_preprocessors.py

chore(tests): remove Langfuse from all preprocessor tests

2026-04-07 14:26:33 +02:00

test_schemas_v3.py

refactor floating_domain to structured object-only payload

2026-03-13 16:09:24 +01:00

test_ws_unified.py

refactor floating_domain to structured object-only payload

2026-03-13 16:09:24 +01:00