feat(ai): upgrade to OpenAI Responses API and enhance template generation #183

1 issue identified (86 code objects reviewed).

• Merge Base: 9175c72
• Head: 6c2a9c1

✅	File Path	Comments Posted
➖	`.gitignore`
➖	`backend/docker-compose.yml`
✅	`docker-compose.src.yml`	0
✅	`frontend/docker-compose.yml`	0
➖	`backend/src/ai/migrations/0004_add_model_choices_and_template_target.py`
✅	`backend/src/processes/tests/test_services/test_templates/test_ai/test_base_ai_service.py`	0
✅	`backend/src/processes/tests/test_services/test_templates/test_ai/test_anon_open_ai_service.py`	0
❌	`backend/src/processes/services/templates/ai.py`	1
✅	`backend/src/processes/tests/test_services/test_templates/test_ai/test_open_ai_service.py`	0

backend/src/processes/services/templates/ai.py

line 260: The model name 'gpt-4.1-mini' on line 260 appears to be a typo. OpenAI does not have a model called gpt-4.1-mini. The intended model was likely 'gpt-4o-mini' or similar. When prompt is None, API calls will fail with an invalid model error. [ Out of scope (triage) ]

backend/src/processes/tests/test_services/test_templates/test_ai/test_anon_open_ai_service.py

line 638: The test will fail because the mock JSON response doesn't include api_name in the tasks, but the production code get_short_template_data does task['api_name'] directly (not .get()), which will raise KeyError. The test expects task_1['api_name'] to be truthy (line 687), but the service will raise an exception before returning any data. [ Cross-file consolidated ]