MicroFish/backend/app/services
Ubuntu 2aa44760d1 feat(f2a-b): step02/03 UX overhaul, Azure OpenAI fix, offline report interviews
Step 02/03 UX:
- Remove duplicate simulation params (total_hours, minutes_per_round) from Fase B form
- Add following_probability + recsys_type to step 03 config panel instead
- Step 03 now read-only by default with Edit / Save toolbar toggle
- Add common.edit and log.configSaved i18n keys to all 4 locales

Backend - Azure OpenAI fix (run_parallel_simulation.py):
- create_model() now detects Azure URLs (cognitiveservices.azure.com / openai.azure.com)
  and uses ModelPlatformType.AZURE with AzureOpenAIModel, passing api_version and
  azure_deployment_name explicitly — fixes 404 "Resource not found" from camel-ai

Backend - offline report interviews (simulation_runner.py):
- interview_agents_batch() falls back to _offline_batch_interview() when OASIS env is
  closed (simulation finished), reading posts from SQLite DB instead of failing with
  "No successful interviews / check OASIS environment status"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 23:20:41 +00:00
..
__init__.py chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
graph_builder.py fix(ontology): handle string attributes from LLM response to prevent TypeError crash 2026-04-26 14:59:10 +00:00
oasis_profile_generator.py feat(f2a-b): step02/03 UX overhaul, Azure OpenAI fix, offline report interviews 2026-05-04 23:20:41 +00:00
ontology_generator.py fix(ontology): handle string attributes from LLM response to prevent TypeError crash 2026-04-26 14:59:10 +00:00
report_agent.py fix(report): strip fabricated tool_result blocks to prevent LLM hallucination loop 2026-04-26 15:06:24 +00:00
simulation_config_generator.py fix(llm): centralise Azure URL normalisation in parse_azure_url utility 2026-04-25 21:09:48 +00:00
simulation_ipc.py chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
simulation_manager.py feat(f2a-b): step02/03 UX overhaul, Azure OpenAI fix, offline report interviews 2026-05-04 23:20:41 +00:00
simulation_runner.py feat(f2a-b): step02/03 UX overhaul, Azure OpenAI fix, offline report interviews 2026-05-04 23:20:41 +00:00
text_processor.py chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
zep_entity_reader.py feat(simulation): add max_agents selector via top-N connectivity in prepare 2026-05-03 21:54:34 +00:00
zep_graph_memory_updater.py refactor(services): replace direct Zep SDK calls with GraphBackend interface 2026-04-25 13:09:59 +00:00
zep_tools.py refactor(services): replace direct Zep SDK calls with GraphBackend interface 2026-04-25 13:09:59 +00:00