chihlasm/resolutionflow
1
0
Fork 0
Code Issues 23 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

feat: route AI model selection through action-type config

Browse Source 
Update get_ai_provider() to accept an optional model override parameter
(applied only to AnthropicProvider; Gemini always uses its own model).
Thread action_type-based model resolution through send_message() and
generate_final_tree() in the AI chat service.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
chihlasm
2026-03-06 23:24:55 -05:00
parent 41b7cd86b8
commit d1d21152d7
2 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
backend/app/core/ai_chat_service.py
View File

@@ -465,7 +465,9 @@ async def send_message(
for msg in history
]
provider = get_ai_provider()
# Resolve model for this action type
action_model = settings.get_model_for_action(action_type)
provider = get_ai_provider(model=action_model)
response_text, input_tokens, output_tokens = await provider.generate_text(
system_prompt=system_prompt,
messages=provider_messages,
@@ -584,7 +586,7 @@ Also provide metadata as a separate JSON object after the tree:
provider_messages.append({"role": "user", "content": generation_instruction})
provider = get_ai_provider()
provider = get_ai_provider(model=settings.get_model_for_action("generate_full"))
for attempt in range(2): # One try + one retry
response_text, input_tokens, output_tokens = await provider.generate_text(