fix(ai): Improve AI object response handling in parse-prd
This commit updates to more robustly handle responses from . Previously, the module strictly expected the AI-generated object to be nested under . This change ensures that it now first checks if itself contains the expected task data object, and then falls back to checking . This enhancement increases compatibility with varying AI provider response structures, similar to the improvements recently made in .
This commit is contained in:
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"models": {
|
||||
"main": {
|
||||
"provider": "google",
|
||||
"modelId": "gemini-2.5-pro-exp-03-25",
|
||||
"provider": "anthropic",
|
||||
"modelId": "claude-3-7-sonnet-20250219",
|
||||
"maxTokens": 100000,
|
||||
"temperature": 0.2
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user