Skip to content

fix(catalog): default openai to gpt-5.5 (matches bundle's extended_thinking=true) #20

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
manojp99 merged 1 commit into from
May 28, 2026
Merged

fix(catalog): default openai to gpt-5.5 (matches bundle's extended_thinking=true) #20

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion src/amplifier_agent_cli/provider_sources.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,11 @@ class _CatalogEntry(TypedDict):
"module": "provider-openai",
"source": "git+https://github.com/microsoft/amplifier-module-provider-openai@main",
"env_var": "OPENAI_API_KEY",
"default_model": "gpt-4o",
# gpt-5.5 chosen so the bundle's default `extended_thinking: true` lands
# on a model that actually accepts the resulting `reasoning.effort`
# parameter. With gpt-4o (non-reasoning), the OpenAI API 400s on every
# turn out of the box. Consumers can override via bundle config.
"default_model": "gpt-5.5",
},
"azure-openai": {
"module": "provider-azure-openai",
Expand Down
Loading