Skip to content

feat(azure-open-ai/gpt-5.6-sol-2026-07-09): add new models [bot]#1724

Open
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-azure-open-ai-gpt-5.6-sol-2026-07-09-20260710-000619
Open

feat(azure-open-ai/gpt-5.6-sol-2026-07-09): add new models [bot]#1724
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-azure-open-ai-gpt-5.6-sol-2026-07-09-20260710-000619

Conversation

@models-bot

@models-bot models-bot Bot commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

Auto-generated by model-addition-agent for azure-open-ai/gpt-5.6-sol-2026-07-09.


Note

Low Risk
Declarative model metadata only; no runtime, auth, or routing logic changes.

Overview
Registers gpt-5.6-sol-2026-07-09 for Azure Open AI via a new provider YAML at providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml.

The entry marks the model active with retirement 2027-07-09, chat and responses modes, thinking enabled, and a ~1.05M context window (922k input / 128k output). It advertises tool-related features (function calling, structured output, tool choice), text + image input, and configurable reasoning_effort (default medium, including none).

Reviewed by Cursor Bugbot for commit 1dad47d. Bugbot is set up for automated code reviews on this repo. Configure here.

mode: chat
model: gpt-5.6-sol-2026-07-09
supportedModes:
- chat

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing costs omit catalog

High Severity

The new Azure entry only sets mode, model, and supportedModes, with no costs block. build-unified-json.ts skips any model whose costs array is empty, so gpt-5.6-sol-2026-07-09 never lands in dist/ai-models.json or the synced gateway catalog despite this PR adding the model.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit a95f218. Configure here.

Comment thread providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml
@github-actions

Copy link
Copy Markdown
Contributor

/test-models

@harshiv-26

Copy link
Copy Markdown
Collaborator

Gateway test results

  • Total: 0
  • Passed: 0
  • Failed: 0
  • Validation failed: 0
  • Errored: 0
  • Skipped: 0
  • Success rate: 0.0%
Provider Model Scenarios

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes using default effort and found 2 potential issues.

There are 3 total unresolved issues (including 1 from previous review).

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit 1dad47d. Configure here.

- low
- medium
- high
type: string

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reasoning effort missing xhigh

Medium Severity

reasoning_effort lists only none, low, medium, and high. The closest Azure sibling gpt-5.5-2026-04-24 and OpenAI gpt-5.6-sol also allow xhigh, so callers using that level may be rejected or misconfigured for this model.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 1dad47d. Configure here.

- parallel_function_calling
- structured_output
- system_messages
- tool_choice

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing prompt caching feature

Medium Severity

The features list omits prompt_caching, while Azure gpt-5.5-2026-04-24 and OpenAI gpt-5.6-sol declare it. Consumers that gate caching on feature flags may disable caching for this model incorrectly.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 1dad47d. Configure here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant