Skip to content

feat(databricks): update model YAMLs [bot]#367

Open
hganwani-droid wants to merge 1 commit intomainfrom
bot/update-databricks-20260319-104150
Open

feat(databricks): update model YAMLs [bot]#367
hganwani-droid wants to merge 1 commit intomainfrom
bot/update-databricks-20260319-104150

Conversation

@hganwani-droid
Copy link
Collaborator

@hganwani-droid hganwani-droid commented Mar 19, 2026

Auto-generated by poc-agent for provider databricks.


Note

Medium Risk
Mainly updates Databricks model metadata, but changes to limits (e.g., context windows/token caps) and deprecation flags can affect downstream model selection and request sizing.

Overview
Refreshes Databricks model YAML metadata by adding explicit context_window values, modalities (text/image and, for Gemini Pro, audio/video/pdf), and thinking support across many chat models.

Updates capability flags and message-role support (e.g., adds system_messages, structured_output, tools, and messages.options for databricks-gpt-5) and annotates models with lifecycle/documentation metadata (isDeprecated, deprecationDate, sources).

Adjusts some token limits to align with stated context windows (notably reducing databricks-gpt-oss-120b max tokens to 128000).

Written by Cursor Bugbot for commit 284b5c5. This will update automatically on new commits. Configure here.

Copy link

@cursor cursor bot left a comment

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 and found 3 potential issues.

Fix All in Cursor

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

max_input_tokens: 131072
max_output_tokens: 131072
max_tokens: 131072
context_window: 128000
Copy link

Choose a reason for hiding this comment

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

Token limit fields accidentally removed from gpt-oss-20b model

High Severity

The max_input_tokens, max_output_tokens, and max_tokens fields (previously 131072) were removed entirely instead of being updated. The limits section now only contains context_window: 128000. The sibling model databricks-gpt-oss-120b.yaml correctly retained all three fields (updated to 128000). Any system reading these token limits will get no value, likely causing errors or falling back to incorrect defaults.

Fix in Cursor Fix in Web

max_input_tokens: 200000
max_output_tokens: 32000
max_tokens: 32000
modalities:
Copy link

Choose a reason for hiding this comment

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

Missing context_window in claude-opus-4 model YAML

Medium Severity

The context_window field was not added to this model's limits, while every other Claude model in this PR (claude-3-7-sonnet, claude-haiku-4-5, claude-opus-4-1, claude-opus-4-5, claude-sonnet-4, claude-sonnet-4-5) received context_window: 200000. Given max_input_tokens is 200000, this omission appears accidental.

Fix in Cursor Fix in Web

max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
Copy link

Choose a reason for hiding this comment

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

Missing context_window in claude-sonnet-4-1 model YAML

Medium Severity

The context_window field was not added to this model's limits, while every other Claude model in this PR received context_window: 200000. The nearly identical databricks-claude-sonnet-4.yaml has context_window: 200000, making this omission inconsistent and likely accidental.

Fix in Cursor Fix in Web

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.

2 participants