feat(opencode): Add Databricks provider support #7984
+783
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add Databricks Foundation Model APIs as a new provider supporting OpenAI-compatible endpoints via /serving-endpoints. Authentication methods (in priority order): - Personal Access Token (DATABRICKS_TOKEN or stored auth) - OAuth M2M (DATABRICKS_CLIENT_ID + DATABRICKS_CLIENT_SECRET) - Azure AD Service Principal (ARM_CLIENT_ID/SECRET/TENANT_ID) Includes default model definitions for Claude, Llama, GPT-5, and Gemini models available through Databricks pay-per-token endpoints. Closes anomalyco#7983
Contributor
|
The following comment was made by an LLM, it may be inaccurate: No duplicate PRs found |
Add Azure CLI as a fallback authentication method for Azure Databricks workspaces (.azuredatabricks.net). When no explicit credentials are provided, attempts to use 'az account get-access-token' if logged in. Also updates default models to current Databricks Foundation Model API offerings (Claude 3.7/4/4.5, Llama 3.1/3.3/4).
The default models were being added as ModelsDev.Model objects directly, but input.models expects Provider.Model objects with capabilities, api, and other transformed properties. Add toProviderModel() helper to properly transform models, matching the fromModelsDevModel() pattern used elsewhere.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Adds Databricks Foundation Model APIs as a new provider, enabling opencode users to connect to their Databricks workspace's pay-per-token LLM endpoints.
Fixes #7983
Changes
provider.ts): Full Databricks provider with OpenAI-compatible endpoint support at/serving-endpointsauth.ts): Added Databricks to auth login flow with clear authentication instructionspreload.ts): Clear Databricks env vars between testsdatabricks.test.ts): 12 tests covering config parsing, auth precedence, URL handling, and model capabilitiesAuthentication Methods
Supports three auth methods (in priority order):
DATABRICKS_TOKENoropencode auth loginDATABRICKS_CLIENT_ID+DATABRICKS_CLIENT_SECRETARM_CLIENT_ID+ARM_CLIENT_SECRET+ARM_TENANT_IDDefault Models
Includes default definitions for common Foundation Model API endpoints (Claude, Llama, GPT-5, Gemini). Users can add custom model endpoints via
opencode.json.Verification
bun test packages/opencode/test/provider/databricks.test.ts