fix(agents): custom model provider routing#2530
Merged
daryllimyt merged 1 commit intomainfrom Apr 15, 2026
Merged
Conversation
9ed4c6a to
067fd57
Compare
|
✅ No security or compliance issues detected. Reviewed everything up to a4388c9. Security Overview
Detected Code Changes
|
This comment has been minimized.
This comment has been minimized.
067fd57 to
a4388c9
Compare
daryllimyt
approved these changes
Apr 15, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 by cubic
Fixes custom model provider routing with a passthrough mode and always proxies LLM traffic through the local bridge. Drops the "openai/" prefix for custom providers in both runtime routing and credential injection for correct upstream routing.
Refactors
litellmwithcustom-model-provider+passthroughonAgentConfigandSandboxAgentConfig(propagated through workflow schemas/payloads).resolve_custom_model_provider_config_activityto loadbase_url, optionalmodel_name, andpassthroughfrom workspace credentials; applied in the durable workflow and management service.LLMSocketProxy: renamedlitellm_urltoupstream_url, addedpassthroughthat stripsAuthorizationand Anthropic-only fields before forwarding; proxy now always starts.openai/prefix forcustom-model-provider(runtime no longer maps to "openai"; gateway injects the rawmodelname).litellmwith optionalLITELLM_BASE_URL; frontend copy updated to reflect “aggregated” definitions.Migration
litellmprovider usage withcustom-model-provider.CUSTOM_MODEL_PROVIDER_BASE_URL(required), optionalCUSTOM_MODEL_PROVIDER_MODEL_NAME, andCUSTOM_MODEL_PROVIDER_PASSTHROUGH=trueto forward directly to your upstream.Written for commit a4388c9. Summary will update on new commits.