feat(DATAGO-126654): implement dynamic model provider configuration and support [4/4]#1200
Open
cyrus2281 wants to merge 30 commits intocyrus/DATAGO-126654/servicesfrom
Open
feat(DATAGO-126654): implement dynamic model provider configuration and support [4/4]#1200cyrus2281 wants to merge 30 commits intocyrus/DATAGO-126654/servicesfrom
cyrus2281 wants to merge 30 commits intocyrus/DATAGO-126654/servicesfrom
Conversation
…o SAM_FEATURE_MODEL_CONFIG_UI
…agement - Added BootstrapRequestListenerComponent to handle model config bootstrap requests. - Introduced dynamic model provider topics for better topic management. - Enhanced PlatformServiceComponent to start a bootstrap listener based on feature flag. - Updated ModelConfigService to retrieve model configurations by alias or ID. - Added FastAPI dependencies for accessing component instances.
mo-radwan1
reviewed
Mar 17, 2026
| # Note: self.max_message_size_bytes is already set by SamComponentBase | ||
|
|
||
| try: | ||
| self._component_id = "platform_service" |
Collaborator
There was a problem hiding this comment.
Would this cause platform to create queues similar to a gateway ? is that introduced for the model UI ?
Collaborator
Author
There was a problem hiding this comment.
Nope, it will only be used for a topic address and a topic subscription (without queue)
Base automatically changed from
solace-pjones/DATAGO-126600/database-schema-community-v2
to
main
March 19, 2026 15:22
…p request listener, dependencies, model config service, and repository
cyrus2281
commented
Mar 19, 2026
src/solace_agent_mesh/services/platform/api/routers/model_configurations_router.py
Show resolved
Hide resolved
src/solace_agent_mesh/services/platform/api/routers/model_configurations_router.py
Show resolved
Hide resolved
src/solace_agent_mesh/services/platform/services/model_config_service.py
Show resolved
Hide resolved
src/solace_agent_mesh/services/platform/components/dynamic_model_provider_listener.py
Outdated
Show resolved
Hide resolved
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.
What is the purpose of this change?
How was this change implemented?
This PR implements a comprehensive enterprise model configuration system:
Key commits:
Key Design Decisions
The design focuses on two key areas:
Model Configuration Management: Using a centralized platform service for model configuration with dynamic updates via A2A topics. This allows for:
WebUI Token Management: Implementing proactive token refresh to prevent 401 errors, especially with long-lived SSE connections that can't easily retry on token expiration.
How was this change tested?
Is there anything the reviewers should focus on/be aware of?
Reviewers should examine the LiteLlm model lifecycle management and how the model configuration flows through the system. The WebUI proactive token refresh implementation is also significant for eliminating 401 errors during long SSE sessions.