fix(dashboard): support Anthropic provider in LLM health check - #1
Open
Milofax wants to merge 4 commits into
Open
fix(dashboard): support Anthropic provider in LLM health check#1Milofax wants to merge 4 commits into
Milofax wants to merge 4 commits into
Conversation
Both UI and MCP server now install graphiti-core from the same source, preventing version mismatches in the shared FalkorDB.
The data volume mount inherits root ownership, preventing the non-root appuser from writing credentials.yaml and .secret_key. Pre-create the directory with correct ownership in the image.
The health check previously only supported OpenAI-compatible APIs by querying /models. Anthropic APIs don't have this endpoint, causing the LLM status to always show "Model Not Found" or "Unreachable" when using Claude via Anthropic-compatible proxies. Now check_model_availability accepts a provider parameter: - openai (default): queries /models to verify the model exists - anthropic: performs a connectivity check to the base URL Both the LLM and embedder checks now pass their provider from config.yaml, so mixed setups (e.g. Anthropic LLM + Ollama embedder) work correctly.
…vars The /config/llm/status and /config/embedder/status endpoints (used by the frontend dashboard) were reading from env vars only, missing the actual provider configuration in config.yaml. This caused Anthropic LLM setups to always show Ollama's URL and "Model Not Found". Now _get_provider_config() reads config.yaml first (which has the correct provider, API URL, and model), falling back to env vars. The health check also supports Anthropic providers (connectivity check instead of /models query).
Collaborator
Author
|
Hey! Just a friendly check-in on this small fix — adds Anthropic provider support to the LLM health check dashboard. Let me know if you'd like any changes! |
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
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
check_model_availabilitynow accepts aproviderparameteranthropicproviders: connectivity check to base URL (no/modelsendpoint available)openaiproviders (default): existing/modelsquery unchangedProblem
When using an Anthropic-compatible LLM (e.g. Claude via proxy), the dashboard always shows "Model Not Found" or "Unreachable" because the health check queries
/models— an endpoint that doesn't exist on Anthropic APIs.Test plan