This repository was archived by the owner on May 26, 2026. It is now read-only.
Conversation
There was a problem hiding this comment.
Pull request overview
Fixes a regression where updating an agent’s model with a minimal payload on self-hosted Letta servers could drop persisted custom LLM/embedding endpoints (e.g., Ollama), breaking agents configured with custom endpoints.
Changes:
- Adds self-hosted-aware preservation logic to keep
llm_config.model_endpointandembedding_config.embedding_endpointintact when switching models. - Refactors base URL handling to be read dynamically from
process.env.LETTA_BASE_URL(instead of a module-level constant). - Adds Vitest regression coverage for self-hosted endpoint preservation and cloud minimal-update behavior.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
src/tools/letta-api.ts |
Preserves self-hosted LLM/embedding endpoint configs during model updates; introduces helper functions for handle parsing and preservation decisions. |
src/tools/letta-api.test.ts |
Adds regression tests covering self-hosted Ollama preservation and cloud minimal update payloads. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Author
|
Addressing the review feedback is pushed. Changes in the follow-up:
Validation:
|
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Context
Self-hosted Letta deployments can store custom model and embedding endpoints such as Ollama. Updating the model with a minimal payload was causing those saved endpoints to be dropped, which broke agents using Docker plus Ollama setups.
Testing