Repository navigation
feat(ai): add UberLLM memory provider preset - #505
Merged
Merged
Conversation
3 tasks done
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds an optional UberLLM memory provider preset on the existing OpenAI Chat Completions transport, following the merged Standard Compute preset in #502 (and CloudGPU in #470). UberLLM is an OpenAI-compatible gateway with one key for many models; model ids keep the vendor prefix.
memoryProvider: "uberllm": endpoint defaulthttps://api.uberllm.dev/v1, model defaultdeepseek/deepseek-v4-flash,UBERLLM_API_KEYfallback, explicitenv://key configuration, and a distinctuberllmsession tag.memory-provider-presets.ts, so key-only configs resolve model and endpoint and readiness works the same as the other presets. Factory, types, config template, example config and all README languages updated.tool_choice: "required"), tool response extraction, overrides, environment-key resolution, and rejection of remote-provider changes from project configuration.https://api.uberllm.dev). Per-model prices: https://uberllm.dev/models.Test plan
UberLLMProvider.executeToolCallagainst the live API with a config built bybuildMemoryProviderConfig({ memoryProvider: "uberllm", memoryApiKey })and a forcedsave_memoriestool. Default modeldeepseek/deepseek-v4-flashreturnedsuccess: truewith the tool arguments parsed ({"memory":"User prefers pnpm over npm for their repository."})."forceToolChoice": falseis documented for models that reject forced tool calls.Checklist
main(do not open PRs from commits already onmain)bun testpasses: ran the touched files only (tests/uberllm-provider.test.ts,tests/ai-provider-config.test.ts,tests/config-resolution.test.ts, plusstandardcompute/cloudgpuprovider tests): 89 pass, 0 fail. Full suite not run locally.bun run typecheckpassesbun run checkpasses for the changed files:prettier --checkclean,eslint --max-warnings=0clean,tsc --noEmitcleanI work on UberLLM.
🤖 Generated with Claude Code