Skip to content

feat(ai): add UberLLM memory provider preset - #505

Merged
EyJunge1 merged 3 commits into
tickernelz:mainfrom
al-global-tech:add-uberllm-provider
Nov 18, 2026
Merged

EyJunge1 merged 3 commits into
tickernelz:mainfrom
al-global-tech:add-uberllm-provider

Conversation

@al-global-tech

Copy link
Copy Markdown
Contributor

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 default https://api.uberllm.dev/v1, model default deepseek/deepseek-v4-flash, UBERLLM_API_KEY fallback, explicit env:// key configuration, and a distinct uberllm session tag.
  • Registered in 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.
  • Tests mirror the Standard Compute ones: authentication, request serialization (tool_choice: "required"), tool response extraction, overrides, environment-key resolution, and rejection of remote-provider changes from project configuration.
  • No defaults change for existing users. Users opt in with their own key (https://uberllm.dev/signup, prepaid, no monthly fee; docs at https://uberllm.dev/docs/quickstart). The docs name the destination for conversation data (https://api.uberllm.dev). Per-model prices: https://uberllm.dev/models.

Test plan

  • Exercised the change locally: ran UberLLMProvider.executeToolCall against the live API with a config built by buildMemoryProviderConfig({ memoryProvider: "uberllm", memoryApiKey }) and a forced save_memories tool. Default model deepseek/deepseek-v4-flash returned success: true with the tool arguments parsed ({"memory":"User prefers pnpm over npm for their repository."}).
  • Known limitations: same as other OpenAI-compatible presets; "forceToolChoice": false is documented for models that reject forced tool calls.

Checklist

  • Branch is based on main (do not open PRs from commits already on main)
  • bun test passes: ran the touched files only (tests/uberllm-provider.test.ts, tests/ai-provider-config.test.ts, tests/config-resolution.test.ts, plus standardcompute/cloudgpu provider tests): 89 pass, 0 fail. Full suite not run locally.
  • bun run typecheck passes
  • bun run check passes for the changed files: prettier --check clean, eslint --max-warnings=0 clean, tsc --noEmit clean
  • Docs / README updated when behavior or contribution process changes

I work on UberLLM.

🤖 Generated with Claude Code

@EyJunge1
EyJunge1 merged commit ff91c6b into tickernelz:main Nov 18, 2026
8 of 9 checks passed
@EyJunge1 EyJunge1 mentioned this pull request Nov 18, 2026
3 tasks done
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants