LLM Integration
Developmentllm-integrationLLM Integration is an Agent Skill for development published in the rapidaai/voice-ai repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Add or modify integration-api LLM providers with caller factory wiring, unified provider routing, streaming behavior, and metric/audit compatibility.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/rapidaai/voice-ai/blob/HEAD/.codex/skills/llm-integration/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/llm-integration, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
LLM Integration Skill
Mission
Add provider callers for chat/stream/verify (plus optional embedding/reranking) with consistent metrics and routing.
Inputs expected from user
- Required capabilities: chat, stream, verify, embedding, reranking.
- Auth and endpoint model.
- Model parameter/tool-calling constraints.
If missing:
- Implement chat + stream + verify first.
- Add embedding/reranking only if provider supports them.
Hard boundaries
In scope:
api/integration-api/internal/caller/<provider>/...api/integration-api/internal/caller/caller.goapi/integration-api/internal/type/callers.goif interfaces changeapi/integration-api/api/unified_provider.gopkg/clients/integration/integration_client.goif routing updates are needed- provider model metadata in
ui/src/providers/<provider>/...
Out of scope:
- assistant-api telephony/STT/TTS/EOS/VAD internals
Implementation workflow
- Build provider caller package (
llm,verify-credential, optional embedding/reranking). - Register in caller factory switches.
- Ensure unified provider endpoint behavior is consistent.
- Keep MetricBuilder lifecycle consistent (
TIME_TAKEN,STATUS). - Add tests for success/failure and stream completion.
- Update provider model metadata where required.
Validation commands
go test ./api/integration-api/internal/caller/...go test ./api/integration-api/api/...go test ./pkg/clients/integration/..../skills/llm-integration/scripts/validate.sh --check-diff --provider <provider>
References
references/checklist.mdreferences/llm-checklist.mdexamples/sample.md