Conversation
Add env-var-driven basePath and backend URL to Next.js configs so the same code works both locally (no env vars = original behavior) and behind nginx on port 443 with path-based routing. Source changes (backward-compatible, 4 lines): - next.config.ts: basePath from NEXT_PUBLIC_BASE_PATH env var - next.config.ts: typescript.ignoreBuildErrors for agent-ui-kit - VoiceClient.tsx: DEFAULT_BACKEND_URL from NEXT_PUBLIC_BACKEND_URL - VideoAvatarClient.tsx: same AGENT.md: full production deployment guide covering nginx config, PM2 ecosystem setup, build commands, and key gotchas (^~ for regex blocks, runtime env vars for basePath, PM2 Python workaround). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive guide for working across agent-samples, agent-toolkit, and agent-ui-kit repositories. Includes workflow for editing each repo, package management, git hooks documentation, and architecture notes.
Rename directories to better describe their architecture: - simple-voice-client → simple-voice-client-no-backend - complete-voice-client → simple-voice-client-with-backend Update all references in README.md, AGENT.md, and AI_SAMPLES_UIKIT_TOOLKIT_DEV.md
- Add URL parameter reading to voice and video clients for profile selection - Fix MLLM url and turn_detection fields to return proper values instead of null - Standardize Anam avatar configuration to use production endpoint - Remove special case handling for Anam avatar vendor - Use consistent API key and avatar ID field names across vendors
Added comprehensive section to prevent common config translation errors: - Profile-based variable naming explanation (VOICE_ prefix requirement) - Critical warning: MLLM_LOCATION not MLLM_REGION - Example translations from base variables to profile variables - Debugging guide for RTM -11033 errors (agent creation failure) - Complete required variables list for Gemini Live MLLM This helps AI assistants correctly translate user-provided configs without changing variable names or missing required prefixes. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- Remove beta endpoint handling for anam - Use standard production endpoint for all avatar vendors - Update avatar params: add anam_base_url to anam config - Use APP_ID for token (not empty string for anam) - Remove X-Request-Id header requirement - Update .env.example with anam production settings - Remove ANAM_AGENT_ENDPOINT and ANAM_BASE_URL from config
Add configurable LLM style, vendor, and greeting_configs fields to the agent payload so simple-backend can work with custom LLM servers and MCP memory servers. Document both as optional advanced features.
digitallysavvy
approved these changes
Apr 10, 2026
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
3 participants
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.
No description provided.