fix(context): prevent context window exhaustion by removing base64 audio data

feat(tts): provide conversation history to text-to-speech tool

feat(tts): stream audio directly without file storage

feat(tools): add text-to-speech capability to agent

feat(ux): clear message input field after submission

refactor(app): streamline chat interface workflow and improve UX

refactor(chat): remove redundant tool decision feedback

fix(ui): improve chain of thought message flow

feat(ui): implement Chain of Thought display for agent reasoning

feat(chat): improve Claude audio transcription response

feat(agent): implement intelligent tool selection for audio transcription

feat(transcription): improve audio transcription workflow

feat(transcription): make Claude aware of transcription results

feat(transcription): replace file upload with URL-based transcription

feat(auth): prioritize environment variables for API keys

feat(ui): add GROQ API key input for transcription tool

feat(transcription): implement URL-based file serving for MCP tool

fix(transcription): resolve audio file processing issues with MCP client

fix(upload): resolve mp4 file upload validation issues

feat(transcription): add audio/video file transcription capabilities

fix(chat): resolve errors in Claude API integration

feat(chat): integrate Claude 3.7 Sonnet API for chat interface