UPDATE: Switch landing page to use VoiceCal LinkedIn diagram

FIX: Correct CSS syntax error in VoiceCal LinkedIn diagram

FEATURE: Add "Try VoiceCal Live" buttons to LinkedIn diagram

DOCS: Create VoiceCal LinkedIn diagram from ChatCal version

SECURITY: Remove sensitive API key logging from startup

CHANGE: Remove in-person meetings, require meeting format

FEATURE: Add phone call meeting type (no Google Meet)

FEATURE: Enforce one meeting per session and improve exit flow

FIX: Prevent phone numbers from being extracted as times

REBRAND: Change ChatCal to VoiceCal in system prompt

FIX: Update OAuth redirect URI to port 8080 for local development

COPY: Update description to "interactive AI speechbot"

COPY: Update description from chatbot to voicebot

REBRAND: Update UI from ChatCal.ai to VoiceCal.ai

FIX: Correct time extraction for 4-digit times with AM/PM (e.g., 1120 AM)

FIX: Remove unnecessary name confirmation for implicit extraction

REVERT: Restore max_iterations to 15 (from 25)

FIX: Add implicit name extraction for statements like "Juan Valdez."

IMPROVE: Smart name parsing and increased max iterations

UX: Add back buttons to LinkedIn diagram and fix instruction visibility

FEATURE: Add Phase 3 Speech-to-Speech to LinkedIn Diagram

SECURITY: Enhance API key protection and update .env.example

FEATURE: Add LinkedIn diagram and improve chat widget UX

VERSION: Bump to 1.1.0 for Google Calendar tool restoration

🎉 MAJOR FIX: ReAct-compatible prompt enables actual tool calling

FIX: Resolve event loop cleanup issues in WorkflowHandler

FIX: Proper async event loop handling for WorkflowHandler

PROMPT: Add explicit tool calling instructions

FIX: Implement proper async WorkflowHandler pattern

FIX: Use synchronous workflow iteration instead of async

RESTORE: Tool calling functionality by removing direct LLM bypass

CRITICAL FIX: Stop LLM from echoing user context in responses

FIX: Prevent STT garbage from corrupting user names

VERSION: Bump to 2.0.17-direct-llm-bypass

BYPASS FIX: Direct LLM call to avoid WorkflowHandler async issues

VERSION: Bump to 2.0.16-workflow-iteration-fix

ALTERNATIVE FIX: Capture workflow response during iteration instead of .result()

VERSION: Bump to 2.0.15-async-workflow-fix

CRITICAL FIX: Resolve async workflow handler result extraction

VERSION: Bump to 2.0.14-stt-working - STT functionality restored

FIX: Server-side format conversion for Groq STT compatibility

VERSION: Bump to 2.0.13-stt-codec-fix

FIX: Use Groq-compatible audio codecs (AAC for MP4, Opus for OGG)

VERSION: Bump to 2.0.12-stt-smart-format

FEATURE: Smart MediaRecorder format detection for Groq STT compatibility

TEST: Try opus filename extension for Groq STT compatibility

VERSION: Bump to 2.0.11-stt-direct-blob

CRITICAL FIX: Use original WebM blob directly for STT transcription

VERSION: Bump to 2.0.10-stt-inline-conversion

FIX: Inline base64 to blob conversion for STT audio data