refactor: migrate weather provider to Open-Meteo, improve location extraction, and inject server time into persona context

fix: correct wttr.in endpoint usage and improve timezone resolution logic for diverse location inputs

feat: add support for immediate camera trigger and bypass LLM generation in think loop

feat: update capture_camera_image to trigger frontend camera modal via marker string

feat: add interactive webcam modal for photo capture and file uploads

refactor: update ASR sample source to local static file

feat: implement camera capture tool to enable vision capabilities via ffmpeg

feat: enhance service warmups with real-data validation and add VLM and SearXNG initialization steps

refactor: require essential environment variables by raising RuntimeErrors instead of using default values

refactor: relocate audio and perception logic to core module and remove legacy ui components

refactor: standardize ASR endpoint to /transcribe and update MiniCPM-V dependency and video decoding logic

feat: migrate ASR backend to Modal Nemotron endpoint with language support

feat: add crypto price tracking tool and update persona architecture documentation

refactor: replace external memory backend with custom sqlite-vec storage engine featuring RRF search and Ebbinghaus decay

refactor: remove redundant self-import in core/memorize.py

refactor: remove redundant LLAMA_MODEL configuration from memorize and think modules

refactor: encapsulate memory management into AikoMemorize class and remove deprecated sqlite-vec implementation details from core/memorize.py

chore: update default USER_ID from OppaAI to Guest

refactor: enable multi-user session support by mapping system prompts and histories to user IDs

feat: implement asynchronous network warmup on login to improve serverless responsiveness

refactor: increase llama context window, remove redundant output format parameter, and add error logging to MioTTS requests

refactor: remove redundant lib2to3 imports from wakeup.py

refactor: update TTS preset and warmup request parameters and add unnecessary imports

refactor: update warmup request to use MIOTTS endpoint instead of ASR transcribe

fix: update TTS endpoint path to v1/tts/file

fix: correct typo in ui.listen module import path and references

fix: escape raw string for VRM UI and correct module import path for ASR functionality

refactor: replace health polls with real inference requests and add ASR warmup to boot sequence

refactor: scope memory management and system prompts to individual user_id sessions throughout the chat pipeline

refactor: update LLM warmup, optimize audio handling by removing conversion, and refine VRM animation API

refactor: replace Fish Speech Modal server with Aiko boot orchestrator for parallel subsystem initialization

refactor: replace local boot orchestration logic with Modal deployment setup for Fish Speech TTS

Add user_id via login

feat: add crypto price tool and update timezone logic to use local system zoneinfo

feat: migrate web search implementation from DuckDuckGo to SearXNG JSON API

refactor: replace SearXNG with DuckDuckGo search and add support for custom search endpoints

Fix eror

Fix error

Fix sanitize query

Fix LLM call URL

Fix wrong llm url

Update tool call

Update tools

Add more simple tools

Add tools call

Delete core/reflect.py

Remove obsolete stuffs

Delete core/listen.py

Delete core/dream.py

Delete core/silence.py