• CHANGELOG.md
  • Added Alexa voice integration via /alexa endpoint with session buffering and localized responses (Add Alexa skill integration and preserve env vars #52).
  • Added Health check system monitoring: disk usage alerts, automatic log rotation, and backup freshness checks (Expand health check with system monitoring #47).
  • Added System prompt injection via --append-system-prompt at runtime instead of copying to ~/.claudio/ (Inject system prompt via --append-system-prompt at runtime #50).
  • Changed Typing indicator to use record_voice action for voice messages and refreshes every 4s (was 15s) (Improve typing indicator with record_voice and 4s refresh #57).
  • Changed Typing indicator loop to no longer cap at 15 minutes — runs while parent process lives (Improve typing indicator with record_voice and 4s refresh #57).
  • Changed preservation of unmanaged env vars (e.g. HASS_TOKEN, ALEXA_SKILL_ID) across claudio_save_env calls (Preserve unmanaged env vars across claudio_save_env calls #53).
  • Changed export of CLAUDIO_DB_FILE, CLAUDIO_PATH, and MEMORY_ENABLED for subprocess access (Export env vars needed by subprocesses #49).
  • Changed Telegram message sending to retry without reply_to_message_id when reply fails (Add Alexa skill integration and preserve env vars #52).
  • Removed Orphan process detection from health check — no longer needed with native Claude Task tools and KillMode=mixed (Remove orphan process detection from health check #55).
  • Fixed Silent backup failures by detecting unmounted drives before rsync and in health check freshness monitoring (Fix silent backup failures: retry alerts, detect unmounted drives #54).
  • Fixed Webhook handler timeout (600s) restoration — accidentally removed, causing potential indefinite thread blocking (Add Alexa skill integration and preserve env vars #52).
  • Fixed Typing indicator curl calls to have --connect-timeout 5 --max-time 10 to prevent hung background processes (Improve typing indicator with record_voice and 4s refresh #57).
  • Fixed Token usage not persisted to SQLite because CLAUDIO_DB_FILE was not exported (Export env vars needed by subprocesses #49).
  • Fixed ELEVENLABS_MODEL and MAX_HISTORY_LINES not persisted across restarts (Sync README and config with actual code #46).
  • Added Security for Alexa request authentication: X.509 certificate chain validation, SHA-256 signature verification, 150s timestamp replay window, skill ID check (Add Alexa skill integration and preserve env vars #52).
  • Added Security for Alexa endpoint to fail closed when cryptography library is unavailable (Add Alexa skill integration and preserve env vars #52).

• The changelog was reviewed by two Opus subagents: a Technical Documentation Writer and a Senior Software Architect.
• Key fixes were applied to the changelog based on review feedback, including moving 'orphan process detection removed' from Fixed to Removed.
• A Security section was added to the changelog for the Alexa authentication stack.
• Missing entries for WEBHOOK_TIMEOUT restoration, reply_to fallback, and env var persistence were added to the changelog.
• A misleading 'exponential backoff' claim was removed from a backup fix description in the changelog.
• Redundant entries for issues Fix silent backup failures: retry alerts, detect unmounted drives #54 and Improve typing indicator with record_voice and 4s refresh #57 were merged within the changelog.

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.