Fix voice drops, integrate WorldMonitor, add self-upgrade brain + HUD overhaul#32
Open
futureworldvision842-lgtm wants to merge 1 commit into
Conversation
… overhaul Voice (root-cause fix for mid-sentence cut-outs): - Add session_resumption + context_window_compression to the Gemini Live config so the server no longer closes the socket mid-sentence; switch to the stable gemini-2.5-flash-native-audio-latest model and fix the PCM mime type. - Capture resumption handles and reconnect seamlessly; don't count resumable drops as failures toward offline fallback. - Smooth playback (coalesce chunks + high-latency buffer) to kill audio stutter; add a mic echo-cooldown to stop false interruptions. WorldMonitor integration (koala73/worldmonitor): - New world_monitor tool/action: 60+ curated RSS feeds across 13 categories with parallel fetch + AI-synthesized spoken brief; Islamabad weather + world outlook. - New "WORLD MONITOR" HUD tab with category buttons, live headlines, weather and situation/outlook panels (auto-refresh). Self-upgrade brain: - skills/ dynamic plugin system (loader auto-registers any MANIFEST+run module). - self_upgrade action: Gemini generates a new skill, validated + compile-checked (with destructive-pattern guardrail) before install; live on next restart. HUD frontend overhaul: - Rebrand MARK XXXIX -> "Muhammad's Jarvis" (title/header/footer). - Live WhatsApp connection badge; PC DIAGNOSTICS panel that flags real problems (CPU/RAM/disk/temp/down services); fix task-list rendering bug. Other: - Prompt: shortcut-learning (save_memory) + register world_monitor/self_upgrade. - Boot launcher (start_jarvis_boot.bat) + add .gitignore (excludes api key, logs, caches, scratch clones, media). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
1 participant
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.
Summary
Major reliability + capability upgrade for the Jarvis voice assistant.
🎙️ Voice (root-cause fix for mid-sentence cut-outs)
session_resumption+context_window_compressionto the Gemini Live config so the server no longer closes the socket mid-sentence; switch to stablegemini-2.5-flash-native-audio-latest; fix PCM mime type.🌍 WorldMonitor integration (koala73/worldmonitor)
world_monitortool/action: 60+ curated RSS feeds across 13 categories, parallel fetch + AI brief, Islamabad weather + world outlook.🧠 Self-upgrade brain
skills/dynamic plugin system (auto-registers anyMANIFEST+runmodule).self_upgradeaction: Gemini generates a new skill, validated + compile-checked (with destructive-pattern guardrail) before install; live on next restart.🖥️ HUD frontend overhaul
Other
save_memory; registeredworld_monitor/self_upgrade.start_jarvis_boot.bat; add.gitignore(excludes API key, logs, caches, scratch clones, media).Reviewer notes
config/api_keys.jsonis intentionally git-ignored (contains a live API key) — never committed.🤖 Generated with Claude Code