- Fix Hal chat: add Chat/Agent mode toggle so users can switch between
direct LLM streaming (Chat) and tool-using Agent mode
- Fix Agent system: graceful degradation when model can't follow
structured THOUGHT/ACTION/PARAMS format (falls back to direct answer
after 2 parse failures instead of looping 20 times)
- Fix frozen build: remove llama_cpp from PyInstaller excludes list
so LLM works in compiled exe
- Add system tray icon: autarch.ico (from icon.svg) used for exe icons,
installer shortcuts, and runtime tray icon
- Update tray.py to load .ico file with fallback to programmatic generation
- Add inline critical CSS for FOUC prevention
- Bump version to 1.5.1
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inlines dark theme colors, sidebar layout, and flex container styles
directly in <head> so they apply immediately. Prevents FOUC when the
external stylesheet is delayed by self-signed cert negotiation or
slow network.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Sidebar button at bottom re-scans modules/ directory on click
- POST /api/modules/reload endpoint returns updated counts and module list
- Button shows success/failure feedback, auto-reloads category pages
- Enables hot-dropping new modules without restarting the server
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Threat Monitor: 7-tab monitoring page (live, connections, network intel,
threats, packet capture, DDoS mitigation, counter-attack) with real-time
SSE streaming and optimized data collection (heartbeat, cached subprocess
calls, bulk process name cache)
- Drill-down popups: Every live monitor stat is clickable, opening a popup
with detailed data (connections list with per-connection detail view,
GeoIP lookup, process kill, bandwidth, ARP spoof, port scan, DDoS status)
- Hal agent mode: Chat routes rewritten to use Agent system with
create_module tool, SSE streaming of thought/action/result steps
- Windows defense module with full security audit
- LLM trainer module and routes
- Defense landing page with platform-specific sub-pages
- Clean up stale files (get-pip.py, download.png, custom_adultsites.json)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Includes ASCII banner, feature overview, architecture docs, acknowledgements
for all open-source dependencies, and essays by darkHal Security Group on
AI liberty, hacker ethics, and geopolitics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Full security platform with web dashboard, 16 Flask blueprints, 26 modules,
autonomous AI agent, WebUSB hardware support, and Archon Android companion app.
Includes Hash Toolkit, debug console, anti-stalkerware shield, Metasploit/RouterSploit
integration, WireGuard VPN, OSINT reconnaissance, and multi-backend LLM support.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
