- deploy/requirements.txt: explicit pip deps (fastapi, uvicorn, aiomysql, aiohttp, anthropic, trafilatura)
- jarvis-deploy.sh: self-installs to /usr/local/bin/ on every run so updates propagate;
auto-creates venv and installs packages if missing before restart attempt
- admin/index.php: add SETUP button next to RESTART — runs full setup+start in one click
(creates venv, installs deps, copies reactor.py, starts it)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3
- Add _ollama_vision_call() using Ollama /api/generate with images array
- handle_screenshot: try llava first (free, on-LAN), fall back to Claude on error;
text-only snapshots now use ollama instead of groq
- handle_vision: same llava-first/Claude-fallback pattern; caller can force
provider='ollama' or 'claude' explicitly; stored provider_used reflects actual
provider that ran
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3
- reactor.py: fix OLLAMA_HOST .95 → .210 (actual Ollama VM IP)
- reactor.py: upgrade OLLAMA_MODEL 1b → 8b (llama3.1:8b has tool-calling, 131K ctx)
- reactor.py: guardian alerts and sitrep now use ollama instead of groq (free, on-LAN, no quota)
- config.example.php: same IP/model fixes + fix GROQ_MODEL_SEARCH to compound-beta-mini (groq/ prefix causes 404)
- deploy script: patch live config.php on every deploy to correct Ollama IP/model and Groq model name
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3
The admin panel restart command used shell_exec which runs /bin/sh (dash on
Ubuntu) — dash doesn't support 'source', so the venv never activated and the
reactor silently never started.
- admin/index.php: wrap restart in bash -c so 'source' works; try systemctl
first then fall back to nohup
- deploy/jarvis-arc.service: add proper systemd unit so reactor auto-starts
on boot and auto-restarts on crash
- deploy/jarvis-deploy.sh: install+enable service file when it changes; mkdir
log dir before restart; fall back to nohup if systemctl not set up yet
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3
- Add CREATE TABLE IF NOT EXISTS for guardian_config and guardian_events in
reactor lifespan so tables are created automatically on next restart
- Fix conversations column bug: reactor used 'message' but schema has 'content';
fix INSERT and SELECT queries to use content (SELECT aliases it as 'message'
so the JSON response key stays the same)
- Add guardian tables to schema.sql for documentation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3
Guardian anomaly alerts and SITREP are pure text reasoning — Groq's
llama-3.3-70b-versatile handles them at near-zero cost with lower
latency. Vision Protocol image analysis stays on Claude (claude-opus-
4-8) because Groq has no vision models. Text-only sysinfo snapshots
(no image captured) also move to Groq.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When deploy/reactor.py changes in a push, the deploy runner now copies it
to the runtime location and restarts jarvis-arc.service automatically.
Eliminates the two-copy drift problem — repo is now canonical.
Arc Reactor was running from /opt/jarvis-arc with no version tracking.
Added to deploy/ so all fixes (metrics_json→metric_data, flat JSON parsing,
disk mount key fix) are captured. WG configs are runtime-generated secrets
and must not be committed.
- deploy/jarvis-watchdog.sh: self-healing watchdog (every 5 min)
* monitors lsws/mysql/redis, restarts on failure
* JARVIS HTTP self-check, restarts OLS on 5xx
* disk/memory alerts inserted to DB
* offline Proxmox VM agents restarted via qm guest exec
* log rotation (1000 line cap)
- deploy/jarvis-deploy.sh: smart deploy with PHP validation
* php8.3 syntax check on every changed .php file
* auto-reverts git commit + inserts critical alert on syntax error
* reloads OLS after JARVIS deploys
- api/endpoints/facts_collector.php: site health monitoring
* curls all 7 managed sites every 3 min
* stores up/down status in kb_facts
- api/endpoints/alerts.php: auto-heal + site alerts
* dispatches restart_service commands when services down on agents
* generates alerts from kb_facts site health data
- public_html/install-agent.sh: one-liner Linux agent installer
* installs deps, downloads agent, registers with JARVIS, sets up systemd
- public_html/webhook.php: fixed infra deploy path to /opt/infra
myron