docs(brain): record v0.3.0 wiring work + verification + open caveats

brain/recent-decisions.md

@@ -1,6 +1,20 @@
 # Recent Decisions
 
-(No decisions in the last 30 days)
+## 2026-06-28 — Agentic OS v0.3.0 working-tree changes (committed 2026-07-25 as 94ce010)
+- Goal: make Agentic OS a complete local dev environment — build apps, programs, agents through the dashboard.
+- Added dynamic agent execution engine (cli/http/mcp) so new agents can be registered at runtime via `/api/agents/register` (persists to `data/agent-registry.json`).
+- Live agent registry + health: `/api/agents`, `check_agent()` dynamic per-registry config.
+- Integrations API (`/api/integrations` add/list) — e.g. webhook targets.
+- Agent-time tracking: `/api/agent-time` (+ recompute + skin), graphify-based session-gap estimate.
+- Agent stats + skill scoring persisted (`data/agent-stats.json`, `compute_skill_score`).
+- Kanban task delete + plugin uninstall endpoints wired.
+- Dashboard modernization: agent-health, plugins marketplace, smart-router, styles; added agent-time monitor page + terminal page.
+- Scheduler rewrite; `start.sh` / `start-agentic-os.sh` improvements.
+- New skills added: firebase-* (10), notion-knowledge-capture, xcode-project-setup, audit-test-plugin, test-plugin.
+- `.gitignore` extended to exclude runtime artifacts (pid, graphify-out, logs).
+- VERIFIED live: server on :8081, all new endpoints return 200; register/unregister persists correctly.
+- CAVEAT (not yet fixed): agent `check_command` runs via `subprocess.run(..., shell=True)` — command-injection risk if a malicious agent config is registered. Local-admin-only exposure; flag for later hardening.
+- CAVEAT: avoid running two `server.py` instances on the same port — registration on one won't show in reads served by the other.
 
 ## Archived (older than 30 days)