feat: todo lists, permission modes, project instructions, and agent robustness

- Add todo_write tool with live checklist rendering in the UI
- Add permission modes (default/plan/auto-edit/auto-accept) cycled via Shift+Tab or /perm
- Load CLAUDE.md/AGENTS.md as project instructions into the system prompt
- Forward sub-agent tool calls/results to parent UI panel
- Auto-compact context mid-turn and keep model moving with a synthetic user turn
- Prune older image_url parts to cap vision token cost
- Idle-abort guard for stalled streaming backends
- Improve background bash jobs, kill whole process trees on timeout/exit
- Expand hooks: command/http hooks, blocking, JSON outputSchema
- MCP: JSON schema → Zod conversion, parallel connection, duplicate server detection
- Add tests for loop, confirmFn, projectInstructions, readFile, bash, todoWrite, contextWindowCache

package.json

@@ -35,6 +35,7 @@
     "marked-terminal": "^7.3.0",
     "openai": "^6.45.0",
     "react": "^19.2.7",
+    "tree-kill": "^1.2.2",
     "zod": "^4.4.3"
   },
   "devDependencies": {