OpenCode-style TUI, model probing, sandboxed auto approval

- TUI: centered home screen with logo, boxed input with mode line, sidebar
  (>=120 cols), Ctrl+P palette, Tab Build/Plan, Shift+Tab approval cycle,
  mouse (cards, cursor, pickers, wheel), /sidebar /mouse /approval
- /models probing: key check on entry (401 re-asks), API models in /model
- Shell sandbox in C: Linux Landlock (writes limited to workspace/tmp,
  ABI>=4 blocks TCP), macOS sandbox_init, rules fallback elsewhere
- Approval modes ask/auto/yolo (default auto); read-only command whitelist;
  ask to rerun outside the sandbox when a command looks blocked
- Upgradable bootstrap scripts (git pull --ff-only, rebuild, reinstall) and
  cst-agent-update; cst-agent --version
- tests: test_sandbox, test_models

include/cst_tools.h

@@ -40,6 +40,7 @@ typedef struct cst_tool_ctx {
   /* todo_write: the list was replaced (text form, one item per line). */
   void (*set_todo)(const char *text, void *ud);
   void *todo_ud;
+  int sandbox; /* run_shell: confine to the workspace (cst_sandbox.h) */
 } cst_tool_ctx_t;
 
 typedef int (*cst_tool_run_fn)(const cst_tool_ctx_t *ctx,