fix(ci): flush profraw coverage data in E2E teardown (#550)

The ironclaw binary only handles SIGINT (via tokio::signal::ctrl_c),
not SIGTERM. When conftest.py sent SIGTERM during teardown, the OS
killed the process immediately without running atexit handlers, so
LLVM never flushed .profraw files. cargo llvm-cov report then found
zero profraw files and failed.

- Send SIGINT instead of SIGTERM so the existing ctrl_c handler
  triggers graceful shutdown → main() returns → atexit runs → profraw
  flushed
- Increase shutdown wait from 5s to 10s for graceful cleanup
- Add a diagnostic step to verify profraw files exist before the
  report step, making future issues visible in CI logs

Co-authored-by: Claude Opus 4.6 <[email protected]>

tests/e2e/conftest.py

@@ -133,9 +133,12 @@ async def ironclaw_server(ironclaw_binary, mock_llm_server):
         )
     finally:
         if proc.returncode is None:
-            proc.send_signal(signal.SIGTERM)
+            # Use SIGINT (not SIGTERM) so tokio's ctrl_c handler triggers a
+            # graceful shutdown.  This lets the LLVM coverage runtime run its
+            # atexit handler and flush .profraw files for cargo-llvm-cov.
+            proc.send_signal(signal.SIGINT)
             try:
-                await asyncio.wait_for(proc.wait(), timeout=5)
+                await asyncio.wait_for(proc.wait(), timeout=10)
             except asyncio.TimeoutError:
                 proc.kill()