test(integration): PR-I.4 — wire new TBs into regression, retire tb_system_e2e

run_regression.sh replaces "System E2E (tb_system_e2e)" + "System E2E
USB_MODE=1 (FT2232H)" with the three PR-I subsuites (tb_system_opcodes,
tb_system_mechanics, tb_system_dataflow). SKIP count for --quick mode
bumped 5 -> 6 to match. "System Top USB_MODE=1 (FT2232H)" via
radar_system_tb.v is kept as a structural smoke test.

Dataflow gets --timeout=600 (vs 300 default). Its 18 ms sim takes
~430-450 s wall on this host; the 300 s default killed it at ~12.4 ms,
before the test logic block ran, yielding UNKNOWN. With 600 s, the TB
finishes cleanly and G2.2/G4.1/G4.2 all pass (3/3). The
matched_filter_multi_segment ST_WAIT_FFT hang documented in the TB
header still affects deeper coverage (G4.4 doppler, G5.x USB egress,
G9.x reset recovery), which remain deferred to PR-J.

tb_system_e2e.v removed (1294 lines) — coverage is fully replaced by
the focused subsuites; its USB_MODE=1 BFM was structurally broken
(wired only the FT601 ports, leaving the FT2232H DUT ports dangling),
which is why a USB_MODE=1 variant could "pass" without exercising the
production FT2232H path.

tb_usb_protocol_v2.v comment updated to point at tb_system_opcodes
for opcode-dispatch integration coverage.

9_Firmware/9_2_FPGA/tb/tb_usb_protocol_v2.v

@@ -17,7 +17,7 @@
 //      Catches future header-vs-body drift and confirms padding is skipped.
 //   5. PR-G G2 — MEDIUM ladder timing opcodes (0x17, 0x18) round-trip via
 //      cmd_opcode/cmd_value (the host_medium_*_cycles registers live in
-//      radar_system_top, exercised at integration level by tb_system_e2e).
+//      radar_system_top, exercised at integration level by tb_system_opcodes).
 // ============================================================================
 
 module tb_usb_protocol_v2;