refactor(server): shared layer-split backend + GGUF inspection + c2-gate plumbing

server/CMakeLists.txt

@@ -217,6 +217,7 @@ add_library(dflash_common STATIC
     src/draft/draft_gguf_loader.cpp
     src/draft/draft_safetensors_loader.cpp
     src/draft/draft_graph.cpp
+    src/qwen3/anchor_scan.cpp
     src/qwen3/qwen3_drafter.cpp
     src/qwen3/qwen3_loader.cpp
     src/qwen3/qwen3_graph.cpp
@@ -576,6 +577,52 @@ if(DFLASH27B_TESTS)
         target_link_libraries(test_bandit_integration PRIVATE dflash_common)
         add_test(NAME bandit_integration COMMAND test_bandit_integration)
     endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_drafter_early_exit_score_range.cpp")
+        add_executable(test_drafter_early_exit_score_range
+            test/test_drafter_early_exit_score_range.cpp)
+        target_include_directories(test_drafter_early_exit_score_range PRIVATE
+            ${CMAKE_CURRENT_SOURCE_DIR}/src/common)
+        add_test(NAME test_drafter_early_exit_score_range
+            COMMAND test_drafter_early_exit_score_range)
+    endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_regime_router.cpp")
+        add_executable(test_regime_router
+            test/test_regime_router.cpp)
+        target_include_directories(test_regime_router PRIVATE
+            ${CMAKE_CURRENT_SOURCE_DIR}/src/common)
+        add_test(NAME regime_router
+            COMMAND test_regime_router)
+    endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_anchor_transitive.cpp")
+        add_executable(test_anchor_transitive
+            test/test_anchor_transitive.cpp
+            src/qwen3/anchor_scan.cpp)
+        target_include_directories(test_anchor_transitive PRIVATE
+            ${CMAKE_CURRENT_SOURCE_DIR}/src/qwen3)
+        add_test(NAME test_anchor_transitive
+            COMMAND test_anchor_transitive)
+    endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_drafter_warm_path_regression.cpp")
+        add_executable(test_drafter_warm_path_regression
+            test/test_drafter_warm_path_regression.cpp)
+        target_include_directories(test_drafter_warm_path_regression PRIVATE
+            ${CMAKE_CURRENT_SOURCE_DIR}/src/common)
+        add_test(NAME test_drafter_warm_path_regression
+            COMMAND test_drafter_warm_path_regression)
+    endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_drafter_tail_capture_guard.cpp")
+        # GREEN phase: built with TAIL_GUARD_USE_NEW_FORMULA — must pass after Bug #42 fix.
+        add_executable(test_drafter_tail_capture_guard
+            test/test_drafter_tail_capture_guard.cpp)
+        target_compile_definitions(test_drafter_tail_capture_guard PRIVATE
+            TAIL_GUARD_USE_NEW_FORMULA)
+        add_test(NAME test_drafter_tail_capture_guard
+            COMMAND test_drafter_tail_capture_guard)
+        # RED phase binary: same source WITHOUT the fix flag — documents the bug.
+        add_executable(test_drafter_tail_capture_guard_red
+            test/test_drafter_tail_capture_guard.cpp)
+        # No TAIL_GUARD_USE_NEW_FORMULA — uses old (buggy) guard, expected to FAIL.
+    endif()
     if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_draft_vs_reference.cpp")
         add_executable(test_draft_vs_reference test/test_draft_vs_reference.cpp)
         target_link_libraries(test_draft_vs_reference PRIVATE dflash_common)

server/README.md

@@ -306,6 +306,8 @@ tokens) is the path to bring code recall to the same ratio as prose.
 
 ## Quick start
 
+> **Looking for the prebuilt Docker image?** See [Quick start](../README.md#quick-start) in the top-level README — `ghcr.io/luce-org/lucebox-hub:cuda12` ships the dflash daemon, Python server, and all weights bind-mountable from the host. The instructions below are for building dflash from source (kernel development, custom arch lists, non-Docker hosts).
+
 ```bash
 git clone --recurse-submodules https://github.com/Luce-Org/lucebox-hub
 cd lucebox-hub/dflash