Makefile.cbm

# Makefile.cbm — Build system for pure C rewrite
#
# Usage:
#   make -f Makefile.cbm test           # Build + run all tests (ASan + UBSan)
#   make -f Makefile.cbm test-foundation # Foundation tests only (fast)
#   make -f Makefile.cbm test-tsan      # Thread sanitizer build
#   make -f Makefile.cbm cbm            # Production binary
#   make -f Makefile.cbm clean-c        # Remove build artifacts

# Compiler selection — override via: make CC=gcc CXX=g++
# macOS: cc (Apple Clang) — universal binary with ASan support
# Linux: gcc/g++ — system default with full sanitizer support
# CI scripts pass CC/CXX explicitly; don't rely on defaults here

# Target architecture (macOS): build.sh/test.sh export ARCHFLAGS="-arch <arch>"
# (see scripts/env.sh). Fold it into the compiler drivers with `override` so it
# reaches EVERY compile and link recipe — including the vendored objects below
# that use their own *_CFLAGS — and so it survives a command-line `CC=` override.
# ARCHFLAGS is empty on Linux/Windows and for native direct `make` invocations,
# leaving CC/CXX unchanged there.
override CC := $(CC) $(ARCHFLAGS)
override CXX := $(CXX) $(ARCHFLAGS)

# ── Common flags ─────────────────────────────────────────────────

# Include paths for:
#   src/         — new foundation headers
#   vendored/    — yyjson, xxhash, sqlite3
#   internal/cbm — existing extraction headers (cbm.h, helpers.h, etc.)
#   internal/cbm/vendored/ts_runtime/include — tree-sitter API
CBM_DIR = internal/cbm
TS_INCLUDE = $(CBM_DIR)/vendored/ts_runtime/include
# Vendored tree-sitter src/ contains unicode/ headers (umachine.h, utf.h, utf8.h).
# This ensures we use our vendored copies instead of requiring system libicu-dev.
TS_SRC = $(CBM_DIR)/vendored/ts_runtime/src

# GCC-only warning suppressions (Clang rejects unknown -Wno-* with -Werror).
# Detect GCC by checking for __GNUC__ without __clang__ — handles all versions.
IS_GCC := $(shell echo | $(CC) -dM -E - 2>/dev/null | grep -q '__GNUC__' && ! echo | $(CC) -dM -E - 2>/dev/null | grep -q '__clang__' && echo yes || echo no)
GCC_ONLY_FLAGS :=
ifeq ($(IS_GCC),yes)
GCC_ONLY_FLAGS := -Wno-format-truncation -Wno-unused-result \
                  -Wno-stringop-truncation -Wno-alloc-size-larger-than
endif

# -Wdate-time: with -Werror, any use of __DATE__/__TIME__/__TIMESTAMP__ fails the
# build. Build-time entropy is how one identical source tree produced a new hash
# on every compile (see the local patch in vendored/mimalloc/src/options.c) —
# once removed, it must not creep back through a new call site.
CFLAGS_COMMON = -std=c11 -D_DEFAULT_SOURCE -D_GNU_SOURCE -Wall -Wextra -Werror \
                -Wno-unused-parameter -Wno-sign-compare -Wdate-time \
                $(GCC_ONLY_FLAGS) \
                -Isrc -Ivendored -Ivendored/sqlite3 \
                -Ivendored/mimalloc/include \
                -I$(CBM_DIR) -I$(TS_INCLUDE) -I$(BUILD_DIR)/generated

CXXFLAGS_COMMON = -std=c++14 -Wall -Wextra -Werror \
                  -Wno-unused-parameter \
                  -I$(CBM_DIR) -I$(TS_INCLUDE)

# Test seams are OPT-IN, never opt-out. Some suites drive behaviour that only a
# test should be able to ask for (fork an orphan the watchdog must reap, publish
# a lease-ownership marker). That code has no production caller and reads exactly
# like malware to a generic classifier, so it must not be in a shipped binary.
# Opt-IN means the failure mode of forgetting the flag is a CLEAN binary rather
# than a leaky one — the opposite choice would make every future release depend
# on someone remembering. scripts/test.sh passes TEST_SEAMS=1 for the suites that
# need it; the test-runner always has them.
TEST_SEAM_DEFINE :=
ifeq ($(TEST_SEAMS),1)
TEST_SEAM_DEFINE := -DCBM_ENABLE_TEST_SEAMS=1
endif

# Production flags (CFLAGS_EXTRA allows CI to inject -DCBM_VERSION)
# CBM_BIND_TS_ALLOCATOR=1: bind the tree-sitter runtime to mimalloc (#424). Only
# the prod build uses mimalloc (MI_OVERRIDE=1); the test build is CRT+ASan, where
# binding would create an alloc/free mismatch, so the guard is prod-only.
CFLAGS_PROD = $(CFLAGS_COMMON) -O2 -DCBM_BIND_TS_ALLOCATOR=1 $(TEST_SEAM_DEFINE) \
              $(GLOBAL_OVERRIDE_DEFINE) $(MEMWASTE_CFLAGS) $(CFLAGS_EXTRA)
CXXFLAGS_PROD = $(CXXFLAGS_COMMON) -O2 $(MEMWASTE_VENDOR_CFLAGS)

# Test flags: debug + sanitizers (override SANITIZE= to disable on Windows)
SANITIZE = -fsanitize=address,undefined -fno-omit-frame-pointer
EDITOR_TEST_DEFINES = -DCBM_JSON_LIKE_ENABLE_TEST_API=1 \
	-DCBM_TOML_EDIT_ENABLE_TEST_API=1 -DCBM_YAML_ENABLE_TEST_API=1 \
	-DCBM_TEXT_EDIT_ENABLE_TEST_API=1 -DCBM_CLI_ENABLE_TEST_API=1 \
	-DCBM_CONFIG_EDIT_PATH_ENABLE_TEST_API=1 \
	-DCBM_DIAGNOSTICS_ENABLE_TEST_API=1 -DCBM_ENABLE_TEST_SEAMS=1
# The build system is the single source of truth for "is this binary
# instrumented": compiler-specific probes (__SANITIZE_ADDRESS__) miss
# clang's feature-check spelling and every non-ASan sanitizer, so the
# trap-UBSan leg once ran NATIVE timing budgets on an instrumented
# binary. Any non-empty SANITIZE ⇒ sanitized budgets everywhere.
ifneq ($(strip $(SANITIZE)),)
SANITIZED_DEFINE = -DCBM_SANITIZED_BUILD=1
else
SANITIZED_DEFINE =
endif
KOTLIN_DEDUP_TEST_DEFINE = -DCBM_KOTLIN_DEDUP_TEST_API=1
CALL_REFERENCE_LOOKUP_TEST_DEFINE = -DCBM_CALL_REFERENCE_LOOKUP_TEST_API=1
INCREMENTAL_TEST_DEFINE = -DCBM_INCREMENTAL_TEST_API=1
COVERAGE_MARKER_TEST_DEFINE = -DCBM_COVERAGE_MARKER_TEST_API=1
CFLAGS_TEST = $(CFLAGS_COMMON) $(EDITOR_TEST_DEFINES) $(SANITIZED_DEFINE) \
	$(KOTLIN_DEDUP_TEST_DEFINE) $(CALL_REFERENCE_LOOKUP_TEST_DEFINE) \
	$(INCREMENTAL_TEST_DEFINE) $(COVERAGE_MARKER_TEST_DEFINE) -g -O1 $(SANITIZE)
CXXFLAGS_TEST = $(CXXFLAGS_COMMON) $(SANITIZED_DEFINE) -g -O1 $(SANITIZE) $(CXX_STDLIB_FLAGS)

# TSan (can't combine with ASan)
TSAN_SANITIZE = -fsanitize=thread -fno-omit-frame-pointer
# CBM_SANITIZED_BUILD is unconditional here: this flag set exists only to build
# an instrumented binary. SANITIZED_DEFINE keys off $(SANITIZE), which TSan does
# not use (it has its own TSAN_SANITIZE), so the define was silently absent and
# every sanitized-budget branch compiled to its NATIVE value on this leg —
# exactly the failure the comment above SANITIZED_DEFINE describes for
# trap-UBSan, repeated on a leg that was never wired up.
#
# The same define now goes on EVERY instrumented flag set of our own code, C and
# C++ alike (CXXFLAGS_TSAN here, GRAMMAR_CFLAGS_TEST/TSAN below). Vendored flag
# sets are left alone: mimalloc, sqlite3, tre, zstd, lz4 and tree-sitter read no
# macro of ours.
CFLAGS_TSAN = $(CFLAGS_COMMON) $(EDITOR_TEST_DEFINES) $(KOTLIN_DEDUP_TEST_DEFINE) \
	$(CALL_REFERENCE_LOOKUP_TEST_DEFINE) $(INCREMENTAL_TEST_DEFINE) \
	$(COVERAGE_MARKER_TEST_DEFINE) \
	-DCBM_SANITIZED_BUILD=1 -g -O1 $(TSAN_SANITIZE)
CXXFLAGS_TSAN = $(CXXFLAGS_COMMON) -DCBM_SANITIZED_BUILD=1 -g -O1 \
                $(TSAN_SANITIZE)

# Windows needs ws2_32 (Winsock), psapi (GetProcessMemoryInfo), shell32
# (CommandLineToArgvW — the UTF-8 argv path in main.c, #423/#20), and
# advapi32 (owner-only activation-candidate ACLs), plus
# --allow-multiple-definition (MinGW CRT symbol clashes).
# Auto-detected via compiler; no manual override needed.
IS_MINGW := $(shell echo | $(CC) -dM -E - 2>/dev/null | grep -q 'define _WIN32 ' && echo yes || echo no)
WIN32_LIBS :=
# Route Windows allocations through mimalloc (#581). mimalloc's own static
# override is gated on _MSC_VER, which clang/MinGW never defines, so it
# compiled out and the CRT won the link: ordinary malloc went to the CRT heap,
# which keeps freed pages committed, leaving every allocator tuning in
# cbm_mem_init POSIX-only. --wrap redirects the same population of allocations
# that link-order override captures on POSIX, so the purge configuration
# finally applies here too. src/foundation/mem_override_win.c supplies the
# wrappers; its deallocating paths check mi_is_in_heap_region so a CRT-owned
# pointer can never reach mi_free (#424).
MIMALLOC_WRAP_SYMS := malloc calloc realloc free strdup strndup _msize \
                      _aligned_malloc _aligned_free
MIMALLOC_WRAP_FLAGS :=
ifeq ($(IS_MINGW),yes)
MIMALLOC_WRAP_FLAGS := $(foreach sym,$(MIMALLOC_WRAP_SYMS),-Wl,--wrap=$(sym))
endif
# Linux wraps a smaller set for MEASUREMENT only (see mem_override_posix.c):
# allocations already reach mimalloc here, but the profiler needs the same
# observation point as Windows or the platform comparison is not like-for-like.
# macOS ld has no --wrap, so it stays census-only.
IS_LINUX := $(shell uname -s 2>/dev/null | grep -q Linux && echo yes || echo no)
MIMALLOC_WRAP_SYMS_POSIX := malloc calloc realloc free strdup
MIMALLOC_WRAP_FLAGS_POSIX :=
ifeq ($(IS_LINUX),yes)
MIMALLOC_WRAP_FLAGS_POSIX := $(foreach sym,$(MIMALLOC_WRAP_SYMS_POSIX),-Wl,--wrap=$(sym))
endif
ifeq ($(IS_MINGW),yes)
# --no-insert-timestamp: the PE header otherwise carries the link wall clock, so
# two Windows builds of identical source are never byte-identical and every
# release is a brand-new file to a reputation system. Same motivation as the
# mimalloc __DATE__ patch; ELF and Mach-O have no equivalent field to clear.
WIN32_LIBS := -lws2_32 -lpsapi -lshell32 -ladvapi32 -lbcrypt -Wl,--allow-multiple-definition -Wl,--stack,8388608 -Wl,--no-insert-timestamp -static
endif

# STATIC=1 produces a fully static binary (for Alpine/musl portable builds)
ifeq ($(STATIC),1)
STATIC_FLAGS := -static
endif

# W^X: demand a non-executable stack on ELF. This is belt to the braces of the
# .note.GNU-stack annotation in vendored/nomic/code_vectors_blob.S — that note
# fixes the CAUSE (an unannotated object makes ld assume the worst for the whole
# link), this flag fixes the OUTCOME, and the composition gate proves it on the
# shipped artifact. ELF-only: Apple's ld rejects -z noexecstack outright and it
# is meaningless for PE, so it is gated rather than made "common".
#
# -z separate-code additionally keeps read-only DATA out of the executable
# segment. GNU ld enables it by default on x86-64 but NOT on aarch64, so the
# arm64 binaries emitted ONE R E PT_LOAD spanning the whole image: .rodata is
# correctly marked A (not AX), but the kernel applies SEGMENT permissions, so
# ~259 MB of tree-sitter parse tables was mapped executable at runtime while the
# amd64 build of the same source mapped them R only. That is a large ROP gadget
# surface for data that is never executed, and it is invisible to section flags.
#
# -z relro + -z now finish the same job on the OTHER writable-but-shouldn't-be
# region: the GOT. Both are free at runtime here (a static binary resolves
# everything at link time, so there is no lazy binding left to pay for), and
# they are added because the SHIPPED artifact measurably lacked the property --
# not because the linker accepts the flags. Measured on this binary, built the
# way .github/workflows/_build.yml builds the Linux release (STATIC=1, gcc 13.3
# / GNU ld 2.42, Ubuntu 24.04 aarch64); PT_GNU_RELRO ends at 0x11DA0000 in both:
#
#   without -z now:  .got 0x11d9ec20+0x13c8, .got.plt 0x11d9ffe8+0x40
#                    -> .got.plt ends at 0x11DA0028, i.e. 40 bytes PAST the
#                       window: those GOT slots stayed writable for the whole
#                       process lifetime, in every Linux binary we have shipped
#   with    -z now:  .got.plt folded into .got (0x11d9ec20+0x13c8, ends
#                    0x11D9FFE8) -> the whole GOT is inside the window and is
#                    re-mapped read-only after startup
#
# -z relro is already this toolchain's default and changes nothing here; it is
# named anyway so the property stops depending on one distro's spec file (the
# musl/portable and glibc-floor images are different toolchains, and a default
# is not a guarantee). A1c/A1d in scripts/ci/check-binary-composition.sh assert
# the OUTCOME on the produced binary, because a flag the compiler accepts is
# not evidence that the artifact gained anything -- the same reason A1 exists
# next to the .note.GNU-stack annotation.
ELF_HARDENING_FLAGS :=
ifeq ($(IS_LINUX),yes)
ifneq ($(IS_MINGW),yes)
ELF_HARDENING_FLAGS := -Wl,-z,noexecstack -Wl,-z,separate-code \
                       -Wl,-z,relro -Wl,-z,now
endif
endif

# MEMWASTE=1: the waste-sanitizer flavour (src/foundation/mem_events.h). Built
# like production -- -O2, mimalloc, the real allocator routing -- plus the event
# layer and its observers, because waste measured under ASan's allocator would
# describe ASan. Frame pointers stay so the macOS observer can walk to the
# caller. On Linux this is also what finally LINKS the --wrap observation shim:
# its flags and source were defined here but never reached a link line, so the
# Linux profiler had been reporting nothing.
#
# Every object is built this way, VENDORED ones included (grammars, the
# tree-sitter runtime, SQLite, tre, lz4, zstd, the C++ preprocessor): waste in
# a vendored parser is waste in this program. mimalloc alone is left as it is --
# its reads and writes are the allocator's own bookkeeping, not program data.
#
# MEMWASTE_ACCESS=1 adds the access lane (reads and writes of every tracked
# block through the compiler's load/store callbacks; clang only). It builds at
# -O1 without vectorisation: at -O2 the callbacks describe the OPTIMISED program,
# and reads the optimiser removed would be reported as never read.
# MEMWASTE_PROFILE=1 adds clang's execution counters (-fprofile-instr-generate)
# for the CPU scaling lane (scripts/memwaste-scaling.py).
# Each flavour needs its own BUILD_DIR: vendored objects are not rebuilt when
# only the flavour changes.
#
# The libc wrappers (mem_override_libc.c) need --wrap on Linux and Windows;
# macOS defines the symbols instead. STATIC=1 (musl) is not a memwaste target.
MEMWASTE ?= 0
MEMWASTE_ACCESS ?= 0
MEMWASTE_PROFILE ?= 0
ifeq ($(MEMWASTE_ACCESS),1)
override MEMWASTE := 1
endif
ifeq ($(MEMWASTE_PROFILE),1)
override MEMWASTE := 1
endif
MEMWASTE_CFLAGS :=
MEMWASTE_VENDOR_CFLAGS :=
MEMWASTE_LDFLAGS :=
MEMWASTE_SRCS :=
MEMWASTE_ALLOC_SYMS_LINUX := malloc calloc realloc free strdup strndup posix_memalign \
                             aligned_alloc memalign
MEMWASTE_LIBC_SYMS_LINUX := memcpy memmove memset memcmp strlen strcmp strncmp \
                            __memcpy_chk __memmove_chk __memset_chk read __read_chk write \
                            pread pwrite pread64 pwrite64 open open64 __open_2 __open64_2 \
                            stat lstat fopen fopen64 fread __fread_chk fwrite opendir readdir \
                            pthread_mutex_lock
MEMWASTE_LIBC_SYMS_WIN := memcpy memmove memset memcmp strlen strcmp strncmp _wfopen fread fwrite
ifeq ($(MEMWASTE),1)
MEMWASTE_CFLAGS := -DCBM_MEMWASTE=1 -fno-omit-frame-pointer
MEMWASTE_VENDOR_CFLAGS := -DCBM_MEMWASTE=1 -fno-omit-frame-pointer
ifeq ($(IS_LINUX),yes)
MEMWASTE_LDFLAGS := $(foreach sym,$(MEMWASTE_ALLOC_SYMS_LINUX) $(MEMWASTE_LIBC_SYMS_LINUX),-Wl,--wrap=$(sym))
MEMWASTE_SRCS := src/foundation/mem_override_posix.c
endif
ifeq ($(IS_MINGW),yes)
MEMWASTE_LDFLAGS := $(foreach sym,$(MEMWASTE_LIBC_SYMS_WIN),-Wl,--wrap=$(sym))
endif
endif
ifeq ($(MEMWASTE_ACCESS),1)
MEMWASTE_ACCESS_FLAGS := -DCBM_MEMWASTE_ACCESS=1 -O1 -fno-vectorize -fno-slp-vectorize \
                         -fsanitize-coverage=inline-bool-flag,trace-loads,trace-stores
MEMWASTE_CFLAGS += $(MEMWASTE_ACCESS_FLAGS)
MEMWASTE_VENDOR_CFLAGS += $(MEMWASTE_ACCESS_FLAGS)
endif
ifeq ($(MEMWASTE_PROFILE),1)
MEMWASTE_PROFILE_FLAGS := -DCBM_MEMWASTE_PROFILE=1 -fprofile-instr-generate -fprofile-update=atomic
MEMWASTE_CFLAGS += $(MEMWASTE_PROFILE_FLAGS)
MEMWASTE_VENDOR_CFLAGS += $(MEMWASTE_PROFILE_FLAGS)
MEMWASTE_LDFLAGS += $(MEMWASTE_PROFILE_FLAGS)
endif

# The POSIX wrap shim exists only so the profiler can observe allocations. It
# must never reach a sanitized build: the Linux/macOS test builds are CRT+ASan,
# and redirecting malloc into mimalloc underneath ASan's own interception mixes
# two allocators on the same pointers. Windows keeps its wrap flags everywhere,
# because there the shim is what makes mimalloc own the allocations at all.
# C++ stdlib selection: MSan builds must link an MSan-instrumented libc++
# instead of the system libstdc++ (scripts/msan.sh overrides both vars).
CXX_STDLIB ?= -lstdc++
CXX_STDLIB_FLAGS ?=
LDFLAGS = -lm $(CXX_STDLIB) -lpthread -lz $(WIN32_LIBS) $(STATIC_FLAGS) $(MIMALLOC_WRAP_FLAGS) $(MEMWASTE_LDFLAGS) $(ELF_HARDENING_FLAGS)
LDFLAGS_TEST = -lm $(CXX_STDLIB) -lpthread -lz $(SANITIZE) $(WIN32_LIBS) $(MIMALLOC_WRAP_FLAGS) $(ELF_HARDENING_FLAGS)
LDFLAGS_TSAN = -lm $(CXX_STDLIB) -lpthread -lz $(TSAN_SANITIZE) $(WIN32_LIBS) $(MIMALLOC_WRAP_FLAGS) $(ELF_HARDENING_FLAGS)

# ── Source files ─────────────────────────────────────────────────

FOUNDATION_SRCS = \
	src/foundation/mem_override_win.c \
    src/foundation/arena.c \
    src/foundation/hash_table.c \
    src/foundation/str_intern.c \
    src/foundation/log.c \
    src/foundation/str_util.c \
    src/foundation/workspace.c \
    src/foundation/platform.c \
    src/foundation/system_info.c \
    src/foundation/slab_alloc.c \
    src/foundation/yaml.c \
    src/foundation/compat.c \
    src/foundation/compat_thread.c \
    src/foundation/compat_fs.c \
    src/foundation/compat_regex.c \
    src/foundation/mem.c \
    src/foundation/mem_core.c \
    src/foundation/mem_events.c \
    src/foundation/mem_override_darwin.c \
    src/foundation/mem_override_libc.c \
    src/foundation/diagnostics.c \
    src/foundation/profile.c \
    src/foundation/dump_verify.c \
    src/foundation/limits.c \
    src/foundation/index_policy.c \
    src/foundation/subprocess.c \
    src/foundation/sha256.c \
    src/foundation/secure_random.c \
    src/foundation/macos_acl.c \
    src/foundation/private_file_lock.c \
    src/foundation/lock_registry.c

# Existing extraction C code (compiled from current location)
EXTRACTION_SRCS = \
    $(CBM_DIR)/cbm.c \
    $(CBM_DIR)/extract_defs.c \
    $(CBM_DIR)/extract_calls.c \
    $(CBM_DIR)/extract_imports.c \
    $(CBM_DIR)/extract_usages.c \
    $(CBM_DIR)/extract_unified.c \
    $(CBM_DIR)/extract_semantic.c \
    $(CBM_DIR)/extract_type_refs.c \
    $(CBM_DIR)/extract_type_assigns.c \
    $(CBM_DIR)/extract_env_accesses.c \
    $(CBM_DIR)/extract_channels.c \
    $(CBM_DIR)/extract_k8s.c \
    $(CBM_DIR)/extract_dbt.c \
    $(CBM_DIR)/sql_values.c \
    $(CBM_DIR)/helpers.c \
    $(CBM_DIR)/result_compact.c \
    $(CBM_DIR)/result_spill.c \
    $(CBM_DIR)/lang_specs.c \
    $(CBM_DIR)/macro_table.c \
    $(CBM_DIR)/iris_export_xml.c \
    $(CBM_DIR)/service_patterns.c

# LSP resolvers (compiled as one unit via lsp_all.c)
LSP_SRCS = $(CBM_DIR)/lsp_all.c

# Header/source dependencies of the lsp_all unity object. lsp_all.c #includes
# every lsp/*.c resolver, which in turn include cbm.h — and CBMCall is copied
# BY VALUE across the lsp -> pipeline boundary (cbm_calls_push). This object is
# compiled standalone and linked in, NOT recompiled with the rest on every link,
# so it must list the headers/sources it pulls in. Without this, a changed struct
# layout (e.g. a new CBMCall field) leaves a stale lsp_all.o with the old layout —
# an ODR mismatch that under-reads the by-value struct copy. Explicit because this
# Makefile does not use compiler auto-dependency (-MMD) generation.
LSP_UNITY_DEPS = $(CBM_DIR)/lsp_all.c \
                 $(wildcard $(CBM_DIR)/lsp/*.c $(CBM_DIR)/lsp/*.h \
                            $(CBM_DIR)/lsp/generated/*.c $(CBM_DIR)/*.h)

# Tree-sitter runtime
TS_RUNTIME_SRC = $(CBM_DIR)/ts_runtime.c
TS_RUNTIME_DEPS = \
	$(TS_RUNTIME_SRC) \
	$(wildcard $(CBM_DIR)/vendored/ts_runtime/include/tree_sitter/*.h) \
	$(wildcard $(CBM_DIR)/vendored/ts_runtime/src/*.c) \
	$(wildcard $(CBM_DIR)/vendored/ts_runtime/src/*.h) \
	$(wildcard $(CBM_DIR)/vendored/ts_runtime/src/portable/*.h) \
	$(wildcard $(CBM_DIR)/vendored/ts_runtime/src/unicode/*.h)

# All 159 grammar shim files
GRAMMAR_SRCS = $(wildcard $(CBM_DIR)/grammar_*.c)

# LZ4 + Aho-Corasick
AC_LZ4_SRCS = $(CBM_DIR)/ac.c $(CBM_DIR)/lz4_store.c

# Zstd compression (for persistent artifacts)
ZSTD_SRCS = $(CBM_DIR)/zstd_store.c

# Preprocessor (C++)
PREPROCESSOR_SRC = $(CBM_DIR)/preprocessor.cpp

# SQLite writer
SQLITE_WRITER_SRC = $(CBM_DIR)/sqlite_writer.c

# Store module (new)
STORE_SRCS = src/store/store.c

# Cypher module (new)
CYPHER_SRCS = src/cypher/cypher.c

# MCP server module (new)
MCP_SRCS = src/mcp/mcp.c src/mcp/index_supervisor.c src/mcp/compact_out.c

# Shared MCP daemon coordination and local transport
DAEMON_SRCS = \
    src/daemon/daemon.c \
    src/daemon/project_lock.c \
    src/daemon/version_cohort.c \
    src/daemon/service.c \
    src/daemon/runtime.c \
    src/daemon/application.c \
    src/daemon/frontend.c \
    src/daemon/host.c \
    src/daemon/bootstrap.c \
    src/daemon/ipc.c

# Discover module (new)
DISCOVER_SRCS = \
    src/discover/language.c \
    src/discover/userconfig.c \
    src/discover/gitignore.c \
    src/discover/discover.c

# Graph buffer module (new)
GRAPH_BUFFER_SRCS = src/graph_buffer/graph_buffer.c

# Pipeline module (new)
PIPELINE_SRCS = \
    src/pipeline/fqn.c \
    src/pipeline/lsp_surface.c \
    src/pipeline/pipeline_delta.c \
    src/pipeline/path_alias.c \
    src/pipeline/registry.c \
    src/pipeline/pipeline.c \
    src/pipeline/pipeline_incremental.c \
    src/pipeline/worker_pool.c \
    src/pipeline/pass_parallel.c \
    src/pipeline/pass_definitions.c \
    src/pipeline/pass_calls.c \
    src/pipeline/pass_lsp_cross.c \
    src/pipeline/pass_usages.c \
    src/pipeline/pass_semantic.c \
    src/pipeline/pass_tests.c \
    src/pipeline/pass_githistory.c \
    src/pipeline/pass_gitdiff.c \
    src/pipeline/pass_configures.c \
    src/pipeline/pass_configlink.c \
    src/pipeline/pass_doclinks.c \
    src/pipeline/pass_route_nodes.c \
    src/pipeline/pass_enrichment.c \
    src/pipeline/pass_envscan.c \
    src/pipeline/pass_compile_commands.c \
    src/pipeline/pass_infrascan.c \
    src/pipeline/pass_k8s.c \
    src/pipeline/pass_similarity.c \
    src/pipeline/pass_semantic_edges.c \
    src/pipeline/pass_complexity.c \
    src/pipeline/pass_importance.c \
    src/pipeline/pass_cross_repo.c \
    src/pipeline/artifact.c \
    src/pipeline/pass_ensemble_routing.c \
    src/pipeline/pass_pkgmap.c

# SimHash / MinHash module
SIMHASH_SRCS = src/simhash/minhash.c

# Semantic embedding module
SEMANTIC_SRCS = src/semantic/semantic.c src/semantic/ast_profile.c src/semantic/rotsq.c

# nomic-embed-code pretrained vectors (assembler blob)
UNIXCODER_BLOB_SRC = vendored/nomic/code_vectors_blob.S

# Traces module (new)
TRACES_SRCS = src/traces/traces.c

# Watcher module (new)
WATCHER_SRCS = src/watcher/watcher.c

# Git context module (new)
GIT_SRCS = src/git/git_context.c

# CLI module (new)
CLI_SRCS = src/cli/cli.c src/cli/progress_sink.c src/cli/hook_augment.c src/cli/client_adapter.c \
	src/cli/agent_clients.c src/cli/agent_profiles.c \
	src/cli/config_json_like.c src/cli/config_toml_edit.c src/cli/config_yaml_edit.c \
	src/cli/config_text_edit.c src/cli/config_edit_path.c src/cli/activation_transaction.c

# UI module (graph visualization)
UI_SRCS = \
    src/ui/config.c \
    src/ui/http_server.c \
    src/ui/layout3d.c \
    src/ui/httpd.c \
    src/ui/embedded_stub.c

# mimalloc (vendored, global allocator override)
#
# Override strategy is platform-specific:
#  * Unix (macOS/Linux): rely on static-link-order override — the prod mimalloc
#    object is linked first so its strong malloc/free symbols win. We do NOT
#    define MI_MALLOC_OVERRIDE here: that would compile alloc-override.c's
#    forwarding definitions (malloc/free/posix_memalign/...) which, on macOS's
#    two-level namespace, makes the binary's free == mi_free while system
#    libraries keep allocating via the system allocator — pointers crossing that
#    boundary hit "mimalloc: error: mi_free: invalid pointer". (Repro:
#    `codebase-memory-mcp index <dir>` aborted on every run.)
#  * Windows (MinGW, static CRT): the link-order trick fails (#424's allocator
#    mismatch), so we define MI_MALLOC_OVERRIDE=1 to compile the static-CRT
#    override added in mimalloc 3.3.0 (the _MSC_VER / _ACRTIMP /
#    _CRT_HYBRIDPATCHABLE entry points) which take precedence over the static
#    CRT's malloc/free.
# Note: mimalloc's source gates the override body on MI_MALLOC_OVERRIDE (CMake
# derives it from the MI_OVERRIDE option); MI_OVERRIDE alone is not read by the
# source — it is kept here only as this project's prod/test marker.
MIMALLOC_SRC = vendored/mimalloc/src/static.c
# Linux belongs on this list too (#1360). The "Unix relies on static-link-order
# override" strategy described above never actually worked: mimalloc defines
# malloc/free ONLY when MI_MALLOC_OVERRIDE is set (it gates alloc-override.c),
# so with the define off there were no strong symbols for the link order to
# prefer. Measured on the shipped v0.9.1-rc.1 artifacts — linux-arm64 glibc AND
# musl-static both report 0/6 allocator-owned size classes, i.e. ordinary malloc
# was going to libc and every purge/reclaim option set in cbm_mem_init applied
# only to the bound sqlite/tree-sitter populations.
#
# The macOS objection does not transfer. That abort is specific to the two-level
# namespace, where this binary's free becomes mi_free while system libraries keep
# allocating from the system allocator, so a pointer crossing the boundary hits
# "mi_free: invalid pointer". ELF is a flat namespace: interposition is
# process-wide and all-or-nothing, which is the configuration mimalloc is
# normally deployed in. macOS therefore stays off, deliberately and permanently.
#
# TWO defines, switched together in ONE place so they cannot drift:
# MI_MALLOC_OVERRIDE reaches the mimalloc translation unit and turns the
# override on; CBM_MEM_GLOBAL_OVERRIDE reaches OUR sources and tells the startup
# audit what to expect. CBM_MEM_GLOBAL_OVERRIDE goes only into CFLAGS_PROD,
# because MIMALLOC_CFLAGS_TEST compiles mimalloc with -DMI_OVERRIDE=0 and no
# override define at all — a test binary has no global override BY CONSTRUCTION
# and must never be told to expect one, or it warns on every run.
MIMALLOC_OVERRIDE_DEFINE :=
GLOBAL_OVERRIDE_DEFINE :=
ifneq ($(filter yes,$(IS_MINGW) $(IS_LINUX)),)
MIMALLOC_OVERRIDE_DEFINE := -DMI_MALLOC_OVERRIDE=1
GLOBAL_OVERRIDE_DEFINE := -DCBM_MEM_GLOBAL_OVERRIDE=1
endif
# MI_DEBUG=0: the production allocator is mimalloc's RELEASE build. Its header
# defaults to MI_DEBUG=2 unless NDEBUG is defined, and nothing here defined it,
# so every shipped binary up to v0.11.0 ran mimalloc's debug build: internal
# assertions, fine-grained statistics, padding on every block and a memset of
# every freed block. The waste sanitizer measured it on the Go corpus as 92 GB
# (macOS) and 444 GB (Linux, where mimalloc also serves libc's malloc) of byte
# work inside the allocator (2026-09-17). Committed-bytes accounting, which the
# memory budget reads, is kept in every build (subproc stats, not MI_STAT).
# The TEST build below keeps mimalloc's debug checks.
MIMALLOC_CFLAGS = -std=c11 -O2 -w \
                  -Ivendored/mimalloc/include \
                  -Ivendored/mimalloc/src \
                  -DMI_OVERRIDE=1 -DMI_DEBUG=0 \
                  $(MIMALLOC_OVERRIDE_DEFINE)
MIMALLOC_CFLAGS_TEST = -std=c11 -g -O1 -w \
                       -Ivendored/mimalloc/include \
                       -Ivendored/mimalloc/src \
                       -DMI_OVERRIDE=0

# sqlite3 (vendored amalgamation — compiled ourselves for ASan instrumentation)
# SQLITE_ENABLE_FTS5: enables the FTS5 full-text search extension used by the
# BM25 search path in search_graph (see nodes_fts virtual table in store.c).
#
# SQLITE_OMIT_LOAD_EXTENSION: no cbm code calls sqlite3_load_extension or
# sqlite3_enable_load_extension, and we never want a graph DB to be able to pull
# a shared library into the process. Loading is off by default at runtime, but
# "disabled by default" is a setting while "not compiled in" is a property —
# this compiles the machinery out, removing the API surface and part of the
# dlopen/dlsym import surface with it. The composition gate asserts the symbols
# are absent from every release artifact.
SQLITE3_OMIT_FLAGS = -DSQLITE_OMIT_LOAD_EXTENSION
SQLITE3_SRC = vendored/sqlite3/sqlite3.c
SQLITE3_CFLAGS = -std=c11 -O2 -w -DSQLITE_DQS=0 -DSQLITE_THREADSAFE=1 -DSQLITE_ENABLE_FTS5 \
                 $(SQLITE3_OMIT_FLAGS) $(MEMWASTE_VENDOR_CFLAGS)
SQLITE3_CFLAGS_TEST = -std=c11 -g -O1 -w -DSQLITE_DQS=0 -DSQLITE_THREADSAFE=1 -DSQLITE_ENABLE_FTS5 \
                      $(SQLITE3_OMIT_FLAGS)

# TRE regex (vendored, Windows only — POSIX uses system <regex.h>)
TRE_SRC = vendored/tre/tre_all.c
TRE_CFLAGS = -std=c11 -g -O1 -w -Ivendored/tre

# yyjson (vendored)
YYJSON_SRC = vendored/yyjson/yyjson.c

# All production sources
PROD_SRCS = $(MEMWASTE_SRCS) $(FOUNDATION_SRCS) $(STORE_SRCS) $(CYPHER_SRCS) $(MCP_SRCS) $(DAEMON_SRCS) $(DISCOVER_SRCS) $(GRAPH_BUFFER_SRCS) $(PIPELINE_SRCS) $(SIMHASH_SRCS) $(SEMANTIC_SRCS) $(TRACES_SRCS) $(WATCHER_SRCS) $(GIT_SRCS) $(CLI_SRCS) $(UI_SRCS) $(YYJSON_SRC)
EXISTING_C_SRCS = $(EXTRACTION_SRCS) $(LSP_SRCS) $(TS_RUNTIME_SRC) \
                  $(GRAMMAR_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC)

# Project headers, as prerequisites for the targets built in one compiler
# invocation from sources (test-runner, test-repro-runner, test-runner-tsan,
# codebase-memory-mcp, test-foundation). Those rules list only .c files, so
# editing a header changed nothing make could see and the target was NOT
# rebuilt — an incremental build then silently tested the OLD header value.
# Found while revert-checking a constants.h change: the check passed because
# nothing had recompiled.
#
# Vendored trees are deliberately excluded — they are pinned, they carry their
# own explicit dep lists (LSP_UNITY_DEPS, TS_RUNTIME_DEPS), and globbing tens of
# thousands of grammar headers would cost more than it protects.
PROJECT_HDRS = $(wildcard src/*.h src/*/*.h $(CBM_DIR)/*.h $(CBM_DIR)/lsp/*.h tests/*.h \
               tests/repro/*.h)

# ── Test sources ─────────────────────────────────────────────────

TEST_FOUNDATION_SRCS = \
    tests/test_main.c \
    tests/test_arena.c \
    tests/test_hash_table.c \
    tests/test_dyn_array.c \
    tests/test_str_intern.c \
    tests/test_log.c \
    tests/test_str_util.c \
    tests/test_index_policy.c \
    tests/test_workspace.c \
    tests/test_platform.c \
    tests/test_diagnostics.c \
    tests/test_complexity.c \
    tests/test_dump_verify.c \
    tests/test_subprocess.c \
    tests/test_private_file_lock.c \
    tests/test_lock_registry.c

TEST_EXTRACTION_SRCS = \
    tests/test_extraction.c \
    tests/test_extraction_inheritance.c \
    tests/test_extraction_imports.c \
    tests/test_parse_coverage.c \
    tests/test_grammar_regression.c \
    tests/test_grammar_labels.c \
    tests/test_grammar_imports.c \
    tests/test_ac.c

TEST_STORE_SRCS = \
    tests/test_store_nodes.c \
    tests/test_store_edges.c \
    tests/test_store_search.c \
    tests/test_store_arch.c \
    tests/test_store_bulk.c \
    tests/test_store_pragmas.c \
    tests/test_store_checkpoint.c \
    tests/test_dump_verify_io.c

TEST_CYPHER_SRCS = \
    tests/test_cypher.c

TEST_MCP_SRCS = \
    tests/test_mcp.c \
    tests/test_index_supervisor.c

TEST_DAEMON_SRCS = \
    tests/test_daemon.c \
    tests/test_project_lock.c \
    tests/test_version_cohort.c \
    tests/test_daemon_version.c \
    tests/test_daemon_runtime.c \
    tests/test_daemon_application.c \
    tests/test_daemon_frontend.c \
    tests/test_daemon_bootstrap.c \
    tests/test_daemon_ipc.c

TEST_DISCOVER_SRCS = \
    tests/test_language.c \
    tests/test_userconfig.c \
    tests/test_gitignore.c \
    tests/test_git_context.c \
    tests/test_discover.c

TEST_GRAPH_BUFFER_SRCS = tests/test_graph_buffer.c

TEST_PIPELINE_SRCS = tests/test_registry.c tests/test_pipeline.c tests/test_importance.c tests/test_cross_repo.c tests/test_fqn.c tests/test_route_canon.c tests/test_path_alias.c tests/test_configlink.c tests/test_doclinks.c tests/test_infrascan.c tests/test_worker_pool.c tests/test_parallel.c tests/test_index_resilience.c tests/test_index_format.c tests/test_call_reference_contract.c tests/repro/repro_call_scope_usages.c tests/repro/repro_call_argument_usages.c tests/repro/repro_reference_precision.c tests/repro/repro_lexical_binding_precision.c tests/repro/repro_call_argument_matrix_a.c tests/repro/repro_call_argument_matrix_b.c tests/repro/repro_call_node_behaviors.c tests/repro/repro_language_registry.c tests/repro/repro_call_node_manifest.c tests/repro/repro_lsp_ordered_signatures.c tests/repro/repro_lsp_ordered_local.c tests/repro/repro_ts_overload_return_chains.c tests/repro/repro_harness_cleanup.c tests/repro/repro_runner_filter.c

TEST_WATCHER_SRCS = tests/test_watcher.c

TEST_LZ4_SRCS = tests/test_lz4.c
TEST_ZSTD_SRCS = tests/test_zstd.c
TEST_ARTIFACT_SRCS = tests/test_artifact.c

TEST_SQLITE_WRITER_SRCS = tests/test_sqlite_writer.c

TEST_GO_LSP_SRCS = tests/test_go_lsp.c

TEST_C_LSP_SRCS = tests/test_c_lsp.c

TEST_PHP_LSP_SRCS = tests/test_php_lsp.c

TEST_CS_LSP_SRCS = tests/test_cs_lsp.c

TEST_CS_LSP_BENCH_SRCS = tests/test_cs_lsp_bench.c

TEST_PERL_LSP_SRCS = tests/test_perl_lsp.c

TEST_SCOPE_SRCS = tests/test_scope.c

TEST_TYPE_REP_SRCS = tests/test_type_rep.c

TEST_PY_LSP_SRCS = tests/test_py_lsp.c

TEST_PY_LSP_BENCH_SRCS = tests/test_py_lsp_bench.c

TEST_PY_LSP_STRESS_SRCS = tests/test_py_lsp_stress.c

TEST_PY_LSP_SCALE_SRCS = tests/test_py_lsp_scale.c

TEST_TS_LSP_SRCS = tests/test_ts_lsp.c
TEST_JAVA_LSP_SRCS = tests/test_java_lsp.c tests/test_java_lsp_coverage.c
TEST_KOTLIN_LSP_SRCS = tests/test_kotlin_lsp.c
TEST_RUST_LSP_SRCS = tests/test_rust_lsp.c

TEST_INTEGRATION_SRCS = tests/test_integration.c tests/test_incremental.c tests/test_lang_contract.c tests/test_edge_imports.c tests/test_edge_structural.c tests/test_lsp_resolution_probe.c tests/test_node_creation_probe.c tests/test_edge_types_probe.c tests/test_convergence_probe.c tests/test_matrix_known_classes.c tests/test_matrix_new_constructs.c tests/test_grammar_probe_a.c tests/test_grammar_probe_b.c tests/test_grammar_probe_c.c tests/test_grammar_probe_d.c tests/test_grammar_probe_e.c tests/test_grammar_probe_f.c tests/test_grammar_probe_g.c

TEST_TRACES_SRCS = tests/test_traces.c


TEST_CLI_SRCS = tests/test_cli.c tests/test_agent_clients.c tests/test_agent_profiles.c \
	tests/test_config_json_like.c \
	tests/test_config_toml_edit.c tests/test_config_yaml_edit.c tests/test_config_text_edit.c \
	tests/test_activation_transaction.c

TEST_MEM_SRCS = tests/test_mem.c tests/test_mem_events.c

TEST_UI_SRCS = tests/test_ui.c
TEST_HTTPD_SRCS = tests/test_httpd.c

TEST_SECURITY_SRCS = tests/test_security.c

TEST_YAML_SRCS = tests/test_yaml.c

TEST_SEMANTIC_SRCS = tests/test_semantic.c
TEST_AST_PROFILE_SRCS = tests/test_ast_profile.c
TEST_SLAB_ALLOC_SRCS = tests/test_slab_alloc.c

TEST_SIMHASH_SRCS = tests/test_simhash.c

TEST_STACK_OVERFLOW_SRCS = tests/test_stack_overflow.c

# Cumulative BUG-REPRODUCTION suite (separate runner, NOT in ALL_TEST_SRCS).
# Contains RED reproductions plus GREEN controls — see tests/repro/repro_main.c.
# Kept out of the gating `make test` so `ci-ok` stays green; run via `make test-repro`.
TEST_REPRO_SRCS = \
    tests/repro/repro_main.c \
    tests/repro/repro_parallel_determinism.c \
    tests/repro/repro_extraction.c \
    tests/repro/repro_runner_filter.c \
    tests/repro/repro_harness_cleanup.c \
    tests/repro/repro_language_registry.c \
    tests/repro/repro_call_node_manifest.c \
    tests/repro/repro_call_scope_usages.c \
    tests/repro/repro_call_argument_usages.c \
    tests/repro/repro_lsp_ordered_signatures.c \
    tests/repro/repro_lsp_ordered_local.c \
    tests/repro/repro_ts_overload_return_chains.c \
    tests/repro/repro_reference_precision.c \
    tests/repro/repro_lexical_binding_precision.c \
    tests/repro/repro_call_argument_matrix_a.c \
    tests/repro/repro_call_argument_matrix_b.c \
    tests/repro/repro_call_node_behaviors.c \
    tests/repro/repro_issue495.c \
    tests/repro/repro_issue521.c \
    tests/repro/repro_issue382.c \
    tests/repro/repro_issue408.c \
    tests/repro/repro_issue56.c \
    tests/repro/repro_issue480.c \
    tests/repro/repro_issue571.c \
    tests/repro/repro_issue523.c \
    tests/repro/repro_issue546.c \
    tests/repro/repro_issue627.c \
    tests/repro/repro_issue514.c \
    tests/repro/repro_issue510.c \
    tests/repro/repro_issue557.c \
    tests/repro/repro_issue520.c \
    tests/repro/repro_issue333.c \
    tests/repro/repro_issue570.c \
    tests/repro/repro_issue409.c \
    tests/repro/repro_issue431.c \
    tests/repro/repro_issue607.c \
    tests/repro/repro_issue403.c \
    tests/repro/repro_issue434.c \
    tests/repro/repro_issue471.c \
    tests/repro/repro_issue221.c \
    tests/repro/repro_issue548.c \
    tests/repro/repro_new_ts_class_field_arrow.c \
    tests/repro/repro_new_py_tuple_unpack.c \
    tests/repro/repro_new_cypher_limit_zero.c \
    tests/repro/repro_issue363.c \
    tests/repro/repro_issue581.c \
    tests/repro/repro_issue787.c \
    tests/repro/repro_issue842.c \
    tests/repro/repro_issue964.c \
    tests/repro/repro_issue1692.c \
    tests/repro/repro_invariant_calls.c \
    tests/repro/repro_invariant_graph.c \
    tests/repro/repro_invariant_breadth.c \
    tests/repro/repro_invariant_enclosing_parity.c \
    tests/repro/repro_invariant_lsp_rescue.c \
    tests/repro/repro_invariant_discovery_fqn.c \
    tests/repro/repro_grammar_core.c \
    tests/repro/repro_grammar_scripting.c \
    tests/repro/repro_grammar_functional.c \
    tests/repro/repro_grammar_systems.c \
    tests/repro/repro_grammar_web.c \
    tests/repro/repro_grammar_config.c \
    tests/repro/repro_grammar_build.c \
    tests/repro/repro_grammar_shells.c \
    tests/repro/repro_grammar_scientific.c \
    tests/repro/repro_grammar_markup.c \
    tests/repro/repro_grammar_misc.c \
    tests/repro/repro_lsp_c_cpp.c \
    tests/repro/repro_lsp_go_py.c \
    tests/repro/repro_lsp_ts.c \
    tests/repro/repro_ts_inherited_method.c \
    tests/repro/repro_lsp_java_cs.c \
    tests/repro/repro_lsp_kt_php_rust.c

ALL_TEST_SRCS =$(TEST_FOUNDATION_SRCS) $(TEST_EXTRACTION_SRCS) $(TEST_STORE_SRCS) $(TEST_CYPHER_SRCS) $(TEST_MCP_SRCS) $(TEST_DAEMON_SRCS) $(TEST_DISCOVER_SRCS) $(TEST_GRAPH_BUFFER_SRCS) $(TEST_PIPELINE_SRCS) $(TEST_WATCHER_SRCS) $(TEST_LZ4_SRCS) $(TEST_ZSTD_SRCS) $(TEST_ARTIFACT_SRCS) $(TEST_SQLITE_WRITER_SRCS) $(TEST_GO_LSP_SRCS) $(TEST_C_LSP_SRCS) $(TEST_PHP_LSP_SRCS) $(TEST_CS_LSP_SRCS) $(TEST_CS_LSP_BENCH_SRCS) $(TEST_PERL_LSP_SRCS) $(TEST_SCOPE_SRCS) $(TEST_TYPE_REP_SRCS) $(TEST_PY_LSP_SRCS) $(TEST_PY_LSP_BENCH_SRCS) $(TEST_PY_LSP_STRESS_SRCS) $(TEST_PY_LSP_SCALE_SRCS) $(TEST_TS_LSP_SRCS) $(TEST_JAVA_LSP_SRCS) $(TEST_KOTLIN_LSP_SRCS) $(TEST_RUST_LSP_SRCS) $(TEST_TRACES_SRCS) $(TEST_CLI_SRCS) $(TEST_MEM_SRCS) $(TEST_UI_SRCS) $(TEST_HTTPD_SRCS) $(TEST_SECURITY_SRCS) $(TEST_YAML_SRCS) $(TEST_SEMANTIC_SRCS) $(TEST_AST_PROFILE_SRCS) $(TEST_SLAB_ALLOC_SRCS) $(TEST_SIMHASH_SRCS) $(TEST_STACK_OVERFLOW_SRCS) $(TEST_INTEGRATION_SRCS)


# ── Build directories ────────────────────────────────────────────

BUILD_DIR = build/c

# ── Object file compilation (grammars need relaxed warnings) ─────

# Grammar + tree-sitter runtime: compiled without -Werror (upstream code has warnings)
GRAMMAR_CFLAGS = -std=c11 -D_DEFAULT_SOURCE -O2 -w -I$(CBM_DIR) -I$(TS_INCLUDE) -I$(TS_SRC) \
                 $(MEMWASTE_VENDOR_CFLAGS)
GRAMMAR_CFLAGS_TEST = -std=c11 -D_DEFAULT_SOURCE -g -O1 -w -I$(CBM_DIR) -I$(TS_INCLUDE) -I$(TS_SRC) \
                      -DCBM_ENABLE_TEST_SEAMS=1 $(SANITIZED_DEFINE) $(SANITIZE)
GRAMMAR_CFLAGS_TSAN = -std=c11 -D_DEFAULT_SOURCE -g -O1 -w -I$(CBM_DIR) -I$(TS_INCLUDE) -I$(TS_SRC) \
                      -DCBM_ENABLE_TEST_SEAMS=1 -DCBM_SANITIZED_BUILD=1 $(TSAN_SANITIZE)

# Object files for grammars + ts_runtime + lsp_all + preprocessor
GRAMMAR_OBJS_TEST = $(patsubst $(CBM_DIR)/%.c,$(BUILD_DIR)/%.o,$(GRAMMAR_SRCS))
TS_RUNTIME_OBJ_TEST = $(BUILD_DIR)/ts_runtime.o
LSP_OBJ_TEST = $(BUILD_DIR)/lsp_all.o
PP_OBJ_TEST = $(BUILD_DIR)/preprocessor.o
GRAMMAR_OBJS_TSAN = $(patsubst $(CBM_DIR)/%.c,$(BUILD_DIR)/tsan_%.o,$(GRAMMAR_SRCS))
TS_RUNTIME_OBJ_TSAN = $(BUILD_DIR)/tsan_ts_runtime.o
LSP_OBJ_TSAN = $(BUILD_DIR)/tsan_lsp_all.o
PP_OBJ_TSAN = $(BUILD_DIR)/tsan_preprocessor.o

# ── Targets ──────────────────────────────────────────────────────

.PHONY: test test-par test-repro test-foundation test-tsan test-daemon-smoke cbm cbm-with-ui frontend embed clean-c lint lint-tidy lint-tidy-diff lint-cppcheck lint-format security fuzz

$(BUILD_DIR):
	mkdir -p $(BUILD_DIR)

# ── Foundation-only test (fast, no extraction) ───────────────────

$(BUILD_DIR)/test-foundation: $(TEST_FOUNDATION_SRCS) $(FOUNDATION_SRCS) $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_TEST) -o $@ $(TEST_FOUNDATION_SRCS) $(FOUNDATION_SRCS) $(LDFLAGS_TEST)

test-foundation: $(BUILD_DIR)/test-foundation
	cd $(CURDIR) && $(BUILD_DIR)/test-foundation

# ── Grammar/TS/LSP object files (compiled with relaxed warnings) ─

# Each grammar_<lang>.c is a unity object that #includes its own vendored
# parser.c and, where the grammar has one, scanner.c. Those includes were
# prerequisites of nothing, so editing a vendored scanner left the object
# untouched and the edit silently absent from the binary: on 2026-09-19 a fix
# to properties/scanner.c appeared not to work at all, and `nm` showed the old
# symbol still sitting in prod_grammar_properties.o. MANIFEST.md's "Local
# source patches" table means patching a vendored scanner is expected, so this
# trap is reachable by design. Same reasoning as LSP_UNITY_DEPS and
# TS_RUNTIME_DEPS above; secondary expansion is what lets one pattern rule name
# each grammar's own directory ($$* is the stem, grammar_properties ->
# properties). Non-grammar objects match no directory and gain no prerequisite.
GRAMMAR_VENDOR_DIR = $(CBM_DIR)/vendored/grammars/$$(subst grammar_,,$$*)
GRAMMAR_UNITY_DEPS = $$(wildcard $(GRAMMAR_VENDOR_DIR)/*.c) \
                     $$(wildcard $(GRAMMAR_VENDOR_DIR)/*.h) \
                     $$(wildcard $(GRAMMAR_VENDOR_DIR)/tree_sitter/*.h)
.SECONDEXPANSION:

$(BUILD_DIR)/%.o: $(CBM_DIR)/%.c $(GRAMMAR_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TEST) -c -o $@ $<

$(BUILD_DIR)/ts_runtime.o: $(TS_RUNTIME_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TEST) -c -o $@ $<

$(BUILD_DIR)/lsp_all.o: $(LSP_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TEST) $(SANITIZE) -c -o $@ $<

$(BUILD_DIR)/preprocessor.o: $(CBM_DIR)/preprocessor.cpp | $(BUILD_DIR)
	$(CXX) $(CXXFLAGS_TEST) -w -I$(CBM_DIR)/vendored -c -o $@ $<

$(BUILD_DIR)/tsan_%.o: $(CBM_DIR)/%.c $(GRAMMAR_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TSAN) -c -o $@ $<

$(BUILD_DIR)/tsan_ts_runtime.o: $(TS_RUNTIME_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TSAN) -c -o $@ $<

$(BUILD_DIR)/tsan_lsp_all.o: $(LSP_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS_TSAN) -c -o $@ $<

$(BUILD_DIR)/tsan_preprocessor.o: $(CBM_DIR)/preprocessor.cpp | $(BUILD_DIR)
	$(CXX) $(CXXFLAGS_TSAN) -w -I$(CBM_DIR)/vendored -c -o $@ $<

# ── Full test binary ─────────────────────────────────────────────

# mimalloc object files
MIMALLOC_OBJ_TEST = $(BUILD_DIR)/mimalloc.o
MIMALLOC_OBJ_TSAN = $(BUILD_DIR)/tsan_mimalloc.o
MIMALLOC_OBJ_PROD = $(BUILD_DIR)/prod_mimalloc.o

$(BUILD_DIR)/mimalloc.o: $(MIMALLOC_SRC) | $(BUILD_DIR)
	$(CC) $(MIMALLOC_CFLAGS_TEST) -c -o $@ $<

$(BUILD_DIR)/tsan_mimalloc.o: $(MIMALLOC_SRC) | $(BUILD_DIR)
	$(CC) $(MIMALLOC_CFLAGS_TEST) $(TSAN_SANITIZE) -c -o $@ $<

# static.c is an AMALGAMATION: it #includes options.c and friends, none of which
# make can see through the single named prerequisite, and the compile flags live
# in this Makefile. Both gaps bit for real — the __DATE__ removal in options.c and
# SQLITE_OMIT_LOAD_EXTENSION below each silently did nothing on an incremental
# build because the object was considered up to date. Depend on the included
# sources AND on this Makefile so a flag change rebuilds too.
$(BUILD_DIR)/prod_mimalloc.o: $(MIMALLOC_SRC) $(wildcard vendored/mimalloc/src/*.c) \
                              $(wildcard vendored/mimalloc/include/*.h) Makefile.cbm | $(BUILD_DIR)
	$(CC) $(MIMALLOC_CFLAGS) -c -o $@ $<

# sqlite3 object files (vendored amalgamation)
SQLITE3_OBJ_TEST = $(BUILD_DIR)/sqlite3.o
SQLITE3_OBJ_TSAN = $(BUILD_DIR)/tsan_sqlite3.o
SQLITE3_OBJ_PROD = $(BUILD_DIR)/prod_sqlite3.o

$(BUILD_DIR)/sqlite3.o: $(SQLITE3_SRC) | $(BUILD_DIR)
	$(CC) $(SQLITE3_CFLAGS_TEST) $(SANITIZE) -c -o $@ $<

$(BUILD_DIR)/tsan_sqlite3.o: $(SQLITE3_SRC) | $(BUILD_DIR)
	$(CC) $(SQLITE3_CFLAGS_TEST) $(TSAN_SANITIZE) -c -o $@ $<

$(BUILD_DIR)/prod_sqlite3.o: $(SQLITE3_SRC) Makefile.cbm | $(BUILD_DIR)
	$(CC) $(SQLITE3_CFLAGS) -c -o $@ $<

# TRE regex (only compiled on Windows — POSIX uses system <regex.h>)
TRE_OBJ_TEST :=
TRE_OBJ_TSAN :=
TRE_OBJ_PROD :=
ifeq ($(IS_MINGW),yes)
TRE_OBJ_TEST = $(BUILD_DIR)/tre.o
TRE_OBJ_TSAN = $(BUILD_DIR)/tsan_tre.o
TRE_OBJ_PROD = $(BUILD_DIR)/prod_tre.o

# tre.o keeps UBSan's alignment check OFF, and that is not a coverage
# preference -- it is a portability fact. Arming it here (attempted, then
# reverted after this bisect) makes the vendored TRE regex engine trap on
# Windows/ARM64, where the CLANGARM64 leg builds with -fsanitize-trap and a
# trap is an illegal instruction with no diagnostic: every fixture-indexing
# suite died with STATUS_ILLEGAL_INSTRUCTION and no message. macOS and Linux
# stay clean under the same check because Windows is LLP64 -- 32-bit long --
# so TRE's struct layouts and access widths differ there and nowhere else.
#
# TRE is third-party code we vendor and do not modify, so the alignment
# behaviour is upstream's to change; suppressing the check for this one
# object is the honest scope. Everything else keeps alignment armed.
$(BUILD_DIR)/tre.o: $(TRE_SRC) | $(BUILD_DIR)
	$(CC) $(TRE_CFLAGS) $(SANITIZE) -fno-sanitize=alignment -c -o $@ $<

$(BUILD_DIR)/tsan_tre.o: $(TRE_SRC) | $(BUILD_DIR)
	$(CC) $(TRE_CFLAGS) $(TSAN_SANITIZE) -c -o $@ $<

$(BUILD_DIR)/prod_tre.o: $(TRE_SRC) | $(BUILD_DIR)
	$(CC) $(TRE_CFLAGS) -O2 $(MEMWASTE_VENDOR_CFLAGS) -c -o $@ $<
endif

# Vendored LZ4 (test build)
LZ4_OBJ_TEST = $(BUILD_DIR)/test_lz4.o $(BUILD_DIR)/test_lz4hc.o
LZ4_OBJ_TSAN = $(BUILD_DIR)/tsan_lz4.o $(BUILD_DIR)/tsan_lz4hc.o
$(BUILD_DIR)/test_lz4.o: $(CBM_DIR)/vendored/lz4/lz4.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(SANITIZE) -w -I$(CBM_DIR) -c -o $@ $<
$(BUILD_DIR)/test_lz4hc.o: $(CBM_DIR)/vendored/lz4/lz4hc.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(SANITIZE) -w -I$(CBM_DIR)/vendored/lz4 -c -o $@ $<
$(BUILD_DIR)/tsan_lz4.o: $(CBM_DIR)/vendored/lz4/lz4.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(TSAN_SANITIZE) -w -I$(CBM_DIR) -c -o $@ $<
$(BUILD_DIR)/tsan_lz4hc.o: $(CBM_DIR)/vendored/lz4/lz4hc.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(TSAN_SANITIZE) -w -I$(CBM_DIR)/vendored/lz4 -c -o $@ $<

# Vendored zstd (test build)
# ZSTD_EXTRA_CFLAGS: hook for sanitizer lanes. The MSan lane needs
# `-include stdint.h` for THIS object only: zstd's MEMORY_SANITIZER-guarded
# block declares __msan_test_shadow returning intptr_t, but the amalgamator
# collapsed the `#define ZSTD_DEPS_NEED_STDINT` re-include that should supply
# it. The flag cannot go on the global SANITIZE line: force-including a libc
# header ahead of a source file freezes glibc's feature-test macros before
# files like sqlite3.c set _GNU_SOURCE themselves, which strips
# MREMAP_MAYMOVE/nanosleep out of their view of libc.
ZSTD_OBJ_TEST = $(BUILD_DIR)/test_zstd.o
ZSTD_OBJ_TSAN = $(BUILD_DIR)/tsan_zstd.o
$(BUILD_DIR)/test_zstd.o: $(CBM_DIR)/vendored/zstd/zstd.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(SANITIZE) $(ZSTD_EXTRA_CFLAGS) -w -I$(CBM_DIR)/vendored/zstd -c -o $@ $<
$(BUILD_DIR)/tsan_zstd.o: $(CBM_DIR)/vendored/zstd/zstd.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -g -O1 $(TSAN_SANITIZE) -w -I$(CBM_DIR)/vendored/zstd -c -o $@ $<

# nomic-embed-code pretrained vector blob
UNIXCODER_OBJ = $(BUILD_DIR)/unixcoder_blob.o
$(UNIXCODER_OBJ): $(UNIXCODER_BLOB_SRC) vendored/nomic/code_vectors.bin | $(BUILD_DIR)
	$(CC) -c -o $@ $<

OBJS_VENDORED_TEST = $(MIMALLOC_OBJ_TEST) $(SQLITE3_OBJ_TEST) $(TRE_OBJ_TEST) $(GRAMMAR_OBJS_TEST) $(TS_RUNTIME_OBJ_TEST) $(LSP_OBJ_TEST) $(PP_OBJ_TEST) $(LZ4_OBJ_TEST) $(ZSTD_OBJ_TEST) $(UNIXCODER_OBJ)
OBJS_VENDORED_TSAN = $(MIMALLOC_OBJ_TSAN) $(SQLITE3_OBJ_TSAN) $(TRE_OBJ_TSAN) $(GRAMMAR_OBJS_TSAN) $(TS_RUNTIME_OBJ_TSAN) $(LSP_OBJ_TSAN) $(PP_OBJ_TSAN) $(LZ4_OBJ_TSAN) $(ZSTD_OBJ_TSAN) $(UNIXCODER_OBJ)

$(BUILD_DIR)/test-runner: $(ALL_TEST_SRCS) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(OBJS_VENDORED_TEST) $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_TEST) -Itests -Itests/repro -o $@ \
		$(ALL_TEST_SRCS) $(PROD_SRCS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_TEST) \
		$(LDFLAGS_TEST)

test: $(BUILD_DIR)/test-runner
	cd $(CURDIR) && $(BUILD_DIR)/test-runner

# Parallel variant: every suite as its own process; identical gate quality
# (see the ZERO-LOSS CONTRACT in scripts/run-tests-parallel.sh — union guard
# against --list-suites + aggregated pass/fail/skip totals).
test-par: $(BUILD_DIR)/test-runner
	cd $(CURDIR) && bash scripts/run-tests-parallel.sh $(BUILD_DIR)/test-runner

# Focused native development is intentionally a separate, explicit target so
# an inherited TEST_SUITES value cannot silently narrow the gating test target.
TEST_SUITES ?=
test-focused: $(BUILD_DIR)/test-runner
	@test -n "$(strip $(TEST_SUITES))" || \
		(echo "TEST_SUITES is required for test-focused"; exit 2)
	cd $(CURDIR) && $(BUILD_DIR)/test-runner $(TEST_SUITES)

# ── Cumulative bug-reproduction runner (RED board by design, non-gating) ──
# Mirrors test-runner's link line but uses repro_main.c (own main + counters)
# and TEST_REPRO_SRCS instead of ALL_TEST_SRCS. Exits non-zero while any bug is
# still reproduced (the expected state); bug-repro.yml surfaces it as a board.
$(BUILD_DIR)/test-repro-runner: $(TEST_REPRO_SRCS) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(OBJS_VENDORED_TEST) $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_TEST) -Itests -o $@ \
		$(TEST_REPRO_SRCS) $(PROD_SRCS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_TEST) \
		$(LDFLAGS_TEST)

test-repro: $(BUILD_DIR)/test-repro-runner
	cd $(CURDIR) && bash tests/repro/repro_script_summary.sh
	cd $(CURDIR) && bash tests/repro/repro_script_zero_selection.sh
	cd $(CURDIR) && bash tests/repro/repro_script_missing_summary.sh
	cd $(CURDIR) && bash tests/repro/repro_script_skipped_summary.sh
	cd $(CURDIR) && bash tests/repro/repro_runner_zero_selection.sh
	cd $(CURDIR) && bash tests/repro/repro_runner_passing_semantics.sh
	cd $(CURDIR) && bash tests/repro/repro_script_no_workspace_artifact.sh
	cd $(CURDIR) && bash tests/repro/repro_script_stderr_summary.sh
	cd $(CURDIR) && bash tests/repro/repro_make_tracks_headers.sh
	cd $(CURDIR) && $(BUILD_DIR)/test-repro-runner

# ── TSan full test ───────────────────────────────────────────────

# Every threaded production surface that runs clean AND stable under TSan:
# allocator concurrency (mem, slab_alloc), the parallel extraction worker pool
# (parallel, worker_pool, pipeline), the filesystem watcher (watcher), the
# embedded HTTP server (httpd), diagnostics sampling (diagnostics), the MCP
# server + mutation guard (mcp, mcp_mutation_guard), subprocess supervision
# (subprocess), and the runnable daemon-coordination paths (daemon,
# daemon_application). Was `mem slab_alloc parallel` — a keyhole that ran TSan
# over no real threaded production code.
#
# NO EXCLUSIONS. A sanitizer covers the complete surface or it is asserting
# coverage it does not have. The three suites once excluded here
# (daemon_runtime, daemon_ipc, daemon_frontend) are back:
#   daemon_ipc, daemon_frontend — the documented test-harness race and thread
#     leaks no longer reproduce; both run clean under TSan.
#   daemon_runtime — did NOT deadlock as documented. It reported a REAL
#     production data race on the log sink (plain global function pointer,
#     written by the configuring thread, read AND CALLED by connection
#     workers), now fixed with atomics in log.c. Excluding the suite is what
#     had hidden it.
TEST_TSAN_SUITES ?= mem slab_alloc parallel worker_pool watcher httpd pipeline \
                    diagnostics mcp mcp_mutation_guard subprocess daemon daemon_application \
                    daemon_runtime daemon_ipc daemon_frontend
# halt_on_error: a race is a bug, stop at the first one.
#
# report_thread_leaks=0: this disables TSan's thread-HYGIENE check only —
# RACE detection, the reason the lane exists, is completely unaffected. Some
# daemon fixtures fork after the process has gone multi-threaded, and in the
# forked child TSan sees the parent's finished threads as never-joined even
# though the fixture joins them (test_daemon_frontend.c:726 joins the thread
# reported at :698). It fires on macOS and not Linux, i.e. it tracks fork
# semantics rather than anything about our code. The alternative was dropping
# whole suites from the lane, which costs real race coverage; this costs none.
TSAN_OPTIONS ?= halt_on_error=1:report_thread_leaks=0
# A fixed concurrent envelope keeps TSan deterministic across developer hosts
# and GitHub runners. Four workers still exercise real races without turning
# sanitizer-instrumented allocator bookkeeping into a high-core lock convoy.
# Normal ASan/native/soak paths remain uncapped. High-worker TSan diagnostics
# invoke test-runner-tsan directly so release gates cannot drift accidentally.

$(BUILD_DIR)/test-runner-tsan: $(ALL_TEST_SRCS) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(OBJS_VENDORED_TSAN) $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_TSAN) -Itests -Itests/repro -o $@ \
		$(ALL_TEST_SRCS) $(PROD_SRCS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_TSAN) \
		$(LDFLAGS_TSAN)

test-tsan: $(BUILD_DIR)/test-runner-tsan
	@echo "ThreadSanitizer workers: 4"
	cd $(CURDIR) && CBM_WORKERS=4 TSAN_OPTIONS="$(TSAN_OPTIONS)" \
		$(BUILD_DIR)/test-runner-tsan $(TEST_TSAN_SUITES)

# Real-binary POSIX lifecycle smoke. The endpoint is deliberately account-wide;
# an explicit Make invocation requires a clean rendezvous and fails rather than
# silently skipping an occupied one. Deterministic C tests cover Windows IPC.
test-daemon-smoke: $(BUILD_DIR)/codebase-memory-mcp
	cd $(CURDIR) && CBM_DAEMON_SMOKE_REQUIRE_RUN=1 python3 tests/test_daemon_smoke.py $(BUILD_DIR)/codebase-memory-mcp

# ── Production binary ────────────────────────────────────────────

# Grammar/TS/LSP objects for production (compiled with relaxed warnings, -O2)
GRAMMAR_OBJS_PROD = $(patsubst $(CBM_DIR)/%.c,$(BUILD_DIR)/prod_%.o,$(GRAMMAR_SRCS))
TS_RUNTIME_OBJ_PROD = $(BUILD_DIR)/prod_ts_runtime.o
LSP_OBJ_PROD = $(BUILD_DIR)/prod_lsp_all.o
PP_OBJ_PROD = $(BUILD_DIR)/prod_preprocessor.o

$(BUILD_DIR)/prod_%.o: $(CBM_DIR)/%.c $(GRAMMAR_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS) -c -o $@ $<

$(BUILD_DIR)/prod_ts_runtime.o: $(TS_RUNTIME_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS) -c -o $@ $<

$(BUILD_DIR)/prod_lsp_all.o: $(LSP_UNITY_DEPS) | $(BUILD_DIR)
	$(CC) $(GRAMMAR_CFLAGS) -c -o $@ $<

$(BUILD_DIR)/prod_preprocessor.o: $(CBM_DIR)/preprocessor.cpp | $(BUILD_DIR)
	$(CXX) $(CXXFLAGS_PROD) -w -I$(CBM_DIR)/vendored -c -o $@ $<

# Vendored LZ4 (compiled separately, not unity-built via lz4_store.c)
LZ4_OBJ_PROD = $(BUILD_DIR)/prod_lz4.o $(BUILD_DIR)/prod_lz4hc.o
$(BUILD_DIR)/prod_lz4.o: $(CBM_DIR)/vendored/lz4/lz4.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -O2 -w $(MEMWASTE_VENDOR_CFLAGS) -I$(CBM_DIR) -c -o $@ $<
$(BUILD_DIR)/prod_lz4hc.o: $(CBM_DIR)/vendored/lz4/lz4hc.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -O2 -w $(MEMWASTE_VENDOR_CFLAGS) -I$(CBM_DIR)/vendored/lz4 -c -o $@ $<

# Vendored zstd (compiled separately, not unity-built via zstd_store.c)
ZSTD_OBJ_PROD = $(BUILD_DIR)/prod_zstd.o
$(BUILD_DIR)/prod_zstd.o: $(CBM_DIR)/vendored/zstd/zstd.c | $(BUILD_DIR)
	$(CC) -std=c11 -D_DEFAULT_SOURCE -O2 -w $(MEMWASTE_VENDOR_CFLAGS) -I$(CBM_DIR)/vendored/zstd -c -o $@ $<

OBJS_VENDORED_PROD = $(MIMALLOC_OBJ_PROD) $(SQLITE3_OBJ_PROD) $(TRE_OBJ_PROD) $(GRAMMAR_OBJS_PROD) $(TS_RUNTIME_OBJ_PROD) $(LSP_OBJ_PROD) $(PP_OBJ_PROD) $(LZ4_OBJ_PROD) $(ZSTD_OBJ_PROD) $(UNIXCODER_OBJ)

MAIN_SRC = src/main.c

# Rebuild when the build CONFIGURATION changes, not only when sources do. The
# product binary is compiled in ONE shot from sources, so after a TEST_SEAMS or
# version flip make finds the binary newer than every source and skips the recipe
# entirely, handing back a binary built with the PREVIOUS configuration. The
# dangerous direction is a release build silently keeping test seams, which is a
# property no reviewer can see by reading the diff. The stamp's CONTENT is the
# configuration and it is rewritten only when that content changes, so ordinary
# incremental builds are unaffected. (Single-quoted: the signature may contain
# the escaped quotes of -DCBM_VERSION, which are literal inside '', but must not
# contain a literal single quote.)
# SANITIZE belongs here: it changes the instrumentation compiled into every
# object, so a build that only changes it MUST rebuild. Its absence made
# `scripts/test.sh SANITIZE= ...` -- the documented way to get a plain build
# for trap debugging -- silently re-run the previously instrumented binary,
# which during this bisect produced a "crashes without sanitizers too" result
# that was pure artifact and sent the investigation down the wrong path.
BUILD_CONFIG_SIG := TEST_SEAMS=$(TEST_SEAMS)|CFLAGS_EXTRA=$(CFLAGS_EXTRA)|SANITIZE=$(SANITIZE)|MEMWASTE=$(MEMWASTE)|MEMWASTE_ACCESS=$(MEMWASTE_ACCESS)|MEMWASTE_PROFILE=$(MEMWASTE_PROFILE)
.PHONY: build-config-check
build-config-check:
$(BUILD_DIR)/.build-config: build-config-check | $(BUILD_DIR)
	@printf '%s\n' '$(BUILD_CONFIG_SIG)' > $@.tmp
	@if cmp -s $@.tmp $@; then rm -f $@.tmp; \
	else mv -f $@.tmp $@; rm -f $(BUILD_DIR)/codebase-memory-mcp; \
	echo "=== build config changed -> full rebuild: $(BUILD_CONFIG_SIG) ==="; fi

$(BUILD_DIR)/codebase-memory-mcp: $(MAIN_SRC) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(OBJS_VENDORED_PROD) $(BUILD_DIR)/.build-config $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_PROD) -o $@ \
		$(MAIN_SRC) $(PROD_SRCS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_PROD) \
		$(LDFLAGS)

cbm: $(BUILD_DIR)/codebase-memory-mcp
	@echo "Built: $(BUILD_DIR)/codebase-memory-mcp"

# ── Build with embedded UI (requires Node.js) ───────────────────

# Swap embedded_stub.c for the generated embedded_assets.c
UI_SRCS_WITH_ASSETS = $(subst src/ui/embedded_stub.c,src/ui/embedded_assets.c,$(UI_SRCS))
PROD_SRCS_WITH_ASSETS = $(subst src/ui/embedded_stub.c,src/ui/embedded_assets.c,$(PROD_SRCS))

# Embedded asset object files (generated by embed script)
EMBED_OBJS = $(wildcard $(BUILD_DIR)/embedded/embed_*.o)

frontend:
	cd graph-ui && npm ci && npm run build

embed: frontend
	scripts/embed-frontend.sh graph-ui/dist $(BUILD_DIR)/embedded

cbm-with-ui: embed $(OBJS_VENDORED_PROD)
	$(CC) $(CFLAGS_PROD) -o $(BUILD_DIR)/codebase-memory-mcp \
		$(MAIN_SRC) $(PROD_SRCS_WITH_ASSETS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_PROD) \
		$(wildcard $(BUILD_DIR)/embedded/embed_*.o) \
		$(LDFLAGS)
	@echo "Built with UI: $(BUILD_DIR)/codebase-memory-mcp"

clean-c: export BUILD_DIR := $(BUILD_DIR)
clean-c:
	@bash -c 'source scripts/path-safety.sh && cbm_remove_build_dir "$$PWD" "$$BUILD_DIR"'

# ── Linting ─────────────────────────────────────────────────────

# clang-tidy and clang-format: use Homebrew LLVM on macOS, overridable via make args
# e.g. make lint-format CLANG_FORMAT=clang-format-18
LLVM_BIN := $(shell brew --prefix llvm 2>/dev/null)/bin
CLANG_TIDY ?= $(shell [ -x "$(LLVM_BIN)/clang-tidy" ] && echo "$(LLVM_BIN)/clang-tidy" || echo clang-tidy)
CLANG_FORMAT ?= $(shell [ -x "$(LLVM_BIN)/clang-format" ] && echo "$(LLVM_BIN)/clang-format" || echo clang-format)
CPPCHECK ?= cppcheck

# macOS SDK sysroot (needed for Homebrew LLVM to find system headers)
SYSROOT = $(shell xcrun --show-sdk-path 2>/dev/null)
SYSROOT_FLAG = $(if $(SYSROOT),-isysroot $(SYSROOT),)

# Our source files (excluding vendored, grammars, tree-sitter runtime)
LINT_SRCS = $(FOUNDATION_SRCS) $(STORE_SRCS) $(CYPHER_SRCS) $(MCP_SRCS) $(DAEMON_SRCS) \
            $(DISCOVER_SRCS) $(GRAPH_BUFFER_SRCS) $(PIPELINE_SRCS) $(SIMHASH_SRCS) $(SEMANTIC_SRCS) \
            $(TRACES_SRCS) $(WATCHER_SRCS) $(CLI_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) \
            $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(MAIN_SRC)
LINT_HDRS = $(wildcard src/**/*.h src/*.h $(CBM_DIR)/*.h)
LINT_TEST_SRCS = $(ALL_TEST_SRCS)

# clang-tidy: deep static analysis (config in .clang-tidy)
lint-tidy:
	@echo "=== clang-tidy ==="
	@$(CLANG_TIDY) --quiet $(LINT_SRCS) -- $(CFLAGS_COMMON) $(SYSROOT_FLAG)

# clang-tidy, scoped to this commit's staged changes only (scripts/lint-tidy-diff.sh).
# The pre-commit hook runs this instead of the full lint-tidy sweep above, so a
# clean commit is not blocked by pre-existing findings elsewhere in the tree.
lint-tidy-diff:
	@scripts/lint-tidy-diff.sh "$(CLANG_TIDY)" $(LINT_SRCS) -- $(CFLAGS_COMMON) $(SYSROOT_FLAG)

# cppcheck: complementary analysis (config in .cppcheck)
lint-cppcheck:
	@echo "=== cppcheck ==="
	@$(CPPCHECK) --enable=warning,style,performance,portability \
		--std=c11 --language=c \
		--suppressions-list=.cppcheck \
		--error-exitcode=1 \
		--inline-suppr \
		--quiet \
		--suppress=varFuncNullUB \
		--suppress=intToPointerCast \
		--suppress=unusedStructMember \
		--suppress=nullPointerOutOfMemory \
		--suppress=nullPointerArithmeticOutOfMemory \
		--suppress=ctunullpointerOutOfMemory \
		--suppress='nullPointer:internal/cbm/sqlite_writer.c' \
		-Isrc -Ivendored -Ivendored/sqlite3 \
		-I$(CBM_DIR) -I$(TS_INCLUDE) -I$(BUILD_DIR)/generated \
		$(LINT_SRCS)

# clang-format: formatting check (config in .clang-format, dry-run = no changes)
lint-format:
	@echo "=== clang-format ==="
	@$(CLANG_FORMAT) --dry-run --Werror $(LINT_SRCS) $(LINT_HDRS)

# Ban ALL NOLINT variants EXCEPT whitelisted NOLINT(misc-no-recursion).
# The whitelist is in src/foundation/recursion_whitelist.h with documented reasoning.
# Rule: NOLINT(misc-no-recursion) is allowed ONLY on function definitions that are
# listed in recursion_whitelist.h. All other NOLINT forms are banned.
lint-no-suppress:
	@echo "=== NOLINT check ==="
	@if grep -rn 'NOLINT' src/ internal/cbm/*.c internal/cbm/*.h 2>/dev/null \
		| grep -v vendored \
		| grep -v 'NOLINT(misc-no-recursion)' \
		| grep -v 'recursion_whitelist.h'; then \
		echo "ERROR: Banned NOLINT comment found in source code."; \
		echo "Only NOLINT(misc-no-recursion) is allowed, and only for whitelisted functions."; \
		echo "See src/foundation/recursion_whitelist.h for the whitelist."; \
		exit 1; \
	fi
	@echo "  Checking NOLINT(misc-no-recursion) against whitelist..."
	@scripts/check-nolint-whitelist.sh

# All linters (run with make -j3 lint for parallel execution)
lint: lint-tidy lint-cppcheck lint-format lint-no-suppress
	@echo "=== All linters passed ==="

# Memory-core linter: memory is allocated through src/foundation/mem_core.h,
# not through raw malloc/calloc/realloc/free/strdup. A checked-in baseline
# (scripts/memory-core-baseline.txt) records each file's raw-site count and the
# gate goes red the moment any file grows. Files only ever go down; lower the
# baseline line in the same change that migrates the file.
lint-memory-core:
	@echo "=== memory-core linter ==="
	@python3 scripts/lint-memory-core.py

# CI linters (no clang-tidy — platform-dependent, enforced locally via pre-commit)
lint-ci: lint-cppcheck lint-format lint-no-suppress lint-memory-core
	@echo "=== CI linters passed ==="

# ── Local memory-diagnostic lanes (not PR-CI gates by decision: the diag
#    build doubles a runner's bill for a marginal delta, and a gating analyzer
#    lane needs a suppression story the NOLINT ban deliberately forbids.
#    Run these on the local ladder; both found real bugs on first use.) ──

# Newest pinned toolchain + ASan/UBSan + straighter stacks. Separate BUILD_DIR
# so the shipping-toolchain build stays untouched.
#
# This lane also turns on the ASan checks that are OFF by default everywhere
# else, which is the difference between running ASan and running all of it:
#   detect_stack_use_after_return  a returned-to stack frame reused later
#   detect_stack_use_after_scope   a pointer outliving its enclosing block
#   strict_string_checks           str* reads validated over the whole buffer
#
# detect_invalid_pointer_pairs is deliberately NOT here. It fires during
# static initialisation inside vendored simplecpp -- a std::string global at
# simplecpp.cpp:101 -- reporting a pair whose second "pointer" is the
# sentinel 0xfffffffffffffff3, i.e. libstdc++ string internals rather than
# anything this codebase wrote. The option is a process-wide runtime flag
# with no per-file scoping, so it cannot be aimed away from vendored code the
# way the analyzer's path filter can. Enabling it would mean a permanently
# red lane reporting a non-defect, which teaches people to ignore the lane.
# The instrumentation it requires (-fsanitize=pointer-compare,pointer-
# subtract) comes out with it, since it is dead weight without the check.
# They stay on the diagnostic lane rather than the gating ones until they have
# a clean history here; promoting them is a separate, deliberate step.
DIAG_LLVM_BIN ?= /opt/homebrew/opt/llvm/bin
diag:
	@echo "=== diagnostic lane: $(shell $(DIAG_LLVM_BIN)/clang --version | head -1) ==="
	$(MAKE) -f Makefile.cbm build/diag/test-runner \
		CC=$(DIAG_LLVM_BIN)/clang CXX=$(DIAG_LLVM_BIN)/clang++ BUILD_DIR=build/diag \
		SANITIZE="-fsanitize=address,undefined -fno-omit-frame-pointer -fno-optimize-sibling-calls"
	ASAN_OPTIONS="detect_stack_use_after_return=1:strict_string_checks=1:detect_stack_use_after_scope=1" \
		./build/diag/test-runner

# ── macOS leak detection ─────────────────────────────────────────
# LeakSanitizer is ON by default under ASan on Linux, so the Linux test leg
# has had leak coverage all along and the Linux-only leaks this branch fixed
# were found there. On macOS it is OFF by default and Apple's clang refuses
# detect_leaks=1 outright ("Exiting: detect_leaks is not supported on this
# platform"), which is why this repo had NO macOS leak coverage — a whole
# platform's worth of the sanitizer matrix missing.
#
# Apple's refusal is not a darwin limitation. Upstream clang supports LSan on
# darwin/arm64: this lane runs the full suite clean and was verified to still
# catch a deliberately leaked allocation. So the lane is simply "the normal
# ASan test build, compiled by Homebrew LLVM instead of Apple clang, run with
# leak detection turned on".
LSAN_LLVM_BIN ?= $(shell brew --prefix llvm 2>/dev/null)/bin
LSAN_SUITES ?=
test-lsan:
	@echo "=== macOS leak lane: $(shell $(LSAN_LLVM_BIN)/clang --version | head -1) ==="
	$(MAKE) -f Makefile.cbm build/lsan/test-runner \
		CC=$(LSAN_LLVM_BIN)/clang CXX=$(LSAN_LLVM_BIN)/clang++ BUILD_DIR=build/lsan
	cd $(CURDIR) && ASAN_OPTIONS="detect_leaks=1:halt_on_error=1" \
		./build/lsan/test-runner $(LSAN_SUITES)

# ── Coverage-guided fuzzing (libFuzzer) ─────────────────────────
# One binary, three targets (tests/fuzz/cbm_fuzz.c): the per-file extractor,
# the Cypher parser, the TOML/YAML/JSON config editors. ASan+UBSan as in the
# test lane, plus fuzzer-no-link on EVERY object -- the vendored grammars and
# the tree-sitter runtime feed coverage back, which is where the parser state
# space lives. Needs a clang that ships libFuzzer (Homebrew LLVM on macOS; Apple
# clang does not). Run through scripts/fuzz.sh.
FUZZ_CC ?= clang
FUZZ_CXX ?= clang++
FUZZ_SANITIZE = -fsanitize=address,undefined,fuzzer-no-link -fno-omit-frame-pointer
FUZZ_SRC = tests/fuzz/cbm_fuzz.c
fuzz:
	$(MAKE) -f Makefile.cbm build/fuzz/cbm-fuzz BUILD_DIR=build/fuzz \
		CC=$(FUZZ_CC) CXX=$(FUZZ_CXX) SANITIZE="$(FUZZ_SANITIZE)"

$(BUILD_DIR)/cbm-fuzz: $(FUZZ_SRC) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) $(OBJS_VENDORED_TEST) $(PROJECT_HDRS) | $(BUILD_DIR)
	$(CC) $(CFLAGS_TEST) -fsanitize=fuzzer -o $@ \
		$(FUZZ_SRC) $(PROD_SRCS) \
		$(EXTRACTION_SRCS) $(AC_LZ4_SRCS) $(ZSTD_SRCS) $(SQLITE_WRITER_SRC) \
		$(OBJS_VENDORED_TEST) \
		$(LDFLAGS_TEST)

# Path-sensitive memory analysis: leak paths, null derefs, uninitialized reads.
# Non-gating: triage findings against the code (this lane's first run produced
# 9 real fixes and 6 recorded false positives — see the analyzer batch commit).
LINT_MEM_CHECKS = -*,clang-analyzer-unix.Malloc,clang-analyzer-unix.MallocSizeof,clang-analyzer-core.NullDereference,clang-analyzer-core.CallAndMessage,clang-analyzer-core.UndefinedBinaryOperatorResult,clang-analyzer-core.uninitialized.*,clang-analyzer-cplusplus.NewDelete,clang-analyzer-cplusplus.NewDeleteLeaks
lint-mem:
	@echo "=== clang-analyzer memory lane (non-gating; triage, don't suppress) ==="
	@printf '%s\n' $(LINT_SRCS) | xargs -P 10 -I{} $(CLANG_TIDY) --quiet \
		--checks='$(LINT_MEM_CHECKS)' {} -- $(CFLAGS_COMMON) $(SYSROOT_FLAG) 2>/dev/null; true

# Gating variant: identical run, but vendored-tree diagnostics are excluded
# (analyzer diagnostics bypass --header-filter by design; this mirrors the
# .cppcheck vendored suppression) and any finding the gate cannot account for
# fails the target. A finding here is a leak path, null deref, or uninitialized
# read the analyzer can prove — triage it against the code.
#
# A finding is accounted for by being FIXED, or — only where the analyzer is
# genuinely wrong — by an argued entry in scripts/lint-mem-whitelist.txt. Each
# entry is pinned to the sha256 of the function it argues about, so editing
# that function invalidates it and the finding must be argued again against
# the new code. A suppression is never allowed to outlive its reasoning, and
# NOLINT is never honoured here.
lint-mem-ci:
	@echo "=== clang-analyzer memory gate ==="
	@printf '%s\n' $(LINT_SRCS) | xargs -P 4 -I{} $(CLANG_TIDY) --quiet \
		--checks='$(LINT_MEM_CHECKS)' {} -- $(CFLAGS_COMMON) $(SYSROOT_FLAG) 2>/dev/null \
		| python3 scripts/lint-mem-gate.py

# ── Security audit (6 layers) ────────────────────────────────────

# Run all security checks: static audit, binary strings, UI, install, network
# Requires: production binary already built (make cbm)
security: cbm
	@echo "=== Running security audit suite ==="
	scripts/security-audit.sh
	scripts/security-strings.sh $(BUILD_DIR)/codebase-memory-mcp
	scripts/security-ui.sh
	scripts/security-install.sh $(BUILD_DIR)/codebase-memory-mcp
	scripts/security-network.sh $(BUILD_DIR)/codebase-memory-mcp
	scripts/security-fuzz.sh $(BUILD_DIR)/codebase-memory-mcp
	scripts/security-vendored.sh
	@echo "=== All security checks passed ==="