refactor(pipeline): port src/pipeline from C to Zig

Makefile.cbm

@@ -161,41 +161,15 @@ MCP_SRCS =
 
 # Graph buffer module is Zig: see CBM_ZIG_SRC.
 
-# Pipeline module (new)
-PIPELINE_SRCS = \
-    src/pipeline/fqn.c \
-    src/pipeline/path_alias.c \
-    src/pipeline/laravel_routing.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/result_spill.c \
-    src/pipeline/service_bindings.c \
-    src/pipeline/pass_lsp_cross.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_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_pkgmap.c
+# Pipeline module: implemented in Zig (src/pipeline/*.zig, part of libcbm_zig).
+# lsp_resolve_shim.c compiles one inline function of lsp_resolve.h that
+# translate-c cannot hand to the Zig side.
+PIPELINE_SRCS = src/pipeline/lsp_resolve_shim.c
 
 # SimHash / MinHash, watcher and git context modules are Zig: see CBM_ZIG_SRC.
 
-# Semantic embedding module
-SEMANTIC_SRCS = src/semantic/semantic.c src/semantic/ast_profile.c src/semantic/rotsq.c
+# Semantic embedding module: implemented in Zig (src/semantic/*.zig, part of libcbm_zig)
+SEMANTIC_SRCS =
 
 # nomic-embed-code pretrained vectors (assembler blob)
 UNIXCODER_BLOB_SRC = vendored/nomic/code_vectors_blob.S
@@ -479,6 +453,28 @@ CBM_ZIG_SRCS = $(CBM_ZIG_SRC) src/cbm_zig_c.h src/cli_zig/cbm_cli_zig.zig src/cl
                src/discover/discover.h src/discover/userconfig.h \
                src/git/git_context.zig src/git/git_context.h \
                src/graph_buffer/graph_buffer.zig src/graph_buffer/graph_buffer.h \
+               src/semantic/ast_profile.zig src/semantic/fp.zig src/semantic/rotsq.zig \
+               src/semantic/semantic.zig \
+               src/semantic/ast_profile.h src/semantic/rotsq.h src/semantic/semantic.h \
+               vendored/nomic/code_vectors.h vendored/nomic/code_tokens.h \
+               src/pipeline/fqn.zig src/pipeline/laravel_routing.zig \
+               src/pipeline/pass_compile_commands.zig src/pipeline/pass_complexity.zig \
+               src/pipeline/pass_configlink.zig src/pipeline/pass_configures.zig \
+               src/pipeline/pass_enrichment.zig src/pipeline/pass_envscan.zig \
+               src/pipeline/pass_gitdiff.zig src/pipeline/pass_githistory.zig \
+               src/pipeline/pass_importance.zig src/pipeline/pass_infrascan.zig \
+               src/pipeline/pass_k8s.zig src/pipeline/pass_lsp_cross.zig \
+               src/pipeline/pass_parallel.zig src/pipeline/pass_pkgmap.zig \
+               src/pipeline/pass_route_nodes.zig src/pipeline/pass_semantic.zig \
+               src/pipeline/pass_semantic_edges.zig src/pipeline/pass_similarity.zig \
+               src/pipeline/pass_tests.zig src/pipeline/path_alias.zig src/pipeline/pipeline.zig \
+               src/pipeline/pipeline_incremental.zig src/pipeline/registry.zig \
+               src/pipeline/result_spill.zig src/pipeline/service_bindings.zig \
+               src/pipeline/util.zig src/pipeline/worker_pool.zig src/pipeline/laravel_routing.h \
+               src/pipeline/lsp_resolve.h src/pipeline/pass_lsp_cross.h \
+               src/pipeline/path_alias.h src/pipeline/pipeline_internal.h \
+               src/pipeline/result_spill.h src/pipeline/worker_pool.h \
+               src/graph_buffer/graph_buffer.h \
                src/simhash/minhash.zig src/simhash/minhash.h \
                src/store/store.zig src/store/store.h \
                src/watcher/watcher.zig src/watcher/watcher.h \

build.zig

@@ -536,37 +536,7 @@ fn grammarSources(b: *std.Build) []const []const u8 {
 const native_sources = [_][]const u8{
     "src/foundation/hash_table.c",
     "src/foundation/c_shim.c",
-    "src/pipeline/fqn.c",
-    "src/pipeline/path_alias.c",
-    "src/pipeline/laravel_routing.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/result_spill.c",
-    "src/pipeline/service_bindings.c",
-    "src/pipeline/pass_lsp_cross.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_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_pkgmap.c",
-    "src/semantic/semantic.c",
-    "src/semantic/ast_profile.c",
-    "src/semantic/rotsq.c",
+    "src/pipeline/lsp_resolve_shim.c",
     "vendored/yyjson/yyjson.c",
     "internal/cbm/cbm.c",
     "internal/cbm/extract_defs.c",

scripts/extract_nomic_vectors.py

@@ -520,7 +520,7 @@ def main():
     print()
     print("next steps:")
     print(f"  1. update Makefile.cbm: change UNIXCODER_BLOB_SRC path to vendored/nomic/")
-    print(f"  2. update #include in semantic.c: \"vendored/nomic/code_vectors.h\"")
+    print(f"  2. update #include in src/cbm_zig_c.h: \"nomic/code_vectors.h\"")
     print(f"  3. arch -arm64 make -j12 -f Makefile.cbm clean-c && arch -arm64 make -j12 -f Makefile.cbm")
 
 

scripts/security-allowlist.txt

@@ -30,7 +30,7 @@ src/mcp/server.zig:cbm_popen:update check to api.github.com (hardcoded URL)
 src/mcp/server.zig:popen:via cbm_popen wrapper calls
 
 # ── Pipeline: git history parsing (git log) ────────────────────────────────
-src/pipeline/pass_githistory.c:cbm_popen_git:git log for file history (path validated)
+src/pipeline/pass_githistory.zig:cbm_popen_git:git log for file history (path validated)
 
 # ── Allowed URLs ───────────────────────────────────────────────────────────
 # Format: URL:justification

scripts/security-audit.sh

@@ -171,7 +171,7 @@ while IFS= read -r match; do
     file=$(echo "$match" | cut -d: -f1)
     relfile="${file#"$ROOT/"}"
     case "$relfile" in
-        src/cli/cli.zig|src/pipeline/*.c|src/foundation/diagnostics.zig|src/mcp/search_tools.zig|src/mcp/index_tools.zig)
+        src/cli/cli.zig|src/pipeline/*.zig|src/foundation/diagnostics.zig|src/mcp/search_tools.zig|src/mcp/index_tools.zig)
             ;; # Known safe (diagnostics.zig: atomic .tmp+rename metrics dump to configured path;
                # search_tools.zig: search pattern/file-list temp files; index_tools.zig:
                # index supervisor response/quarantine files)

src/cbm_zig.zig

@@ -61,6 +61,37 @@ comptime {
     checkExports(@import("mcp/project_tools.zig"));
     checkExports(@import("mcp/search_tools.zig"));
     checkExports(@import("mcp/server.zig"));
+    checkExports(@import("pipeline/fqn.zig"));
+    checkExports(@import("pipeline/laravel_routing.zig"));
+    checkExports(@import("pipeline/pass_compile_commands.zig"));
+    checkExports(@import("pipeline/pass_complexity.zig"));
+    checkExports(@import("pipeline/pass_configlink.zig"));
+    checkExports(@import("pipeline/pass_configures.zig"));
+    checkExports(@import("pipeline/pass_enrichment.zig"));
+    checkExports(@import("pipeline/pass_envscan.zig"));
+    checkExports(@import("pipeline/pass_gitdiff.zig"));
+    checkExports(@import("pipeline/pass_githistory.zig"));
+    checkExports(@import("pipeline/pass_importance.zig"));
+    checkExports(@import("pipeline/pass_infrascan.zig"));
+    checkExports(@import("pipeline/pass_k8s.zig"));
+    checkExports(@import("pipeline/pass_lsp_cross.zig"));
+    checkExports(@import("pipeline/pass_parallel.zig"));
+    checkExports(@import("pipeline/pass_pkgmap.zig"));
+    checkExports(@import("pipeline/pass_route_nodes.zig"));
+    checkExports(@import("pipeline/pass_semantic.zig"));
+    checkExports(@import("pipeline/pass_semantic_edges.zig"));
+    checkExports(@import("pipeline/pass_similarity.zig"));
+    checkExports(@import("pipeline/pass_tests.zig"));
+    checkExports(@import("pipeline/path_alias.zig"));
+    checkExports(@import("pipeline/pipeline.zig"));
+    checkExports(@import("pipeline/pipeline_incremental.zig"));
+    checkExports(@import("pipeline/registry.zig"));
+    checkExports(@import("pipeline/result_spill.zig"));
+    checkExports(@import("pipeline/service_bindings.zig"));
+    checkExports(@import("pipeline/worker_pool.zig"));
+    checkExports(@import("semantic/ast_profile.zig"));
+    checkExports(@import("semantic/rotsq.zig"));
+    checkExports(@import("semantic/semantic.zig"));
     checkExports(@import("simhash/minhash.zig"));
     checkExports(@import("store/store.zig"));
     checkExports(@import("watcher/watcher.zig"));

src/cbm_zig_c.h

@@ -63,6 +63,35 @@
 #ifdef __linux__
 #include <sys/sysinfo.h>
 #endif
+
+/* C11 atomics, as translate-c can read them. translate-c has no atomic
+ * types, so a declaration that names one (the pipeline context's cancel flag,
+ * the shared id counter) would be dropped together with everything that uses
+ * it. Here an atomic type is its plain type and the atomic operations are the
+ * compiler builtins, which keeps those declarations and their layout. The Zig
+ * side reads and writes such fields with @atomicLoad / @atomicStore /
+ * @atomicRmw. Only this translation unit sees the view: the C sources keep
+ * the real <stdatomic.h>. */
+#define __CLANG_STDATOMIC_H /* keeps clang's <stdatomic.h> out */
+#define _Atomic
+typedef _Bool atomic_bool;
+typedef int atomic_int;
+typedef unsigned int atomic_uint;
+typedef long atomic_long;
+typedef unsigned long atomic_ulong;
+typedef long long atomic_llong;
+typedef unsigned long long atomic_ullong;
+#define memory_order_relaxed __ATOMIC_RELAXED
+#define memory_order_consume __ATOMIC_CONSUME
+#define memory_order_acquire __ATOMIC_ACQUIRE
+#define memory_order_release __ATOMIC_RELEASE
+#define memory_order_acq_rel __ATOMIC_ACQ_REL
+#define memory_order_seq_cst __ATOMIC_SEQ_CST
+#define atomic_load(p) __atomic_load_n((p), __ATOMIC_SEQ_CST)
+#define atomic_load_explicit(p, o) __atomic_load_n((p), (o))
+#define atomic_fetch_add(p, v) __atomic_fetch_add((p), (v), __ATOMIC_SEQ_CST)
+#define atomic_fetch_add_explicit(p, v, o) __atomic_fetch_add((p), (v), (o))
+
 #include <mimalloc.h>
 
 #include "foundation/arena.h"
@@ -91,12 +120,26 @@
 #include "foundation/system_info_internal.h"
 #include "foundation/compat_fs_internal.h"
 #include "foundation/yaml.h"
+#include "arena.h"
+#include "cbm.h"
+#include "helpers.h"
+#include "lang_specs.h"
+#include "lsp/c_lsp.h"
+#include "lsp/go_lsp.h"
+#include "lsp/java_lsp.h"
+#include "lsp/kotlin_lsp.h"
+#include "lsp/php_lsp.h"
+#include "lsp/py_lsp.h"
+#include "lsp/rust_cargo.h"
+#include "lsp/rust_lsp.h"
+#include "lsp/ts_lsp.h"
+#include "lsp/zig_lsp.h"
 #include "mcp/mcp.h"
-#include "pipeline/pipeline.h"
-#include "pipeline/worker_pool.h"
-#include "semantic/semantic.h"
+#include "nomic/code_vectors.h"
+#include "service_patterns.h"
 #include "store/store.h"
 #include "tree_sitter/api.h"
+#include "xxhash/xxhash.h"
 #include "zova/cbm_zova.h"
 #include "zova/cbm_zova_bridge.h"
 #include "zova/cbm_zova_coordination.h"
@@ -139,6 +182,16 @@ static inline FILE *cbm_zig_stderr(void) {
 #include "git/git_context.h"
 #include "graph_buffer/graph_buffer.h"
 #include "mcp/index_supervisor.h"
+#include "pipeline/laravel_routing.h"
+#include "pipeline/lsp_resolve.h"
+#include "pipeline/pass_lsp_cross.h"
+#include "pipeline/path_alias.h"
+#include "pipeline/pipeline.h"
+#include "pipeline/pipeline_internal.h"
+#include "pipeline/result_spill.h"
+#include "pipeline/worker_pool.h"
+#include "semantic/ast_profile.h"
+#include "semantic/semantic.h"
 #include "simhash/minhash.h"
 #include "watcher/watcher.h"