@@ -324,8 +324,14 @@ jobs:
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
+      # Pinned: the unversioned `llvm` formula tracks Homebrew stable, so the
+      # leg's compiler changed under us when stable moved 22 -> 23 (a new
+      # -Wunused-but-set-global under -Werror broke the build on whichever
+      # runner drew the 23 bottle, and passed on the ones that drew 22). A
+      # test verdict must be a function of the code, not of the image snapshot;
+      # moving to a newer major is a deliberate one-line bump here.
       - name: Install LSan-capable toolchain
-        run: brew install llvm ccache
+        run: brew install llvm@22 ccache
 
       - name: Compiler cache (content-verified, restore)
         uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
@@ -340,7 +346,7 @@ jobs:
         env:
           ASAN_OPTIONS: "detect_leaks=1:halt_on_error=1"
         run: |
-          LLVM_PREFIX="$(brew --prefix llvm)"
+          LLVM_PREFIX="$(brew --prefix llvm@22)"
           scripts/test.sh CC="$LLVM_PREFIX/bin/clang" CXX="$LLVM_PREFIX/bin/clang++"
 
       - name: Compiler cache (save)
 
@@ -247,6 +247,18 @@ The upstream indexing engine is intentionally preserved through the CLI-first mi
 
 The first vertical slice does **not** rewrite the graph schema, parser pipeline, store format, or existing indexes.
 
+### Shared graph artifact
+
+`.codebase-memory/graph.db.zst` is an optional zstd-compressed snapshot of the graph that sits next to the source. `codebase-memory-cli index` writes or refreshes it (the watcher refreshes it with a faster, lower-compression tier), and a first `index` on a clone with no local database imports it before running incremental indexing. A `.codebase-memory/.gitattributes` line with `merge=ours` is created on first export so concurrent edits do not conflict on the binary file.
+
+- **Commit it deliberately.** The artifact is rewritten on every index, including the watcher's fast tier, and git stores each rewrite as a full new blob. Committing every refresh turns a 20 MB file into gigabytes of history. Pick a cadence (a release, a milestone, a nightly job) rather than committing every save.
+- **Git LFS, if it must move on every commit.** Track it from the repo-root `.gitattributes` and leave the auto-created `.codebase-memory/.gitattributes` in place; the nearer file keeps supplying `merge=ours`, and only `filter` comes from the root:
+  ```gitattributes
+  .codebase-memory/graph.db.zst filter=lfs diff=lfs merge=lfs -text
+  ```
+  Track only the `.zst`; `artifact.json` is small and carries the schema version. The attribute applies to future commits only, so a repo that already has the blobs in history needs `git-filter-repo` first. GitHub meters LFS storage and bandwidth, and every teammate needs `git lfs install`; without it the checkout leaves a pointer file, the integrity-checked import refuses it, and they fall back to a full reindex.
+- **Optional.** Add `.codebase-memory/` to `.gitignore` if everyone should reindex from scratch.
+
 ## Configuration
 
 Common commands:
 
@@ -0,0 +1,59 @@
+/* @vitest-environment jsdom */
+import "@testing-library/jest-dom/vitest";
+import { cleanup, render, screen, waitFor } from "@testing-library/react";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { App } from "./App";
+import { messages } from "./lib/i18n";
+
+vi.mock("./components/GraphTab", () => ({ GraphTab: () => null }));
+vi.mock("./components/StatsTab", () => ({ StatsTab: () => null }));
+vi.mock("./components/ControlTab", () => ({ ControlTab: () => null }));
+vi.mock("./lib/i18n", async (importOriginal) => {
+  const actual = await importOriginal<typeof import("./lib/i18n")>();
+  return { ...actual, useUiMessages: () => messages.en };
+});
+
+describe("App", () => {
+  afterEach(() => {
+    cleanup();
+    vi.unstubAllGlobals();
+    window.history.replaceState(null, "", "/");
+  });
+
+  it("shows the serving binary version", async () => {
+    vi.stubGlobal("fetch", vi.fn(async () =>
+      new Response(JSON.stringify({ lang: "en", version: "0.10.8" }), {
+        status: 200,
+        headers: { "Content-Type": "application/json" },
+      }),
+    ));
+
+    render(<App />);
+
+    expect(await screen.findByText("v0.10.8")).toBeVisible();
+  });
+
+  it("hides the version when the config has no string version", async () => {
+    const fetchMock = vi.fn(async () =>
+      new Response(JSON.stringify({ lang: "en", version: 108 }), { status: 200 }),
+    );
+    vi.stubGlobal("fetch", fetchMock);
+
+    render(<App />);
+
+    await waitFor(() => expect(fetchMock).toHaveBeenCalledWith("/api/ui-config"));
+    expect(screen.queryByTitle("Server version")).not.toBeInTheDocument();
+  });
+
+  it("hides the version when the config request fails", async () => {
+    const fetchMock = vi.fn(async () => {
+      throw new Error("offline");
+    });
+    vi.stubGlobal("fetch", fetchMock);
+
+    render(<App />);
+
+    await waitFor(() => expect(fetchMock).toHaveBeenCalledWith("/api/ui-config"));
+    expect(screen.queryByTitle("Server version")).not.toBeInTheDocument();
+  });
+});
@@ -33,8 +33,24 @@ function routeUrl(tab: TabId, project: string | null): string {
 export function App() {
   const t = useUiMessages();
   const [route, setRoute] = useState<RouteState>(readRoute);
+  const [version, setVersion] = useState<string | null>(null);
   const { tab: activeTab, project: selectedProject } = route;
 
+  useEffect(() => {
+    let cancelled = false;
+    void fetch("/api/ui-config")
+      .then((response) => (response.ok ? response.json() : null))
+      .then((config) => {
+        if (!cancelled && typeof config?.version === "string" && config.version) {
+          setVersion(config.version);
+        }
+      })
+      .catch(() => {});
+    return () => {
+      cancelled = true;
+    };
+  }, []);
+
   /* Normalize the URL on first load so it always carries the current route. */
   useEffect(() => {
     const initial = readRoute();
@@ -73,6 +89,14 @@ export function App() {
             <span className="text-[13px] font-semibold text-foreground/90 tracking-tight">
               Codebase Memory
             </span>
+            {version && (
+              <span
+                className="translate-y-px text-[10px] font-mono text-foreground/30"
+                title="Server version"
+              >
+                {version.startsWith("v") ? version : `v${version}`}
+              </span>
+            )}
           </div>
 
           {/* Tabs inline in header */}
 
@@ -1,3 +1,7 @@
+/* Full declaration set for the same CBMArena, and it must precede cbm.h:
+ * internal/cbm/arena.h declares a subset and the two share the CBM_ARENA_H
+ * guard, so whichever is included first is the one this file sees. */
+#include "foundation/arena.h" // cbm_arena_init_sized
 #include "cbm.h"
 #include "arena.h" // CBMArena, cbm_arena_init/alloc/strdup/destroy
 #include "helpers.h"
@@ -871,9 +875,13 @@ static void cbm_error_regions_push(cbm_error_regions_t *acc, TSNode n) {
  * untouched.
  *
  * #1746: the Dockerfile grammar places that zero-width missing newline before
- * trailing horizontal whitespace rather than at raw EOF. Preserve the broad
- * exact-EOF rule above; only extend it past spaces/tabs when the missing token
- * is specifically a newline. */
+ * trailing whitespace rather than at raw EOF. Preserve the broad exact-EOF
+ * rule above; only extend it past blanks when the missing token is specifically
+ * a newline. */
+static bool cbm_is_blank_not_newline(char c) {
+    return c == ' ' || c == '\t' || c == '\v' || c == '\f' || c == '\r';
+}
+
 static bool cbm_is_eof_terminator_miss(TSNode n, const char *source, int source_len) {
     if (!ts_node_is_missing(n) || source_len < 0) {
         return false;
@@ -890,7 +898,7 @@ static bool cbm_is_eof_terminator_miss(TSNode n, const char *source, int source_
         return false;
     }
     for (uint32_t i = end; i < (uint32_t)source_len; i++) {
-        if (source[i] != ' ' && source[i] != '\t') {
+        if (!cbm_is_blank_not_newline(source[i])) {
             return false;
         }
     }
@@ -1323,11 +1331,27 @@ CBMFileResult *cbm_extract_file(const char *source, int source_len, CBMLanguage
     return r;
 }
 
-CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLanguage language,
-                                   const char *project, const char *rel_path,
-                                   int64_t timeout_micros, const char **extra_defines,
-                                   const char **include_paths, const CBMMacroTable *macro_table,
-                                   const CBMReturnTypeTable *return_type_table) {
+/* Initial block for the per-file traversal scratch arena, chosen by measuring
+ * arena_grow on a 14k-file TypeScript tree: it fires on one file in 12,000 at
+ * both this size and at 1 MB, and on most files at 256 KB, where the two
+ * channel walks alone are exactly 262144 bytes. 512 KB therefore buys the same
+ * growth behaviour as 1 MB for half the resident block per worker. It is also
+ * exactly MI_LARGE_MAX_OBJ_SIZE in the vendored mimalloc
+ * (vendored/mimalloc/include/mimalloc/types.h:426, MI_LARGE_PAGE_SIZE/8 with
+ * MI_ENABLE_LARGE_PAGES defaulting to 1 at :115 and not overridden here), so
+ * the block is still bin-allocated from a large page. Growth is not free at
+ * this size for the same reason: arena_grow doubles to 1 MiB, which is above
+ * that bound and so a singleton OS allocation. One file in twelve thousand
+ * pays it, which is why the cost is accepted. */
+enum { CBM_EXTRACT_SCRATCH_BLOCK = CBM_SZ_512 * CBM_SZ_1K };
+
+static CBMFileResult *extract_file_ex_body(const char *source, int source_len, CBMLanguage language,
+                                           const char *project, const char *rel_path,
+                                           int64_t timeout_micros, const char **extra_defines,
+                                           const char **include_paths,
+                                           const CBMMacroTable *macro_table,
+                                           const CBMReturnTypeTable *return_type_table,
+                                           CBMArena *scratch) {
     // Allocate result on heap (arena inside for all string data)
     enum { SINGLE = 1 };
     CBMFileResult *result = (CBMFileResult *)calloc(SINGLE, sizeof(CBMFileResult));
@@ -1446,6 +1470,7 @@ CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLangua
     // Build extraction context
     CBMExtractCtx ctx = {
         .arena = a,
+        .scratch = scratch,
         .result = result,
         .source = source,
         .source_len = source_len,
@@ -1574,6 +1599,7 @@ CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLangua
                     // Build context for expanded source — extract only calls via unified extractor
                     CBMExtractCtx pp_ctx = {
                         .arena = a,
+                        .scratch = scratch,
                         .result = result,
                         .source = expanded,
                         .source_len = expanded_len,
@@ -1810,6 +1836,26 @@ CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLangua
     return result;
 }
 
+/* Public entry. Owns the traversal scratch arena for the whole of one file's
+ * extraction: created here, handed to the body as ctx->scratch, destroyed on
+ * the way out. The body has seven early returns, so bracketing it in a wrapper
+ * is what keeps that to one create and one destroy. If the arena cannot be
+ * created, the body is handed NULL and the traversal stacks fall back to the
+ * result arena, which is what shipped before #1997. */
+CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLanguage language,
+                                   const char *project, const char *rel_path,
+                                   int64_t timeout_micros, const char **extra_defines,
+                                   const char **include_paths, const CBMMacroTable *macro_table,
+                                   const CBMReturnTypeTable *return_type_table) {
+    CBMArena scratch;
+    cbm_arena_init_sized(&scratch, CBM_EXTRACT_SCRATCH_BLOCK);
+    CBMFileResult *result = extract_file_ex_body(
+        source, source_len, language, project, rel_path, timeout_micros, extra_defines,
+        include_paths, macro_table, return_type_table, scratch.nblocks > 0 ? &scratch : NULL);
+    cbm_arena_destroy(&scratch);
+    return result;
+}
+
 void cbm_free_result(CBMFileResult *result) {
     if (!result) {
         return;
 
@@ -269,6 +269,10 @@ typedef struct {
                                         // pass_lsp_cross.c. Default false.
     bool requires_lsp_resolution;       // synthetic semantic candidate (for example an implicit
                                         // C++ operator). Never fall back to textual resolution.
+    bool callee_is_locally_bound;       // bare call foo() whose callee identifier is bound as a
+                                        // parameter of an enclosing function, so it cannot be the
+                                        // module-level foo. Python only today. Read by the
+                                        // weak-local-binding guard. Default false.
 } CBMCall;
 
 typedef struct {
@@ -589,6 +593,13 @@ typedef struct {
 
 typedef struct {
     CBMArena *arena;
+    /* Scratch for AST traversal, owned by the cbm_extract_file_ex call that
+     * built this context and destroyed when it returns. Nothing a
+     * CBMFileResult points at may be allocated here: `arena` is the result's
+     * own, and it outlives extraction by the whole pipeline (#1997). NULL in a
+     * context built without one, in which case the stacks fall back to
+     * `arena`. */
+    CBMArena *scratch;
     CBMFileResult *result;
     const char *source;
     int source_len;