Support native macOS speech relocation and safe indexing

tools/speech-runtime/CMakeLists.txt

@@ -33,6 +33,11 @@ else()
     set(GGML_METAL OFF CACHE BOOL "" FORCE)
   endif()
 endif()
+if(APPLE AND NOT SEARCHI_INTERNAL_CPU)
+  # Every dylib/backend must resolve beside the installed worker, without the build tree.
+  set(CMAKE_INSTALL_RPATH "@loader_path")
+  set(CMAKE_BUILD_WITH_INSTALL_RPATH ON)
+endif()
 if(UNIX AND NOT APPLE AND NOT SEARCHI_INTERNAL_CPU)
   # The staged worker and every dynamic backend live together. RUNPATH is
   # non-transitive, so each shared target needs its own relocatable lookup.
@@ -51,7 +56,7 @@ if(MSVC)
   target_compile_options(searchi-speech-worker PRIVATE /utf-8)
 endif()
 if(APPLE)
-  set_target_properties(searchi-speech-worker PROPERTIES BUILD_RPATH "$ORIGIN;@loader_path" INSTALL_RPATH "$ORIGIN;@loader_path")
+  set_target_properties(searchi-speech-worker PROPERTIES BUILD_RPATH "@loader_path" INSTALL_RPATH "@loader_path")
 elseif(UNIX)
   set_target_properties(searchi-speech-worker PROPERTIES BUILD_RPATH "$ORIGIN" INSTALL_RPATH "$ORIGIN")
 endif()

tools/speech-runtime/macos_smoke.py

@@ -0,0 +1,30 @@
+"""Check installed Mac speech linkage and real recognition of an owned PCM fixture."""
+import argparse,json,struct,subprocess
+from pathlib import Path
+
+def check_runtime(runtime):
+    names={p.name for p in runtime.iterdir() if p.is_file()}
+    for p in runtime.iterdir():
+        if not p.is_file() or not (p.name=='searchi-speech-worker' or p.suffix in {'.dylib','.so'}):continue
+        loads=subprocess.check_output(['otool','-L',str(p)],text=True).splitlines()[1:]
+        for line in loads:
+            dep=line.strip().split(' (',1)[0]
+            assert dep.startswith(('/System/Library/','/usr/lib/')) or dep.startswith('@rpath/') and Path(dep).name in names,(p.name,dep)
+        meta=subprocess.check_output(['otool','-l',str(p)],text=True).splitlines()
+        paths=[meta[i+2].strip().split(' (',1)[0].removeprefix('path ')for i,l in enumerate(meta)if l.strip()=='cmd LC_RPATH']
+        assert paths and all(x=='@loader_path' for x in paths),(p.name,paths)
+
+def frames(raw):
+    out=[]
+    while raw:
+        assert len(raw)>=4
+        n=struct.unpack('<I',raw[:4])[0];assert 0<n<=4*1024*1024 and len(raw)>=4+n
+        out.append(json.loads(raw[4:4+n]));raw=raw[4+n:]
+    return out
+
+if __name__=='__main__':
+    a=argparse.ArgumentParser();a.add_argument('--runtime',type=Path,required=True);a.add_argument('--models',type=Path,required=True);a.add_argument('--pcm',type=Path,required=True);a.add_argument('--output',type=Path,required=True);args=a.parse_args();check_runtime(args.runtime)
+    pcm=args.pcm.read_bytes();assert len(pcm)%4==0 and 0<len(pcm)//4<=480000
+    command=[str(args.runtime/'searchi-speech-worker'),str(args.models/'ggml-base.bin'),str(args.models/'ggml-silero-v6.2.0.bin'),'auto']
+    result=subprocess.run(command,input=b'\x02'+struct.pack('<I',len(pcm)//4)+pcm,capture_output=True,timeout=180,check=True)
+    messages=frames(result.stdout);assert len(messages)==2 and messages[0]['ready'] and messages[0]['distribution_auto'];assert messages[1]['ok'];text=' '.join(x.get('text','')for x in messages[1].get('sentences',[])).lower();assert 'free' in text and 'equal' in text,text;args.output.write_text(json.dumps(messages,indent=2));print('PASS: installed @loader_path closure and actual recognition; backend',messages[1].get('backend_observed'))