refactor(ai_client): extract _create_gemini_cache_result helper (Phase 10 site 5)

Site L1773: cache.create block in _send_gemini had multiple global side
effects (sets _gemini_cache, _gemini_cache_created_at, _gemini_cached_file_paths,
returns chat_config with cached_content). Except body reset globals on failure.

Per TIER1_REVIEW: logging is NOT a drain. MIGRATE to Result[Any].

New helper _create_gemini_cache_result(sys_instr, tools_decl, file_items) -> Result[Any]:
- Returns Result(data=chat_config) on SDK success (sets globals, logs [CACHE CREATED])
- Returns Result(data=None, errors=[ErrorInfo]) on SDK failure (resets globals,
  logs [CACHE FAILED])
- Preserves original semantics: globals set on success, reset on failure

Caller:
  cached_config_result = _create_gemini_cache_result(sys_instr, tools_decl, file_items)
  if cached_config_result.ok:
      chat_config = cached_config_result.data

Audit: ai_client BC 5 -> 4. _send_gemini cache-related BC sites all migrated.

src/ai_client.py

@@ -1664,6 +1664,46 @@ def _should_cache_gemini_result(sys_instr: str) -> Result[bool]:
    errors=[ErrorInfo(kind=ErrorKind.INTERNAL, message=f"failed to count gemini tokens: {e}", source="ai_client._should_cache_gemini_result", original=e)],
   )
 
+def _create_gemini_cache_result(sys_instr: str, tools_decl: Any, file_items: list[dict[str, Any]] | None) -> Result[Any]:
+ """Create a Gemini cache and the corresponding GenerateContentConfig.
+
+ Returns Result(data=chat_config_with_cached_content) on success and
+ Result(data=None, errors=[ErrorInfo]) on SDK failure. Side effects on
+ globals _gemini_cache, _gemini_cache_created_at, _gemini_cached_file_paths
+ are managed inside the helper (set on success, reset on failure to match
+ original semantics).
+ """
+ global _gemini_cache, _gemini_cache_created_at, _gemini_cached_file_paths
+ types = _require_warmed("google.genai").types
+ try:
+  _gemini_cache = _gemini_client.caches.create(
+   model=_model,
+   config=types.CreateCachedContentConfig(
+    system_instruction=sys_instr,
+    tools=cast(Any, tools_decl),
+    ttl=f"{_GEMINI_CACHE_TTL}s",
+   )
+  )
+  _gemini_cache_created_at = time.time()
+  _gemini_cached_file_paths = [str(item.get("path", "")) for item in (file_items or []) if item.get("path")]
+  chat_config = types.GenerateContentConfig(
+   cached_content=_gemini_cache.name,
+   temperature=_temperature,
+   max_output_tokens=_max_tokens,
+   safety_settings=[types.SafetySetting(category=types.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, threshold=types.HarmBlockThreshold.BLOCK_ONLY_HIGH)]
+  )
+  _append_comms("OUT", "request", {"message": f"[CACHE CREATED] {_gemini_cache.name}"})
+  return Result(data=chat_config)
+ except Exception as e:
+  _gemini_cache             = None
+  _gemini_cache_created_at  = None
+  _gemini_cached_file_paths = []
+  _append_comms("OUT", "request", {"message": f"[CACHE FAILED] {type(e).__name__}: {e} \u2014 falling back to inline system_instruction"})
+  return Result(
+   data=None,
+   errors=[ErrorInfo(kind=ErrorKind.INTERNAL, message=f"failed to create gemini cache: {type(e).__name__}: {e}", source="ai_client._create_gemini_cache_result", original=e)],
+  )
+
 def _extract_gemini_thoughts(resp: Any) -> str:
  """
   Extracts concatenated thinking text from a Gemini response object's parts.
@@ -1752,29 +1792,9 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str,
    
    should_cache = _should_cache_gemini_result(sys_instr).data
    if should_cache and _gemini_client:
-    try:
-     _gemini_cache = _gemini_client.caches.create(
-      model=_model,
-      config=types.CreateCachedContentConfig(
-       system_instruction=sys_instr,
-       tools=cast(Any, tools_decl),
-       ttl=f"{_GEMINI_CACHE_TTL}s",
-      )
-     )
-     _gemini_cache_created_at = time.time()
-     _gemini_cached_file_paths = [str(item.get("path", "")) for item in (file_items or []) if item.get("path")]
-     chat_config = types.GenerateContentConfig(
-      cached_content=_gemini_cache.name,
-      temperature=_temperature,
-      max_output_tokens=_max_tokens,
-      safety_settings=[types.SafetySetting(category=types.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, threshold=types.HarmBlockThreshold.BLOCK_ONLY_HIGH)]
-     )
-     _append_comms("OUT", "request", {"message": f"[CACHE CREATED] {_gemini_cache.name}"})
-    except Exception as e:
-     _gemini_cache = None
-     _gemini_cache_created_at = None
-     _gemini_cached_file_paths = []
-     _append_comms("OUT", "request", {"message": f"[CACHE FAILED] {type(e).__name__}: {e} \u2014 falling back to inline system_instruction"})
+    cached_config_result = _create_gemini_cache_result(sys_instr, tools_decl, file_items)
+    if cached_config_result.ok:
+     chat_config = cached_config_result.data
    kwargs: dict[str, Any] = {"model": _model, "config": chat_config}
    if old_history:
     kwargs["history"] = old_history

tests/tier2/phase10_site5_test.py

@@ -0,0 +1,18 @@
+"""Phase 10 site 5: _create_gemini_cache_result helper."""
+import sys
+sys.path.insert(0, ".")
+
+
+def test_phase10_site5_create_gemini_cache_result_exists():
+    import src.ai_client
+    assert hasattr(src.ai_client, "_create_gemini_cache_result"), \
+        "_create_gemini_cache_result helper missing"
+
+
+def test_phase10_site5_create_gemini_cache_result_returns_result():
+    import src.ai_client
+    import inspect
+    fn = src.ai_client._create_gemini_cache_result
+    sig = inspect.signature(fn)
+    assert "Result" in str(sig.return_annotation), \
+        f"_create_gemini_cache_result return must be Result, got {sig.return_annotation}"