refactor(ai_client): obliterate 5 legacy model-list wrappers (Phase 4)

Phase 4 (5 of 9 cruft sites obliterated):

OBLITERATED wrappers:
1. _reread_file_items (4 callers in _send_gemini + _send_gemini_cli + 2 others)
2. _list_anthropic_models (1 caller in list_models)
3. _list_gemini_models (1 caller in list_models)
4. _extract_gemini_thoughts (1 caller in _send_gemini)
5. _list_minimax_models (2 callers in _set_minimax_provider_result + set_provider)

Migration: each caller now uses the _result sibling directly with .ok check
+ .data extraction. The Result[T] error context (structured ErrorInfo) is now
propagated instead of dropped. _send_gemini gets .data with explicit .ok check.

Updated tests to assert OBLITERATED state (5 sub-track 5 tests inverted from
'_legacy_preserved' to '_legacy_obliterated'):
- tests/test_baseline_result.py: test_phase9_redo_modules_import_cleanly
- tests/tier2/phase10_invariant_test.py: _list_gemini_models removed from list
- tests/tier2/phase10_site1_test.py: _legacy_unchanged -> _legacy_obliterated
- tests/tier2/phase11_invariant_test.py: _extract/_list_minimax moved to obliterated
- tests/tier2/phase11_sites78_test.py: _legacy_preserved -> _legacy_obliterated
- tests/tier2/phase12_invariant_test.py: _list_anthropic moved to obliterated
- tests/tier2/phase12_site4_test.py: _legacy_preserved -> _legacy_obliterated
- tests/test_gemini_thinking_format.py: helper uses _result directly
- tests/test_cruft_removal.py: 5 new obliterated-wrappers invariant tests

Test result: 122/122 pass (31 baseline + 16 heuristic + 9 cruft + 5 thinking + 61 tier2).
Audit gate: src/ai_client.py --strict exits 0 (no new violations introduced).
Wrapper count: 9 -> 3 (Phase 5-6 remaining: rag_engine 1, gui_2 2).

src/ai_client.py

@@ -389,12 +389,12 @@ def _set_minimax_provider_result(model: str) -> Result[list[str]]:
  Returns the list of valid model names. On credentials load failure,
  returns Result(data=[], errors=[ErrorInfo(...)]). The legacy caller
  (set_provider) inspects result.ok to decide whether to use the
- fetched list or fall back to _list_minimax_models("") for empty key.
+ fetched list or fall back to _list_minimax_models_result("") for empty key.
  """
  try:
   creds = _load_credentials()
   api_key = creds.get("minimax", {}).get("api_key", "")
-  return Result(data=_list_minimax_models(api_key))
+  return Result(data=_list_minimax_models_result(api_key).data)
  except (OSError, ValueError) as e:
   return Result(
    data=[],
@@ -424,7 +424,8 @@ def set_provider(provider: str, model: str, validate: bool = True) -> None:
    _model = model
  elif provider == "minimax":
   result = _set_minimax_provider_result(model)
-  valid_models = result.data if result.ok else _list_minimax_models("")
+  fallback_result = _list_minimax_models_result("")
+  valid_models = result.data if result.ok else fallback_result.data
   if model not in valid_models:
    _model = "MiniMax-M2.5"
   else:
@@ -492,11 +493,17 @@ def reset_session() -> None:
 
 def list_models(provider: str) -> list[str]:
  creds = _load_credentials()
- if   provider == "gemini":     return _list_gemini_models(creds["gemini"]["api_key"])
- elif provider == "anthropic":  return _list_anthropic_models()
+ if   provider == "gemini":
+  result = _list_gemini_models_result(creds["gemini"]["api_key"])
+  return result.data if result.ok else []
+ elif provider == "anthropic":
+  result = _list_anthropic_models_result()
+  return result.data if result.ok else []
  elif provider == "deepseek":   return _list_deepseek_models(creds["deepseek"]["api_key"])
  elif provider == "gemini_cli": return _list_gemini_cli_models()
- elif provider == "minimax":    return _list_minimax_models(creds["minimax"]["api_key"])
+ elif provider == "minimax":
+  result = _list_minimax_models_result(creds["minimax"]["api_key"])
+  return result.data if result.ok else []
  elif provider == "qwen":       return _list_qwen_models()
  elif provider == "grok":       return _list_grok_models()
  elif provider == "llama":      return _list_llama_models()
@@ -1070,40 +1077,6 @@ def _reread_file_items_result(file_items: list[dict[str, Any]]) -> Result[tuple[
  return Result(data=(refreshed, changed), errors=errors)
 
 
-def _reread_file_items(file_items: list[dict[str, Any]]) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]:
- """
-  Re-reads file items from the filesystem if their modification times have changed.
-  Functional Purpose:
-   Iterates through context files, compares current filesystem mtime against cached mtime,
-   and reads file contents if changes are detected, returning both the full refreshed set
-   and the subset of changed items.
-
-  Parameters & Inputs: file_items (list[dict[str, Any]]): List of file dictionaries containing keys "path" and optionally "mtime", "content".
-
-  Returns: tuple[list[dict[str, Any]], list[dict[str, Any]]]: A tuple containing (refreshed_items, changed_items).
-
-  Immediate-Mode DAG / Thread Context:
-   Called by: _send_gemini
-   Calls: pathlib.Path.stat, pathlib.Path.read_text
-
-  SSDL: `o-> [I:get_mtime] -> [B:changed?] -> [I:read_file] -> [T:diff_text]`
-
-  Thread Boundaries: Runs synchronously in the caller thread. Does synchronous blocking file system I/O.
-
-  Thin wrapper over _reread_file_items_result; the legacy tuple shape is
-  preserved for backward compatibility, but the try/except Exception lives
-  in the Result variant (where it can capture structured ErrorInfo).
-  Per-file read errors are logged to stderr as warnings (operator-visible
-  drain) and included in err_item[\"error\"] = True for in-band flag checks.
- """
- result = _reread_file_items_result(file_items)
- if result.errors:
-  for err in result.errors:
-   sys.stderr.write(f"[AI_CLIENT] {err.ui_message()}\n")
-  sys.stderr.flush()
- refreshed, changed = result.data
- return refreshed, changed
-
 def _build_file_context_text(file_items: list[dict[str, Any]]) -> str:
  if not file_items:
   return ""
@@ -1355,9 +1328,6 @@ def _list_anthropic_models_result() -> Result[list[str]]:
   )
 
 
-def _list_anthropic_models() -> list[str]:
- return _list_anthropic_models_result().data
-
 def _ensure_anthropic_client() -> None:
  global _anthropic_client
  anthropic = _require_warmed("anthropic")
@@ -1581,7 +1551,8 @@ def _send_anthropic(
      })
     _append_comms("OUT", "request", {"message": f"[TOOL OUTPUT BUDGET EXCEEDED: {_cumulative_tool_bytes} bytes]"})
    if file_items:
-    file_items, changed = _reread_file_items(file_items)
+    _reread_result = _reread_file_items_result(file_items)
+    file_items, changed = _reread_result.data
     refreshed_ctx       = _build_file_diff_text(changed)
     if refreshed_ctx:
      tool_results.append({
@@ -1665,9 +1636,6 @@ def _list_gemini_models_result(api_key: str) -> Result[list[str]]:
   )
 
 
-def _list_gemini_models(api_key: str) -> list[str]:
- return _list_gemini_models_result(api_key).data
-
 def _ensure_gemini_client() -> None:
   global _gemini_client
   genai = _require_warmed("google.genai")
@@ -1812,15 +1780,6 @@ def _extract_gemini_thoughts_result(resp: Any) -> Result[str]:
   )
 
 
-def _extract_gemini_thoughts(resp: Any) -> str:
- """
-  Extracts concatenated thinking text from a Gemini response object's parts.
-  Parts with thought=True are thinking segments; parts with thought=False or unset are visible text.
-  The google-genai SDK filters thoughts out of resp.text, so we must scan parts directly.
-  Returns "" if no thoughts are present.
- """
- return _extract_gemini_thoughts_result(resp).data
-
 def _get_gemini_history_list(chat: Any | None) -> list[Any]:
  if not chat: return []
  if hasattr(chat, "_history"):    return cast(list[Any], chat._history)
@@ -2014,7 +1973,8 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str,
     # Check if this is the last tool to trigger file refresh
     if i == len(results) - 1:
      if file_items:
-      file_items, changed = _reread_file_items(file_items)
+      _reread_result = _reread_file_items_result(file_items)
+      file_items, changed = _reread_result.data
       ctx = _build_file_diff_text(changed)
       if ctx:
        out += f"\n\n{_get_context_marker()}\n\n{ctx}"
@@ -2034,7 +1994,8 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str,
    _append_comms("OUT", "tool_result_send", {"results": log})
    payload = f_resps
   res = "\n\n".join(all_text) if all_text else "(No text returned)"
-  thought_text = _extract_gemini_thoughts(final_resp if stream_callback else resp)
+  thought_text_result = _extract_gemini_thoughts_result(final_resp if stream_callback else resp)
+  thought_text = thought_text_result.data if thought_text_result.ok else ""
   if thought_text:
    res = f"<thinking>\n{thought_text}\n</thinking>\n\n{res}"
   if monitor.enabled: monitor.end_component("ai_client._send_gemini")
@@ -2126,7 +2087,8 @@ def _send_gemini_cli(md_content: str, user_message: str, base_dir: str,
    for i, (name, call_id, out, _) in enumerate(results_iter):
     if i == len(results_iter) - 1:
      if file_items:
-      file_items, changed = _reread_file_items(file_items)
+      _reread_result = _reread_file_items_result(file_items)
+      file_items, changed = _reread_result.data
       ctx = _build_file_diff_text(changed)
       if ctx:
        out += f"\n\n{_get_context_marker()}\n\n{ctx}"
@@ -2416,7 +2378,8 @@ def _send_deepseek(md_content: str, user_message: str, base_dir: str,
    for i, (name, call_id, out, _) in enumerate(results):
     if i == len(results) - 1:
      if file_items:
-      file_items, changed = _reread_file_items(file_items)
+      _reread_result = _reread_file_items_result(file_items)
+      file_items, changed = _reread_result.data
       ctx = _build_file_diff_text(changed)
       if ctx:
        out += f"\n\n{_get_context_marker()}\n\n{ctx}"
@@ -2484,9 +2447,6 @@ def _list_minimax_models_result(api_key: str) -> Result[list[str]]:
   )
 
 
-def _list_minimax_models(api_key: str) -> list[str]:
- return _list_minimax_models_result(api_key).data
-
 def _repair_minimax_history(history: list[dict[str, Any]]) -> None:
  if not history: return
  last = history[-1]