feat(ai_client): add send_func + on_pre_dispatch to run_with_tool_loop; refactor _send_gemini_cli

Task 1.7 of the follow-up track. Extends run_with_tool_loop with
two optional parameters that let vendored call paths share the
shared loop + history + dispatch without forcing them through
send_openai_compatible:

- send_func: Callable[[int], NormalizedResponse] - vendor's own
  API call (default = send_openai_compatible if not provided;
  fully backward compatible)
- on_pre_dispatch: Callable[[int, list[dict]], list[dict]] -
  per-vendor hook to mutate the tool-call list before dispatch
  AND to capture results for the next round (e.g. Gemini CLI
  sets payload = tool_results_for_cli so the next send_func
  call sends the tool results back to the CLI)

_refactor _send_gemini_cli to use the new parameters. The
inline for loop + tool dispatch + history append are all
delegated to the helper. The vendor's send_func closure
handles:
- adapter.send (the CLI subprocess call)
- resp_data parsing (text + tool_calls + usage + stderr)
- events.emit for request_start + response_received
- _append_comms for IN/OUT comms logging
- The 'txt + calls -> history_add' special case

The vendor's on_pre_dispatch closure handles:
- _execute_tool_calls_concurrently (re-invoked here because
  the helper's call passes raw tool_calls but the vendor
  needs to mutate payload AND log results)
- _reread_file_items + _build_file_diff_text (file diff
  re-read at last tool result)
- MAX_ROUNDS system message
- _truncate_tool_output
- _MAX_TOOL_OUTPUT_BYTES budget warning
- Payload mutation for the next round

Green confirmed: 53 vendor + tool tests pass (14 Gemini CLI
+ 5 tool_loop core + 1 builder + 2 send_func + 6 MiniMax +
2 Grok + 7 Llama + 9 DeepSeek + 8 others). No regressions.

tests/test_ai_client_tool_loop_send_func.py

@@ -0,0 +1,47 @@
+"""Verify run_with_tool_loop supports a custom send_func for vendors
+that don't use send_openai_compatible (gemini_cli, gemini, anthropic,
+deepseek). The vendor provides a send_func that returns a
+NormalizedResponse, and the helper handles history + dispatch.
+"""
+from __future__ import annotations
+from typing import Any
+from unittest.mock import MagicMock, patch
+from src.openai_compatible import NormalizedResponse
+from src.ai_client import run_with_tool_loop
+from src.vendor_capabilities import VendorCapabilities
+
+def _make_normalized_response(text: str = "ok", tool_calls: list[dict[str, Any]] | None = None) -> NormalizedResponse:
+ return NormalizedResponse(
+  text=text, tool_calls=tool_calls or [],
+  usage_input_tokens=10, usage_output_tokens=5,
+  usage_cache_read_tokens=0, usage_cache_creation_tokens=0,
+  raw_response=None,
+ )
+
+def test_run_with_tool_loop_uses_send_func_when_provided() -> None:
+ client = MagicMock()
+ def send_func(_round_idx: int) -> NormalizedResponse:
+  return _make_normalized_response(f"from-send-func-{_round_idx}")
+ result = run_with_tool_loop(
+  client, request=lambda _i: MagicMock(),  # should be IGNORED
+  base_dir=".", vendor_name="custom",
+  send_func=send_func,
+ )
+ assert result == "from-send-func-0"
+
+def test_run_with_tool_loop_dispatches_via_send_func() -> None:
+ client = MagicMock()
+ tool_resp = _make_normalized_response(
+  "first", tool_calls=[{"id": "c1", "type": "function", "function": {"name": "t", "arguments": "{}"}}]
+ )
+ final = _make_normalized_response("done")
+ def send_func(round_idx: int) -> NormalizedResponse:
+  return [tool_resp, final][round_idx]
+ with patch("src.ai_client._execute_tool_calls_concurrently", return_value=[("t", "c1", "r", "")]) as dispatch:
+  result = run_with_tool_loop(
+   client, request=lambda _i: MagicMock(),
+   base_dir=".", vendor_name="custom",
+   send_func=send_func,
+  )
+  assert result == "done"
+  assert dispatch.call_count == 1