Add real-time per-tool-call audit streaming (HARNESS-WP-0002-T03)

Claude Code executes its own tools internally in --print mode -- there
is no way for a caller to externally dispatch individual tool calls
without abandoning that self-contained agent model. What
--output-format stream-json --include-hook-events does allow: observing
each tool_use/tool_result/hook event in real time.

- adapter.py: AgenticClaudeCodeAdapter gains an optional on_tool_event
  callback; streaming mode (Popen + background reader thread) is used
  only when set, blocking subprocess.run path is unchanged otherwise.
- runner.py: run_task gains emit_tool_events/on_tool_event, collecting
  events onto RunResult.tool_events and posting a tool_call hub event
  per tool when reporting is enabled.
- cli.py: --stream-tool-events flag on `run`, prints each event as a
  tagged JSON line ahead of the unchanged final result block.

Live-verified against the real claude CLI: 5 real tool events streamed
correctly (2x Bash, 1x Write) plus Stop hook lifecycle events, real
commit landed, final result block unchanged. 13 new tests
(test_adapter.py + 2 in test_runner.py), all passing.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

tests/test_runner.py

@@ -206,3 +206,65 @@ def test_taskspec_rejects_non_repo(tmp_path) -> None:
     )
     with pytest.raises(TaskSpecError, match="not a git repository"):
         TaskSpec.from_file(spec_file)
+
+
+def test_run_task_wires_on_tool_event_when_emit_tool_events(tmp_path, monkeypatch) -> None:
+    repo = _make_repo(tmp_path)
+    spec = _spec(repo)
+    captured: dict = {}
+
+    class FakeStreamingAdapter:
+        def __init__(self, workdir, tool_profile, on_tool_event=None):
+            captured["on_tool_event"] = on_tool_event
+
+        def execute_prompt(self, prompt, config):
+            captured["on_tool_event"](
+                {"type": "assistant", "message": {"content": [{"type": "tool_use", "name": "Read"}]}}
+            )
+            (repo / "HELLO.md").write_text("hi\n")
+            subprocess.run(["git", "add", "."], cwd=repo, check=True)
+            subprocess.run(
+                ["git", "-c", "user.email=t@t", "-c", "user.name=t", "commit", "-qm", "task"],
+                cwd=repo,
+                check=True,
+            )
+            from llm_connect.models import LLMResponse
+
+            return LLMResponse(content="done", model="m", usage={}, finish_reason="stop", metadata={})
+
+    monkeypatch.setattr("rein_aharness.adapter.AgenticClaudeCodeAdapter", FakeStreamingAdapter)
+
+    result = run_task(spec, report_to_hub=False, write_metrics=False, emit_tool_events=True)
+
+    assert captured["on_tool_event"] is not None
+    assert len(result.tool_events) == 1
+    assert result.tool_events[0]["message"]["content"][0]["name"] == "Read"
+
+
+def test_run_task_default_adapter_gets_no_callback_when_not_requested(tmp_path, monkeypatch) -> None:
+    repo = _make_repo(tmp_path)
+    spec = _spec(repo)
+    captured: dict = {}
+
+    class FakeAdapter:
+        def __init__(self, workdir, tool_profile, on_tool_event=None):
+            captured["on_tool_event"] = on_tool_event
+
+        def execute_prompt(self, prompt, config):
+            (repo / "HELLO.md").write_text("hi\n")
+            subprocess.run(["git", "add", "."], cwd=repo, check=True)
+            subprocess.run(
+                ["git", "-c", "user.email=t@t", "-c", "user.name=t", "commit", "-qm", "task"],
+                cwd=repo,
+                check=True,
+            )
+            from llm_connect.models import LLMResponse
+
+            return LLMResponse(content="done", model="m", usage={}, finish_reason="stop", metadata={})
+
+    monkeypatch.setattr("rein_aharness.adapter.AgenticClaudeCodeAdapter", FakeAdapter)
+
+    result = run_task(spec, report_to_hub=False, write_metrics=False)
+
+    assert captured["on_tool_event"] is None
+    assert result.tool_events == []