Add verbose flag to ask

README.md

@@ -43,6 +43,9 @@ haiku-rag ask "Who is the author of haiku.rag?" --cite
 # Deep QA (multi-agent question decomposition)
 haiku-rag ask "Who is the author of haiku.rag?" --deep --cite
 
+# Deep QA with verbose output
+haiku-rag ask "Who is the author of haiku.rag?" --deep --verbose
+
 # Multi‑agent research (iterative plan/search/evaluate)
 haiku-rag research \
   "What are the main drivers and trends of global temperature anomalies since 1990?" \

docs/cli.md

@@ -97,7 +97,12 @@ Use deep QA for complex questions (multi-agent decomposition):
 haiku-rag ask "What are the main features and architecture of haiku.rag?" --deep --cite
 ```
 
-The QA agent will search your documents for relevant information and provide a comprehensive answer. With `--cite`, responses include citations showing which documents were used. With `--deep`, the question is decomposed into sub-questions that are answered in parallel before synthesizing a final answer.
+Show verbose output with deep QA:
+```bash
+haiku-rag ask "What are the main features and architecture of haiku.rag?" --deep --verbose
+```
+
+The QA agent will search your documents for relevant information and provide a comprehensive answer. With `--cite`, responses include citations showing which documents were used. With `--deep`, the question is decomposed into sub-questions that are answered in parallel before synthesizing a final answer. With `--verbose` (only with `--deep`), you'll see the planning, searching, evaluation, and synthesis steps as they happen.
 When available, citations use the document title; otherwise they fall back to the URI.
 
 ## Research

src/haiku/rag/app.py

@@ -194,10 +194,18 @@ class HaikuRAGApp:
             for chunk, score in results:
                 self._rich_print_search_result(chunk, score)
 
-    async def ask(self, question: str, cite: bool = False, deep: bool = False):
+    async def ask(
+        self,
+        question: str,
+        cite: bool = False,
+        deep: bool = False,
+        verbose: bool = False,
+    ):
         async with HaikuRAG(db_path=self.db_path) as self.client:
             try:
                 if deep:
+                    from rich.console import Console
+
                     from haiku.rag.qa.deep.dependencies import DeepQAContext
                     from haiku.rag.qa.deep.graph import build_deep_qa_graph
                     from haiku.rag.qa.deep.nodes import DeepPlanNode
@@ -208,7 +216,9 @@ class HaikuRAGApp:
                         original_question=question, use_citations=cite
                     )
                     state = DeepQAState(context=context)
-                    deps = DeepQADeps(client=self.client)
+                    deps = DeepQADeps(
+                        client=self.client, console=Console() if verbose else None
+                    )
 
                     start_node = DeepPlanNode(
                         provider=Config.QA_PROVIDER,

src/haiku/rag/cli.py

@@ -304,11 +304,16 @@ def ask(
         "--deep",
         help="Use deep multi-agent QA for complex questions",
     ),
+    verbose: bool = typer.Option(
+        False,
+        "--verbose",
+        help="Show verbose progress output (only with --deep)",
+    ),
 ):
     from haiku.rag.app import HaikuRAGApp
 
     app = HaikuRAGApp(db_path=db)
-    asyncio.run(app.ask(question=question, cite=cite, deep=deep))
+    asyncio.run(app.ask(question=question, cite=cite, deep=deep, verbose=verbose))
 
 
 @cli.command("research", help="Run multi-agent research and output a concise report")

tests/test_app.py

@@ -248,6 +248,23 @@ async def test_ask_with_cite(app: HaikuRAGApp, monkeypatch):
     mock_client.ask.assert_called_once_with("test question", cite=True)
 
 
+@pytest.mark.asyncio
+async def test_ask_with_verbose(app: HaikuRAGApp, monkeypatch):
+    """Test asking a question with verbose (should be ignored for non-deep)."""
+    mock_answer = "Test answer"
+    mock_client = AsyncMock()
+    mock_client.ask.return_value = mock_answer
+    mock_client.__aenter__.return_value = mock_client
+
+    mock_print = MagicMock()
+    monkeypatch.setattr(app.console, "print", mock_print)
+
+    with patch("haiku.rag.app.HaikuRAG", return_value=mock_client):
+        await app.ask("test question", verbose=True)
+
+    mock_client.ask.assert_called_once_with("test question", cite=False)
+
+
 @pytest.mark.asyncio
 async def test_ask_with_deep(app: HaikuRAGApp, monkeypatch):
     """Test asking a question with deep QA."""
@@ -308,3 +325,32 @@ async def test_ask_with_deep_and_cite(app: HaikuRAGApp, monkeypatch):
     call_kwargs = mock_graph.run.call_args[1]
     assert call_kwargs["state"].context.original_question == "test question"
     assert call_kwargs["state"].context.use_citations is True
+
+
+@pytest.mark.asyncio
+async def test_ask_with_deep_and_verbose(app: HaikuRAGApp, monkeypatch):
+    """Test asking a question with deep QA and verbose output."""
+    from haiku.rag.qa.deep.models import DeepAnswer
+
+    mock_output = DeepAnswer(answer="Deep QA answer", sources=["test.md"])
+    mock_result = MagicMock()
+    mock_result.output = mock_output
+
+    mock_graph = AsyncMock()
+    mock_graph.run.return_value = mock_result
+
+    mock_client = AsyncMock()
+    mock_client.__aenter__.return_value = mock_client
+
+    mock_print = MagicMock()
+    monkeypatch.setattr(app.console, "print", mock_print)
+
+    with patch("haiku.rag.app.HaikuRAG", return_value=mock_client):
+        with patch(
+            "haiku.rag.qa.deep.graph.build_deep_qa_graph", return_value=mock_graph
+        ):
+            await app.ask("test question", deep=True, verbose=True)
+
+    mock_graph.run.assert_called_once()
+    call_kwargs = mock_graph.run.call_args[1]
+    assert call_kwargs["deps"].console is not None

tests/test_cli.py

@@ -207,7 +207,7 @@ def test_ask():
 
         assert result.exit_code == 0
         mock_app_instance.ask.assert_called_once_with(
-            question="What is Python?", cite=False, deep=False
+            question="What is Python?", cite=False, deep=False, verbose=False
         )
 
 
@@ -221,7 +221,7 @@ def test_ask_with_cite():
 
         assert result.exit_code == 0
         mock_app_instance.ask.assert_called_once_with(
-            question="What is Python?", cite=True, deep=False
+            question="What is Python?", cite=True, deep=False, verbose=False
         )
 
 
@@ -235,7 +235,7 @@ def test_ask_with_deep():
 
         assert result.exit_code == 0
         mock_app_instance.ask.assert_called_once_with(
-            question="What is Python?", cite=False, deep=True
+            question="What is Python?", cite=False, deep=True, verbose=False
         )
 
 
@@ -249,7 +249,21 @@ def test_ask_with_deep_and_cite():
 
         assert result.exit_code == 0
         mock_app_instance.ask.assert_called_once_with(
-            question="What is Python?", cite=True, deep=True
+            question="What is Python?", cite=True, deep=True, verbose=False
+        )
+
+
+def test_ask_with_deep_and_verbose():
+    with patch("haiku.rag.app.HaikuRAGApp") as mock_app:
+        mock_app_instance = MagicMock()
+        mock_app_instance.ask = AsyncMock()
+        mock_app.return_value = mock_app_instance
+
+        result = runner.invoke(cli, ["ask", "What is Python?", "--deep", "--verbose"])
+
+        assert result.exit_code == 0
+        mock_app_instance.ask.assert_called_once_with(
+            question="What is Python?", cite=False, deep=True, verbose=True
         )