feat(runtime): add planner reflection history with rationale and thinking

- ToolCallDecision captures thinking blocks and pre-tool text output
- AnthropicToolCallingClient supports optional extended thinking (budget_tokens + beta header)
- PlannedStep carries rationale and thinking from each LLM decision
- WorldEvent replaces scene_summary with rationale/thinking/page fields (backward-compatible)
- AI planner system prompt instructs reflection before each tool call
- _history_summary() emits compact {page, rationale, action, success} dicts
- Cloud DB migration 0011 adds nullable rationale/thinking columns to planner_decision_log
- OpenAI client extracts reasoning_content into thinking field

tests/test_tool_calling_client.py

@@ -435,3 +435,187 @@ def test_build_client_selects_provider_and_resolves_default_model() -> None:
 def test_build_client_honors_explicit_model_override() -> None:
     client = build_client(PlannerConfig(provider="openai", model="gpt-5.6-custom"))
     assert client.model == "gpt-5.6-custom"
+
+
+# --- thinking / text_output capture -----------------------------------------
+
+
+def test_anthropic_client_captures_thinking_block() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [
+                {"type": "thinking", "thinking": "I should tap the button."},
+                {"type": "tool_use", "name": "tap", "input": {"x": 10, "y": 20}},
+            ]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model", transport=FakeTransport(messages)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.thinking == "I should tap the button."
+    assert decision.text_output is None
+
+
+def test_anthropic_client_captures_text_block_as_text_output() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [
+                {"type": "text", "text": "Previous step succeeded. Now tapping login."},
+                {"type": "tool_use", "name": "tap", "input": {"x": 5, "y": 5}},
+            ]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model", transport=FakeTransport(messages)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.text_output == "Previous step succeeded. Now tapping login."
+    assert decision.thinking is None
+
+
+def test_anthropic_client_captures_both_thinking_and_text_output() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [
+                {"type": "thinking", "thinking": "Deep thought."},
+                {"type": "text", "text": "Step succeeded. Tapping next."},
+                {"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 1}},
+            ]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model", transport=FakeTransport(messages)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.thinking == "Deep thought."
+    assert decision.text_output == "Step succeeded. Tapping next."
+
+
+def test_anthropic_client_tool_only_response_has_none_thinking_and_text_output() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [
+                {"type": "tool_use", "name": "tap", "input": {"x": 0, "y": 0}},
+            ]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model", transport=FakeTransport(messages)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.thinking is None
+    assert decision.text_output is None
+
+
+def test_openai_client_captures_reasoning_content() -> None:
+    completions = FakeCompletions(
+        response={
+            "choices": [
+                {
+                    "message": {
+                        "reasoning_content": "I reasoned about this step.",
+                        "tool_calls": [
+                            {"function": {"name": "tap", "arguments": '{"x": 1, "y": 2}'}}
+                        ],
+                    }
+                }
+            ]
+        }
+    )
+    client = OpenAIToolCallingClient(
+        model="test-model", transport=FakeOpenAITransport(completions)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.thinking == "I reasoned about this step."
+    assert decision.text_output is None
+
+
+def test_openai_client_no_reasoning_content_gives_none_thinking() -> None:
+    completions = FakeCompletions(
+        response={
+            "choices": [
+                {
+                    "message": {
+                        "tool_calls": [
+                            {"function": {"name": "tap", "arguments": '{"x": 1, "y": 2}'}}
+                        ]
+                    }
+                }
+            ]
+        }
+    )
+    client = OpenAIToolCallingClient(
+        model="test-model", transport=FakeOpenAITransport(completions)
+    )
+    decision = client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert decision.thinking is None
+
+
+def test_anthropic_client_sends_thinking_param_when_budget_set() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [{"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 2}}]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model",
+        transport=FakeTransport(messages),
+        thinking_budget_tokens=2048,
+    )
+    client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    call = messages.calls[0]
+    assert call["thinking"] == {"type": "enabled", "budget_tokens": 2048}
+    assert "interleaved-thinking-2025-05-14" in call["betas"]
+    # max_tokens must be >= budget + 1
+    assert call["max_tokens"] >= 2049
+
+
+def test_anthropic_client_enforces_max_tokens_floor_for_thinking() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [{"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 2}}]
+        }
+    )
+    # max_tokens=1024, budget=4096 → max_tokens should be raised to 4097
+    client = AnthropicToolCallingClient(
+        model="test-model",
+        transport=FakeTransport(messages),
+        max_tokens=1024,
+        thinking_budget_tokens=4096,
+    )
+    client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    assert messages.calls[0]["max_tokens"] == 4097
+
+
+def test_anthropic_client_no_thinking_param_when_budget_not_set() -> None:
+    messages = FakeMessages(
+        response={
+            "content": [{"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 2}}]
+        }
+    )
+    client = AnthropicToolCallingClient(
+        model="test-model", transport=FakeTransport(messages)
+    )
+    client.decide(
+        system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
+    )
+    call = messages.calls[0]
+    assert "thinking" not in call
+    assert "betas" not in call