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

packages/cloud-platform/cloud/db_models.py

@@ -155,6 +155,8 @@ class PlannerDecisionLogRow(Base):
     tool_name: Mapped[str] = mapped_column(String, nullable=False)
     arguments_json: Mapped[str] = mapped_column(Text, nullable=False)
     created_at: Mapped[str] = mapped_column(String, nullable=False)
+    rationale: Mapped[str | None] = mapped_column(Text, nullable=True)
+    thinking: Mapped[str | None] = mapped_column(Text, nullable=True)
 
 
 class PluginRow(Base):

packages/cloud-platform/cloud/internal_api/api.py

@@ -504,6 +504,8 @@ def create_internal_router(
                 tool_name=decision.tool_name,
                 arguments_json=json.dumps(decision.arguments),
                 now=utc_now(),
+                rationale=getattr(decision, "text_output", None),
+                thinking=getattr(decision, "thinking", None),
             )
         logger.info(
             "planner-decision request resolved",

packages/cloud-platform/cloud/migrations/versions/0011_planner_decision_log_reflection.py

@@ -0,0 +1,27 @@
+"""Add rationale and thinking columns to planner_decision_log."""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0011_planner_decision_log_reflection"
+down_revision = "0010_skill_management"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "planner_decision_log",
+        sa.Column("rationale", sa.Text(), nullable=True),
+    )
+    op.add_column(
+        "planner_decision_log",
+        sa.Column("thinking", sa.Text(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("planner_decision_log", "thinking")
+    op.drop_column("planner_decision_log", "rationale")

packages/cloud-platform/cloud/repository.py

@@ -134,6 +134,8 @@ class PlannerDecisionRecord:
     tool_name: str
     arguments_json: str
     created_at: datetime
+    rationale: str | None = None
+    thinking: str | None = None
 
 
 class CloudRepository(Protocol):
@@ -518,6 +520,8 @@ class CloudRepository(Protocol):
         tool_name: str,
         arguments_json: str,
         now: datetime,
+        rationale: str | None = None,
+        thinking: str | None = None,
     ) -> int:
         """Insert one planner-decision log row, returning the assigned step_index.
 

packages/cloud-platform/cloud/schema.py

@@ -9,7 +9,7 @@ from alembic.runtime.migration import MigrationContext
 from cloud.database import create_database_engine, normalize_database_url
 
 
-HEAD_REVISION = "0010_skill_management"
+HEAD_REVISION = "0011_planner_decision_log_reflection"
 
 
 class SchemaVersionError(RuntimeError):

packages/cloud-platform/cloud/sql_repository.py

@@ -1694,6 +1694,8 @@ class SQLAlchemyCloudRepository:
         tool_name: str,
         arguments_json: str,
         now: datetime,
+        rationale: str | None = None,
+        thinking: str | None = None,
     ) -> int:
         with self._sessions.begin() as session:
             current_max = session.scalars(
@@ -1714,6 +1716,8 @@ class SQLAlchemyCloudRepository:
                     tool_name=tool_name,
                     arguments_json=arguments_json,
                     created_at=_iso(now),
+                    rationale=rationale,
+                    thinking=thinking,
                 )
             )
             session.flush()
@@ -1766,6 +1770,8 @@ class SQLAlchemyCloudRepository:
                 tool_name=row.tool_name,
                 arguments_json=row.arguments_json,
                 created_at=_parse_dt(row.created_at),  # type: ignore[arg-type]
+                rationale=row.rationale,
+                thinking=row.thinking,
             )
             for row in rows
         ]