q792602257 a5aeb8889c 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

2026-07-15 12:43:22 +08:00

..

__init__.py

feat: checkpoint device agent runtime milestones

2026-07-06 17:24:03 +08:00

config.py

feat: checkpoint device agent runtime milestones

2026-07-06 17:24:03 +08:00

model.py

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

2026-07-15 12:43:22 +08:00

models.py

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

2026-07-15 12:43:22 +08:00