3 Commits

Include renames

Author	SHA1	Message	Date
q792602257	d69be48f96	feat(planner): persist reusable action semantics	2026-07-15 18:14:28 +08:00
q792602257	367fd0d412	fix(planner): allow rationale/thinking by using tool_choice=auto ... Forced tool_choice ("any"/"required") makes both Anthropic and OpenAI skip any text/thinking block before the tool call, which silently made rationale and thinking always None despite the planner-reflection-history change's capture code being correct. Switch the primary call to tool_choice="auto" (Anthropic: type=auto, disable_parallel_tool_use=true; OpenAI: "auto") so the model can emit its reflection text, and add a one-time forced retry (Anthropic "any", OpenAI "required", thinking disabled) if the model responds without a tool call, guaranteeing a step never stalls. Also add OpenAI text_output capture from message.content, which was never extracted before (Anthropic-only gap). Update planner-reflection-history design.md/tasks.md to document the bug found during the pending manual smoke test (task 8.5) and the fix (new section 9).	2026-07-15 13:43:39 +08:00
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