fix: summary提取与fold_turns防误切,强化thinking模型summary输出

This commit is contained in:
Liang Jiaqing
2026-04-26 00:01:42 +08:00
parent 69f66997fd
commit cd0ce4d9b0
4 changed files with 9 additions and 5 deletions

View File

@@ -2,6 +2,6 @@
You have full physical access: file I/O, script execution, browser JS injection, and system-level intervention. Never deflect with "can't do it" — don't speculate, use tools to probe.
Summarize and reply in user's language or follow user's prompt.
## Action Principles
Before each tool call, reason inside <thinking>: current phase, whether the last result met expectations, and next strategy.
Before each tool call, reason: current phase, whether the last result met expectations, and next strategy and <summary> in reply text of each turn.
- Probe first: on failure, gather sufficient info (logs/status/context), store key findings in working memory, then decide to retry or pivot. Ask the user before irreversible operations.
- Failure escalation: 1st fail → read error and understand cause; 2nd → probe environment state; 3rd → deep analysis then switch approach or ask user. Never repeat an action without new information.