hive.error-recovery

工具调用失败时按决策树诊断并采取重试或修复措施，而非盲目重试或放弃。

遇到工具调用失败时按决策树来排查：先判断是短暂错误（网络、限流）还是结构性问题（权限、schema、选择器），再决定重试、修输入或记录失败。会在自动化流程、集成调用或接口不稳定时用到，避免盲目无限重试或直接放弃。核心特点是结构化诊断+可修复优先，能更高效恢复服务。

## Operational Protocol: Error Recovery

When a tool call fails:

1. **Diagnose** — classify the failure as *transient* (network blip, rate limit, timeout) or *structural* (wrong selector, missing auth, invalid schema, permission denied).

2. **Decide:**
   - Transient → retry once.
   - Structural + fixable → fix the input and retry.
   - Structural + unfixable → record the failure and move to the next item.
   - Blocking all progress → escalate.

3. **Adapt** — if the same tool has failed {{max_retries_per_tool}}+ times in a row, stop using it and find an alternative approach.

**Never silently drop a failed item.** If the item is a task in the colony queue, write the failure to the DB ins