Welcome To openEuler Community

Hey @chuchengkai , thanks for your contribution to the community.

Bot Usage Manual

I'm the Bot here serving you. You can find the instructions on how to interact with me at Here . That means you can comment below every pull request or issue to trigger Bot Commands. You can self-configure the PR merge rules for this repository. For more details, please refer to Here.

Contact Guide

If you have any questions, please contact the SIG: sig-intelligence ,
and any of the maintainers: @fromhsc, @gogoxiaoxiao, @huzhengce, @kaitiandu, @leon-wang2021, @liumiao27, @lyhu, @wqianli ,
and any of the committers: @chantsztung, @jie-qi, @vanient9gap, @xiangyou_xie, @xtchen .

核查结论：代码中不存在"固定重试 8 次"的规则。LLM 请求重试次数由 providers.max_retries 控制（单个 Chat 请求的最大尝试次数，含首次），代码默认值和随 RPM 发布的默认配置 plugins/mcp/ram-a-mem.json 均为 3 —— 复现中观察到的"重试 3 次"正是该默认配置的预期行为。

"LLM 服务不可用"（连接拒绝/超时等传输层错误）属于会触发重试的类别：按指数退避（1s/2s/4s…，上限 64s）重试，max_retries=3 即首次请求 + 最多 2 次重试；其余如 HTTP 400/401/404（例如 base_url 路径错误）不会重试，立即失败。

已在 PR #24 补充完整文档说明（何时触发重试、何时不触发、max_retries 的准确含义、与 reasoning_only_retry/json_repair_attempts 的关系），欢迎审阅。