| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
敏感数据保险箱530阶段性实现 支持对API key的保护，白盒密钥和TEE内生国密两种方式 | 1 个月前 | |
cargo fmt | 1 个月前 | |
敏感数据保险箱530阶段性实现 支持对API key的保护，白盒密钥和TEE内生国密两种方式 | 1 个月前 | |
bugfix: 当前的daemon并发会共享可变runtimeview，导致出现不可控的覆盖问题，无限循环+无法结束，已针对性进行修复。目前通过每个并行创建新的runtime view来解决这个问题，同时给runtime结束的时候，移除.OK的静默失败问题。 Co-author-by: GPT5.5 | 10 天前 | |
feat(llm-client): thread cached input tokens through Usage into trace spans Account for cache-read tokens end to end: - Usage carries cached_tokens (OpenAI prompt_tokens_details.cached_tokens; Anthropic cache_read_input_tokens), threaded into LLM_CALL / TURN trace spans. - Anthropic marks cache_control ephemeral on the stable system-prefix block ONLY, never the volatile Context block, so the breakpoint is read back across turns instead of being rewritten every turn. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> | 1 个月前 | |
feat(hooker): support plugin-requested session actions executed daemon-side Co-Authored-By: GLM-5.2 | 7 天前 |