Agent 工程

TypeSafe Jev 用 Choice、Score 和 Noul 处理 Agent 的受约束决策，让模型负责模糊判断，代码继续掌握合法动作和副作用。

WorkflowAgent, step boundaries, and idempotency keys explain safe recovery after crashes, timeouts, and human pauses, with a proposed Lora PI Kit adaptation.

用 WorkflowAgent、Step 边界和幂等键解释 Agent 在崩溃、超时和人工暂停后怎样安全恢复，并给出 Lora PI Kit 的迁移思路。

AI agent engineering readings for September 18 to 19, 2026, with key findings, engineering implications, suggested sections, and primary sources.

覆盖 2026-09-18 至 09-19 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。

Where keys belong when coding agents call GitHub, databases, and cloud APIs, and how vaults and credential brokers define access boundaries.

解释 Coding Agent 调用 GitHub、数据库和云 API 时，应用密钥、执行器密钥和第三方凭据该放在哪里，以及 Vault 与 Credential Broker 的边界。

AI agent engineering readings for September 11 to 18, 2026, with key findings, engineering implications, suggested sections, and primary sources.

覆盖 2026-09-11 至 09-18 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。

How Tool Search loads definitions on demand, affects prompt caching, and differs from MCP connections and ARD resource discovery.

解释 Tool Search 如何按需加载工具定义，为什么它会影响 Prompt Cache，以及 MCP、Tool Search 和 ARD 分别解决什么问题。

AI agent engineering readings for September 11 to 17, 2026, with key findings, engineering implications, suggested sections, and primary sources.