09. Agent Permission Is More Than Allow or Deny
Authorization decides whether one principal may perform one action on one resource under specific conditions
系列专题
Agent Runtime Lab: From Packet Capture to Replay
16 篇文章，按顺序阅读或从当前问题进入。
07. Are Parallel Tool Calls Actually Faster?
Concurrency shortens only independent waiting time and adds result joining, cancellation, and resource pressure
12. Context, Summaries, and Long-Term Memory Are Different
Longer retention does not create stronger knowledge; unverified memory carries old errors into new tasks
15. Evaluating an Agent Beyond Its Final Answer
A plausible answer does not prove that evidence is real, execution was authorized, or interruption recovery is correct
01. How System Prompts Are Assembled
The model does not receive one prompt. It receives context blocks assembled from different sources for different purposes.
06. How Tool Results Should Return to the Model
The model does not observe local execution; the runtime must carry evidence into the next turn
04. How Tool Schemas Change Agent Behavior
The model does not operate the system directly; it selects from the actions exposed by the runtime
10. Preventing Duplicate Side Effects
Retrying a model call spends computation; retrying a send, payment, or create operation can change the external world twice
02. Prompt Length, Context Growth, and Cache Cost
A second request carries more than the new input; the history policy determines latency, cost, and recoverability
00. Reading the Agent Runtime from Its Traces
Reconstructing an Agent from requests, events, and failures instead of inferring it from product descriptions