Directories
¶
| Path | Synopsis |
|---|---|
|
Command approver runs one scripted run to a publication-shaped approval, serves approver/webhook over its database on a loopback port, and acts as the chat bot on the other end: it fetches the approval's text rendering, prints it as the message an operator would read, posts the decision bound to the hash it showed, and then resumes the run the way the consumer's own process would.
|
Command approver runs one scripted run to a publication-shaped approval, serves approver/webhook over its database on a loopback port, and acts as the chat bot on the other end: it fetches the approval's text rendering, prints it as the message an operator would read, posts the decision bound to the hash it showed, and then resumes the run the way the consumer's own process would. |
|
live
module
|
|
|
mcp
module
|
|
|
Command recheck shows a finished run checked again: a scripted agent reads, writes, and publishes under a lenient policy that allows all three; the run is then re-checked under a stricter policy, which prints the steps it would have stopped; last, one event is altered in a copy of the database, and the check agentrt verify runs finds it.
|
Command recheck shows a finished run checked again: a scripted agent reads, writes, and publishes under a lenient policy that allows all three; the run is then re-checked under a stricter policy, which prints the steps it would have stopped; last, one event is altered in a copy of the database, and the check agentrt verify runs finds it. |
|
Command scripted runs one deterministic agent run against in-memory tools and prints the persisted event trace.
|
Command scripted runs one deterministic agent run against in-memory tools and prints the persisted event trace. |
Click to show internal directories.
Click to hide internal directories.