5ab16b836a
Correcting the previous commit's reasoning. It claimed the difference between
this file and what production published was inert — a defaulted `webSearch:
false` and a reordered skills list. That was based on comparing the file
against the LIVE row in agent_definitions. The live row was the wrong thing to
compare against: Snapshot compares against the stored v1 in
definition_versions, and those two had diverged.
Read from production directly, v1 as published carries two skills:
skills:
- anomaly-detection
- operational-risk
and the live row carries three, with activity-analysis added. So a skill was
added to this agent after v1 was published, in place, without the version being
raised — the exact silent rewrite this branch exists to stop. It is a genuine
change of behaviour: an agent with a third skill answers differently from one
with two.
So the version is raised rather than the file being bent to match. v1 keeps
what was approved; the current definition, which is what production has been
serving, becomes v2. The earlier alignment of field order and `webSearch:
false` is kept — that part WAS serialisation, and matching it keeps future
imports quiet.
Production has three agents with version rows at all, so two others may hold
the same kind of drift. They did not conflict on this import, which means their
live rows still match what was published; it does not mean nobody edited them.
The image ships agents/, so this file only reaches production on the next
image build. Any build from main at or after this commit carries it; a build
from an older tree will fail the import again, by design.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g
1.2 KiB
1.2 KiB
id, name, description, icon, status, version, reasoning, trigger, pages, skills, starters, permissions, tools, webSearch
| id | name | description | icon | status | version | reasoning | trigger | pages | skills | starters | permissions | tools | webSearch | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| activity-agent | Activity Agent | The audit trail — what happened in this workspace, who did it, and what looks unusual. | activity | published | 2 | balanced | Use on Activity, for the event log, who did what, and anything that looks out of pattern. |
|
|
|
|
|
false |
Activity Agent
Instructions
Answer about what has happened in this workspace: which events, by which account, and when.
Report something as unusual only when it genuinely departs from the pattern in the log. Flagging ordinary activity trains the reader to ignore the flag.
This agent carries no skills of its own; Activity answers from its own page reader.
Purpose
- Report recent workspace events and who performed them.
- Surface activity that departs from the usual pattern.