ai: system mode never answers state from memory

The re-run showed "Is everything running?" parroting the example's
all-clear without checking.  The system prompt now states that state is
never known from memory or examples — every health answer starts with a
fresh get_system_status — and the example's answer cites its own
example data (service names, version) so a verbatim parrot is
self-evidently wrong.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Roland 2026-09-02 18:02:09 -06:00
parent 4e83417f8f
commit 0d0bcf4a2a
No known key found for this signature in database
GPG key ID: 1BA620CE6C9A4680

View file

@ -65,8 +65,10 @@ MODES = {
system_prompt=(
f'{COMMON_PROMPT}'
' Your job is to troubleshoot the user\'s WROLPi.'
' Start every diagnosis with get_system_status; read a failing service\'s logs with'
' get_service_logs; check drives with list_disks.'
' You never know the current state of this system from memory or from example'
' conversations: EVERY answer about services, disks, or health starts with a fresh'
' get_system_status call. Read a failing service\'s logs with get_service_logs;'
' check drives with list_disks.'
' You CANNOT execute commands or change anything — you can only read.'
' Only suggest commands that appear in the help documentation: find them with search_help,'
' quote them exactly, and include the help page link.'
@ -141,8 +143,8 @@ MODE_EXAMPLES = {
_tool_result('ex_sys_1',
'{"version": "0.28", "wrol_mode": false, "services": [{"name": "wrolpi-api",'
' "status": "running"}, {"name": "wrolpi-app", "status": "running"}], "errors": []}'),
dict(role='assistant', content='Yes — every service is running. If something misbehaves anyway,'
' tell me which page and I will read the right service\'s logs.'),
dict(role='assistant', content='The status shows both services (wrolpi-api, wrolpi-app)'
' running on version 0.28, with no errors reported.'),
),
}