a digital entity named phi that roams bsky phi.zzstoatzz.io
2
fork

Configure Feed

Select the types of activity you want to include in your feed.

fix: clarify check_services is operator infrastructure, not phi's own status

phi was calling check_services when asked "you online?" because it
conflated its own status with operator service health. tightened the
operational instructions and tool docstring to make the distinction
explicit.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

zzstoatzz 275f386f ca398f63

+8 -6
+1 -1
loq.toml
··· 13 13 14 14 [[rules]] 15 15 path = "src/bot/agent.py" 16 - max_lines = 961 16 + max_lines = 963 17 17 18 18 [[rules]] 19 19 path = "src/bot/memory/namespace_memory.py"
+7 -5
src/bot/agent.py
··· 138 138 - get_own_posts: read your own recent top-level posts. use this when you need to review what you've posted — do NOT use list_records for your own posts. 139 139 140 140 service health: 141 - - check_services: check health of nate's services (plyr, PDS, prefect, relays, etc). 142 - use during daily reflection. if something is down, post about it and tag @{settings.owner_handle}. 141 + - check_services: check health of your operator's infrastructure (plyr, PDS, prefect, relays, etc). 142 + these are nate's services, not yours — their status has nothing to do with whether you're online. 143 + use during daily reflection or when someone specifically asks about service/infrastructure status. 144 + if something is down, post about it and tag @{settings.owner_handle}. 143 145 144 146 IMPORTANT: never paginate through list_records repeatedly. if you need more data than one call returns, work with what you have. endless pagination wastes your request budget and produces no response. 145 147 """.strip() ··· 815 817 816 818 @self.agent.tool 817 819 async def check_services(ctx: RunContext[PhiDeps]) -> str: 818 - """Check health of nate's services via the evergreen status proxy. 819 - Returns status, response time, and any failures. Use during daily 820 - reflection or when asked about service health.""" 820 + """Check health of your operator's infrastructure services (not your own status). 821 + Returns status, response time, and any failures for plyr, PDS, prefect, relays, etc. 822 + Use during daily reflection or when someone specifically asks about service/infrastructure health.""" 821 823 return await _check_services_impl() 822 824 823 825 logger.info("phi agent initialized with pdsx + pub-search mcp tools")