Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by CuriouslyC on Sunday September 21, 2025 @05:58PM
(#45327052)
Kind of amazes me how many people bitch about agent performance but don't hook their guys up to Otel, crack Phoenix and get to work, but instead randomly tweak prompts in response to team vibes.
[ Parent
| on HN ]
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by chrisweekly on Sunday September 21, 2025 @06:32PM
(#45327271)
Good point. Also (tangent), I followed your profile link to https://sibylline.dev and am thoroughly impressed. Stoked to have found your treasure trove of repos and insights.
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by CuriouslyC on Sunday September 21, 2025 @07:27PM
(#45327607)
Don't play with them unless you're good at debugging alpha code (claude/codex can do it fine), I haven't ironed out env specific stuff or clarified the installation/usage, and I'm still doing UI polish/optimization passes (yay async simd rust). I'll do showy releases once I've got the tools one click install ready, in the meantime please feel free to drop an issue on any of my projects if there are features or questions you have.
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by chrisweekly on Sunday September 21, 2025 @09:10PM
(#45328171)
Sounds good, will do. Good luck getting them polished up!
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by yahoozoo on Sunday September 21, 2025 @10:15PM
(#45328494)
Could you elaborate? How does knowing numerical usage metrics help?
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by CuriouslyC on Sunday September 21, 2025 @11:23PM
(#45328811)
With Phoenix + Clickhouse being fed from Otel, you can do queries over your traces for deep analysis. If I want to see which tool calls are failing and why (or just get tool statistics), or find common patterns in flagged/failure traces ("simpler solution") and their causes, it's one query and some wiring.
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by thewisenerd on Monday September 22, 2025 @12:45AM
(#45329155)
you mention traces
but the documentation only specifies metrics and logs
https://docs.claude.com/en/docs/claude-code/monitoring-usage
am i missing something here? or is this a case where they were lazy to do traces in the claude code sdk, so its logs + log attributes?
Re:We instrumented Claude Code with OpenTelemetry (tokens, c...
by CuriouslyC on Monday September 22, 2025 @02:40AM
(#45329830)
You can get traces out of every agent framework that doesn't suck. You might need to collect from a proxy to get them from Claude because Anthropic is bigtime amateur hour.