Bringing Observability to Claude Code: Opentelemetry in Action

Posted3 months agoActive3 months ago

pranay01

51 points

18 comments

signoz.ioTechstory

controversialmixed

Debate

80/100

ObservabilityOpentelemetryAI Monitoring

Key topics

Observability

Opentelemetry

AI Monitoring

The article discusses using OpenTelemetry to monitor Claude Code, sparking a debate about the implications of increased observability on developer surveillance and performance monitoring.

Snapshot generated from the HN discussion

Discussion Activity

Moderate engagement

First comment

23m

Peak period

6-9h

Avg / period

2.3

Comment distribution18 data points

Loading chart...

Based on 18 loaded comments

Key moments

01Story posted
Sep 21, 2025 at 2:37 PM EDT
3 months ago
Step 01
02First comment
Sep 21, 2025 at 2:59 PM EDT
23m after posting
Step 02
03Peak activity
6 comments in 6-9h
Hottest window of the conversation
Step 03
04Latest activity
Sep 23, 2025 at 3:57 PM EDT
3 months ago
Step 04

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (18 comments)

Showing 18 comments

CuriouslyC

3 months ago

2 replies

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.

chrisweekly

3 months ago

1 reply

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.

CuriouslyC

3 months ago

1 reply

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.

chrisweekly

3 months ago

Sounds good, will do. Good luck getting them polished up!

yahoozoo

3 months ago

1 reply

Could you elaborate? How does knowing numerical usage metrics help?

CuriouslyC

3 months ago

1 reply

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.

thewisenerd

3 months ago

1 reply

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?

CuriouslyC

3 months ago

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.

oefrha

3 months ago

1 reply

Collecting detailed per-request traces and calculating user-specific metrics finer than a total cost feels about as intrusive as one of those periodic screenshot programs forced by really shitty remote jobs or freelancing contracts. It's pretty gross.

pranay01Author

3 months ago

I don't think the primary goal here is "surveillance" but better understanding where in the team are tools like claude code getting adopted, what models are being used, are there best practices to learn in token usage which could make it more efficient

sofia44

3 months ago

1 reply

I think this tackles a really important area - nice job. Looking forward to following.

pranay01Author

3 months ago

great to hear. yes, it can help understand how developers are using Claude Code and also optimise token usage etc.

N_Lens

3 months ago

1 reply

I’d like to see this leveraged for agent platforms & orchestration rather than for surveillance on human software engineers. Humans don’t perform well in panopticons, but robots do (In my humble opinion).

pranay01Author

3 months ago

1 reply

> leveraged for agent platforms & orchestration

can you share more on what you mean by this?

N_Lens

3 months ago

1 reply

Claude Code Agents can be integrated into existing platforms such as github. I can envision agents automatically handling issues with certain tags, or doing pull request reviews, or other such similar trigger based behaviour.

In that kind of orchestration this observability would be invaluable.

pranay01Author

3 months ago

interesting. So, you mean say if an agent is working on automatically doing a PR review, how many such calls to agents are failing, how much time they are taking, etc?

Lot of this you can do with traces today which trace AI specific calls

pdntspa

3 months ago

aka let's spy on our devs more than we already are and give their pointy-haired bosses even more leverage to harass them with AI-usage KPI BS

tomrod

3 months ago

Very nice!

View full discussion on Hacker News

ID: 45325410Type: storyLast synced: 11/20/2025, 2:30:18 PM

Want the full context?