Claude Code usage tracking by LangWatch

does the terminal replay work for headless/CI runs with no TTY, or does capturing the replay need an actual interactive session? we run a chunk of our agent work in CI and cost visibility there is usually the blind spot

congrats on the launch! Does this use any bandwidth during the session? Especially long ones

Congrats on launch! Can it dig through my year worrh of session data to analyze my usage patterns retroactively, or does it start tracking only once installed?

Manouk's "we run a fleet of coding agents ourselves and had no idea what they actually cost" is the honest version of this. Same here — our answer was "we'll find out when the subsidies stop."One push: cost per session can mislead. The number that changes how you route work is cost per outcome — per merged PR, per green CI run, per fix that actually held. A run that spends 3x on the expensive model and lands it first try beats a cheap model looping four times — but a per-session view shows the opposite, and quietly trains you to downgrade the model that was earning its price.You're already logging tool calls as spansm that: span → the commit or test run itproduced. On the roadmap, or are you deliberately staying at the session boundary?+1 to the immutable price-stamp point above, with a wrinkle: it has to cut both ways. Rates must never change historical reports by accident — but "what the new prices" is exactly the question the subsidy argument makes people ask. That's a deliberate re-price, not a mutation.

Congrats on the launch! Seeing which Claude Code session actually burned the budget instead of guessing would be a relief, and the cache reads split out as their own token class is a thoughtful detail. How would this work for a small team, can we see everyone's sessions in one shared view or is it one workspace per developer?

The one-command setup makes trying it out much less intimidating. 😊

This feels especially useful as AI coding workflows become part of everyday engineering. Congrats 🙌🏻

Congrats! How much overhead does the tracking introduce during long-running Claude Code sessions?

Congrats on shipping this! Finally a way to know exactly how much those late-night Claude Code sessions are costing me. My wallet thanks you already!

It would be interesting if LangWatch suggested ways to reduce costs based on previous usage.

Can the platform can identify inefficient prompting patterns across multiple sessions?

Watching an entire terminal session replay sounds surprisingly valuable for onboarding teammates.

the MCP tool calls as spans is the bit i want most. i drive a browser automation MCP from claude code all day and the screenshots are obviously the expensive part, except obviously is doing a lot of work in that sentence because i have no per-call number for any of it.cache reads and writes counted separately is the other one, that is where the surprise usually hides.

really proud of this launch!

great product! knowing the per-seat cost but not which sessions burned is a proper problem, especially as the costs keep rising. this is going to save me from getting broke!