Claude Code v2.1.277 · 18 Sep 2026
Internal log wording for the --max-budget-usd halt now says 'this run's spend' instead of 'total cost'
You'll notice Tier: how much it should matter to you
1 Useful: my rating, 1 to 5
0 Signal: worth watching, 1 to 5
Headless Mode Area: what it touches
Improvements Kind: in v2.1.277, 18 Sep 26
Improvements Section of the release
What
The internal log line printed when a headless (print mode) run hits its --max-budget-usd
Why
This is a wording change to the internal log message; the budget-halt behavior itself is unchanged.
See this entry in the whole of v2.1.277 →
18 Sep 2026 · 402 entries, this one is #141.
29 126 23 224
Open the release →
Names in this entry
cli --max-budget-usd Stop the run once estimated spend on API calls reaches this amount (print mode only). Claude Code checks the cap against its client-side cost estimate , which can differ from your bill. Spend from subagents counts toward the cap. Spend can pass the cap, so leave headroom . When you return to a conversation with --continue or --resume, totals restored from earlier runs don't count toward it. Once spend reaches the cap, spawning another subagent fails with Budget limit reached, and Claude Code stops background subagents that are still running; the cap-enforcement behaviors require Claude Code v2.1.217 or later
Is this right?
0 0 Feedback
What's wrong with this entry?
Hard to understand Too vague Looks wrong Not relevant to me Too long Missing the detail I wanted Duplicate of another card
Clear Learned something new I can act on this Good catch
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
← Previous · 140 of 402
File-read attribution message punctuation changed from em dash to colon
You'll notice File Tools
In v2.1.277 Improvements release-page order
Next → · 142 of 402
Sandboxed commands get a fallback TMPDIR when needed but unset
You'll notice Sandbox
