CLAUDE LABJP
VERSION — v2.1.227 landed on August 10 with no new features, just fixes around plan detection and CI behaviorAUTO — Two days remain until August 14, when auto mode becomes the default in Claude Code for Pro, Max, and TeamCI — Bash commands no longer fail across the board under claude-code-action with allowed_non_write_users on GitHub-hosted runnersBILLING — Sessions started with an expired token could misread your plan and nudge Max users toward usage credits; that is now fixedSUNSET — The legacy Workbench and the experimental prompt tool APIs retire on August 17, five days outPRICE — Sonnet 5 promo pricing at $2/$10 per Mtok runs through August 31, moving to $3/$15 on September 1VERSION — v2.1.227 landed on August 10 with no new features, just fixes around plan detection and CI behaviorAUTO — Two days remain until August 14, when auto mode becomes the default in Claude Code for Pro, Max, and TeamCI — Bash commands no longer fail across the board under claude-code-action with allowed_non_write_users on GitHub-hosted runnersBILLING — Sessions started with an expired token could misread your plan and nudge Max users toward usage credits; that is now fixedSUNSET — The legacy Workbench and the experimental prompt tool APIs retire on August 17, five days outPRICE — Sonnet 5 promo pricing at $2/$10 per Mtok runs through August 31, moving to $3/$15 on September 1
TAG

Unattended operation

1 articles
Back to all tags
Related:
Claude Agent SDK1Agent design1Reliability1Cost optimization1
API & SDK/2026-06-28Advanced

Every Tool Call Succeeds, Yet Nothing Moves Forward: Detecting Stagnation in Unattended Agents

No errors, yet the agent keeps replaying the same move while your budget quietly drains. Here is how to detect a success-but-no-progress loop using a progress oracle and action fingerprints, with a working Python implementation that halts safely.