CLAUDE LABJP
SANDBOX — Claude Code adds a sandbox.credentials setting that blocks sandboxed commands from reading credential files and secret environment variablesMODEL — Org-configured model restrictions now apply across the model picker, --model, /model, and ANTHROPIC_MODELAGENTS — Sessions that edit, merge, comment on, or push to an existing PR now link to that PR in the claude agents viewFIX — Fixed --json-schema silently producing unstructured output on an invalid schema, plus messages lost at the --max-turns limitRECAP — Claude adds a monthly recap and focus settings in beta, with break reminders, quiet hours, and work insightsOPUS — Claude Opus 4.7 is now generally available with stronger long-running coding tasks and higher-resolution visionSANDBOX — Claude Code adds a sandbox.credentials setting that blocks sandboxed commands from reading credential files and secret environment variablesMODEL — Org-configured model restrictions now apply across the model picker, --model, /model, and ANTHROPIC_MODELAGENTS — Sessions that edit, merge, comment on, or push to an existing PR now link to that PR in the claude agents viewFIX — Fixed --json-schema silently producing unstructured output on an invalid schema, plus messages lost at the --max-turns limitRECAP — Claude adds a monthly recap and focus settings in beta, with break reminders, quiet hours, and work insightsOPUS — Claude Opus 4.7 is now generally available with stronger long-running coding tasks and higher-resolution vision
TAG

Classification

1 articles
Back to all tags
Related:
Claude API1Vision1Evaluation1Indie Dev1
API & SDK/2026-07-10Advanced

Don't Trust the Confidence Score: Per-Class Calibration and Abstain Routing for Vision Classification

Overall accuracy looked fine while individual categories quietly collapsed. Here is how I calibrated Claude Vision's self-reported confidence per class and routed abstentions to a human queue.