◉CLAUDE LABJP
●SLACK — Claude Tag launches in beta on Slack: tag @Claude into channels to delegate tasks and connect tools, data, and codebases●SECURITY — Claude Code adds a sandbox.credentials setting to block sandboxed commands from reading credential files and secrets●FIX — Remote MCP tool calls that once hung for five minutes now abort with an error instead of blocking●MCP — Enterprise MCP connectors gain Okta provisioning, giving users zero-touch access on first login●MODEL — Claude Fable 5 offers a 1M-token context, always-on adaptive thinking, and 128K output●LINEUP — Opus 4.8, Sonnet 4.6, and Haiku 4.5 lead the lineup; pick the right one per task●SLACK — Claude Tag launches in beta on Slack: tag @Claude into channels to delegate tasks and connect tools, data, and codebases●SECURITY — Claude Code adds a sandbox.credentials setting to block sandboxed commands from reading credential files and secrets●FIX — Remote MCP tool calls that once hung for five minutes now abort with an error instead of blocking●MCP — Enterprise MCP connectors gain Okta provisioning, giving users zero-touch access on first login●MODEL — Claude Fable 5 offers a 1M-token context, always-on adaptive thinking, and 128K output●LINEUP — Opus 4.8, Sonnet 4.6, and Haiku 4.5 lead the lineup; pick the right one per task
TAG

Scheduled jobs

3 articles
← Back to all tags
Related:
Claude API2Claude Agent SDK1Distributed locks1Production1Design1rate limits1capacity planning1operations1Anthropic SDK1Automation1Fallback1
⬡ API & SDK/2026-06-25Advanced

When the Previous Run Hasn't Finished and the Next One Starts: Leases and Fencing Tokens for Scheduled Agents

A scheduled agent that runs on a fixed clock can overtake itself and start twice. From the moment a naive lock breaks to leases, fencing tokens, and bounded catch-up — worked through with the implementation I actually run.

⬡ API & SDK/2026-06-24Advanced

What I Decided the Day the Ceiling Doubled: A Headroom Budget for Scheduled Jobs on One Shared API Key

Why I did not compress my intervals when the rate limit doubled, and how to design a headroom budget for running several scheduled jobs on one shared API key, with measurement and working code.

⬡ API & SDK/2026-06-16Advanced

Confirm Your Model Actually Responds Before a Scheduled Run Begins

A model you configured can be gone before your nightly job even wakes up. Tell retirement, withdrawal, and regional restriction apart with a single startup probe, then rewrite the run config to an eligible model — with complete, working TypeScript.