Tutorials

7 posts

tutorials · Sep 16 · 13 min

A 300-Second WebFetch Fail Is Not a Hung Model

A red WebFetch at five minutes is a download deadline, not a stuck model. Print the named CLI pin, the deadline env, and the named owner before you page the model.

tutorials · Sep 10 · 14 min

Treat Unreadable Managed Settings as Empty

When a managed allow-list cannot be read, Claude Code now admits nothing. Classify the block, name who owns the file, then resume the coding agent.

tutorials · Sep 4 · 12 min

Name the Copilot Surface Before You Trust the Exclusion List

A Copilot content exclusion is a policy row. App and CLI now honor it. Agent chat in the editor still can. Name the owner of the list and of the surface before you call a secret recovered.

tutorials · Aug 26 · 13 min

Empty Tool Output Is Not Success Until the Harness Says Interrupted

An interrupted MCP tool in a headless coding-agent session used to look finished. Treat empty completion as a bug until the harness asserts an interrupted error.

tutorials · Aug 14 · 10 min

Building a Background Agent Recovery CLI: The Three-Gate Check

Chat said done is not recovered. I wait for a file on disk, a job log that names why the run stopped, and one fail-once restart from the last good commit.

tutorials · Aug 1 · 13 min

A table beta bump is still a pilot decision

TanStack Table 9.0.0-beta.64 honors explicit global-filter opt-in. That is pilot hygiene, not permission to unpin stable 8.21.3. Here is the gate list before a Vue admin table leaves the spike branch.

dev-ecosystem · Jul 23 · 15 min

Audit the resume boundary: verify a coding agent from repository evidence

A practical way to decide whether a resumed coding-agent run is safe to continue: inspect local evidence, enforce command gates, review the diff, preserve test logs, and make rollback cheap.