Warning: This build has drifted.
The coverage report for this pull request build may be inaccurate because its base commit is no longer the HEAD of its target branch.
This means it includes changes from outside the original pull request, including, potentially, unrelated coverage changes.

    • Learn more: For more information on this, see Tracking coverage changes for pull request builds.
    • Fix now: For a quick fix, rebase this PR at GitHub. Your next report should be accurate.
    • Prevent going forward: To avoid this issue with future PRs, see these Recommended CI Configurations.

docs(skill): refine timeout guidance with background-task handling

Replace the hardcoded 1800000 suggestion with "max supported by your
harness" after discovering that Claude Code caps at 600000 but does not
kill the child process — it auto-backgrounds the bash call and hands the
model a task output path. The session auto-resumes when the task
completes.

Split Step 3 recovery into two cases:
  - Case A: background task handoff (Claude Code): do not Read the task
    output file while the child is still running; poll via BashOutput or
    trust the auto-resume, then cat the known output path on completion.
  - Case B: hard timeout error (no background handoff): the existing
    user-confirmation + ls -t /tmp/revdiff-output-* recovery.

Validated by running a real revdiff session in a separate Claude Code,
watching the JSONL transcript cross the 600000ms boundary, and observing
auto-background + auto-resume behaviour.