docs(eval): use conservative Terminal-Bench concurrency defaults

[chadvoegele]

What does this PR do?

Type of change: documentation.

Chad's Agent: split the concurrency changes out of #2475. Set Terminal-Bench 2.1's starting concurrency to 8 per shard, keeping max_concurrent and sandbox.concurrency equal in the recipe, example, and canary commands.

This is a conservative default, not a benchmark mandate or proven improvement. Capacity adjustments require latency/queueing evidence and matched comparison settings; benchmark limits and scoring remain unchanged. This PR is independent of the bounded-failure policy in #2475.

Usage

max_concurrent: 8
sandbox:
  concurrency: 8

Testing

• Evaluation skill tests: 7 passed.
• YAML parsing and recipe/example concurrency and repeat consistency: passed.
• Changed-file pre-commit hooks: passed.
• git diff --check: passed.
• No live benchmark or Harbor rerun; timeout improvement is unverified.

Before your PR is "Ready for review"

Contributor and security guidance read; commit signed and signed off.

• Is this change backward compatible?: ✅ — config schema unchanged; concurrency default reduced.
• Copied code or new PIP dependency?: N/A
• New necessary tests?: N/A — config/documentation only; consistency checked locally.
• Changelog updated?: N/A
• Claude approval?: ❌ — not requested; draft.

Additional Information

Concurrency-only split from #2475. No evaluation jobs submitted.

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

[coderabbitai]

Important

Draft PR not reviewed

Draft PRs are not automatically reviewed by default.

• Trigger a manual review

To automatically review draft PRs, update your CodeRabbit configuration:

reviews:
  auto_review:
    drafts: true

• Autopilot · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Autopilot is currently an internal CodeRabbit preview.

---

_{Comment @coderabbitai help to get the list of available commands.}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 68.76%. Comparing base (e4884ba) to head (d991a80).

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2646   +/-   ##
=======================================
  Coverage   68.75%   68.76%           
=======================================
  Files         618      618           
  Lines       69455    69455           
=======================================
+ Hits        47752    47758    +6     
+ Misses      21703    21697    -6     

Flag	Coverage Δ
unit	58.71% <ø> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.