perf: optimize disk I/O by batching writes in _process_batch_worker

[EMREYSLCY]

What does this PR do?

Related Issue

Fixes #

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

How to Test

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform:

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

For New Skills

• This skill is broadly useful to most users (if bundled) — see Contributing Guide
• SKILL.md follows the standard format (frontmatter, trigger conditions, steps, pitfalls)
• No external dependencies that aren't already available (prefer stdlib, curl, existing Hermes tools)
• I've tested the skill end-to-end: hermes --toolsets skills -q "Use the X skill to do Y"

Screenshots / Logs

[teknium1]

Thanks for targeting repeated output-file opens in the batch worker.

Problems

• batch_runner.py:474 on this PR appends trajectory_entry outside the if result["success"] and result["trajectory"] block that creates it at lines 441-471. A failed first prompt therefore raises UnboundLocalError; a failure after a success appends the prior entry again.
• The PR changes no tests. The current worker test at tests/test_batch_runner_checkpoint.py:160-186 covers a successful no-reasoning discard, not a failed prompt in this path.

Suggested changes

• Keep the append inside the successful-trajectory block.
• Add a regression test with failed and successful worker results, asserting only successful entries are written.

Automated hermes-sweeper review.

[teknium1]

trajectory_entry is only assigned in the successful-result guard above. A failed first prompt raises UnboundLocalError here; after a prior success, this appends that prior entry again. Keep this append inside the guard.