feat(kanban): enforce native review handoff evidence (#10)

[solovision24]

• feat(kanban): route implementation handoffs through review

• fix(kanban): allow requeued review workers past PR guard (Add logging for first 100 chars of the tool call args json / tool response #9)

• fix(kanban): allow requeued review workers past PR guard

• fix(kanban): preserve review routing after crash requeue

• fix(kanban): preserve native review lane on crash

• fix(kanban): apply retry guards to native reviews

• fix(kanban): guard native review respawns during cooldown

---

• feat(kanban): enforce native review handoff evidence

• fix(kanban): make native review handoff canonical

---

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 extending the existing review lane with a structured handoff and immutable metadata validation. Current main still uses the review-required block convention (agent/prompt_builder.py:246-253), so this is not redundant.

Problems

• The new preservation logic only covers detect_crashed_workers (hermes_cli/kanban_db.py:7815-7840). Other running-task recovery paths in this PR head still set status='ready': TTL reclaim (hermes_cli/kanban_db.py:4734), max-runtime timeout (:7433), and stale-worker recovery (:7558). Those cards then use ordinary ready dispatch, whereas sdlc-review is force-loaded only in review dispatch (:8827-8870). A timed-out, stale, or failed-to-spawn reviewer can therefore lose its review-lane contract.

Suggested changes

• Route every running-to-retry transition through one source-lane helper and add coverage for TTL and timeout/stale requeues of review cards.

Automated hermes-sweeper review.

[teknium1]

This preserves the review lane only for detected crashes. TTL reclaim, max-runtime timeout, stale-worker recovery, and review-spawn failure still transition a claimed review task to ready, which routes it through ordinary dispatch rather than the sdlc-review path. Please centralize this source-lane decision and cover those retry paths.