- Option B / C-3b: Deprecate isolation.root and remove its 4 legacy consumers in lib.sh, workspace_uuid.py, verify_session.py, and stop_session.sh.
- M2~M7 Migration: Implement artifact_path, verify_artifact, purge_artifacts, spawn_spec, resume_spec, auth_ok, discover, ready_tokens, exit_key, and delegate_agent_key across BaseAgentAdapter and all 4 adapters (Claude, Agy, Hermes, Cline).
- Migrate shell duplications in lib.sh, create_session.sh, resume_session.sh, stop_session.sh, and reconcile.sh to python -m lib_py.agents facts.
- Hardening & Corrections: Fix Cline resume_spec flag to '-i --id', apply shlex.quote across all facts variables with MAM_ prefix, add safe fallback in wait_for_tui_ready.
- Add comprehensive contract tests in tests/test_a4_adapter_contract.py and sync IMPROVEMENTS.md / LOG.md.
- Verified: 100% PASS across unit, component, contract, and integration tests.
- Replace legacy s[:16]-s[-15:] truncation with 8-char SHA-1 hash suffix in sanitize.py and lib.sh to prevent workspace name collisions
- Align mock Herdr error messages in tests/conftest.py to real Herdr 0.8.0 output format
- Add missing required/invalid_agent_name to early abort regex in lib.sh
- Remove legacy heuristics in lib.sh has-session and unify mock agent lookups
- Add unit tests in tests/test_sanitize_and_mock_errors.py (256/256 passed)
- Update .agents/MULTI_AGENT_RULES.md & .ko.md to align with TMUX concepts
- Add .agents/INSTALL.md guide for MAM setup and workflows
- Clean up legacy markdown reports under .agents/reports/
- Refactor MAM scripts in .agents/skills/ (rename resolve_herdr_session to resolve_herdr_workspace)
- Improve workspace pane splitting/re-use logic in lib.sh
- Reduce paste safety sleep in send_keys_safe and support linking ~/.claude.json
Applies the P0-P3 fixes from the multi-agent-mux-loop audit
(.mam/jobs/ab686e47/claude-reports/report-final.md):
- P0-1: capture BASE_COMMIT before Phase 2 and diff against it, so reviewer
diffs stay non-empty and cumulative even after the Creator commits per the
documented DoD (bare `git diff` alone showed nothing once committed).
- P0-2: has_verdict now matches only the report's last non-blank line, so a
stray [VERDICT: ...] token quoted mid-report as a formatting example can no
longer flip the outcome.
- P1-1: replace the English-only refactor/complex/design/architect keyword
sniff (dead code against Korean-language reviewer reports) with an explicit
[ESCALATE: PLANNER] tag the reviewer prompt now asks for.
- P1-2: resolve_all_reviewers/resolve_agent_type/resolve_planner_session now
read through lib.sh's load_state_json single source of truth instead of
each hand-rolling its own SQLite+YAML lookup; resolve_agent_type's name
fallback matches exact hyphen segments instead of a substring `in` check.
- P2-1: warn when --all-reviewer and --reviewer are both given, since the
latter is silently discarded.
- P2-2: correct the SKILL.md CLI-mapping table row that overstated an
automated lint gate and an unconditional Planner feedback loop.
- P3: fix lib.sh shellcheck SC2164 (unguarded cd in start_watchdog) and
annotate the intentional SC2317 dual source/exec guard.
Verified: shellcheck clean on both scripts, bash -n syntax OK, and the
rewritten has_verdict/resolve_* functions were unit-tested against this
repo's live .mam/agent-sessions state.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Godopu
Antigravity
