🔍 Code Review Report — Job 0e947af1

Job ID: 0e947af1
Reviewer: claude (herdr:canary-projects-multi-agent-mux-reviewer-claude)
Target Commits:
- d2a8247: fix(resume): pass workspace, role, and epoch to update_yaml_resumed.sh to fix fallback silent bugs
- 57bc1b2: fix(resume): declare default AGENT variable in update_yaml_resumed.sh to avoid unbound variable error (latest)
Files: .agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh, .agents/skills/multi-agent-mux-resume/scripts/resume_session.sh

1. Executive Summary

d2a8247 extended update_yaml_resumed.sh to accept --workspace/--role and compute epoch, so that auto-created session rows (added in cb88771) get correct cwd/role instead of silent placeholder fallbacks. While rewriting the variable block, it accidentally dropped the pre-declaration of AGENT="", which — under set -euo pipefail — breaks the script whenever it's invoked without an explicit --agent flag (the documented fallback-inference path). 57bc1b2 is a one-line fix that restores the declaration.

I reproduced the regression directly (see §2) and confirmed 57bc1b2 resolves it without side effects. I also found one unresolved, narrower gap left over from d2a8247 itself (§3), and one pre-existing, unrelated test failure (§4). Neither blocks this fix.

Verdict: the change under review (57bc1b2) is correct, minimal, and verified safe.

2. Verified Regression + Fix

Reproduction — d2a8247 (before 57bc1b2), invoking the script the way SKILL.md's documented manual-recovery example and tests/test_tier2_component.py::test_comp_resume_update_yaml do — i.e. without --agent, relying on suffix inference:

$ bash update_yaml_resumed.sh --session test-resumed-session-creator-claude --uuid new-uuid-999
update_yaml_resumed.sh: line 43: AGENT: unbound variable
exit code: 1

This is because d2a8247's diff replaced the AGENT="" line with WORKSPACE=""/ROLE="" instead of adding to it:

 SESSION_NAME=""
 UUID=""
-AGENT=""
+WORKSPACE=""
+ROLE=""

AGENT is only ever assigned inside the arg-parsing loop if --agent is passed; the fallback block (if [ -z "$AGENT" ]; then ...) reads it unconditionally, so any invocation without --agent reads an undeclared variable and — because of set -u — crashes before the fallback logic even runs.

At current HEAD (with 57bc1b2 applied), the same invocation:

$ bash update_yaml_resumed.sh --session test-resumed-session-creator-claude --uuid new-uuid-999
updated: test-resumed-session-creator-claude status=running (resume id -> per-row own id)
exit code: 0

57bc1b2's fix is exactly the declaration restore, nothing else — a correct, minimal, low-risk patch.

Test suite: tests/ -k "resume or resumed" → 14 passed, 1 failed (unrelated, see §4). test_comp_resume_update_yaml — the test that exercises this exact no---agent path — passes at HEAD.

bash -n syntax check: both update_yaml_resumed.sh and resume_session.sh OK.

3. Residual Gap in `d2a8247` (not addressed by `57bc1b2`, non-blocking)

d2a8247's commit message claims it "passes workspace, role, and epoch ... to fix fallback silent bugs," but the wiring is incomplete in resume_session.sh:

The "herdr already running" branch (resume_session.sh:58-59) still calls update_yaml_resumed.sh with only --session/--uuid/--agent — no --workspace, no --role.
Only the "newly spawned" branch (resume_session.sh:118-119) passes --workspace.
--role is never passed by any caller in the repo (confirmed via grep across .agents/, deploy/, tests/) — it always relies on update_yaml_resumed.sh's suffix-based inference (*-planner-*/*-reviewer-*/else creator).

Practical impact: low but real. The role-inference fallback is safe in practice because session names consistently follow the -creator-/-planner-/-reviewer- convention. The missing --workspace at line 58 only matters in the narrow case where update_yaml_resumed.sh has to auto-create a session row (the cb88771 feature) for an already-running herdr session that has no existing YAML entry (e.g. an orphaned/manually-attached session) — in that case cwd falls back to WORKSPACE_ROOT (the mux repo root) rather than the actual workspace the caller passed to resume_session.sh --workspace. That's precisely the class of "fallback silent bug" d2a8247 set out to fix, just not closed on this call site.

Recommendation (fast-follow, not a blocker): add --workspace "$WORKSPACE" to the call at resume_session.sh:58-59 for symmetry with line 118-119. Not a design/redesign issue — a one-line change, so no escalation warranted.

4. Pre-existing, Unrelated Test Failure (noted for awareness)

tests/test_tier4_e2e.py::test_e2e_scenario2_disconnect_resume fails with KeyError: 'isolation' (orig_session["isolation"]["root"]). This predates the commits under review: f0a2103 (refactor(isolation): simplify agent session isolation..., 2 commits before d2a8247) removed the isolation field from session rows, and the subsequent test-alignment pass (9ba45e5) updated test_tier1_unit.py/test_tier2_component.py/conftest.py but missed this e2e test. Out of scope for this review; flagging so it isn't mistaken for a regression from d2a8247/57bc1b2.

5. Conclusion

Item	Status
`57bc1b2` fixes the `AGENT` unbound-variable regression	✅ Verified via direct reproduction
No new regressions introduced by `57bc1b2`	✅ Confirmed (diff is a single added line)
`bash -n` syntax	✅ Pass on both scripts
Resume-related test suite	✅ 14/15 pass (1 pre-existing unrelated failure, §4)
`d2a8247`'s stated goal (workspace/role always correctly propagated)	⚠️ Partially incomplete (§3) — narrow edge case, simple 1-line fix, not blocking

No design-level rework is required; the outstanding item (§3) is a straightforward follow-up patch.

[VERDICT: PASS]

6.0 KiB Raw Blame History