fix(autonomy): verify shell work before completing tickets - #131
Conversation
There was a problem hiding this comment.
Deterministic Validator approval for exact head c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51.
Ticket: ticket-095
Correlation ID: koru-pr-131-ticket-095
Model: zai/glm-5.3
Reviewed diff chunks: 2
Advisory LLM verdict: APPROVE
Advisory summary: Reviewed all 2 diff chunk(s). Chunk implements shell-drive finalization correctly: verification now runs before marking done, a missing/mismatched verification receipt blocks closure, and explicit unsuccessful-work prose vetoes auto-done. Note precedence was corrected to preserve raw stdout. Tests cover the new paths and all CI checks pass. | Reviewed chunk 2 of 2: adds tests to shell_drive_finalize covering failed verification paths (missing receipt, reopened ticket) asserting finalize returns verify_failed and never transiently completes tickets with 'ticket done'. No production code or security issues visible in this chunk. All CI checks pass.
Advisory findings: none
The LLM output above is advisory and was not used as the approval trust root.
Actual PR impact radar
Exact range: ab9dba9ec5b42ab68430ac96fd5b825bdbf665f0...c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51
Change digest: dae578bbba17c50d776f6b546d3ab3ad6a1fcd210a76db30c4963694c49634bf
Score: 56/100 (L), estimated 65 min, split recommended: true
Affected services/components: repository-wide/unclassified
Machine-readable radar JSONL and SVG
{"actual_change":{"additions":178,"base_sha":"ab9dba9ec5b42ab68430ac96fd5b825bdbf665f0","binary_files":0,"categories":{"code":2,"configuration":1,"docs":4,"tests":1},"change_digest":"dae578bbba17c50d776f6b546d3ab3ad6a1fcd210a76db30c4963694c49634bf","comparison":"ab9dba9ec5b42ab68430ac96fd5b825bdbf665f0...c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51","deletions":23,"file_count":8,"files":["project/ticket-095/README.md","project/ticket-095/ai-codex-logs.txt","project/ticket-095/ai-codex.md","project/ticket-095/changelog.md","project/ticket-095/intent.json","project/ticket-095/preprompt.md","src/koru/autonomy/shell_drive_finalize.py","tests/test_shell_drive_finalize.py"],"head_sha":"c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51","service_count":0,"services":[]},"assessment_mode":"observed-pr","axes":{"coupling":4,"delivery":2,"scope":4,"uncertainty":3,"validation":1},"complexity":"L","confidence":0.9,"diagnostics":["RADAR-ACCEPTANCE-MISSING","RADAR-BUDGET-EXCEEDED"],"estimate":{"budget_minutes":30,"minutes":65,"within_budget":false},"impact":{"components":["finalization","project","src/koru","tests"],"files":["finalization/post-run","project/ticket-095/README.md","project/ticket-095/ai-codex-logs.txt","project/ticket-095/ai-codex.md","project/ticket-095/changelog.md","project/ticket-095/intent.json","project/ticket-095/preprompt.md","src/koru/autonomy/shell_drive_finalize.py","tests/test_shell_drive_finalize.py"],"public_interfaces":[],"runtime_dependencies":0},"schema":"subactor.ticket-radar/v1","score":56,"split":{"parts":[{"estimated_minutes":14,"name":"Implement finalization","scope":["finalization"]},{"estimated_minutes":14,"name":"Implement project","scope":["project"]},{"estimated_minutes":14,"name":"Implement src/koru","scope":["src/koru"]},{"estimated_minutes":14,"name":"Implement tests","scope":["tests"]},{"estimated_minutes":15,"name":"Validate and project to trackers","scope":["tests","planfile","github/gitlab/jira projections"]}],"reason":"estimated_minutes_exceed_budget","recommended":true},"standards":[{"id":"wellmanifest/dsl","revision":"6c60fc4e0dd1f1bb74f46a7745e28019908d1203","version":"0.1.0-dev"},{"id":"wellmanifest/ticket-lifecycle","revision":"5bf581907a87b46a13a73e6c033d3abe4d9a306f","version":"0.1.0-dev"},{"id":"wellmanifest/git-lifecycle","revision":"7d77d4b7af57e69bc75c3a0290b3a4805c5c4438","version":"0.2.0-dev"},{"id":"wellmanifest/logs","revision":"48c284ef7a069055c0bcb6b900147ce5e65f8b43","version":"0.3.0"}],"ticket_ref":"ticket-095"}<svg xmlns="http://www.w3.org/2000/svg" width="128" height="128" viewBox="0 0 128 128" role="img"><title>ticket-095: fix(autonomy): verify shell work before completing tickets</title><rect width="128" height="128" rx="12" fill="#f8fafc"/><g stroke-width="1"><polygon points="64,55 72,61 69,71 59,71 56,61" fill="none" stroke="#d7dde5"/><polygon points="64,47 80,59 74,78 54,78 48,59" fill="none" stroke="#d7dde5"/><polygon points="64,38 89,56 79,85 49,85 39,56" fill="none" stroke="#d7dde5"/><polygon points="64,30 97,53 84,92 44,92 31,53" fill="none" stroke="#d7dde5"/><polygon points="64,21 105,51 89,99 39,99 23,51" fill="none" stroke="#d7dde5"/><line x1="64" y1="64" x2="64" y2="21" stroke="#aab4c0"/><line x1="64" y1="64" x2="105" y2="51" stroke="#aab4c0"/><line x1="64" y1="64" x2="89" y2="99" stroke="#aab4c0"/><line x1="64" y1="64" x2="39" y2="99" stroke="#aab4c0"/><line x1="64" y1="64" x2="23" y2="51" stroke="#aab4c0"/></g><polygon points="64,30 97,53 79,85 59,71 48,59" fill="#fb923c" fill-opacity="0.45" stroke="#c2410c" stroke-width="2"/><circle cx="64" cy="64" r="3" fill="#c2410c"/><g font-family="sans-serif" font-size="7" fill="#334155"><text x="64" y="11" text-anchor="middle">SCO</text><text x="114" y="48" text-anchor="middle">COU</text><text x="95" y="107" text-anchor="middle">UNC</text><text x="33" y="107" text-anchor="middle">VAL</text><text x="14" y="48" text-anchor="middle">DEL</text></g><text x="64" y="124" text-anchor="middle" font-family="sans-serif" font-size="8" fill="#0f172a">L · 65m</text></svg>DECISION D-095-3404
TICKET ticket-095
HEAD_SHA c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51
CORRELATION_ID koru-pr-131-ticket-095
ACTOR agent:ifuri-validator-agent[bot]
APPLIED_RULE P-CORE-015
INPUT author_login = "tom-sapletta-com"
INPUT observed_checks = ["governance / enforce=PASS","standard packs / conformance=PASS","governance / remote lifecycle=PASS","standard packs / conformance=PASS","onedev/local-verify=PASS"]
INPUT required_checks = ["onedev/local-verify","standard packs / conformance"]
INPUT required_checks_source = "protected registry + GitHub applied rules (env/request)"
INPUT reviewer_login = "ifuri-validator-agent[bot]"
INPUT superseded_checks = ["smoke"]
INPUT ticket_radar_receipt = {"schema":"subactor.ticket-radar/v1","base_sha":"ab9dba9ec5b42ab68430ac96fd5b825bdbf665f0","head_sha":"c39dcabc2297e6fa5dffd2b71e14fe277c2b8f51","change_digest":"dae578bbba17c50d776f6b546d3ab3ad6a1fcd210a76db30c4963694c49634bf","score":56,"complexity":"L","estimated_minutes":65,"split_recommended":true,"services":[],"authority":"ADVISORY","promotion":"FORBIDDEN"}
VERDICT APPROVE AUTHORITY DETERMINISTIC
REJECTED REQUEST_CHANGES BECAUSE NO_UNSAFE_CHANGE_REASON_FOUND
ADVISORY llm_verdict = "APPROVE" MODEL "zai/glm-5.3"
ASSERT VERDICT_AUTHORITY != "ADVISORY"
A shell client can exit successfully while reporting denied edits or no changes. Preserve its actual output and veto automatic completion on explicit unsuccessful-work reports. In verified mode, run verification before marking the ticket done and require a result for the correct ticket.
Validation: 31 finalization/post-run tests, Ruff, managed governance, Docker Compose, compileall and whitespace checks pass. Negative prose is a conservative veto; ticket-specific positive acceptance evidence remains separate work.
Ticket: ticket-095.