refactor(ticket-189): split supervisor question LLM answering into focused helpers (STARTER-606) - #373
Conversation
…cused helpers (STARTER-606) _question_answers_via_llm drops from cyclomatic complexity 26 to 9 by extracting behavior-preserving module helpers: _load_subllm (optional import resolution), _question_spec (spec building), _subllm_answer_stdout (transport and exit-status handling), _parse_answer_payload (strict JSON parse with prose salvage), _normalize_answer_set (label filtering, invented-label fallback, single-choice trimming). Guard order, log messages and answer semantics are unchanged (verified by a 17-case differential harness); the module is also made ruff-clean by fixing its two pre-existing findings (UP035 Callable import, one E501 f-string split with identical value).
There was a problem hiding this comment.
Validator approval after policy checks for exact head b3eb435fcc57c7a31b6d1962814de73738ac827d.
Ticket: ticket-189
Correlation ID: local-semcod-koru-pr-373-ticket-189
Model: zai/glm-5.3
Reviewed diff chunks: 2
Advisory LLM verdict: APPROVE
Advisory summary: Reviewed all 2 diff chunk(s). Behavior-preserving refactor of _question_answers_via_llm into module-level helpers, consistent with the stated CC-reduction goal. Required checks (onedev/local-verify, standard packs / conformance) all PASS per protected assessment; required_checks_passed is true. README claims of differential testing, ruff cleanup, and governance pass are corroborated by passing required checks. | Refactoring chunk extracts LLM question-answering stages from _question_answers_via_llm into module-level helpers. Required checks (onedev/local-verify, standard packs / conformance) all PASS per protected check assessment. Behavior preserved: early return None on invalid subllm answer matches the previous valid-flag break; question-spec, parsing, and normalization guard order retained. Remaining diffs are formatting-only line reflows.
Advisory findings: none
The LLM output above is advisory and was not used as the approval trust root.
Semantic review prerequisite: not_required; policy 676cb4516bbfed2a000e40b9b1b6e4a430ecc761ec546aeb53d721a1905cfdd7.
Actual PR impact radar
Exact range: 0f60955f2e2a7c61ecd585c6567177e7aac83927...b3eb435fcc57c7a31b6d1962814de73738ac827d
Change digest: 249b4eba5ebe4d1c04c8017563072145420d0bf2cf5716a5acaabd399025815b
Score: 64/100 (L), estimated 78 min, split recommended: true
Affected services/components: repository-wide/unclassified
Machine-readable radar JSONL and SVG
{"actual_change":{"additions":230,"base_sha":"0f60955f2e2a7c61ecd585c6567177e7aac83927","binary_files":0,"categories":{"code":1,"configuration":1,"docs":1},"change_digest":"249b4eba5ebe4d1c04c8017563072145420d0bf2cf5716a5acaabd399025815b","comparison":"0f60955f2e2a7c61ecd585c6567177e7aac83927...b3eb435fcc57c7a31b6d1962814de73738ac827d","deletions":49,"file_count":3,"files":["project/ticket-189/README.md","project/ticket-189/intent.json","src/koruapi/opencode_supervisor.py"],"head_sha":"b3eb435fcc57c7a31b6d1962814de73738ac827d","service_count":0,"services":[]},"assessment_mode":"observed-pr","axes":{"coupling":5,"delivery":3,"scope":3,"uncertainty":3,"validation":2},"complexity":"L","confidence":0.9,"diagnostics":["RADAR-ACCEPTANCE-MISSING","RADAR-BUDGET-EXCEEDED"],"estimate":{"budget_minutes":30,"minutes":78,"within_budget":false},"impact":{"components":["check","origin","project","src/koruapi","tests","ticket"],"files":["check/format","origin/main","project/governance-check.sh","project/ticket-189/README.md","project/ticket-189/intent.json","src/koruapi/opencode_supervisor.py","tests/test_dashboard_terminals.py","ticket/189-opencode-supervisor-question-llm"],"public_interfaces":["src/koruapi/opencode_supervisor.py"],"runtime_dependencies":0},"schema":"subactor.ticket-radar/v1","score":64,"split":{"parts":[{"estimated_minutes":20,"name":"Define contract and acceptance boundary","scope":["src/koruapi/opencode_supervisor.py"]},{"estimated_minutes":10,"name":"Implement check","scope":["check"]},{"estimated_minutes":10,"name":"Implement origin","scope":["origin"]},{"estimated_minutes":10,"name":"Implement project","scope":["project"]},{"estimated_minutes":10,"name":"Implement src/koruapi","scope":["src/koruapi"]},{"estimated_minutes":10,"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-189"}<svg xmlns="http://www.w3.org/2000/svg" width="128" height="128" viewBox="0 0 128 128" role="img"><title>ticket-189: refactor(ticket-189): split supervisor question LLM answering into focused helpers (STARTER-606)</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="64,38 105,51 79,85 54,78 39,56" 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 · 78m</text></svg>DECISION D-189-1913
TICKET ticket-189
HEAD_SHA b3eb435fcc57c7a31b6d1962814de73738ac827d
CORRELATION_ID local-semcod-koru-pr-373-ticket-189
ACTOR agent:ifuri-validator-agent[bot]
APPLIED_RULE P-CORE-015
INPUT author_login = "tom-sapletta-com"
INPUT observed_checks = ["standard packs / conformance=PASS","governance / remote lifecycle=PASS","governance / enforce=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 semantic_review_assessment = {"schema":"subactor.validator/semantic-review-assessment/v1","subject":{"repository":"semcod/koru","pull_request":373,"head_sha":"b3eb435fcc57c7a31b6d1962814de73738ac827d","base_sha":"0f60955f2e2a7c61ecd585c6567177e7aac83927","diff_sha256":"47c8b0e137dabde1c92d2e0b68f81e23a045a8fcdb55a9c3da1e21728a327e1e"},"policy":{"policy_schema":"subactor.validator/semantic-review-policy/v1","policy_version":1,"policy_sha256":"676cb4516bbfed2a000e40b9b1b6e4a430ecc761ec546aeb53d721a1905cfdd7","required":false,"critical_paths":[],"observed_paths":["project/ticket-189/README.md","project/ticket-189/intent.json","src/koruapi/opencode_supervisor.py"]},"grounding":"full-diff-not-per-finding-proof","execution_authority":false,"status":"not_required","reason":null,"review_sha256":null,"unresolved":[]}
INPUT superseded_checks = ["smoke"]
INPUT ticket_radar_receipt = {"schema":"subactor.ticket-radar/v1","base_sha":"0f60955f2e2a7c61ecd585c6567177e7aac83927","head_sha":"b3eb435fcc57c7a31b6d1962814de73738ac827d","change_digest":"249b4eba5ebe4d1c04c8017563072145420d0bf2cf5716a5acaabd399025815b","score":64,"complexity":"L","estimated_minutes":78,"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"
Extract the LLM question-answering stages (SubLLM import resolution, question spec building, subllm transport, JSON salvage parsing, answer normalization) from
_question_answers_via_llm(src/koruapi/opencode_supervisor.py, CC 26 → 9) into focused module-level helpers (_load_subllm,_question_spec,_subllm_answer_stdout,_parse_answer_payload,_normalize_answer_set). Behavior unchanged: guard order, log messages, and answer normalization preserved; no public API change.Ticket: ticket-189 (workstream: application, status: IN_PROGRESS).
Planfile source: STARTER-606 (code2llm high-CC function).
Validation evidence (branch
ticket/189-opencode-supervisor-question-llm, headb3eb435f, baseorigin/main=0f60955f): recorded inproject/ticket-189/README.mdon the branch — code2llm CC re-run under 15 plus independent AST recount and 17-case differential harness,tests/test_dashboard_terminals.pypasses unmodified, ruff check/format clean,./project/governance-check.sh --base origin/mainpasses.