issue-closeout

Autonomy contract. This step is agent-handled, not founder-gated. Once every pending in-scope finding has a non-pending disposition (accepted/rejected/deferred) AND every accepted patch has been applied with required_checks green, close the issue automatically without founder confirmation. The founder is notified post-closeout via the final report (step 6). Founder-gated steps remain: /issue-approve, /prd-approve, /prd-split commit, and any mid-issue scope amendment. Disposition rationale text and patch correctness still need to meet the merge-blocker rules in step 3. Autonomy is about removing the gate prompt, not lowering the bar.

Close the active DSSE issue. Execute in order:

1. Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" status. Confirm receipts.verified and receipts.reviewed are both set. If either is null, stop and tell the founder which step is missing. Do not relaunch /issue-review on your own initiative; that command has its own iteration cap.

2. Pull the snapshotted scope and the pending findings:

   ALLOWED=$(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" allowed-files)
   ISSUE_ID=$(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" status | python3 -c "import sys,json; print(json.load(sys.stdin).get('issue_id',''))")
   python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_findings.py" list "$ISSUE_ID" --only-pending
   

   The list output is JSON: each finding has id, source, severity, body, affected_path, out_of_scope. Show them to the founder one by one. Out-of-scope findings are already filtered from the gate but are still in the list for visibility.

3. Triage each pending in-scope finding using these merge-blocker rules. The disposition is the verb. Use the writer; do NOT hand-edit the JSONL:

   • accepted -> correctness bug introduced by this issue's diff. Patch it now in allowed_files. After the patch lands, mark accepted (the resolved_at stamp is the receipt that the patch happened):

     python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_findings.py" set-disposition "$ISSUE_ID" <finding-id> accepted
     

     If the patch requires re-running checks, re-run /issue-verify. Do NOT auto-relaunch /issue-review. The runner's review-rounds cap exists to break loops; you must respect it. The founder opts in if they want another adversarial pass.

   • deferred -> valid finding but out of contract for this issue (architectural debt, unchanged-code patterns, follow-up work). Rationale REQUIRED. Optional --followup-issue-id if a tracking issue exists:

     python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_findings.py" set-disposition "$ISSUE_ID" <finding-id> deferred \
       --rationale "tracked for follow-up: applies to all 09 agents, not just this slice"
     

   • rejected -> Codex misread scope or hallucinated the issue. Rationale REQUIRED:

     python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_findings.py" set-disposition "$ISSUE_ID" <finding-id> rejected \
       --rationale "codex flagged a config value that is intentionally null; design doc says null disables the feature"
     

4. After every pending in-scope finding has a non-pending disposition (the runner's gate counts these), check the count:

   python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_findings.py" count "$ISSUE_ID" --in-scope-pending
   

   Must print 0. If non-zero, the gate will block close. Re-triage the remaining findings.

5. Commit the patches applied above first: close re-reads the size class from committed HEAD, and uncommitted code counts as L. Record triage, then close. Run these as two separate steps and STOP if the first one exits non-zero -- there is no set -e here, so a failed triage would otherwise fall through into close and produce a confusing second failure at the receipt gate:

   python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" triage
   python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" close