Orchestrata Ultimate › Plans › plan_subphase_0_1 › CHECKLIST

Sub-phase 0.1 Pipeline Checklist

Source: plans/plan_subphase_0_1/CHECKLIST.md at 8a2cb42ad · last changed 2026-07-27 · first committed 2026-04-12 · 119 lines.

Prose pending.

Plan text

Sub-phase 0.1 Pipeline Checklist

Every step must be marked DONE with evidence before proceeding to the next.

Phase A: Pre-requisites (before any pipeline step)

• [ ] A1. Git working tree is clean (git status shows no modified tracked files)
• [ ] A2. On master branch
• [ ] A3. Orchestrator tool bugs fixed and committed SEPARATELY:
  • [ ] A3a. create_sandbox.py list-vs-dict fix for _generate_existing_dataclasses
  • [ ] A3b. generate_prompt.py missing basename Jinja2 filter
• [ ] A4. agent_config.yaml has all required fields: sandbox_base, subplan_path, spec_section_start, spec_section_end, destination (not dest), context_files as source/name dicts
• [ ] A5. Neo4j is running and reachable

Evidence: ___

Phase B: Pipeline Step 1 — Preflight

• [ ] B1. Run: python scripts/orchestrator/preflight.py --config plans/plan_subphase_0_1/agent_config.yaml
• [ ] B2. Result: env_vars PASS, neo4j PASS, redis PASS, neo4j_data PASS
• [ ] B3. Warnings documented (imports WARN, ast_freshness WARN, git_clean WARN are expected)
• [ ] B4. No unexpected FAILs beyond known import chain bug

Evidence: ___

Phase C: Pipeline Step 2 — Generate Tests

• [ ] C1. Run generate_pytest.py on ALL 10 affected source files
• [ ] C2. Generated test files exist in tests/generated/ for each source file
• [ ] C3. Count of generated test methods documented

Evidence: ___

Phase D: Pipeline Step 3 — Create Sandbox

• [ ] D1. Run: python scripts/orchestrator/create_sandbox.py --config plans/plan_subphase_0_1/agent_config.yaml
• [ ] D2. Exit code 0
• [ ] D3. work/ contains exactly 10 files (matching writable_files)
• [ ] D4. context/ contains: spec.md, standards.md, traceability.md, existing_design.mmd, existing_dataclasses.md, ast-ultimate.json, execution-plan.md, subplan.md
• [ ] D5. verify/ is empty

Evidence: ___

Phase E: Pipeline Step 4 — Generate Prompt

• [ ] E1. Run: python scripts/orchestrator/generate_prompt.py --config plans/plan_subphase_0_1/agent_config.yaml --output /tmp/subphase-0.1-prompt.md
• [ ] E2. Exit code 0
• [ ] E3. Prompt file exists and is non-empty

Evidence: ___

Phase F: Pipeline Step 5 — Agent Execution in Sandbox

• [ ] F1. All edits made ONLY to files in work/ directory
• [ ] F2. No repo files modified directly
• [ ] F3. All 10 bug fixes applied (B1-B10 + CLI)
• [ ] F4. work/AUDIT.md created with all 6 required sections
• [ ] F5. Each fix individually verified by reading the changed file in work/

Evidence: ___

Phase G: Pipeline Step 6 — Verify Agent

• [ ] G1. Run: python scripts/orchestrator/verify_agent.py --config plans/plan_subphase_0_1/agent_config.yaml
• [ ] G2. All verify_commands PASS
• [ ] G3. verify/results.md exists
• [ ] G4. If any FAIL: agent fixes in work/, re-run (max 3 iterations)
• [ ] G5. Final result: PASS

Evidence: ___

Phase H: Pipeline Step 7 — Validate Audit

• [ ] H1. Run: python scripts/orchestrator/validate_audit.py --config plans/plan_subphase_0_1/agent_config.yaml
• [ ] H2. file_exists PASS
• [ ] H3. sections PASS (all 6)
• [ ] H4. self_audit_rows PASS (16 rows)
• [ ] H5. no_fail_rows PASS
• [ ] H6. requirements PASS (all 10 REQs)
• [ ] H7. speculative_language PASS
• [ ] H8. changeset_files PASS

Evidence: ___

Phase I: Pipeline Step 8 — Human Review

• [ ] I1. Full diff presented to user
• [ ] I2. User explicitly approves

Evidence: ___

Phase J: Pipeline Step 9 — Merge

• [ ] J1. Run: python scripts/orchestrator/merge_agent.py --config plans/plan_subphase_0_1/agent_config.yaml --no-merge
• [ ] J2. Commit created on branch fix/subphase-0.1-ultimate-bugs
• [ ] J3. All tests pass on branch
• [ ] J4. User decides on merge to master

Evidence: ___

Related

• Plans
• Orchestrata Ultimate — project index
• Workflow
• Tasks