Fix P23-03 original acceptance contract and Opus implementation direction

docs/plans/original-completion-2026-10-02/execution/p23-03/EXISTING_BASELINE_APPLICABILITY.json

@@ -0,0 +1,107 @@
+{
+  "scope": "Existing actual full176 baseline coverage for next P23-03 audit; not P23-03 acceptance",
+  "source_head": "e01e04c62d689016aee1f1a6c614c11a45adcd84",
+  "baseline_receipts": {
+    "input": {
+      "path": "/Users/korizatou114/Projects/とりにく工房ゲーム制作部/artifacts/original-completion-2026-10-02/p08-03-final-regression-d369d1c-r01/runner-input.json",
+      "sha256": "734aecf949e0e9215f679e458bc61326462181142959d451619b0c07539c5e3c"
+    },
+    "all_tests": {
+      "path": "/Users/korizatou114/Projects/とりにく工房ゲーム制作部/artifacts/original-completion-2026-10-02/p08-03-final-regression-d369d1c-r01/all-tests.json",
+      "sha256": "5d9c081e6066457d15aee3c1b90e2d0633810c270f78de8aa4a722c25d32878f"
+    }
+  },
+  "executed_source_count": 1330,
+  "current_source_differences": [],
+  "reusable_baseline_suites": [
+    {
+      "test": "tests/s2/test_inventory_logistics.gd",
+      "passed": true,
+      "executed_source_sha256": "ef8b87e721f57210da02b8cd0822f58e1a4c1cdaa19fe56301a03a87891e73d6",
+      "current_source_sha256": "ef8b87e721f57210da02b8cd0822f58e1a4c1cdaa19fe56301a03a87891e73d6",
+      "exact_test_source": true,
+      "reported_checks": 65,
+      "completion_marker": "PASS: 65 checks\n"
+    },
+    {
+      "test": "tests/s3/test_guest_observation_restore_order.gd",
+      "passed": true,
+      "executed_source_sha256": "7abf5692a07edf8270fa9bf4d9ee89a3835741c208c4c670dc605158532284f2",
+      "current_source_sha256": "7abf5692a07edf8270fa9bf4d9ee89a3835741c208c4c670dc605158532284f2",
+      "exact_test_source": true,
+      "reported_checks": 52,
+      "completion_marker": "Guest observation restore-order diagnostic: 52 checks, 0 failures\n"
+    },
+    {
+      "test": "tests/supply/test_supply_logistics_bridge.gd",
+      "passed": true,
+      "executed_source_sha256": "2d6ed12048b9f17e2f44208bb386d9e06eefa7962e21507fc8e63500aa66052e",
+      "current_source_sha256": "2d6ed12048b9f17e2f44208bb386d9e06eefa7962e21507fc8e63500aa66052e",
+      "exact_test_source": true,
+      "reported_checks": 121,
+      "completion_marker": "PASS: 121 checks / 0 failures\n"
+    },
+    {
+      "test": "tests/ui/test_business_management.gd",
+      "passed": true,
+      "executed_source_sha256": "2c76697f9a911e9dded63ebbbc2b82ee9e616777c50a637eebd91dc4932f85a5",
+      "current_source_sha256": "2c76697f9a911e9dded63ebbbc2b82ee9e616777c50a637eebd91dc4932f85a5",
+      "exact_test_source": true,
+      "reported_checks": 119,
+      "completion_marker": "Business management UI: 119 checks, 0 failures\n"
+    },
+    {
+      "test": "tests/ui/test_elevator_management.gd",
+      "passed": true,
+      "executed_source_sha256": "dff2d3f2a1cea84224aee8f70c4ad53d731df173bc7d16d7ec012c0d16c62e11",
+      "current_source_sha256": "dff2d3f2a1cea84224aee8f70c4ad53d731df173bc7d16d7ec012c0d16c62e11",
+      "exact_test_source": true,
+      "reported_checks": 21,
+      "completion_marker": "Elevator management UI: 21 checks, 0 failures\n"
+    },
+    {
+      "test": "tests/ui/test_guest_observation.gd",
+      "passed": true,
+      "executed_source_sha256": "8f5af3d6ef367512b34d0cf35fd8c1d2848d020419dddfa234120206dbe4f6e4",
+      "current_source_sha256": "8f5af3d6ef367512b34d0cf35fd8c1d2848d020419dddfa234120206dbe4f6e4",
+      "exact_test_source": true,
+      "reported_checks": 22,
+      "completion_marker": "Guest observer: 22 checks, 0 failures\n"
+    },
+    {
+      "test": "tests/ui/test_pixel_tower.gd",
+      "passed": true,
+      "executed_source_sha256": "f149f4b5507247dadf623e777e90b9bdb81f54324b406a8f55adaf89b649866a",
+      "current_source_sha256": "f149f4b5507247dadf623e777e90b9bdb81f54324b406a8f55adaf89b649866a",
+      "exact_test_source": true,
+      "reported_checks": 281,
+      "completion_marker": "PASS: 281 pixel tower checks\n"
+    },
+    {
+      "test": "tests/ui/test_room_presentation.gd",
+      "passed": true,
+      "executed_source_sha256": "eeea7cfbdd534d5e182dc00ec09cb1a8d3688aba85ccf16beb98fe79c70686a9",
+      "current_source_sha256": "eeea7cfbdd534d5e182dc00ec09cb1a8d3688aba85ccf16beb98fe79c70686a9",
+      "exact_test_source": true,
+      "reported_checks": 284,
+      "completion_marker": "PASS: 284 room presentation checks; failures=0\n"
+    },
+    {
+      "test": "tests/world/test_path_transit_density.gd",
+      "passed": true,
+      "executed_source_sha256": "8de5fc8bdf8631ff41fcd4862cea40daa3316040f381f182dc6fe09dba9f3cb9",
+      "current_source_sha256": "8de5fc8bdf8631ff41fcd4862cea40daa3316040f381f182dc6fe09dba9f3cb9",
+      "exact_test_source": true,
+      "reported_checks": 46,
+      "completion_marker": "Path transit density: 46 checks, 0 failures\n"
+    }
+  ],
+  "missing_acceptance": [
+    "All six cross-section categories state/display snapshot equivalence",
+    "Identical demand controlled route-improvement comparison visible and computed",
+    "Actual P23-03 normal OS observation with distinct-PID formal resume",
+    "Exact changed-source final full regression, independent review, integration/final"
+  ],
+  "new_engine_runs": 0,
+  "updated_at_jst": "2026-10-15T07:38:42.792747+09:00"
+}

docs/plans/original-completion-2026-10-02/execution/p23-03/registration-baseline.json

@@ -0,0 +1,10 @@
+[
+  {
+    "id": "P23-03",
+    "requirement_id": "P23-03",
+    "text": "部屋、行列、EV、職員、物資、営業状態が断面上で理解できる表示へ調整する。 受入: 人物や設備の表示が実状態に対応し、同需要の動線改善を観察できる。",
+    "validation_ids": [
+      "p23-life-observation"
+    ]
+  }
+]

docs/plans/original-completion-2026-10-02/execution/p23-03/registration-policy.json

@@ -0,0 +1,23 @@
+{
+  "max_implementers": 1,
+  "max_llm": 2,
+  "max_heavy_tests": 1,
+  "max_llm_runs": null,
+  "timeout_seconds": 900,
+  "test_timeout_seconds": 300,
+  "max_repair_attempts": null,
+  "api_fallback": false,
+  "owner_approval_required": true,
+  "allowed_services": [
+    "codex",
+    "claude",
+    "agy"
+  ],
+  "ui_mode": "semi-automatic",
+  "claude_max_budget_usd": null,
+  "models": {
+    "codex": "gpt-6.1-sol",
+    "claude": "claude-opus-5-5",
+    "agy": null
+  }
+}

docs/plans/original-completion-2026-10-02/execution/p23-03/registration-validations.json

@@ -0,0 +1,11 @@
+{
+  "p23-life-observation": {
+    "argv": [
+      "{python}",
+      "-B",
+      "tools/check_p23_life_observation_evidence.py",
+      "--verify-only"
+    ],
+    "timeout_seconds": 180
+  }
+}

docs/spec/acceptance/P23-03.json

@@ -0,0 +1,76 @@
+{
+  "schema": "original-delivery-unit-v1",
+  "plan_id": "P23-03",
+  "title": "生活の観察",
+  "authority": {
+    "approved_plan": "docs/plans/original-completion-2026-10-02/IMPLEMENTATION_PLAN.md#p23",
+    "original": "docs/traceability/original/BASELINE.txt",
+    "original_sha256": "75e4bdbdeb379c9269553f0c776bdb9cc96e01f2d6aa5ca650d132c63a8aeb1a",
+    "original_lines": [
+      10,
+      13,
+      16,
+      25,
+      37,
+      43,
+      69,
+      83,
+      106,
+      216
+    ]
+  },
+  "original_work": "部屋、行列、EV、職員、物資、営業状態が断面上で理解できる表示へ調整する。",
+  "original_acceptance": "人物や設備の表示が実状態に対応し、同需要の動線改善を観察できる。",
+  "denominator": {
+    "packages": 30,
+    "delivery_units": 88,
+    "this_unit": 1,
+    "partial_credit": false
+  },
+  "commander_direction": {
+    "path": "docs/plans/original-completion-2026-10-02/execution/p23-03/OPUS_CONCRETE_IMPLEMENTATION_DIRECTION.json",
+    "run": "83e836e232c74975aaf51f4fab5a1af9",
+    "codex_model": "gpt-6-astra"
+  },
+  "conditions": [
+    "room_occupancy_and_operation",
+    "queues_and_overflow",
+    "elevator_state_and_passengers",
+    "staff_state_and_jobs",
+    "supplies_and_carried_goods",
+    "same_demand_route_improvement",
+    "normal_os_and_distinct_pid_resume"
+  ],
+  "scope": [
+    "All original six categories remain required: room, queue, EV, staff, goods, business state. Generic display of actual definitions/state, never an implementation limited to fixture IDs.",
+    "Representative acceptance scenarios use existing original-matched constructible definitions and real runtime operations, no undefined facility proxies or invented costs/mana/staff capacities. They do not establish all30 construction, finished asset, rights or natural-gameplay acceptance.",
+    "Retain P08/P22 package dependencies in plan. Available unit inputs: integrated P08-02/03, P22-01 inventory, current Runtime/report definitions and existing Kenney/code art. Unavailable P08-01 geometry/production values, D08/D09 quantities, P22-02/03 asset work remain explicitly open; they may not be silently considered done.",
+    "No Runtime/service/production data values or new assets. No visual redesign or new UI entry. Necessary existing renderer/read-only presentation wiring and evidence only."
+  ],
+  "worker_deliverables": [
+    "Phase0 API_AND_STATE_MAP.md: real file:line and SHA for same-seed/reset/arrival inputs/build commands/clock/public reports/formal save-load APIs. Confirm actual deterministic demand mechanism before related implementation. If unavailable, preserve work and report precise missing capability and minimal separate proposal; do not manufacture same-demand proof or stop unrelated preparation.",
+    "One coherent frame observation model consumed by actual drawing, with public deep-copy get_life_observation_report. Cover actual room users and occupancy vs queue, state reasons, queues/overflow, EV position/load/direction/phase, staff task/state/layer/position, carried goods and actual supply report data. Preserve existing motion/layer/nonmutation/selection behavior.",
+    "Visible per-room business reason using FacilityInstance enum names; distinguish closed/no access/no power/no staff/degraded and suspended raid/damage from actual fields. No ambiguous reliance solely on tiny color lamp or utilization badge.",
+    "Visible normal-view route density and actual supplies, reusing established visual style and existing get_cell_traffic/report fields; no fictional stock/request data.",
+    "tests/ui/test_p23_life_observation.gd, diagnostics fixtures, Root run_p23_life_observation.py and strict checker with meaningful negatives, condition matrix and honest implementation metadata. No placeholder PASS or fixed all-true assertions."
+  ],
+  "evidence_requirements": [
+    "Whole typed actual state and draw-consumed report rows; checker independently recomputes each relevant field using enum/schema definitions, never trusts all-boolean or self-asserted report. Screenshots pixel/rect provenance must correspond to actual rendered report positions.",
+    "LayoutsA/B: identical recorded seed, demand/arrival script, budget, initial clock, service definitions and unchanged production settings; actual Runtime paths differ only through predeclared allowed layout improvement. Record actual arrival input events, paths/arrival times, queues/wait metrics/density/completed services. Predeclare relevant metric; B strictly improves without new arbitrary numeric threshold. Fixture-only fabricated state is not valid same-demand proof.",
+    "Root actual OS observation on both layouts across six categories, FRONT/BACK, ordinary pan/zoom; formal save and distinct actual PID normal load, state/display remains correct. Handler tests or submitted scripts are not OS.",
+    "Collector request/ACK lifecycle, full actual CUA tool call IDs/arguments/screenshots/calibration from start, named helper self-properties, exact PID/engine/source/spec/settings/environment and guarded whole default-player profiles. No partial failed run splicing, no raw receipt relabel.",
+    "Use existing owned process/ordinary audio teardown gates. Check engine end/cleanup/protection on every run. Preserve failure history.",
+    "Sparse diagnostic snapshots with every acceptance field, content-hash reuse and streamed manifests; no unnecessary all-state-per-frame copies or arbitrary review byte limit. Required source/evidence may not be omitted for size.",
+    "Final exact frozen candidate: worker static/local and impact first; Root native/OS then mandatory one full regression, independent Opus all-condition review, integration/final/ledger. Reuse only matching actual source/input/settings/environment applicability.",
+    "Pin stable immutable spec/contract/fixture/engine/source plus relevant normative plan acceptance text. Record progress metadata separately, avoiding unnecessary reruns from unrelated progress-only plan text changes. Never ignore normative input change.",
+    "No Windows same-distribution/device credit, P23-02 held-gesture or x3 performance credit, P25 finished asset/full motion credit, or all30 facility credit from this unit."
+  ],
+  "worker_instructions": [
+    "Read original work/acceptance, actual recorded Opus direction and relevant current sources before changes; do Phase0 static API audit first.",
+    "One Codex Astra worker, no nested providers/agents/parallel workers. User removed all individual repair/inference/material caps; do not stop on old2/3/500k restrictions. Timeout900 unchanged. No API fallback/new billing/permissions.",
+    "Root only executes Godot/native/OS/full regression after genuine submitted. Worker runs meaningful local Python syntax/checker tests only, no Godot or full regression. Missing Root evidence is expected at worker submission; state it explicitly.",
+    "Keep exact allowed paths. completion_marker_contracts append only one strict source authority entry; suite-policy only if new suite uses existing ordinary cleanup, sourceSHA-specific entry preserve all old policies.",
+    "Use existing run_all_tests.py/source refs/strict marker/protected-profile/typed codec/owned process infrastructure read-only; no broad harness reimplementation or proof-gate removal.",
+    "If actual required defect outside allowed scope occurs, provide failing evidence/minimal proposal and preserve independent work. Root and Opus decide scope next."
+  ]
+}