{"abstract":"Failed turns leave the allowance unchanged even though every completed turn consumes budget.","category":"Agent workflow termination","checks":7,"contract":"Return max(0, allowance - number of completed outcomes), clamped at zero.","contract_signature":"allowance, outcomes","evaluation_group":"w3-agent-workflow-termination-successful-turn-budget","failed_approach":"Charging only failed turns leaves successful work free.","family":"w3-agent-workflow-termination-successful-turn-budget","id":"FA-99926","implementations":{"attempt":{"sha256":"95f2d079b86eb5ff1174e4f75c318395f0671df4c01ec75395f61ec7634c3b92","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(allowance, outcomes):\n    return max(0,allowance-outcomes.count('error'))\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('all used mixed', solve(N,['ok','error']*N),0)\ncheck('failed turn debits', solve(3,['error']),2)\ncheck('successful turn debits', solve(3,['ok']),2)\ncheck('empty outcomes', solve(N,[]),N)\ncheck('overrun', solve(1,['ok','error']),0)\ncheck('empty allowance', solve(0,[]),0)\ncheck('two outcomes', solve(4,['ok','error']),2)\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"},"broken":{"sha256":"a1afd1496ad0591aa812757fab4b60de613b77934e974cc189dfe6aebf0a6f36","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(allowance, outcomes):\n    return max(0,allowance-outcomes.count('ok'))\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('all used mixed', solve(N,['ok','error']*N),0)\ncheck('failed turn debits', solve(3,['error']),2)\ncheck('successful turn debits', solve(3,['ok']),2)\ncheck('empty outcomes', solve(N,[]),N)\ncheck('overrun', solve(1,['ok','error']),0)\ncheck('empty allowance', solve(0,[]),0)\ncheck('two outcomes', solve(4,['ok','error']),2)\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"}},"limitations":"Each item in outcomes is one completed turn, labeled ok or error. This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.","method":"Deterministic executable model with adversarial boundary fixtures.","provenance":{"created_by":"Failure Map","dependencies":"Python standard library","family":"w3-agent-workflow-termination-successful-turn-budget","generated_at":"2026-09-30T16:48:29.887613+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"This toy decision rule isolates one bounded agent-loop completion contract.","root_cause":"The ledger subtracts successful outcomes only.","sha256":"1bd663c723ff6047044df579057dc8a0c589618fda7bd1fd24915e0dbd42732b","title":"Workflow: only successful turns debit the workflow budget · case 01","variant":1,"variant_policy":"The fixture code references N, supplied as 1 through 5. Fixed boundary checks may repeat. These records share one mechanism and must remain together in evaluation splits.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":31.261,"exit_code":1,"observations":[{"actual":0,"check":"all used mixed","expected":0,"passed":true},{"actual":2,"check":"failed turn debits","expected":2,"passed":true},{"actual":3,"check":"successful turn debits","expected":2,"passed":false},{"actual":1,"check":"empty outcomes","expected":1,"passed":true},{"actual":0,"check":"overrun","expected":0,"passed":true},{"actual":0,"check":"empty allowance","expected":0,"passed":true},{"actual":3,"check":"two outcomes","expected":2,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"all used mixed\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"failed turn debits\", \"actual\": 2, \"expected\": 2, \"passed\": true}, {\"check\": \"successful turn debits\", \"actual\": 3, \"expected\": 2, \"passed\": false}, {\"check\": \"empty outcomes\", \"actual\": 1, \"expected\": 1, \"passed\": true}, {\"check\": \"overrun\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty allowance\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"two outcomes\", \"actual\": 3, \"expected\": 2, \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":31.011,"exit_code":1,"observations":[{"actual":0,"check":"all used mixed","expected":0,"passed":true},{"actual":3,"check":"failed turn debits","expected":2,"passed":false},{"actual":2,"check":"successful turn debits","expected":2,"passed":true},{"actual":1,"check":"empty outcomes","expected":1,"passed":true},{"actual":0,"check":"overrun","expected":0,"passed":true},{"actual":0,"check":"empty allowance","expected":0,"passed":true},{"actual":3,"check":"two outcomes","expected":2,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"all used mixed\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"failed turn debits\", \"actual\": 3, \"expected\": 2, \"passed\": false}, {\"check\": \"successful turn debits\", \"actual\": 2, \"expected\": 2, \"passed\": true}, {\"check\": \"empty outcomes\", \"actual\": 1, \"expected\": 1, \"passed\": true}, {\"check\": \"overrun\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty allowance\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"two outcomes\", \"actual\": 3, \"expected\": 2, \"passed\": false}], \"passed\": false}\n"}},"member_only":{"stages":["fixed"],"fields":["implementations.fixed","verification.fixed","harness","repair"],"note":"The verified repair, its recorded checks, the repair description, and the scoring harness are available to members."}}