{ "schema_version": 1, "generated_at": "2026-11-02T22:50:16.358712+00:00", "model": "see individual runs", "runs": [ { "id": "flights", "title": "Search future flights", "goal": "Find one-way flights from Zurich to London on February 01, 2027, for one adult in economy. Stop when matching flight options are visible. Do not select or book a flight.", "url": "https://www.google.com/travel/flights?hl=en", "local": false, "status": "passed", "agent_status": "ready", "completion_source": "independent_verifier", "verification_checks": 23, "rejected_completion_claims": 0, "elapsed_ms": 323359, "wall_ms": 324891, "model": "jev-style-2b-decision-v4", "text_model": "qwen3.8-27b-uncensored-q4_k_m", "hybrid": true, "fallback_calls": 13, "capture_enabled": true, "final_frame_captured": true, "captured_frames": 15, "all_decisions_reviewed": false, "all_executed_actions_reviewed": true, "reviews_skipped_stale": 8, "timing": { "primary_ms": 42656, "review_ms": 270622, "text_ms": 4565, "other_ms": 5516 }, "fallback_models": [ "qwen3.8-27b-uncensored-q4_k_m" ], "probability_source": "jevstyle", "verification": { "passed": true, "checks": [ { "name": "flight search page", "passed": true }, { "name": "one way", "passed": true }, { "name": "one passenger", "passed": true }, { "name": "economy cabin", "passed": true }, { "name": "Zürich origin committed", "passed": true }, { "name": "London destination committed", "passed": true }, { "name": "departure date", "passed": true }, { "name": "departure year", "passed": true }, { "name": "visible matching flights", "passed": true } ] }, "error": null, "steps": [ { "step": 1, "operation": "CLICK", "target": "10", "label": "CLICK element 10", "latency_ms": 15191, "elapsed_ms": 15557, "confidence": 0.3200446362112461, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.45603570896899687, "TYPE_TEXT": 0.25463706874066483, "SCROLL_DOWN": 0.09584259872084376, "WAIT": 0.07805349245453032, "BLOCKED": 0.11543113111496431 }, "target_probabilities": { "1": 0.008418976289913577, "2": 0.02732632180863219, "3": 0.03475969661360342, "4": 0.09690929186466775, "5": 0.0008561653009569271, "6": 0.0008479198541349414, "7": 0.0024775499995019832, "8": 0.003005426380336015, "9": 0.0019126393569749442, "10": 0.015482535165620275, "11": 0.007818224878438917, "12": 0.03687590182002497, "13": 0.06841581458103752, "14": 0.14912412965803346, "15": 0.3991140115532572, "16": 0.008414357396883074, "17": 0.042035557117489165, "18": 0.046184970805054425, "19": 0.006356590459099119, "20": 0.01866748449434985, "21": 0.012567800931746897, "22": 0.004376981504342409, "23": 0.008051652165900983 } }, { "step": 2, "operation": "CLICK", "target": "2", "label": "CLICK element 2", "latency_ms": 6278, "elapsed_ms": 22156, "confidence": 0.37556972817378775, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.5004557825390302, "SCROLL_DOWN": 0.2531277718360789, "WAIT": 0.10464035829895334, "DONE": 0.08168243973871427, "BLOCKED": 0.060093647587223305 }, "target_probabilities": { "1": 0.0958888711337494, "2": 0.7979527480453091, "3": 0.10615838082094144 } }, { "step": 3, "operation": "CLICK", "target": "13", "label": "CLICK element 13", "latency_ms": 15126, "elapsed_ms": 39058, "confidence": 0.3928541667931129, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.5142833334344903, "TYPE_TEXT": 0.1972203992976412, "SCROLL_DOWN": 0.09355567644482753, "WAIT": 0.09721468049302293, "BLOCKED": 0.09772591033001814 }, "target_probabilities": { "1": 0.0074710646623258525, "2": 0.01924427612634116, "3": 0.019318966552992277, "4": 0.04405404303929823, "5": 0.000827376093181249, "6": 0.0008548446738460472, "7": 0.002522554179830672, "8": 0.0034250352881441235, "9": 0.0016524653956730279, "10": 0.11449697774163094, "11": 0.015843529705509986, "12": 0.03042168914005317, "13": 0.10158928439685391, "14": 0.21928805875681973, "15": 0.28266163573803177, "16": 0.03263760749222701, "17": 0.039511296764768646, "18": 0.005347452524463748, "19": 0.028199146451015098, "20": 0.014936385882728241, "21": 0.006427561071734289, "22": 0.009268748322530867 } }, { "step": 4, "operation": "TYPE_TEXT", "target": "1", "label": "TYPE_TEXT element 1", "latency_ms": 13127, "elapsed_ms": 57959, "confidence": 0.4260849179305395, "text_latency_ms": 4565, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.1296877720536212, "CLICK": 0.5408679343444316, "SCROLL_DOWN": 0.13375869054941772, "WAIT": 0.117782472311782, "BLOCKED": 0.0779031307407476 }, "target_probabilities": { "1": 1.0 } }, { "step": 5, "operation": "CLICK", "target": "3", "label": "CLICK element 3", "latency_ms": 11234, "elapsed_ms": 69336, "confidence": 0.20621662625794074, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.2425071131158835, "CLICK": 0.33851385521495064, "SCROLL_DOWN": 0.19554525664263336, "WAIT": 0.12011010548362389, "DONE": 0.02741053867311891, "BLOCKED": 0.07591313086978972 }, "target_probabilities": { "1": 0.06384811590653473, "2": 0.2621408195602903, "3": 0.18295393207424496, "4": 0.010183191755445107, "5": 0.047101561636297, "6": 0.05723524654731022, "7": 0.23272411557662895, "8": 0.010677425268082097, "9": 0.1264488316527114, "10": 0.006686760022455256 } }, { "step": 6, "operation": "CLICK", "target": "14", "label": "CLICK element 14", "latency_ms": 15080, "elapsed_ms": 86164, "confidence": 0.33025201404048, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.46420161123238396, "TYPE_TEXT": 0.23257176847599095, "SCROLL_DOWN": 0.11917728263094365, "WAIT": 0.09380800569942196, "BLOCKED": 0.09024133196125947 }, "target_probabilities": { "1": 0.004415238470903116, "2": 0.010129999838363917, "3": 0.015576647258220477, "4": 0.03531595549880973, "5": 0.0006073963940592228, "6": 0.0006434332649901858, "7": 0.00181670440504391, "8": 0.001972056957707553, "9": 0.0009889268226358297, "10": 0.060725750714875903, "11": 0.007054747881806821, "12": 0.013954975143286252, "13": 0.015619272522962675, "14": 0.49141931537528954, "15": 0.219030469377326, "16": 0.03414370087100297, "17": 0.015001903594098634, "18": 0.004435785848060738, "19": 0.02859702114339899, "20": 0.023034527635416316, "21": 0.006929331331944427, "22": 0.008586839649796773 } }, { "step": 7, "operation": "CLICK", "target": "8", "label": "CLICK element 8", "latency_ms": 12273, "elapsed_ms": 99654, "confidence": 0.4753195960052381, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.1443783086243436, "CLICK": 0.5802556768041904, "SCROLL_DOWN": 0.144782903185383, "WAIT": 0.0775845757158451, "BLOCKED": 0.052998535670237955 }, "target_probabilities": { "1": 0.26496952680524183, "2": 0.06751268698692124, "3": 0.07088114993209718, "4": 0.055196313302971686, "5": 0.009955853777377772, "6": 0.02297857820984501, "7": 0.0051857705983188295, "8": 0.49550262248487686, "9": 0.00781749790234967 } }, { "step": 8, "operation": "CLICK", "target": "16", "label": "CLICK element 16", "latency_ms": 17077, "elapsed_ms": 118701, "confidence": 0.4505385614924138, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.560430849193931, "TYPE_TEXT": 0.17187077177898866, "SCROLL_DOWN": 0.10247910362672247, "WAIT": 0.12121421888204846, "BLOCKED": 0.04400505651830943 }, "target_probabilities": { "1": 0.0034987597279514202, "2": 0.005519949076646535, "3": 0.006448238453586878, "4": 0.021610123261977126, "5": 0.0004179252044667397, "6": 0.000411896290211359, "7": 0.0018419499316260255, "8": 0.0016184059076621053, "9": 0.0008269700434460153, "10": 0.04501569495411339, "11": 0.009797871435859468, "12": 0.011153188330000034, "13": 0.023345453666757294, "14": 0.0032341530830762213, "15": 0.2491655851539376, "16": 0.2323809613525186, "17": 0.31058517162794486, "18": 0.027183289883101716, "19": 0.005213194218086833, "20": 0.021582407144076606, "21": 0.010192882313032005, "22": 0.0030623239167544528, "23": 0.00589360502316668 } }, { "step": 9, "operation": "CLICK", "target": "62", "label": "CLICK element 62", "latency_ms": 33529, "elapsed_ms": 152695, "confidence": 0.5373463316418788, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.18227380531964374, "CLICK": 0.6298770653135031, "SCROLL_DOWN": 0.0762919468606384, "WAIT": 0.05330993903514205, "BLOCKED": 0.05824724347107285 }, "target_probabilities": { "1": 0.2841938687970475, "2": 0.08440405535471174, "3": 0.016516125008005676, "4": 0.00523241184478628, "5": 0.0047327850528870044, "6": 0.0038574254972259816, "7": 0.004646787778663934, "8": 0.0025425921593731225, "9": 0.002407308500071315, "10": 0.001512516696173591, "11": 0.001773767021459979, "12": 0.0027774069879290997, "13": 0.001658872837556557, "14": 0.0016309228465719524, "15": 0.001514950682464496, "16": 0.0020277759061536047, "17": 0.0018569363460615902, "18": 0.001549289014370634, "19": 0.0016439961467554834, "20": 0.0016273688810834635, "21": 0.0012690497210582248, "22": 0.0013304772627574278, "23": 0.001977046489102524, "24": 0.0018147112133247933, "25": 0.0014888021017111096, "26": 0.0014726294112865457, "27": 0.0017016637151263821, "28": 0.0012381893388215912, "29": 0.0012643359899972937, "30": 0.003259953783888551, "31": 0.3173360464088468, "32": 0.0158746694251598, "33": 0.005681640567663066, "34": 0.0033627257517683524, "35": 0.0034042409510815805, "36": 0.0041887292982455354, "37": 0.009345233887408889, "38": 0.0026409509605844978, "39": 0.0018101512087436312, "40": 0.0016890250224856458, "41": 0.0023744952273328573, "42": 0.0018824318722916928, "43": 0.0012724877770674534, "44": 0.0022799853365230677, "45": 0.001987605824691757, "46": 0.0019233833724384042, "47": 0.002680765220180445, "48": 0.0015026541148921127, "49": 0.0014648077490114501, "50": 0.0015071506642448903, "51": 0.0010394596099286013, "52": 0.0016094835871733138, "53": 0.0019487649503235394, "54": 0.002889982283556705, "55": 0.0023891180254807173, "56": 0.0018367783067171144, "57": 0.002920142988816368, "58": 0.0034188719173822387, "59": 0.0024861520912202667, "60": 0.00388487964780808, "61": 0.09860768366797587, "62": 0.031028795022943857, "63": 0.01680668487358409 } }, { "step": 10, "operation": "CLICK", "target": "66", "label": "CLICK element 66", "latency_ms": 51413, "elapsed_ms": 208383, "confidence": 0.41799133367487784, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.1738013226701806, "CLICK": 0.5343930669399023, "SCROLL_DOWN": 0.09984753957940205, "WAIT": 0.09520919466170057, "BLOCKED": 0.09674887614881442 }, "target_probabilities": { "1": 0.09547103523085364, "2": 0.03847155543451359, "3": 0.0029749768267924126, "4": 0.0017923334974101004, "5": 0.0024349393985361755, "6": 0.003110131725528689, "7": 0.002859062351195431, "8": 0.0011343101840171083, "9": 0.002635982013113382, "10": 0.0008084458763219796, "11": 0.0009662713847842174, "12": 0.0012592212342193627, "13": 0.0016370108734964563, "14": 0.001324886484322104, "15": 0.0015880423313704387, "16": 0.002053585301421238, "17": 0.000881042705292755, "18": 0.0005637496567659538, "19": 0.0012599624036192492, "20": 0.001005685929784567, "21": 0.0007423163085104397, "22": 0.0006713474955399556, "23": 0.000636804588089939, "24": 0.0007244335703941777, "25": 0.000682319177218825, "26": 0.0009126720647547345, "27": 0.0007025491802975871, "28": 0.0003674549675332204, "29": 0.0007076466761674474, "30": 0.0008902011342186177, "31": 0.0033018429872372114, "32": 0.0012981339361767545, "33": 0.007865160036215737, "34": 0.5115440540177051, "35": 0.10038330993087714, "36": 0.01579498479451465, "37": 0.02230490398247603, "38": 0.004996151912881816, "39": 0.006933432072976463, "40": 0.0074795913810283025, "41": 0.0031236108627158803, "42": 0.003287358532652323, "43": 0.0019834606875599016, "44": 0.001711406654223314, "45": 0.004259467502169464, "46": 0.002666439962328576, "47": 0.003428719156484286, "48": 0.0019851887605948594, "49": 0.0017850922041809736, "50": 0.00500171284516042, "51": 0.0019518471280100937, "52": 0.004695229142138116, "53": 0.001994301315838412, "54": 0.0012679461915259221, "55": 0.0011413549614826986, "56": 0.002322289176960771, "57": 0.00487360029796004, "58": 0.003012454986625268, "59": 0.002769095741580151, "60": 0.005952693611567942, "61": 0.013629013858883585, "62": 0.0062168404526927856, "63": 0.009163972809900039, "64": 0.018251493355124212, "65": 0.005129093243433915, "66": 0.02259980649654085, "67": 0.012624969003492184 } }, { "step": 11, "operation": "CLICK", "target": "34", "label": "CLICK element 34", "latency_ms": 45830, "elapsed_ms": 258747, "confidence": 0.524639263444802, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.12601676605460296, "CLICK": 0.6197114107558417, "SCROLL_DOWN": 0.08402742669431708, "WAIT": 0.09775907362810889, "BLOCKED": 0.07248532286712941 }, "target_probabilities": { "1": 0.3092625559066865, "2": 0.1139036246180966, "3": 0.1293404099488606, "4": 0.006755271744116888, "5": 0.008762884593987602, "6": 0.02367809602209752, "7": 0.014750739685672675, "8": 0.010029540397031165, "9": 0.013823003213139087, "10": 0.003527592038527669, "11": 0.008410039332114698, "12": 0.007583459323910069, "13": 0.009041435484282675, "14": 0.004832204024258178, "15": 0.0031487351205332103, "16": 0.0057053789422400695, "17": 0.0031506352804395077, "18": 0.0034248518467575872, "19": 0.006186946660573017, "20": 0.0049268299953850354, "21": 0.002983649920774405, "22": 0.00292273679886154, "23": 0.006199106451886781, "24": 0.0021200872665755647, "25": 0.002848093330633711, "26": 0.004111842056217808, "27": 0.006336625844853799, "28": 0.00243655362131817, "29": 0.0029970597924792093, "30": 0.005366423447232175, "31": 0.006954412134506873, "32": 0.013832767143080616, "33": 0.02720545753520685, "34": 0.04353366139913411, "35": 0.00549425735681498, "36": 0.003443037228953602, "37": 0.01870272844770661, "38": 0.002397840184019158, "39": 0.0021432854961824397, "40": 0.009028676101391247, "41": 0.003260085906284383, "42": 0.005500754285121281, "43": 0.0025053101418355006, "44": 0.002837619887473326, "45": 0.0024677256748537467, "46": 0.002478801396248093, "47": 0.0030442934985842303, "48": 0.0016211167884515997, "49": 0.0026088014437098566, "50": 0.006377196739403867, "51": 0.004818306514010054, "52": 0.005300079587460296, "53": 0.003910778530790069, "54": 0.00166155205164973, "55": 0.0015589472146223752, "56": 0.003233916839670168, "57": 0.0061833684846513675, "58": 0.004495349550608095, "59": 0.001714738337506663, "60": 0.005075708545871969, "61": 0.011651957432924794, "62": 0.010415217994955863, "63": 0.02225734622312084, "64": 0.02371849119365195 } }, { "step": 12, "operation": "CLICK", "target": "65", "label": "CLICK element 65", "latency_ms": 47005, "elapsed_ms": 306354, "confidence": 0.4172416590346698, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "TYPE_TEXT": 0.10416608190135421, "CLICK": 0.5337933272277359, "SCROLL_DOWN": 0.10937863113508982, "WAIT": 0.1776092537195145, "BLOCKED": 0.07505270601630559 }, "target_probabilities": { "1": 0.021216169593630763, "2": 0.01760485831800737, "3": 0.0016671250350835053, "4": 0.00419820850668998, "5": 0.001225001156924609, "6": 0.0011778036790397988, "7": 0.0032161428380965825, "8": 0.0010335925909395515, "9": 0.001145394527304556, "10": 0.0015623866706652328, "11": 0.0007410419830429642, "12": 0.0010352802454046321, "13": 0.0010715317563644898, "14": 0.0009666641030468616, "15": 0.0006296319628578267, "16": 0.0006026943936880989, "17": 0.0016564348704730697, "18": 0.000380397689101599, "19": 0.0005299435160961098, "20": 0.0008081104675640552, "21": 0.00033411858341790486, "22": 0.00043687448025148535, "23": 0.00044127691587864283, "24": 0.0006683370497246211, "25": 0.00034339467184076413, "26": 0.0004250342658875204, "27": 0.0007648328477871297, "28": 0.0004931316969864307, "29": 0.00032252785743643866, "30": 0.000277793193018145, "31": 0.0009543799995063879, "32": 0.0014294397441775525, "33": 0.0005197021879808047, "34": 0.0015113924519436427, "35": 0.022132055926310543, "36": 0.0007840566027718887, "37": 0.0003464106696665605, "38": 0.0013903561412772483, "39": 0.000468919461410509, "40": 0.00040937071624178647, "41": 0.006504494479753687, "42": 0.0004256855477600374, "43": 0.00036306914823569015, "44": 0.00018362881647967448, "45": 0.00036483153411686795, "46": 0.0005568008550046853, "47": 0.00029998264430000713, "48": 0.00020128885335195387, "49": 0.0002251601915565821, "50": 0.00031248409072043477, "51": 0.0010647675701650546, "52": 0.0005404964573666816, "53": 0.0005279692188975893, "54": 0.00020081887464850343, "55": 0.0003380692479072648, "56": 0.00028746986413873935, "57": 0.0003502111116174133, "58": 0.0005964871966340508, "59": 0.0007584679193246562, "60": 0.0004826687108294951, "61": 0.0005088840623904761, "62": 0.001110223811792064, "63": 0.0006396025096155624, "64": 0.0022657631491014734, "65": 0.8839688547667538 } }, { "step": 13, "operation": "CLICK", "target": "17", "label": "CLICK element 17", "latency_ms": 14634, "elapsed_ms": 321403, "confidence": 0.41523085077695965, "text_latency_ms": 0, "decision_source": "local_fallback", "probability_source": "jevstyle", "fallback_model": "qwen3.8-27b-uncensored-q4_k_m", "operation_probabilities": { "CLICK": 0.07188655220052867, "TYPE_TEXT": 0.03177253163456043, "SCROLL_DOWN": 0.06363562641472553, "WAIT": 0.3036773589855201, "DONE": 0.5126923756474664, "BLOCKED": 0.01633555511719899 }, "target_probabilities": { "1": 0.0019544391063725233, "2": 0.003115840135952819, "3": 0.0026574385686194114, "4": 0.015980406246838462, "5": 0.0003641417318487303, "6": 0.00035168850171548845, "7": 0.0014722208643252932, "8": 0.0012232167491839712, "9": 0.0006137740332789434, "10": 0.04490231992856982, "11": 0.028862514680214918, "12": 0.2589151587501319, "13": 0.028614876280452114, "14": 0.0054841615242767, "15": 0.17857483733713478, "16": 0.1330941157313596, "17": 0.25688009239309845, "18": 0.006646550754855628, "19": 0.0025620654786837646, "20": 0.012896620439527235, "21": 0.005493306623589713, "22": 0.002800693738390679, "23": 0.006539520401579051 } } ], "decisions": [ { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.45603570896899687, "TYPE_TEXT": 0.25463706874066483, "SCROLL_DOWN": 0.09584259872084376, "WAIT": 0.07805349245453032, "BLOCKED": 0.11543113111496431 }, "target_probabilities": { "1": 0.008418976289913577, "2": 0.02732632180863219, "3": 0.03475969661360342, "4": 0.09690929186466775, "5": 0.0008561653009569271, "6": 0.0008479198541349414, "7": 0.0024775499995019832, "8": 0.003005426380336015, "9": 0.0019126393569749442, "10": 0.015482535165620275, "11": 0.007818224878438917, "12": 0.03687590182002497, "13": 0.06841581458103752, "14": 0.14912412965803346, "15": 0.3991140115532572, "16": 0.008414357396883074, "17": 0.042035557117489165, "18": 0.046184970805054425, "19": 0.006356590459099119, "20": 0.01866748449434985, "21": 0.012567800931746897, "22": 0.004376981504342409, "23": 0.008051652165900983 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1465, "fallback_latency_ms": 13718, "latency_ms": 15191, "elapsed_ms": 15198, "confidence": 0.3200446362112461 }, { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.5004557825390302, "SCROLL_DOWN": 0.2531277718360789, "WAIT": 0.10464035829895334, "DONE": 0.08168243973871427, "BLOCKED": 0.060093647587223305 }, "target_probabilities": { "1": 0.0958888711337494, "2": 0.7979527480453091, "3": 0.10615838082094144 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 741, "fallback_latency_ms": 5533, "latency_ms": 6278, "elapsed_ms": 21918, "confidence": 0.37556972817378775 }, { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.5142833334344903, "TYPE_TEXT": 0.1972203992976412, "SCROLL_DOWN": 0.09355567644482753, "WAIT": 0.09721468049302293, "BLOCKED": 0.09772591033001814 }, "target_probabilities": { "1": 0.0074710646623258525, "2": 0.01924427612634116, "3": 0.019318966552992277, "4": 0.04405404303929823, "5": 0.000827376093181249, "6": 0.0008548446738460472, "7": 0.002522554179830672, "8": 0.0034250352881441235, "9": 0.0016524653956730279, "10": 0.11449697774163094, "11": 0.015843529705509986, "12": 0.03042168914005317, "13": 0.10158928439685391, "14": 0.21928805875681973, "15": 0.28266163573803177, "16": 0.03263760749222701, "17": 0.039511296764768646, "18": 0.005347452524463748, "19": 0.028199146451015098, "20": 0.014936385882728241, "21": 0.006427561071734289, "22": 0.009268748322530867 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1514, "fallback_latency_ms": 13603, "latency_ms": 15126, "elapsed_ms": 38913, "confidence": 0.3928541667931129 }, { "operation": "TYPE_TEXT", "operation_probabilities": { "TYPE_TEXT": 0.1296877720536212, "CLICK": 0.5408679343444316, "SCROLL_DOWN": 0.13375869054941772, "WAIT": 0.117782472311782, "BLOCKED": 0.0779031307407476 }, "target_probabilities": { "1": 1.0 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1205, "fallback_latency_ms": 11912, "latency_ms": 13127, "elapsed_ms": 53130, "confidence": 0.4260849179305395 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.2425071131158835, "CLICK": 0.33851385521495064, "SCROLL_DOWN": 0.19554525664263336, "WAIT": 0.12011010548362389, "DONE": 0.02741053867311891, "BLOCKED": 0.07591313086978972 }, "target_probabilities": { "1": 0.06384811590653473, "2": 0.2621408195602903, "3": 0.18295393207424496, "4": 0.010183191755445107, "5": 0.047101561636297, "6": 0.05723524654731022, "7": 0.23272411557662895, "8": 0.010677425268082097, "9": 0.1264488316527114, "10": 0.006686760022455256 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1201, "fallback_latency_ms": 10024, "latency_ms": 11234, "elapsed_ms": 69255, "confidence": 0.20621662625794074 }, { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.46420161123238396, "TYPE_TEXT": 0.23257176847599095, "SCROLL_DOWN": 0.11917728263094365, "WAIT": 0.09380800569942196, "BLOCKED": 0.09024133196125947 }, "target_probabilities": { "1": 0.004415238470903116, "2": 0.010129999838363917, "3": 0.015576647258220477, "4": 0.03531595549880973, "5": 0.0006073963940592228, "6": 0.0006434332649901858, "7": 0.00181670440504391, "8": 0.001972056957707553, "9": 0.0009889268226358297, "10": 0.060725750714875903, "11": 0.007054747881806821, "12": 0.013954975143286252, "13": 0.015619272522962675, "14": 0.49141931537528954, "15": 0.219030469377326, "16": 0.03414370087100297, "17": 0.015001903594098634, "18": 0.004435785848060738, "19": 0.02859702114339899, "20": 0.023034527635416316, "21": 0.006929331331944427, "22": 0.008586839649796773 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1506, "fallback_latency_ms": 13566, "latency_ms": 15080, "elapsed_ms": 85991, "confidence": 0.33025201404048 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.1443783086243436, "CLICK": 0.5802556768041904, "SCROLL_DOWN": 0.144782903185383, "WAIT": 0.0775845757158451, "BLOCKED": 0.052998535670237955 }, "target_probabilities": { "1": 0.26496952680524183, "2": 0.06751268698692124, "3": 0.07088114993209718, "4": 0.055196313302971686, "5": 0.009955853777377772, "6": 0.02297857820984501, "7": 0.0051857705983188295, "8": 0.49550262248487686, "9": 0.00781749790234967 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1130, "fallback_latency_ms": 11137, "latency_ms": 12273, "elapsed_ms": 99396, "confidence": 0.4753195960052381 }, { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.560430849193931, "TYPE_TEXT": 0.17187077177898866, "SCROLL_DOWN": 0.10247910362672247, "WAIT": 0.12121421888204846, "BLOCKED": 0.04400505651830943 }, "target_probabilities": { "1": 0.0034987597279514202, "2": 0.005519949076646535, "3": 0.006448238453586878, "4": 0.021610123261977126, "5": 0.0004179252044667397, "6": 0.000411896290211359, "7": 0.0018419499316260255, "8": 0.0016184059076621053, "9": 0.0008269700434460153, "10": 0.04501569495411339, "11": 0.009797871435859468, "12": 0.011153188330000034, "13": 0.023345453666757294, "14": 0.0032341530830762213, "15": 0.2491655851539376, "16": 0.2323809613525186, "17": 0.31058517162794486, "18": 0.027183289883101716, "19": 0.005213194218086833, "20": 0.021582407144076606, "21": 0.010192882313032005, "22": 0.0030623239167544528, "23": 0.00589360502316668 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1584, "fallback_latency_ms": 15485, "latency_ms": 17077, "elapsed_ms": 118417, "confidence": 0.4505385614924138 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.18227380531964374, "CLICK": 0.6298770653135031, "SCROLL_DOWN": 0.0762919468606384, "WAIT": 0.05330993903514205, "BLOCKED": 0.05824724347107285 }, "target_probabilities": { "1": 0.2841938687970475, "2": 0.08440405535471174, "3": 0.016516125008005676, "4": 0.00523241184478628, "5": 0.0047327850528870044, "6": 0.0038574254972259816, "7": 0.004646787778663934, "8": 0.0025425921593731225, "9": 0.002407308500071315, "10": 0.001512516696173591, "11": 0.001773767021459979, "12": 0.0027774069879290997, "13": 0.001658872837556557, "14": 0.0016309228465719524, "15": 0.001514950682464496, "16": 0.0020277759061536047, "17": 0.0018569363460615902, "18": 0.001549289014370634, "19": 0.0016439961467554834, "20": 0.0016273688810834635, "21": 0.0012690497210582248, "22": 0.0013304772627574278, "23": 0.001977046489102524, "24": 0.0018147112133247933, "25": 0.0014888021017111096, "26": 0.0014726294112865457, "27": 0.0017016637151263821, "28": 0.0012381893388215912, "29": 0.0012643359899972937, "30": 0.003259953783888551, "31": 0.3173360464088468, "32": 0.0158746694251598, "33": 0.005681640567663066, "34": 0.0033627257517683524, "35": 0.0034042409510815805, "36": 0.0041887292982455354, "37": 0.009345233887408889, "38": 0.0026409509605844978, "39": 0.0018101512087436312, "40": 0.0016890250224856458, "41": 0.0023744952273328573, "42": 0.0018824318722916928, "43": 0.0012724877770674534, "44": 0.0022799853365230677, "45": 0.001987605824691757, "46": 0.0019233833724384042, "47": 0.002680765220180445, "48": 0.0015026541148921127, "49": 0.0014648077490114501, "50": 0.0015071506642448903, "51": 0.0010394596099286013, "52": 0.0016094835871733138, "53": 0.0019487649503235394, "54": 0.002889982283556705, "55": 0.0023891180254807173, "56": 0.0018367783067171144, "57": 0.002920142988816368, "58": 0.0034188719173822387, "59": 0.0024861520912202667, "60": 0.00388487964780808, "61": 0.09860768366797587, "62": 0.031028795022943857, "63": 0.01680668487358409 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 3525, "fallback_latency_ms": 29976, "latency_ms": 33529, "elapsed_ms": 152295, "confidence": 0.5373463316418788 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.1738013226701806, "CLICK": 0.5343930669399023, "SCROLL_DOWN": 0.09984753957940205, "WAIT": 0.09520919466170057, "BLOCKED": 0.09674887614881442 }, "target_probabilities": { "1": 0.09547103523085364, "2": 0.03847155543451359, "3": 0.0029749768267924126, "4": 0.0017923334974101004, "5": 0.0024349393985361755, "6": 0.003110131725528689, "7": 0.002859062351195431, "8": 0.0011343101840171083, "9": 0.002635982013113382, "10": 0.0008084458763219796, "11": 0.0009662713847842174, "12": 0.0012592212342193627, "13": 0.0016370108734964563, "14": 0.001324886484322104, "15": 0.0015880423313704387, "16": 0.002053585301421238, "17": 0.000881042705292755, "18": 0.0005637496567659538, "19": 0.0012599624036192492, "20": 0.001005685929784567, "21": 0.0007423163085104397, "22": 0.0006713474955399556, "23": 0.000636804588089939, "24": 0.0007244335703941777, "25": 0.000682319177218825, "26": 0.0009126720647547345, "27": 0.0007025491802975871, "28": 0.0003674549675332204, "29": 0.0007076466761674474, "30": 0.0008902011342186177, "31": 0.0033018429872372114, "32": 0.0012981339361767545, "33": 0.007865160036215737, "34": 0.5115440540177051, "35": 0.10038330993087714, "36": 0.01579498479451465, "37": 0.02230490398247603, "38": 0.004996151912881816, "39": 0.006933432072976463, "40": 0.0074795913810283025, "41": 0.0031236108627158803, "42": 0.003287358532652323, "43": 0.0019834606875599016, "44": 0.001711406654223314, "45": 0.004259467502169464, "46": 0.002666439962328576, "47": 0.003428719156484286, "48": 0.0019851887605948594, "49": 0.0017850922041809736, "50": 0.00500171284516042, "51": 0.0019518471280100937, "52": 0.004695229142138116, "53": 0.001994301315838412, "54": 0.0012679461915259221, "55": 0.0011413549614826986, "56": 0.002322289176960771, "57": 0.00487360029796004, "58": 0.003012454986625268, "59": 0.002769095741580151, "60": 0.005952693611567942, "61": 0.013629013858883585, "62": 0.0062168404526927856, "63": 0.009163972809900039, "64": 0.018251493355124212, "65": 0.005129093243433915, "66": 0.02259980649654085, "67": 0.012624969003492184 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 3807, "fallback_latency_ms": 47575, "latency_ms": 51413, "elapsed_ms": 208198, "confidence": 0.41799133367487784 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.12601676605460296, "CLICK": 0.6197114107558417, "SCROLL_DOWN": 0.08402742669431708, "WAIT": 0.09775907362810889, "BLOCKED": 0.07248532286712941 }, "target_probabilities": { "1": 0.3092625559066865, "2": 0.1139036246180966, "3": 0.1293404099488606, "4": 0.006755271744116888, "5": 0.008762884593987602, "6": 0.02367809602209752, "7": 0.014750739685672675, "8": 0.010029540397031165, "9": 0.013823003213139087, "10": 0.003527592038527669, "11": 0.008410039332114698, "12": 0.007583459323910069, "13": 0.009041435484282675, "14": 0.004832204024258178, "15": 0.0031487351205332103, "16": 0.0057053789422400695, "17": 0.0031506352804395077, "18": 0.0034248518467575872, "19": 0.006186946660573017, "20": 0.0049268299953850354, "21": 0.002983649920774405, "22": 0.00292273679886154, "23": 0.006199106451886781, "24": 0.0021200872665755647, "25": 0.002848093330633711, "26": 0.004111842056217808, "27": 0.006336625844853799, "28": 0.00243655362131817, "29": 0.0029970597924792093, "30": 0.005366423447232175, "31": 0.006954412134506873, "32": 0.013832767143080616, "33": 0.02720545753520685, "34": 0.04353366139913411, "35": 0.00549425735681498, "36": 0.003443037228953602, "37": 0.01870272844770661, "38": 0.002397840184019158, "39": 0.0021432854961824397, "40": 0.009028676101391247, "41": 0.003260085906284383, "42": 0.005500754285121281, "43": 0.0025053101418355006, "44": 0.002837619887473326, "45": 0.0024677256748537467, "46": 0.002478801396248093, "47": 0.0030442934985842303, "48": 0.0016211167884515997, "49": 0.0026088014437098566, "50": 0.006377196739403867, "51": 0.004818306514010054, "52": 0.005300079587460296, "53": 0.003910778530790069, "54": 0.00166155205164973, "55": 0.0015589472146223752, "56": 0.003233916839670168, "57": 0.0061833684846513675, "58": 0.004495349550608095, "59": 0.001714738337506663, "60": 0.005075708545871969, "61": 0.011651957432924794, "62": 0.010415217994955863, "63": 0.02225734622312084, "64": 0.02371849119365195 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 3755, "fallback_latency_ms": 42036, "latency_ms": 45830, "elapsed_ms": 258572, "confidence": 0.524639263444802 }, { "operation": "CLICK", "operation_probabilities": { "TYPE_TEXT": 0.10416608190135421, "CLICK": 0.5337933272277359, "SCROLL_DOWN": 0.10937863113508982, "WAIT": 0.1776092537195145, "BLOCKED": 0.07505270601630559 }, "target_probabilities": { "1": 0.021216169593630763, "2": 0.01760485831800737, "3": 0.0016671250350835053, "4": 0.00419820850668998, "5": 0.001225001156924609, "6": 0.0011778036790397988, "7": 0.0032161428380965825, "8": 0.0010335925909395515, "9": 0.001145394527304556, "10": 0.0015623866706652328, "11": 0.0007410419830429642, "12": 0.0010352802454046321, "13": 0.0010715317563644898, "14": 0.0009666641030468616, "15": 0.0006296319628578267, "16": 0.0006026943936880989, "17": 0.0016564348704730697, "18": 0.000380397689101599, "19": 0.0005299435160961098, "20": 0.0008081104675640552, "21": 0.00033411858341790486, "22": 0.00043687448025148535, "23": 0.00044127691587864283, "24": 0.0006683370497246211, "25": 0.00034339467184076413, "26": 0.0004250342658875204, "27": 0.0007648328477871297, "28": 0.0004931316969864307, "29": 0.00032252785743643866, "30": 0.000277793193018145, "31": 0.0009543799995063879, "32": 0.0014294397441775525, "33": 0.0005197021879808047, "34": 0.0015113924519436427, "35": 0.022132055926310543, "36": 0.0007840566027718887, "37": 0.0003464106696665605, "38": 0.0013903561412772483, "39": 0.000468919461410509, "40": 0.00040937071624178647, "41": 0.006504494479753687, "42": 0.0004256855477600374, "43": 0.00036306914823569015, "44": 0.00018362881647967448, "45": 0.00036483153411686795, "46": 0.0005568008550046853, "47": 0.00029998264430000713, "48": 0.00020128885335195387, "49": 0.0002251601915565821, "50": 0.00031248409072043477, "51": 0.0010647675701650546, "52": 0.0005404964573666816, "53": 0.0005279692188975893, "54": 0.00020081887464850343, "55": 0.0003380692479072648, "56": 0.00028746986413873935, "57": 0.0003502111116174133, "58": 0.0005964871966340508, "59": 0.0007584679193246562, "60": 0.0004826687108294951, "61": 0.0005088840623904761, "62": 0.001110223811792064, "63": 0.0006396025096155624, "64": 0.0022657631491014734, "65": 0.8839688547667538 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 3926, "fallback_latency_ms": 43048, "latency_ms": 47005, "elapsed_ms": 305825, "confidence": 0.4172416590346698 }, { "operation": "CLICK", "operation_probabilities": { "CLICK": 0.07188655220052867, "TYPE_TEXT": 0.03177253163456043, "SCROLL_DOWN": 0.06363562641472553, "WAIT": 0.3036773589855201, "DONE": 0.5126923756474664, "BLOCKED": 0.01633555511719899 }, "target_probabilities": { "1": 0.0019544391063725233, "2": 0.003115840135952819, "3": 0.0026574385686194114, "4": 0.015980406246838462, "5": 0.0003641417318487303, "6": 0.00035168850171548845, "7": 0.0014722208643252932, "8": 0.0012232167491839712, "9": 0.0006137740332789434, "10": 0.04490231992856982, "11": 0.028862514680214918, "12": 0.2589151587501319, "13": 0.028614876280452114, "14": 0.0054841615242767, "15": 0.17857483733713478, "16": 0.1330941157313596, "17": 0.25688009239309845, "18": 0.006646550754855628, "19": 0.0025620654786837646, "20": 0.012896620439527235, "21": 0.005493306623589713, "22": 0.002800693738390679, "23": 0.006539520401579051 }, "decision_source": "local_fallback", "probability_source": "jevstyle", "primary_latency_ms": 1608, "fallback_latency_ms": 13009, "latency_ms": 14634, "elapsed_ms": 321062, "confidence": 0.41523085077695965 } ], "decision_calls": 21, "text_calls": 1 } ], "batch_status": "completed", "planned_scenarios": [ "flights" ], "review_every_step": true, "configuration": { "fallback_enabled": true, "fallback_threshold": 1.0, "fallback_format": "action_enum", "max_actions": 40, "max_seconds": 900.0, "stop_when_verified": true, "http_timeout_seconds": 120.0, "capture_enabled": true }, "source_hashes": { "scripts/run_scenarios.py": "10b481f0373045882b2257175be9a02856da2eede9f85b282694ff75c21cc9ab", "jev_ultrafast/__init__.py": "5d2e83009ae3802e2edecf120f19b0380a27247e21a7b641b2a430c98dcbd208", "jev_ultrafast/agent.py": "f037b1619ba1865e59f5cc9ff288988f994186b2f51dbf457dfdf8f53bae4fda", "jev_ultrafast/browser.py": "ee08dafa93d731bd292aa0263a578a29c8001cf22eef3c59fe44a159649155ee", "jev_ultrafast/demo.py": "b69705afe7e61d6183cbba3243d2bac5165d8f56253becb6a9a59b01e3c4f5b9", "jev_ultrafast/fallback.py": "fd8303fbcd6eabe752c579df1d9a08cb712726ccc07451bf87417b894bcdecdb", "jev_ultrafast/model.py": "84ba9499069071b5404eed83fdc5cbfbdc6e1629d75d1ef3b79191654d6236df", "jev_ultrafast/progress.py": "ec4a90995b2dd054e0d56e6e2a6720f00eff446a63047a330d8b821a441dfb76", "jev_ultrafast/questions.py": "fc11e334d9b31977bddb7d9319b9fd7bd16e05db7f9242c45c277e49c264617b", "jev_ultrafast/scenarios.py": "25a6569229cc2fc33458e6eddcd00bfa53280b643dd80d6db8fee6f9a94c37e8", "jev_ultrafast/snapshot.js": "eb8f6607dabaa2243a125d49a326ab7bb607a095677794e2c5e50f12e5f1caa7" }, "measurement": { "elapsed_ms": "Agent decision loop; excludes browser setup and independent final verification", "wall_ms": "Browser setup, decision loop, independent verification and cleanup", "scope": "Live attempts on named tasks; synthetic fixtures are not a general web benchmark", "replay": "Executed actions and separate decision scores; no recorded video or simulated actions" }, "summary": { "passed": 1, "failed": 0, "blocked": 0 } }