zizi-al/games-development-ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
games-development-ai/contracts/prompts/eval/playtest.actor/runs/run-20260725.jsonl
lili 87777975c7 feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门) 
actor/judge prompt eval 闭合: actor 3.0.5 正文强化+baseline(7轮); judge 3.0.14 正文强化+anyTerms同义词补全+baseline(judge-a 13轮/judge-b 33轮); registry/checker 版本对齐+顺序锚点 fail-closed 双保险
W-GOLD-LIVE live_prompt: play-loop 契约开口(request/3+provenance/3+ReferenceAssetRecord/1+Registry/1+迁移清单15条); cheap_verify 切v3+消费对账六闸(只消费active)+生成prompt注入接线(0 active不注入); Node runner playtest-v3.cdp.cjs 升/3+绊线恢复; 真模型回归验向后兼容
full_gate+三批基线: full_gate.py 集成runner串六子门+降级+22测; baseline_gates.py fresh25阈值+historical11预期表(2 needs_human交创始人定标)+shadow20框架+38测
注: registry cheap-system 登记 1.8.0→1.8.1 同步此前在途 cheap-system.md frontmatter 升版(修 pre-commit 版本漂移); cheap_verify/cheap_studio/validate/test_acceptance_v3/test_cheap_service_driver 为在途M含本会话叠加+此前W-AXIS在途(同一线无法hunk分离); 3红测试根因与raw审计未入本提交
2026-07-25 18:47:47 -07:00

8 lines
48 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{"ts": "2026-07-25T21:32:14.041781+00:00", "runId": "20260725T212959.054195Z-p10911-n1785014999054462000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 5, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 5, "cohortSchemaOk": 5, "perKeyCorrectCounts": {"actor:tap:shop-open": 1, "actor:wait:simon-highlight": 1, "actor:tap:runner-restart": 1, "actor:key:2048-merge": 1, "actor:tap:match3-select": 1}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/run-manifest.json", "sha256": "9ebf80e15604df8fd4e03ce9d812d3534e33b23cfab9523e96b7cff7b5643ed2", "runAuditHash": "ff4fa72a87338e5212e7a678a20f74ad446562ff7eb9e3ae562bcd68865a25e8", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.223279, "promptTokens": 15342, "completionTokens": 21653, "totalLatencyMs": 131453, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 1 轮；三轮 cohort 正确 5/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/response-0002.txt", "size": 59, "sha256": "feff78279d02f3a605423b239eca786b2f921ce84ccc452fab674801acc806b1", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/response-0004.txt", "size": 68, "sha256": "c3b03f423032e56dc17348c6efe493808914fa29fd86bd6dffc5111790f11ed8", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T212959.054195Z-p10911-n1785014999054462000/response-0005.txt", "size": 215, "sha256": "9cf918b92ed45c661957d121cfb082e1d5b3c3163e608db4c27ae4e4d88673bb", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:33:55.281309+00:00", "runId": "20260725T213231.377284Z-p46858-n1785015151377523000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.8, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 2, "previousRunIds": ["20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": false, "cohortRuns": 2, "cohortCorrect": 9, "cohortSchemaOk": 10, "perKeyCorrectCounts": {"actor:tap:shop-open": 2, "actor:wait:simon-highlight": 2, "actor:tap:runner-restart": 2, "actor:key:2048-merge": 2, "actor:tap:match3-select": 1}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": false}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/run-manifest.json", "sha256": "c9046240975ccba4a3f4811088cf8c3d9dbea0903f6d673f363d8a72abb4efcd", "runAuditHash": "1d2190648328bb333405f49b507579b4e04059df8d6c27ad840d591b4d359939", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.108444, "promptTokens": 15346, "completionTokens": 8543, "totalLatencyMs": 80415, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 2 轮；三轮 cohort 正确 9/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/response-0002.txt", "size": 59, "sha256": "feff78279d02f3a605423b239eca786b2f921ce84ccc452fab674801acc806b1", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/response-0004.txt", "size": 67, "sha256": "37f1161c4e31dbf59573e6e409e3c8b684924dfbba0ed1216c3844ea7cf46aec", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": false, "verdict": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T213231.377284Z-p46858-n1785015151377523000/response-0005.txt", "size": 203, "sha256": "98afd832cd0f57c15169dfef0739db04b028dcf32fe7c93bce35a99aad7adc00", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:36:31.216057+00:00", "runId": "20260725T213412.951270Z-p77946-n1785015252951508000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.8, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 3, "previousRunIds": ["20260725T213231.377284Z-p46858-n1785015151377523000", "20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": false, "cohortRuns": 3, "cohortCorrect": 13, "cohortSchemaOk": 15, "perKeyCorrectCounts": {"actor:tap:shop-open": 3, "actor:wait:simon-highlight": 3, "actor:tap:runner-restart": 3, "actor:key:2048-merge": 3, "actor:tap:match3-select": 1}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": false}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/run-manifest.json", "sha256": "31db7e9718ba53058e84bb94029576d62c498b049c1007d23e6c2e057ab3e656", "runAuditHash": "84b27f54157f96f7cb0ed41406a6b5a2898ac530e86038eb2e6ee4f089033253", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.174311, "promptTokens": 15346, "completionTokens": 16062, "totalLatencyMs": 134717, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 3 轮；三轮 cohort 正确 13/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/response-0002.txt", "size": 59, "sha256": "703467aa67f7f462f537c430ede4a4aea8de199d020412a7f2bce3423000976b", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/response-0004.txt", "size": 68, "sha256": "c3b03f423032e56dc17348c6efe493808914fa29fd86bd6dffc5111790f11ed8", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": false, "verdict": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T213412.951270Z-p77946-n1785015252951508000/response-0005.txt", "size": 203, "sha256": "35759ae2a487a1fa09ad0cfcf7d75c89ff497ae98a5ac24f43925888212c3632", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:38:00.263317+00:00", "runId": "20260725T213653.249754Z-p3512-n1785015413250012000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 5, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 4, "previousRunIds": ["20260725T213412.951270Z-p77946-n1785015252951508000", "20260725T213231.377284Z-p46858-n1785015151377523000", "20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": false, "cohortRuns": 3, "cohortCorrect": 13, "cohortSchemaOk": 15, "perKeyCorrectCounts": {"actor:tap:shop-open": 3, "actor:wait:simon-highlight": 3, "actor:tap:runner-restart": 3, "actor:key:2048-merge": 3, "actor:tap:match3-select": 1}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/run-manifest.json", "sha256": "b2b9037a5f66e1312ea6dee664f3475fe9fe129369185ad95decfb2a108d72f7", "runAuditHash": "64cc136cb2f71e758fcdaee36d710c0bf2fb4f2c93b4878422ac81831053e50b", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.114673, "promptTokens": 15346, "completionTokens": 9254, "totalLatencyMs": 63473, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 4 轮；三轮 cohort 正确 13/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/response-0002.txt", "size": 59, "sha256": "feff78279d02f3a605423b239eca786b2f921ce84ccc452fab674801acc806b1", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/response-0004.txt", "size": 67, "sha256": "37f1161c4e31dbf59573e6e409e3c8b684924dfbba0ed1216c3844ea7cf46aec", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T213653.249754Z-p3512-n1785015413250012000/response-0005.txt", "size": 203, "sha256": "f77a4987c6a29cd7506ce8849f8b0da1a33c2ea6e400065ec0c93a93f548e3c8", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:40:32.790864+00:00", "runId": "20260725T213835.239154Z-p35162-n1785015515239394000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 5, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": true, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 5, "previousRunIds": ["20260725T213653.249754Z-p3512-n1785015413250012000", "20260725T213412.951270Z-p77946-n1785015252951508000", "20260725T213231.377284Z-p46858-n1785015151377523000", "20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": true, "cohortRuns": 3, "cohortCorrect": 14, "cohortSchemaOk": 15, "perKeyCorrectCounts": {"actor:tap:shop-open": 3, "actor:wait:simon-highlight": 3, "actor:tap:runner-restart": 3, "actor:key:2048-merge": 3, "actor:tap:match3-select": 2}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/run-manifest.json", "sha256": "25689fac0e71fb0bbdc040212ff7b8283924495775238742c993e2813db9d8f9", "runAuditHash": "e8e50e7c2f49c49a6eb62ec9f38566a691df452c37abfb4ee32c69f33cd81681", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.204559, "promptTokens": 15346, "completionTokens": 19515, "totalLatencyMs": 114026, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 5 轮；三轮 cohort 正确 14/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/response-0002.txt", "size": 59, "sha256": "feff78279d02f3a605423b239eca786b2f921ce84ccc452fab674801acc806b1", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/response-0004.txt", "size": 68, "sha256": "c3b03f423032e56dc17348c6efe493808914fa29fd86bd6dffc5111790f11ed8", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T213835.239154Z-p35162-n1785015515239394000/response-0005.txt", "size": 203, "sha256": "41b01a5a6fc0d413ae86596302bb5405c795024297870b5e000d84b8efe7e010", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:42:46.084395+00:00", "runId": "20260725T214050.618414Z-p71076-n1785015650618663000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.8, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": true, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 6, "previousRunIds": ["20260725T213835.239154Z-p35162-n1785015515239394000", "20260725T213653.249754Z-p3512-n1785015413250012000", "20260725T213412.951270Z-p77946-n1785015252951508000", "20260725T213231.377284Z-p46858-n1785015151377523000", "20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": true, "cohortRuns": 3, "cohortCorrect": 14, "cohortSchemaOk": 15, "perKeyCorrectCounts": {"actor:tap:shop-open": 3, "actor:wait:simon-highlight": 3, "actor:tap:runner-restart": 3, "actor:key:2048-merge": 3, "actor:tap:match3-select": 2}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": false}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "baseline_updated_rerun_required", "allGreen": false, "baselineUpdateRequested": true, "baselineUpdateEligible": true, "baselineUpdated": true, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/run-manifest.json", "sha256": "eb17b21dc75a6a7dcbf7f4f5af0374b854f091e8c70ba5f1f2924e2ef0db22d0", "runAuditHash": "ed19f073baa675ac2b4acfa3c9c028a3d0403b21bb5d43c099af23fd8d5687ef", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.143287, "promptTokens": 15348, "completionTokens": 12520, "totalLatencyMs": 111955, "nError": 0, "gate3_note": "无基线，首次跑（advisory，未拦）", "gate4_note": "无基线，首次跑（advisory，未拦）", "gate5_note": "同请求合格 6 轮；三轮 cohort 正确 14/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/response-0002.txt", "size": 59, "sha256": "feff78279d02f3a605423b239eca786b2f921ce84ccc452fab674801acc806b1", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/response-0004.txt", "size": 67, "sha256": "37f1161c4e31dbf59573e6e409e3c8b684924dfbba0ed1216c3844ea7cf46aec", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": false, "verdict": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T214050.618414Z-p71076-n1785015650618663000/response-0005.txt", "size": 203, "sha256": "18254d9635491c2cac2274c1f08c0a3e3f5475f009654cdcbd2d9ec2c20ceeec", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
{"ts": "2026-07-25T21:45:51.421100+00:00", "runId": "20260725T214411.582140Z-p8189-n1785015851582364000", "promptId": "playtest.actor", "version": "3.0.5", "model": "MiniMax-M3", "promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "nSamples": 5, "nJudged": 5, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.8, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": true, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86", "stability": {"qualified": true, "consecutiveRuns": 7, "previousRunIds": ["20260725T214050.618414Z-p71076-n1785015650618663000", "20260725T213835.239154Z-p35162-n1785015515239394000", "20260725T213653.249754Z-p3512-n1785015413250012000", "20260725T213412.951270Z-p77946-n1785015252951508000", "20260725T213231.377284Z-p46858-n1785015151377523000", "20260725T212959.054195Z-p10911-n1785014999054462000"], "cohortReady": false, "cohortRuns": 3, "cohortCorrect": 13, "cohortSchemaOk": 15, "perKeyCorrectCounts": {"actor:tap:shop-open": 3, "actor:wait:simon-highlight": 3, "actor:tap:runner-restart": 3, "actor:key:2048-merge": 3, "actor:tap:match3-select": 1}, "identity": {"promptBodySha256": "f7dc86291acc972ff5c435cf237466ac9b5f68afdad0e5370fdeed70dee0e611", "fixtureSnapshot": {"inputsSha256": "a7b1a98b218fa85389be87bad9c3257ff53fab3d8b9ff8e6a4097d71522a45ea", "labelsSha256": "b64b11d243664524a379451821a4376b4f47205d59c4b9c6af45a1237dd7433f", "imageFixturesSha256": "9e4f9925ed262f893806d6513f271b71d8602c1d7961124f2122d56910979efd", "overallSha256": "5a21968b68e1952717284cdf282950d854ea45064b32f8b5f0c73dcae0b0e624"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "ae9186ccd7cbf1a80a189a42e72cf12cd482a86e13e2686ea3c598758262754f", "thinkingBudgetTokens": 4000, "maxTokens": 20000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "905d06814ba986760e4b269319a8a1dcd1b1d4433eeacfda0e5f0245a1049f86"}, "requestBodySha256": {"actor:tap:shop-open": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687", "actor:wait:simon-highlight": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c", "actor:tap:runner-restart": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717", "actor:key:2048-merge": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb", "actor:tap:match3-select": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}, "signatures": {"actor:tap:shop-open": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:wait:simon-highlight": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "actor:tap:runner-restart": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "actor:key:2048-merge": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "actor:tap:match3-select": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}}, "perKeyCorrect": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": false}, "perKeySchemaOk": {"actor:tap:shop-open": true, "actor:wait:simon-highlight": true, "actor:tap:runner-restart": true, "actor:key:2048-merge": true, "actor:tap:match3-select": true}, "requiredRuns": 3}, "status": "passed", "allGreen": true, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/run-manifest.json", "sha256": "4a3448015e0576649d0fc815e33f31218b1d633882124deabb7439290d0c3399", "runAuditHash": "922e86c09e8047fef9284ee1589aaa9fedbad67dbc3d8ad5dfc7506586ea541c", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.145526, "promptTokens": 15346, "completionTokens": 12776, "totalLatencyMs": 96315, "nError": 0, "gate3_note": "Actor 金标单轮标准保持达标", "gate4_note": "成本Δ=+1.6%(限+50%) 延迟Δ=-14.0%(限+100%)", "gate5_note": "同请求合格 7 轮；三轮 cohort 正确 13/15", "perKey": {"actor:tap:shop-open": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 3226715500, "rawAudit": {"path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/response-0001.txt", "size": 154, "sha256": "ca5475390fc3dccf5515a285284251cdba9d1892f6d841edad1e91675ee121b7", "requestBodySha256": "0a135b2fa2ebcc65effff52c6a94f103f0eadcf5e901987a657516f0f2e35687"}}, "actor:wait:simon-highlight": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "wait", "error": null}, "schema_bad": [], "error": null, "seed": 2674839459, "rawAudit": {"path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/response-0002.txt", "size": 59, "sha256": "3f533063331ab8f724ff78db9ee53bacd7fdeb0dcfaf030c1c9e5b5df8c132d8", "requestBodySha256": "32df34f67d9b0149a72e617d2a0845df489a93130b3c40ec2d5cb62917b9a17c"}}, "actor:tap:runner-restart": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 923624043, "rawAudit": {"path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/response-0003.txt", "size": 154, "sha256": "ab9699d4e555176fa7a27a5241ead71bd024e9ca5b5755bab730382fd84de528", "requestBodySha256": "9ac035737c839662d99b43ab8681a1dca74f39e146eb307916cc85348a34c717"}}, "actor:key:2048-merge": {"schema_ok": true, "correct": true, "verdict": {"schemaOk": true, "correct": true, "actionType": "key", "error": null}, "schema_bad": [], "error": null, "seed": 3641176648, "rawAudit": {"path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/response-0004.txt", "size": 67, "sha256": "37f1161c4e31dbf59573e6e409e3c8b684924dfbba0ed1216c3844ea7cf46aec", "requestBodySha256": "ca57077aceb428da48a399f6b6badd2361efcbd59509e984a6e08389c2e3cedb"}}, "actor:tap:match3-select": {"schema_ok": true, "correct": false, "verdict": {"schemaOk": true, "correct": false, "actionType": "tap", "error": null}, "schema_bad": [], "error": null, "seed": 214026103, "rawAudit": {"path": "raw/20260725T214411.582140Z-p8189-n1785015851582364000/response-0005.txt", "size": 203, "sha256": "3e915076049fb2bc13b1a93bca5a749db1b0e1cfdaa7f1465c215e65dea7ab83", "requestBodySha256": "3618e2fb33df1f39d7ebcba10986fffc5cee9bade1a9164e43dd9bea89df503b"}}}}
Reference in New Issue View Git Blame Copy Permalink