@hona/openeval 0.2.2 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/JUDGING.md +134 -23
- package/README.md +67 -9
- package/package.json +3 -2
- package/src/app/cost-plan.ts +20 -16
- package/src/app/eval-state.ts +2 -1
- package/src/app/grade-recording.ts +72 -0
- package/src/app/input-fingerprints.ts +22 -8
- package/src/app/judge-evidence.ts +26 -11
- package/src/app/judge-run.ts +36 -19
- package/src/app/load-benchmark.ts +46 -15
- package/src/app/read-results.ts +35 -2
- package/src/app/read-run.ts +23 -2
- package/src/app/rejudge.ts +2 -1
- package/src/app/run-benchmark.ts +4 -0
- package/src/app/run-eval-pipeline.ts +2 -1
- package/src/app/run-eval.ts +13 -0
- package/src/app/scores.ts +76 -34
- package/src/app/serve-results.ts +2 -0
- package/src/evidence.ts +4 -1
- package/src/index.ts +15 -3
- package/src/infra/evidence/index.ts +39 -2
- package/src/infra/evidence/tool-calls.ts +5 -2
- package/src/infra/judging/agent.ts +3 -2
- package/src/infra/judging/code-result.ts +102 -0
- package/src/infra/judging/code-source.ts +96 -0
- package/src/infra/judging/code-worker.ts +26 -0
- package/src/infra/judging/code.ts +97 -0
- package/src/infra/judging/contract.ts +82 -64
- package/src/infra/judging/evidence-tool.ts +3 -1
- package/src/infra/judging/index.ts +14 -0
- package/src/infra/judging/judge-agent.md +24 -18
- package/src/infra/judging/observer.ts +8 -7
- package/src/infra/judging/submission.ts +8 -8
- package/src/infra/judging/tools.ts +9 -9
- package/src/infra/opencode/host.ts +1 -1
- package/src/infra/opencode/read-recording.ts +6 -1
- package/src/infra/opencode/version.ts +1 -0
- package/src/infra/recording/index.ts +244 -0
- package/src/infra/recording/metrics.ts +193 -0
- package/src/infra/sqlite/index.ts +29 -19
- package/src/judge-context.ts +141 -0
- package/src/judgment.ts +26 -17
- package/src/types.ts +36 -17
- package/src/view.ts +40 -14
- package/viewer/assets/{abnfDiagram-VCTEODGH-B1kcYgQG.js → abnfDiagram-VCTEODGH-rgmalTBh.js} +1 -1
- package/viewer/assets/{angular-html-DrYCUiZv.js → angular-html-CcaajvLj.js} +1 -1
- package/viewer/assets/{angular-ts-BgjwQn-Z.js → angular-ts-COx6AtG2.js} +1 -1
- package/viewer/assets/{apl-DlHqe8o4.js → apl-lBEnC_vz.js} +1 -1
- package/viewer/assets/{arc-C4nf7ZoY.js → arc-BQ0cQOwK.js} +1 -1
- package/viewer/assets/architecture-7GRP2DOG-DcUKSnYa.js +1 -0
- package/viewer/assets/{architectureDiagram-5GKGNRK7-BIWoe0fO.js → architectureDiagram-5GKGNRK7-_XIJP-LV.js} +1 -1
- package/viewer/assets/{astro-BrlHnIh9.js → astro-Ca8FrXna.js} +1 -1
- package/viewer/assets/{blade-DOcerOiW.js → blade-B07ZVjUX.js} +1 -1
- package/viewer/assets/{blockDiagram-I7D4REHJ-C3x13a9m.js → blockDiagram-I7D4REHJ-BdcDRYB-.js} +1 -1
- package/viewer/assets/{c-BMbThxEo.js → c-4MsqXzJK.js} +1 -1
- package/viewer/assets/{c4Diagram-7LVT6UL2-BeWktchx.js → c4Diagram-7LVT6UL2-E3nvwqBd.js} +1 -1
- package/viewer/assets/channel-CViXUg9J.js +1 -0
- package/viewer/assets/{chapel-k2cjkSmc.js → chapel-BlwR_8zu.js} +1 -1
- package/viewer/assets/{chunk-4HAMMTFA-o6YtJsqE.js → chunk-4HAMMTFA-DN_vtpqx.js} +1 -1
- package/viewer/assets/{chunk-75Z2AOVW-KohQa9Nw.js → chunk-75Z2AOVW-DWMGmicp.js} +1 -1
- package/viewer/assets/{chunk-DU6HZSFF-C88wxc6m.js → chunk-DU6HZSFF-D2RGHn75.js} +1 -1
- package/viewer/assets/{chunk-F27PBJKO-mO4AP2as.js → chunk-F27PBJKO-wfQZ5Ilx.js} +1 -1
- package/viewer/assets/{chunk-GMAD6QVW-DzQX2Cld.js → chunk-GMAD6QVW-DrlfUg7k.js} +1 -1
- package/viewer/assets/{chunk-GVQU2GXP-CS78RfJD.js → chunk-GVQU2GXP-BHoRLKIU.js} +1 -1
- package/viewer/assets/{chunk-IMKFNOWR-DxS42GUo.js → chunk-IMKFNOWR-mxLyQhYU.js} +1 -1
- package/viewer/assets/{chunk-L3NEJ4N5-DGo-uYLy.js → chunk-L3NEJ4N5-IpGl-pvp.js} +1 -1
- package/viewer/assets/{chunk-OSK3NFVY-BOcXQG16.js → chunk-OSK3NFVY-t0yN50X6.js} +1 -1
- package/viewer/assets/{chunk-P2QGCYS3-B7GnZdIQ.js → chunk-P2QGCYS3-BPBYYOcK.js} +1 -1
- package/viewer/assets/{chunk-POPQ4Y6H-DgBcYHog.js → chunk-POPQ4Y6H-DIOcv86B.js} +1 -1
- package/viewer/assets/{chunk-PWAF6VOD-DpEq6qHA.js → chunk-PWAF6VOD-CqVB-mzq.js} +1 -1
- package/viewer/assets/{chunk-SHT3W25Y-CrOGxKM2.js → chunk-SHT3W25Y-DwOEgFIr.js} +1 -1
- package/viewer/assets/{chunk-SVP7TREG-4HY7Fljj.js → chunk-SVP7TREG-Dfg1jHc3.js} +1 -1
- package/viewer/assets/{chunk-TICWLB2K-B1Rl31EC.js → chunk-TICWLB2K-DE6tQNRu.js} +1 -1
- package/viewer/assets/{chunk-XXDRQBXY-CK8giEW-.js → chunk-XXDRQBXY-Bu8dW06M.js} +1 -1
- package/viewer/assets/classDiagram-ZZMXUADV-O1Zm0_p8.js +1 -0
- package/viewer/assets/classDiagram-v2-VYDZK3BY-O1Zm0_p8.js +1 -0
- package/viewer/assets/{cobol-CupUwvw9.js → cobol-BS_DrT-b.js} +1 -1
- package/viewer/assets/{coffee-C17pkozF.js → coffee-Clk97ecB.js} +1 -1
- package/viewer/assets/{cose-bilkent-JH36ORCC-V1OmrmCv.js → cose-bilkent-JH36ORCC-B3xA8n2e.js} +1 -1
- package/viewer/assets/{cpp-BJwVQVXg.js → cpp-aunMdKLY.js} +1 -1
- package/viewer/assets/{crystal-BF-oCN-L.js → crystal-B1oihgG5.js} +1 -1
- package/viewer/assets/{css-BMgkVI3c.js → css-ClOubSVo.js} +1 -1
- package/viewer/assets/{cynefin-OW5HDTMX-BEjY_gsc.js → cynefin-OW5HDTMX-DdEeq9jN.js} +1 -1
- package/viewer/assets/{cynefinDiagram-5FMLGOSQ-bfSYgr6z.js → cynefinDiagram-5FMLGOSQ-BwHCV_5V.js} +1 -1
- package/viewer/assets/{dagre-GXQ25YYZ-VtwTgGfa.js → dagre-GXQ25YYZ-BkuWRmq-.js} +1 -1
- package/viewer/assets/{diagram-S7CK7UJ4-CHaAAyW7.js → diagram-S7CK7UJ4-C5WGyCny.js} +1 -1
- package/viewer/assets/{diagram-UQ7AKVKN-CjL65-As.js → diagram-UQ7AKVKN-mdununKH.js} +1 -1
- package/viewer/assets/{diagram-VSXAHHWV-Cnxrk1TJ.js → diagram-VSXAHHWV-CpuvU9Ij.js} +1 -1
- package/viewer/assets/{diagram-VX7I27RA-D78jPXr7.js → diagram-VX7I27RA-CcLmTPwv.js} +1 -1
- package/viewer/assets/{diagram-Z3DM3KII-DKjnOaF2.js → diagram-Z3DM3KII-DWCnKyKY.js} +1 -1
- package/viewer/assets/{dist-BTYPW0dz.js → dist-1DE7d697.js} +1 -1
- package/viewer/assets/{ebnfDiagram-PWID7BFC-7XiXh5Lx.js → ebnfDiagram-PWID7BFC-9M_-_M-B.js} +1 -1
- package/viewer/assets/{edge-B34N_HjN.js → edge-NsPpWeFX.js} +1 -1
- package/viewer/assets/{elixir-CQzWMyKD.js → elixir-CXZ4zQTn.js} +1 -1
- package/viewer/assets/{elm-BNJiG-wg.js → elm-DVXugwZs.js} +1 -1
- package/viewer/assets/{erDiagram-RLTQ6QDP-YPFEgZxU.js → erDiagram-RLTQ6QDP-B2j6iCkZ.js} +1 -1
- package/viewer/assets/{erb-D5Rm3UNa.js → erb-h8ybsnSQ.js} +1 -1
- package/viewer/assets/eventmodeling-NTZA5JFV-CpMf6avu.js +1 -0
- package/viewer/assets/flowDiagram-HODETNUW-DIKEcF1k.js +1 -0
- package/viewer/assets/{ganttDiagram-EL5Y4UJY-ergSGtTP.js → ganttDiagram-EL5Y4UJY-CR2QLJ-I.js} +1 -1
- package/viewer/assets/{git-rebase-BpIMZIRG.js → git-rebase-CT9f4kn8.js} +1 -1
- package/viewer/assets/{gitGraph-4MIJSDKK-CZt4REVj.js → gitGraph-4MIJSDKK-DGw-0dqe.js} +1 -1
- package/viewer/assets/{gitGraphDiagram-WWUBYQGX-h9QMzC2r.js → gitGraphDiagram-WWUBYQGX-BW112jVV.js} +1 -1
- package/viewer/assets/{glimmer-js-SeSwns5_.js → glimmer-js-B17pi1gL.js} +1 -1
- package/viewer/assets/{glimmer-ts-BExI5tTz.js → glimmer-ts-CNmwRbOn.js} +1 -1
- package/viewer/assets/{glsl-CXikKw2b.js → glsl-By4kbzYa.js} +1 -1
- package/viewer/assets/{graphql-6GpQIInt.js → graphql-BrDJs0bG.js} +1 -1
- package/viewer/assets/{hack-i7rizvpB.js → hack-NosEIqRi.js} +1 -1
- package/viewer/assets/{haml-C68gmkTf.js → haml-B-GQD8Zj.js} +1 -1
- package/viewer/assets/{handlebars-BBn_c0Xt.js → handlebars-1vSTccT5.js} +1 -1
- package/viewer/assets/{html-BObmAZQA.js → html-BBEodwWE.js} +1 -1
- package/viewer/assets/{html-derivative-BjMuR1LM.js → html-derivative-ClDEAvlc.js} +1 -1
- package/viewer/assets/{http-BJBk8gt0.js → http-I0uH89QQ.js} +1 -1
- package/viewer/assets/{hurl-D7obCYfg.js → hurl-JU97iWqA.js} +1 -1
- package/viewer/assets/{index-FMtYXcX7.js → index-CXBRQlCH.js} +5 -5
- package/viewer/assets/{index-Wz0qQyIk.css → index-D6HZB4Yz.css} +1 -1
- package/viewer/assets/{info-A6RAGUB7-CrzitQIU.js → info-A6RAGUB7-aRrZ0_i2.js} +1 -1
- package/viewer/assets/{infoDiagram-27XIBGKW-D2CgRDxu.js → infoDiagram-27XIBGKW-BnD3mUdL.js} +1 -1
- package/viewer/assets/{ishikawaDiagram-5VMMS53U-BhnQMHOo.js → ishikawaDiagram-5VMMS53U-u-wcafFg.js} +1 -1
- package/viewer/assets/{java-5VJU_EW8.js → java-BxAxXJLN.js} +1 -1
- package/viewer/assets/{javascript-r8UgndxQ.js → javascript-DNepMMwm.js} +1 -1
- package/viewer/assets/{jinja-BY2ibHG5.js → jinja-CfKdKg9T.js} +1 -1
- package/viewer/assets/{jison-C_7YxymZ.js → jison-C62ElGA9.js} +1 -1
- package/viewer/assets/{journeyDiagram-3NMN7TZE-DSBzKQEa.js → journeyDiagram-3NMN7TZE-E6uhr_fk.js} +1 -1
- package/viewer/assets/{json-8e1WlJYD.js → json-DSQqeQzH.js} +1 -1
- package/viewer/assets/{jsx-BYp5GD4Y.js → jsx-CpZi9Ceb.js} +1 -1
- package/viewer/assets/{julia-Bkob1uVX.js → julia-CypyJgFE.js} +1 -1
- package/viewer/assets/{just-CUnSjty-.js → just-_p8XAy70.js} +1 -1
- package/viewer/assets/{kanban-definition-UXKFOSKX-CotbrQue.js → kanban-definition-UXKFOSKX-Blo6hDj7.js} +1 -1
- package/viewer/assets/{latex-UdE3ivqk.js → latex-Blby6_jP.js} +1 -1
- package/viewer/assets/{line-DDh6a6hz.js → line-CQc5Trjj.js} +1 -1
- package/viewer/assets/{linear-BxMsCbKb.js → linear-BjWjnaEC.js} +1 -1
- package/viewer/assets/{liquid-WL4MvEIT.js → liquid-x3m9Bx2x.js} +1 -1
- package/viewer/assets/{lua-CtOubZta.js → lua-Da9XAgwV.js} +1 -1
- package/viewer/assets/{marko-C0GSQJi3.js → marko-Gu1d_h3t.js} +1 -1
- package/viewer/assets/{mdc-DUivddFc.js → mdc-CM0pUbEe.js} +1 -1
- package/viewer/assets/{mermaid-parser.core-FhKE_uv2.js → mermaid-parser.core-DR191xUW.js} +3 -3
- package/viewer/assets/{mermaid.core-BSOWwyvd.js → mermaid.core-DnwMH2U1.js} +4 -4
- package/viewer/assets/{mindmap-definition-YA3MSWOX-tsLZ_Opn.js → mindmap-definition-YA3MSWOX-KrnPcZeq.js} +1 -1
- package/viewer/assets/{nginx-B__INAtC.js → nginx-DAKCD0HY.js} +1 -1
- package/viewer/assets/{nim-UEY12GJF.js → nim-BvNTuhqF.js} +1 -1
- package/viewer/assets/{org-DDIZsz95.js → org-B-tOc6Cc.js} +1 -1
- package/viewer/assets/{packet-AYTQ26CC-CqdJnqfo.js → packet-AYTQ26CC-Cl2KBEou.js} +1 -1
- package/viewer/assets/{pegDiagram-XKGWAZYB-BJs7qu7m.js → pegDiagram-XKGWAZYB--GvmNzTl.js} +1 -1
- package/viewer/assets/{perl-D5KwNZt7.js → perl-RyNpCOE-.js} +1 -1
- package/viewer/assets/{php-BEs7d_Dk.js → php-D5gke6Nh.js} +1 -1
- package/viewer/assets/{pie-WAS4IAKB-lgzqBWqy.js → pie-WAS4IAKB-RfZPDbVI.js} +1 -1
- package/viewer/assets/{pieDiagram-E7YTZNPT-Cxe9LnnE.js → pieDiagram-E7YTZNPT-BbcD9IEY.js} +1 -1
- package/viewer/assets/{pug-B0dsfQOV.js → pug-CSZdPWzF.js} +1 -1
- package/viewer/assets/{qml-XPIhrIzf.js → qml-CCUSNo18.js} +1 -1
- package/viewer/assets/{quadrantDiagram-AXDQQJYC-D5JGwC11.js → quadrantDiagram-AXDQQJYC-DHP-nbSh.js} +1 -1
- package/viewer/assets/{r-C6hQdpIM.js → r-Cl6F5Lf8.js} +1 -1
- package/viewer/assets/{radar-RG4KPBEZ-B7JRLhUA.js → radar-RG4KPBEZ-DdfC1yOQ.js} +1 -1
- package/viewer/assets/{railroad-74A4TZTK-Df7ZQBLn.js → railroad-74A4TZTK-MHxcKgVS.js} +1 -1
- package/viewer/assets/railroad-abnf-HS5TGJTU-yEJXYTCu.js +1 -0
- package/viewer/assets/railroad-ebnf-LZEXJU2U-CEc058YK.js +1 -0
- package/viewer/assets/railroad-peg-WCYAUIDC-0iFSHGbV.js +1 -0
- package/viewer/assets/{railroadDiagram-O6MQD6OU-DZJzpmP8.js → railroadDiagram-O6MQD6OU-sxdxPqy-.js} +1 -1
- package/viewer/assets/{razor-C3KSUuOw.js → razor-hm0vLE-h.js} +1 -1
- package/viewer/assets/{regexp-n-T936Rk.js → regexp-BhIot3VY.js} +1 -1
- package/viewer/assets/{requirementDiagram-BXWQKSXE-Be9lEFrk.js → requirementDiagram-BXWQKSXE-CrZXt7Yu.js} +1 -1
- package/viewer/assets/{rst-fVnHDyXD.js → rst-C3giCu1C.js} +1 -1
- package/viewer/assets/{ruby-DuRgxlXF.js → ruby-B6fOYc5V.js} +1 -1
- package/viewer/assets/{sankeyDiagram-P5KCCOFB-BsgKAEBN.js → sankeyDiagram-P5KCCOFB-BVK_LjzN.js} +1 -1
- package/viewer/assets/{sas-C0WA2OFa.js → sas-a9NUQlsy.js} +1 -1
- package/viewer/assets/{scss-CQDZ4smR.js → scss-ChVMSp7G.js} +1 -1
- package/viewer/assets/{sequenceDiagram-WJ2MYXX4-BkUDWL0D.js → sequenceDiagram-WJ2MYXX4-B4E1wY9a.js} +1 -1
- package/viewer/assets/{shellscript-CE84G0GP.js → shellscript-Dxbnxou2.js} +1 -1
- package/viewer/assets/{shellsession-BdJvdaqL.js → shellsession-DWcRFAj_.js} +1 -1
- package/viewer/assets/{soy-BSxOREC0.js → soy-C-D-pvKx.js} +1 -1
- package/viewer/assets/{sql-D4MN9uRI.js → sql-W7nl9Rxy.js} +1 -1
- package/viewer/assets/{src-BT_kESTA.js → src-C_D1vmKd.js} +1 -1
- package/viewer/assets/{stata-B6nXAaGV.js → stata-BWq3CAeQ.js} +1 -1
- package/viewer/assets/{stateDiagram-D77RDMKH-C80wp8xG.js → stateDiagram-D77RDMKH-Dc8nXUDp.js} +1 -1
- package/viewer/assets/stateDiagram-v2-MP3YSRHH-SMxxOURe.js +1 -0
- package/viewer/assets/{surrealql-fVjZmhV3.js → surrealql-BkXUcx4E.js} +1 -1
- package/viewer/assets/{svelte-DnBQ5p7d.js → svelte-CowGUt9l.js} +1 -1
- package/viewer/assets/{swimlanes-42K2YHIH-Cff6yT8e.js → swimlanes-42K2YHIH-BtZAMLQ7.js} +1 -1
- package/viewer/assets/swimlanesDiagram-VR7AAH4N-C_XphOba.js +8 -0
- package/viewer/assets/{templ-TCx51Uts.js → templ-ejLYfFxc.js} +1 -1
- package/viewer/assets/{tex-CF6SMAQ_.js → tex-McefVK6r.js} +1 -1
- package/viewer/assets/{timeline-definition-24CTP7MA-Cje7BvaN.js → timeline-definition-24CTP7MA-TvSh-paH.js} +1 -1
- package/viewer/assets/{treeView-Q6P3EWNA-D-QLY3IO.js → treeView-Q6P3EWNA-BRIxIFdd.js} +1 -1
- package/viewer/assets/{treemap-WGGIJYW6-BCHcTa4N.js → treemap-WGGIJYW6-CeY__ApH.js} +1 -1
- package/viewer/assets/{ts-tags-BqLRnADX.js → ts-tags-D8LHJIWj.js} +1 -1
- package/viewer/assets/{tsx-D7KpDX0b.js → tsx-BkPshBHh.js} +1 -1
- package/viewer/assets/{twig-CEZLObpN.js → twig-CmfWCxbk.js} +1 -1
- package/viewer/assets/{typescript-DAbIDLbf.js → typescript-DnVmzADb.js} +1 -1
- package/viewer/assets/{typst-CqN7-whv.js → typst-BpEOIbiv.js} +1 -1
- package/viewer/assets/{vennDiagram-4TSXK5OY-Bz20rx02.js → vennDiagram-4TSXK5OY-Ba-jimVX.js} +1 -1
- package/viewer/assets/{vue-html-DQmvvKbd.js → vue-html-C-XYg42q.js} +1 -1
- package/viewer/assets/{vue-vine-Did3qTVW.js → vue-vine-DK68dTen.js} +1 -1
- package/viewer/assets/{vue-kTxN6wdc.js → vue-zII4ln6o.js} +1 -1
- package/viewer/assets/{wardley-WFR3VGLG-CpXaqOit.js → wardley-WFR3VGLG-e2A2dYzM.js} +1 -1
- package/viewer/assets/{wardleyDiagram-VM6X3IG4-Cz06jHpA.js → wardleyDiagram-VM6X3IG4-D2Rq1FsU.js} +1 -1
- package/viewer/assets/{xml-te2hFcAA.js → xml-Cc-dIbaq.js} +1 -1
- package/viewer/assets/{xsl-X4fuKSVl.js → xsl-C7A6UsbO.js} +1 -1
- package/viewer/assets/{xychartDiagram-S5SC5T6Z-BXCw0sfu.js → xychartDiagram-S5SC5T6Z-De55Qsdg.js} +1 -1
- package/viewer/assets/{yaml-NHtDSZab.js → yaml-BJLNLIRM.js} +1 -1
- package/viewer/index.html +2 -2
- package/viewer/assets/architecture-7GRP2DOG-Be250VKZ.js +0 -1
- package/viewer/assets/channel-DtULXRee.js +0 -1
- package/viewer/assets/classDiagram-ZZMXUADV-Bmqu01Xf.js +0 -1
- package/viewer/assets/classDiagram-v2-VYDZK3BY-Bmqu01Xf.js +0 -1
- package/viewer/assets/eventmodeling-NTZA5JFV-CJCg5f6p.js +0 -1
- package/viewer/assets/flowDiagram-HODETNUW-BFzq4Zvs.js +0 -1
- package/viewer/assets/railroad-abnf-HS5TGJTU-Z8q3QVTf.js +0 -1
- package/viewer/assets/railroad-ebnf-LZEXJU2U-BWoRkG3W.js +0 -1
- package/viewer/assets/railroad-peg-WCYAUIDC-BzoV1cN7.js +0 -1
- package/viewer/assets/stateDiagram-v2-MP3YSRHH-CYdsKKlz.js +0 -1
- package/viewer/assets/swimlanesDiagram-VR7AAH4N-niTUGjMT.js +0 -8
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.