agentv 5.0.0-next.1 → 5.2.0-next.1

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.
Files changed (108) hide show
  1. package/README.md +239 -53
  2. package/dist/{agentv-provider-AYXH7WLW-NJRC6UQX.js → agentv-provider-AYXH7WLW-6YZKZ7PS.js} +2 -2
  3. package/dist/{artifact-writer-QD52FC56.js → artifact-writer-SN6UNL5G.js} +15 -8
  4. package/dist/{chunk-GZJMODLW.js → chunk-3S6A2RKR.js} +45880 -30542
  5. package/dist/chunk-3S6A2RKR.js.map +1 -0
  6. package/dist/{chunk-6Q56CEXV.js → chunk-3X357HS4.js} +7900 -8985
  7. package/dist/chunk-3X357HS4.js.map +1 -0
  8. package/dist/{chunk-6JVM4GJI.js → chunk-46K2OET3.js} +187 -80
  9. package/dist/chunk-46K2OET3.js.map +1 -0
  10. package/dist/{chunk-IJEZFZJR.js → chunk-7BGERE6L.js} +2 -2
  11. package/dist/chunk-7BGERE6L.js.map +1 -0
  12. package/dist/{chunk-UG4JHZYM.js → chunk-ALVZQUZP.js} +670 -1427
  13. package/dist/chunk-ALVZQUZP.js.map +1 -0
  14. package/dist/{chunk-RCIEHFQ2.js → chunk-PEUTJS7B.js} +3 -3
  15. package/dist/{chunk-5H446C7X.js → chunk-QMRVH5ZP.js} +2 -8
  16. package/dist/{chunk-IBI7A5RP.js → chunk-T4AD3H3Y.js} +3444 -2251
  17. package/dist/chunk-T4AD3H3Y.js.map +1 -0
  18. package/dist/cli.js +8 -9
  19. package/dist/cli.js.map +1 -1
  20. package/dist/dashboard/assets/{index-D5_8DE_B.js → index-DNgf3qJ2.js} +1 -1
  21. package/dist/dashboard/assets/index-D_bokML8.css +1 -0
  22. package/dist/dashboard/assets/index-r_jSJmlw.js +121 -0
  23. package/dist/dashboard/index.html +2 -2
  24. package/dist/{dist-KJ6PELQY.js → dist-DEPJOMCA.js} +74 -60
  25. package/dist/{docker-workspace-ZJ2ESVBI-6UDETQII.js → docker-workspace-NNK4Z6FR-QRTIG6TM.js} +3 -3
  26. package/dist/{exec-MYPAJJP7-C5HD5WG5.js → exec-4HFFRQ3B-AXDMJNLJ.js} +3 -3
  27. package/dist/index.js +8 -9
  28. package/dist/{interactive-2WMVAASS.js → interactive-36ZNMQB2.js} +13 -29
  29. package/dist/interactive-36ZNMQB2.js.map +1 -0
  30. package/dist/skills/agentv-bench/SKILL.md +38 -34
  31. package/dist/skills/agentv-bench/agents/analyzer.md +6 -6
  32. package/dist/skills/agentv-bench/agents/comparator.md +4 -5
  33. package/dist/skills/agentv-bench/agents/grader.md +4 -4
  34. package/dist/skills/agentv-bench/references/autoresearch.md +3 -3
  35. package/dist/skills/agentv-bench/references/description-optimization.md +2 -2
  36. package/dist/skills/agentv-bench/references/environment-adaptation.md +10 -10
  37. package/dist/skills/agentv-bench/references/eval-yaml-spec.md +51 -30
  38. package/dist/skills/agentv-bench/references/migrating-from-skill-creator.md +4 -4
  39. package/dist/skills/agentv-bench/references/subagent-pipeline.md +13 -12
  40. package/dist/skills/agentv-eval-migrations/SKILL.md +33 -0
  41. package/dist/skills/agentv-eval-migrations/references/breaking-changes.md +1012 -0
  42. package/dist/skills/agentv-eval-review/SKILL.md +6 -3
  43. package/dist/skills/agentv-eval-review/scripts/lint_eval.py +1 -1
  44. package/dist/skills/agentv-eval-writer/SKILL.md +380 -246
  45. package/dist/skills/agentv-eval-writer/references/{config-schema.json → config.schema.json} +6 -5
  46. package/dist/skills/agentv-eval-writer/references/custom-evaluators.md +23 -18
  47. package/dist/skills/agentv-eval-writer/references/eval.schema.json +9852 -0
  48. package/dist/skills/agentv-eval-writer/references/python-helpers.md +8 -8
  49. package/dist/skills/agentv-eval-writer/references/rubric-evaluator.md +21 -22
  50. package/dist/skills/agentv-trace-analyst/SKILL.md +4 -4
  51. package/dist/templates/.agentv/targets.yaml +41 -40
  52. package/dist/{ts-eval-loader-RE43OAGX-AMRCUKBZ.js → ts-eval-loader-OMG2JBHP-OP5RR7A3.js} +5 -4
  53. package/package.json +19 -4
  54. package/dist/chunk-6JVM4GJI.js.map +0 -1
  55. package/dist/chunk-6Q56CEXV.js.map +0 -1
  56. package/dist/chunk-76FOHROU.js +0 -96
  57. package/dist/chunk-76FOHROU.js.map +0 -1
  58. package/dist/chunk-GZJMODLW.js.map +0 -1
  59. package/dist/chunk-HSHTTN6C.js +0 -565
  60. package/dist/chunk-HSHTTN6C.js.map +0 -1
  61. package/dist/chunk-IBI7A5RP.js.map +0 -1
  62. package/dist/chunk-IJEZFZJR.js.map +0 -1
  63. package/dist/chunk-LRULMAAA.js +0 -1711
  64. package/dist/chunk-LRULMAAA.js.map +0 -1
  65. package/dist/chunk-R3CXYNTN.js +0 -1238
  66. package/dist/chunk-R3CXYNTN.js.map +0 -1
  67. package/dist/chunk-UG4JHZYM.js.map +0 -1
  68. package/dist/chunk-VQ2ZO7XJ.js +0 -2098
  69. package/dist/chunk-VQ2ZO7XJ.js.map +0 -1
  70. package/dist/chunk-XALGXSKB.js +0 -21
  71. package/dist/chunk-XALGXSKB.js.map +0 -1
  72. package/dist/dashboard/assets/index-BVMrdN8a.js +0 -119
  73. package/dist/dashboard/assets/index-DZWXfWsv.css +0 -1
  74. package/dist/esm-NNMQYIKT.js +0 -32
  75. package/dist/esm-R77SNOF5.js +0 -65
  76. package/dist/esm-RVQPUGWH.js +0 -1207
  77. package/dist/esm-RVQPUGWH.js.map +0 -1
  78. package/dist/esm-TTEMJEVV.js +0 -933
  79. package/dist/esm-TTEMJEVV.js.map +0 -1
  80. package/dist/esm-ZADQ4XQH-QUFGGZL4.js +0 -924
  81. package/dist/esm-ZADQ4XQH-QUFGGZL4.js.map +0 -1
  82. package/dist/exec-MYPAJJP7-C5HD5WG5.js.map +0 -1
  83. package/dist/getMachineId-bsd-HSK5LZMG.js +0 -41
  84. package/dist/getMachineId-bsd-HSK5LZMG.js.map +0 -1
  85. package/dist/getMachineId-darwin-4DP6CCJV.js +0 -41
  86. package/dist/getMachineId-darwin-4DP6CCJV.js.map +0 -1
  87. package/dist/getMachineId-linux-44LJ5UJB.js +0 -33
  88. package/dist/getMachineId-linux-44LJ5UJB.js.map +0 -1
  89. package/dist/getMachineId-unsupported-NVK6IATM.js +0 -24
  90. package/dist/getMachineId-unsupported-NVK6IATM.js.map +0 -1
  91. package/dist/getMachineId-win-YZ36S7VA.js +0 -43
  92. package/dist/getMachineId-win-YZ36S7VA.js.map +0 -1
  93. package/dist/interactive-2WMVAASS.js.map +0 -1
  94. package/dist/otlp-json-file-exporter-RY63S3IG-PZBQPVYY.js +0 -9
  95. package/dist/otlp-json-file-exporter-RY63S3IG-PZBQPVYY.js.map +0 -1
  96. package/dist/skills/agentv-eval-writer/references/eval-schema.json +0 -17295
  97. package/dist/skills/agentv-eval-writer/references/experiment-schema.json +0 -278
  98. package/dist/src-76ISS3LH.js +0 -1733
  99. package/dist/src-76ISS3LH.js.map +0 -1
  100. package/dist/ts-eval-loader-RE43OAGX-AMRCUKBZ.js.map +0 -1
  101. /package/dist/{agentv-provider-AYXH7WLW-NJRC6UQX.js.map → agentv-provider-AYXH7WLW-6YZKZ7PS.js.map} +0 -0
  102. /package/dist/{artifact-writer-QD52FC56.js.map → artifact-writer-SN6UNL5G.js.map} +0 -0
  103. /package/dist/{chunk-RCIEHFQ2.js.map → chunk-PEUTJS7B.js.map} +0 -0
  104. /package/dist/{chunk-5H446C7X.js.map → chunk-QMRVH5ZP.js.map} +0 -0
  105. /package/dist/{dist-KJ6PELQY.js.map → dist-DEPJOMCA.js.map} +0 -0
  106. /package/dist/{docker-workspace-ZJ2ESVBI-6UDETQII.js.map → docker-workspace-NNK4Z6FR-QRTIG6TM.js.map} +0 -0
  107. /package/dist/{esm-NNMQYIKT.js.map → exec-4HFFRQ3B-AXDMJNLJ.js.map} +0 -0
  108. /package/dist/{esm-R77SNOF5.js.map → ts-eval-loader-OMG2JBHP-OP5RR7A3.js.map} +0 -0
@@ -1 +0,0 @@
1
- {"version":3,"sources":["../../../packages/core/src/runtime/exec.ts"],"sourcesContent":["interface ExecOptions {\n readonly cwd?: string;\n readonly timeoutMs?: number;\n /** Additional environment variables to pass to the subprocess */\n readonly env?: Record<string, string>;\n}\n\nfunction shellEscapePath(value: string): string {\n if (process.platform === 'win32') {\n // Very small escape helper for file paths in cmd.exe context.\n // Wrap in double-quotes and escape existing double-quotes.\n return `\"${value.replaceAll('\"', '\"\"')}\"`;\n }\n // POSIX: single-quote escape (close/open around embedded single quotes).\n return `'${value.replaceAll(\"'\", `'\\\"'\\\"'`)}'`;\n}\n\n// IPC protocol: stdin/stdout JSON was chosen over JSON-RPC (overkill for one-shot eval),\n// HTTP (unnecessary network overhead for local scripts), and in-process (no isolation,\n// single-language only). Each evaluation is isolated by design for reproducibility and\n// safe parallelization. Process spawn overhead (~10-50ms) is acceptable for eval workloads.\nexport async function execFileWithStdin(\n argv: readonly string[],\n stdinPayload: string,\n options: ExecOptions = {},\n): Promise<{\n readonly stdout: string;\n readonly stderr: string;\n readonly exitCode: number;\n}> {\n if (argv.length === 0) {\n throw new Error('Executable argv must include at least one entry');\n }\n\n // Use Node's child_process path even under Bun. Bun 1.3.3 can hang when a\n // Bun.spawn child is a Node process reading stdin, which breaks code grader\n // and workspace hook execution on CI's pinned Bun version.\n return execFileWithStdinNode(argv, stdinPayload, options);\n}\n\n/**\n * Node.js implementation using child_process.spawn\n */\nasync function execFileWithStdinNode(\n argv: readonly string[],\n stdinPayload: string,\n options: ExecOptions,\n): Promise<{\n readonly stdout: string;\n readonly stderr: string;\n readonly exitCode: number;\n}> {\n const { spawn } = await import('node:child_process');\n\n return new Promise((resolve, reject) => {\n const [cmd, ...args] = argv;\n const child = spawn(cmd, args, {\n cwd: options.cwd,\n stdio: ['pipe', 'pipe', 'pipe'],\n // Merge additional env vars with process.env\n env: options.env ? { ...process.env, ...options.env } : process.env,\n });\n\n const stdoutChunks: Buffer[] = [];\n const stderrChunks: Buffer[] = [];\n\n child.stdout?.on('data', (chunk: Buffer) => stdoutChunks.push(chunk));\n child.stderr?.on('data', (chunk: Buffer) => stderrChunks.push(chunk));\n\n let timedOut = false;\n const timeout =\n options.timeoutMs !== undefined\n ? setTimeout(() => {\n timedOut = true;\n child.kill('SIGKILL');\n }, options.timeoutMs)\n : undefined;\n\n child.on('error', (error) => {\n if (timeout !== undefined) clearTimeout(timeout);\n reject(error);\n });\n\n child.on('close', (code) => {\n if (timeout !== undefined) clearTimeout(timeout);\n\n if (timedOut) {\n reject(new Error(`Process timed out after ${options.timeoutMs}ms`));\n return;\n }\n\n const stdout = Buffer.concat(stdoutChunks).toString('utf8').replace(/\\r\\n/g, '\\n');\n const stderr = Buffer.concat(stderrChunks).toString('utf8').replace(/\\r\\n/g, '\\n');\n\n resolve({\n stdout,\n stderr,\n exitCode: code ?? 0,\n });\n });\n\n // Write stdin and close\n if (child.stdin) {\n child.stdin.write(stdinPayload);\n child.stdin.end();\n }\n });\n}\n\n/**\n * Execute a shell command with the given stdin payload.\n *\n * Why this exists:\n * - Some providers/scripts (notably Node.js) must receive stdin reliably.\n * - In some Bun environments, `Bun.spawn` does not forward stdin to Node correctly.\n * - Capture stdout/stderr via temp files to avoid pipe incompatibilities.\n */\nexport async function execShellWithStdin(\n command: string,\n stdinPayload: string,\n options: ExecOptions = {},\n): Promise<{\n readonly stdout: string;\n readonly stderr: string;\n readonly exitCode: number;\n}> {\n const { mkdir, readFile, rm, writeFile } = await import('node:fs/promises');\n const { tmpdir } = await import('node:os');\n const path = await import('node:path');\n const { randomUUID } = await import('node:crypto');\n\n const dir = path.join(tmpdir(), `agentv-exec-${randomUUID()}`);\n await mkdir(dir, { recursive: true });\n\n const stdinPath = path.join(dir, 'stdin.txt');\n const stdoutPath = path.join(dir, 'stdout.txt');\n const stderrPath = path.join(dir, 'stderr.txt');\n\n await writeFile(stdinPath, stdinPayload, 'utf8');\n\n const wrappedCommand =\n process.platform === 'win32'\n ? `(${command}) < ${shellEscapePath(stdinPath)} > ${shellEscapePath(stdoutPath)} 2> ${shellEscapePath(stderrPath)}`\n : `(${command}) < ${shellEscapePath(stdinPath)} > ${shellEscapePath(stdoutPath)} 2> ${shellEscapePath(stderrPath)}`;\n\n const { spawn } = await import('node:child_process');\n try {\n const exitCode = await new Promise<number>((resolve, reject) => {\n const child = spawn(wrappedCommand, {\n shell: true,\n cwd: options.cwd,\n stdio: ['ignore', 'ignore', 'ignore'],\n // Merge additional env vars with process.env\n env: options.env ? { ...process.env, ...options.env } : process.env,\n });\n\n const timeout = options.timeoutMs\n ? setTimeout(() => {\n child.kill();\n reject(new Error(`Process timed out after ${options.timeoutMs}ms`));\n }, options.timeoutMs)\n : undefined;\n\n child.on('error', (error) => {\n if (timeout !== undefined) {\n clearTimeout(timeout);\n }\n reject(error);\n });\n\n child.on('exit', (code) => {\n if (timeout !== undefined) {\n clearTimeout(timeout);\n }\n resolve(code ?? 0);\n });\n });\n\n const stdout = (await readFile(stdoutPath, 'utf8')).replace(/\\r\\n/g, '\\n');\n const stderr = (await readFile(stderrPath, 'utf8')).replace(/\\r\\n/g, '\\n');\n return { stdout, stderr, exitCode };\n } finally {\n await rm(dir, { recursive: true, force: true });\n }\n}\n"],"mappings":";;;AAOA,SAAS,gBAAgB,OAAuB;AAC9C,MAAI,QAAQ,aAAa,SAAS;AAGhC,WAAO,IAAI,MAAM,WAAW,KAAK,IAAI,CAAC;EACxC;AAEA,SAAO,IAAI,MAAM,WAAW,KAAK,OAAS,CAAC;AAC7C;AAMA,eAAsB,kBACpB,MACA,cACA,UAAuB,CAAC,GAKvB;AACD,MAAI,KAAK,WAAW,GAAG;AACrB,UAAM,IAAI,MAAM,iDAAiD;EACnE;AAKA,SAAO,sBAAsB,MAAM,cAAc,OAAO;AAC1D;AAKA,eAAe,sBACb,MACA,cACA,SAKC;AACD,QAAM,EAAE,MAAM,IAAI,MAAM,OAAO,oBAAoB;AAEnD,SAAO,IAAI,QAAQ,CAAC,SAAS,WAAW;AACtC,UAAM,CAAC,KAAK,GAAG,IAAI,IAAI;AACvB,UAAM,QAAQ,MAAM,KAAK,MAAM;MAC7B,KAAK,QAAQ;MACb,OAAO,CAAC,QAAQ,QAAQ,MAAM;;MAE9B,KAAK,QAAQ,MAAM,EAAE,GAAG,QAAQ,KAAK,GAAG,QAAQ,IAAI,IAAI,QAAQ;IAClE,CAAC;AAED,UAAM,eAAyB,CAAC;AAChC,UAAM,eAAyB,CAAC;AAEhC,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAkB,aAAa,KAAK,KAAK,CAAC;AACpE,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAkB,aAAa,KAAK,KAAK,CAAC;AAEpE,QAAI,WAAW;AACf,UAAM,UACJ,QAAQ,cAAc,SAClB,WAAW,MAAM;AACf,iBAAW;AACX,YAAM,KAAK,SAAS;IACtB,GAAG,QAAQ,SAAS,IACpB;AAEN,UAAM,GAAG,SAAS,CAAC,UAAU;AAC3B,UAAI,YAAY,OAAW,cAAa,OAAO;AAC/C,aAAO,KAAK;IACd,CAAC;AAED,UAAM,GAAG,SAAS,CAAC,SAAS;AAC1B,UAAI,YAAY,OAAW,cAAa,OAAO;AAE/C,UAAI,UAAU;AACZ,eAAO,IAAI,MAAM,2BAA2B,QAAQ,SAAS,IAAI,CAAC;AAClE;MACF;AAEA,YAAM,SAAS,OAAO,OAAO,YAAY,EAAE,SAAS,MAAM,EAAE,QAAQ,SAAS,IAAI;AACjF,YAAM,SAAS,OAAO,OAAO,YAAY,EAAE,SAAS,MAAM,EAAE,QAAQ,SAAS,IAAI;AAEjF,cAAQ;QACN;QACA;QACA,UAAU,QAAQ;MACpB,CAAC;IACH,CAAC;AAGD,QAAI,MAAM,OAAO;AACf,YAAM,MAAM,MAAM,YAAY;AAC9B,YAAM,MAAM,IAAI;IAClB;EACF,CAAC;AACH;AAUA,eAAsB,mBACpB,SACA,cACA,UAAuB,CAAC,GAKvB;AACD,QAAM,EAAE,OAAO,UAAU,IAAI,UAAU,IAAI,MAAM,OAAO,kBAAkB;AAC1E,QAAM,EAAE,OAAO,IAAI,MAAM,OAAO,SAAS;AACzC,QAAM,OAAO,MAAM,OAAO,WAAW;AACrC,QAAM,EAAE,WAAW,IAAI,MAAM,OAAO,aAAa;AAEjD,QAAM,MAAM,KAAK,KAAK,OAAO,GAAG,eAAe,WAAW,CAAC,EAAE;AAC7D,QAAM,MAAM,KAAK,EAAE,WAAW,KAAK,CAAC;AAEpC,QAAM,YAAY,KAAK,KAAK,KAAK,WAAW;AAC5C,QAAM,aAAa,KAAK,KAAK,KAAK,YAAY;AAC9C,QAAM,aAAa,KAAK,KAAK,KAAK,YAAY;AAE9C,QAAM,UAAU,WAAW,cAAc,MAAM;AAE/C,QAAM,iBACJ,QAAQ,aAAa,UACjB,IAAI,OAAO,OAAO,gBAAgB,SAAS,CAAC,MAAM,gBAAgB,UAAU,CAAC,OAAO,gBAAgB,UAAU,CAAC,KAC/G,IAAI,OAAO,OAAO,gBAAgB,SAAS,CAAC,MAAM,gBAAgB,UAAU,CAAC,OAAO,gBAAgB,UAAU,CAAC;AAErH,QAAM,EAAE,MAAM,IAAI,MAAM,OAAO,oBAAoB;AACnD,MAAI;AACF,UAAM,WAAW,MAAM,IAAI,QAAgB,CAAC,SAAS,WAAW;AAC9D,YAAM,QAAQ,MAAM,gBAAgB;QAClC,OAAO;QACP,KAAK,QAAQ;QACb,OAAO,CAAC,UAAU,UAAU,QAAQ;;QAEpC,KAAK,QAAQ,MAAM,EAAE,GAAG,QAAQ,KAAK,GAAG,QAAQ,IAAI,IAAI,QAAQ;MAClE,CAAC;AAED,YAAM,UAAU,QAAQ,YACpB,WAAW,MAAM;AACf,cAAM,KAAK;AACX,eAAO,IAAI,MAAM,2BAA2B,QAAQ,SAAS,IAAI,CAAC;MACpE,GAAG,QAAQ,SAAS,IACpB;AAEJ,YAAM,GAAG,SAAS,CAAC,UAAU;AAC3B,YAAI,YAAY,QAAW;AACzB,uBAAa,OAAO;QACtB;AACA,eAAO,KAAK;MACd,CAAC;AAED,YAAM,GAAG,QAAQ,CAAC,SAAS;AACzB,YAAI,YAAY,QAAW;AACzB,uBAAa,OAAO;QACtB;AACA,gBAAQ,QAAQ,CAAC;MACnB,CAAC;IACH,CAAC;AAED,UAAM,UAAU,MAAM,SAAS,YAAY,MAAM,GAAG,QAAQ,SAAS,IAAI;AACzE,UAAM,UAAU,MAAM,SAAS,YAAY,MAAM,GAAG,QAAQ,SAAS,IAAI;AACzE,WAAO,EAAE,QAAQ,QAAQ,SAAS;EACpC,UAAA;AACE,UAAM,GAAG,KAAK,EAAE,WAAW,MAAM,OAAO,KAAK,CAAC;EAChD;AACF;","names":[]}