rea/experiments/analysis-efficiency/javascript-facts-agent-history.json

{
  "final_harness_sha256": "9a6b4fc87fed586a2c64cdf6f483332872b1445911d644528bb2fc81b600c9e7",
  "historical_versions": [
    {
      "version": "disabled-host",
      "sha256": "be8b6945a89d345dd0b819da8aa8522bc6b6a84de2a39a86172986a4c8f08cfd",
      "patch_from_final": "--- javascript-facts-agent.mjs\n+++ historical-harness.mjs\n@@ -5,76 +5,30 @@\n import { pathToFileURL } from \"node:url\";\n import { parseArgs } from \"node:util\";\n import { performance } from \"node:perf_hooks\";\n-import { closeVerifierResources } from \"../../scripts/lib/verifier-cleanup.mjs\";\n \n-const { values } = parseArgs({\n-  options: {\n-    repository: { type: \"string\" },\n-    artifact: { type: \"string\" },\n-    arm: { type: \"string\" },\n-    task: { type: \"string\" },\n-    output: { type: \"string\" },\n-  },\n-});\n-for (const key of [\"repository\", \"artifact\", \"output\"])\n-  assert.ok(values[key] && isAbsolute(values[key]));\n+const { values } = parseArgs({ options: {\n+  repository: { type: \"string\" }, artifact: { type: \"string\" },\n+  arm: { type: \"string\" }, task: { type: \"string\" }, output: { type: \"string\" },\n+} });\n+for (const key of [\"repository\", \"artifact\", \"output\"]) assert.ok(values[key] && isAbsolute(values[key]));\n assert.ok([\"export\", \"view\"].includes(values.arm));\n assert.ok([\"direct\", \"partial\", \"negative\"].includes(values.task));\n-const { PrivateRuntimeRoot } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\"))\n-);\n-const { runOwnedCommand, OwnedCommandFailure } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\"))\n-);\n-await mkdir(values.output, { mode: 0o700 });\n-const workspace = await PrivateRuntimeRoot.create({\n-  prefix: \"rea-facts-agent-\",\n-});\n-const object = (properties) => ({\n-  type: \"object\",\n-  properties,\n-  required: Object.keys(properties),\n-  additionalProperties: false,\n-});\n+const { PrivateRuntimeRoot } = await import(pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\")));\n+const { runOwnedCommand, OwnedCommandFailure } = await import(pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\")));\n+const workspace = await PrivateRuntimeRoot.create({ prefix: \"rea-facts-agent-\" });\n+const object = (properties) => ({ type: \"object\", properties, required: Object.keys(properties), additionalProperties: false });\n const string = { type: \"string\" };\n const nullableString = { type: [\"string\", \"null\"] };\n const strings = { type: \"array\", items: string };\n const schema = object({\n   parent_evidence_id: string,\n-  native: object({\n-    path: string,\n-    node_id: string,\n-    sha256: nullableString,\n-    observed_byte_identity: { type: \"boolean\" },\n-    runtime_execution: {\n-      type: \"string\",\n-      enum: [\"unknown\", \"observed\", \"inferred\"],\n-    },\n-    observation_ids: strings,\n-  }),\n+  native: object({ path: string, node_id: string, sha256: nullableString, observed_byte_identity: { type: \"boolean\" }, runtime_execution: { type: \"string\", enum: [\"unknown\", \"observed\", \"inferred\"] }, observation_ids: strings }),\n   package: object({ name: nullableString, version: nullableString }),\n-  processing_gaps: {\n-    type: \"array\",\n-    items: object({\n-      path: string,\n-      operation: string,\n-      analysis_status: nullableString,\n-      authority: string,\n-      state: string,\n-      confidence: string,\n-      observation_id: string,\n-    }),\n-  },\n+  processing_gaps: { type: \"array\", items: object({ path: string, operation: string, analysis_status: nullableString, authority: string, state: string, confidence: string, observation_id: string }) },\n   source_coverage: object({ application: string, semantic: string }),\n   limitations: strings,\n });\n-const sources = [\n-  \"ElectronAppWrapper.js\",\n-  \"ElectronAppWrapper.js.map\",\n-  \"index.html\",\n-  \"package.json\",\n-  \"node_modules/keytar/build/Release/keytar.node\",\n-];\n+const sources = [\"ElectronAppWrapper.js\", \"ElectronAppWrapper.js.map\", \"index.html\", \"package.json\", \"node_modules/keytar/build/Release/keytar.node\"];\n const selectedPaths = sources.slice(1);\n const nativePath = sources[4];\n const common = `Investigate 
    },
    {
      "version": "host-v2",
      "sha256": "a2c85bcfa820261a020124f3b54b649a3dd5bf4a68adb591add0abd7905e29e4",
      "patch_from_final": "--- javascript-facts-agent.mjs\n+++ historical-harness.mjs\n@@ -5,76 +5,30 @@\n import { pathToFileURL } from \"node:url\";\n import { parseArgs } from \"node:util\";\n import { performance } from \"node:perf_hooks\";\n-import { closeVerifierResources } from \"../../scripts/lib/verifier-cleanup.mjs\";\n \n-const { values } = parseArgs({\n-  options: {\n-    repository: { type: \"string\" },\n-    artifact: { type: \"string\" },\n-    arm: { type: \"string\" },\n-    task: { type: \"string\" },\n-    output: { type: \"string\" },\n-  },\n-});\n-for (const key of [\"repository\", \"artifact\", \"output\"])\n-  assert.ok(values[key] && isAbsolute(values[key]));\n+const { values } = parseArgs({ options: {\n+  repository: { type: \"string\" }, artifact: { type: \"string\" },\n+  arm: { type: \"string\" }, task: { type: \"string\" }, output: { type: \"string\" },\n+} });\n+for (const key of [\"repository\", \"artifact\", \"output\"]) assert.ok(values[key] && isAbsolute(values[key]));\n assert.ok([\"export\", \"view\"].includes(values.arm));\n assert.ok([\"direct\", \"partial\", \"negative\"].includes(values.task));\n-const { PrivateRuntimeRoot } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\"))\n-);\n-const { runOwnedCommand, OwnedCommandFailure } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\"))\n-);\n-await mkdir(values.output, { mode: 0o700 });\n-const workspace = await PrivateRuntimeRoot.create({\n-  prefix: \"rea-facts-agent-\",\n-});\n-const object = (properties) => ({\n-  type: \"object\",\n-  properties,\n-  required: Object.keys(properties),\n-  additionalProperties: false,\n-});\n+const { PrivateRuntimeRoot } = await import(pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\")));\n+const { runOwnedCommand, OwnedCommandFailure } = await import(pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\")));\n+const workspace = await PrivateRuntimeRoot.create({ prefix: \"rea-facts-agent-\" });\n+const object = (properties) => ({ type: \"object\", properties, required: Object.keys(properties), additionalProperties: false });\n const string = { type: \"string\" };\n const nullableString = { type: [\"string\", \"null\"] };\n const strings = { type: \"array\", items: string };\n const schema = object({\n   parent_evidence_id: string,\n-  native: object({\n-    path: string,\n-    node_id: string,\n-    sha256: nullableString,\n-    observed_byte_identity: { type: \"boolean\" },\n-    runtime_execution: {\n-      type: \"string\",\n-      enum: [\"unknown\", \"observed\", \"inferred\"],\n-    },\n-    observation_ids: strings,\n-  }),\n+  native: object({ path: string, node_id: string, sha256: nullableString, observed_byte_identity: { type: \"boolean\" }, runtime_execution: { type: \"string\", enum: [\"unknown\", \"observed\", \"inferred\"] }, observation_ids: strings }),\n   package: object({ name: nullableString, version: nullableString }),\n-  processing_gaps: {\n-    type: \"array\",\n-    items: object({\n-      path: string,\n-      operation: string,\n-      analysis_status: nullableString,\n-      authority: string,\n-      state: string,\n-      confidence: string,\n-      observation_id: string,\n-    }),\n-  },\n+  processing_gaps: { type: \"array\", items: object({ path: string, operation: string, analysis_status: nullableString, authority: string, state: string, confidence: string, observation_id: string }) },\n   source_coverage: object({ application: string, semantic: string }),\n   limitations: strings,\n });\n-const sources = [\n-  \"ElectronAppWrapper.js\",\n-  \"ElectronAppWrapper.js.map\",\n-  \"index.html\",\n-  \"package.json\",\n-  \"node_modules/keytar/build/Release/keytar.node\",\n-];\n+const sources = [\"ElectronAppWrapper.js\", \"ElectronAppWrapper.js.map\", \"index.html\", \"package.json\", \"node_modules/keytar/build/Release/keytar.node\"];\n const selectedPaths = sources.slice(1);\n const nativePath = sources[4];\n const common = `Investigate 
    },
    {
      "version": "host-v3",
      "sha256": "43a4d59016c1fec1a9a2957c9b32c32fb8a91e77311c2813f05fdf89ae388fca",
      "patch_from_final": "--- javascript-facts-agent.mjs\n+++ historical-harness.mjs\n@@ -5,76 +5,31 @@\n import { pathToFileURL } from \"node:url\";\n import { parseArgs } from \"node:util\";\n import { performance } from \"node:perf_hooks\";\n-import { closeVerifierResources } from \"../../scripts/lib/verifier-cleanup.mjs\";\n \n-const { values } = parseArgs({\n-  options: {\n-    repository: { type: \"string\" },\n-    artifact: { type: \"string\" },\n-    arm: { type: \"string\" },\n-    task: { type: \"string\" },\n-    output: { type: \"string\" },\n-  },\n-});\n-for (const key of [\"repository\", \"artifact\", \"output\"])\n-  assert.ok(values[key] && isAbsolute(values[key]));\n+const { values } = parseArgs({ options: {\n+  repository: { type: \"string\" }, artifact: { type: \"string\" },\n+  arm: { type: \"string\" }, task: { type: \"string\" }, output: { type: \"string\" },\n+} });\n+for (const key of [\"repository\", \"artifact\", \"output\"]) assert.ok(values[key] && isAbsolute(values[key]));\n assert.ok([\"export\", \"view\"].includes(values.arm));\n assert.ok([\"direct\", \"partial\", \"negative\"].includes(values.task));\n-const { PrivateRuntimeRoot } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\"))\n-);\n-const { runOwnedCommand, OwnedCommandFailure } = await import(\n-  pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\"))\n-);\n+const { PrivateRuntimeRoot } = await import(pathToFileURL(join(values.repository, \"dist/process/PrivateRuntimeRoot.js\")));\n+const { runOwnedCommand, OwnedCommandFailure } = await import(pathToFileURL(join(values.repository, \"dist/process/OwnedCommand.js\")));\n await mkdir(values.output, { mode: 0o700 });\n-const workspace = await PrivateRuntimeRoot.create({\n-  prefix: \"rea-facts-agent-\",\n-});\n-const object = (properties) => ({\n-  type: \"object\",\n-  properties,\n-  required: Object.keys(properties),\n-  additionalProperties: false,\n-});\n+const workspace = await PrivateRuntimeRoot.create({ prefix: \"rea-facts-agent-\" });\n+const object = (properties) => ({ type: \"object\", properties, required: Object.keys(properties), additionalProperties: false });\n const string = { type: \"string\" };\n const nullableString = { type: [\"string\", \"null\"] };\n const strings = { type: \"array\", items: string };\n const schema = object({\n   parent_evidence_id: string,\n-  native: object({\n-    path: string,\n-    node_id: string,\n-    sha256: nullableString,\n-    observed_byte_identity: { type: \"boolean\" },\n-    runtime_execution: {\n-      type: \"string\",\n-      enum: [\"unknown\", \"observed\", \"inferred\"],\n-    },\n-    observation_ids: strings,\n-  }),\n+  native: object({ path: string, node_id: string, sha256: nullableString, observed_byte_identity: { type: \"boolean\" }, runtime_execution: { type: \"string\", enum: [\"unknown\", \"observed\", \"inferred\"] }, observation_ids: strings }),\n   package: object({ name: nullableString, version: nullableString }),\n-  processing_gaps: {\n-    type: \"array\",\n-    items: object({\n-      path: string,\n-      operation: string,\n-      analysis_status: nullableString,\n-      authority: string,\n-      state: string,\n-      confidence: string,\n-      observation_id: string,\n-    }),\n-  },\n+  processing_gaps: { type: \"array\", items: object({ path: string, operation: string, analysis_status: nullableString, authority: string, state: string, confidence: string, observation_id: string }) },\n   source_coverage: object({ application: string, semantic: string }),\n   limitations: strings,\n });\n-const sources = [\n-  \"ElectronAppWrapper.js\",\n-  \"ElectronAppWrapper.js.map\",\n-  \"index.html\",\n-  \"package.json\",\n-  \"node_modules/keytar/build/Release/keytar.node\",\n-];\n+const sources = [\"ElectronAppWrapper.js\", \"ElectronAppWrapper.js.map\", \"index.html\", \"package.json\", \"node_modules/keytar/build/Release/keytar.node\"];\n const selectedPaths = sources.slice(1);\n const nativePath = sources[4];\n const common = `Investigate 
    },
    {
      "version": "pre-review",
      "sha256": "bf2764245b5c17d2663945f0951f887e23ecd9a112a24418ea43ab29dfc844b5",
      "patch_from_final": "--- javascript-facts-agent.mjs\n+++ historical-harness.mjs\n@@ -5,7 +5,6 @@\n import { pathToFileURL } from \"node:url\";\n import { parseArgs } from \"node:util\";\n import { performance } from \"node:perf_hooks\";\n-import { closeVerifierResources } from \"../../scripts/lib/verifier-cleanup.mjs\";\n \n const { values } = parseArgs({\n   options: {\n@@ -157,37 +156,13 @@\n   args.push(\"-c\", `${key}=${JSON.stringify(value)}`);\n args.push(prompt);\n const start = performance.now();\n-let cleanupOwner;\n-let primaryError;\n+let retainWorkspace = false;\n let commandResult;\n-let report;\n-let cliVersion = null;\n-let phase = \"cli-version\";\n const controller = new AbortController();\n const cancel = () => controller.abort();\n process.on(\"SIGINT\", cancel);\n process.on(\"SIGTERM\", cancel);\n try {\n-  const version = (commandResult = await runOwnedCommand(\n-    {\n-      command: \"codex\",\n-      arguments: [\"--version\"],\n-      cwd: workspace.path,\n-      env: { ...process.env },\n-      runId: `rea-facts-cli-version-${randomUUID()}`,\n-      expectedCommand: null,\n-      sweepTokenOwnedProcesses: true,\n-    },\n-    { timeoutMs: 10_000, diagnosticBytes: 64 * 1024 },\n-    { signal: controller.signal },\n-  ));\n-  const observedVersion = version.stdout.text.trim();\n-  assert.ok(\n-    observedVersion.length > 0,\n-    \"Codex CLI version probe returned no version\",\n-  );\n-  cliVersion = observedVersion;\n-  phase = \"agent-trial\";\n   await writeFile(schemaPath, JSON.stringify(schema));\n   const result = (commandResult = await runOwnedCommand(\n     {\n@@ -248,7 +223,7 @@\n     harness_sha256: createHash(\"sha256\")\n       .update(await readFile(new URL(import.meta.url)))\n       .digest(\"hex\"),\n-    cli_version: cliVersion,\n+    cli_version: \"0.161.0\",\n     enabled_tools: enabled,\n     code_mode_host: true,\n     prompt,\n@@ -283,21 +258,22 @@\n   await writeFile(join(values.output, \"stderr.log\"), result.stderr.text, {\n     mode: 0o600,\n   });\n-  report = {\n-    task: values.task,\n-    arm: values.arm,\n-    elapsed_ms: metadata.elapsed_ms,\n-    exit_code: result.exitCode,\n-    usage: metadata.usage,\n-    tool_calls: tools.length,\n-    answered: answer !== null,\n-    report: join(values.output, \"trial.json\"),\n-  };\n+  console.log(\n+    JSON.stringify({\n+      task: values.task,\n+      arm: values.arm,\n+      elapsed_ms: metadata.elapsed_ms,\n+      exit_code: result.exitCode,\n+      usage: metadata.usage,\n+      tool_calls: tools.length,\n+      answered: answer !== null,\n+      report: join(values.output, \"trial.json\"),\n+    }),\n+  );\n   if (result.exitCode !== 0 || answer === null) process.exitCode = 1;\n } catch (cause) {\n-  primaryError = cause;\n-  cleanupOwner =\n-    cause instanceof OwnedCommandFailure ? cause.cleanupOwner : undefined;\n+  retainWorkspace =\n+    cause instanceof OwnedCommandFailure && cause.cleanupOwner !== undefined;\n   const snapshot =\n     cause instanceof OwnedCommandFailure ? cause.snapshot : commandResult;\n   const writes = await Promise.allSettled([\n@@ -308,41 +284,15 @@\n           task: values.task,\n           arm: values.arm,\n           classification: \"incomplete-pilot\",\n-          phase,\n-          cli_version: cliVersion,\n-          requested_model: config.model,\n-          reasoning: config.model_reasoning_effort,\n           message: cause.message,\n           reason:\n             cause instanceof OwnedCommandFailure\n               ? cause.reason\n               : \"verification\",\n           elapsed_ms: performance.now() - start,\n-          cleanup_owner_retained: cleanupOwner !== undefined,\n-          retained_workspace:\n-            cleanupOwner === undefined ? null : workspace.path,\n-          cleanup_failure:\n-            cause instanceof OwnedCommandFailure ? cause.cleanupFailure : null,\n-          cleanup_result:\n-            cause instanceof OwnedCommandFailure\n-              ? (cause.cleanupResult ?? null)\n-              : null,\n-          resources:\n-      
    }
  ]
}