@tangle-network/agent-bench 0.8.6 → 0.8.9

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 (4) hide show
  1. package/CHANGELOG.md +12 -0
  2. package/package.json +6 -6
  3. package/scripts/verify-pier-agent.mts +1 -0
  4. package/src/benchmarks/humaneval.test.mts +2 -2
package/CHANGELOG.md CHANGED
@@ -1,5 +1,17 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.8.9
4
+
5
+ - Consume Runtime 0.134.4, Eval 0.145.11, Interface 0.52.0, Knowledge 7.2.6, and Sandbox 0.26.1 as one compatible dependency set.
6
+
7
+ ## 0.8.8
8
+
9
+ - Verify candidate execution against Runtime 0.133.6 and its terminal aggregate-token integrity result.
10
+
11
+ ## 0.8.7
12
+
13
+ - Consume Runtime 0.132.11, Eval 0.145.2, Interface 0.47.0, Knowledge 7.2.4, and Sandbox 0.21.1 as one compatible dependency set.
14
+
3
15
  ## 0.8.6
4
16
 
5
17
  - Consume Runtime 0.132.6 with the settled provider-model identity contract.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-bench",
3
- "version": "0.8.6",
3
+ "version": "0.8.9",
4
4
  "type": "module",
5
5
  "description": "Benchmark adapters and execution for agent-runtime across coding, tool-use, RAG, memory, browser, and terminal tasks.",
6
6
  "repository": {
@@ -25,11 +25,11 @@
25
25
  }
26
26
  },
27
27
  "dependencies": {
28
- "@tangle-network/agent-eval": "0.145.0",
29
- "@tangle-network/agent-interface": "0.46.1",
30
- "@tangle-network/agent-knowledge": "7.2.3",
31
- "@tangle-network/sandbox": "0.19.4",
32
- "@tangle-network/agent-runtime": "0.132.6"
28
+ "@tangle-network/agent-eval": "0.145.11",
29
+ "@tangle-network/agent-interface": "0.52.0",
30
+ "@tangle-network/agent-knowledge": "7.2.6",
31
+ "@tangle-network/sandbox": "0.26.1",
32
+ "@tangle-network/agent-runtime": "0.134.4"
33
33
  },
34
34
  "devDependencies": {
35
35
  "@arethetypeswrong/cli": "0.18.5",
package/scripts/verify-pier-agent.mts CHANGED
@@ -512,6 +512,7 @@ ${proofArm === 'success' ? "(task / 'src/status.txt').write_text('ready\\nowner=
512
512
  preparationId,
513
513
  grantDigest: `sha256:${'c'.repeat(64)}`,
514
514
  closed: true,
515
+ usageWithinLimits: true,
515
516
  calls: [],
516
517
  }),
517
518
  },
package/src/benchmarks/humaneval.test.mts CHANGED
@@ -13,8 +13,8 @@ describe('HumanEval Python isolation', () => {
13
13
  writeFileSync(
14
14
  fakeDocker,
15
15
  `#!/usr/bin/env node
16
- const fs = require('node:fs')
17
- const path = require('node:path')
16
+ import fs from 'node:fs'
17
+ import path from 'node:path'
18
18
  const args = process.argv.slice(2)
19
19
  if (args[0] === 'rm') process.exit(0)
20
20
  if (process.env.FAKE_DOCKER_MISSING === '1') {