@tangle-network/agent-bench 0.13.3 → 0.13.11
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/CHANGELOG.md +38 -0
- package/package.json +6 -6
- package/src/swe-bench-env.test.ts +5 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,43 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.13.11
|
|
4
|
+
|
|
5
|
+
Accept Eval 0.184 and require Knowledge 17.1.1 through the shared dependency catalog.
|
|
6
|
+
Benchmark behavior is unchanged.
|
|
7
|
+
|
|
8
|
+
## 0.13.10
|
|
9
|
+
|
|
10
|
+
Accept Sandbox SDK 0.47 through the shared dependency catalog.
|
|
11
|
+
Benchmark behavior is unchanged.
|
|
12
|
+
|
|
13
|
+
## 0.13.9
|
|
14
|
+
|
|
15
|
+
Accept agent-interface 2.11.0 through the shared dependency catalog.
|
|
16
|
+
Benchmark behavior is unchanged.
|
|
17
|
+
|
|
18
|
+
## 0.13.8
|
|
19
|
+
|
|
20
|
+
Accept Sandbox SDK 0.46 through the shared dependency catalog.
|
|
21
|
+
Benchmark behavior is unchanged.
|
|
22
|
+
|
|
23
|
+
## 0.13.7
|
|
24
|
+
|
|
25
|
+
Support Eval 0.183 and require Knowledge 17.1 through the shared dependency catalog.
|
|
26
|
+
Consume Runtime 0.249.0 through the workspace dependency.
|
|
27
|
+
|
|
28
|
+
## 0.13.6
|
|
29
|
+
|
|
30
|
+
Follow Runtime 0.244.0 through the workspace dependency. Benchmark APIs and grading are unchanged.
|
|
31
|
+
|
|
32
|
+
## 0.13.5
|
|
33
|
+
|
|
34
|
+
Consume Runtime 0.243.0 through the existing workspace dependency. Benchmark APIs and grading behavior are unchanged.
|
|
35
|
+
|
|
36
|
+
## 0.13.4
|
|
37
|
+
|
|
38
|
+
Require Interface `^2.10.0` and consume Runtime 0.242.0 through the published dependency ranges, keeping benchmark consumers on the checkpoint-training receipt contract.
|
|
39
|
+
Benchmark execution and grading behavior are unchanged.
|
|
40
|
+
|
|
3
41
|
## 0.13.3
|
|
4
42
|
|
|
5
43
|
Support Sandbox 0.41 and consume Runtime 0.233.1 through the published dependency ranges.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@tangle-network/agent-bench",
|
|
3
|
-
"version": "0.13.
|
|
3
|
+
"version": "0.13.11",
|
|
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.
|
|
29
|
-
"@tangle-network/agent-interface": "^2.
|
|
30
|
-
"@tangle-network/agent-knowledge": "^17.
|
|
31
|
-
"@tangle-network/sandbox": ">=0.36.4 <0.
|
|
32
|
-
"@tangle-network/agent-runtime": "^0.
|
|
28
|
+
"@tangle-network/agent-eval": ">=0.183.0 <0.185.0",
|
|
29
|
+
"@tangle-network/agent-interface": "^2.11.0",
|
|
30
|
+
"@tangle-network/agent-knowledge": "^17.1.1",
|
|
31
|
+
"@tangle-network/sandbox": ">=0.36.4 <0.48.0",
|
|
32
|
+
"@tangle-network/agent-runtime": "^0.256.0"
|
|
33
33
|
},
|
|
34
34
|
"devDependencies": {
|
|
35
35
|
"@arethetypeswrong/cli": "0.18.5",
|
|
@@ -47,6 +47,11 @@ const makeRelativeSymlinkRepo = (): { root: string; source: string; destination:
|
|
|
47
47
|
`core.hooksPath=${hooksDir}`,
|
|
48
48
|
'-c',
|
|
49
49
|
'commit.gpgsign=false',
|
|
50
|
+
// A commit starts `git maintenance run --auto` in the background, which creates and removes
|
|
51
|
+
// .git/objects/maintenance.lock while the test copies the checkout. The copy then fails with
|
|
52
|
+
// ENOENT on a file that vanished: 5 of 240 copies on Node 22.23 and 24.11, 0 of 400 without it.
|
|
53
|
+
'-c',
|
|
54
|
+
'maintenance.auto=false',
|
|
50
55
|
'commit',
|
|
51
56
|
'--quiet',
|
|
52
57
|
'-m',
|