lastlight-evals 0.7.30 → 0.9.0
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/README.md +38 -1
- package/datasets/dependency-merge/README.md +69 -0
- package/datasets/dependency-merge/instances.json +168 -0
- package/datasets/dependency-merge/tier.json +5 -0
- package/datasets/fix/README.md +57 -0
- package/datasets/fix/instances.json +229 -0
- package/datasets/fix/repos/fix__env-mismatch-node-version/.github/workflows/ci.yml +15 -0
- package/datasets/fix/repos/fix__env-mismatch-node-version/README.md +3 -0
- package/datasets/fix/repos/fix__env-mismatch-node-version/package.json +15 -0
- package/datasets/fix/repos/fix__env-mismatch-node-version/src/group.js +4 -0
- package/datasets/fix/repos/fix__env-mismatch-node-version/test/group.test.js +9 -0
- package/datasets/fix/repos/fix__flaky-promoted/.github/workflows/ci.yml +15 -0
- package/datasets/fix/repos/fix__flaky-promoted/README.md +3 -0
- package/datasets/fix/repos/fix__flaky-promoted/package.json +12 -0
- package/datasets/fix/repos/fix__flaky-promoted/src/poll.js +9 -0
- package/datasets/fix/repos/fix__flaky-promoted/test/poll.test.js +8 -0
- package/datasets/fix/repos/fix__flaky-timeout/.github/workflows/ci.yml +15 -0
- package/datasets/fix/repos/fix__flaky-timeout/README.md +3 -0
- package/datasets/fix/repos/fix__flaky-timeout/package.json +12 -0
- package/datasets/fix/repos/fix__flaky-timeout/src/poll.js +9 -0
- package/datasets/fix/repos/fix__flaky-timeout/test/poll.test.js +8 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/.github/workflows/ci.yml +28 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/README.md +3 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/e2e/smoke.test.js +10 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/package.json +12 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/src/retry.js +13 -0
- package/datasets/fix/repos/fix__infra-dependent-e2e/test/retry.test.js +8 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/.github/workflows/ci.yml +15 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/README.md +3 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/package.json +15 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/src/slug.js +6 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/test/slug.test.js +7 -0
- package/datasets/fix/repos/fix__reproducible-api-removal/vendor/tiny-case/index.js +4 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/.github/workflows/ci.yml +15 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/README.md +3 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/package.json +12 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/src/format.js +6 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/src/rates.js +6 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/test/format.test.js +7 -0
- package/datasets/fix/repos/fix__upstream-broken-base-red/test/rates.test.js +7 -0
- package/datasets/fix/repos-head/fix__env-mismatch-node-version/package.json +15 -0
- package/datasets/fix/repos-head/fix__flaky-promoted/package.json +12 -0
- package/datasets/fix/repos-head/fix__flaky-timeout/package.json +12 -0
- package/datasets/fix/repos-head/fix__infra-dependent-e2e/package.json +12 -0
- package/datasets/fix/repos-head/fix__reproducible-api-removal/package.json +15 -0
- package/datasets/fix/repos-head/fix__reproducible-api-removal/vendor/tiny-case/index.js +4 -0
- package/datasets/fix/repos-head/fix__upstream-broken-base-red/package.json +12 -0
- package/datasets/fix/tier.json +5 -0
- package/datasets/repo-config/instances.json +35 -0
- package/datasets/repo-config/lastlight/repoconfig__prompt-override/agent-context/repo-notes.md +9 -0
- package/datasets/repo-config/lastlight/repoconfig__prompt-override/lastlight.yml +22 -0
- package/datasets/repo-config/lastlight/repoconfig__prompt-override/workflows/prompts/answer.md +27 -0
- package/datasets/repo-config/tier.json +5 -0
- package/dist/fake-github.js +228 -5
- package/dist/fake-github.js.map +1 -1
- package/dist/grade.js +90 -1
- package/dist/grade.js.map +1 -1
- package/dist/mechanism.test.js +420 -2
- package/dist/mechanism.test.js.map +1 -1
- package/dist/pr-context.js +162 -0
- package/dist/pr-context.js.map +1 -0
- package/dist/repo-config.js +141 -0
- package/dist/repo-config.js.map +1 -0
- package/dist/run-instance.js +134 -7
- package/dist/run-instance.js.map +1 -1
- package/dist/run.js +8 -0
- package/dist/run.js.map +1 -1
- package/dist/schema.js +0 -13
- package/dist/schema.js.map +1 -1
- package/dist/seed.js +7 -0
- package/dist/seed.js.map +1 -1
- package/package.json +4 -4
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "lastlight-evals",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.9.0",
|
|
4
4
|
"description": "Eval harness for Last Light workflows — drives the real production workflows against a mocked GitHub and grades deterministically (SWE-bench compatible).",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
|
@@ -31,10 +31,10 @@
|
|
|
31
31
|
"@clack/prompts": "^1.7.0",
|
|
32
32
|
"chalk": "^6.0.0",
|
|
33
33
|
"yaml": "^2.5.0",
|
|
34
|
-
"lastlight-core": "0.
|
|
34
|
+
"lastlight-core": "0.23.0"
|
|
35
35
|
},
|
|
36
36
|
"peerDependencies": {
|
|
37
|
-
"agentic-pi": "^0.
|
|
37
|
+
"agentic-pi": "^0.4.0"
|
|
38
38
|
},
|
|
39
39
|
"devDependencies": {
|
|
40
40
|
"@types/node": "^26.1.1",
|
|
@@ -42,7 +42,7 @@
|
|
|
42
42
|
"typescript": "^5.7.0",
|
|
43
43
|
"vitest": "^4.1.10",
|
|
44
44
|
"wrangler": "^4.114.0",
|
|
45
|
-
"agentic-pi": "0.
|
|
45
|
+
"agentic-pi": "0.4.0"
|
|
46
46
|
},
|
|
47
47
|
"scripts": {
|
|
48
48
|
"build": "npm run build:harness && npm run build:dashboard",
|