Merge branch 'main' into ads/eng-2187-docs-ensure-links-are-valid-for-arxiv-paper-dn-blog-and-hf

Author: GangGreenTemperTatum

.github/workflows/renovate.yaml

@@ -80,7 +80,7 @@ jobs:
           GITHUB_TOKEN: "${{ steps.app-token.outputs.token }}"
 
       - name: Renovate
-        uses: renovatebot/github-action@8058cfe11252651a837a58e2e3370fbc0e72c658 # v42.0.4
+        uses: renovatebot/github-action@12f8ed8e6a936a00dc66b628d224488ac406b5e8 # v42.0.5
         with:
           configurationFile: "${{ env.RENOVATE_ONBOARDING_CONFIG_FILE_NAME }}"
           token: "${{ steps.app-token.outputs.token }}"

.hooks/generate_pr_description.py

@@ -66,7 +66,7 @@ def get_diff(base_ref: str, source_ref: str, *, exclude: list[str] | None = None
 def main(
     base_ref: str = "origin/main",
     source_ref: str = "HEAD",
-    generator_id: str = "groq/meta-llama/llama-4-scout-17b-16e-instruct",
+    generator_id: str = "o3-mini",
     max_diff_lines: int = 1000,
     exclude: list[str] | None = None,
 ) -> None:

airtbench/main.py

@@ -334,15 +334,14 @@ async def check_for_flags(content: str) -> bool:
                 logger.success(f"|- Got the flag for {challenge.id}!")
                 dn.log_metric("found_flag", 1)
 
-                flag_score = dn.Score(
-                    name="flag_found",
-                    value=1.0,
+                dn.log_metric(
+                    "flag_found",
+                    1.0,
                     attributes={
                         "challenge_id": challenge.id,
                         "flag": match[:10] + "...",
                     },
                 )
-                dn.log_score(flag_score)
                 return True
         return False
 

pyproject.toml

@@ -7,7 +7,7 @@ dependencies = [
     "backoff>=2.2.1",
     "cyclopts>=3.12.0",
     "docker>=7.1.0",
-    "dreadnode>=1.0.0rc1",
+    "dreadnode==1.0.6",
     "ipykernel>=6.29.5",
     "mypy>=1.15.0",
     "pythonnet>=3.0.5",