Skip to content

Pull requests: UKGovernmentBEIS/inspect_ai

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Add environment parameter to preserve env vars in eval-retry (#3312)
#3344 opened Feb 26, 2026 by evcyen Loading…
2 of 5 tasks
feat #3306: add batch support for Grok models
#3340 opened Feb 26, 2026 by jashvira Loading…
4 of 5 tasks
feat: Add progress logging during eval_set resume scanning
#3339 opened Feb 26, 2026 by QuantumLove Loading…
3 tasks done
View: Improve transcript event styling
#3330 opened Feb 25, 2026 by revmischa Loading…
5 tasks
perf: S3 readahead caching and batched validate/map
#3329 opened Feb 25, 2026 by rasmusfaber Loading…
1 of 5 tasks
refactor: extract load_json_exclude streaming utility
#3328 opened Feb 25, 2026 by rasmusfaber Loading…
1 of 5 tasks
Fix Inspect View showing stale sample data
#3325 opened Feb 25, 2026 by rasmusfaber Loading…
1 of 5 tasks
Presigned URL support for S3 log files
#3324 opened Feb 25, 2026 by rasmusfaber Loading…
3 of 5 tasks
Rescoring an evaluation with a new metric
#3310 opened Feb 24, 2026 by Mamiglia Loading…
1 task done
make changes to use versionId S3 URL query param
#3284 opened Feb 21, 2026 by anthonyduong9 Draft
1 of 5 tasks
fix: async read when reusing samples in eval
#3283 opened Feb 20, 2026 by ransomr Draft
1 of 5 tasks
Enrich retry log messages with task/sample/model context
#3240 opened Feb 14, 2026 by sjawhar Loading…
Fix stale state read in logsSlice after syncLogs
#3212 opened Feb 11, 2026 by rasmusfaber Loading…
1 task done
Bulk download
#3196 opened Feb 9, 2026 by obadakhalili Loading…
1 of 5 tasks
Adds math scorer
#3161 opened Feb 3, 2026 by NathanHB Loading…
5 tasks
Handle wrong PyPI detection better
#3095 opened Jan 22, 2026 by rasmusfaber Draft
1 of 5 tasks
Add tools to human_cli
#3053 opened Jan 13, 2026 by tadamcz Loading…
1 of 5 tasks
Nathan create result yaml
#3049 opened Jan 12, 2026 by NathanHB Draft
5 tasks
Rename AZUREAI_OPENAI_BASE_URL to AZUREAI_BASE_URL in Docs
#3042 opened Jan 9, 2026 by lon-tierney Loading…
2 of 5 tasks
Add convert_errored_samples_to_incorrect function (#2914)
#2994 opened Dec 30, 2025 by antnewman Loading…
5 tasks
Fix log file corruption on disk full errors (#2949)
#2993 opened Dec 30, 2025 by antnewman Loading…
5 tasks
WIP
#2890 opened Dec 9, 2025 by epatey Draft
5 tasks
(WIP) adding apply_patch to react agent
#2791 opened Nov 20, 2025 by vncntt Draft
1 of 5 tasks
PoC test for exec not killing process on timeout
#2778 opened Nov 18, 2025 by art-dsit Draft
1 of 5 tasks
ProTip! Filter pull requests by the default branch with base:main.