Skip to content

Pull requests: Kiln-AI/Kiln

New pull request New
42 Open 1,548 Closed
42 Open 1,548 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix Linux tray icon scaling
#1767 opened Sep 13, 2026 by krisnaparahita Loading…
3 tasks done
1
3
Give agents a house-controls check before they touch the web UI
#1766 opened Sep 12, 2026 by chiang-daniel Contributor Loading…
1 of 2 tasks
10
feat(compare): radar scale toggle, hideable usage axes, row renames
#1765 opened Sep 11, 2026 by tawnymanticore Collaborator Loading…
1 of 2 tasks
3
feat: run multi-turn synthetic eval inputs against synthetic worlds
#1761 opened Sep 9, 2026 by sfierro Contributor • Draft
2 tasks done
3
feat: add synthetic worlds for evals against replayable tool state
#1760 opened Sep 9, 2026 by sfierro Contributor • Draft
2 tasks done
2
feat: route GPT-5.4+ and GPT-6 Astra to /v1/responses and enable tools
#1757 opened Sep 8, 2026 by tawnymanticore Collaborator Loading…
2 tasks done
2
Git import: null project descriptions scan as blank instead of failing
#1752 opened Sep 3, 2026 by chiang-daniel Contributor Loading…
2 tasks done
2
Eval Builder V2: spec-driven evals with generated data, real traces, and calibrated judges
#1731 opened Aug 25, 2026 by chiang-daniel Contributor • Draft
2
Deterministic judges: missing nested fields score Fail instead of erroring
#1709 opened Aug 20, 2026 by chiang-daniel Contributor Loading…
4
Redesign example-picker tabs as DaisyUI boxed tabs
#1699 opened Aug 19, 2026 by scosman Collaborator Loading…
2 tasks done
1
[eb-v2 review] Code Tools: parameter validation, allowlist isolation, and wizard fixes
#1655 opened Aug 5, 2026 by chiang-daniel Contributor Loading…
16
[eb-v2 review] Git import: bind the trust prompt to the repo it was granted for — sign-off requested
#1654 opened Aug 5, 2026 by chiang-daniel Contributor Loading…
9
[eb-v2 review] Eval V2 core: sandbox, trace persistence, and datamodel guard fixes
#1652 opened Aug 5, 2026 by chiang-daniel Contributor Loading…
20
[eb-v2 review] Generate/SDG: load-failure handling and coordination notes
#1650 opened Aug 5, 2026 by chiang-daniel Contributor Loading…
11
Add per-score direction flag to eval output scores
#1622 opened Jul 23, 2026 by scosman Collaborator Loading…
2 tasks done
8
Release digest skill improvements
#1597 opened Jul 18, 2026 by sfierro Contributor Loading…
6
chore: replace together fork with official PyPI package
#1596 opened Jul 17, 2026 by leonardmq Collaborator Loading…
5
Eval V2: Code-eval scorer helpers + custom-typed metrics (re-landing of #1568)
#1592 opened Jul 17, 2026 by chiang-daniel Contributor Loading…
19
feat: Kiln assistant — auto mode, background eval jobs, and sub-agents (runtime, tabs UI, steer/stop)
#1561 opened Jul 10, 2026 by leonardmq Collaborator • Draft
30
feat: add dataset runs total and rating summary stats to dataset page
#1513 opened Jun 24, 2026 by Vismay299 Loading…
3
fix: handle process pool crashes in PDF conversion and event loop lock binding
#1512 opened Jun 24, 2026 by Vismay299 Loading…
6
feat: support configurable concurrency limits for evals and generation
#1511 opened Jun 24, 2026 by Vismay299 Loading…
1
8
feat: allow manual data entry/correction for task dataset
#1510 opened Jun 24, 2026 by Vismay299 Loading…
1
7
feat: allow filtering dataset by synthetic data topic tree
#1509 opened Jun 24, 2026 by Vismay299 Loading…
8
feat: show total run counts and add collapsible topics in web UI
#1506 opened Jun 23, 2026 by Vismay299 Loading…
6
ProTip! Mix and match filters to narrow down what you’re looking for.