Skip to content

Pull requests: benchflow-ai/benchflow

New pull request New
15 Open 665 Closed
15 Open 665 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

Pin OpenCode harness to 1.17.20
#931 opened Jul 14, 2026 by bingran-you Collaborator Loading…
5
fix(result): normalize result artifact timestamps area:rollout Issue / PR lives primarily in the "rollout" subsystem. enhancement New feature or request P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#928 opened Jul 13, 2026 by bingran-you Collaborator Loading…
1
6
Preserve OpenHands context budget area:eval Issue / PR lives primarily in the "eval" subsystem. area:rollout Issue / PR lives primarily in the "rollout" subsystem. enhancement New feature or request P1 Important debt — must fix soon, but does not block the current release. status:in-progress Has assignee or linked draft PR.
#927 opened Jul 13, 2026 by Yiminnn Contributor • Draft
2
fix(eval): clean Linear issue UX paths area:diagnostics Issue / PR lives primarily in the "diagnostics" subsystem. area:eval Issue / PR lives primarily in the "eval" subsystem. area:rollout Issue / PR lives primarily in the "rollout" subsystem. bug Something isn't working P1 Important debt — must fix soon, but does not block the current release. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#918 opened Jul 11, 2026 by bingran-you Collaborator Loading…
3
7
chore(release): start 0.6.6 development review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#914 opened Jul 11, 2026 by bingran-you Collaborator Loading…
2
fix(skill-eval): match punctuated exact answers area:eval Issue / PR lives primarily in the "eval" subsystem. bug Something isn't working P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#900 opened Jul 7, 2026 by bingran-you Collaborator Loading…
1
6
fix(diagnostics): unify diagnostic serialization area:diagnostics Issue / PR lives primarily in the "diagnostics" subsystem. P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#895 opened Jul 6, 2026 by bingran-you Collaborator Loading…
1
15
fix(adapters): Toolathlon spawn-time token resolution + exit-code verifier scoring area:eval Issue / PR lives primarily in the "eval" subsystem. bug Something isn't working P1 Important debt — must fix soon, but does not block the current release. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#887 opened Jul 3, 2026 by bingran-you Collaborator Loading…
20
feat(cli): bench init onboarding wizard + bench doctor area:diagnostics Issue / PR lives primarily in the "diagnostics" subsystem. enhancement New feature or request P1 Important debt — must fix soon, but does not block the current release. review:changes-requested Author needs to push more commits before this can merge. status:blocked Waiting on external dependency. Add a comment explaining why.
#883 opened Jul 2, 2026 by Yiminnn Contributor Loading…
24
fix(litellm): retry transient upstream 5xx at the proxy area:eval Issue / PR lives primarily in the "eval" subsystem. bug Something isn't working P1 Important debt — must fix soon, but does not block the current release. review:changes-requested Author needs to push more commits before this can merge. status:blocked Waiting on external dependency. Add a comment explaining why.
#882 opened Jul 2, 2026 by Yiminnn Contributor Loading…
13
feat(multi-agent): native concurrent floor (bench eval run --agents) + bf.* trajectory tree + hosted medical benchmark area:eval Issue / PR lives primarily in the "eval" subsystem. enhancement New feature or request P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:changes-requested Author needs to push more commits before this can merge. status:blocked Waiting on external dependency. Add a comment explaining why.
#846 opened Jun 28, 2026 by Yiminnn Contributor • Draft
3 of 6 tasks
22
Merge main into the 0.7 line + land OSWorld vendored evaluator area:eval Issue / PR lives primarily in the "eval" subsystem. enhancement New feature or request P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:changes-requested Author needs to push more commits before this can merge. status:blocked Waiting on external dependency. Add a comment explaining why.
#827 opened Jun 24, 2026 by xdotli Member Loading…
17
fix(deps): require anyio>=4.10 so the daytona SDK imports area:sandbox Issue / PR lives primarily in the "sandbox" subsystem. bug Something isn't working P1 Important debt — must fix soon, but does not block the current release. review:pending PR is ready-for-review, no reviewer engagement yet. status:blocked Waiting on external dependency. Add a comment explaining why.
#826 opened Jun 24, 2026 by xdotli Member Loading…
19
chore(deps)!: 7-day dependency cooldown (uv exclude-newer + CI assert) enhancement New feature or request P2 Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained. review:pending PR is ready-for-review, no reviewer engagement yet. status:ready Triaged, unassigned, available to claim.
#788 opened Jun 15, 2026 by xdotli Member Loading…
42
feat(sandbox): Enforce network_mode allowlist on docker area:sandbox Issue / PR lives primarily in the "sandbox" subsystem. enhancement New feature or request P1 Important debt — must fix soon, but does not block the current release. review:changes-requested Author needs to push more commits before this can merge. status:blocked Waiting on external dependency. Add a comment explaining why.
#785 opened Jun 15, 2026 by Yiminnn Contributor Loading…
48
ProTip! no:milestone will show everything without a milestone.