Skip to content

Pull requests: openclaw/shellbench

New pull request New
11 Open 41 Closed
11 Open 41 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(eval): trial log dirs are world-writable merge-risk: 🚨 availability 🚨 Merging this PR could cause crashes, hangs, restart loops, stalls, or process outages. merge-risk: 🚨 compatibility 🚨 Merging this PR could break existing users, config, migrations, defaults, or upgrades. P1 Urgent regression or broken agent/channel workflow affecting real users now. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask.
#67 opened Aug 16, 2026 by SebTardif Loading…
2 tasks done
2
fix(eval): time out hung docker kill and compose down merge-risk: 🚨 availability 🚨 Merging this PR could cause crashes, hangs, restart loops, stalls, or process outages. P2 Normal priority bug or improvement with limited blast radius. proof: sufficient Contributor real behavior proof is sufficient. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.
#66 opened Aug 15, 2026 by SebTardif Loading…
2 tasks done
6
fix(native-eval): reject invalid harness runs merge-risk: 🚨 availability 🚨 Merging this PR could cause crashes, hangs, restart loops, stalls, or process outages. merge-risk: 🚨 compatibility 🚨 Merging this PR could break existing users, config, migrations, defaults, or upgrades. P1 Urgent regression or broken agent/channel workflow affecting real users now. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#64 opened Jul 30, 2026 by vincentkoc Member • Draft
2 tasks done
1
1
fix(native-eval): benchmark genuine OpenClaw code mode merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. P2 Normal priority bug or improvement with limited blast radius. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#62 opened Jul 29, 2026 by vincentkoc Member Loading…
5 of 6 tasks
1
2
feat(native-eval): export tool discovery telemetry merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. P2 Normal priority bug or improvement with limited blast radius. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#60 opened Jul 29, 2026 by vincentkoc Member Loading…
3 tasks done
1
1
feat(native-eval): support OpenClaw candidate packages merge-risk: 🚨 security-boundary 🚨 Merging this PR could weaken sandboxing, authorization, credentials, or sensitive data. P2 Normal priority bug or improvement with limited blast radius. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#57 opened Jul 29, 2026 by vincentkoc Member Loading…
2 tasks done
1
2
fix(native-eval): rebootstrap replacement leases merge-risk: 🚨 compatibility 🚨 Merging this PR could break existing users, config, migrations, defaults, or upgrades. P2 Normal priority bug or improvement with limited blast radius. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.
#58 opened Jul 29, 2026 by vincentkoc Member Loading…
5 tasks done
1
1
fix: apply native reasoning effort to harnesses merge-risk: 🚨 compatibility 🚨 Merging this PR could break existing users, config, migrations, defaults, or upgrades. P1 Urgent regression or broken agent/channel workflow affecting real users now. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#54 opened Jul 29, 2026 by vincentkoc Member Loading…
4 tasks done
1
1
fix: accept Claude native trajectories merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. P2 Normal priority bug or improvement with limited blast radius. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.
#52 opened Jul 29, 2026 by vincentkoc Member Loading…
3 tasks done
1
feat(eval): add task analysis and trace publishing merge-risk: 🚨 compatibility 🚨 Merging this PR could break existing users, config, migrations, defaults, or upgrades. merge-risk: 🚨 security-boundary 🚨 Merging this PR could weaken sandboxing, authorization, credentials, or sensitive data. P1 Urgent regression or broken agent/channel workflow affecting real users now. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action.
#48 opened Jul 29, 2026 by vincentkoc Member • Draft
6 tasks done
1
feat: integrate spatio-temporal violation dynamics and align with upstream fixes merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. P2 Normal priority bug or improvement with limited blast radius. rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask.
#31 opened Jun 2, 2026 by HaoLi111 Contributor Loading…
13
ProTip! Adding no:label will show everything without a label.