-
Notifications
You must be signed in to change notification settings - Fork 53
Pull requests: benchflow-ai/benchflow
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(branch): composed snapshotting, stage-level branching, and bench eval ablate
#1046
opened Aug 20, 2026 by
JeremyJC67
Loading…
5 tasks done
docs(branch): RFC for composed environment snapshotting + rollout branching
#1045
opened Aug 20, 2026 by
JeremyJC67
Loading…
2 tasks done
fix(rollout): keep completed rollouts when publish-path execs time out
#1043
opened Aug 20, 2026 by
tulerfeng
Loading…
feat(results): preserve structured failure diagnostics
#1038
opened Aug 19, 2026 by
yangziao56
•
Draft
Add --publish-bucket and --eval-results-* flags to bench eval run
#1035
opened Aug 17, 2026 by
NathanHB
Loading…
feat(viewer): reviewer-grade trajectory pages, multi-run browsing, and hf:// dataset sources
#1034
opened Aug 17, 2026 by
ljr145733
Loading…
Flag chat-only completions (zero tool calls with model output) as a diagnostic
#1025
opened Aug 16, 2026 by
ljr145733
Loading…
Refresh BenchFlow docs with a local-first quickstart
#1009
opened Aug 16, 2026 by
ElegantLin
Contributor
•
Draft
test(skills): align self-gen with catalog cleanup
#1005
opened Aug 15, 2026 by
bingran-you
Collaborator
Loading…
feat(viewer): render run traces from a payload with a JS renderer
#987
opened Aug 14, 2026 by
Polarisyjr
Loading…
fix(litellm): provision Vertex sandbox runtime
#985
opened Aug 14, 2026 by
kywch
Collaborator
Loading…
feat(trajectories): canonical trace IR with ACP and ATIF converters
#984
opened Aug 13, 2026 by
Galius5136
Loading…
12 of 13 tasks
fix(review): separate review and verifier rubric lifecycles
#981
opened Aug 13, 2026 by
bingran-you
Collaborator
Loading…
fix(litellm): bind host proxy to 0.0.0.0 when the docker gateway is unbindable
#947
opened Aug 6, 2026 by
manunicholasjacob
Loading…
fix(sandbox): resolve the no-web loopback endpoint per adapter
#940
opened Jul 30, 2026 by
bingran-you
Collaborator
Loading…
fix(sandbox): stop with-skill builds poisoning no-skill rollouts
#938
opened Jul 28, 2026 by
bingran-you
Collaborator
Loading…
fix(acp): preserve streamed usage on timeout
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:blocked
Waiting on external dependency. Add a comment explaining why.
#934
opened Jul 22, 2026 by
bingran-you
Collaborator
Loading…
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…
Previous Next
ProTip!
Adding no:label will show everything without a label.