-
Notifications
You must be signed in to change notification settings - Fork 35
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Missing agent credentials should be clean non-retryable rollout errors
area:diagnosticsIssue / PR lives primarily in the "diagnostics" subsystem.Issue / PR lives primarily in the "diagnostics" subsystem.area:rolloutIssue / PR lives primarily in the "rollout" subsystem.Issue / PR lives primarily in the "rollout" subsystem.bugSomething isn't workingSomething isn't workingP1Important debt — must fix soon, but does not block the current release.Important debt — must fix soon, but does not block the current release.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.#917 In benchflow-ai/benchflow;ProgramBench YAML eval should fail cleanly when generated tasks are missing
area:evalIssue / PR lives primarily in the "eval" subsystem.Issue / PR lives primarily in the "eval" subsystem.bugSomething isn't workingSomething isn't workingP1Important debt — must fix soon, but does not block the current release.Important debt — must fix soon, but does not block the current release.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.#915 In benchflow-ai/benchflow;bench eval create should expose --max-retries alias
area:evalIssue / PR lives primarily in the "eval" subsystem.Issue / PR lives primarily in the "eval" subsystem.bugSomething isn't workingSomething isn't workingP2Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.#916 In benchflow-ai/benchflow;skill-eval exact-match verifier: word-boundary regex can't match ground truths ending in a non-word char (e.g. ')')
area:evalIssue / PR lives primarily in the "eval" subsystem.Issue / PR lives primarily in the "eval" subsystem.bugSomething isn't workingSomething isn't workingP2Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.#897 In benchflow-ai/benchflow;Concurrent rollouts race on os.environ: pi-acp launcher and openclaw shim mutate process env per rollout
area:sandboxIssue / PR lives primarily in the "sandbox" subsystem.Issue / PR lives primarily in the "sandbox" subsystem.bugSomething isn't workingSomething isn't workingP2Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.questionFurther information is requestedFurther information is requestedstatus:blockedWaiting on external dependency. Add a comment explaining why.Waiting on external dependency. Add a comment explaining why.Status: Open.Diagnostic dataclasses use bare-str fields where Literal/enum belongs; reason constant duplicated across modules
area:diagnosticsIssue / PR lives primarily in the "diagnostics" subsystem.Issue / PR lives primarily in the "diagnostics" subsystem.enhancementNew feature or requestNew feature or requestP2Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.result.json schema bloat: top-level/agent_result duplication and started_at/finished_at not ISO 8601
area:rolloutIssue / PR lives primarily in the "rollout" subsystem.Issue / PR lives primarily in the "rollout" subsystem.enhancementNew feature or requestNew feature or requestP2Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.Anti-pattern / type safety / docs precision / minor schema drift / non-deterministic but contained.reviewingFix PR open and awaiting reviewFix PR open and awaiting reviewstatus:in-progressHas assignee or linked draft PR.Has assignee or linked draft PR.Status: Open.