Skip to content

🐛 bug: reviewer agent has mysteriously inconsistent configuration for inference #14678

Closed

Description

@MikeSpreitzer

What happened?

I use the hive for FMA, dashboard at https://hosted-llm-d-incubation-llm-d-fast-m-yfzz.apps.fmaas-vllm-d.fmaas.res.ibm.com/ . ACMM level 2. In the dashboard's overall configuration, I configured it to use an IBM-internal LiteLLM gateway. Weeks ago, when ACMM level 2 did not include the reviewer agent . Today I find that the scanner, quality, and guide agents are indeed using that. However, I find that the reviewer agent ---recently introduced by (I don't know what) --- is configured to use copilot.

Expected behavior

I expected the reviewer agent to use the same inference configuration as my other agents.

Reproduction steps

Outlined above, to the degree that I know them.

Environment

  • Branch/version: v5.186.4-439-g551ffc34f
  • Deployment method: Hive Hub
  • Operating system or Kubernetes version: unknown
  • Relevant configuration (redact secrets): ?

Logs or screenshots

Here is some of the reviewer agent's configuration:

Image

Additional context

Activity

  1. added
    help wantedDenotes an issue that needs help from a contributor. Must meet "help wanted" guidelines.
    on Oct 27, 2026
  2. MikeSpreitzer commented on Oct 27, 2026

    @MikeSpreitzer
    ContributorAuthor
  3. added
    needs-triageIndicates an issue or PR lacks a `triage/foo` label and requires one.
    on Oct 27, 2026
  4. hivecommons-hive commented on Oct 27, 2026

    @hivecommons-hive
    Contributor

    Thanks — this hive only works issues from OWNER, MEMBER, COLLABORATOR automatically. A maintainer can admit this one by adding the label triage/accepted (configured in issue_filter.reporter_trust.untrusted_require_labels). Until then the hive will not claim, label, or open PRs for it. See https://github.com/hivecommons/hive/blob/HEAD/GOVERNANCE.md#reporter-trust-and-escalation for what these terms mean and how to become a trusted reporter.

  5. added
    stage/010-actionableTriaged; eligible for the hive to pick up
    and removed
    needs-triageIndicates an issue or PR lacks a `triage/foo` label and requires one.
    on Oct 27, 2026
  6. hivecommons-hive commented on Oct 27, 2026

    @hivecommons-hive
    Contributor

    🔒 Claimed by @Karibhou (contributor on hive hosted-available-oke-11-placeholder-r05x). The claim lasts 30m0s without activity and renews while the work continues. Reply /unclaim to release, or /claim to take it over if you outrank the holder.

  7. hivecommons-hive commented on Oct 27, 2026

    @hivecommons-hive
    Contributor

    🔓 Claim by @Karibhou released (lease revoked).

  8. 76 remaining items

  9. kubestellar-prow commented on Nov 5, 2026

    @kubestellar-prow
    Contributor

    @MikeSpreitzer: Reopened this issue.

    Details

    In response to this:

    /reopen

    No, scanner agent, you are confused about the version of hive that is running for FMA. It is not v5.186.4-677-g4ca1d3fd2. In my previous reopen, on Nov 4, I reported that the version of hive running is crux/v0.2.0-449-g55318dc61 . Commit 55318dc is part of PR 16451 , which merged Nov 3.

    Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

  10. github-actions commented on Nov 5, 2026

    @github-actions
    Contributor

    Reopened at the request of @MikeSpreitzer, who reported this issue.If this was closed by a merged PR, first check whether the fix has reached you: it only takes effect after it ships in a tagged release and your deployment updates to it. If your running version already contains the fix and the problem persists, please add whatever you are still seeing (running version, logs, steps) so it is not closed the same way again. See #6762 for why this command exists.

  11. github-actions commented on Nov 5, 2026

    @github-actions
    Contributor

    @MikeSpreitzer this issue was closed by @hivecommons-hive[bot] as completed.

    If this was closed by a merged PR, the fix only takes effect once it ships in a tagged release and your deployment updates to it — check your running version against the fix before concluding the fix failed.

    If you are still seeing the problem, comment /reopen and it will be reopened for you — you do not need write access. Please add what you are still observing (running version, logs, steps) so it is not closed the same way again.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workinghelp wantedDenotes an issue that needs help from a contributor. Must meet "help wanted" guidelines.triage/acceptedIndicates an issue or PR is ready to be actively worked on.

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions