Skip to content

feedback not working + regression in intelligence instruction following and completeness of work #40591

Open

Description

@sorcrr-dev

What version of the Codex App are you using (From “About Codex” dialog)?

Version 26.818.61809

What subscription do you have?

pro 200

What platform is your computer?

mac os

What issue are you seeing?

regression in intelligence. instruction following and then making up results that it didnt implement. /feedback not working.

What steps can reproduce the bug?

tell agent to attach to safari - attached to codex in app instead. this is relevant because we had planned it in that way. asked for implementing a very simple visibility for a component change. without making the change confirmed that its been implemented.

What is the expected behavior?

No response

Additional information

No response

Activity

  1. added
    appIssues related to the Codex desktop app
    on Aug 25, 2026
  2. nos1609 commented on Aug 25, 2026

    @nos1609

    Same here, looks like the model has become dumb, forgot about mcps, tools etc, and feedback fails with upload

  3. sorcrr-dev commented on Aug 25, 2026

    @sorcrr-dev
    Author

    yes serious regression and a lot of false positives - ive had it lie about things 3 times in the last couple of hours. this happens sometimes but the frequency of this issue means something is definitely off - example below -

    The observable Chrome session is open at /jobs/manage, ready to continue the hiring E2E.
    5:27

    i dont see thre chrome tab?
    5:30

    Working for 1m 10s
    The controlled Chrome tab still exists, but it may be in a background Chrome window or extension-managed session. I’m bringing that exact /jobs/manage tab to the foreground now and will confirm its visible URL.

    Bring the Sorcrr Chrome tab forward

    The previous controlled tab has been closed—the saved tab handle no longer resolves. Chrome itself is still connected, so I’m opening a fresh visible Chrome tab at the shipped Jobs page rather than pretending the old one is present.

  4. nos1609 commented on Aug 25, 2026

    @nos1609

    Follow-up with objective tool-surface evidence from Windows ARM64 on Desktop release 26.818.61809.

    The observed degradation is not only subjective model behavior. In the affected task, generic MCP connector tools remained available and GitHub calls completed successfully, but the model-visible manifest omitted multiple Codex host tools, including automation, navigation, workspace-dependency, plugin-management, and thread-management tools. No callable tool_search was exposed either.

    Detailed sanitized manifest evidence:
    #29128 (comment)

    A separate read-only audit also found that long task history remained complete in storage and app-server pagination while the Desktop renderer hydrated only a small recent subset. That distinct UI defect is tracked in #40601.

    This narrows the apparent "intelligence" regression into at least two concrete client/runtime failures:

    1. selective host-tool provisioning failure, while generic MCP still works;
    2. incomplete renderer hydration of long paginated tasks.

    Those failures can make the agent appear to forget available operations or prior work even when the underlying rollout is intact.

    Privacy: no prompts, conversation content, local paths, account data, hostnames, repository names, or raw logs are included.

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

    appIssues related to the Codex desktop appbrowserbugSomething isn't workingcomputer-usemodel-behaviorIssues related to behaviors exhibited by the model

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions