Skip to content

Keep getting "Item with id 'rs_xxxxx' not found. Items are not persisted when 'store' is set to false" and out of context #7724

Closed

Description

@avesed

Description

Keep getting 2 errors when using GPT models. Both login (OpenAI Plus) or using api (from reverse CLI).

  1. "Item with id 'rs_xxxxx' not found. Items are not persisted when 'store' is set to false."
  2. out of context

Plugins

none

OpenCode version

1.1.12

Steps to reproduce

  1. Use gpt-5.2-codex
  2. Normal use, after some work
  3. error shows

Screenshot and/or share link

Image Image

Operating System

Ubuntu 24.04 LTS

Terminal

opencode windows

Activity

  1. github-actions commented on Jan 11, 2026

    @github-actions
    Contributor

    This issue might be a duplicate of existing issues. Please check:

    Feel free to ignore if none of these address your specific case.

  2. avesed commented on Jan 11, 2026

    @avesed
    Author

    Adding

    "store": false
    

    fixes the first issue, but it is still hitting the context limit. I have to manually do /compact to continue.

  3. rekram1-node commented on Jan 11, 2026

    @rekram1-node
    Contributor

    @avesed can u do opencode export > session.json (this is a command to run in ur terminal and will output the session.json file) can u send me a file of a session that this happened in?

  4. avesed commented on Jan 11, 2026

    @avesed
    Author

    @avesed can u do opencode export > session.json (this is a command to run in ur terminal and will output the session.json file) can u send me a file of a session that this happened in?

    I upgraded to 1.1.13, so far (about an hour of use), haven't got any error. But on the other hand, after setting "store": false, it kinda burn though tokens, used about 20M tokens in 40min, in my normal workflow (which don't use this much).

  5. 280601922 commented on Jan 12, 2026

    @280601922

    @avesed can u do opencode export > session.json (this is a command to run in ur terminal and will output the session.json file) can u send me a file of a session that this happened in?你能做 opencode export > session.json (这是一个在您的终端中运行的命令,并将输出 session.json 文件)你能发给我一个发生这种情况的会话文件吗?多模型翻译对比

    I've encountered this issue as well. The attachment shows the problematic session using the gpt-5.2-codex model. I set store:false, but it didn't resolve the problem.

    Image

    session.json

  6. avesed commented on Jan 12, 2026

    @avesed
    Author

    @280601922 我的格式是这样的,加limit是因为有时候我会触发issue里的第2个报错,改完之后我确实不会有报错了,但是token用的非常快(尤其如果你用的是反代,直接登录还好一点),建议小心使用

    {
      "$schema": "https://opencode.ai/config.json",
      "provider": {
        "openai": {
          "options": {
            "baseURL": "",
            "apiKey": ""
          },
          "models": {
            "gpt-5.2-codex": {
              "options": {
                "store": false,
                "reasoningEffort": "xhigh",
                "textVerbosity": "medium",
                "reasoningSummary": "auto",
                "include": ["reasoning.encrypted_content"],
                "limit": {
                "context": 250000,
                "output": 65000
                }
              }
            }
          }
        }
      }
    }
    
  7. 280601922 commented on Jan 12, 2026

    @280601922

    @280601922 我的格式是这样的,加limit是因为有时候我会触发issue里的第2个报错,改完之后我确实不会有报错了,但是token用的非常快(尤其如果你用的是反代,直接登录还好一点),建议小心使用

    {
      "$schema": "https://opencode.ai/config.json",
      "provider": {
        "openai": {
          "options": {
            "baseURL": "",
            "apiKey": ""
          },
          "models": {
            "gpt-5.2-codex": {
              "options": {
                "store": false,
                "reasoningEffort": "xhigh",
                "textVerbosity": "medium",
                "reasoningSummary": "auto",
                "include": ["reasoning.encrypted_content"],
                "limit": {
                "context": 250000,
                "output": 65000
                }
              }
            }
          }
        }
      }
    }
    

    感谢, 我的opencode.json里的配置跟你的不太一样(有个variants的参数,我理解,是不是options参数是针对用的具体推理级别,额外要指定下? 另外我使用了oh-my-opencode不知道跟这个插件有没有关系

    Image
  8. avesed commented on Jan 13, 2026

    @avesed
    Author

    @280601922 这个我不太确定,因为我的opencode没有自己生成opencode.json,我是自己按doc写的~/.config/opencode/opencode.json

  9. arjun810 commented on Jan 13, 2026

    @arjun810
    Contributor

    Getting this frequently with codex via zen

  10. PSU3D0 commented on Jan 14, 2026

    @PSU3D0

    Getting this issue probably 50% of sessions - usually after 50-60 turns - with 5.2 Codex

  11. elijahdev0 commented on Jan 14, 2026

    @elijahdev0

    Getting this as well please someone mention if they found a fix

  12. rekram1-node commented on Jan 15, 2026

    @rekram1-node
    Contributor

    Should be fixed in next release.

    cc @elijahdev0

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

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions