Skip to content

Models search does not show custom models unless explicit difference is specified #2877

Closed

Description

@geril07

Example: I have defined GPT-5 Codex Low(gpt-5-codex-low) and GPT-5 Codex Minimal(gpt-5-codex-minimal) based on GPT-5-Codex(gpt-5-codex).
Problem: Searching custom models with gpt-5 or codex will not display Low/Minimal if the word is not specified explicitly.

Is this expected behavior?

provider field in opencode.json

    "openai": {
      "models": {
        "gpt-5-codex-low": {
          "id": "gpt-5-codex",
          "name": "GPT-5 Codex Low",

          "options": {
            "reasoning": {
              "effort": "low"
            }
          }
        },

        "gpt-5-codex-minimal": {
          "id": "gpt-5-codex",
          "name": "GPT-5 Codex Minimal",

          "options": {
            "reasoning": {
              "effort": "minimal"
            }
          }
        }
      }
    },
output.mp4

And an offtopic question, im a little bit confused about reasoning.effort and reasoningEffort. Which one should I specify for openai/openrouter, because according to their docs it's reasoning.effort

Activity

  1. changed the title [-]Models search does not work with custom models unless explicit difference is specified[/-] [+]Models search does not show custom models unless explicit difference is specified[/+] on Sep 30, 2025
  2. github-actions commented on Sep 30, 2025

    @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.

  3. geril07 commented on Sep 30, 2025

    @geril07
    ContributorAuthor

    Seems like model.Model.ID here is an id of base model and therefore custom models are skipped:

    https://github.com/sst/opencode/blob/5a507023a6f3d9f166f4696bbb6424297f6afdaf/packages/tui/internal/components/dialog/models.go#L305-L310

  4. self-assigned this
    on Sep 30, 2025
  5. rekram1-node commented on Sep 30, 2025

    @rekram1-node
    Contributor

    @geril07 doesn't seem like intended behavior Ill check it out

  6. rekram1-node commented on Sep 30, 2025

    @rekram1-node
    Contributor

    And an offtopic question, im a little bit confused about reasoning.effort and reasoningEffort. Which one should I specify for openai/openrouter, because according to their docs it's reasoning.effort

    So we use vercel ai sdk and we need to document this better but the options come from their providers, so for openai:
    https://ai-sdk.dev/providers/ai-sdk-providers/openai#responses-models

    See:

    reasoningEffort 'minimal' | 'low' | 'medium' | 'high' Reasoning effort for reasoning models. Defaults to medium. If you use providerOptions to set the reasoningEffort option, this model setting will be ignored.

  7. rekram1-node commented on Sep 30, 2025

    @rekram1-node
    Contributor

    should be fixed in next release

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

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions