Skip to content

Organization-managed GPT models do not defer MCP tools despite Responses API and toolSearch enabled #5481

Backlog

Description

@samuelmasuy

Summary

Organization-managed GPT models load all MCP tool definitions upfront, even when tool search is enabled and the model uses the Responses API.

The same underlying model defers tools when accessed through GitHub’s hosted offering or a directly configured external provider using Responses.

This becomes expensive with large tool definitions: a separate organization-managed Sol test consumed 236,905 actual input tokens for a simple “Reply OK” prompt that required no tools.

Environment

  • Copilot CLI 1.0.110, macOS arm64.
  • Custom model configured centrally through GitHub organization settings, not local BYOK.
  • Selected model: <org>/<key-name>/gpt-6-luna.
  • Organization configuration:
    • Responses API
    • Tool calling, Streaming, Vision and Thinking enabled.
  • CLI setting: "toolSearch": true.
  • MCP server setting: "deferTools": "auto".

Reproduction

  1. Configure an organization-managed GPT model using Responses.
  2. Connect enough MCP tools to exceed the tool-search threshold. Our test used 48 synthetic MCP tools.
  3. Start a fresh interactive CLI conversation and select the organization-managed model.
  4. Ask it to call one known synthetic read-only tool.
  5. Inspect the turn tool surface resolved diagnostic.
  6. Repeat with hosted and directly configured models.

Results

Same tool inventory and underlying GPT‑6 Luna model:

Connection API Total tools Deferred tools
Organization-managed Responses 49 0
GitHub-hosted Responses 49 49
Direct external Gateway Responses 49 49

The total includes one native function. All three cases successfully called the requested tool and returned its result.

The organization-managed case reports:

{
  "tool_search_enabled": true,
  "model_tool_calls_allowed": true,
  "opted_out": false,
  "client_path": false,
  "builtin_path": false,
  "generic_path": false,
  "deferred_tool_count": 0
}

Expected behavior / question

Organization-managed models should support on-demand tool loading where the model and endpoint support it, or clearly explain why tool search is unavailable despite being enabled.

Could the organization-qualified model ID or catalog family: "custom" be preventing selection of the Responses tool-search path? Is there a supported way for an organization administrator to enable this capability?

Related

Activity

  1. added
    area:enterpriseGitHub Enterprise (GHE/GHES) support, org policies, and enterprise settings
    area:mcpMCP server configuration, discovery, connectivity, OAuth, policy, and registry
    area:modelsModel selection, availability, switching, rate limits, and model-specific behavior
    and removed on Nov 17, 2026
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

    area:enterpriseGitHub Enterprise (GHE/GHES) support, org policies, and enterprise settingsarea:mcpMCP server configuration, discovery, connectivity, OAuth, policy, and registryarea:modelsModel selection, availability, switching, rate limits, and model-specific behavior

    Type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions