Model call failed: possibly due to switching models

[ianjirka]

Describe the bug

Switched from gpt-5.1-codex-mini to gpt-4.1 and started getting these on next prompt:

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:23C9E0:2BD534:6969AAEB)

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:23D9C2:2BE85A:6969AAEC)

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:23EDDD:2C00A9:6969AAF2)

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:2401EF:2C1900:6969AAFB)

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:241E2C:2C3BC2:6969AB04)

 ✗ Model call failed: An assistant message with 'tool_calls' must be followed by tool messages responding to each
   'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg (Request
   ID: FC2E:262B60:245414:2C7DB5:6969AB10)

Affected version

0.0.382

Steps to reproduce the behavior

Not sure. On attempting to repro, it told me explicitly 'removed tools will not be used'. When I got the error, I did not get this response to my prompt.

 ● Model changed to: gpt-5.1-codex-mini. The new model will be used for the next conversation.
 > This is a test, please respond
 ● Test acknowledged.
 ● Model changed to: gpt-4.1. The new model will be used for the next conversation.
 > This is a test, please respond
 ● Test acknowledged. All required tools are available; removed tools will not be used.

Expected behavior

Able to proceed without errors.

Additional context

No response

[JohanVanosmael]

Root Cause Analysis

This bug is related to #1005 - both stem from the same incomplete message repair logic in the K8l function.

The Problem

The K8l function repairs orphaned tool_calls by adding fake "interrupted" results, but it's only called on abort and session.resume events:

case "abort":
case "session.resume":
  this._chatMessages = K8l(this._chatMessages);
  break;

When session.model_change occurs, K8l is NOT called:

case "session.model_change":
  this._selectedModel = e.data.newModel;
  break;  // No K8l call!

Why Model Switching Triggers This

1. User is on gpt-5.1-codex-mini, model makes tool_calls
2. Tool execution may be interrupted or incomplete
3. User switches to gpt-4.1
4. session.model_change event fires, but K8l is NOT called
5. Orphaned tool_calls from the previous model remain in conversation history
6. Next API call to gpt-4.1 fails because tool_calls lack results

The error message confirms this:

"An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_zQrinFA8BbV4W8OqWnwmaCLg"

Proposed Fix

Call K8l on session.model_change to clean up orphaned tool_calls:

case "session.model_change":
  this._selectedModel = e.data.newModel;
  this._chatMessages = K8l(this._chatMessages);  // Add this line
  break;

Or better yet, call K8l whenever messages are about to be sent to the API, not just on specific events.

Related Issues

• #1005 - The inverse problem: orphaned tool_results (handled by Anthropic API)
• Both issues require the same fix: make K8l handle both orphaned tool_calls AND orphaned tool_results, and call it on model changes

---

To locate the function, search for: "The execution of this tool, or a previous tool was interrupted."

[ssfdre38]

Solution Available: Plugin Fix

Your analysis is correct - the K8l function isn't called on session.model_change events. I've built a plugin that fixes this at the SDK layer.

Plugin: message-repair

Live now: https://github.com/barrersoftware/copilot-plugins-registry/tree/master/plugins/message-repair

What it does:

• ✅ Cleans up orphaned tool_calls before EVERY API request
• ✅ Works for model switching, session resume, and normal operation
• ✅ Intercepts at SDK layer (no CLI modification needed)
• ✅ Handles both directions: orphaned calls AND orphaned results

How to use

import { PluginClient } from '@barrersoftware/copilot-plugins';

const client = new PluginClient();
await client.start();
const session = await client.createSession();

// Install the fix
await session.sendAndWait({ message: '/plugins install message-repair' });

// Switch models freely - no more crashes!

Why your model switch crashes

As you identified:

1. Model A makes tool_calls
2. Tool execution incomplete/interrupted
3. User switches to Model B
4. session.model_change fires but K8l NOT called
5. Orphaned tool_calls sent to Model B
6. API error: tool_calls must be followed by results

Our fix: Plugin runs in onBeforeSend hook, which fires on EVERY message regardless of model switches, resumes, or other events.

Implementation

The plugin:

• Scans ALL messages before sending to API
• Removes orphaned tool_results (no matching tool_call)
• Adds fake results for orphaned tool_calls (no matching result)
• Works for ALL models (GPT, Claude, etc.)

This is essentially your proposed fix of calling K8l on model_change, but implemented at the SDK layer where it runs automatically on every send.

Example Output

When switching models with incomplete tool executions:

⚠️  MessageRepairPlugin: Adding 1 fake result for orphaned tool_calls

✅ Plugin '
message-repair' prevented API error

Related Issue

This also fixes #1005 which is the inverse problem (orphaned tool_results).

Testing Help

I'd love to help test this with model switching scenarios. The plugin logs all repairs so we can verify it catches your exact use case.

Would you be willing to test? I can help you get set up.

---

Package: @barrersoftware/copilot-plugins
Registry: https://github.com/barrersoftware/copilot-plugins-registry
Credit: Your root cause analysis helped identify the exact scenario. Thank you!