OpenClaw + GitHub Copilot GPT-5.4 技术修复指南

OpenClaw + GitHub Copilot GPT-5.4 Technical Fix Guide

Date: 2026-03-07

Overview

This guide documents how to make github-copilot/gpt-5.4 work inside OpenClaw when the model already works in OpenCode but fails in OpenClaw.

The final solution requires both:

1. a config fix in ~/.openclaw/openclaw.json
2. a runtime patch in the installed OpenClaw bundle

This is necessary because the problem is not only model registration. It is also an OpenClaw transport-routing issue for GitHub Copilot Responses API traffic.

Symptoms

The following errors may appear during debugging:

Symptom 1: model rejected

github-copilot/gpt-5.4 ... not allowed

Symptom 2: IDE auth header missing

HTTP 400: bad request: missing Editor-Version header for IDE auth

Symptom 3: unsupported provider mode

No API provider registered for api: github-copilot

Symptom 4: wrong endpoint

HTTP 400: model "gpt-5.4" is not accessible via the /chat/completions endpoint

Symptom 5: gateway instability

gateway disconnected: closed | idle

Root Cause Analysis

There are four distinct problems.

1. Model config and allowlist mismatch

OpenClaw could see the provider, but github-copilot/gpt-5.4 was not fully wired into the active model config path used by the agent defaults.

2. Missing GitHub Copilot IDE headers

GitHub Copilot requires IDE-style headers for auth. OpenClaw was sending requests through a generic OpenAI-compatible path, so required headers were not included.

Required headers:

User-Agent: GitHubCopilotChat/0.35.0
Editor-Version: vscode/1.107.0
Editor-Plugin-Version: copilot-chat/0.35.0
Copilot-Integration-Id: vscode-chat

Without them, Copilot returns:

missing Editor-Version header for IDE auth

3. GPT-5.4 is not a Chat Completions model

gpt-5.4 must use the Responses API, not /chat/completions.

So this is wrong for gpt-5.4:

"api": "openai-completions"

This is required instead:

"api": "openai-responses"

4. OpenClaw transport routing only handled openai, not github-copilot

Even after changing gpt-5.4 to openai-responses, OpenClaw still fell back to the generic stream path because its embedded runner only activated the Responses transport for provider openai.

That caused OpenClaw to keep hitting /chat/completions for GitHub Copilot GPT-5.4.

Files Involved

Config file

~/.openclaw/openclaw.json

Installed OpenClaw runtime bundle

/home/water/.nvm/versions/node/v22.22.0/lib/node_modules/openclaw/dist/reply-DhtejUNZ.js

Reapply script

~/.openclaw/workspace/ken-patchs/reapply-openclaw-copilot-gpt54-patches.mjs

Step 1: Fix the OpenClaw config

Update the GitHub Copilot provider block in ~/.openclaw/openclaw.json.

Provider-level requirements

Use:

"baseUrl": "https://api.individual.githubcopilot.com",
"api": "openai-completions"

Why keep provider API as openai-completions?

• OpenClaw runtime expects the provider to stay on a supported generic adapter path
• switching the entire provider to github-copilot caused runtime/provider registration failures

Model-level requirements for GPT-5.4

Set the gpt-5.4 model entry to:

{
  "id": "gpt-5.4",
  "name": "GPT-5.4",
  "api": "openai-responses",
  "reasoning": true,
  "input": ["text", "image"],
  "cost": {
    "input": 0,
    "output": 0,
    "cacheRead": 0,
    "cacheWrite": 0
  },
  "contextWindow": 128000,
  "maxTokens": 64000
}

Agent model registration

Make sure this exists:

"agents": {
  "defaults": {
    "models": {
      "github-copilot/gpt-5.4": {}
    }
  }
}

Step 2: Patch OpenClaw to inject Copilot IDE headers

OpenClaw needs to attach Copilot IDE headers before sending provider requests.

In /home/water/.nvm/versions/node/v22.22.0/lib/node_modules/openclaw/dist/reply-DhtejUNZ.js, add a wrapper like this near the other provider wrappers:

const GITHUB_COPILOT_IDE_HEADERS = {
  "User-Agent": "GitHubCopilotChat/0.35.0",
  "Editor-Version": "vscode/1.107.0",
  "Editor-Plugin-Version": "copilot-chat/0.35.0",
  "Copilot-Integration-Id": "vscode-chat"
};

function createGitHubCopilotHeadersWrapper(baseStreamFn) {
  const underlying = baseStreamFn ?? streamSimple;
  return (model, context, options) => {
    return underlying(model, context, {
      ...options,
      headers: {
        ...GITHUB_COPILOT_IDE_HEADERS,
        ...options?.headers
      }
    });
  };
}

Then apply it inside the provider wrapper logic:

if (provider === "github-copilot") agent.streamFn = createGitHubCopilotHeadersWrapper(agent.streamFn);

Step 3: Patch OpenClaw to route GitHub Copilot Responses correctly

Find the branch that decides which stream transport to use.

Original behavior:

} else if (params.model.api === "openai-responses" && params.provider === "openai") {

Replace it with:

} else if (params.model.api === "openai-responses" && (params.provider === "openai" || params.provider === "github-copilot")) {

Why this matters:

• before the patch, github-copilot never entered the Responses transport branch
• OpenClaw fell back to streamSimple
• streamSimple hit /chat/completions
• GPT-5.4 rejected that endpoint

After this patch:

• github-copilot + openai-responses uses the correct Responses transport
• GPT-5.4 no longer falls back to Chat Completions

Step 4: Validate and restart

Validate config JSON

node -e "JSON.parse(require('fs').readFileSync('/home/water/.openclaw/openclaw.json','utf8')); console.log('OK')"

Validate patched bundle syntax

node --check "/home/water/.nvm/versions/node/v22.22.0/lib/node_modules/openclaw/dist/reply-DhtejUNZ.js"

Restart gateway

openclaw gateway restart

Verification Procedure

1. Set the model to github-copilot/gpt-5.4
2. Send a simple prompt like hi
3. Confirm the gateway stays connected
4. Confirm none of these errors return:

missing Editor-Version header for IDE auth
model "gpt-5.4" is not accessible via the /chat/completions endpoint
No API provider registered for api: github-copilot

Reapply After OpenClaw Updates

Because the runtime fix patches the installed OpenClaw bundle, upgrades or reinstalls may overwrite it.

Use the reapply script:

node ~/.openclaw/workspace/ken-patchs/reapply-openclaw-copilot-gpt54-patches.mjs
openclaw gateway restart

Design Notes

Why not switch the whole provider to api: "github-copilot"?

That looked tempting, but OpenClaw's runtime path did not have a compatible registered streaming provider for that mode in this setup, which caused runtime/provider registration failures.

Why not keep GPT-5.4 on openai-completions?

Because GitHub Copilot GPT-5.4 is not accessible on /chat/completions. It must go through the Responses API.

Why did OpenCode work earlier?

OpenCode already handled the GitHub Copilot transport path correctly, including the required Copilot headers and the proper API mode, while OpenClaw needed both config and runtime fixes.

Recommended Maintenance Notes

• Keep this guide with the reapply script path documented nearby
• After any OpenClaw upgrade, rerun the patch script
• If OpenClaw changes its bundle file name, update the script path target accordingly
• If GitHub Copilot changes required IDE header versions, update both the runtime patch and reapply script

Quick Recovery Commands

node ~/.openclaw/workspace/ken-patchs/reapply-openclaw-copilot-gpt54-patches.mjs
openclaw gateway restart
openclaw status

Final State

With the config fix and runtime patches in place, github-copilot/gpt-5.4 works in OpenClaw and the gateway remains stable.