Codex CLI with Azure OpenAI gpt-5.6-sol fails due to Codex-specific tools / collaboration namespace

[Soorma718]

What version of Codex CLI is running?

0.144.0

What subscription do you have?

Azure API

Which model were you using?

gpt-5.6-sol

What platform is your computer?

Linux / WSL

What terminal emulator and version are you using (if applicable)?

Ghostty

Codex doctor report

What issue are you seeing?

• Azure deployment:

  gpt-5.6-sol

• Model version:

  2026-07-09

• Deployment type:

  Global Standard

• Azure portal target URI:

  https://************.cognitiveservices.azure.com/openai/responses?api-version=2025-04-01-preview

Relevant Codex config

  model = "gpt-5.6-sol"
  model_provider = "azure"
  model_reasoning_effort = "max"
  web_search = "disabled"

  [model_providers.azure]
  name = "Azure OpenAI"
  base_url = "************.cognitiveservices.azure.com/openai"
  env_key = "AZURE_OPENAI_API_KEY"
  wire_api = "responses"
  query_params = { "api-version" = "2025-04-01-preview" }

I also tested with:

  base_url = "https://************.cognitiveservices.azure.com/openai/v1"
  wire_api = "responses"

What works

A direct Azure Responses API call to the portal-provided endpoint works successfully.

Example request:

  POST https:/***************.azure.com/openai/responses?api-version=2025-04-01-preview
  api-key: <redacted>
  Content-Type: application/json

Payload:

  {
    "model": "gpt-5.6-sol",
    "input": "Reply exactly: OK",
    "max_output_tokens": 64,
    "store": false,
    "reasoning": {
      "effort": "high",
      "summary": "auto"
    }
  }

Response succeeds and returns:

  OK

I also tested Azure-supported reasoning efforts:

  none    works
  low     works
  medium  works
  high    works
  xhigh   works
  max     works
  ultra   rejected by Azure

So the Azure deployment, endpoint, key, and model are valid.

What fails in Codex

Running Codex CLI against the same Azure deployment fails before the model can answer.

Example:

  codex exec \
    --ephemeral \
    --skip-git-repo-check \
    -c 'model_provider="azure"' \
    -c 'model_providers.azure.name="Azure OpenAI"' \
    -c 'model_providers.azure.base_url="**********.cognitiveservices.azure.com/openai"' \
    -c 'model_providers.azure.env_key="AZURE_OPENAI_API_KEY"' \
    -c 'model_providers.azure.wire_api="responses"' \
    -c 'model_providers.azure.query_params={"api-version"="2025-04-01-preview"}' \
    -c 'web_search="disabled"' \
    -c 'model_reasoning_effort="high"' \
    "Reply exactly: OK"

Error:

  {
    "error": {
      "message": "X-OpenAI-Internal-Codex-Responses-Lite only supports function tools, custom tools, and client-executed tool search.",
      "type": "invalid_request_error",
      "param": "tools",
      "code": "unsupported_value"
    }
  }

Additional debugging

I put a localhost proxy between Codex and Azure to inspect the outgoing request.

Codex sends a Responses API payload containing input items of type:

  {
    "type": "additional_tools",
    "role": "developer",
    "tools": [...]
  }

The included additional tools were:

  exec
  wait
  request_user_input
  collaboration

The collaboration entry is a namespace tool:

  {
    "type": "namespace",
    "name": "collaboration",
    "description": "Tools for spawning and managing sub-agents."
  }

When forwarding this request to Azure after stripping Codex-only headers, Azure rejects it with:

  {
    "error": {
      "message": "Invalid Value: 'tools'. Namespace 'collaboration' is reserved for encrypted tool use by this model.",
      "type": "invalid_request_error",
      "param": "tools",
      "code": null
    }
  }

If the proxy removes only the collaboration namespace tool and forwards the rest of the request to Azure, Codex works successfully, including normal
shell tool use.

For example, after stripping the collaboration namespace, this works:

  codex exec "Use shell to run pwd, then reply with only the resulting path."

Codex successfully runs:

  pwd

and returns the expected path.

Expected behavior

Codex should support Azure OpenAI Responses deployments such as gpt-5.6-sol without sending Azure-incompatible internal headers or unsupported tool
namespace declarations.

At minimum, when model_provider is a custom/Azure provider, Codex should either:

1. avoid sending X-OpenAI-Internal-Codex-Responses-Lite, or
2. avoid sending hosted/internal Codex-only tool formats to Azure, or
3. feature-detect / config-gate the collaboration namespace tool, or
4. provide a config option to disable collaboration/multi-agent tool injection for providers that reject it.

Actual behavior

Codex sends provider-incompatible internal/tool metadata, causing Azure to reject the request even though the same model/deployment works through the
Azure Responses API directly.

Workaround

A local proxy can make it work by:

1. forwarding requests to:

  https://*********************.azure.com/openai/responses?api-version=2025-04-01-preview

2. forwarding only minimal auth/content headers,
3. removing the collaboration namespace from additional_tools.

With that workaround, Codex works with:

  gpt-5.6-sol
  reasoning.effort = max

but native Codex subagents / collaboration cannot work because the rejected namespace has to be stripped.

Request

Could Codex add proper Azure OpenAI Responses support for current GPT-5.6 Azure deployments, especially:

• no X-OpenAI-Internal-Codex-Responses-Lite behavior for Azure/custom providers,
• no Azure-incompatible collaboration namespace tool unless supported,
• a config flag to disable collaboration/multi-agent additional tools,
• support for Azure preview Responses endpoint format:

    /openai/responses?api-version=2025-04-01-preview
  

• support for model_reasoning_effort = "max" for models that accept it.

Direct Azure API calls confirm that gpt-5.6-sol itself works and accepts max; the failure appears to be Codex request-shaping/tooling compatibility, not
the Azure deployment.

What steps can reproduce the bug?

Running Codex CLI against the same Azure deployment fails before the model can answer.

Example:

  codex exec \
    --ephemeral \
    --skip-git-repo-check \
    -c 'model_provider="azure"' \
    -c 'model_providers.azure.name="Azure OpenAI"' \
    -c 'model_providers.azure.base_url="**********.cognitiveservices.azure.com/openai"' \
    -c 'model_providers.azure.env_key="AZURE_OPENAI_API_KEY"' \
    -c 'model_providers.azure.wire_api="responses"' \
    -c 'model_providers.azure.query_params={"api-version"="2025-04-01-preview"}' \
    -c 'web_search="disabled"' \
    -c 'model_reasoning_effort="high"' \
    "Reply exactly: OK"

Error:

  {
    "error": {
      "message": "X-OpenAI-Internal-Codex-Responses-Lite only supports function tools, custom tools, and client-executed tool search.",
      "type": "invalid_request_error",
      "param": "tools",
      "code": "unsupported_value"
    }
  }

What is the expected behavior?

No response

Additional information

No response

[github-actions]

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

• Codex with GPT-5.6-Sol through Azure fails every turn with X-OpenAI-Internal-Codex-Responses-Lite #31870
• 🩹 All GPT-5.6 Sol turns fail because MultiAgentV2 uses reserved collaboration.spawn_agent #31864

Powered by Codex Action

[thiagoperes]

I used this gpt-5.6-sol-xhigh to make a one-liner fix. Use at your own discretion:

python3 -c 'import json,os,re,shutil,subprocess,tempfile; from pathlib import Path; d=Path.home()/".codex"; d.mkdir(parents=True,exist_ok=True); exe=shutil.which("codex") or (_ for _ in ()).throw(SystemExit("codex not found in PATH")); td=tempfile.TemporaryDirectory(); env=os.environ.copy(); env["CODEX_HOME"]=td.name; data=json.loads(subprocess.check_output([exe,"debug","models"],env=env,text=True)); td.cleanup(); model=next((x for x in data.get("models",[]) if x.get("slug")=="gpt-5.6-sol"),None); model is not None or (_ for _ in ()).throw(SystemExit("gpt-5.6-sol not found in Codex model catalog")); model["use_responses_lite"]=False; model["multi_agent_version"]="v1"; catalog=d/"models.azure.json"; tmp=d/"models.azure.json.tmp"; tmp.write_text(json.dumps(data,indent=2)+"\n"); os.replace(tmp,catalog); cfg=d/"config.toml"; old=cfg.read_text() if cfg.exists() else ""; cfg.exists() and shutil.copy2(cfg,str(cfg)+".bak"); first=re.search(r"(?m)^[ \t]*\[",old); head=old[:first.start()] if first else old; tail=old[first.start():] if first else ""; head=re.sub(r"(?m)^[ \t]*(?:model|model_catalog_json)[ \t]*=.*(?:\n|$)","",head); text="model = \"gpt-5.6-sol\"\nmodel_catalog_json = "+json.dumps(str(catalog))+"\n"+head+tail; text+="" if text.endswith("\n") else "\n"; settings="multi_agent = true\nmulti_agent_v2 = false\n"; section=re.compile(r"(?ms)^([ \t]*\[features\][ \t]*(?:#.*)?\n)(.*?)(?=^[ \t]*\[|\Z)"); text=section.sub(lambda m:m.group(1)+settings+re.sub(r"(?m)^[ \t]*multi_agent(?:_v2)?[ \t]*=.*(?:\n|$)","",m.group(2)),text,count=1) if section.search(text) else text+"\n[features]\n"+settings; ctmp=d/"config.toml.tmp"; ctmp.write_text(text); os.replace(ctmp,cfg); print("Codex Azure workaround installed; fully restart Codex/VS Code and start a new conversation.")'

[kenny7869]

It looks like Azure has resolved this issue, as I haven't encountered the same problem again today(2026-07-13 09:56 UTC+8).