openclaw - 💡(How to fix) Fix [Bug]: v2026.4.26 ships `coding-agent` skill + `codex` provider with `openai/gpt-5.5` as silent default — breaks stacks without OpenAI configured [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#73358Fetched 2026-04-29 06:20:36
View on GitHub
Comments
2
Participants
3
Timeline
3
Reactions
0
Timeline (top)
commented ×2closed ×1

Error Message

[diagnostic] lane task error: error="No API key found for provider "openai". Auth store: …/auth-profiles.json (agentDir: …). Configure auth for this agent (openclaw agents add <id>) or copy auth-profiles.json from the main agentDir." [model-fallback/decision] requested=openai/gpt-5.5 candidate=openai/gpt-5.5 reason=auth next=none Embedded agent failed before reply: No API key found for provider "openai".

Root Cause

  1. A codex provider in the agent's models.json catalog with gpt-5.5, gpt-5.4-mini, gpt-5.2
  2. A new bundled skill coding-agent (eligible by default because claude, codex, opencode, pi are on PATH) that delegates to Codex unless explicitly disabled
  3. A model-fallback/decision runtime that attempts openai/gpt-5.5 as a candidate

Fix Action

Fix / Workaround

Workaround (what fixed it)

Code Example

[diagnostic] lane task error: error="No API key found for provider \"openai\". Auth store: …/auth-profiles.json (agentDir: …). Configure auth for this agent (openclaw agents add <id>) or copy auth-profiles.json from the main agentDir."
[model-fallback/decision] requested=openai/gpt-5.5 candidate=openai/gpt-5.5 reason=auth next=none
Embedded agent failed before reply: No API key found for provider "openai".

---

# 1. Strip codex provider from agent models.json
python3 -c "import json; p='~/.openclaw/agents/main/agent/models.json'; ..." # remove 'codex' provider key

# 2. Remove openai/* from huggingface catalog
# (3 entries: openai/gpt-oss-120b, openai/gpt-oss-20b, openai/gpt-oss-safeguard-20b)

# 3. Disable coding-agent skill (per docs at /tools/skills-config)
#    Set skills.entries.coding-agent.enabled = false in BOTH ~/.openclaw/openclaw.json
#    AND $OPENCLAW_STATE_DIR/openclaw.json

# 4. Restart gateway
openclaw gateway restart
RAW_BUFFERClick to expand / collapse

Bug

Upgrading to OpenClaw 2026.4.26 (verified node[…]: 2026.4.26) on a stack that never had OpenAI configured introduces:

  1. A codex provider in the agent's models.json catalog with gpt-5.5, gpt-5.4-mini, gpt-5.2
  2. A new bundled skill coding-agent (eligible by default because claude, codex, opencode, pi are on PATH) that delegates to Codex unless explicitly disabled
  3. A model-fallback/decision runtime that attempts openai/gpt-5.5 as a candidate

Result on a stack with no OPENAI_API_KEY:

[diagnostic] lane task error: error="No API key found for provider \"openai\". Auth store: …/auth-profiles.json (agentDir: …). Configure auth for this agent (openclaw agents add <id>) or copy auth-profiles.json from the main agentDir."
[model-fallback/decision] requested=openai/gpt-5.5 candidate=openai/gpt-5.5 reason=auth next=none
Embedded agent failed before reply: No API key found for provider "openai".

Every chat lane fails before reply with no obvious upgrade-time prompt that an OpenAI key is now required.

Stack details (no OpenAI ever configured)

  • models.json providers in use: deepseek, anthropic, ollama (all keys configured)
  • Agents.defaults.model.primary: deepseek/deepseek-v4-flash
  • Agents.defaults.model.fallbacks: deepseek/deepseek-v4-pro, ollama/qwen3.6:27b-heretic
  • No auth-profiles.json for OpenAI; user has stated repeatedly they do not use ChatGPT/Codex.

Expected

  • Bundled coding-agent / codex provider should NOT be enabled by default on agents that have never configured an OpenAI auth profile.
  • If a user has a primary + fallbacks chain that routes to non-OpenAI providers, the runtime should not synthesize an openai/gpt-5.5 candidate.
  • Upgrade flow should warn ("This release adds a Codex coding-agent skill — needs OpenAI auth to use") and require explicit enable.

Workaround (what fixed it)

# 1. Strip codex provider from agent models.json
python3 -c "import json; p='~/.openclaw/agents/main/agent/models.json'; ..." # remove 'codex' provider key

# 2. Remove openai/* from huggingface catalog
# (3 entries: openai/gpt-oss-120b, openai/gpt-oss-20b, openai/gpt-oss-safeguard-20b)

# 3. Disable coding-agent skill (per docs at /tools/skills-config)
#    Set skills.entries.coding-agent.enabled = false in BOTH ~/.openclaw/openclaw.json
#    AND $OPENCLAW_STATE_DIR/openclaw.json

# 4. Restart gateway
openclaw gateway restart

After this, openclaw skills check shows Disabled: 1 and the auth-failure spam stops.

Reproducibility

100% on any v2026.4.26 install where the user does not have an OpenAI key.

Related

  • #71609 (device_token_mismatch rate-limit loop) — adjacent, also occurred in same session but separate root cause
  • #72966 ([Bug] openai-codex/gpt-5.5 hangs silently on 2026.4.25) — that issue is about Codex usage failing when invoked; this issue is about Codex being enabled silently as default even when the user has no OpenAI

Suggestion

Either (a) gate the coding-agent skill behind explicit OpenAI auth presence, (b) make Codex one peer of many in the routing decision rather than the default, or (c) require an opt-in flag during upgrade.

extent analysis

TL;DR

Disable the coding-agent skill and remove OpenAI providers to prevent authentication errors after upgrading to OpenClaw 2026.4.26 without an OpenAI API key.

Guidance

  • To fix the issue, follow the provided workaround steps: remove the codex provider from models.json, delete OpenAI entries from the Hugging Face catalog, disable the coding-agent skill in both ~/.openclaw/openclaw.json and $OPENCLAW_STATE_DIR/openclaw.json, and restart the gateway.
  • Verify the fix by running openclaw skills check to ensure the coding-agent skill is disabled and checking for any remaining authentication errors.
  • Be aware that this issue only occurs on stacks that have never had OpenAI configured and have upgraded to OpenClaw 2026.4.26.

Example

The workaround steps include a Python command to remove the codex provider from models.json, but the exact command is truncated in the issue. A possible implementation could be:

import json
with open('~/.openclaw/agents/main/agent/models.json', 'r+') as f:
    models = json.load(f)
    if 'codex' in models:
        del models['codex']
    f.seek(0)
    json.dump(models, f)
    f.truncate()

However, this is not explicitly stated in the issue and should be used with caution.

Notes

This fix assumes that the user does not intend to use the coding-agent skill or OpenAI providers. If OpenAI functionality is required, an OpenAI API key must be configured.

Recommendation

Apply the workaround to disable the coding-agent skill and remove OpenAI providers, as this is the most straightforward solution to prevent authentication errors.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING