openclaw-model-failover

# openclaw-model-failover (OpenClaw Plugin)

This is an **OpenClaw Gateway plugin**, not an agent skill.

It mitigates outages by automatically switching the model used for a conversation when it detects:
- Rate limits / quota exhaustion (HTTP 429, RESOURCE_EXHAUSTED)
- Auth/scope failures (e.g. OpenAI: missing `api.responses.write`)

## Install

### Option A: ClawHub

```bash
clawhub install openclaw-model-failover
```

### Option B: From repo (dev)

```bash
openclaw plugins install -l ~/.openclaw/workspace/openclaw-model-failover
openclaw gateway restart
```

## Configure

Set model fallback order (example):

- Anthropic -> OpenAI -> Google

See README for the full config block.

# openclaw-model-failover

OpenClaw plugin to **auto-detect rate limits/quota errors** and switch sessions to fallback LLMs.

## What it does

- Chooses a model based on a **preferred order** before each agent run.
- Detects rate-limit/quota failures and marks the current model as **temporarily limited**.
- Detects temporary provider/plugin cooldown errors (for example `copilot-proxy` in cooldown) and fails over.
- Optionally patches pinned WhatsApp group sessions so you don’t get stuck with `API rate limit reached` loops.

## Install (dev)

```bash
cd ~/.openclaw/workspace/openclaw-model-failover
openclaw plugins install -l .
openclaw gateway restart
```

## ClawHub

This plugin is published on **clawhub.ai** and installable via:

```bash
clawhub install openclaw-model-failover
```

## Configure

In your OpenClaw config:

```json
{
  "plugins": {
    "entries": {
      "openclaw-model-failover": {
        "enabled": true,
        "config": {
          "modelOrder": [
            "openai-codex/gpt-5.3-codex",
            "anthropic/claude-opus-4-6",
            "github-copilot/claude-sonnet-4.6",
            "google-gemini-cli/gemini-3-pro-preview",
            "anthropic/claude-sonnet-4-6",
            "openai-codex/gpt-5.2",
            "google-gemini-cli/gemini-2.5-pro",
            "perplexity/sonar-deep-research",
            "perplexity/sonar-pro",
            "google-gemini-cli/gemini-2.5-flash",
            "google-gemini-cli/gemini-3-flash-preview"
          ],
          "cooldownMinutes": 300,
          "unavailableCooldownMinutes": 15,
          "patchSessionPins": true,
          "notifyOnSwitch": true,
          "debugLogging": false,
          "debugLogSampleRate": 1.0
        }
      }
    }
  }
}
```

## Status Inspection

Check which models are currently blocked and when they become available again.

### CLI

```bash
# Pretty-print current status
npx tsx status.ts

# Machine-readable JSON output
npx tsx status.ts --json

# Clear a specific model's r...