← Back to Skills Marketplace
Model Failover Doctor
by
halfmoon82
· GitHub ↗
· v1.0.0
387
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install model-failover-doctor
Description
Diagnose and fix OpenClaw "All models failed" errors by detecting invalid model IDs, provider mismatches, and session fallback issues with optional auto-repair.
Usage Guidance
This tool appears to do what it says: diagnose and optionally auto-fix failover config problems by reading/writing OpenClaw config files and restarting the gateway. Before running with --fix (or --restart): 1) run the script with --dry-run first to preview changes; 2) inspect the generated backups under ~/.openclaw/workspace/.lib/.mfd_backups/ so you can restore if needed; 3) manually review the proposed edits to message-injector/index.ts and pools/session files to ensure they match your intended routing/overrides; 4) run fixes during a maintenance window since the gateway restart will affect availability. If you have concerns, you can open the script (model_failover_doctor.py) and the referenced files to verify behavior—there are no network calls or credential exfiltration signs in the provided code.
Capability Analysis
Type: OpenClaw Skill
Name: model-failover-doctor
Version: 1.0.0
The 'model-failover-doctor' skill performs high-risk administrative tasks, including automated patching of TypeScript source code (message-injector/index.ts) using regular expressions and the modification of core configuration files (pools.json, session_model_state.json). It also executes system commands via subprocess to restart the OpenClaw gateway. While these actions are aligned with the stated purpose of fixing model failover issues and the script includes a local backup mechanism, the automated modification of executable code and broad file system access constitute significant operational risks.
Capability Assessment
Purpose & Capability
The name/description match what the code and SKILL.md do: detect and repair failover issues by reading/writing OpenClaw config files (message-injector, pools.json, session_model_state.json) and creating backups. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md and the script instruct reading and modifying files under ~/.openclaw (openclaw.json, .lib/pools.json, .lib/session_model_state.json and a message-injector index.ts). It also supports --dry-run, --fix, and --restart. These actions are in-scope for a failover repair tool, but note the script will read potentially sensitive configuration files and will write changes to these files when --fix is used (it creates timestamped backups first).
Install Mechanism
No install spec; the skill is instruction+script only. Nothing is downloaded from external URLs and no new binaries are installed.
Credentials
The skill requests no environment variables or external credentials. It operates on config files within ~/.openclaw, which is appropriate for a tool that repairs gateway/session configuration. Access to those files is necessary for its stated purpose.
Persistence & Privilege
The skill is not always-on and does not request elevated platform privileges. It modifies OpenClaw config/extension files (message-injector, pools/session state) and writes backups in its workspace area; this is expected for a repair tool. Autonomous invocation is allowed by default, but that is the platform norm and not a unique concern here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install model-failover-doctor - After installation, invoke the skill by name or use
/model-failover-doctor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of "model-failover-doctor" skill:
- Diagnoses and fixes the "All models failed" error in OpenClaw.
- Provides clear trigger conditions for when to use the tool (e.g., identical model ID failures across providers, post-restart message failures, improper manual edits).
- Supports diagnosis-only, auto-fix with gateway restart, and dry-run preview modes.
- Includes a root cause quick reference table for common issues and auto-fix availability.
- Details most frequent root cause (MI-1) and its resolution.
- Ensures all auto-fixes are backed up for safety and manual recovery.
Metadata
Frequently Asked Questions
What is Model Failover Doctor?
Diagnose and fix OpenClaw "All models failed" errors by detecting invalid model IDs, provider mismatches, and session fallback issues with optional auto-repair. It is an AI Agent Skill for Claude Code / OpenClaw, with 387 downloads so far.
How do I install Model Failover Doctor?
Run "/install model-failover-doctor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Model Failover Doctor free?
Yes, Model Failover Doctor is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Model Failover Doctor support?
Model Failover Doctor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Model Failover Doctor?
It is built and maintained by halfmoon82 (@halfmoon82); the current version is v1.0.0.
More Skills