Summary

When running openclaw doctor --fix, it shows a false warning:

Memory search provider is set to "local" but no local model file was found.

However, openclaw memory status --deep shows:

Model: hf:ggml-org/embeddinggemma-300m-qat-q8_0-GGUF/embeddinggemma-300m-qat-Q8_0.gguf
Embeddings: ready
Vector: ready

The memory search is actually working correctly. The doctor check is buggy.

Steps to reproduce

1. Run openclaw doctor
2. Observe false warning about memory search

Expected behavior

No warning should appear when memory search is actually working.

Actual behavior

Openclaw doctor incorrectly reports "Memory search provider is set to "local" but no local model was found"

OpenClaw version

2026.2.26

Operating system

macOS 26.3 (arm64)

Install method

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response