───────────────────────────────────────
⚠ Compression model (alibaba/qwen3.6-plus) context is 131,072 tokens, but the main model's compression threshold was 209,715 tokens. Auto-lowered this session's threshold to 131,072 tokens so compression can run.
To make this permanent, edit config.yaml — either:
- Use a larger compression model:
auxiliary:
compression:
model: <model-with-209,715+-context> - Lower the compression threshold:
compression:
threshold: 0.50
⚠️ API call failed (attempt 1/3): BadRequestError [HTTP 400]
🔌 Provider: nous Model: moonshotai/kimi-k2.6
🌐 Endpoint: https://inference-api.nousresearch.com/v1
📝 Error: HTTP 400: This request is not valid. Check the model name and other parameters. Additional info: Invalid request: tools.function.parameters is not a valid moonshot flavored json schema, details: <At path 'properties.designSystem': conflicting keywords found after $ref expansion: description>
📋 Details: {'status': 400, 'message': "This request is not valid. Check the model name and other parameters. Additional info: Invalid request: tools.function.parameters is not a valid moonshot flavored json schema, details: <At path 'properties.designSystem': conflicting keywords found after $ref expansion: de
⚠️ Non-retryable error (HTTP 400) — trying fallback...
❌ Non-retryable error (HTTP 400): HTTP 400: This request is not valid. Check the model name and other parameters. Additional info: Invalid request: tools.function.parameters is not a valid moonshot flavored json schema, details: <At path 'properties.designSystem': conflicting keywords found after $ref expansion: description>
❌ Non-retryable client error (HTTP 400). Aborting.
🔌 Provider: nous Model: moonshotai/kimi-k2.6
🌐 Endpoint: https://inference-api.nousresearch.com/v1
💡 This type of error won't be fixed by retrying.
─ ⚕ Hermes