How System Message Tools Work
Continue implements an innovative approach called system message tools that ensures consistent tool functionality across all models, regardless of their native capabilities. This allows Agent mode to work seamlessly with a wider range of models and providers.How System Message Tools Function
Instead of relying solely on native tool calling APIs (which vary between providers), Continue converts tools into XML format and includes them in the system message. The model generates tool calls as structured XML within its response, which Continue then parses and executes. This approach provides:- Universal compatibility - Any model capable of following instructions can use tools, not just those with native tool support
- Consistent behavior - Tool calls work identically across OpenAI, Anthropic, local models, and others
- Better reliability - Models that struggle with native tools often perform better with system message tools
- Seamless switching - Change between providers without modifying your workflow
Recommended Agent Models
| Model role | Best open models | Best closed models | Notes |
|---|---|---|---|
| Agent Plan | GLM 4.5 (355B) GLM 4.5 Air (106B) | Closed models are slightly better than open models | |
| Chat Edit | Closed and open models have pretty similar performance | ||
| Autocomplete | Closed models are slightly better than open models | ||
| Apply | N/A | Open models are not good enough for this model role | |
| Embed | Qwen3 Embedding | Codestral Embed | Closed models are slightly better than open models |
| Rerank | zerank-1 zerank-1-small Qwen3 Reranker | Relace Code Rerank | Open models are beginning to emerge for this model role |
| Next Edit | Closed models are better than open models |