You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| `add_description_parameter` | boolean | ✗ | When `true`, adds agent descriptions as a parameter in tool schemas. Helps with tool selection in multi-agent scenarios. |
73
75
| `code_mode_tools` | boolean | ✗ | When `true`, formats tool responses in a code-optimized format with structured output schemas. Useful for MCP gateway and programmatic access. |
74
76
| `max_iterations` | int | ✗ | Maximum number of tool-calling loops. Default: unlimited (0). Set this to prevent infinite loops. |
77
+
| `max_consecutive_tool_calls` | int | ✗ | Maximum consecutive identical tool calls before the agent is terminated, preventing degenerate loops. Default: `5`. |
78
+
| `max_old_tool_call_tokens` | int | ✗ | Maximum number of tokens to keep from old tool call arguments and results. Older tool calls beyond this budget have their content replaced with a placeholder, saving context space. Tokens are approximated as `len/4`. Set to `-1` to disable truncation (unlimited). Default: `40000`. |
75
79
| `num_history_items` | int | ✗ | Limit the number of conversation history messages sent to the model. Useful for managing context window size with long conversations. Default: unlimited (all messages sent). |
76
80
| `rag` | array | ✗ | List of RAG source names to attach to this agent. References sources defined in the top-level `rag` section. See [RAG]({{ '/features/rag/' | relative_url }}). |
77
81
| `skills` | boolean | ✗ | Enable automatic skill discovery from standard directories. |
0 commit comments