configure_detection
Configure loop detection parameters and progress indicators for AI agents to identify repetitive or alternating action patterns and monitor task progress efficiently.
Instructions
Configure loop detection parameters and domain-specific progress indicators
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| alternating_threshold | No | Threshold for detecting alternating action patterns (0.0-1.0) | |
| min_actions_for_detection | No | Minimum number of actions required before loop detection | |
| progress_indicators | No | Action patterns that indicate positive task progress (e.g., ["success", "complete", "found"]) | |
| progress_threshold_adjustment | No | How much to increase thresholds when progress indicators are present | |
| repetition_threshold | No | Threshold for detecting repetitive action patterns (0.0-1.0) | |
| semantic_intents | No | Domain-specific action intents for semantic analysis (e.g., ["navigating", "clicking", "typing"]) |
Input Schema (JSON Schema)
{
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"alternating_threshold": {
"default": 0.5,
"description": "Threshold for detecting alternating action patterns (0.0-1.0)",
"type": "number"
},
"min_actions_for_detection": {
"default": 5,
"description": "Minimum number of actions required before loop detection",
"type": "number"
},
"progress_indicators": {
"default": [],
"description": "Action patterns that indicate positive task progress (e.g., [\"success\", \"complete\", \"found\"])",
"items": {
"type": "string"
},
"type": "array"
},
"progress_threshold_adjustment": {
"default": 0.2,
"description": "How much to increase thresholds when progress indicators are present",
"type": "number"
},
"repetition_threshold": {
"default": 0.4,
"description": "Threshold for detecting repetitive action patterns (0.0-1.0)",
"type": "number"
},
"semantic_intents": {
"default": [],
"description": "Domain-specific action intents for semantic analysis (e.g., [\"navigating\", \"clicking\", \"typing\"])",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
}