plan_crawl
Compiles concepts, entity scope, and dates into a ranked, failover-aware crawl plan without fetching data; reports unroutable concepts and unmapped entities instead of dropping them.
Instructions
Plan a concept crawl -> CrawlPlan artifact (concepts in, methods out).
Compiles desired concepts + entity scope + date range into a ranked, failover-aware CrawlPlan. Does not fetch. Unroutable concepts (no confirmed binding) and unmapped entities (no per-source identifier) are reported, not silently dropped.
If since_last is True, the plan's date_range.start is derived from the minimum
per-concept max(date) already in semantic_observations (incremental crawl).
Either start or since_last must be provided. If both, start wins.
end defaults to today if not provided.
mode is per_date (one request per concept x entity x date) or series
(one request per concept x entity against a bulk_history endpoint; the pipeline
explodes the returned frame). Series mode refuses concepts bound only to non-bulk
functions.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"concept_ids": "<concept_ids>",
"entity_type": "<entity_type>"
},
"name": "plan_crawl"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | ||
| mode | No | per_date | |
| start | No | ||
| frequency | No | ||
| entity_ids | No | ||
| since_last | No | ||
| concept_ids | Yes | ||
| entity_type | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||