cache
Search previously cached web content instantly using full-text search, URL patterns, and date filters to avoid network requests.
Instructions
Search previously fetched content without hitting the network. Run this BEFORE any search/fetch — cache hits return instantly with full markdown.
Key parameters:
query: FTS5 full-text search over cached markdown + titles (supports AND, OR, NOT, "phrase").
url_pattern: glob filter on URLs (e.g. "example.com").
since: ISO date — only entries cached after this date.
stats: true to get cache size, entry count, oldest/newest dates.
clear: true to delete matching entries.
Persists across sessions. No remote round-trip.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Search strategy when query is provided. "fts" (default) runs keyword-only BM25 over the FTS5 index. "hybrid" additionally runs semantic vector search and fuses both rankings with reciprocal rank fusion for higher-recall lookups; falls back to FTS when the embedding index is empty or unavailable. | |
| clear | No | Clear matching cache entries (requires at least one filter: query, url_pattern, or since) | |
| limit | No | Maximum number of results to return (default 20). | |
| query | No | Full-text search over cached content | |
| since | No | ISO date — only results cached after this date | |
| stats | No | Return cache statistics (total URLs, size, date range) | |
| url_pattern | No | Filter by URL glob pattern (e.g., "*example.com*") | |
| check_changes | No | Re-fetch all matching cached URLs and report which ones have changed. Returns a list of URLs with changed/unchanged status and diff summaries. Use with query or url_pattern to scope which cached entries to check. | |
| max_tokens_out | No | Token-budget cap on total output (cl100k-base BPE). Caps the aggregate size of all returned markdown bodies; bodies past the budget are truncated or dropped. |