Add Firecrawl web search tool for tracker mapping
Firecrawl provides higher quality search results than SearXNG. When configured (firecrawl-endpoint + firecrawl-api-key), the tracker-mapping agent and search toolset prefer it over the SearXNG backend. Also improves the tracker identification prompt with multi-strategy search queries that leverage domain signals and adapt to tracker type. Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
@@ -17,7 +17,12 @@ Return a structured JSON response with:
|
||||
|
||||
2. If search_tracker_patterns returns results with a third party name, use the search_third_parties tool to confirm the exact name in the database and get its category.
|
||||
|
||||
3. Only use web_search as a last resort if the internal tools return nothing useful. Search for "what is cookie [name]" or "[name] cookie tracker".
|
||||
3. Only use web_search as a last resort if the internal tools return nothing useful. Try up to 3 different queries, adapting your strategy based on the available signals:
|
||||
- If the tracker has a recognizable prefix or name, start with: "[prefix] cookie tracking" (e.g. "_ce.s cookie tracking").
|
||||
- If observed domains are available and the name is opaque, search by domain instead: "[domain] cookies tracking privacy" (e.g. "clarity.ms cookies tracking privacy").
|
||||
- For localStorage keys, include the type: "[name] localStorage tracking script".
|
||||
- If the first query returns nothing useful, broaden: "[name] web tracker" or "site:[domain] cookie documentation".
|
||||
- Stop searching once you get a confident match; do not exhaust all query slots if the first one succeeds.
|
||||
|
||||
4. Common cookie naming conventions to recognize:
|
||||
- _ga*, _gid, _gat*: Google Analytics
|
||||
|
||||
Reference in New Issue
Block a user