rohit/probo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reuse mapping agent to attribute trackers in enricher

Browse Source 
The enrichment worker no longer invents a description when a tracker's
purpose cannot be substantiated; it records an empty description and
marks the row enriched so the stale-recovery loop does not retry it.

Vendor identification is the mapping pipeline's job, so the enricher
reuses the existing tracker-mapping agent to attribute a third party
for an unlinked common pattern before describing it. A confident
catalog match seeds the enrichment prompt and links the pattern, but
the enricher never creates or overrides an attribution.

When a blank, unlinked catalog row later gains a third party through
the mapping pipeline's upsert, enrichment is re-armed so the now-known
vendor gets a second, better-informed description attempt.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-05-29 18:11:15 +02:00
parent 7360c6eb27
commit 9b03d199da
7 changed files with 639 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pkg/cookiebanner/prompts/tracker_enrichment.txt.tmpl
View File

@@ -6,7 +6,7 @@ You are a privacy and web-tracking compliance expert. Your job is to write an ac
Given a tracker pattern (cookie name, local storage key, etc.), its type, max-age, and the third party that operates it when known, produce a concise factual description of the tracker's purpose.
Return a structured JSON response with:
- description: one or two sentences describing what this tracker stores or does and the purpose it serves (e.g. analytics, advertising, session management, security). When the operating company is known, name it.
- description: one or two sentences describing what this tracker stores or does and the purpose it serves (e.g. analytics, advertising, session management, security). When the operating company is known, name it. Leave this empty when you cannot substantiate the purpose from evidence.
</task>
<instructions>
@@ -23,5 +23,5 @@ Return a structured JSON response with:
4. Keep the description concise (one to two sentences) and free of marketing language. It should read as a neutral, compliance-grade statement of purpose.
5. If you genuinely cannot determine the tracker's purpose, write a minimal factual description based on its type and name (e.g. "Cookie set by an unidentified third party; purpose could not be determined.") rather than inventing details.
5. If you genuinely cannot substantiate the tracker's purpose from evidence, return an empty description. Do not write a fallback such as "purpose could not be determined", and do not guess a purpose from the name or max-age alone (e.g. do not claim a key is "used for session" just because it has no expiry). An empty description is preferable to an unverified one.
</instructions>