Try to use regex heuristics instead of llm for generating one-click rules #176
Conversation
There was a problem hiding this comment.
Pull Request Overview
Replaces LLM-based popup confirmation (llmMatch) with regex-based confirmation (regexMatch) for generating one-click autoconsent rules. Introduces a new required regexConfirmedPopups field in the manifest type while leaving legacy llm code commented out.
- Swaps logic from llmMatch to regexMatch throughout rule generation and processing.
- Updates type definitions to add regexConfirmedPopups and optionally retain a deprecated _llmConfirmedPopups field.
- Leaves prior llm-related code commented out instead of removing it, increasing noise.
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| post-processing/generate-autoconsent-rules/types.js | Adds regexConfirmedPopups field and renames llmConfirmedPopups to optional _llmConfirmedPopups. |
| post-processing/generate-autoconsent-rules/main.js | Replaces llmMatch-based filtering with regexMatch and comments out former logic. |
| post-processing/generate-autoconsent-rules/generation.js | Updates rule generation to use regexMatch; retains commented llm code and re-derives popup list. |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
| // const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch); | ||
| const regexConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.regexMatch); | ||
| // if (llmConfirmedPopups.length > 1 || llmConfirmedPopups[0].rejectButtons.length > 1) { | ||
| if (regexConfirmedPopups.length > 1 || regexConfirmedPopups[0].rejectButtons.length > 1) { |
There was a problem hiding this comment.
This block assumes regexConfirmedPopups is non-empty (accessing regexConfirmedPopups[0]) based on an earlier guard in the caller; add an explicit guard or an assertion here to make the dependency clear, and consider passing the already-filtered list from the caller instead of recomputing it to avoid duplicated logic.
| if (regexConfirmedPopups.length > 1 || regexConfirmedPopups[0].rejectButtons.length > 1) { | |
| if (regexConfirmedPopups.length > 1 || (regexConfirmedPopups.length > 0 && regexConfirmedPopups[0].rejectButtons.length > 1)) { |
| // const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch); | ||
| const regexConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.regexMatch); | ||
|
|
||
| // shortcut if no popups with llmMatch | ||
| if (llmConfirmedPopups.length === 0) { | ||
| // if (llmConfirmedPopups.length === 0) { | ||
| if (regexConfirmedPopups.length === 0) { | ||
| return { newRuleFiles, updatedRuleFiles, keptCount: 0, reviewNotes: [], updatedExistingRules }; | ||
| } | ||
|
|
||
| const matchingRules = findMatchingExistingRules(initialUrl, finalUrl, collectorResult, existingRules); | ||
| console.log( | ||
| `Detected ${llmConfirmedPopups.length} unhandled cookie popup(s) on ${finalUrl} (matched ${matchingRules.length} existing rules)`, | ||
| // `Detected ${llmConfirmedPopups.length} unhandled cookie popup(s) on ${finalUrl} (matched ${matchingRules.length} existing rules)`, |
There was a problem hiding this comment.
Commented-out legacy llm* code increases noise; remove it or add a concise comment explaining when (or if) it will be reintroduced. Version control preserves history, so keeping multiple commented lines inline can hinder readability.
muodov
force-pushed
the
test-regex-based-generation
branch
from
4d35c4e to
7dc59f6
Compare
1 participant
No description provided.