* [LLM Classification] Do not HTML-encode re-used tags again
The tags of an entry are stored HTML-encoded: `applyClassification()`
encodes the tags returned by the LLM with `htmlspecialchars()`, like
SimplePie does for the categories of the feeds.
When an already classified entry is updated without any change to its
prompt, the extension re-uses the stored tags instead of calling the
LLM again, but passed them as-is to `applyClassification()`, which
encoded them a second time. So a tag such as `R&D` became `R&D` in
the database after classification, then `R&D` after the next
such update, and so on. When a list of allowed tags is configured, the
encoded tags did not match the list anymore (`R&D` is not `R&D`),
and were silently removed from the entry.
Decode the stored tags before re-using them, so that they go through
the same encoding and allow-list check as the tags returned by the LLM.
Decoding first also lets tags match a configured prefix containing such
characters.
Bump the extension version to 0.3.2.
* [LLM Classification] Decode single quotes in re-used tags too
* Use PHP 8.1+ callable syntax in registerHook calls
Documentation update for code examples: https://github.com/FreshRSS/FreshRSS/pull/9443
* Change compatibility to FreshRSS 1.25.0+ in GridView
Since PHP 8.1 syntax is being used now
When filtering tags by prefix, the prefix was being preserved on existing tags
before they were re-added. This caused the prefix to be duplicated when
applyClassification re-applied it. Now we strip the prefix from existing tags
before re-adding them, preventing the duplication issue.
Closes#496
* [LLM Classification] Skip duplicate LLM calls on no-op feed updates
Some RSS sources re-publish existing articles with no semantic change
(reformatted author, tweaked date, new enclosure attribute, etc.).
FreshRSS detects these as updated entries via hash mismatch and calls
EntryBeforeInsert again, which previously triggered another LLM API
call for every such pseudo-update.
The extension now stores a SHA-1 of the prompt it sent (plus the exact
list of tags it assigned) on each classified entry, under the
'llm_classification' attribute namespace. On a feed update of an
already-classified entry:
- if the new prompt hashes to the same value, the prior tags are
restored and no LLM call is made;
- otherwise, behaviour follows the new 'Re-classify when content
changes' toggle (default on): call the LLM and refresh, or keep the
prior tags untouched.
When re-classifying, the prior tag list is used to remove only those
exact tags (instead of the previous prefix-based heuristic), so manual
tags sharing the prefix are preserved.
* Simplification
* Remove option (for now)
* Re-use existing information instead of additional attribute
* Reduce code
* fix: prompt_hash is cleared for updated entries
Signed-off-by: Adam Tao <tcx4c70@gmail.com>
* Remove PHPStan help
* Typo
---------
Signed-off-by: Adam Tao <tcx4c70@gmail.com>
Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>
Asish
Inverle
Alexandre Alapetite
a-p-a-n
tcx4c70andAlexandre Alapetite