refactor: hard-cut RSS infrastructure (scope C)

Removes the entire RSS feature surface — feeds, items, embeddings, reactions,
discussion-note flow, briefing news context, settings, env-vars, and DB
tables. Keeps the URL-generic article-reader (the read_article LLM tool)
under a clean module so the LLM can still fetch arbitrary article content
from URLs the user provides.

Backend:
- New services/article_fetcher.py — single source of trafilatura URL→text
- New services/tools/article.py — read_article tool (was nested under tools/rss)
- Delete services/rss.py, rss_classifier.py, rss_filtering.py, article_context.py
- Delete services/tools/rss.py
- Delete models/rss_feed.py (RssFeed, RssItem), models/rss_item_embedding.py
- services/embeddings.py: drop upsert/semantic_search/backfill RSS helpers
- services/llm.py: remove _build_briefing_article_context, briefing-conv branch,
  ARTICLE_DISCUSS_SEED skip-RAG branch; drop get_rss_items / add_rss_feed from
  the actions list
- services/generation_task.py: drop _maybe_save_article_discussion_note + caller
- routes/chat.py: drop /api/chat/from-article/<id> endpoint
- routes/journal.py: re-import via web.py refactor (article_fetcher path)
- services/tools/__init__.py: register `article`, drop `rss`
- services/tools/_registry.py: drop the requires=='rss' check
- app.py: drop backfill_rss_item_embeddings + backfill_rss_article_content tasks
- config.py: prose-only edit (no env var change — RSS env vars were never first-class)

Frontend:
- stores/settings.ts: drop rssEnabled
- SettingsView.vue: drop the RSS-classification mention
- api/client.ts: drop openArticleInChat (the from-article endpoint is gone)

Tests:
- Delete tests/test_rss_service.py, test_news_api.py, test_article_reading.py

Migration:
- 0042_drop_rss: DROP TABLE rss_item_embeddings, rss_item_reactions, rss_items,
  rss_feeds; DELETE settings rows for rss_enabled / briefing_*_topics

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-04-26 12:33:30 -04:00
parent cacfcac86a
commit dbd9f00061
26 changed files with 150 additions and 2029 deletions
-2
View File
@@ -38,11 +38,9 @@ from fabledassistant.models.note_version import NoteVersion # noqa: E402, F401
from fabledassistant.models.group import Group, GroupMembership # noqa: E402, F401
from fabledassistant.models.share import NoteShare, ProjectShare # noqa: E402, F401
from fabledassistant.models.notification import Notification # noqa: E402, F401
from fabledassistant.models.rss_feed import RssFeed, RssItem # noqa: E402, F401
from fabledassistant.models.weather_cache import WeatherCache # noqa: E402, F401
from fabledassistant.models.api_key import ApiKey # noqa: E402, F401
from fabledassistant.models.user_profile import UserProfile # noqa: E402, F401
from fabledassistant.models.rss_item_embedding import RssItemEmbedding # noqa: E402, F401
from fabledassistant.models.moment import ( # noqa: E402, F401
Moment,
MomentEmbedding,
-96
View File
@@ -1,96 +0,0 @@
from datetime import datetime, timezone
from sqlalchemy import ARRAY, BigInteger, DateTime, ForeignKey, Index, Integer, Text, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column, relationship
from fabledassistant.models import Base
class RssFeed(Base):
__tablename__ = "rss_feeds"
id: Mapped[int] = mapped_column(primary_key=True)
user_id: Mapped[int] = mapped_column(Integer, ForeignKey("users.id", ondelete="CASCADE"))
url: Mapped[str] = mapped_column(Text)
title: Mapped[str] = mapped_column(Text, default="")
category: Mapped[str | None] = mapped_column(Text, nullable=True)
last_fetched_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
items: Mapped[list["RssItem"]] = relationship(
back_populates="feed", cascade="all, delete-orphan"
)
__table_args__ = (
UniqueConstraint("user_id", "url", name="uq_rss_feeds_user_url"),
Index("ix_rss_feeds_user_id", "user_id"),
)
def to_dict(self) -> dict:
return {
"id": self.id,
"url": self.url,
"title": self.title,
"category": self.category,
"last_fetched_at": self.last_fetched_at.isoformat() if self.last_fetched_at else None,
}
class RssItem(Base):
__tablename__ = "rss_items"
id: Mapped[int] = mapped_column(primary_key=True)
feed_id: Mapped[int] = mapped_column(Integer, ForeignKey("rss_feeds.id", ondelete="CASCADE"))
guid: Mapped[str] = mapped_column(Text)
title: Mapped[str] = mapped_column(Text, default="")
url: Mapped[str] = mapped_column(Text, default="")
published_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
# Truncated to 2000 chars to keep DB size reasonable
content: Mapped[str] = mapped_column(Text, default="")
# Full trafilatura-extracted article body, populated lazily on first
# discuss-click / enrichment pass. Nullable — most items never get this
# cached. Expires naturally with the item (90-day retention).
content_full: Mapped[str | None] = mapped_column(Text, nullable=True)
# Map-reduced conversation-ready context derived from content_full. See
# services/article_context.py — populated on first discuss click so
# repeat clicks skip both the fetch and the LLM map step.
context_prepared: Mapped[str | None] = mapped_column(Text, nullable=True)
content_fetched_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
fetched_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), default=lambda: datetime.now(timezone.utc)
)
topics: Mapped[list[str]] = mapped_column(
ARRAY(Text), nullable=False, default=list, server_default="{}"
)
classified_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
# Note persisting the first-click discussion summary. Set by the article
# discussion pipeline once the seeded chat completes its first assistant
# reply; links back into RAG so re-discussing the same article lands the
# prior summary in context.
discussion_note_id: Mapped[int | None] = mapped_column(
BigInteger, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
)
feed: Mapped["RssFeed"] = relationship(back_populates="items")
__table_args__ = (
UniqueConstraint("feed_id", "guid", name="uq_rss_items_feed_guid"),
Index("ix_rss_items_feed_id", "feed_id"),
Index("ix_rss_items_published_at", "published_at"),
)
def to_dict(self) -> dict:
return {
"id": self.id,
"feed_id": self.feed_id,
"guid": self.guid,
"title": self.title,
"url": self.url,
"published_at": self.published_at.isoformat() if self.published_at else None,
"content": self.content,
"topics": self.topics or [],
"classified_at": self.classified_at.isoformat() if self.classified_at else None,
}
@@ -1,25 +0,0 @@
from datetime import datetime, timezone
from sqlalchemy import DateTime, ForeignKey, Integer
from sqlalchemy.dialects.postgresql import JSONB
from sqlalchemy.orm import Mapped, mapped_column
from fabledassistant.models import Base
class RssItemEmbedding(Base):
"""Stores the embedding vector for an RSS item, used for semantic news search."""
__tablename__ = "rss_item_embeddings"
rss_item_id: Mapped[int] = mapped_column(
Integer,
ForeignKey("rss_items.id", ondelete="CASCADE"),
primary_key=True,
)
user_id: Mapped[int] = mapped_column(Integer, nullable=False, index=True)
embedding: Mapped[list] = mapped_column(JSONB, nullable=False)
updated_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)