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:
@@ -37,84 +37,6 @@ _TOOL_CALL_MARKER = re.compile(r"^\s*\[TOOL_CALLS\]\s*", re.IGNORECASE)
|
||||
DB_FLUSH_INTERVAL = 5.0 # seconds between partial DB flushes
|
||||
|
||||
|
||||
async def _maybe_save_article_discussion_note(
|
||||
user_id: int, conv_id: int, reply_content: str,
|
||||
) -> None:
|
||||
"""Persist a seeded article-discussion's first reply as a Note.
|
||||
|
||||
Fires after ``run_generation`` completes. Looks for a synthetic
|
||||
read_article seed message on the conversation; if found AND the linked
|
||||
``rss_items`` row has no ``discussion_note_id`` yet, saves ``reply_content``
|
||||
as a Note, tags it, and writes the backlink. Subsequent discuss clicks on
|
||||
the same article are a no-op (already linked).
|
||||
|
||||
Failures are logged and swallowed — the chat UI should never break because
|
||||
Note persistence hit a snag.
|
||||
"""
|
||||
try:
|
||||
if not reply_content or not reply_content.strip():
|
||||
return
|
||||
from sqlalchemy import select as _select
|
||||
from fabledassistant.models.conversation import Message as _Message
|
||||
from fabledassistant.models.rss_feed import RssItem as _RssItem
|
||||
from fabledassistant.services.notes import create_note
|
||||
|
||||
async with async_session() as session:
|
||||
result = await session.execute(
|
||||
_select(_Message)
|
||||
.where(_Message.conversation_id == conv_id)
|
||||
.order_by(_Message.id.asc())
|
||||
)
|
||||
messages = result.scalars().all()
|
||||
seed_meta = None
|
||||
for m in messages:
|
||||
meta = m.msg_metadata or {}
|
||||
if meta.get("article_seed") and meta.get("rss_item_id"):
|
||||
seed_meta = meta
|
||||
break
|
||||
if seed_meta is None:
|
||||
return
|
||||
item_id = int(seed_meta["rss_item_id"])
|
||||
item = await session.get(_RssItem, item_id)
|
||||
if item is None or item.discussion_note_id is not None:
|
||||
return
|
||||
article_title = (item.title or "Untitled article").strip()
|
||||
article_url = item.url
|
||||
article_topics = list(item.topics or [])
|
||||
|
||||
note_title = f"Article: {article_title}"[:200]
|
||||
body_parts = [f"**Source:** {article_url}"] if article_url else []
|
||||
body_parts.append(reply_content.strip())
|
||||
note_body = "\n\n".join(body_parts)
|
||||
tags = ["article-summary"] + [t for t in article_topics if t]
|
||||
note = await create_note(
|
||||
user_id=user_id,
|
||||
title=note_title,
|
||||
body=note_body,
|
||||
tags=tags,
|
||||
entity_meta={
|
||||
"source": "article_discussion",
|
||||
"rss_item_id": item_id,
|
||||
"url": article_url,
|
||||
"conversation_id": conv_id,
|
||||
},
|
||||
)
|
||||
|
||||
async with async_session() as session:
|
||||
fresh = await session.get(_RssItem, item_id)
|
||||
if fresh is not None and fresh.discussion_note_id is None:
|
||||
fresh.discussion_note_id = note.id
|
||||
await session.commit()
|
||||
logger.info(
|
||||
"Saved article-discussion summary as note %d for rss_item %d (conv %d)",
|
||||
note.id, item_id, conv_id,
|
||||
)
|
||||
except Exception:
|
||||
logger.warning(
|
||||
"Failed to persist article-discussion note for conv %d",
|
||||
conv_id, exc_info=True,
|
||||
)
|
||||
|
||||
# Human-readable labels for each tool, shown in the status indicator
|
||||
_TOOL_LABELS: dict[str, str] = {
|
||||
"create_note": "Creating note/task",
|
||||
@@ -593,28 +515,16 @@ async def run_generation(
|
||||
msg_count = len(non_system)
|
||||
should_gen_title = not conv_title or (msg_count > 0 and msg_count % 10 == 0)
|
||||
|
||||
# Persist article-discussion seed conversations as a Note on their
|
||||
# first assistant reply. This makes "Discuss" summaries part of RAG
|
||||
# so the knowledge base stops being amnesiac about articles the user
|
||||
# has already engaged with. The hook detects a seeded conversation by
|
||||
# finding a synthetic read_article assistant message whose
|
||||
# msg_metadata carries ``article_seed: True`` and whose rss_items row
|
||||
# has no discussion_note_id yet. Fire-and-forget so the done event
|
||||
# lands immediately.
|
||||
asyncio.create_task(_maybe_save_article_discussion_note(
|
||||
user_id, conv_id, buf.content_so_far,
|
||||
))
|
||||
|
||||
if should_gen_title:
|
||||
# Feed the title model the *raw* conversation turns only — never
|
||||
# the post-build_context ``messages`` list. ``build_context``
|
||||
# prepends RAG snippets, RSS excerpts, URL content, and briefing
|
||||
# article dumps INTO the user message string itself, so filtering
|
||||
# by role="user" downstream still surfaces that noise as the
|
||||
# "user's message". That pollution caused wildly-wrong titles
|
||||
# (bug #109) — the small background model was staring at article
|
||||
# excerpts instead of what the user actually typed. Pass the
|
||||
# original history + the raw user_content + the assistant reply.
|
||||
# prepends RAG snippets and URL content INTO the user message
|
||||
# string itself, so filtering by role="user" downstream still
|
||||
# surfaces that noise as the "user's message". That pollution
|
||||
# caused wildly-wrong titles (bug #109) — the small background
|
||||
# model was staring at article excerpts instead of what the user
|
||||
# actually typed. Pass the original history + the raw user_content
|
||||
# + the assistant reply.
|
||||
title_messages: list[dict] = [
|
||||
{"role": m["role"], "content": m.get("content") or ""}
|
||||
for m in history
|
||||
|
||||
Reference in New Issue
Block a user