Commit Graph

3 Commits

Author SHA1 Message Date
bvandeusen 7bd1548f71 fix(discuss): hard-fail empty articles and skip RAG on seed turn
Discuss flow was hallucinating unrelated content when article
extraction returned empty or RAG pulled in orphan notes that looked
more relevant than the generic seed prompt.

- seed_article_discussion raises EmptyArticleError on empty body;
  briefing and /news routes return 422 instead of staging an empty
  synthetic tool result.
- build_context skips RAG auto-injection when user_message matches
  ARTICLE_DISCUSS_SEED so the article IS the context on turn one;
  follow-up turns keep RAG on.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-14 18:13:17 -04:00
bvandeusen ba90ad8132 feat(article-discuss): unify /news + briefing entry points, persist summaries to RAG
Both the /news discuss button and the briefing discuss button now call a
shared seed_article_discussion() helper that stages the synthetic
read_article tool exchange and the conversational seed prompt — behavior
stays byte-identical across entry points. /news also auto-starts
generation so the chat screen lands on an in-flight stream.

First assistant reply in a seeded article conversation is persisted as a
Note (tags: article-summary + article topics) and backlinked via
rss_items.discussion_note_id, so the knowledge base stops being amnesiac
about articles the user has engaged with.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-14 07:54:24 -04:00
bvandeusen 8205590f8d feat(briefing): cache + map-reduce article context for rich discuss chats
The Discuss button on news cards was producing one-shot replies because
the model got the whole trafilatura blob dropped into history with a
canned "summarize and discuss this article" prompt — no length guard, no
prep, no invitation to converse. Large articles got silently truncated by
Ollama; small articles got a tepid reply.

This reworks discuss_article around a three-layer cache:

  context_prepared  →  content_full  →  fresh trafilatura fetch

First click on a small article fetches once, writes through to both
caches, and passes the body straight into the synthetic read_article
tool-result. First click on a large article additionally runs a parallel
map step (services/article_context.py) that chunks the body on paragraph
boundaries, summarizes each ~8k chunk to ~300 words of dense factual
prose via the background model, and concatenates the summaries under
section headers — all pinned to num_ctx=16384 so the map step doesn't
itself fall victim to silent truncation. Repeat clicks on either path
skip straight to the chat turn.

The canned summary prompt is replaced with a conversational seed that
invites the user into an actual discussion rather than a one-shot
synopsis, matching the goal of "have a conversation about an article,
not just read it."

discuss_topic is intentionally left untouched — it's the multi-article
aggregation path and needs a separate rework. Follow-up task will decide
whether to retire it or rework it on the cached-context approach.

Closes task #106.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-13 20:52:00 -04:00