thallada/the-daily-epub
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Show what the pipeline understood about each article

Browse Source 
A muted one-line note now follows every article: the deep assessment's
topic group, format, depth and technicality, the specific topics it
extracted, and the reader interests the article matched best, e.g.

  Software engineering · analysis essay · in depth · highly technical ·
  Topics: copy-on-write, ZFS · Interests: Filesystems, Rust

It renders on the web article page footer, on the public and private
issue-page entries, in the EPUB article footer and in the EPUB "In This
Issue" index (both editions), always styled like the existing meta lines
so it stays secondary to the content.

`Pick` gains `top_interests` (serde default, no migration), filled from
the signals stage when the editor assembles the lineup; the facets were
already on the issue snapshot via `Pick.llm`, so earlier issues show the
facet and topic parts and only future issues carry interests. One shared
builder, `understanding_line` in epub::chapters, feeds every surface.

The dev seed gives four picks facets and interests so the line can be
eyeballed locally.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QVPagF6jfDv78CC5Jv2wp4
This commit is contained in:
thallada
2026-09-08 19:44:00 +00:00
co-authored by Claude Fable 5.1
parent 7ce8c65939
commit bedbcb218f
17 changed files with 285 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -5
View File
@@ -13,11 +13,12 @@ the summaries and *The Brief*. It assembles two EPUB editions (a standard one
and one tuned for the Xteink X4 e-ink reader), converts the X4 edition to XTC, and
publishes the lot over its own OPDS catalog — which doubles as a
[BookOrbit](https://github.com/thallada/bookorbit) watched folder if you run one.
Each article chapter ends with Loved it / Good / Not for me links that feed back
into tomorrow's curation, and a short *Behind the paper* chapter before the
colophon says what the run considered, how the deep set was admitted, whether
the learned signals were active, the ten highest-utility near misses, and what
it all cost.
Each article chapter ends with a one-line note of what the pipeline made of the
piece (topic, format, depth, and the reader interests it matched) and Loved it /
Good / Not for me links that feed back into tomorrow's curation; a short *Behind
the paper* chapter before the colophon says what the run considered, how the
deep set was admitted, whether the learned signals were active, the ten
highest-utility near misses, and what it all cost.
Steady-state cost is roughly **$1/day**: $0.05–0.30 in DeepSeek tokens plus
~$0.50–0.80 for the Claude editor and a few cents of Voyage AI embeddings, each