After a rewrite of the prompt rule and a few more live issues the line still
read as a second abstract, so it goes entirely: the rule and the "why" key in
the editor's JSON, the parsing and 14-word cap, the Pick field, the
issue_articles and candidate_runs writes, the Brief prompt's per-pick why,
the explain output, the dashboard "editor" columns, and the rendering on the
web index, article and public pages, the Atom feed and both EPUB pages.
The "Matches: …" interests line stays (restyled in the next commit). The
issue_articles.why and candidate_runs.editor_why columns remain in the
schema unused; stored issue snapshots that still carry "why" deserialize
because Pick ignores unknown fields.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ESJbbzQ1b8fs5AA65tKw2q
Across 96 picks in four live issues the "Why it's here" line was a 12-word
restatement of the summary printed next to it: one used the second person,
five mentioned the reader at all. Rule 8 now says what the line is for, what
it must not do (describe the piece, list the interests shown beneath it), and
gives a bad/good pair.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NxctvrEPQZ9pX58LRgGYNZ
A fourth explicit verdict, "AI slop" (Vote::Slop, label `slop`), joins the
rating widget on the web, the EPUB footer links, the /r/ confirmation page,
the CLI, imports and the dashboard filters. It counts as a full negative
(curation.feedback.slop_value, -1.0) in the neighbour and affinity signals.
Beyond that, each run loads the authors whose current verdict is slop, with
no lookback, and multiplies the preliminary blend and the utility of every
candidate by that author by 1 - curation.ranking.slop_author_penalty (0.75),
so they sink before triage. The flag is recorded in signals_json, shown by
`explain` and the dashboard signals table, and the confirmation names the
author (or says no author is known, in which case only the rating applies).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VXYGBPoHZSDSfE5WcJ9bvj
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
[llm] assigns the bulk and editor roles by name over a [providers.*]
registry (kind = openai | anthropic, per-provider model, effort, daily
ceiling and price table); DeepseekBackend becomes OpenAiCompatibleBackend
(reasoning_effort passthrough), AnthropicBackend builds from the same
ProviderConfig, meters and provider_costs are keyed by provider name.
Gemini 3.8 Flash is declared via Google's OpenAI-compatible endpoint so
switching the editor is one line (or DAILY_EPUB_LLM__EDITOR=gemini for an
A/B dry run). Stale [deepseek]/[anthropic] tables, the top-level
max_daily_usd and the old key env vars fail loudly.
daily-epub config check validates and prints the resolved roles, models,
key presence and paths without opening the database.
docs/runbooks/curation-v2-migration.md walks the server upgrade from v1.
Registry implemented by a Claude agent from an orchestrator brief;
verified fmt/clippy(-W dead_code)/test green.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
assess.rs replaces score.rs (DEEP_INSTRUCTIONS, representative sample
with [BEGINNING]/[MIDDLE]/[END], facets, cached deep rows with --rescore
bypass), rank.rs adds the utility blend over present signals with gate
ramps and the leader-clustered shortlist (cap 2 → 3 → uncapped, protected
top-N, exploration reserve), editor.rs replaces select.rs with the §13
rendering and utility-ordered fallbacks. ScoredArticle is gone; Candidate
is the only flow type. deep_batch_size replaces score_batch_size.
Started by Codex (cut off by its usage limit mid-verification) and
finished by a Claude agent from docs/plans/curation-v2-briefs/step5.md;
reviewed against plan §12–§13.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
thalladaandClaude Fable 5.1