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 best-effort pipeline stage after social enrichment asks Miniflux to
discover the feeds behind each aggregator-only article, validates every
result by sniffing the body, and records the survivors as feed candidates
with a per-host memo. Ranking is a shrunk mean over the linked articles'
existing telemetry and ratings. `daily-epub feeds discover` runs the same
pass over recent articles for seeding.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QVPagF6jfDv78CC5Jv2wp4
The Ratings page gains an "Import ratings" form: paste URLs (one per
line), choose a verdict and an optional note. Rows land in the new
rating_imports table and the new import-ratings job (same systemd job
template as the rest of the catalogue) canonicalizes each URL, reuses or
fetches + extracts the article, embeds it with Voyage when enabled, and
appends an explicit rating event with source "import". Per-URL status
shows on the Ratings page; the job page's journal is the live log.
Imported articles have no entry row (best_entry_id NULL, feed "Imported")
and no sources, so they act as rated neighbours without touching the
feed prior. The CLI's rating-event construction moves to rate::record_explicit
and the dashboard job start path is shared as jobs::start_job.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QVPagF6jfDv78CC5Jv2wp4
`app` alone said how long the origin took; it could not say where. The
header now also carries `sess` (the session/auth layers around the
routed stack), `db` (SQLite statement time, statement count in `desc`)
and `tpl` (askama rendering), each only where it was measured.
`db` needs a tracing layer: sqlx-sqlite runs statements on a worker
thread and only reports elapsed time there, inside the span the caller
handed it. The new `web::timing` module hangs the request's metrics on a
per-request span and reads them back off sqlx's `sqlx::query` event.
The layer's filter admits every span up to DEBUG, which is what lets it
see the request span past the middleware spans below it; the module docs
spell out the process-wide cost of that.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5eMEmWEnjMXBsBob5FDW
The site is about to sit behind Cloudflare, where the public pages will be
allowed to live at the edge for a day (`s-maxage`, next commit). That is only
correct if the edge is emptied the moment a new issue lands, so the origin now
does the emptying itself rather than leaving it to an operator to remember.
`[cdn]` is inert by default: with no `provider` nothing is called and no token
is needed, so an origin with no CDN behaves exactly as before. Setting
`provider = "cloudflare"` without both a zone id and `DAILY_EPUB_CDN__API_TOKEN`
is a config error — a half-configured purge would publish into a stale edge and
say nothing.
The purge is `purge_everything` on purpose. A new issue changes more than its
own page: `/`, `/issues`, `/feed.xml`, `/issues.json`, and the previous issue's
page too, whose "latest" nav marker moves. A per-URL list of that set is exactly
the kind of thing that silently rots, and everything expensive at the edge is
content-hashed, so refilling it costs one origin fetch.
A purge failure is logged at warn and never fails the run: the paper is already
published and recorded by then, and a few stale hours are not worth failing over.
`daily-epub cdn purge` runs the same code by hand; it takes no run lock because
it touches neither the database nor the publish directories.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5eMEmWEnjMXBsBob5FDW
Job catalogue and daily-epub job run, the systemd job unit and polkit rule,
SystemdRunner/MockRunner, the Jobs pages with status and journal tail, the
stats_data refactor with a byte-identical CLI, the stats page and the
overview sparklines.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NHyYupFdBiR4VfoUM7NjSM
Migration 0004 (users, sessions, config_changes, profile_versions, jobs,
rating_events.user_id, runs.report_json, issues.issue_json), the issue
snapshot writer and loader, the web module skeleton with layout and static
assets, axum-login/tower-sessions over a sqlx session store, password-auth
users with a CLI, the login throttle, the origin check, security headers,
and the public issue pages, archive, Atom feed and robots.txt.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NHyYupFdBiR4VfoUM7NjSM
[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
Dead code and stale v1 comments removed (clippy -W dead_code clean, the
three world.rs warnings fixed), the Brief chapter's TOC title renamed from
"From the Editor", features prune now also sweeps article_assessments and
generate runs the sweep once after publishing, the example config is
tested key-for-key against Config::default(), README commands match
--help, and docs/plans/2026-08-15-implementation-notes.md records the
Anthropic and Voyage facts, the new tables, the budget-day rule and the
lock.
Implemented by a Claude agent from docs/plans/curation-v2-briefs/step7.md.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
Behind-the-paper chapter (behind.xhtml, both editions) built from the run's
StageCounts and candidate_runs near misses; daily-epub stats [--days N];
StageCounts gains knn/feed gates and verdicts_in_prompt, timings split
into summaries + brief, the four-line §15.4 info block logged once per
run and printed by print_report; src/lock.rs flock guard on
<database_path>.lock for generate, profile rebuild, features backfill and
backfill-social; README updated for the new CLI, env vars and costs.
Implemented by a Claude agent from docs/plans/curation-v2-briefs/step6.md;
reviewed against plan §5, §15.
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
DeepSeek triage over every eligible article (plan §10) with cached
assessments in article_assessments, the union admission with quotas and
exploration slots (§11), hygiene moved to admit.rs with the churn rule
reading assessments, prefilter.rs reduced to hygiene and text heuristic,
prefilter_keep removed in favour of curation.ranking.deep_keep, the
scores table dropped (migration 0003), and --rescore on generate.
Implemented by Codex (gpt-5.4, high effort) from
docs/plans/curation-v2-briefs/step4.md; reviewed against plan §10–§11.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
Union merge of the Claude editor (step 2) and the embeddings/signals/telemetry
work (step 3): both config trees, per-provider LLM budgets plus the Voyage
meter, one startup provider log, runs.config_json with ranking and voyage
settings, and selected picks' why lines landing in candidate_runs.editor_why.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
- embedding.rs: EmbeddingBackend + VoyageBackend, batched bounded-concurrency
client with its own UsageMeter, f32 BLOB codec, article/interest embedding
cache keyed by model, dimension and sha256 of the embedded text.
- signals.rs: z-scored interest match, decayed rated-neighbour preference
with the knn gate, feed affinity with the feed gate, social, text heuristic
without social terms, mid-rank percentile normalizer, preliminary blend.
- telemetry.rs: candidate_runs writer with §7.5 signals_json, explain and
near-misses renderers, prune.
- [voyage] and the full [curation.ranking] config with validation.
- CLI: explain, features backfill|prune, generate --skip-embeddings.
- Pipeline: hygiene rows, embed and signals stages before the old prefilter;
same-date regeneration no longer excludes its own picks.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
- AnthropicBackend (Messages API, cached system block, output_config.effort,
server-side fallbacks, refusal surfaced as an error); Llms { bulk, editor }
with editor_or_bulk(); PriceTable-based UsageMeter per provider.
- [anthropic], [editorial], deepseek.max_concurrent_requests and
curation.max_article_count config; startup logs resolved providers.
- Budget day is the UTC date of started_at, preloaded from
runs.provider_costs_json; finish_run writes provider_costs_json and
config_json. Stage A batches run concurrently with per-batch budget checks.
- Editor prompt with one-line "why" per pick; no minimum lineup size;
--max-articles is a ceiling; top-up branch deleted; why stored on picks and
issue_articles.why and rendered in chapters and In this issue.
- Summaries on the editor client (3k-token input, concurrency 4, bulk then
excerpt fallback); "The Brief" replaces From the Editor; section intros gone.
- Colophon carries per-provider costs and models.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
- Migration 0002: rating_events, article_embeddings, interest_embeddings,
article_assessments, candidate_runs, runs.config_json/provider_costs_json,
issue_articles.why; copies ratings into rating_events and drops ratings and
feed_priors (scores stays until step 4).
- Vote is Loved | Good | NotForMe; legacy `up` links still verify as Loved.
- Footer offers Loved it / Good / Not for me; the confirmation page offers the
other two so a mis-tap can be corrected. handle_rating appends one event.
- db::current_ratings implements the latest-explicit-event rule with summaries
and facets; `ratings list|set|clear` CLI appends source='cli' events.
- data/profile.md replaces the hard-coded reader prose; the system prompt is
rebuilt every run in the §8.4 order with a recent-verdicts block.
- Weekly rebuild reads summaries, facets and notes; feed priors removed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
It turns out it is currently impossible for the Xteink X4 to download
XTC files from an OPDS server. So I switched the built-in OPDS server in
this binary (daily.hallada.net/opds) to serve the EPUB files instead of
the XTC files. The X4 is pretty capable of reading the X4 edition of the
EPUB that was optimized for it anyways, and I prefer the flexibility of
EPUB, so I might end up eventually deleting the XTC conversion. For now,
I kept the conversion step (in case I ever want to ever try manually
copying them to the device) and I keep a limited number of XTC issues on
the server since they are quite big in filesize. The BookOrbit
integration is now optional since the built-in OPDS server is able to
serve the EPUBs. In my installation, I serve the EPUBs through both. The
daily.hallada.net/opds server is just a little quicker to navigate and
download the EPUBs on the X4 since the BookOrbit OPDS requires diving
into a couple layers of folders before you get to the files.
Full implementation of a personalized daily newspaper delivered as an
EPUB.
Articles are pulled from a local self-hosted Miniflux instance, enriched
with comments, summarized and filtered by DeepSeek AI, and then
assembled into two EPUB editions: standard and optimized for the Xteink
X4 e-ink reader. Both are served by the local self-hosted BookOrbit OPDS
server in a separate library. Then the X4 edition is futher converted to
XTC format and served over a separate OPDS server hosted by the Rust
binary. Runs are tracked in a local SQLite database so runs are
idempotent per date.
Full documentation of the plan is in docs/plans and setup and install
instructions are in the README.md file.
thalladaandClaude Fable 5.1