docs: sync D14 with best-of-3 confirmation and fix stale counts - #10
Merged
Conversation
- docs/DESIGN.md D10: correct researched-title count in the tier table (7 -> 8; the Gone Girl addition was never reflected there). - docs/DESIGN.md D14: the 'best-of-3 draft generation not implemented yet' note was stale -- it shipped and was confirmed working live (Citizen Kane, 3/3 candidates, 4/4/5 grounded claims) two commits after it was written, but only CLAUDE.md was updated at the time. Replaces the stale paragraph with what actually happened: the Groq 403 that blocked the first live run, its unexplained resolution, and the live confirmation numbers. Also records the one real but minor quality gap found in that run (author_voice returning generic critic commentary instead of a real quote) so it isn't only living in CLAUDE.md. - README.md Stack section: corrected a wrong claim that Anthropic Claude powers research-assist drafting. webapp/research_assist.py is Groq-only (hardcoded llama-3.3-70b-versatile, no Anthropic client anywhere in the file) -- there is no Claude path there at all, so 'research-assist's default model' incorrectly implied an alternative that doesn't exist. Everything else checked against the running repo (test count, CI workflow name, all 20 titles/tmdb_ids/spoiler labels, 8 researched entries + their translations, gitignore vs project-layout table, README anchor links, v1.0.0 release tag) and found accurate -- no further changes needed there. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01YSnwX5AyHkAXxGgFxE7uu6
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Scheduled documentation-sync pass. Cross-checked
README.md/docs/DESIGN.mdagainstsrc/preshow/,evals/,content/researched/,tests/,.github/workflows/tests.yml, and GitHub itself (open PRs, latest release). Most docs were already accurate (previous doc-sync PR #8 had done a thorough job); found and fixed three real inaccuracies:docs/DESIGN.mdD10 table saidcontent/researched/*.jsonhas "7, hand-written" entries — the repo actually has 8 (Gone Girl was added later; D14's own prose already said 8, only this table row was stale).docs/DESIGN.mdD14 still described best-of-3 draft generation as "not implemented yet" — but two later commits (33722d3,329c93c) implemented it and confirmed it working live against Groq, updating onlyCLAUDE.mdand neverdocs/DESIGN.md. Replaced the stale paragraph with what actually happened: the fix, the transient Groq 403 that blocked the first live attempt and its unexplained resolution, the live confirmation numbers (3/3 candidates, 4/4/5 grounded claims), and the minorauthor_voicequality gap found in that run.README.mdStack section claimed Anthropic Claude powers "research-assist drafting."webapp/research_assist.pyonly importsgroq.Groqand hardcodesllama-3.3-70b-versatile— no Anthropic client anywhere in that file. Reworded so Groq is described as the only model that tool uses.Docs-only change — no
src//webapp//evals//tests/files touched.Verified consistent and left untouched: test count (8, matches CI badge), CI workflow, all 20 titles have
tmdb_id+ label files, translation cache counts (8 researched + 12 browse-tier = 20), model names cited in results tables,.gitignorevs. the "Project layout" table, and all README anchor links.Flagged for manual review (out of scope for this run — not repo doc files)
twistify.onrender.com) this run — this environment's egress proxy blocks it. README's own cold-start/filesystem-wipe caveats should still be trusted as-is.v1.0.0are stale (say "7 curated entries," list judge-external-calibration and the baseline run as "pending" — both now done) — a Release body isn't a repo file, so out of this task's scope; worth a manual edit if it matters for portfolio presentation.evals/results/substring_calibration.jsonhas a leftover Spanish-language"nota"field predating the project's English-only pass — a data artifact underevals/, not documentation, flagging for a possible follow-up cleanup.How to verify
docs/DESIGN.mdD10/D14 vs.content/researched/*.json(8 files) andwebapp/research_assist.py'sdraft_best_of(); README Stack section vs.webapp/research_assist.py's imports.Per this repo's CLAUDE.md, once CI (
tests.yml) is green this PR will be merged without further confirmation.🤖 Generated with Claude Code
Generated by Claude Code