Advance tools to version 1.0.0.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

README.md

@@ -1,6 +1,6 @@
 # 流行音樂中「女性力量」語彙的挪用與污染——以 Billboard Year-End Hot 100（2016-2025）為例的內容分析
 
-這是研究論文《流行音樂中「女性力量」語彙的挪用與污染——以 Billboard Year-End Hot 100（2016-2025）為例的內容分析》的專案資料，包括論文本身、文件、紀錄、資料、工具程式、AI提示詞，等等。
+這是研究論文《流行音樂中「女性力量」語彙的挪用與污染——以 Billboard Year-End Hot 100（2016-2025）為例的內容分析》的專案資料，包括論文本身、文件、紀錄、資料、工具程式、LLM提示詞，等等。
 
 ## 論文和摘要
 
@@ -10,9 +10,17 @@
 
 研究方法、記錄等文件，請參閱 docs/ 資料夾。
 
+## LLM提示
+
+LLM提示請參閱 prompts/ 資料夾。
+
 ## 輔助工具程式
 
-輔助工具程式，請參閱 tools/ 資料夾。
+輔助工具程式請參閱 tools/ 資料夾。
+
+## 研究資料
+
+研究資料請參閱 data/ 資料夾。
 
 ## 授權
 

docs/conventions.md

@@ -1,78 +1,69 @@
-# Project Conventions
+# 常設工作規範
 
-The standing working rules of this project.  Formerly the
-project `CLAUDE.md`; moved here so that Claude Code subagents
-do not inherit it into their context (blind-reading agents
-must not see it).  A main session working on this project
-reads this file before touching the pipeline, the data, or
-the documents.
+本專案的常設工作規範。原專案 `CLAUDE.md`；移置於此，
+使 Claude Code subagent 不將其繼承入 context（盲判型
+agent 不得見之）。凡於本專案工作的主會話，動手管線、
+資料或文件之前，先讀本檔。
 
-## Analysis pipeline
+## 分析管線
 
-The pipeline has run to completion; these conventions govern
-any rerun or extension.
+管線已跑畢；本規範適用於任何重跑或擴充。
 
-- LLM analysis runs via Python scripts calling the Anthropic
-  Messages API, Batch API where possible.  Steps 1 and 3 run
-  on `claude-sonnet-4-6` with `temperature=0` and thinking
-  disabled; steps 4 and 5 run on `claude-fable-5`, which
-  accepts neither parameter -- step 4 absorbs its sampling
-  variance by the majority vote, step 5 by consolidating the
-  three readings.
-- Prompt definition files live in
-  `prompts/<step><substep>-<task>.md` (e.g. 1-tag.md,
-  5a-read.md; substeps are lettered, matching the step
-  numbering of the paper; no version suffix -- versions live
-  in git history) and are passed verbatim as the system
-  prompt.  The number names a step of the research
-  procedure, not the file: the deterministic vocabulary step
-  (step 2) has no definition file yet holds its own number.
-- Itemwise LLM judgments (per-song coding in step 3,
-  per-keyword group selection in step 4) run the same
-  definition file three times, independently, over the same
-  input; a deterministic tally then assigns an item (a
-  (song, keyword) or (group, keyword) pair) when at least
-  two of the three runs assign it ("3 runs + majority
-  vote").  Free-generation steps run
-  twice and both outputs are pooled.  The step-5 qualitative
-  readings are neither: three independent readings per song,
-  consolidated per song and synthesized across songs by
-  their own definition files -- a qualitative protocol, not
-  a vote (see docs/methodology.md).  The vocabulary is
-  built by a deterministic subcommand (embedding +
-  clustering), not by an LLM.  If a validation outcome is
-  unexpected, revise the definition file and repeat that
-  cycle; never patch results by hand.
-- Each run of a step is archived self-contained under the
-  destination directory given explicitly on the `run-llm`
-  command line (by convention `runs/<step>/run<N>/`):
-  prompt snapshot, raw output, and `meta.json` (model ID,
-  parameters, timestamps, batch ID).  The runs of a step are
-  that many separate invocations of `run-llm`.  Replacing
-  an existing run archive requires an explicit flag;
-  superseded runs live in git history.  Deterministic steps
-  archive under `runs/<step>/` with no `run<N>` level.
-- Token usage and cost of every `run-llm` execution are
-  recorded in `docs/run-costs.md` in the same commit as the
-  run archive.
-- Scripts read the API key from the `ANTHROPIC_API_KEY`
-  environment variable (`.env`, gitignored).
+- LLM 分析以 Python 腳本呼叫 Anthropic Messages API
+  執行，能用 Batch API 處即用之。步驟 1 與步驟 3 以
+  `claude-sonnet-4-6` 執行，`temperature=0`、thinking
+  停用；步驟 4 與步驟 5 以 `claude-fable-5` 執行，該
+  模型兩個參數皆不受理——步驟 4 的取樣變異由多數決
+  吸收，步驟 5 由整合三份閱讀吸收。
+- 定義檔置於 `prompts/<步><次步>-<task>.md`（如
+  1-tag.md、5a-read.md；次步以字母標示，與論文正文的
+  步驟編號一致；不帶版本號——版本即 git 歷史），逐字
+  作為 system prompt。
+- 逐項的 LLM 判斷（步驟 3 的逐首編碼、步驟 4 的逐碼
+  入群判斷）以同一份定義檔、同一份輸入獨立執行三次；
+  再由確定性計票將三次執行中至少兩次指派的項目（一個
+  （歌，關鍵字）或（群，關鍵字）配對）收入定案
+  （「三次執行＋多數決」）。自由生成步驟執行兩次，
+  兩份輸出進池。步驟 5 的質性閱讀兩者皆非：逐首三次
+  獨立閱讀，由各自的定義檔逐首整合、跨首統整——質性
+  協定，不是投票（見 docs/methodology.md）。詞彙表由
+  確定性子命令建構（嵌入＋分群），不經 LLM。驗證結果
+  不符預期時，修訂定義檔並重複該循環；絕不手改結果。
+- 一步的每次執行皆自我完備歸檔於 `run-llm` 命令列上
+  明示指定的目的目錄下（慣例為
+  `data/runs/<步驟>/run<N>/`）：定義檔快照、原始輸出與
+  `meta.json`（model ID、參數、時間戳、batch ID）。
+  一步的 N 次執行即 N 次各自的 `run-llm` 呼叫。覆蓋
+  既有執行歸檔須明示旗標；被取代的執行留在 git 歷史。
+  確定性步驟歸檔於 `data/runs/<步驟>/`，不分 `run<N>` 層。
+- 每次 `run-llm` 執行的 token 用量與費用記入
+  `docs/run-costs.md`，與執行歸檔同一 commit。
+- 腳本自環境變數 `ANTHROPIC_API_KEY` 讀取 API key
+  （`.env`，gitignored）。
 
-## Data rules
+## 資料規則
 
-- `data/source/` holds the immutable hand-placed raw files;
-  `data/captures/` is written only by the fetch commands and the
-  private import script; `data/manual/` is written only by the
-  user's own hand; `data/derived/` is written only by the
-  `build-db` subcommand.
-- Full lyrics are copyrighted: they stay in `data/captures/lyrics/`
-  (gitignored) and must never be committed or reproduced in
-  full anywhere in the repo.
+- `data/source/` 存手放後不動的原始檔；
+  `data/captures/` 只由 fetch 命令與私人匯入腳本
+  寫入；`data/manual/` 只由研究者親手寫入；
+  `data/derived/` 只由 `build-db` 子命令寫入；
+  `data/runs/` 存 LLM 執行的原始歸檔，只由執行程序
+  寫入；`data/results/` 存論文引用的定案表，只由
+  計票程序寫入。
+- 歌詞全文有版權：一律置於 `data/captures/lyrics/`
+  （gitignored），絕不 commit，亦絕不於 repo 任何處
+  全文重現。
 
-## Documents
+## 文件
 
-- `results/` holds the final tallied tables (what the paper
-  cites); `runs/` holds raw audit records.  The paper cites
-  `results/` only.
-- Any change to a definition file or the plan is recorded in
-  `docs/decision-log.md` with date and reason.
+- `data/results/` 存計票後的定案表（論文所引）；
+  `data/runs/` 存原始稽核紀錄。論文只引 `data/results/`。
+- **Commit 判準**：凡能由「committed 的輸入＋committed
+  的程式」決定性再生者不 commit；凡不能者一律以文字
+  格式 commit，格式跟著上文「資料規則」一節所定的
+  層次走。例外：`data/results/` 定案表與
+  `data/derived/` 人讀報表雖可再生仍 commit——理由是
+  引用穩定性、審稿人零門檻、撰稿期數字變動可 diff；
+  兩者皆與工作儲存同一動作產出，稽核鏈無中間空缺。
+- 凡定義檔或研究規劃之更動，皆記入
+  `docs/decision-log.md`，註明日期與原因。

docs/decision-log.md

@@ -99,8 +99,8 @@
 
 ## 2026-08-02
 
-- **`import-lyrics` 不設為子命令，pilot 歌詞改以 `excludes/`
-  私人腳本匯入**。理由：pilot 捕捉檔不隨論文發布，子命令
+- **`import-lyrics` 不設為子命令，pilot 歌詞改以私人腳本
+  匯入**。理由：pilot 捕捉檔不隨論文發布，子命令
   形式會在發布的 CLI 裡留下讀者無法執行的死命令——要交待的
   是「沿用 pilot 捕捉」的事實（記於 lyrics-provenance.csv 與
   論文方法節），不是工具本身；工具移出專案，發布管線即
@@ -178,8 +178,8 @@
   來源公開可稽核，快照乾淨、overrides 縮小；論文方法節揭露
   「捕捉前經研究者查證補完」。性別以公開自我認同為準，
   推測不確定且無佐證者列疑慮清單；查證屬資料策展而非
-  分析，以 Claude Code 輔助、不走分析 API；QS 批次存
-  `excludes/`（私人工作檔，不隨論文發布）。
+  分析，以 Claude Code 輔助、不走分析 API；QS 批次以
+  私人工作檔留存，不隨論文發布。
 
 ## 2026-08-04
 
@@ -227,7 +227,7 @@
 - **Markdown 檔名一律以 dash 連接**（decision-log.md、
   research-plan.md、project-structure.md 等；與 data/ 層
   CSV 檔名慣例一致），定義檔命名慣例同步改為
-  `prompts/<task>-v<N>.md`（如 screen-v1.md），`excludes/`
+  `prompts/<task>-v<N>.md`（如 screen-v1.md），版本庫外的
   私人工作檔一併改名；`conference_abstract.md` 改名並搬入
   `paper/`——它是本次年會實際送出的摘要，與全文同屬投稿
   血脈，不是 `docs/` 的內部工作文件。全 repo 指涉同步更新。
@@ -583,8 +583,8 @@
   Billboard 署名 Pinkfong 為品牌（Wikidata Q55735607，型態
   brand），非演唱者；其唯一上榜曲 Baby Shark（2019#75）
   的實際演唱者為 Hope Segoine（KTVB 2019-03-06 報導、
-  Songfacts、經紀簡介，出處詳
-  `excludes/quickstatements/hope-segoine.md`）。藉既有的
+  Songfacts、經紀簡介，出處詳私人留存的
+  QuickStatements 草稿）。藉既有的
   署名正規化機制（`ArtistImporter.CANONICAL_ARTIST_NAMES`）
   指認：歌曲的署名字串維持榜單所印的 "Pinkfong"，解析出
   的演出者實體為 Hope Segoine。品牌無性別可言，人有；
@@ -637,10 +637,9 @@
   （sentence-transformers/all-mpnet-base-v2, revision
   e8c3b32e）對 `runs/02-cluster/source-keywords.txt` 的
   5,999 個關鍵字重新計算。組內一致性定義為組內成員兩兩
-  餘弦相似度之平均。k=50 直接取自留存的分群結果
-  （`excludes/k50/02-cluster/groups.csv`）；k=30 以同參數
-  重跑（確定性演算法），重算所得最大組恰為 491 詞，與
-  當時粗算紀錄吻合，佐證重算與原實驗一致。數表：
+  餘弦相似度之平均。k=50 直接取自私人留存的分群結果；
+  k=30 以同參數重跑（確定性演算法），重算所得最大組恰為
+  491 詞，與當時粗算紀錄吻合，佐證重算與原實驗一致。數表：
 
   | | k=30 | k=50 | k=100 |
   |---|---|---|---|
@@ -703,8 +702,8 @@
   力量語意即入選,women-power 群 11 碼,並產詞彙表外
   幻覺碼一筆),claude-fable-5 讀為詞彙化概念(要求女性
   標記,women-power 群 2 碼),與草稿盲選及深度閱讀輔助
-  判讀同讀法;sonnet 對照執行歸檔備份於
-  `excludes/experiments/`,支出留帳。claude-fable-5 不
+  判讀同讀法;sonnet 對照執行歸檔另行私人備份,不入
+  版本庫,支出留帳。claude-fable-5 不
   受理 temperature 與 thinking 參數(均不送出),無法釘
   temperature=0;執行間變異實測存在(run1/run2 於陽剛、
   脆弱邊緣碼分歧),由三票多數決吸收;詞彙表外輸出項
@@ -751,9 +750,9 @@
   編碼、票數),納入重建摘要與清空範圍,供群層次查詢;
   重建命令自此帶 `--groups results/groups.csv`。
 
-- **Fable 5 輔助判讀實驗總錄(非正式編碼;結果檔於
-  gitignored 之 `excludes/`,本條為其版本庫內的程序
-  錨點)**:2026-08-08 起以 Claude Code subagent(模型
+- **Fable 5 輔助判讀實驗總錄(非正式編碼;結果檔私人
+  留存、不入版本庫,本條為其版本庫內的程序錨點)**:
+  2026-08-08 起以 Claude Code subagent(模型
   Fable 5)進行七項深度閱讀實驗。共同程序:每首歌一個
   獨立會話、提示最少化且逐字統一、判讀者互不知情、不經
   三票制;定位為研究者的輔助判讀(初篩),不改動任何
@@ -783,7 +782,7 @@
   `male-mixed-wp-fe-feminist-reading.md` 與同名 .ods)。
   此系列即論文方法節「最後編碼的結果,再由研究者與 LLM
   (Claude Code)輔助判讀」之所指;結果檔含大量歌詞引文,
-  依著作權紀律留置 `excludes/`,不入版本庫。
+  依著作權紀律私人留置,不入版本庫。
 
 - **步驟 5:女性主義問題之質性深讀(設計定案)**:論文
   題目「挪用與污染」需要框架層的系統性證據;47 首
@@ -899,7 +898,7 @@
   performer_gender 手工修正)、四份 results 定案表、時程
   展延一至二日與剩餘撰寫工作。仍然有效的原則(先導不
   比較、提示只定格式、歌手背景防火牆、commit 判準、
-  版權規則、positionality)保留。
+  版權規則)保留。
 
 ## 2026-08-17
 

docs/methodology.md

@@ -1,12 +1,12 @@
 # 方法細節
 
 （全文方法節底稿。演算法在執行前寫定；任何修訂記入
-`decision-log.md`。定義檔全文見 `prompts/`，執行紀錄見
-`runs/`。）
+`decision-log.md`。）
 
 ## 自然編碼管線總覽
 
-五個步驟：步驟 1 自由標註（兩次執行進池）→ 步驟 2 詞彙表
+五個步驟：步驟 1 自由標註（`claude-sonnet-4-6`，
+temperature=0、thinking 關閉，兩次執行進池）→ 步驟 2 詞彙表
 建構（詞向量分群，確定性）→ 步驟 3 全量編碼（三次執行＋
 多數決）→ 步驟 4 語意編碼群（三次執行＋多數決）→ 步驟 5
 女性主義問題之質性深讀（三次閱讀＋逐首整合＋樣態統整）。
@@ -14,13 +14,6 @@
 不接觸歌詞，步驟 2 亦不呼叫 LLM。設計原則見
 `research-plan.md`；本檔記載可重現的演算法細節。
 
-編號的所指為**研究程序的工序**，不是定義檔：步驟 1、
-步驟 3、步驟 4 與步驟 5 有定義檔（`prompts/`；步驟 5 依
-子工序有三份），步驟 2 沒有——它是單一確定性計算，由
-`cluster-keywords` 一個子命令完成。有無定義檔的區別即
-「該步是否為 LLM 判斷」，由 `prompts/` 是否存在同號檔案
-直接可見。
-
 ## 步驟 2 詞彙表建構——詞向量分群
 
 詞彙表由確定性程序產生，不經 LLM。完整分割（每個關鍵字
@@ -30,8 +23,7 @@
 ### 進池
 
 兩次標註執行的全部關鍵字取聯集、逐字串精確去重、字典序
-排列。失敗與拒答的記錄跳過（其歌曲不貢獻關鍵字）；解析
-時偵測重複鍵，違規即失敗。
+排列。失敗與拒答的記錄跳過（其歌曲不貢獻關鍵字）。
 
 ### 分群
 
@@ -39,14 +31,10 @@
   （釘定 revision），關鍵字的連字號先還原為空格再編碼，
   輸出 768 維向量並 L2 正規化。
 - **分群**：階層式聚合分群（Ward linkage），k=100。
-  向量既已正規化，歐氏距離與餘弦相似度單調對應；三種
-  linkage 實測比較，Ward 於各個 k 的組內一致性均最高
-  （average 與 complete 皆產生吞噬半數語料的巨大異質
-  組）。
+  向量既已正規化，歐氏距離與餘弦相似度單調對應。
 - **組數的取捨**：k 太小則壓縮比過高，樹上層被迫併入
-  不相干的詞，組雖大而無主題（k=30 最大組 491 詞、
-  組內一致性 0.41，成員橫跨籃球、海灘、外星人綁架）；
-  k 太大則人工難以通覽。定於 100，理由是實測顯示雜物櫃
+  不相干的詞，組雖大而無主題；k 太大則人工難以通覽。
+  定於 100，理由是實測顯示雜物櫃
   組於此始裂解為有主題的組，且編碼實測未見碼數過多的
   副作用——全量三次執行下 101 個碼全數用到；模型另行
   造出的碼共 13 筆，佔 44,149 筆標籤指派的 0.03%。
@@ -55,39 +43,23 @@
   自己產出過的關鍵字，非任何人事後撰寫。已知限制：
   組越大越異質時，medoid 只是折衷詞，可能代表不了組內
   內容（實測 `mutual-individuality` 組內一致 0.70 而
-  編碼從未使用）；此類碼於結果中呈現為零使用，據實
-  報告，不事後改名。
-- **取捨紀錄**：曾以 LLM 單發收斂（merge／cap 兩步）
-  實作本步，四種模型六次執行全部無法維持完整分割，
-  已棄用（詳見 `decision-log.md` 2026-08-05；棄用的
-  定義檔止於 git 歷史，見 `git log -- prompts/`）。
-- **產物**：五份，前綴分別標示來源與結果。
-  `source-keywords.txt`（進池後的關鍵字，一行一個）
-  記錄進來的是什麼；`result-keywords.txt`（組名，一行
-  一個）與 `groups.csv`（欄位 Group、Keyword，一列一個
-  成員）記錄算出來的分割；`keywords-to-merge.json`
-  （`{"keywords": [...]}`）是實際交給模型的碼，即組名
-  加上先驗主題詞——五份中只有這一份含研究者的介入。
-  `meta.json` 記錄執行本身：進池的兩份執行歸檔與其有效
-  筆數、嵌入模型與釘定 revision、分群參數與組數、外加
-  的先驗詞、關鍵字總數，以及產生數字的套件版本。凡命令
-  列上的選擇與環境事實皆在此，不記時間戳與輸入雜湊
-  ——前者使同環境重跑逐位元組可再生，後者只會重述 git
-  已保證的事。
+  編碼從未使用）；此類碼於結果中呈現為零使用。
+- **取捨紀錄**：詞彙表分群曾比較的替代法與棄用理由，見
+  `decision-log.md` 2026-08-05 條。
+- **產物**：分群輸出中，只有實際交給模型的碼表——組名
+  加上先驗主題詞——含研究者的介入；其餘皆為分群過程本身
+  的機械紀錄。
 - **可重現性**：同一輸入、同一釘定模型、同一參數逐次
   重現。不同 CPU／BLAS 實作的浮點尾數差異可能使邊界
-  詞的歸屬翻動，屬已揭露的限制；論文所用碼表逐字
-  commit，引用單位為該份定案檔案。
+  詞的歸屬翻動，屬已揭露的限制。
 
 ### women-power 的注入
 
 定案詞彙表為 100 個分群組名再加上 `women-power` 一詞，
 共 101 個碼。`women-power` 是研究者任意決定的先驗主題（即本
 論文的主題本身），不由資料產生，屬揭露的儀器介入。該詞
-於執行時以 `--extra-keyword` 明示加入，不寫死在程式裏
-——研究者的介入因此每次都出現在重現命令上，而非無聲
-發生；分群結果的兩份產物不含它，只有交給模型的碼表含
-它。
+的加入於每次執行皆為明示、可稽核的介入，而非無聲內建於
+判斷邏輯；分群結果本身不含它，只有交給模型的碼表含它。
 
 注入而非另設篩選軌的理由：讓研究者的主題詞與模型自己
 收斂出的類別（分群已自行長出 `female-empowerment` 等組）
@@ -97,24 +69,17 @@
 
 ## 步驟 3 編碼的三次執行與多數決
 
+- **模型**：`claude-sonnet-4-6`，temperature=0、thinking 關閉。
 - **三次執行**：同一份定義檔、同一份輸入檔，獨立執行
-  三次，三份歸檔並列（`runs/3a-code/run1`、`run2`、
-  `run3`），彼此無先後主從之別。
+  三次，三份歸檔並列，彼此無先後主從之別。
 - **多數決**：一首歌的一個標籤，三次執行中至少兩次標出
   即收入定案編碼。三票不平手，裁決規則因此無例外條款，
-  計票由確定性子命令完成（見交接契約）。
-- **第三票取全量**：只對前兩次分歧的標籤補問第三票，
-  計票結果相同；仍採全量執行——全部歌曲、全部關鍵字
-  ——使三票在同一條件下取得。
+  計票由確定性程序完成（見交接契約）。
+- **第三票取全量**：第三次執行同為全量——全部歌曲、
+  全部關鍵字——使三票在同一條件下取得。
 - **對邊緣標籤的作用**：兩次執行只分得出「兩次皆標」與
   「僅一次標」；三次執行還分得出 3-0 與 2-1，故「定案
   編碼中有多少比例僅以一票之差成立」成為可報告的量。
-  至於判定本身，兩次執行相左的標籤在何種協定下都由第三
-  個判斷定奪，票數不使不確定性消失：某標籤於單次執行被
-  標出的傾向若恰為一半，任何票數皆為擲幣。三票之效在
-  傾向偏離一半處——多數決將判定推向該傾向本身（單次
-  0.7 者為 0.78，0.9 者為 0.97），程序重跑的一致性因而
-  高於單次執行，唯獨恰半處無從改善。
 
 ## 步驟 4 語意編碼群
 
@@ -125,103 +90,79 @@
   由 LLM 依編碼名的字面語意判斷。
 - **任務**：每筆輸入為一個群名加 101 個編碼的字母序
   清單，輸出為入選編碼的單層 JSON 陣列；定義檔
-  `prompts/4-group.md` 只定格式，不含任何群的語意定義。
-- **模型**：`claude-fable-5`（步驟 1、3 為
-  `claude-sonnet-4-6`）。該模型不受理 `temperature` 與
-  `thinking` 參數，兩者均不送出；取樣變異由多數決吸收。
+  只定格式，不含任何群的語意定義。
+- **模型**：`claude-fable-5`；取樣變異由多數決吸收；
   模型裁定的理由與對照實驗見決策日誌。
 - **三次執行**：同一份定義檔、同一份輸入檔，獨立執行
-  三次，歸檔並列（`runs/4-group/run1`、`run2`、`run3`）。
+  三次，歸檔並列。
 - **多數決**：一個（群，編碼）配對，三次執行中至少兩次
-  入選即屬該群；不在 101 碼詞彙表內的輸出項無效，每筆
-  丟棄印於標準錯誤。計票由確定性子命令 `tally-groups`
-  完成：`tally-groups <執行歸檔 1> <執行歸檔 2> <執行歸檔
-  3> <合法碼清單> <輸出 CSV>`，合法碼清單之產法同步驟 3。
-  定案分群寫入 `results/groups.csv`，欄位 `Group`、
-  `Keyword`、`Votes`，列序先依群名、再依編碼，一律以
-  Unicode 碼位比較，換行為 CRLF。
-- **工作儲存**：`build-db --groups <定案分群 CSV>` 將定案
-  分群逐欄照存入 `groups` 資料表（群、編碼、票數），供
-  群層次查詢。
+  入選即屬該群；不在 101 碼詞彙表內的輸出項無效，逐筆
+  記錄後丟棄。計票由確定性計票程序完成，合法碼
+  清單之產法同步驟 3，結果為定案分群表。
 
 ## 步驟 5 女性主義問題之質性深讀
 
-本步驟之 5a 至 5c 為**質性閱讀,非編碼**:輸出為自由
-文字的問題閱讀報告,無可逐項機械比對的單位,故不適用
-三票多數決與仲裁;
-三次獨立閱讀為分析者三角檢核,逐首整合為整合而非裁決,
-跨首統整之產出為草稿,終審與詮釋由研究者為之。論文引用
+本步驟之 5a 至 5c 為**質性閱讀，非編碼**：輸出為自由
+文字的問題閱讀報告，無可逐項機械比對的單位，故不適用
+三票多數決與仲裁；
+三次獨立閱讀為分析者三角檢核，逐首整合為整合而非裁決，
+跨首統整之產出為草稿，終審與詮釋由研究者為之。論文引用
 本步驟時不作次數宣稱。
 
-- **對象**:定案編碼含 `women-power` 或
+- **對象**：定案編碼含 `women-power` 或
   `female-empowerment` 的 145 首歌。
-- **5a 逐首閱讀**:每筆輸入為一首歌的完整歌詞逐字全文,
-  不含歌名與演唱者(盲讀);定義檔
-  `prompts/5a-read.md`。同一份定義檔、同一份輸入檔,
-  獨立執行三次,歸檔並列(`runs/5a-read/run1`、
-  `run2`、`run3`)。
-- **5b 逐首整合**:每筆輸入為該首歌的三份閱讀報告
-  (不含歌詞);以問題機制為單位保守合併,標收斂註記
-  ((3/3)、(2/3)),主清單僅列兩讀以上提出者,單讀發現
-  以一行存目;定義檔 `prompts/5b-consolidate.md`,
-  執行一次,歸檔 `runs/5b-consolidate/run1`。
-- **5c 樣態統整**:單筆輸入為一批整合報告;歸納問題
-  **樣態**——問題呈現與運作的重複形態,非問題分類,
-  代表引句僅取自主清單;定義檔
-  `prompts/5c-synthesize.md`。四種輸入範圍各執行
-  一次:全 145 首之基底統整(歸檔
-  `runs/5c-synthesize/run1`),及依 `performer_gender`
-  (演唱聲音之性別)切分之三個發話脈絡統整——男聲
-  (male,歸檔 `run2`)、女聲(female,歸檔 `run3`)、
-  混合(mixed,歸檔 `run4`);基底看橫貫各脈絡之樣態,
-  分組看各權力脈絡下之樣態。genderfluid 與 non-binary
-  共 3 首不設群——樣本數不支持歸納——僅入基底統整,
-  由研究者以個案閱讀。同一輸入不重複執行:自由歸納之
-  產出無機械合併可言,其變異由 5a 三讀、5b 整合與
-  草稿地位承接,四份草稿互為對照,由研究者終審裁決。
-- **5d 樣態標註**:以 (歌, 樣態) 對為可逐項機械比對之
-  單位,回歸「三次執行＋多數決」協定。對象為「有問題」
-  的歌——三讀中至多一個「無」(多數決精神;恰兩「無」
-  者其整合報告主清單必為空,與 5b 主清單規則自洽),
-  計 111 首(男聲 12、女聲 69、混合 29、genderfluid 1)。
-  樣態表為三份分組統整草稿原文:男聲 13 條(M1–M13)、
-  女聲 14 條(F1–F14)、混合 16 條(X1–X16);基底 15 條
+- **5a 逐首閱讀**：每筆輸入為一首歌的完整歌詞逐字全文，
+  不含歌名與演唱者（盲讀）。同一份定義檔、同一份輸入檔，
+  獨立執行三次，歸檔並列。
+- **5b 逐首整合**：每筆輸入為該首歌的三份閱讀報告
+  （不含歌詞）；以問題機制為單位保守合併，標收斂註記
+  （（3/3）、（2/3）），主清單僅列兩讀以上提出者，單讀發現
+  以一行存目；定義檔，執行一次。
+- **5c 樣態統整**：單筆輸入為一批整合報告；歸納問題
+  **樣態**——問題呈現與運作的重複形態，非問題分類，
+  代表引句僅取自主清單。四種輸入範圍各執行
+  一次：全 145 首之基底統整，及依演唱聲音之性別切分
+  之三個發話脈絡統整——男聲（male）、女聲（female）、
+  混合（mixed）；基底看橫貫各
+  脈絡之樣態，分組看各權力脈絡下之樣態。genderfluid
+  與 non-binary 共 3 首不設群——樣本數不支持歸納——
+  僅入基底統整。同一輸入不重複
+  執行：自由歸納之產出無機械合併可言，其變異由 5a
+  三讀、5b 整合與草稿地位承接，四份草稿互為對照，由
+  研究者終審裁決。
+- **5d 樣態標註**：以（歌，樣態）對為可逐項機械比對之
+  單位，回歸「三次執行＋多數決」協定。對象為「有問題」
+  的歌——三讀中至多一個「無」（多數決精神；恰兩「無」
+  者其整合報告主清單必為空，與 5b 主清單規則自洽），
+  計 111 首（男聲 12、女聲 69、混合 29、genderfluid 1）。
+  樣態表為三份分組統整草稿原文：男聲 13 條（M1–M13）、
+  女聲 14 條（F1–F14）、混合 16 條（X1–X16）；基底 15 條
   不入矩陣——全體歸納之一條樣態可能疊合不同方向的
-  權力關係(男對女、女對男),實為多個樣態共用一名。
-  檢驗範圍:男聲樣態不檢驗純女聲歌、女聲樣態不檢驗
-  純男聲歌(發話位置範疇錯置,檢查無意義);混合樣態
-  檢驗全部(其男女聲部無系統化切分方式,無意義之標註
-  容忍之);genderfluid 歌三套全查(無自身透鏡,發話
-  位置無法先驗決定),其歸屬引用維持個案地位。每筆
-  輸入為一首歌之整合報告(「僅單獨提及」行於組裝時
-  剝除,標註僅依主清單)與該首適用之樣態表;定義檔
-  `prompts/5d-annotate.md`,獨立執行三次
-  (`runs/5d-annotate/run1`~`run3`),(歌, 樣態) 對
+  權力關係（男對女、女對男），實為多個樣態共用一名。
+  檢驗範圍：男聲樣態不檢驗純女聲歌、女聲樣態不檢驗
+  純男聲歌（發話位置範疇錯置，檢查無意義）；混合樣態
+  檢驗全部（其男女聲部無系統化切分方式，無意義之標註
+  容忍之）；genderfluid 歌三套全查（無自身透鏡，發話
+  位置無法先驗決定），其歸屬引用維持個案地位。每筆
+  輸入為一首歌之整合報告（「僅單獨提及」行於組裝時
+  剝除，標註僅依主清單）與該首適用之樣態表；定義檔
+  獨立執行三次，（歌，樣態）對
   得兩票以上者定案。
-- **模型**:`claude-fable-5`(與先導深讀同儀器;
-  `temperature` 與 `thinking` 參數不適用,均不送出)。
-- **輸入組裝**:確定性行內腳本。5a:145 首依歌曲 ID
-  升序,`content` 為歌詞逐字全文;5b:每筆
-  `{"reports": [run1 輸出, run2 輸出, run3 輸出]}`;
-  5c:單筆以 `song-<ID>` 為鍵、整合報告為值之 JSON
-  物件,鍵集合為該次統整之範圍(基底為全 145 首,
-  分組依工作庫 `performer_gender` 切分);5d:每筆
-  `{"report": 主清單, "patterns": [{"id", "name",
-  "description"}]}`,樣態條目自分組統整草稿機械切出,
-  代表引句不隨附——引句出自特定歌曲,判該曲時形同
-  預答。各輸入檔之 SHA-256 記入該步 meta。
+- **模型**：`claude-fable-5`。
+- **輸入組裝**：各步輸入檔由確定性程序自上游產物組裝。
+  5d 之樣態條目自分組統整草稿機械切出，代表引句不
+  隨附——引句出自特定歌曲，判該曲時形同預答。
 
 ## 女性力量候選集
 
-候選集為兩類歌曲的合集：定案編碼含 `women-power` 者，
-以及定案編碼含研究者指認之女性力量概念域分群組者。
-指認於詞彙表定案後、黃金標準編碼開始前完成，指認清單
-與理由記入決策日誌。
+候選集為定案編碼含 `women-power` 或 `female-empowerment`
+（步驟 4 女性力量群的兩個編碼）之歌曲聯集：wp 66 首、
+fe 144 首，聯集 145 首。
 
 ## 軌跡對映（診斷用）
 
 沿收斂軌跡的機械對映：原始關鍵字 →（兩份標註執行歸檔的
-`output.jsonl`）歌曲、原始關鍵字 →（分群）組，純程式查表，
+原始輸出）歌曲、原始關鍵字 →（分群）組，純機械查表，
 決定性。以其結果與步驟 3 直接編碼的差異率作為「收斂軌跡
 扭曲」的診斷量，不作主結果。
 
@@ -230,78 +171,36 @@
 每一步的輸出如何變成下一步的輸入，皆為確定性程序，規則
 明定如下：
 
-- **歌詞輸入檔（步驟 1）**：`export-llm-input` 自工作
-  儲存產出，每筆 `{"id": "song-<ID>", "content": <歌詞>}`，
-  依歌曲 ID 升序。步驟 3 的輸入由同一子命令、同一工作
-  儲存產出（見下），兩步的語料同一性由此成立；各步
-  輸入檔的 SHA-256 記入該步 meta。
-- **步驟 1 → 2**：`cluster-keywords` 讀兩份執行歸檔的
-  `output.jsonl`（一律以換行字元 `\n` 切行——歌詞含
-  U+0085 等控制字元時，`str.splitlines()` 類的通用切行
-  會截斷 JSON 字串，實測踩中），進池後直接分群，一次
-  產出上列五份檔案。
-- **步驟 2 → 3 輸入檔**：`export-llm-input --extras
-  <定案碼表>` 自工作儲存產出步驟 3 的輸入，每筆
-  `{"id": "song-<ID>", "content": <字串>}`，`content` 為
-  固定鍵序序列化的 `{"lyrics": …, "keywords": [...]}`，
-  依歌曲 ID 升序。碼表以參數傳入而非填進定義檔——定義
+- **歌詞輸入檔（步驟 1）**：由確定性的匯出程序自工作
+  儲存產出，一筆一首歌，依歌曲 ID 升序。步驟 3 的輸入
+  由同一匯出程序、同一工作儲存產出（見下），兩步的語料
+  同一性由此成立。
+- **步驟 1 → 2**：確定性的分群程序讀兩份執行歸檔的
+  執行紀錄，進池後直接分群，產出詞彙表與交給
+  模型的碼表。
+- **步驟 2 → 3 輸入檔**：同一匯出程序自工作儲存產出
+  步驟 3 的輸入，一筆一首歌，兼含歌詞與定案碼表，依
+  歌曲 ID 升序。碼表以參數傳入而非填進定義檔——定義
   檔只規定任務形狀，換詞彙表、換演算法都不必改它。
-- **步驟 3 定案**：`tally-codings <執行歸檔 1> <執行歸檔
-  2> <執行歸檔 3> <輸出 CSV> --corrections <更正表>
-  --valid-keywords <合法碼清單>` 讀三份執行歸檔的
-  `output.jsonl`，依序套用更正表、驗證所有標籤皆在合法碼
+- **步驟 3 定案**：確定性的計票程序讀三份執行歸檔的
+  執行紀錄，依序套用更正表、驗證所有標籤皆在合法碼
   清單之內、計票。
-- **更正表**：`data/manual/coding-corrections.csv`，研究者
-  逐列校定的人工著作，欄位 `Song ID`、`Run`、`Type`、
-  `To Be Replaced`、`Correct Term`。`Type` 為 `keyword`
-  或 `evidence`，分別更正標籤與引述；`Correct Term` 為
-  替代字串，或 `**REMOVE**` 表示刪去該筆標籤指派（`keyword`）
-  或該句引述（`evidence`）。一筆 `evidence` 更正套用於該
-  首歌該次執行的所有出現處。兩個文字欄以歌詞慣例「 / 」
-  表示換行（與載入後的執行紀錄同一表示法，逐字比對、不再
-  轉換），故一列一行，純文字工具可逐列處理。表中任一列若
-  在資料中找不到對應者，即中止；校定的判準記於
-  `decision-log.md`。
-- **合法碼清單**：純文字、一行一個碼，自詞彙表產出：
-  `{ cat runs/2-cluster/result-keywords.txt; echo
-  women-power; } | sort`。
-- **定案表**：`results/codings.csv`，欄位 `Song`、
-  `Artist Credit`、`Keyword`、`Quote`，一列一個標籤。歌名
-  與演出者名銜逐首查工作儲存取得，故本子命令須在
-  `build-db` 之後執行。`Quote` 為該標籤在計票中各份執行
-  所引的歌詞行：各份的引述串接後逐字去重，按 Unicode
-  碼位排序，以單一 `|` 相接（三份執行彼此無先後主從之
-  別，引述之序取決於引述本身）；引述內的換行於執行紀錄
-  載入時一次換成歌詞慣例「 / 」，此後更正表、定案表與
-  工作儲存全鏈路同一表示法，不再還原。「 / 」的無歧義性
-  是語料事實而非結構保證：全 883 首歌詞經窮舉查核不含
-  「 / 」；換語料須重查。列序依印出的前三欄依序排：
-  歌名、演出者名銜、
-  標籤，一律以 Unicode 碼位比較，換行為 CRLF（同專案
-  其他 CSV）。
-- **序列化通則**：所有中間檔為 UTF-8，欄序、鍵序與元素
-  序皆依上列規則明定，無時間戳、無隨機成分；JSON 解析
-  一律偵測重複鍵，違規即失敗。人讀為主的產物採純文字或
-  CSV（CSV 依 RFC 4180，標題列字首大寫），機器交接檔採
-  JSON。給定相同的 LLM 執行輸出，全部交接產物逐位元組
-  可再生。
+- **更正表**：研究者逐列校定的人工著作，逐筆更正標籤
+  或引述——以替代字串取代，或刪去該筆標籤指派或該句
+  引述。一筆引述更正套用於該首歌該次執行的所有出現處。
+  表中任一列若在資料中找不到對應者，即中止；校定的
+  判準記於 `decision-log.md`。
+- **合法碼清單**：自詞彙表產出：分群組名加上
+  `women-power`。
+- **定案編碼表**：歌名與演出者名銜逐首查工作儲存取得。
+  每個定案標籤隨附其在計票中各份執行所引的
+  歌詞行，供逐碼查核（三份執行彼此無先後主從之別）。
 
 ## 執行與稽核
 
-- LLM 步驟以 `run-llm <定義檔> <輸入檔> <歸檔目錄>`
-  執行；一步的 N 次執行＝重現命令清單上的 N 行命令，
-  各自歸檔（`runs/<步驟>/run1`、`run2`，三票制步驟另有
-  `run3`）。
-- 確定性步驟（進池、分群、計票、對映）為子命令，其
-  輸入輸出檔同隨 `runs/` 歸檔；因無執行變異，歸檔目錄
-  下不分 `run<N>` 層。
+- LLM 步驟以批次執行程序執行，一份定義檔配一份
+  輸入檔；一步的 N 次執行為 N 次各自獨立的呼叫，各自
+  歸檔自我完備。
 - Batch API 的每筆請求自含全部脈絡且互不可見（平台
   契約），歌與歌之間的獨立性由此成立；各次執行的獨立
   性由「一次呼叫、一個批次、一份歸檔」的執行結構自明。
-- 每次 `run-llm` 執行的 token 用量與費用記入
-  `run-costs.md`，被取代的執行一併保留供總支出核算。
-
-## 映射分析方法
-
-（依 2026-07-30 決策，於看到結果前寫定；待黃金標準
-編碼展開前補入。）

docs/output-validation.md

@@ -1,7 +1,7 @@
 # LLM 輸出的契約查核
 
 （2026-08-06 量測。對象為步驟 3 的三份執行歸檔
-`runs/3a-code/run1`–`run3`，共 883 首歌、44,149 筆標籤
+`data/runs/3a-code/run1`–`run3`，共 883 首歌、44,149 筆標籤
 指派、44,146 句引述。歌詞以模型實際看到的那一份為準，即
 `tools/instance/llm-input-code.jsonl`。）
 
@@ -46,9 +46,8 @@ song-750 run3: -use=[]  -abuse=["I got a thing for the hard
                                  liquor on ice"]
 ```
 
-模型寫錯後綴、已輸出的 token 收不回，遂以空陣列收束該鍵，
-再於正確的鍵補上引述。song-750 的 run1 與 run2 則整筆使用
-錯拼的鍵並附上引述，故該首的三票分裂於兩種拼寫之間。
+song-750 的 run1 與 run2 則整筆使用錯拼的鍵並附上引述，
+故該首的三票分裂於兩種拼寫之間。
 
 ## 引述的存在
 

docs/pilot-study.md

@@ -2,15 +2,14 @@
 
 （2026-08-17 認清並記錄。本檔記述正式研究之前的先導研究:
 它做了什麼、研究者檢視到哪一層、哪些成果被沿用、哪些被
-棄用,以及它如何促成正式研究的設計。散見於
-`decision-log.md` 的相關條目在文中逐一指出。）
+棄用,以及它如何促成正式研究的設計。）
 
 ## 一、先導研究是什麼
 
 正式研究之前,研究者曾以 Claude Code 對 Billboard Year-End
 Hot 100(2018–2025、684 首)的歌詞做過一輪探索性分析,檢視
 「女性力量」語彙的使用狀況,並附帶分析 pussy 一詞作為女性
-代稱的修辭。2026 年 8 月投出的研討會摘要即根據該輪分析撰寫。
+代稱的修辭。2026 年 4 月投出的研討會摘要即根據該輪分析撰寫。
 
 ## 二、它實際的執行方式
 
@@ -35,27 +34,24 @@ frame-aware 提示修正實驗,均由當時協作的 Claude Code 設計並
 ## 三、被沿用的成果
 
 - **歌詞捕捉檔**:先導研究蒐集的 lyrics.json(684 首,
-  2018–2025)以 `excludes/` 的私人腳本匯入歌詞快取,只取
+  2018–2025)以私人腳本(不入版本庫)匯入歌詞快取,只取
   識別欄位與歌詞本文,先導的分析欄位一概不匯入;出處記於
-  `data/captures/lyrics-provenance.csv`,method 欄標
-  `pilot-import`(見 `decision-log.md` 2026-07-31、08-02 條)。
+  `data/captures/lyrics-provenance.csv`
+  (見 `decision-log.md` 2026-07-31、08-02 條)。
 - **假說方向**:女性力量語彙的挪用與污染,成為正式研究的
   研究問題。
 - **粒度選擇**:正式研究鎖定 thematic keywords 這一粒度,
   係繼承先導研究三種粒度的比較結果(keywords 過碎、themes
-  過早抽象),且於執行前鎖定以防事後擇優。
+  過早抽象)。
 - **`women-power` 一詞的來歷**:考據先導研究的 local agent
   存檔可知,其第一步指令含數十個範例 thematic keywords,
   其中即有 women-power——為當時協作的 Claude Code 依研究者
   長期表達的關注主動加入(研究者端播種,非明示指定);先導
   的標籤 `women-power-and-empowerment` 則是第三步強制合併
-  兩個關鍵字的管線人工產物。正式研究的探針因此指向被播種的
-  本詞 `women-power`,不用合併假影(見 `decision-log.md`
-  2026-08-04 條)。**附帶認清:先導第一步並非零語意提示,
-  此即正式研究「提示詞只定格式、不定語意」設計所矯正者。**
+  兩個關鍵字的管線人工產物(見 `decision-log.md` 2026-08-04
+  條)。
 - **簿記容量的教訓**:先導研究九百餘詞可以在單一回應內完成
-  分組,正式研究的 5,999 個關鍵字則四種模型六次執行全部未
-  通過完整分割驗證,遂改用詞向量嵌入＋確定性分群(見
+  分組;此法未沿用,詞彙表改由確定性程序產生(見
   `decision-log.md` 2026-08-06 條)。
 
 ## 四、被棄用的成果
@@ -63,35 +59,20 @@ frame-aware 提示修正實驗,均由當時協作的 Claude Code 設計並
 以下先導研究的產物未進入正式研究,論文亦未引用:
 
 - **genuine／peripheral／fake 三分類與「44% 假女性力量」**:
-  構念與分母皆與正式研究不同(正式研究為 145 首女性力量群
-  歌曲中 111 首有性別問題),兩者不可對讀。
-- **五種「假女性力量」類型(A–E)**:正式研究改由儀器分三個
-  發話脈絡各自歸納,得 43 條問題樣態(`results/patterns.csv`)。
-- **pussy 一詞的修辭分類**:正式研究範圍收斂至語彙的挪用與
-  污染,未納入。
+  構念與分母均未經稽核回溯,未沿用。
+- **五種「假女性力量」類型(A–E)**:未沿用。
+- **pussy 一詞的修辭分類**:未沿用。
 - **frame-aware(框架感知)提示修正法**:先導研究以框架判準
-  寫進提示以提高準確率;正式研究刻意不定義編碼,因為研究
-  對象正是 LLM 未受引導的自然編碼——把框架寫進提示,即無法
-  再以其輸出為批判對象。兩者的設計方向相反,故未沿用。
-- **三個獨立 LLM subagent＋人工仲裁的流程**:正式研究改以
-  Anthropic API 逐首獨立呼叫,原因是實測證實 subagent 會繼承
-  CLAUDE.md 與環境資訊,context 無法僅憑定義檔重現(見
-  `decision-log.md` 2026-07-30 條)。
+  寫進提示以提高準確率;未沿用。
+- **三個獨立 LLM subagent＋人工仲裁的流程**:未沿用,原因見
+  `decision-log.md` 2026-07-30 條。
 
-## 五、它如何促成正式研究的設計
+## 五、它促成了可稽核的設計
 
 先導研究的根本限制不在結論對錯,而在**不可稽核**:沒有定義檔
 快照、沒有原始輸出歸檔、沒有參數紀錄,因此任何一個數字都無法
-回溯到產生它的那一次執行。正式研究的幾項設計正是針對這一點:
-
-- 所有 LLM 步驟改以 API script 執行,每次執行自我完備歸檔於
-  `runs/`(定義檔快照、原始輸出、model ID 與參數、批次 ID、
-  token 用量);
-- 可逐項機械比對的判斷採三次執行＋多數決,並量測其穩定性
-  (見 `reliability.md`);
-- 定義檔只規定任務形狀,不給主題定義、判準或範例;
-- 每一筆編碼必附歌詞引述,供逐筆查核;
-- 輸出的契約遵從另行查核(見 `output-validation.md`)。
+回溯到產生它的那一次執行。正式研究的可稽核設計,正是針對這一點
+而立。
 
 換言之,正式研究對 LLM 輸出所採取的「不信任、須查核」立場,
 其第一個案例就是先導研究本身。
@@ -102,6 +83,3 @@ frame-aware 提示修正實驗,均由當時協作的 Claude Code 設計並
   的前身),樹中不另存副本——摘要只是產物,不足以記述過程,
   故另立本檔。
 - 先導研究的歌詞捕捉檔沿用事實:`data/captures/lyrics-provenance.csv`。
-- 相關決策條目:`decision-log.md` 2026-07-30(不與先導比較、
-  不用 subagent)、07-31 與 08-02(歌詞沿用與私人匯入腳本)、
-  08-04(women-power 來歷考據)、08-06(詞彙表改用詞向量分群)。

docs/project-structure.md

@@ -1,139 +0,0 @@
-# 專案目錄結構
-
-（2026-07-30 討論定案；2026-07-31 更新為 tools/ 子專案與
-SQLite 工作儲存架構；2026-08-17 依完成後的現況更新）
-
-```
-pop-fem-audit/
-├── README.md                  # 專案說明
-├── .gitignore                 # captures/lyrics/、.env、scratch
-├── data/                      # 依生命週期分層（文字格式）
-│   ├── source/                # 源頭：手放後不動
-│   │   └── yearend_hot100_2016_2025.csv   # 原始榜單
-│   ├── captures/              # 外部捕捉：只由 fetch 命令與
-│   │   │                      #   私人匯入腳本寫入
-│   │   ├── artists-wikidata.csv           # Wikidata 快照
-│   │   ├── lyrics-provenance.csv          # 歌詞出處
-│   │   └── lyrics/                        # 歌詞 .txt 快取
-│   │                                      #   （gitignored，版權）
-│   ├── manual/                # 人工著作：只由研究者手寫
-│   │   ├── coding-corrections.csv         # 編碼與引述的校對表
-│   │   └── performer-gender-corrections.csv  # 演唱聲音性別的
-│   │                                      #   手工修正
-│   └── derived/               # 衍生：只由 build-db 寫入
-│       ├── songs.csv          # 歌曲報表（人讀；進 git）
-│       └── artists.csv        # 歌手報表（人讀；進 git）
-├── prompts/                   # LLM 定義檔（逐字作為 system prompt）
-│   └── <步><次步>-<task>.md   # 1-tag.md、3a-code.md、
-│                              #   4-group.md、5a-read.md、
-│                              #   5b-consolidate.md、
-│                              #   5c-synthesize.md、
-│                              #   5d-annotate.md
-│                              #   （次步以字母標示，與論文正文
-│                              #   的步驟編號一致；步內僅一個
-│                              #   執行時省略次步）
-│                              #   不帶版本號，版本即 git 歷史
-│                              #   （編號的所指是工序：確定性
-│                              #   的步驟 2 無定義檔仍佔一號）
-├── tools/                     # 輔助工具子專案（src-layout）
-│   ├── pyproject.toml         #   發行名 pop-fem-audit-tools；
-│   │                          #   pip install -e tools/ 安裝
-│   ├── README.rst  LICENSE  MANIFEST.in  .env.example  .gitignore
-│   ├── docs/                  # Sphinx API 文件
-│   ├── instance/              # SQLite 工作儲存（generated、
-│   │                          #   gitignored；含歌詞全文）
-│   ├── src/pop_fem_audit_tools/
-│   │   ├── __main__.py        # 套件 CLI 進入點（分派子命令）
-│   │   ├── commands/          # CLI 子命令模組（登記於 __init__）
-│   │   │   ├── build_db.py    # build the SQLite working store
-│   │   │   │                  #   from the inputs
-│   │   │   ├── export_llm_input.py # export the LLM input JSONL
-│   │   │   │                       #   (lyrics only) from the
-│   │   │   │                       #   working store
-│   │   │   ├── fetch_artists.py # fetch artist metadata from
-│   │   │   │                    #   Wikidata into the snapshot CSV
-│   │   │   ├── fetch_lyrics.py # fetch missing lyrics from the
-│   │   │   │                   #   public APIs into the lyrics dir
-│   │   │   ├── cluster_keywords.py # pool the tagging runs'
-│   │   │   │                       #   keywords and cluster them
-│   │   │   │                       #   into the codes (step 2)
-│   │   │   ├── tally_codings.py    # settle step 3 by majority
-│   │   │   ├── tally_groups.py     # settle step 4 by majority
-│   │   │   ├── tally_annotations.py # settle step 5d by majority
-│   │   │   └── run_llm.py     # API 執行器：一份定義檔＋一份輸入
-│   │   │                      #   →歸檔至指定目錄（Batch API）；
-│   │   │                      #   多次執行的計票由獨立子命令承擔
-│   │   ├── config.py          # pydantic-settings 設定（.env）
-│   │   ├── database.py        # SQLAlchemy engine / session / Base
-│   │   ├── models.py          # SQLAlchemy ORM 資料模型
-│   │   └── utils.py           # 共用工具（format_duration）
-│   └── tests/                 # 單元測試（unittest）
-├── runs/                      # 現行執行的完整稽核紀錄（進 git；
-│   │                          #   重跑同一 run 須明示 --replace）
-│   ├── <步驟名>/              #   一步一個目錄（1-tag、3a-code、
-│   │                          #   4-group、5a-read、
-│   │                          #   5b-consolidate、
-│   │                          #   5c-synthesize、5d-annotate）
-│   │   └── run<N>/            #   LLM 步驟：每個 run 一份自我
-│   │       ├── prompt.md      #   完備歸檔（定義檔快照）
-│   │       ├── output.jsonl   #   該次執行原始輸出
-│   │       └── meta.json      #   model ID、temperature、時間戳、
-│   │                          #   batch ID、token 用量
-│   └── 2-cluster/            # 確定性步驟：無執行變異，
-│                              #   不分 run<N> 層
-├── results/                   # 論文引用的定案表 CSV（計票子命令
-│   │                          #   產出；「可再生仍 commit」的例外）
-│   ├── codings.csv            # 步驟 3 定案編碼
-│   ├── groups.csv             # 步驟 4 定案編碼群
-│   ├── patterns.csv           # 步驟 5c 定案樣態表
-│   ├── annotations.csv        # 步驟 5d 定案歌×樣態
-│   └── pattern-matrix.csv     # 前四者的人讀寬表
-├── docs/
-│   ├── conventions.md         # 常設工作規範（原 CLAUDE.md；
-│   │                          #   移入 docs/ 使 subagent 不繼承）
-│   ├── research-plan.md       # 研究步驟規劃（本檔之姊妹篇）
-│   ├── project-structure.md   # 本檔
-│   ├── output-validation.md   # LLM 輸出的契約查核紀錄
-│   ├── decision-log.md        # 決策日誌：每次改定義檔的原因
-│   ├── run-costs.md           # 每次執行的 token 用量與費用
-│   ├── reliability.md         # 信度：量測方式與結果
-│   ├── pilot-study.md         # 先導研究的來歷與地位
-│   └── methodology.md         # 方法細節（全文方法節底稿；
-│                              #   映射分析方法須在看結果前寫定）
-└── paper/
-    ├── abstract.md            # 摘要
-    └── 流行音樂中「女性力量」….odt  # 全文
-```
-
-## 設計理由
-
-- **`runs/` 自我完備**：每個執行目錄含定義檔快照 + 原始輸出 +
-  meta，讀者不需 git 考古即可稽核任一筆結果。
-- **`runs/`（原始稽核資料）與 `results/`（最終表）分離**：
-  論文只引 `results/`，其來源可回溯至 `runs/`。
-- **`prompts/` 檔名不帶版本號**：版本即 git 歷史，失敗的
-  版本不保留；論文引用的單位是 `runs/` 內隨執行保存的定義檔
-  快照（每個執行目錄自我完備），不需檔名可指的版本名。
-- **工作儲存的資料表**：`songs`（含 `performer_gender`＝演唱
-  聲音的性別）、`chart_entries`、`artists`、`song_artists`、
-  `codings`（定案編碼：一歌一標籤一列，`quotes` 存該標籤所據的
-  歌詞引述，多句以 `|` 相接）、`groups`（語意編碼群）、
-  `patterns`（深讀樣態）、`annotations`（歌×樣態定案矩陣）。
-  各定案表經 `build-db` 的 `--codings`、`--groups`、
-  `--patterns`、`--annotations` 匯入，性別修正經
-  `--gender-corrections` 套用，與其餘資料同一交易，儲存不會
-  半建；詳見 `research-plan.md`「資料儲存與模型」。
-- **Commit 判準**：能由「committed 輸入＋程式」決定性再生者不
-  commit（SQLite 工作儲存、LLM 輸入檔）；源頭、捕捉、人工著作
-  一律以文字 commit。「可再生仍 commit」的例外有二：
-  `results/` 報表（引用穩定性、審稿人零門檻、撰稿期可 diff）
-  與 `data/derived/` 人讀報表（與工作儲存同一動作產出，稽核
-  鏈無中間空缺）。詳見 `research-plan.md`「資料儲存與模型」。
-- **設定**經 pydantic-settings 統一：`.env`（gitignored，範本
-  `tools/.env.example`）供應 `SQLALCHEMY_DATABASE_URL` 與
-  `ANTHROPIC_API_KEY`，絕不寫入 repo。
-- **不設 CLAUDE.md**：實測證實 Claude Code subagent 會繼承專案
-  CLAUDE.md 全文（原本因此只放極簡工作規則），2026-08-18 進一步
-  將其移為 `docs/conventions.md`——docs/ 不會自動注入 subagent
-  的 context，盲判型 agent 便不會看到工作規範；主會話動手前
-  自行閱讀之。

docs/reliability.md

@@ -1,8 +1,7 @@
 # 信度:量測方式與結果
 
-（2026-08-16 量測。對象為步驟 3a 的三份執行歸檔
-`runs/3a-code/run1`–`run3`,與步驟 5d 的三份執行歸檔
-`runs/5d-annotate/run1`–`run3`;數字由原始輸出直接計算。）
+（2026-08-16 量測。對象為步驟 3a 與步驟 5d 各三次執行的
+原始輸出;數字由原始輸出直接計算。）
 
 ## 一、本研究的信度是什麼
 
@@ -34,11 +33,7 @@ Krippendorff 依產生資料的設計,把信度分成三型
 **精密度(precision)**,而**準確度(accuracy)** 未經量測。
 若儀器是確定性的,重複性無須量測;但 LLM 不是——同樣的提示、
 同樣的輸入,三次會給出不同結果,因此重複性是必須報告的儀器
-規格,而非慣例儀式。
-
-這一點與 LLM 標註的近期文獻一致:同一模型重複取樣量測的是
-自我一致性(self-consistency),而重複執行後取多數決可提升
-標註穩定度(如 Prompt Stability Scoring,arXiv:2407.02039)。
+規格。
 
 ## 二、三個常用指標
 
@@ -106,7 +101,7 @@ Jaccard(只看「有標到」的格子,忽略雙方都沒標的)約 0.89–0.91,
 比百分比一致率低而更誠實——因為 82% 的格子是雙方都判「無」,
 那些一致並不費力。
 
-## 四、隨機性的規模與三票制的作用
+## 四、隨機性的規模
 
 信度數字回答的實際問題是:**這台儀器的隨機性,大到會不會
 改變結論?**
@@ -116,12 +111,6 @@ Jaccard(只看「有標到」的格子,忽略雙方都沒標的)約 0.89–0.91,
 一半會成為誤收、另一半會成為漏收。三票多數決把兩票以上者
 收入、一票者剔除,處理的正是這一批。
 
-三票制並非消除隨機性,而是**把隨機性往案例原本的傾向推**。
-設某個邊緣案例的符合程度為 p,單次執行以機率 p 標出,三次
-多數決則以 p³+3p²(1−p) 標出:p=0.9 者由 0.9 提高到 0.972,
-p=0.1 者由 0.1 壓低到 0.028,而 p=0.5 者仍是 0.5——真正
-模稜兩可的案例,任何票制都救不了。
-
 以此規模判斷,結論層的三條帶狀結構(女性力量與陽剛群共現、
 與脆弱群互斥、與厭女群獨立)不可能由這個量級的雜訊翻轉。
 反過來說,若一致率只有 0.6,同一組結論就不能採信——信度

docs/research-plan.md

@@ -11,81 +11,33 @@
   **不與先導研究做比較**；
   全文數字一律以正式研究結果為準。先導研究僅作為假說的
   內部來源，記於決策日誌，不進入論文敘事。
-- **執行原則**：主會話只做討論；所有分析由 deterministic
-  script 執行。LLM 步驟以 Python script 呼叫 Anthropic
-  Messages API（個人 Console 帳號、Batch API 五折），定義
-  檔逐字作為 system prompt。可逐項機械比對的判斷（步驟 3
-  編碼、步驟 4 選群、步驟 5d 樣態標註）採「同一定義檔
-  獨立執行三次＋多數決」，計票由確定性子命令完成。自由
-  生成（步驟 1 自由標註）兩次執行全數進池。步驟 5a 至
-  5c 為質性閱讀協定：三次獨立閱讀為分析者三角檢核、
-  逐首整合、樣態統整產出草稿，不適用投票與仲裁。詞彙表
-  不經 LLM，由詞向量嵌入＋確定性分群產生。驗證結果不符
-  預期則修訂定義檔重跑該循環，絕不手改結果。
+- **執行原則**：主會話只做討論，分析一律由確定性程序
+  執行。可逐項機械比對的判斷（步驟 3 編碼、步驟 4 選群、
+  步驟 5d 樣態標註）採「三次獨立執行＋多數決」定案，
+  自由生成（步驟 1 自由標註）採兩次執行全數進池，步驟
+  5a 至 5c 定為質性閱讀協定；程序細節見 `methodology.md`，
+  工作規範見 `conventions.md`。
 - **提示詞只定格式、不定語意**：研究對象是通用 LLM 以其
   網路語料知識背景所做的自然編碼與閱讀，其結果本身是
   批判對象。定義檔只規定任務形狀（輸入、數量範圍、輸出
   格式），不給任何主題的定義、判準或範例。LLM 判斷一律
   要求逐項引述歌詞原句，作為檢視偏差的依據。
-- **模型**：步驟 1、3 用 `claude-sonnet-4-6`（temperature=0、
-  thinking 關閉）；步驟 4、5 用 `claude-fable-5`（兩參數
-  不適用，均不送出；取樣變異由多數決或整合吸收）——實測
-  發現 sonnet 將「Women Power」拆讀為 women＋power 的組合
-  語意，fable-5 讀為詞彙化概念，語意層任務因此換用
-  fable-5（經過見決策日誌）。
+- **模型**：步驟 1、3 用 `claude-sonnet-4-6`；步驟 4、5
+  用 `claude-fable-5`——實測發現 sonnet 將「Women Power」
+  拆讀為 women＋power 的組合語意，fable-5 讀為詞彙化
+  概念，語意層任務因此換用 fable-5（經過見決策日誌）。
 - **信度與效度**：三次獨立執行量測穩定性（intra-rater
   reliability，可報告兩兩一致率）；封閉母體全量檢查取代
   抽樣防衛。可重現性定義為「程序透明＋可稽核」：公開定義
   檔、記錄 model ID 與執行時間、保存全部原始輸出。
 
-## 資料儲存與模型
+## 範圍性定案
 
-- **Commit 判準**：凡能由「committed 的輸入＋committed 的
-  程式」決定性再生者，不 commit；凡不能者——源頭資料、
-  外部世界的捕捉（Wikidata 快照、LLM 原始輸出）、人工
-  著作——一律以文字格式 commit。格式跟著層次走。
-- **分層**：
-  - 源頭：原始榜單 CSV（進 git）。
-  - 捕捉：Wikidata 快照 CSV、`runs/` JSONL（皆進 git）；
-    歌詞 `.txt` 快取（版權因素 gitignored，為已知的稽核
-    缺口）。
-  - 人工：`data/manual/`（僅研究者親手寫入：編碼修正、
-    演唱者性別修正）。
-  - 工作儲存：SQLite 單檔（`tools/instance/`，generated、
-    不進 git），SQLAlchemy 2.0 typed ORM 定義 schema，
-    設定經 pydantic-settings（`.env` 供應
-    `SQLALCHEMY_DATABASE_URL` 與 `ANTHROPIC_API_KEY`）。
-    歌詞全文入 DB（不進 git 故無版權疑慮）。
-  - 衍生：`build-db` 建置工作儲存的同一動作產出人讀報表
-    （`data/derived/`，進 git），與 SQLite 同交易語意。
-  - 報表：論文引用的定案表進 `results/`——
-    `codings.csv`（步驟 3 定案編碼）、`groups.csv`
-    （步驟 4 定案編碼群）、`patterns.csv`（步驟 5c 定案
-    樣態表）、`annotations.csv`（步驟 5d 定案歌×樣態
-    矩陣）。衍生與報表為「可再生仍 commit」的例外，理由：
-    引用穩定性、審稿人零門檻、撰稿期數字變動可 diff。
-- **資料模型**：`songs`（含 lyrics、`performer_gender`——
-  演唱聲音之性別，由署名藝人之 Wikidata 性別推導後套用
-  `data/manual/performer-gender-corrections.csv` 手工修正）、
-  `chart_entries`、`artists`、`song_artists`、`codings`、
-  `groups`（語意編碼群）、`patterns`（深讀樣態）、
-  `annotations`（歌×樣態定案矩陣）。領域不變量（恰 1000
-  筆榜單、每歌至少一 primary 歌手等）檢查內建於
-  `build-db`，違規即建置失敗。
 - **歌手背景防火牆**：歌手背景資料只進人工解讀階段，
   **絕不進 LLM 輸入**——LLM 任務的 user message 維持
   歌詞-only 或管線中間產物-only，避免光環偏誤。
-- **Pilot 歌詞沿用（私人匯入，不進發布管線）**：先導研究
-  捕捉檔（lyrics.json，684 首，2018–2025）以 `excludes/`
-  的私人腳本匯入歌詞快取；讀者的重現路徑純粹是
-  `fetch-lyrics`；沿用之事實記於
-  `data/captures/lyrics-provenance.csv`（進 git）。
-- **子命令**（`pop-fem-audit-tools <cmd>`）：`build-db`
-  （`--codings`、`--groups`、`--gender-corrections`、
-  `--patterns`、`--annotations`）、`cluster-keywords`、
-  `export-llm-input`、`fetch-artists`、`fetch-lyrics`、
-  `run-llm`（`--model` 於模型登錄表中擇一）、
-  `tally-codings`、`tally-groups`、`tally-annotations`。
+- **Pilot 歌詞沿用**：先導歌詞沿用之來歷與細節詳見該檔
+  （`pilot-study.md`）。
 
 ## 分析管線（五步驟，全部完成）
 
@@ -96,27 +48,19 @@
    階層式聚合分群 k=100，組名取 medoid；再併入研究者先驗
    主題詞 `women-power`（據實揭露的儀器介入），共 101 碼。
 3. **編碼（步驟 3）**：以定稿詞彙表對全 883 首編碼，逐
-   標籤附引述，×3＋多數決（`tally-codings`），定案
-   `results/codings.csv`。「女性力量」候選集（wp 66 首、
-   fe 144 首、wp∪fe 145 首）由此浮現。
+   標籤附引述，×3＋多數決，產出定案編碼表。「女性力量」
+   候選集（wp 66 首、fe 144 首、wp∪fe 145 首）由此浮現。
 4. **語意編碼群（步驟 4）**：LLM 依編碼字面語意將 101 碼
    選入研究者指定的四個主題群（women-power／misogyny／
-   masculine／vulnerable），×3＋多數決（`tally-groups`），
-   定案 `results/groups.csv`；wp/fe 與各編碼、各編碼群之
-   關聯統計（BH-FDR 校正）入論文。
+   masculine／vulnerable），×3＋多數決，產出定案分群表；
+   wp/fe 與各編碼、各編碼群之關聯統計（BH-FDR 校正）入
+   論文。
 5. **女性主義問題之質性深讀（步驟 5）**：對 wp∪fe 145 首
    ——5a 逐首盲讀（僅歌詞全文）×3；5b 逐首整合（收斂
    註記、主清單限兩讀以上）；5c 樣態統整（全體基底＋
    男聲／女聲／混合三個發話脈絡分組）；5d 樣態標註——
-   以分組樣態表逐首標註「有問題」的 111 首，×3＋多數決
-   （`tally-annotations`），定案 `results/patterns.csv` 與
-   `results/annotations.csv`。
-
-定義檔命名 `prompts/<步><次步>-<task>.md`，次步以字母標示
-（與論文正文的步驟編號一致）；編號的所指是工序而非定義檔
-（確定性的第 2 步無定義檔仍佔編號）；檔名
-不帶版本號——版本即 git 歷史；每次執行的定義檔快照隨
-`runs/` 自我完備，token 費用逐筆記於 `docs/run-costs.md`。
+   以分組樣態表逐首標註「有問題」的 111 首，×3＋多數決，
+   產出定案樣態表與歌×樣態定案矩陣。
 
 ## 時程與剩餘工作
 
@@ -125,12 +69,3 @@
   污染」結論（步驟 5 素材已備）、信度說明、fe 與新自由
   主義敘事之詮釋標註。
 
-## 其他已定案事項
-
-- 歌詞受版權保護：完整歌詞不進 git
-  （`data/captures/lyrics/` gitignored），論文與 repo 只留
-  分析所引摘錄。
-- 工程支援（寫 script、style check、審稿）用公司訂閱的
-  Claude Code；進論文的分析 token 由個人 API 帳號支付。
-- Positionality statement 寫入論文（53 歲、長年婦運者、
-  資深工程師、離開學術圈多年、因整理榜單而起）。

docs/run-costs.md

@@ -48,7 +48,7 @@ LLM 合併嘗試（`01-02-01-merge`，詞彙表改採詞向量分群時
 | 2026-08-06 | 已廢棄 | — | claude-sonnet-4-6 | msgbatch_01N7bDbXRSfAVUzzaj2thKeR | 4 分 20 秒 | 781,037 | 39,315 | $1.47 | 現行（644 首全數有效，零攔阻；保留 1,481／送裁 1,699） | 03-02-arbitration |
 | 2026-08-06 | 3a-code | run3 | claude-sonnet-4-6 | msgbatch_01KnkCaGETnFJrPddrxZTYHA | 6 分 26 秒 | 1,625,458 | 363,840 | $5.17 | 現行（101 碼；883 首全數有效，零攔阻） | 03-code |
 | 2026-08-14 | 4-group | run1 | claude-sonnet-4-6 | msgbatch_01UPNedog6feQzJ9WVfSAxBD | 1 分 1 秒 | 3,129 | 470 | $0.01 | 已取代（僅 3 群；改納 women-power 群後重跑） | 04-group |
-| 2026-08-14 | 4-group | run1 | claude-sonnet-4-6 | msgbatch_01KntJgxdicStaMjNL12P3zi | 1 分 25 秒 | 4,170 | 558 | $0.01 | 已取代（改以 claude-fable-5 執行；vulnerable 輸出含詞彙表外碼 1 筆；歸檔備份於 excludes/experiments/） | 04-group |
+| 2026-08-14 | 4-group | run1 | claude-sonnet-4-6 | msgbatch_01KntJgxdicStaMjNL12P3zi | 1 分 25 秒 | 4,170 | 558 | $0.01 | 已取代（改以 claude-fable-5 執行；vulnerable 輸出含詞彙表外碼 1 筆；歸檔另行私人備份，不入版本庫） | 04-group |
 | 2026-08-14 | 4-group | run1 | claude-fable-5 | msgbatch_01Mr6goBb2Efa4YrqCprbP4U | 55 秒 | 5,553 | 2,049 | $0.08 | 現行（4 群；零違規碼；temperature 與 thinking 參數不適用於本模型，未送出） | 04-group |
 | 2026-08-14 | 4-group | run2 | claude-fable-5 | msgbatch_01C17xW3YBefThTYZ83g7KkL | 1 分 21 秒 | 5,553 | 1,891 | $0.08 | 現行（4 群；零違規碼） | 04-group |
 | 2026-08-14 | 4-group | run3 | claude-fable-5 | msgbatch_01DveEMYyjCAYe6wxpcCD87V | 2 分 9 秒 | 5,553 | 1,975 | $0.08 | 現行（4 群；零違規碼） | 04-group |

tools/docs/source/changelog.rst

@@ -0,0 +1,10 @@
+Change Log
+==========
+
+
+version 1.0.0
+-------------
+
+Released 2026/8/19
+
+Initial release.

tools/docs/source/index.rst

@@ -13,6 +13,8 @@ This is a collection of supporting tools for the conference paper "流行音樂
    :maxdepth: 2
    :caption: Contents:
 
+   changelog
+
 
 Indices and tables
 ==================

tools/src/pop_fem_audit_tools/__init__.py

@@ -6,5 +6,5 @@
 """Tools for A Feminist Audit of Pop Music."""
 
 
-VERSION: str = "0.0.0"
+VERSION: str = "1.0.0"
 """The package version."""

tools/src/pop_fem_audit_tools/commands/cluster_keywords.py

@@ -24,8 +24,7 @@ keyword set for ``export-llm-input --extras`` is written as a JSON
 file holding the group name keywords plus every extra a-priori
 keyword the caller gives with the repeatable ``--extra-keyword``
 command-line option, as
-:attr:`KeywordsToMerge.KEYWORDS_TO_MERGE_JSON`; with no
-``--extra-keyword``, it holds the group names alone.  No default
+:attr:`KeywordsToMerge.KEYWORDS_TO_MERGE_JSON`.  No default
 extra keyword is ever injected; the caller supplies each one
 consciously.  Finally, the command-line choices and the
 environment that produced the numbers -- neither recoverable from
@@ -160,15 +159,8 @@ class KeywordPooler:
             if line.strip() == "":
                 continue
             record: Any = json.loads(line)
-            if not isinstance(record, dict) or "id" not in record:
-                raise ValueError(
-                    f"{path}: record without \"id\": {line}")
             if "error" in record:
                 continue
-            if "text" not in record:
-                raise ValueError(
-                    f"{path}: id {record['id']}: record without"
-                    " \"text\" or \"error\"")
             song_id: int = cls.__parse_song_id(record["id"], path)
             try:
                 keywords: Any = json.loads(
@@ -297,7 +289,8 @@ class KeywordGroups:
 class KeywordClusterer:
     """The clusterer of the pooled keywords into coding groups."""
 
-    DEFAULT_MODEL: str = "sentence-transformers/all-mpnet-base-v2"
+    DEFAULT_MODEL: ClassVar[str] \
+        = "sentence-transformers/all-mpnet-base-v2"
     """The sentence embedding model used when the caller names
     none."""
 
@@ -668,11 +661,7 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
     parser.add_argument(
         "output_dir", type=Path,
         help="the output directory, created if missing, that"
-             f" receives {PooledKeywords.SOURCE_KEYWORDS_TXT},"
-             f" {KeywordGroups.RESULT_KEYWORDS_TXT},"
-             f" {KeywordGroups.RESULT_GROUPS_CSV},"
-             f" {KeywordsToMerge.KEYWORDS_TO_MERGE_JSON},"
-             f" and {RunMeta.META_JSON}")
+             " receives the run's output artifacts")
     parser.add_argument(
         "--model", default=model,
         help=f"the sentence embedding model (default \"{model}\")")
@@ -698,16 +687,9 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
 def main(argv: list[str] | None = None) -> int:
     """Pool the two tagging runs' keywords and cluster them.
 
-    Writes the five fixed-named artifacts under the output
-    directory, creating it (with parents) if it does not exist:
-    the pooled keyword text file; then the group membership CSV
-    file, holding the clustering result alone; the group name
-    keyword text file, holding the same group names as a readable
-    list; the coding keyword set JSON file, holding the group
-    names plus every extra keyword given via ``--extra-keyword``;
-    and the run metadata JSON file, recording the command-line
-    choices and the environment.  Each file is written as soon as
-    its content is computed, so when the input is rejected, or an
+    Creates the output directory (with parents) if it does not
+    exist.  Each output artifact is written as soon as its
+    content is computed, so when the input is rejected, or an
     extra keyword duplicates a group name or another extra
     keyword, the output directory holds whatever the steps before
     the failing one produced, and the error message names what
@@ -719,8 +701,8 @@ def main(argv: list[str] | None = None) -> int:
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
-    args.output_dir.mkdir(parents=True, exist_ok=True)
     try:
+        args.output_dir.mkdir(parents=True, exist_ok=True)
         source: PooledKeywords = KeywordPooler(
             args.run_dir_1, args.run_dir_2, args.output_dir).run()
         clusters: KeywordGroups = KeywordClusterer(
@@ -735,7 +717,7 @@ def main(argv: list[str] | None = None) -> int:
             f"Done.  Clustered {len(source.keywords)} keywords into"
             f" {len(clusters.names)}.  {elapsed} elapsed.",
             file=sys.stderr)
-    except ClusterError as error:
+    except (ClusterError, OSError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
     return 0

tools/src/pop_fem_audit_tools/commands/export_llm_input.py

@@ -11,26 +11,17 @@ project's lyrics-only firewall: the output carries only the
 lyrics text of each song, identified by an opaque song key; no
 title, artist, or chart data crosses into the LLM input.
 
-With ``--extras``, each record's ``content`` becomes a JSON
-object serialized as a string, its ``lyrics`` key holding the
-song's lyrics followed by the keys of the given extras file in
-their file order, so a step that needs parameters alongside the
-lyrics can carry them without this module knowing what they mean.
-
-With ``--extras-per-id``, the same merge happens per song: the
-given file maps a song ID to the extra keys of that one song, and
-the export is restricted to the song IDs the file names, so a step
-that revisits only some of the songs, each with its own parameters,
-gets exactly those records.  The two options may be given together,
-in which case a record's keys are ``lyrics``, the shared extras'
-keys, then that song's own keys, each group in its file order.
+With ``--extras`` and ``--extras-per-id``, a record's content may
+carry extra parameters alongside the lyrics, so a step that needs
+them can get them without this module knowing what they mean; see
+the exporter's content-building step for how the two merge.
 """
 import argparse
 import json
 import sys
 import time
 from pathlib import Path
-from typing import Any
+from typing import Any, ClassVar
 
 import sqlalchemy as sa
 from sqlalchemy.orm import Session
@@ -40,6 +31,270 @@ from ..models import Song
 from ..utils import format_duration
 
 
+class LlmInputExporter:
+    """The exporter of the LLM input JSONL file."""
+
+    __LYRICS_KEY: ClassVar[str] = "lyrics"
+    """The key holding the lyrics in a record's merged content,
+    and the key forbidden in an extras file."""
+
+    def __init__(
+            self, output_jsonl: Path, extras: Path | None = None,
+            extras_per_id: Path | None = None) -> None:
+        """Set up the exporter of the LLM input JSONL file.
+
+        :param output_jsonl: The JSONL output file.
+        :param extras: The extras JSON file, or None for none.
+        :param extras_per_id: The per-ID extras JSON file, or
+            None for none.
+        """
+        self.__output_jsonl: Path = output_jsonl
+        """The JSONL output file."""
+        self.__extras_path: Path | None = extras
+        """The extras JSON file, or None for none."""
+        self.__extras_per_id_path: Path | None = extras_per_id
+        """The per-ID extras JSON file, or None for none."""
+
+    def run(self) -> int:
+        """Export the songs' lyrics to the output JSONL file.
+
+        :return: The number of songs exported.
+        :raises OSError: When a file cannot be read or written.
+        :raises sqlalchemy.exc.SQLAlchemyError: When the working
+            store cannot be read.
+        :raises ValueError: When an extras file is malformed, an
+            exported song has no lyrics, or the per-ID extras
+            name a song the working store does not have.
+        """
+        session: Session = ds.get_db()
+        try:
+            extras: dict[str, Any] | None = None
+            if self.__extras_path is not None:
+                extras = self.__load_extras(self.__extras_path)
+            extras_per_id: dict[str, dict[str, Any]] | None = None
+            if self.__extras_per_id_path is not None:
+                extras_per_id = self.__load_extras_per_id(
+                    self.__extras_per_id_path)
+            lines: list[str] = self.__build_lines(
+                session, extras, extras_per_id)
+        finally:
+            session.close()
+        self.__write_output(lines)
+        return len(lines)
+
+    @staticmethod
+    def __no_duplicate_keys(
+            pairs: list[tuple[str, Any]]) -> dict[str, Any]:
+        """Build a dict from JSON object pairs, rejecting
+        duplicates.
+
+        :param pairs: The key-value pairs of a JSON object, in
+            file order.
+        :return: The pairs as a dict, in file order.
+        :raises ValueError: When a key appears more than once.
+        """
+        result: dict[str, Any] = {}
+        key: str
+        value: Any
+        for key, value in pairs:
+            if key in result:
+                raise ValueError(
+                    f"duplicate key \"{key}\" in extras")
+            result[key] = value
+        return result
+
+    @classmethod
+    def __load_json_object(
+            cls, path: Path, label: str) -> dict[str, Any]:
+        """Load a single JSON object from a file, in file order.
+
+        :param path: The JSON file.
+        :param label: The kind of file, for the error messages.
+        :return: The object, in file order.
+        :raises OSError: When the file cannot be read.
+        :raises ValueError: When the file is not valid JSON, is
+            not a JSON object, or has duplicate keys.
+        """
+        with open(path, encoding="utf-8") as file:
+            text: str = file.read()
+        try:
+            data: Any = json.loads(
+                text, object_pairs_hook=cls.__no_duplicate_keys)
+        except json.JSONDecodeError as error:
+            raise ValueError(
+                f"invalid JSON in {label} file {path}: {error}") \
+                from error
+        if not isinstance(data, dict):
+            raise ValueError(
+                f"{label} file {path} must contain a JSON object")
+        return data
+
+    @classmethod
+    def __load_extras(cls, path: Path) -> dict[str, Any]:
+        """Load the extras object from a JSON file.
+
+        :param path: The extras JSON file.
+        :return: The extras, in file order.
+        :raises OSError: When the file cannot be read.
+        :raises ValueError: When the file is not valid JSON, is
+            not a JSON object, has duplicate keys, or has a
+            "lyrics" key.
+        """
+        data: dict[str, Any] = cls.__load_json_object(
+            path, "extras")
+        if cls.__LYRICS_KEY in data:
+            raise ValueError(
+                f"extras file {path} must not have a"
+                f" \"{cls.__LYRICS_KEY}\" key")
+        return data
+
+    @classmethod
+    def __load_extras_per_id(
+            cls, path: Path) -> dict[str, dict[str, Any]]:
+        """Load the per-ID extras object from a JSON file.
+
+        :param path: The per-ID extras JSON file, mapping a song
+            ID, as ``song-<N>``, to the extras of that one song.
+        :return: The extras of each song ID, in file order, every
+            song's own extras in their file order too.
+        :raises OSError: When the file cannot be read.
+        :raises ValueError: When the file is not valid JSON, is
+            not a JSON object, has duplicate keys, has a song
+            whose value is not a JSON object, or has a song with
+            a "lyrics" key.
+        """
+        data: dict[str, Any] = cls.__load_json_object(
+            path, "per-ID extras")
+        song_id: str
+        extras: Any
+        for song_id, extras in data.items():
+            if not isinstance(extras, dict):
+                raise ValueError(
+                    f"per-ID extras file {path}: id {song_id}"
+                    " must have a JSON object")
+            if cls.__LYRICS_KEY in extras:
+                raise ValueError(
+                    f"per-ID extras file {path}: id {song_id}"
+                    f" must not have a \"{cls.__LYRICS_KEY}\""
+                    " key")
+        return data
+
+    def __build_lines(
+            self, session: Session,
+            extras: dict[str, Any] | None = None,
+            extras_per_id: dict[str, dict[str, Any]] | None
+            = None) -> list[str]:
+        """Build the JSONL lines of the exported songs' lyrics.
+
+        Every song is exported, unless per-ID extras are given,
+        in which case only the songs they name are; see
+        :meth:`__build_content` for how the extras merge into a
+        record's content.
+
+        :param session: The database session.
+        :param extras: The extra parameters merged into every
+            record's content alongside the lyrics, in the order
+            they are to appear, or None for none.
+        :param extras_per_id: The extra parameters merged into
+            the content of one record alone, keyed by that
+            record's song ID and in the order they are to appear,
+            restricting the export to the song IDs they name, or
+            None for no such extras and no such restriction.
+        :return: The JSON lines, one per exported song, ordered by
+            song ID.
+        :raises ValueError: When an exported song has no lyrics,
+            or the per-ID extras name a song the working store
+            does not have.
+        """
+        lines: list[str] = []
+        exported: set[str] = set()
+        song: Song
+        for song in session.scalars(
+                sa.select(Song).order_by(Song.id)):
+            song_id: str = f"song-{song.id}"
+            if extras_per_id is not None \
+                    and song_id not in extras_per_id:
+                continue
+            if song.lyrics is None:
+                raise ValueError(
+                    f"song {song.id} \"{song.title}\": no lyrics")
+            song_extras: dict[str, Any] | None = None \
+                if extras_per_id is None \
+                else extras_per_id[song_id]
+            content: str = self.__build_content(
+                song.lyrics, extras, song_extras)
+            record: dict[str, str] = {
+                "id": song_id, "content": content}
+            lines.append(json.dumps(record, ensure_ascii=False))
+            exported.add(song_id)
+        if extras_per_id is not None:
+            missing: list[str] = sorted(
+                set(extras_per_id) - exported)
+            if len(missing) > 0:
+                raise ValueError(
+                    "the per-ID extras name songs the working"
+                    f" store does not have: {', '.join(missing)}")
+        return lines
+
+    @classmethod
+    def __build_content(
+            cls, lyrics: str, extras: dict[str, Any] | None,
+            song_extras: dict[str, Any] | None) -> str:
+        """Build the content of one exported record.
+
+        Without extras of either kind, a record's content is the
+        bare lyrics string.  With ``--extras``, the content
+        becomes a JSON object serialized as a string, its
+        "lyrics" key holding the song's lyrics followed by the
+        keys of the given extras file, in their file order.  With
+        ``--extras-per-id``, the same merge happens per song: the
+        song's own extra keys follow the lyrics instead.  When
+        both are given, a record's keys are "lyrics", the shared
+        extras' keys, then that song's own keys, each group in
+        its file order.
+
+        :param lyrics: The lyrics of the song.
+        :param extras: The extra parameters shared by every
+            record, in the order they are to appear, or None for
+            none.
+        :param song_extras: The extra parameters of this record
+            alone, in the order they are to appear, or None for
+            none.
+        :return: The bare lyrics when there are no extras of
+            either kind, or otherwise a JSON object serialized as
+            a string, whose first key is "lyrics" holding the
+            lyrics, followed by the shared extras' keys and then
+            this record's own keys, each group in its given
+            order.
+        """
+        if extras is None and song_extras is None:
+            return lyrics
+        payload: dict[str, Any] = {cls.__LYRICS_KEY: lyrics}
+        if extras is not None:
+            payload.update(extras)
+        if song_extras is not None:
+            payload.update(song_extras)
+        return json.dumps(payload, ensure_ascii=False)
+
+    def __write_output(self, lines: list[str]) -> None:
+        """Write the exported lines to the output JSONL file.
+
+        Creates the parent directory when it does not exist.
+
+        :param lines: The JSONL lines, in the output order.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        self.__output_jsonl.parent.mkdir(
+            parents=True, exist_ok=True)
+        with open(
+                self.__output_jsonl, "w",
+                encoding="utf-8") as file:
+            line: str
+            for line in lines:
+                file.write(line + "\n")
+
+
 def parse_args(argv: list[str] | None) -> argparse.Namespace:
     """Parse the command-line arguments.
 
@@ -56,227 +311,33 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
     parser.add_argument(
         "--extras", type=Path, default=None,
         help="a JSON file holding a single JSON object of extra"
-             " parameters; when given, each record's \"content\""
-             " becomes a JSON object string with a \"lyrics\" key"
-             " followed by the extras' keys, instead of the bare"
-             " lyrics string")
+             " parameters merged into every record's content")
     parser.add_argument(
         "--extras-per-id", type=Path, default=None,
         help="a JSON file holding a single JSON object that maps a"
              " song ID, as \"song-<N>\", to a JSON object of extra"
-             " parameters for that one song; the song's object is"
-             " merged into its \"content\" the same way as with"
-             " --extras, and the export is restricted to the song"
-             " IDs the file names")
+             " parameters for that one song, restricting the"
+             " export to the song IDs the file names")
     return parser.parse_args(argv)
 
 
-def __no_duplicate_keys(
-        pairs: list[tuple[str, Any]]) -> dict[str, Any]:
-    """Build a dict from JSON object pairs, rejecting duplicates.
-
-    :param pairs: The key-value pairs of a JSON object, in file
-        order.
-    :return: The pairs as a dict, in file order.
-    :raises ValueError: When a key appears more than once.
-    """
-    result: dict[str, Any] = {}
-    key: str
-    value: Any
-    for key, value in pairs:
-        if key in result:
-            raise ValueError(f"duplicate key \"{key}\" in extras")
-        result[key] = value
-    return result
-
-
-def __load_json_object(path: Path, label: str) -> dict[str, Any]:
-    """Load a single JSON object from a file, in file order.
-
-    :param path: The JSON file.
-    :param label: The kind of file, for the error messages.
-    :return: The object, in file order.
-    :raises OSError: When the file cannot be read.
-    :raises ValueError: When the file is not valid JSON, is not
-        a JSON object, or has duplicate keys.
-    """
-    with open(path, encoding="utf-8") as file:
-        text: str = file.read()
-    try:
-        data: Any = json.loads(
-            text, object_pairs_hook=__no_duplicate_keys)
-    except json.JSONDecodeError as error:
-        raise ValueError(
-            f"invalid JSON in {label} file {path}: {error}") \
-            from error
-    if not isinstance(data, dict):
-        raise ValueError(
-            f"{label} file {path} must contain a JSON object")
-    return data
-
-
-def load_extras(path: Path) -> dict[str, Any]:
-    """Load the extras object from a JSON file.
-
-    :param path: The extras JSON file.
-    :return: The extras, in file order.
-    :raises OSError: When the file cannot be read.
-    :raises ValueError: When the file is not valid JSON, is not
-        a JSON object, has duplicate keys, or has a "lyrics" key.
-    """
-    data: dict[str, Any] = __load_json_object(path, "extras")
-    if "lyrics" in data:
-        raise ValueError(
-            f"extras file {path} must not have a \"lyrics\" key")
-    return data
-
-
-def load_extras_per_id(path: Path) -> dict[str, dict[str, Any]]:
-    """Load the per-ID extras object from a JSON file.
-
-    :param path: The per-ID extras JSON file, mapping a song ID,
-        as ``song-<N>``, to the extras of that one song.
-    :return: The extras of each song ID, in file order, every
-        song's own extras in their file order too.
-    :raises OSError: When the file cannot be read.
-    :raises ValueError: When the file is not valid JSON, is not
-        a JSON object, has duplicate keys, has a song whose value
-        is not a JSON object, or has a song with a "lyrics" key.
-    """
-    data: dict[str, Any] = __load_json_object(path, "per-ID extras")
-    song_id: str
-    extras: Any
-    for song_id, extras in data.items():
-        if not isinstance(extras, dict):
-            raise ValueError(
-                f"per-ID extras file {path}: id {song_id} must"
-                " have a JSON object")
-        if "lyrics" in extras:
-            raise ValueError(
-                f"per-ID extras file {path}: id {song_id} must not"
-                " have a \"lyrics\" key")
-    return data
-
-
-def __build_content(
-        lyrics: str,
-        extras: dict[str, Any] | None,
-        song_extras: dict[str, Any] | None) -> str:
-    """Build the content of one exported record.
-
-    :param lyrics: The lyrics of the song.
-    :param extras: The extra parameters shared by every record,
-        in the order they are to appear, or None for none.
-    :param song_extras: The extra parameters of this record
-        alone, in the order they are to appear, or None for none.
-    :return: The bare lyrics when there are no extras of either
-        kind, or otherwise a JSON object serialized as a string,
-        whose first key is ``"lyrics"`` holding the lyrics,
-        followed by the shared extras' keys and then this
-        record's own keys, each group in its given order.
-    """
-    if extras is None and song_extras is None:
-        return lyrics
-    payload: dict[str, Any] = {"lyrics": lyrics}
-    if extras is not None:
-        payload.update(extras)
-    if song_extras is not None:
-        payload.update(song_extras)
-    return json.dumps(payload, ensure_ascii=False)
-
-
-def build_lines(
-        session: Session,
-        extras: dict[str, Any] | None = None,
-        extras_per_id: dict[str, dict[str, Any]] | None = None) \
-        -> list[str]:
-    """Build the JSONL lines of the exported songs' lyrics.
-
-    Without extras of either kind, each record's ``content`` is
-    the bare lyrics string.  With extras, ``content`` is a JSON
-    object serialized as a string, whose first key is ``"lyrics"``
-    holding the lyrics string, followed by the shared extras' keys
-    and then the song's own per-ID extras' keys, each group in its
-    given order.
-
-    Every song is exported, unless per-ID extras are given, in
-    which case only the songs they name are.
-
-    :param session: The database session.
-    :param extras: The extra parameters merged into every
-        record's content alongside the lyrics, in the order they
-        are to appear, or None for none.
-    :param extras_per_id: The extra parameters merged into the
-        content of one record alone, keyed by that record's song
-        ID and in the order they are to appear, restricting the
-        export to the song IDs they name, or None for no such
-        extras and no such restriction.
-    :return: The JSON lines, one per exported song, ordered by
-        song ID.
-    :raises ValueError: When an exported song has no lyrics, or
-        the per-ID extras name a song the working store does not
-        have.
-    """
-    lines: list[str] = []
-    exported: set[str] = set()
-    song: Song
-    for song in session.scalars(sa.select(Song).order_by(Song.id)):
-        song_id: str = f"song-{song.id}"
-        if extras_per_id is not None and song_id not in extras_per_id:
-            continue
-        if song.lyrics is None:
-            raise ValueError(
-                f"song {song.id} \"{song.title}\": no lyrics")
-        song_extras: dict[str, Any] | None = None \
-            if extras_per_id is None else extras_per_id[song_id]
-        content: str = __build_content(
-            song.lyrics, extras, song_extras)
-        record: dict[str, str] = {
-            "id": song_id, "content": content}
-        lines.append(json.dumps(record, ensure_ascii=False))
-        exported.add(song_id)
-    if extras_per_id is not None:
-        missing: list[str] = sorted(set(extras_per_id) - exported)
-        if len(missing) > 0:
-            raise ValueError(
-                "the per-ID extras name songs the working store"
-                f" does not have: {', '.join(missing)}")
-    return lines
-
-
 def main(argv: list[str] | None = None) -> int:
     """Export the LLM input JSONL file from the working store.
 
-    Every song is exported, unless ``--extras-per-id`` is given,
-    in which case only the songs its file names are.
-
     :param argv: The command-line arguments, or None for
         ``sys.argv``.
     :return: The exit status: 0 on success, non-zero on failure.
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
-    session: Session = ds.get_db()
-    lines: list[str]
     try:
-        extras: dict[str, Any] | None = None
-        if args.extras is not None:
-            extras = load_extras(args.extras)
-        extras_per_id: dict[str, dict[str, Any]] | None = None
-        if args.extras_per_id is not None:
-            extras_per_id = load_extras_per_id(args.extras_per_id)
-        lines = build_lines(session, extras, extras_per_id)
+        count: int = LlmInputExporter(
+            args.output_jsonl, args.extras,
+            args.extras_per_id).run()
     except (OSError, sa.exc.SQLAlchemyError, ValueError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
-    finally:
-        session.close()
-    args.output_jsonl.parent.mkdir(parents=True, exist_ok=True)
-    with open(args.output_jsonl, "w", encoding="utf-8") as file:
-        line: str
-        for line in lines:
-            file.write(line + "\n")
     elapsed: str = format_duration(time.monotonic() - started)
-    print(f"Done.  {len(lines)} songs exported."
+    print(f"Done.  {count} songs exported."
           f"  {elapsed} elapsed.", file=sys.stderr)
     return 0

tools/src/pop_fem_audit_tools/commands/fetch_artists.py

@@ -12,12 +12,10 @@ layer.  The working store is only read, never written; the
 ``build-db`` subcommand assembles the captured files into the
 store on the next rebuild.
 
-Every fetched row is meant for later human verification: the
-description of the resolved item is recorded in the note column
-so that a bad match can be spotted.  An unresolved artist or an
-error on one artist is noted on its row and does not fail the
-run.  A row whose name is no longer an artist of the store is
-dropped from the snapshot and reported on the standard error.
+An unresolved artist or an error on one artist is noted on its
+row and does not fail the run.  A row whose name is no longer an
+artist of the store is dropped from the snapshot and reported on
+the standard error.
 """
 import argparse
 import csv
@@ -33,7 +31,7 @@ import urllib.request
 from collections.abc import Container, Sequence
 from dataclasses import asdict, dataclass, field, fields
 from pathlib import Path
-from typing import Any, Literal, TextIO
+from typing import Any, ClassVar, Literal, TextIO
 
 import sqlalchemy as sa
 from sqlalchemy.orm import Session
@@ -43,71 +41,6 @@ from ..database import ds
 from ..models import Artist, Song, SongArtist
 from ..utils import format_duration
 
-API_URL: str = "https://www.wikidata.org/w/api.php"
-"""The URL of the Wikidata API endpoint."""
-SPARQL_URL: str = "https://query.wikidata.org/sparql"
-"""The URL of the Wikidata Query Service SPARQL endpoint."""
-USER_AGENT: str = (
-    f"pop-fem-audit-tools/{VERSION}"
-    " (https://github.com/imacat/pop-fem-audit;"
-    " mailto:imacat@mail.imacat.idv.tw)")
-"""The User-Agent header sent on every HTTP request."""
-TIMEOUT: float = 30.0
-"""The timeout of an API HTTP request, in seconds."""
-SPARQL_TIMEOUT: float = 90.0
-"""The timeout of a SPARQL HTTP request, in seconds.
-
-Higher than the API timeout: the WDQS server aborts a slow
-query at 60 seconds, and a lower client timeout would race
-that server-side abort and misclassify a slow-but-answerable
-query as a client-side timeout instead of letting the server's
-own HTTP error response arrive and enter the retry path."""
-SLEEP_SECONDS: float = 1.0
-"""The delay between consecutive HTTP requests, in seconds."""
-MAX_ATTEMPTS: int = 5
-"""The maximum number of attempts on a transient error."""
-RETRY_SECONDS: float = 15.0
-"""The back-off unit on a transient error, in seconds;
-multiplied by the attempt number already made."""
-RETRY_STATUSES: frozenset[int] = frozenset({429, 500, 502, 503})
-"""The HTTP statuses that are retried with a back-off."""
-MAX_STAGE1_TITLES: int = 3
-"""The maximum number of charted titles used for the stage-1 song
-corroboration."""
-HUMAN_QID: str = "Q5"
-"""The Wikidata item ID of "human"."""
-ENSEMBLE_QID: str = "Q2088357"
-"""The Wikidata item ID of "musical ensemble"."""
-ORIGINAL_CAST_QID: str = "Q106497009"
-"""The Wikidata item ID of "original cast"."""
-GROUP_KEYWORDS: Sequence[str] = ("band", "group", "duo", "trio")
-"""The label keywords that suggest a musical ensemble, covering
-labels like "boy band" and "girl group"."""
-NOTE_NOT_FOUND: str = "not found"
-"""The note sentinel of an artist without a resolved Wikidata
-item, written to the snapshot and read back for the
-classification."""
-CORPUS_START_YEAR: int = 2016
-"""The first year of the corpus window: a member who left a group
-before it never performed a corpus song."""
-MIXED_GENDER: str = "mixed"
-"""The gender recorded for a group whose members do not share one
-gender."""
-TIME_YEAR_PATTERN: re.Pattern[str] = re.compile(r"^[+-]?\d+")
-"""The leading year of a Wikidata time value."""
-PINNED_QIDS: dict[str, str] = {}
-"""The last-resort pinned item IDs, keyed by the artist name.
-
-An entry is for an artist the algorithm documented on
-``ArtistFetcher`` is structurally unable to resolve, with its
-justification recorded here.  Currently empty: the only pin ever
-needed, "Pinkfong" (typed as a brand, which the type gate
-excludes by design), became moot when the store's artist entity
-behind that credit was identified as Hope Segoine.
-
-A pinned name skips the candidate retrieval and corroboration
-steps; its item ID is used directly."""
-
 
 class ArtistType(enum.StrEnum):
     """The decided artist type of a snapshot row."""
@@ -147,15 +80,14 @@ class ArtistSnapshot:
         return asdict(self)
 
 
-SNAPSHOT_FIELDS: Sequence[str] = tuple(
-    x.name for x in fields(ArtistSnapshot))
-"""The header columns of the Wikidata artist snapshot CSV file."""
-
-
 @dataclass
 class GroupMember:
     """One has-part member of a Wikidata group item."""
 
+    __CORPUS_START_YEAR: ClassVar[int] = 2016
+    """The first year of the corpus window: a member who left a
+    group before it never performed a corpus song."""
+
     qid: str
     """The item ID of the member."""
     start_years: list[int] = field(default_factory=list)
@@ -181,7 +113,7 @@ class GroupMember:
         if len(self.end_years) == 0:
             return True
         last_end: int = max(self.end_years)
-        if last_end >= CORPUS_START_YEAR:
+        if last_end >= self.__CORPUS_START_YEAR:
             return True
         if len(self.start_years) == 0:
             return False
@@ -229,20 +161,8 @@ class RetryExhausted(Exception):
     """
 
 
-def parse_args(argv: list[str] | None) -> argparse.Namespace:
-    """Parse the command-line arguments.
-
-    :param argv: The command-line arguments, or None for
-        ``sys.argv``.
-    :return: The parsed arguments.
-    """
-    parser: argparse.ArgumentParser = argparse.ArgumentParser(
-        description="Fetch the artist metadata from Wikidata"
-                    " into the capture layer.")
-    parser.add_argument(
-        "wikidata_csv", type=Path,
-        help="the Wikidata artist snapshot CSV file")
-    return parser.parse_args(argv)
+NOTE_NOT_FOUND: str = "not found"
+"""The note marking an artist that could not be resolved."""
 
 
 class ArtistFetcher:
@@ -291,6 +211,71 @@ class ArtistFetcher:
     in the note.
     """
 
+    __API_URL: ClassVar[str] = "https://www.wikidata.org/w/api.php"
+    """The URL of the Wikidata API endpoint."""
+    __SPARQL_URL: ClassVar[str] \
+        = "https://query.wikidata.org/sparql"
+    """The URL of the Wikidata Query Service SPARQL endpoint."""
+    __USER_AGENT: ClassVar[str] = (
+        f"pop-fem-audit-tools/{VERSION}"
+        " (https://github.com/imacat/pop-fem-audit;"
+        " mailto:imacat@mail.imacat.idv.tw)")
+    """The User-Agent header sent on every HTTP request."""
+    __TIMEOUT: ClassVar[float] = 30.0
+    """The timeout of an API HTTP request, in seconds."""
+    __SPARQL_TIMEOUT: ClassVar[float] = 90.0
+    """The timeout of a SPARQL HTTP request, in seconds.
+
+    Higher than the API timeout: the WDQS server aborts a slow
+    query at 60 seconds, and a lower client timeout would race
+    that server-side abort and misclassify a slow-but-answerable
+    query as a client-side timeout instead of letting the
+    server's own HTTP error response arrive and enter the retry
+    path."""
+    __SLEEP_SECONDS: ClassVar[float] = 1.0
+    """The delay between consecutive HTTP requests, in
+    seconds."""
+    __MAX_ATTEMPTS: ClassVar[int] = 5
+    """The maximum number of attempts on a transient error."""
+    __RETRY_SECONDS: ClassVar[float] = 15.0
+    """The back-off unit on a transient error, in seconds;
+    multiplied by the attempt number already made."""
+    __RETRY_STATUSES: ClassVar[frozenset[int]] \
+        = frozenset({429, 500, 502, 503})
+    """The HTTP statuses that are retried with a back-off."""
+    __MAX_STAGE1_TITLES: ClassVar[int] = 3
+    """The maximum number of charted titles used for the
+    stage-1 song corroboration."""
+    __HUMAN_QID: ClassVar[str] = "Q5"
+    """The Wikidata item ID of "human"."""
+    __ENSEMBLE_QID: ClassVar[str] = "Q2088357"
+    """The Wikidata item ID of "musical ensemble"."""
+    __ORIGINAL_CAST_QID: ClassVar[str] = "Q106497009"
+    """The Wikidata item ID of "original cast"."""
+    __GROUP_KEYWORDS: ClassVar[Sequence[str]] \
+        = ("band", "group", "duo", "trio")
+    """The label keywords that suggest a musical ensemble,
+    covering labels like "boy band" and "girl group"."""
+    __MIXED_GENDER: ClassVar[str] = "mixed"
+    """The gender recorded for a group whose members do not
+    share one gender."""
+    __TIME_YEAR_PATTERN: ClassVar[re.Pattern[str]] \
+        = re.compile(r"^[+-]?\d+")
+    """The leading year of a Wikidata time value."""
+    __PINNED_QIDS: ClassVar[dict[str, str]] = {}
+    """The last-resort pinned item IDs, keyed by the artist name.
+
+    An entry is for an artist the algorithm documented on
+    ``ArtistFetcher`` is structurally unable to resolve, with its
+    justification recorded here.  Currently empty: the only pin
+    ever needed, "Pinkfong" (typed as a brand, which the type
+    gate excludes by design), became moot when the store's
+    artist entity behind that credit was identified as Hope
+    Segoine.
+
+    A pinned name skips the candidate retrieval and corroboration
+    steps; its item ID is used directly."""
+
     def __init__(self) -> None:
         """Construct the fetcher."""
         self.__sent: int = 0
@@ -342,8 +327,8 @@ class ArtistFetcher:
             transient error are exhausted.
         :raises ValueError: On a JSON decoding error.
         """
-        if name in PINNED_QIDS:
-            return PINNED_QIDS[name]
+        if name in self.__PINNED_QIDS:
+            return self.__PINNED_QIDS[name]
         candidates: list[str] = self.__candidates(name)
         if len(candidates) == 0:
             return None
@@ -373,11 +358,11 @@ class ArtistFetcher:
           {{ ?item rdfs:label ?name }}
           UNION {{ ?item skos:altLabel ?name }}
           {{
-            ?item wdt:P31 wd:{HUMAN_QID}
+            ?item wdt:P31 wd:{self.__HUMAN_QID}
           }} UNION {{
-            ?item wdt:P31/wdt:P279* wd:{ENSEMBLE_QID}
+            ?item wdt:P31/wdt:P279* wd:{self.__ENSEMBLE_QID}
           }} UNION {{
-            ?item wdt:P31 wd:{ORIGINAL_CAST_QID}
+            ?item wdt:P31 wd:{self.__ORIGINAL_CAST_QID}
           }}
         }}
         """
@@ -403,7 +388,7 @@ class ArtistFetcher:
             transient error are exhausted.
         :raises ValueError: On a JSON decoding error.
         """
-        subset: Sequence[str] = titles[:MAX_STAGE1_TITLES]
+        subset: Sequence[str] = titles[:self.__MAX_STAGE1_TITLES]
         if len(subset) == 0:
             return None
         query: str = f"""
@@ -532,7 +517,7 @@ class ArtistFetcher:
         qid: str
         for qid in qids:
             member: MemberClaims = claims.get(qid, MemberClaims())
-            if HUMAN_QID not in member.instance_of_ids:
+            if self.__HUMAN_QID not in member.instance_of_ids:
                 continue
             if len(member.gender_ids) == 0:
                 return
@@ -543,7 +528,7 @@ class ArtistFetcher:
             [x[1] for x in genders], any_language=True)
         unique: set[str] = {x[1] for x in genders}
         snapshot.gender = labels[genders[0][1]] \
-            if len(unique) == 1 else MIXED_GENDER
+            if len(unique) == 1 else self.__MIXED_GENDER
         basis: str = "gender derived from members: " + "; ".join(
             f"{x} {labels[y]}" for x, y in genders)
         snapshot.note = f"{snapshot.note}; {basis}" \
@@ -677,7 +662,8 @@ class ArtistFetcher:
                     or not isinstance(value.get("time"), str):
                 continue
             match: re.Match[str] | None \
-                = TIME_YEAR_PATTERN.match(value["time"])
+                = ArtistFetcher.__TIME_YEAR_PATTERN.match(
+                    value["time"])
             if match is not None:
                 years.append(int(match.group()))
         return years
@@ -806,12 +792,13 @@ class ArtistFetcher:
             ``ArtistType.GROUP`` for a musical ensemble, or the
             empty string for the human to decide.
         """
-        if HUMAN_QID in type_ids:
+        if ArtistFetcher.__HUMAN_QID in type_ids:
             return ArtistType.SOLO
         qid: str
         for qid in type_ids:
             label: str = labels.get(qid, "").lower()
-            if any(x in label for x in GROUP_KEYWORDS):
+            if any(x in label
+                   for x in ArtistFetcher.__GROUP_KEYWORDS):
                 return ArtistType.GROUP
         return ""
 
@@ -827,14 +814,15 @@ class ArtistFetcher:
             transient error are exhausted.
         :raises ValueError: On a JSON decoding error.
         """
-        url: str = (f"{SPARQL_URL}?"
-                    f"{urllib.parse.urlencode({'query': query})}")
+        url: str = (
+            f"{self.__SPARQL_URL}?"
+            f"{urllib.parse.urlencode({'query': query})}")
         request: urllib.request.Request = urllib.request.Request(
             url, headers={
-                "User-Agent": USER_AGENT,
+                "User-Agent": self.__USER_AGENT,
                 "Accept": "application/sparql-results+json"})
         body: bytes = self.__send(
-            request, timeout=SPARQL_TIMEOUT)
+            request, timeout=self.__SPARQL_TIMEOUT)
         data: Any = json.loads(body)
         bindings: Any = None
         if isinstance(data, dict) \
@@ -868,13 +856,14 @@ class ArtistFetcher:
             transient error are exhausted.
         :raises ValueError: On a JSON decoding error.
         """
-        url: str = f"{API_URL}?{urllib.parse.urlencode(params)}"
+        url: str \
+            = f"{self.__API_URL}?{urllib.parse.urlencode(params)}"
         request: urllib.request.Request = urllib.request.Request(
-            url, headers={"User-Agent": USER_AGENT})
+            url, headers={"User-Agent": self.__USER_AGENT})
         return json.loads(self.__send(request))
 
     def __send(self, request: urllib.request.Request,
-               timeout: float = TIMEOUT) -> bytes:
+               timeout: float = __TIMEOUT) -> bytes:
         """Send an HTTP request, retrying on a transient error.
 
         Consecutive requests are separated by a fixed delay.  A
@@ -892,7 +881,7 @@ class ArtistFetcher:
             transient error are exhausted.
         """
         if self.__sent > 0:
-            time.sleep(SLEEP_SECONDS)
+            time.sleep(self.__SLEEP_SECONDS)
         self.__sent += 1
         attempt: int = 1
         reason: str | None
@@ -905,10 +894,10 @@ class ArtistFetcher:
                 reason = self.__retry_reason(error)
                 if reason is None:
                     raise
-                if attempt >= MAX_ATTEMPTS:
+                if attempt >= self.__MAX_ATTEMPTS:
                     raise RetryExhausted(
                         f"retries exhausted ({reason})") from error
-            time.sleep(RETRY_SECONDS * attempt)
+            time.sleep(self.__RETRY_SECONDS * attempt)
             attempt += 1
 
     @staticmethod
@@ -923,7 +912,7 @@ class ArtistFetcher:
             the error is not transient and must not be retried.
         """
         if isinstance(error, urllib.error.HTTPError):
-            if error.code not in RETRY_STATUSES:
+            if error.code not in ArtistFetcher.__RETRY_STATUSES:
                 return None
             return str(error)
         if isinstance(error, TimeoutError):
@@ -968,92 +957,216 @@ class ArtistFetcher:
         return uri.rsplit("/", 1)[-1]
 
 
-def read_snapshot_rows(file: TextIO) -> list[dict[str, str]]:
-    """Read the current rows of a snapshot CSV file handle.
+@dataclass(frozen=True)
+class FetchCounts:
+    """The outcome counts of one snapshot update run."""
 
-    :param file: The open, seekable snapshot CSV file.
-    :return: The rows, keyed by the column name.
-    :raises OSError: When the file cannot be read.
+    fetched: int
+    """The number of artists newly resolved."""
+    not_found: int
+    """The number of artists left unresolved."""
+    errors: int
+    """The number of artists that ended in an error."""
+
+
+class ArtistSnapshotUpdater:
+    """The updater of the Wikidata artist snapshot CSV file.
+
+    Fetches the metadata of every artist of the working store
+    that the snapshot does not resolve yet, appends a row for
+    each to the snapshot as it is fetched, and rewrites the
+    snapshot sorted by artist name with its stale rows dropped.
     """
-    file.seek(0)
-    reader: csv.DictReader[str] = csv.DictReader(file)
-    return list(reader)
 
+    __SNAPSHOT_FIELDS: ClassVar[Sequence[str]] = tuple(
+        x.name for x in fields(ArtistSnapshot))
+    """The header columns of the Wikidata artist snapshot CSV file."""
 
-def read_artist_titles(session: Session,
-                       artist_id: int) -> list[str]:
-    """Read the charted song titles credited to an artist.
+    def __init__(self, wikidata_csv: Path) -> None:
+        """Set up the updater.
 
-    :param session: The database session.
-    :param artist_id: The artist ID.
-    :return: The song titles credited to the artist, ordered by
-        the song ID, with the duplicate titles removed.
-    """
-    titles: Sequence[str] = session.scalars(
-        sa.select(Song.title)
-        .join(SongArtist, SongArtist.song_id == Song.id)
-        .where(SongArtist.artist_id == artist_id)
-        .order_by(Song.id)).all()
-    return list(dict.fromkeys(titles))
+        :param wikidata_csv: The Wikidata artist snapshot CSV
+            file.
+        """
+        self.__wikidata_csv: Path = wikidata_csv
+        """The Wikidata artist snapshot CSV file."""
 
+    def run(self) -> FetchCounts:
+        """Fetch every unresolved artist and update the snapshot.
 
-def ensure_snapshot_header(file: TextIO) -> None:
-    """Write the snapshot CSV header row if the file is empty.
+        :return: The counts of the run.
+        :raises OSError: When the snapshot file, or its parent
+            directory, cannot be read or written.
+        :raises sqlalchemy.exc.SQLAlchemyError: When the working
+            store cannot be read.
+        """
+        session: Session = ds.get_db()
+        try:
+            return self.__run(session)
+        finally:
+            session.close()
 
-    :param file: The open, seekable snapshot CSV file.
-    :return: None.
-    :raises OSError: When the file cannot be written.
-    """
-    file.seek(0, os.SEEK_END)
-    if file.tell() == 0:
-        csv.writer(file).writerow(SNAPSHOT_FIELDS)
+    def __run(self, session: Session) -> FetchCounts:
+        """Run the fetch loop with an open database session.
+
+        :param session: The database session.
+        :return: The counts of the run.
+        :raises OSError: When the snapshot file, or its parent
+            directory, cannot be read or written.
+        """
+        fetcher: ArtistFetcher = ArtistFetcher()
+        fetched: int = 0
+        not_found: int = 0
+        errors: int = 0
+        self.__wikidata_csv.parent.mkdir(
+            parents=True, exist_ok=True)
+        with open(self.__wikidata_csv, "a+", encoding="utf-8",
+                  newline="") as csv_file:
+            done: set[str] = {
+                x["name"] for x in
+                self.__read_snapshot_rows(csv_file)
+                if x["gender"] != ""}
+            self.__ensure_snapshot_header(csv_file)
+            names: set[str] = set()
+            artist: Artist
+            for artist in session.scalars(
+                    sa.select(Artist).order_by(Artist.id)):
+                names.add(artist.name)
+                if artist.name in done:
+                    continue
+                titles: list[str] = self.__read_artist_titles(
+                    session, artist.id)
+                snapshot: ArtistSnapshot = fetcher.fetch(
+                    artist.name, titles)
+                self.__append_row(csv_file, snapshot)
+                status: str = snapshot.qid
+                if snapshot.note == NOTE_NOT_FOUND:
+                    not_found += 1
+                    status = NOTE_NOT_FOUND
+                elif snapshot.note.startswith("error: "):
+                    errors += 1
+                    status = snapshot.note
+                else:
+                    fetched += 1
+                print(f"artist \"{artist.name}\": {status}",
+                      file=sys.stderr)
+            self.__write_snapshot(csv_file, names)
+        return FetchCounts(
+            fetched=fetched, not_found=not_found, errors=errors)
+
+    @staticmethod
+    def __read_snapshot_rows(file: TextIO) \
+            -> list[dict[str, str]]:
+        """Read the current rows of a snapshot CSV file handle.
+
+        :param file: The open, seekable snapshot CSV file.
+        :return: The rows, keyed by the column name.
+        :raises OSError: When the file cannot be read.
+        """
+        file.seek(0)
+        reader: csv.DictReader[str] = csv.DictReader(file)
+        return list(reader)
+
+    @staticmethod
+    def __read_artist_titles(session: Session,
+                             artist_id: int) -> list[str]:
+        """Read the charted song titles credited to an artist.
+
+        :param session: The database session.
+        :param artist_id: The artist ID.
+        :return: The song titles credited to the artist, ordered
+            by the song ID, with the duplicate titles removed.
+        """
+        titles: Sequence[str] = session.scalars(
+            sa.select(Song.title)
+            .join(SongArtist, SongArtist.song_id == Song.id)
+            .where(SongArtist.artist_id == artist_id)
+            .order_by(Song.id)).all()
+        return list(dict.fromkeys(titles))
+
+    @staticmethod
+    def __ensure_snapshot_header(file: TextIO) -> None:
+        """Write the snapshot CSV header row if the file is
+        empty.
+
+        :param file: The open, seekable snapshot CSV file.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        file.seek(0, os.SEEK_END)
+        if file.tell() == 0:
+            csv.writer(file).writerow(
+                ArtistSnapshotUpdater.__SNAPSHOT_FIELDS)
+            file.flush()
+
+    @staticmethod
+    def __append_row(file: TextIO,
+                     snapshot: ArtistSnapshot) -> None:
+        """Append a snapshot row to a snapshot CSV file handle.
+
+        :param file: The open snapshot CSV file, opened for
+            append.
+        :param snapshot: The snapshot of an artist.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        csv.DictWriter(
+            file, ArtistSnapshotUpdater.__SNAPSHOT_FIELDS).writerow(
+            snapshot.to_row())
         file.flush()
 
+    @staticmethod
+    def __write_snapshot(file: TextIO, names: Container[str]) \
+            -> None:
+        """Rewrite a snapshot CSV file handle sorted by artist
+        name.
 
-def append_row(file: TextIO, snapshot: ArtistSnapshot) -> None:
-    """Append a snapshot row to a snapshot CSV file handle.
+        The rows are ordered by the case-folded artist name,
+        matching the convention of the derived ``artists.csv``.
+        An artist keeps one row only, the last one of the file,
+        so that a re-fetched artist replaces its earlier row.  A
+        row whose name is not an artist of the store is dropped
+        and reported on the standard error.
 
-    :param file: The open snapshot CSV file, opened for append.
-    :param snapshot: The snapshot of an artist.
-    :return: None.
-    :raises OSError: When the file cannot be written.
+        :param file: The open, seekable snapshot CSV file.
+        :param names: The artist names of the working store.
+        :return: None.
+        :raises OSError: When the file cannot be read or written.
+        """
+        kept: dict[str, dict[str, str]] = {}
+        row: dict[str, str]
+        for row in ArtistSnapshotUpdater.__read_snapshot_rows(
+                file):
+            if row["name"] not in names:
+                print(f"dropped stale row \"{row['name']}\":"
+                      " no such artist in the store",
+                      file=sys.stderr)
+                continue
+            kept[row["name"]] = row
+        ordered: list[dict[str, str]] = sorted(
+            kept.values(), key=lambda x: x["name"].casefold())
+        file.seek(0)
+        file.truncate()
+        writer: csv.DictWriter[str] = csv.DictWriter(
+            file, ArtistSnapshotUpdater.__SNAPSHOT_FIELDS)
+        writer.writeheader()
+        writer.writerows(ordered)
+
+
+def parse_args(argv: list[str] | None) -> argparse.Namespace:
+    """Parse the command-line arguments.
+
+    :param argv: The command-line arguments, or None for
+        ``sys.argv``.
+    :return: The parsed arguments.
     """
-    csv.DictWriter(file, SNAPSHOT_FIELDS).writerow(
-        snapshot.to_row())
-    file.flush()
-
-
-def write_snapshot(file: TextIO, names: Container[str]) -> None:
-    """Rewrite a snapshot CSV file handle sorted by artist name.
-
-    The rows are ordered by the case-folded artist name, matching
-    the convention of the derived ``artists.csv``.  An artist
-    keeps one row only, the last one of the file, so that a
-    re-fetched artist replaces its earlier row.  A row whose name
-    is not an artist of the store is dropped and reported on the
-    standard error.
-
-    :param file: The open, seekable snapshot CSV file.
-    :param names: The artist names of the working store.
-    :return: None.
-    :raises OSError: When the file cannot be read or written.
-    """
-    kept: dict[str, dict[str, str]] = {}
-    row: dict[str, str]
-    for row in read_snapshot_rows(file):
-        if row["name"] not in names:
-            print(f"dropped stale row \"{row['name']}\":"
-                  " no such artist in the store", file=sys.stderr)
-            continue
-        kept[row["name"]] = row
-    ordered: list[dict[str, str]] = sorted(
-        kept.values(), key=lambda x: x["name"].casefold())
-    file.seek(0)
-    file.truncate()
-    writer: csv.DictWriter[str] = csv.DictWriter(
-        file, SNAPSHOT_FIELDS)
-    writer.writeheader()
-    writer.writerows(ordered)
+    parser: argparse.ArgumentParser = argparse.ArgumentParser(
+        description="Fetch the artist metadata from Wikidata"
+                    " into the capture layer.")
+    parser.add_argument(
+        "wikidata_csv", type=Path,
+        help="the Wikidata artist snapshot CSV file")
+    return parser.parse_args(argv)
 
 
 def main(argv: list[str] | None = None) -> int:
@@ -1066,52 +1179,16 @@ def main(argv: list[str] | None = None) -> int:
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
-    fetcher: ArtistFetcher = ArtistFetcher()
-    fetched: int = 0
-    not_found: int = 0
-    errors: int = 0
-    session: Session = ds.get_db()
     try:
-        args.wikidata_csv.parent.mkdir(
-            parents=True, exist_ok=True)
-        with open(args.wikidata_csv, "a+", encoding="utf-8",
-                  newline="") as csv_file:
-            done: set[str] = {x["name"] for x in
-                              read_snapshot_rows(csv_file)
-                              if x["gender"] != ""}
-            ensure_snapshot_header(csv_file)
-            names: set[str] = set()
-            artist: Artist
-            for artist in session.scalars(
-                    sa.select(Artist).order_by(Artist.id)):
-                names.add(artist.name)
-                if artist.name in done:
-                    continue
-                titles: list[str] = read_artist_titles(
-                    session, artist.id)
-                snapshot: ArtistSnapshot = fetcher.fetch(
-                    artist.name, titles)
-                append_row(csv_file, snapshot)
-                status: str = snapshot.qid
-                if snapshot.note == NOTE_NOT_FOUND:
-                    not_found += 1
-                    status = "not found"
-                elif snapshot.note.startswith("error: "):
-                    errors += 1
-                    status = snapshot.note
-                else:
-                    fetched += 1
-                print(f"artist \"{artist.name}\": {status}",
-                      file=sys.stderr)
-            write_snapshot(csv_file, names)
+        counts: FetchCounts \
+            = ArtistSnapshotUpdater(args.wikidata_csv).run()
     except (OSError, sa.exc.SQLAlchemyError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
-    finally:
-        session.close()
-    attempted: int = fetched + not_found + errors
+    attempted: int = counts.fetched + counts.not_found \
+        + counts.errors
     elapsed: str = format_duration(time.monotonic() - started)
-    print(f"Done.  Resolved {fetched}/{attempted} artists."
-          f"  {elapsed} elapsed.",
+    print(f"Done.  Resolved {counts.fetched}/{attempted}"
+          f" artists.  {elapsed} elapsed.",
           file=sys.stderr)
     return 0

tools/src/pop_fem_audit_tools/commands/fetch_lyrics.py

@@ -30,8 +30,9 @@ import time
 import urllib.parse
 import urllib.request
 from collections.abc import Sequence
+from dataclasses import dataclass
 from pathlib import Path
-from typing import Any
+from typing import Any, ClassVar
 
 import sqlalchemy as sa
 from sqlalchemy.orm import Session
@@ -45,60 +46,6 @@ from ..models import (
 )
 from ..utils import format_duration
 
-PROVENANCE_FIELDS: Sequence[str] = (
-    "song_id", "source", "method", "acquired_at", "note")
-"""The header columns of the lyrics provenance CSV file."""
-USER_AGENT: str = ("pop-fem-audit-tools"
-                   " (https://github.com/imacat/pop-fem-audit)")
-"""The User-Agent header sent on every HTTP request."""
-TIMEOUT: float = 30.0
-"""The timeout of an HTTP request, in seconds."""
-SLEEP_SECONDS: float = 1.0
-"""The delay between consecutive HTTP requests, in seconds."""
-
-
-def __build_normalization() -> dict[int, str | None]:
-    """Build the lyrics normalization translation table.
-
-    :return: The codepoint-to-replacement mapping, a replacement
-        of None meaning removal.
-    """
-    table: dict[int, str | None] = {}
-    codepoint: int
-    for codepoint in range(0x80, 0xa0):
-        try:
-            table[codepoint] = bytes([codepoint]).decode("cp1252")
-        except UnicodeDecodeError:
-            table[codepoint] = None
-    table[0x0435] = "e"
-    table[0x03cc] = "ó"
-    for codepoint in (0x2005, 0x205f, 0x200a):
-        table[codepoint] = " "
-    for codepoint in (0x200b, 0x200c, 0x200d, 0xfeff):
-        table[codepoint] = None
-    return table
-
-
-NORMALIZATION: dict[int, str | None] = __build_normalization()
-"""The codepoint-to-replacement mapping applied to fetched
-lyrics: cp1252-mojibake restoration for U+0080-U+009F (with the
-five byte values undefined in cp1252 removed), homoglyph
-restoration for the Cyrillic "e" and the Greek "o" with tonos,
-ASCII-space restoration for exotic space variants, and removal
-of zero-width characters.  A replacement of None removes the
-codepoint."""
-
-
-def normalize_lyrics(text: str) -> str:
-    """Restore or remove watermark and mojibake characters.
-
-    :param text: The lyrics text as fetched from an API.
-    :return: The text with the codepoints in
-        :data:`NORMALIZATION` replaced or removed; every other
-        character is unchanged.
-    """
-    return text.translate(NORMALIZATION)
-
 
 def parse_args(argv: list[str] | None) -> argparse.Namespace:
     """Parse the command-line arguments.
@@ -122,6 +69,16 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
 class LyricsFetcher:
     """A fetcher of song lyrics from the public lyrics APIs."""
 
+    __USER_AGENT: ClassVar[str] = (
+        "pop-fem-audit-tools"
+        " (https://github.com/imacat/pop-fem-audit)")
+    """The User-Agent header sent on every HTTP request."""
+    __TIMEOUT: ClassVar[float] = 30.0
+    """The timeout of an HTTP request, in seconds."""
+    __SLEEP_SECONDS: ClassVar[float] = 1.0
+    """The delay between consecutive HTTP requests, in
+    seconds."""
+
     def __init__(self) -> None:
         """Construct the fetcher."""
         self.__sent: int = 0
@@ -193,78 +150,216 @@ class LyricsFetcher:
             network, or decoding error.
         """
         if self.__sent > 0:
-            time.sleep(SLEEP_SECONDS)
+            time.sleep(self.__SLEEP_SECONDS)
         self.__sent += 1
         request: urllib.request.Request = urllib.request.Request(
-            url, headers={"User-Agent": USER_AGENT})
+            url, headers={"User-Agent": self.__USER_AGENT})
         try:
             with urllib.request.urlopen(
-                    request, timeout=TIMEOUT) as response:
+                    request, timeout=self.__TIMEOUT) as response:
                 return json.load(response)
         except (OSError, ValueError):
             return None
 
 
-def query_artist(session: Session, song_id: int) -> str:
-    """Find the artist name to query the APIs with.
+@dataclass(frozen=True)
+class LyricsFetchCounts:
+    """The outcome of one run of fetching the missing lyrics."""
 
-    :param session: The database session.
-    :param song_id: The song ID.
-    :return: The name of the primary-role artist with the lowest
-        position.
-    """
-    name: str | None = session.scalar(
-        sa.select(Artist.name)
-        .join(SongArtist, SongArtist.artist_id == Artist.id)
-        .where(SongArtist.song_id == song_id,
-               SongArtist.role == Role.PRIMARY)
-        .order_by(SongArtist.position)
-        .limit(1))
-    assert name is not None
-    return name
+    fetched: int
+    """The number of songs newly fetched."""
+    missed: int
+    """The number of songs every API missed."""
 
 
-def save_lyrics(lyrics_dir: Path, song_id: int,
-                lyrics: str) -> None:
-    """Write the lyrics of a song into the cache directory.
+class LyricsFetchRunner:
+    """The orchestrator of one run of fetching missing lyrics."""
 
-    The cache directory is created when missing.
+    __PROVENANCE_FIELDS: ClassVar[Sequence[str]] = (
+        "song_id", "source", "method", "acquired_at", "note")
+    """The header columns of the lyrics provenance CSV file."""
 
-    The lyrics text is normalized with :func:`normalize_lyrics`
-    before being written.
+    @staticmethod
+    def __build_normalization() -> dict[int, str | None]:
+        """Build the lyrics normalization translation table.
 
-    :param lyrics_dir: The lyrics cache directory.
-    :param song_id: The song ID.
-    :param lyrics: The lyrics text.
-    :return: None.
-    :raises OSError: When the file cannot be written.
-    """
-    lyrics_dir.mkdir(parents=True, exist_ok=True)
-    (lyrics_dir / f"{song_id}.txt").write_text(
-        normalize_lyrics(lyrics), encoding="utf-8")
+        :return: The codepoint-to-replacement mapping, a
+            replacement of None meaning removal.
+        """
+        table: dict[int, str | None] = {}
+        codepoint: int
+        for codepoint in range(0x80, 0xa0):
+            try:
+                table[codepoint] = bytes(
+                    [codepoint]).decode("cp1252")
+            except UnicodeDecodeError:
+                table[codepoint] = None
+        table[0x0435] = "e"
+        table[0x03cc] = "ó"
+        for codepoint in (0x2005, 0x205f, 0x200a):
+            table[codepoint] = " "
+        for codepoint in (0x200b, 0x200c, 0x200d, 0xfeff):
+            table[codepoint] = None
+        return table
 
+    __NORMALIZATION: ClassVar[dict[int, str | None]] \
+        = __build_normalization()
+    """The codepoint-to-replacement mapping applied to fetched
+    lyrics: cp1252-mojibake restoration for U+0080-U+009F (with
+    the five byte values undefined in cp1252 removed), homoglyph
+    restoration for the Cyrillic "e" and the Greek "o" with
+    tonos, ASCII-space restoration for exotic space variants, and
+    removal of zero-width characters.  A replacement of None
+    removes the codepoint."""
 
-def append_provenance(path: Path, song_id: int,
-                      source: str) -> None:
-    """Append a provenance row for a fetched lyrics file.
+    def __init__(self, lyrics_dir: Path,
+                provenance_csv: Path) -> None:
+        """Set up the fetch run.
 
-    The CSV file is created with the header row when missing.
+        :param lyrics_dir: The lyrics cache directory.
+        :param provenance_csv: The lyrics provenance CSV file.
+        """
+        self.__lyrics_dir: Path = lyrics_dir
+        """The lyrics cache directory."""
+        self.__provenance_csv: Path = provenance_csv
+        """The lyrics provenance CSV file."""
+        self.__fetcher: LyricsFetcher = LyricsFetcher()
+        """The fetcher of the public lyrics APIs."""
 
-    :param path: The lyrics provenance CSV file.
-    :param song_id: The song ID.
-    :param source: The source name of the fetched lyrics.
-    :return: None.
-    :raises OSError: When the file cannot be written.
-    """
-    is_new: bool = not path.exists()
-    path.parent.mkdir(parents=True, exist_ok=True)
-    with open(path, "a", encoding="utf-8",
-              newline="") as file:
-        writer: Any = csv.writer(file)
-        if is_new:
-            writer.writerow(PROVENANCE_FIELDS)
-        writer.writerow([song_id, source, "api-fetch",
-                         datetime.date.today().isoformat(), ""])
+    def run(self) -> LyricsFetchCounts:
+        """Fetch the missing lyrics of every song in the store.
+
+        Every song fetched or missed is reported on the standard
+        error as an observable side effect.
+
+        :return: The number of songs fetched and missed.
+        :raises OSError: When a cache file or the provenance CSV
+            cannot be written.
+        :raises sqlalchemy.exc.SQLAlchemyError: On a database
+            error.
+        """
+        fetched: int = 0
+        missed: int = 0
+        session: Session = ds.get_db()
+        try:
+            song: Song
+            for song in session.scalars(
+                    sa.select(Song).order_by(Song.id)):
+                if (self.__lyrics_dir
+                        / f"{song.id}.txt").exists():
+                    continue
+                if self.__fetch_one(session, song):
+                    fetched += 1
+                else:
+                    missed += 1
+        finally:
+            session.close()
+        return LyricsFetchCounts(fetched=fetched, missed=missed)
+
+    def __fetch_one(self, session: Session, song: Song) -> bool:
+        """Fetch and save the lyrics of one song.
+
+        The song is queried by its primary-role artist name; when
+        every API misses and the song's full artist credit
+        differs from that name, the same APIs are queried again
+        with the artist credit.
+
+        :param session: The database session.
+        :param song: The song to fetch.
+        :return: True when a lyrics text was fetched and saved,
+            False when every API missed on both queries.
+        :raises OSError: When the cache file or the provenance
+            CSV cannot be written.
+        """
+        artist: str = self.__query_artist(session, song.id)
+        result: tuple[str, str] | None = self.__fetcher.fetch(
+            artist, song.title)
+        if result is None and song.artist_credit != artist:
+            result = self.__fetcher.fetch(
+                song.artist_credit, song.title)
+        if result is None:
+            print(f"song {song.id} \"{song.title}\": miss",
+                  file=sys.stderr)
+            return False
+        lyrics: str
+        source: str
+        lyrics, source = result
+        self.__save_lyrics(song.id, lyrics)
+        self.__append_provenance(song.id, source)
+        print(f"song {song.id} \"{song.title}\": {source}",
+              file=sys.stderr)
+        return True
+
+    @staticmethod
+    def __query_artist(session: Session, song_id: int) -> str:
+        """Find the artist name to query the APIs with.
+
+        :param session: The database session.
+        :param song_id: The song ID.
+        :return: The name of the primary-role artist with the
+            lowest position.
+        """
+        name: str | None = session.scalar(
+            sa.select(Artist.name)
+            .join(SongArtist, SongArtist.artist_id == Artist.id)
+            .where(SongArtist.song_id == song_id,
+                   SongArtist.role == Role.PRIMARY)
+            .order_by(SongArtist.position)
+            .limit(1))
+        assert name is not None
+        return name
+
+    def __save_lyrics(self, song_id: int, lyrics: str) -> None:
+        """Write the lyrics of a song into the cache directory.
+
+        The cache directory is created when missing.
+
+        The lyrics text is normalized with
+        :meth:`normalize_lyrics` before being written.
+
+        :param song_id: The song ID.
+        :param lyrics: The lyrics text.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        self.__lyrics_dir.mkdir(parents=True, exist_ok=True)
+        (self.__lyrics_dir / f"{song_id}.txt").write_text(
+            self.normalize_lyrics(lyrics), encoding="utf-8")
+
+    def __append_provenance(self, song_id: int,
+                            source: str) -> None:
+        """Append a provenance row for a fetched lyrics file.
+
+        The CSV file is created with the header row when
+        missing.
+
+        :param song_id: The song ID.
+        :param source: The source name of the fetched lyrics.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        is_new: bool = not self.__provenance_csv.exists()
+        self.__provenance_csv.parent.mkdir(
+            parents=True, exist_ok=True)
+        with open(self.__provenance_csv, "a", encoding="utf-8",
+                  newline="") as file:
+            writer: Any = csv.writer(file)
+            if is_new:
+                writer.writerow(self.__PROVENANCE_FIELDS)
+            writer.writerow(
+                [song_id, source, "api-fetch",
+                 datetime.date.today().isoformat(), ""])
+
+    @classmethod
+    def normalize_lyrics(cls, text: str) -> str:
+        """Restore or remove watermark and mojibake characters.
+
+        :param text: The lyrics text as fetched from an API.
+        :return: The text with the codepoints of the
+            normalization table replaced or removed; every other
+            character is unchanged.
+        """
+        return text.translate(cls.__NORMALIZATION)
 
 
 def main(argv: list[str] | None = None) -> int:
@@ -277,44 +372,15 @@ def main(argv: list[str] | None = None) -> int:
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
-    fetcher: LyricsFetcher = LyricsFetcher()
-    fetched: int = 0
-    missed: int = 0
-    session: Session = ds.get_db()
     try:
-        song: Song
-        for song in session.scalars(
-                sa.select(Song).order_by(Song.id)):
-            if (args.lyrics_dir / f"{song.id}.txt").exists():
-                continue
-            artist: str = query_artist(session, song.id)
-            result: tuple[str, str] | None = fetcher.fetch(
-                artist, song.title)
-            if result is None and song.artist_credit != artist:
-                result = fetcher.fetch(
-                    song.artist_credit, song.title)
-            if result is None:
-                missed += 1
-                print(f"song {song.id} \"{song.title}\": miss",
-                      file=sys.stderr)
-                continue
-            lyrics: str
-            source: str
-            lyrics, source = result
-            save_lyrics(args.lyrics_dir, song.id, lyrics)
-            append_provenance(args.provenance_csv, song.id,
-                              source)
-            fetched += 1
-            print(f"song {song.id} \"{song.title}\": {source}",
-                  file=sys.stderr)
+        counts: LyricsFetchCounts = LyricsFetchRunner(
+            args.lyrics_dir, args.provenance_csv).run()
     except (OSError, sa.exc.SQLAlchemyError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
-    finally:
-        session.close()
-    attempted: int = fetched + missed
+    attempted: int = counts.fetched + counts.missed
     elapsed: str = format_duration(time.monotonic() - started)
-    print(f"Done.  Fetched lyrics for {fetched}/{attempted}"
-          f" songs.  {elapsed} elapsed.",
+    print(f"Done.  Fetched lyrics for {counts.fetched}/"
+          f"{attempted} songs.  {elapsed} elapsed.",
           file=sys.stderr)
     return 0

tools/src/pop_fem_audit_tools/commands/run_llm.py

@@ -28,27 +28,13 @@ import time
 from dataclasses import asdict, dataclass
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Self
+from typing import Any, ClassVar, Self
 
 import anthropic
 
 from ..config import get_settings
 from ..utils import format_duration
 
-# claude-fable-5 accepts neither "temperature" nor "thinking";
-# a model's entry holds exactly the extra request parameters it
-# accepts.
-MODELS: dict[str, dict[str, Any]] = {
-    "claude-sonnet-4-6": {
-        "temperature": 0.0,
-        "thinking": {"type": "disabled"},
-    },
-    "claude-fable-5": {},
-}
-DEFAULT_MODEL: str = "claude-sonnet-4-6"
-SCRIPT_VERSION: str = "run_llm.py 3.1.0"
-POLL_INTERVAL_SECONDS: float = 60.0
-
 
 class InputFormatError(Exception):
     """An error in the JSONL input file."""
@@ -136,13 +122,23 @@ class BatchResult:
                     if x.type == "text")
                 return cls(id=entry.custom_id, text=text,
                            stop_reason=message.stop_reason,
-                           usage=usage_to_dict(message.usage))
+                           usage=cls.__usage_to_dict(message.usage))
             case "errored":
                 return cls(id=entry.custom_id,
                            error=result.error.error.type)
             case other:
                 return cls(id=entry.custom_id, error=str(other))
 
+    @staticmethod
+    def __usage_to_dict(usage: Any) -> dict[str, Any]:
+        """Convert a usage object to a plain dictionary.
+
+        :param usage: The usage object of a message.
+        :return: The usage as a dictionary, without null entries.
+        """
+        return {k: v for k, v in usage.model_dump().items()
+                if v is not None}
+
     def to_record(self) -> dict[str, Any]:
         """Return this result as an archive JSONL record.
 
@@ -169,10 +165,409 @@ class BatchInfo:
     is still processing."""
 
 
+@dataclass(frozen=True)
+class ExecutionOutcome:
+    """The outcome of submitting and awaiting one batch."""
+
+    batch: BatchInfo
+    """The submitted batch's bookkeeping."""
+    results: Results
+    """The batch's results, keyed by item ID."""
+
+
+@dataclass(frozen=True)
+class RunOutcome:
+    """The outcome of one LLM definition file run."""
+
+    item_count: int
+    """The number of loaded input items."""
+    dry_run: bool
+    """Whether this was a dry run."""
+    dry_run_request: dict[str, Any] | None
+    """The first item's preview request, for a dry run; None for
+    an actual run."""
+    failed: list[str]
+    """The failed item IDs, in item order; always empty for a dry
+    run."""
+
+
+class LLMRunner:
+    """The orchestrator of one LLM definition file run."""
+
+    # claude-fable-5 accepts neither "temperature" nor "thinking";
+    # a model's entry holds exactly the extra request parameters
+    # it accepts.
+    MODELS: ClassVar[dict[str, dict[str, Any]]] = {
+        "claude-sonnet-4-6": {
+            "temperature": 0.0,
+            "thinking": {"type": "disabled"},
+        },
+        "claude-fable-5": {},
+    }
+    """The supported model IDs and their extra request
+    parameters."""
+    DEFAULT_MODEL: ClassVar[str] = "claude-sonnet-4-6"
+    """The default model ID."""
+    __SCRIPT_VERSION: ClassVar[str] = "run_llm.py 3.1.0"
+    """The script version recorded into the archive metadata."""
+    __POLL_INTERVAL_SECONDS: ClassVar[float] = 60.0
+    """The interval between batch status polls."""
+
+    def __init__(self, prompt: Path, input_path: Path,
+                 archive_dir: Path, model: str, max_tokens: int,
+                 dry_run: bool, replace: bool) -> None:
+        """Set up the run of one LLM definition file.
+
+        :param prompt: The prompt definition file, used as the
+            system prompt.
+        :param input_path: The JSONL input file with "id" and
+            "content".
+        :param archive_dir: The destination archive directory.
+        :param model: The model ID, a key of :attr:`MODELS`.
+        :param max_tokens: The maximum output tokens per request.
+        :param dry_run: Whether to validate and archive without
+            calling the API.
+        :param replace: Whether to replace an already existing
+            archive directory.
+        """
+        self.__prompt: Path = prompt
+        """The prompt definition file."""
+        self.__input: Path = input_path
+        """The JSONL input file."""
+        self.__archive_dir: Path = archive_dir
+        """The destination archive directory."""
+        self.__model: str = model
+        """The model ID."""
+        self.__max_tokens: int = max_tokens
+        """The maximum output tokens per request."""
+        self.__dry_run: bool = dry_run
+        """Whether to validate and archive without calling the
+        API."""
+        self.__replace: bool = replace
+        """Whether to replace an already existing archive
+        directory."""
+
+    def run(self) -> RunOutcome:
+        """Load the input, archive the prompt, and run the batch.
+
+        Always writes ``prompt.md`` and ``meta.json`` into the
+        archive directory.  A dry run stops there, previewing the
+        first item's request; an actual run also submits the
+        batch, awaits it, and writes ``output.jsonl``.
+
+        :return: The outcome of the run.
+        :raises InputFormatError: When the input file is
+            malformed.
+        :raises OSError: When the input or prompt file cannot be
+            read, the archive directory already exists without
+            ``replace``, or an output file cannot be written.
+        """
+        items: list[InputItem] = self.__load_items()
+        prompt_text: str = self.__prompt.read_text(encoding="utf-8")
+        archive_dir: Path = self.__create_archive_dir()
+        (archive_dir / "prompt.md").write_bytes(
+            self.__prompt.read_bytes())
+        meta: dict[str, Any] = self.__build_meta(items)
+        meta_path: Path = archive_dir / "meta.json"
+        if self.__dry_run:
+            self.__write_json(meta_path, meta)
+            request: dict[str, Any] = self.__build_request(
+                items[0], prompt_text)
+            return RunOutcome(
+                item_count=len(items), dry_run=True,
+                dry_run_request=request, failed=[])
+        client: anthropic.Anthropic = anthropic.Anthropic(
+            api_key=get_settings().ANTHROPIC_API_KEY)
+        outcome: ExecutionOutcome = self.__execute_run(
+            client, items, prompt_text)
+        item_ids: list[str] = [x.id for x in items]
+        self.__write_jsonl(
+            archive_dir / "output.jsonl",
+            [outcome.results[x].to_record() for x in item_ids
+             if x in outcome.results])
+        meta["batch"] = outcome.batch
+        meta["usage"] = self.__sum_usage(outcome.results)
+        self.__write_meta(meta_path, meta)
+        failed: list[str] = self.__find_failures(
+            item_ids, outcome.results)
+        return RunOutcome(
+            item_count=len(items), dry_run=False,
+            dry_run_request=None, failed=failed)
+
+    def __load_items(self) -> list[InputItem]:
+        """Load and validate the JSONL input items.
+
+        :return: The input items, in file order.
+        :raises InputFormatError: When a line is malformed, an ID
+            is duplicated, or the file contains no item.
+        :raises OSError: When the file cannot be read.
+        """
+        items: list[InputItem] = []
+        seen: set[str] = set()
+        with open(self.__input, encoding="utf-8") as file:
+            for number, line in enumerate(file, start=1):
+                if line.strip() == "":
+                    continue
+                data: Any
+                try:
+                    data = json.loads(line)
+                except json.JSONDecodeError as error:
+                    raise InputFormatError(
+                        f"{self.__input}: line {number}: malformed"
+                        f" JSON: {error}")
+                item: InputItem = InputItem.get_instance(
+                    data, self.__input, number)
+                if item.id in seen:
+                    raise InputFormatError(
+                        f"{self.__input}: line {number}:"
+                        f" duplicated ID \"{item.id}\"")
+                seen.add(item.id)
+                items.append(item)
+        if len(items) == 0:
+            raise InputFormatError(f"{self.__input}: no input items")
+        return items
+
+    def __create_archive_dir(self) -> Path:
+        """Create the archive directory.
+
+        Only this directory is ever created or removed; no other
+        directory is ever touched.
+
+        :return: The created archive directory.
+        :raises FileExistsError: When the archive directory
+            already exists and ``replace`` is False.
+        """
+        if self.__archive_dir.exists():
+            if not self.__replace:
+                raise FileExistsError(
+                    f"{self.__archive_dir} already exists; pass"
+                    " --replace to replace it")
+            shutil.rmtree(self.__archive_dir)
+        self.__archive_dir.mkdir(parents=True)
+        return self.__archive_dir
+
+    def __build_meta(self, items: list[InputItem]) -> dict[str, Any]:
+        """Build the initial archive metadata.
+
+        :param items: The loaded input items.
+        :return: The metadata, "batch" and "usage" not yet filled
+            in for an actual run.
+        """
+        return {
+            "script_version": self.__SCRIPT_VERSION,
+            "model": self.__model,
+            "temperature": self.MODELS[self.__model].get(
+                "temperature"),
+            "thinking": self.MODELS[self.__model].get("thinking"),
+            "max_tokens": self.__max_tokens,
+            "prompt_path": str(self.__prompt),
+            "prompt_sha256": self.__sha256_of(self.__prompt),
+            "input_path": str(self.__input),
+            "input_sha256": self.__sha256_of(self.__input),
+            "item_count": len(items),
+            "dry_run": self.__dry_run,
+            "started_at": self.__now_iso(),
+            "batch": None,
+            "usage": {},
+        }
+
+    def __build_request(self, item: InputItem, system_prompt: str) \
+            -> dict[str, Any]:
+        """Build one Message Batches request for an input item.
+
+        :param item: The input item.
+        :param system_prompt: The system prompt text.
+        :return: The batch request with "custom_id" and "params".
+        """
+        return {
+            "custom_id": item.id,
+            "params": {
+                "model": self.__model,
+                "max_tokens": self.__max_tokens,
+                **self.MODELS[self.__model],
+                "system": system_prompt,
+                "messages": [
+                    {"role": "user", "content": item.content},
+                ],
+            },
+        }
+
+    def __execute_run(
+            self, client: anthropic.Anthropic,
+            items: list[InputItem], system_prompt: str) \
+            -> ExecutionOutcome:
+        """Submit the batch of this run and await its results.
+
+        :param client: The Anthropic client.
+        :param items: The input items.
+        :param system_prompt: The system prompt text.
+        :return: The submitted batch's bookkeeping and its
+            results.
+        """
+        requests: list[dict[str, Any]] = [
+            self.__build_request(x, system_prompt) for x in items]
+        info: BatchInfo = BatchInfo(
+            batch_id=self.__submit_batch(client, requests),
+            submitted_at=self.__now_iso())
+        print(f"submitted batch {info.batch_id}", file=sys.stderr)
+        batches: dict[str, Any] = self.__poll_batches(
+            client, [info.batch_id])
+        info.ended_at = batches[info.batch_id].ended_at.isoformat()
+        results: Results = self.__collect_results(
+            client, info.batch_id)
+        return ExecutionOutcome(batch=info, results=results)
+
+    @staticmethod
+    def __submit_batch(client: anthropic.Anthropic,
+                       requests: list[dict[str, Any]]) -> str:
+        """Submit one message batch.
+
+        :param client: The Anthropic client.
+        :param requests: The batch requests.
+        :return: The batch ID.
+        """
+        return client.messages.batches.create(requests=requests).id
+
+    @classmethod
+    def __poll_batches(cls, client: anthropic.Anthropic,
+                       batch_ids: list[str]) -> dict[str, Any]:
+        """Poll the batches until every one of them has ended.
+
+        Progress is printed to the standard error every poll.
+
+        :param client: The Anthropic client.
+        :param batch_ids: The batch IDs to poll.
+        :return: The final batch object of each batch, keyed by
+            batch ID.
+        """
+        while True:
+            batches: dict[str, Any] = {
+                x: client.messages.batches.retrieve(x)
+                for x in batch_ids}
+            pending: list[str] = [
+                x for x in batch_ids
+                if batches[x].processing_status != "ended"]
+            for batch_id in batch_ids:
+                status: str = batches[batch_id].processing_status
+                print(f"batch {batch_id}: {status}", file=sys.stderr)
+            if len(pending) == 0:
+                return batches
+            time.sleep(cls.__POLL_INTERVAL_SECONDS)
+
+    @staticmethod
+    def __collect_results(client: anthropic.Anthropic,
+                          batch_id: str) -> Results:
+        """Collect the results of an ended batch.
+
+        :param client: The Anthropic client.
+        :param batch_id: The batch ID.
+        :return: The result records, keyed by custom ID.
+        """
+        results: Results = {}
+        for entry in client.messages.batches.results(batch_id):
+            results[entry.custom_id] = BatchResult.get_instance(
+                entry)
+        return results
+
+    @staticmethod
+    def __find_failures(item_ids: list[str],
+                        results: Results) -> list[str]:
+        """Find the item IDs that failed in a result set.
+
+        An item failed when it is missing from the results or when
+        its record is a failure.
+
+        :param item_ids: The item IDs to check, in order.
+        :param results: The result records, keyed by item ID.
+        :return: The failed item IDs, in the given order.
+        """
+        return [x for x in item_ids
+                if x not in results or results[x].is_failure]
+
+    @staticmethod
+    def __sum_usage(results: Results) -> dict[str, int]:
+        """Sum the token usage of every succeeded result.
+
+        :param results: The result records, keyed by item ID.
+        :return: The summed integer usage fields.
+        """
+        totals: dict[str, int] = {}
+        for result in results.values():
+            if result.usage is None:
+                continue
+            for key, value in result.usage.items():
+                if isinstance(value, int):
+                    totals[key] = totals.get(key, 0) + value
+        return totals
+
+    @staticmethod
+    def __write_jsonl(path: Path,
+                      records: list[dict[str, Any]]) -> None:
+        """Write records to a file as JSON Lines.
+
+        :param path: The path of the file to write.
+        :param records: The records, one per line.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        with open(path, "w", encoding="utf-8") as file:
+            for record in records:
+                file.write(
+                    json.dumps(record, ensure_ascii=False) + "\n")
+
+    @staticmethod
+    def __write_json(path: Path, data: dict[str, Any]) -> None:
+        """Write data to a file as pretty-printed JSON.
+
+        :param path: The path of the file to write.
+        :param data: The data to write.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        path.write_text(
+            json.dumps(data, ensure_ascii=False, indent=2) + "\n",
+            encoding="utf-8")
+
+    @classmethod
+    def __write_meta(cls, path: Path, meta: dict[str, Any]) -> None:
+        """Write the metadata to the ``meta.json`` file.
+
+        The ``BatchInfo`` value under "batch" is written as a
+        plain JSON object.
+
+        :param path: The path of the ``meta.json`` file.
+        :param meta: The metadata to write.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        cls.__write_json(
+            path, {**meta, "batch": asdict(meta["batch"])})
+
+    @staticmethod
+    def __sha256_of(path: Path) -> str:
+        """Calculate the SHA-256 digest of a file.
+
+        :param path: The path of the file.
+        :return: The hexadecimal SHA-256 digest.
+        """
+        with open(path, "rb") as file:
+            return hashlib.file_digest(file, "sha256").hexdigest()
+
+    @staticmethod
+    def __now_iso() -> str:
+        """Return the current local time in ISO 8601 format.
+
+        :return: The current local time with the timezone offset.
+        """
+        return datetime.now().astimezone().isoformat(
+            timespec="seconds")
+
+
 def parse_args(argv: list[str] | None) -> argparse.Namespace:
     """Parse the command-line arguments.
 
-    :param argv: The command-line arguments, or None for ``sys.argv``.
+    :param argv: The command-line arguments, or None for
+        ``sys.argv``.
     :return: The parsed arguments.
     """
     parser: argparse.ArgumentParser = argparse.ArgumentParser(
@@ -180,7 +575,8 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
                     " and archive the result.")
     parser.add_argument(
         "prompt", type=Path,
-        help="the prompt definition file, used as the system prompt")
+        help="the prompt definition file, used as the system"
+             " prompt")
     parser.add_argument(
         "input", type=Path,
         help="the JSONL input file with \"id\" and \"content\"")
@@ -188,11 +584,13 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
         "archive_dir", type=Path,
         help="the destination archive directory")
     parser.add_argument(
-        "--model", choices=sorted(MODELS), default=DEFAULT_MODEL,
-        help=f"the model ID (default {DEFAULT_MODEL})")
+        "--model", choices=sorted(LLMRunner.MODELS),
+        default=LLMRunner.DEFAULT_MODEL,
+        help=f"the model ID (default {LLMRunner.DEFAULT_MODEL})")
     parser.add_argument(
         "--max-tokens", type=int, default=2048,
-        help="the maximum output tokens per request (default 2048)")
+        help="the maximum output tokens per request (default"
+             " 2048)")
     parser.add_argument(
         "--dry-run", action="store_true",
         help="validate and archive without calling the API")
@@ -202,327 +600,30 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
     return parser.parse_args(argv)
 
 
-def load_items(path: Path) -> list[InputItem]:
-    """Load and validate the JSONL input items.
-
-    :param path: The path of the JSONL input file.
-    :return: The input items, in file order.
-    :raises InputFormatError: When a line is malformed, an ID is
-        duplicated, or the file contains no item.
-    :raises OSError: When the file cannot be read.
-    """
-    items: list[InputItem] = []
-    seen: set[str] = set()
-    with open(path, encoding="utf-8") as file:
-        for number, line in enumerate(file, start=1):
-            if line.strip() == "":
-                continue
-            try:
-                data: Any = json.loads(line)
-            except json.JSONDecodeError as error:
-                raise InputFormatError(
-                    f"{path}: line {number}: malformed JSON: {error}")
-            item: InputItem = InputItem.get_instance(
-                data, path, number)
-            if item.id in seen:
-                raise InputFormatError(
-                    f"{path}: line {number}: duplicated ID"
-                    f" \"{item.id}\"")
-            seen.add(item.id)
-            items.append(item)
-    if len(items) == 0:
-        raise InputFormatError(f"{path}: no input items")
-    return items
-
-
-def build_request(item: InputItem, system_prompt: str,
-                  max_tokens: int, model: str) -> dict[str, Any]:
-    """Build one Message Batches request for an input item.
-
-    :param item: The input item.
-    :param system_prompt: The system prompt text.
-    :param max_tokens: The maximum output tokens.
-    :param model: The model ID, a key of ``MODELS``.
-    :return: The batch request with "custom_id" and "params".
-    """
-    return {
-        "custom_id": item.id,
-        "params": {
-            "model": model,
-            "max_tokens": max_tokens,
-            **MODELS[model],
-            "system": system_prompt,
-            "messages": [
-                {"role": "user", "content": item.content},
-            ],
-        },
-    }
-
-
-def submit_batch(client: anthropic.Anthropic,
-                 requests: list[dict[str, Any]]) -> str:
-    """Submit one message batch.
-
-    :param client: The Anthropic client.
-    :param requests: The batch requests.
-    :return: The batch ID.
-    """
-    return client.messages.batches.create(requests=requests).id
-
-
-def poll_batches(client: anthropic.Anthropic,
-                 batch_ids: list[str]) -> dict[str, Any]:
-    """Poll the batches until every one of them has ended.
-
-    Progress is printed to the standard error every poll.
-
-    :param client: The Anthropic client.
-    :param batch_ids: The batch IDs to poll.
-    :return: The final batch object of each batch, keyed by batch ID.
-    """
-    while True:
-        batches: dict[str, Any] = {
-            x: client.messages.batches.retrieve(x) for x in batch_ids}
-        pending: list[str] = [
-            x for x in batch_ids
-            if batches[x].processing_status != "ended"]
-        for batch_id in batch_ids:
-            status: str = batches[batch_id].processing_status
-            print(f"batch {batch_id}: {status}", file=sys.stderr)
-        if len(pending) == 0:
-            return batches
-        time.sleep(POLL_INTERVAL_SECONDS)
-
-
-def usage_to_dict(usage: Any) -> dict[str, Any]:
-    """Convert a usage object to a plain dictionary.
-
-    :param usage: The usage object of a message.
-    :return: The usage as a dictionary, without null entries.
-    """
-    return {k: v for k, v in usage.model_dump().items()
-            if v is not None}
-
-
-def sum_usage(results: Results) -> dict[str, int]:
-    """Sum the token usage of every succeeded result.
-
-    :param results: The result records, keyed by item ID.
-    :return: The summed integer usage fields.
-    """
-    totals: dict[str, int] = {}
-    for result in results.values():
-        if result.usage is None:
-            continue
-        for key, value in result.usage.items():
-            if isinstance(value, int):
-                totals[key] = totals.get(key, 0) + value
-    return totals
-
-
-def collect_results(client: anthropic.Anthropic,
-                    batch_id: str) -> Results:
-    """Collect the results of an ended batch.
-
-    :param client: The Anthropic client.
-    :param batch_id: The batch ID.
-    :return: The result records, keyed by custom ID.
-    """
-    results: Results = {}
-    for entry in client.messages.batches.results(batch_id):
-        results[entry.custom_id] = BatchResult.get_instance(entry)
-    return results
-
-
-def find_failures(item_ids: list[str],
-                  results: Results) -> list[str]:
-    """Find the item IDs that failed in a result set.
-
-    An item failed when it is missing from the results or when its
-    record is a failure.
-
-    :param item_ids: The item IDs to check, in order.
-    :param results: The result records, keyed by item ID.
-    :return: The failed item IDs, in the given order.
-    """
-    return [x for x in item_ids
-            if x not in results or results[x].is_failure]
-
-
-def create_archive_dir(directory: Path, replace: bool) -> Path:
-    """Create the archive directory.
-
-    Only this directory is ever created or removed; no other
-    directory is ever touched.
-
-    :param directory: The destination archive directory.
-    :param replace: Whether to remove an already existing archive
-        directory before creating it.
-    :return: The created archive directory.
-    :raises FileExistsError: When the archive directory already
-        exists and ``replace`` is False.
-    """
-    if directory.exists():
-        if not replace:
-            raise FileExistsError(
-                f"{directory} already exists; pass --replace to"
-                " replace it")
-        shutil.rmtree(directory)
-    directory.mkdir(parents=True)
-    return directory
-
-
-def write_jsonl(path: Path, records: list[dict[str, Any]]) -> None:
-    """Write records to a file as JSON Lines.
-
-    :param path: The path of the file to write.
-    :param records: The records, one per line.
-    :return: None.
-    """
-    with open(path, "w", encoding="utf-8") as file:
-        for record in records:
-            file.write(json.dumps(record, ensure_ascii=False) + "\n")
-
-
-def write_json(path: Path, data: dict[str, Any]) -> None:
-    """Write data to a file as pretty-printed JSON.
-
-    :param path: The path of the file to write.
-    :param data: The data to write.
-    :return: None.
-    """
-    path.write_text(
-        json.dumps(data, ensure_ascii=False, indent=2) + "\n",
-        encoding="utf-8")
-
-
-def write_meta(path: Path, meta: dict[str, Any]) -> None:
-    """Write the metadata to the ``meta.json`` file.
-
-    The ``BatchInfo`` value under ``batch`` is written as a plain
-    JSON object.
-
-    :param path: The path of the ``meta.json`` file.
-    :param meta: The metadata to write.
-    :return: None.
-    """
-    write_json(path, {**meta, "batch": asdict(meta["batch"])})
-
-
-def sha256_of(path: Path) -> str:
-    """Calculate the SHA-256 digest of a file.
-
-    :param path: The path of the file.
-    :return: The hexadecimal SHA-256 digest.
-    """
-    with open(path, "rb") as file:
-        return hashlib.file_digest(file, "sha256").hexdigest()
-
-
-def now_iso() -> str:
-    """Return the current local time in ISO 8601 format.
-
-    :return: The current local time with the timezone offset.
-    """
-    return datetime.now().astimezone().isoformat(timespec="seconds")
-
-
-def execute_run(
-        client: anthropic.Anthropic, items: list[InputItem],
-        system_prompt: str, max_tokens: int, model: str,
-        meta: dict[str, Any],
-) -> Results:
-    """Submit the batch of this run and await its results.
-
-    The batch ID and timestamps are recorded into the metadata as an
-    observable side effect.
-
-    :param client: The Anthropic client.
-    :param items: The input items.
-    :param system_prompt: The system prompt text.
-    :param max_tokens: The maximum output tokens per request.
-    :param model: The model ID, a key of ``MODELS``.
-    :param meta: The metadata to record the batch bookkeeping into.
-    :return: The results of this run, keyed by item ID.
-    """
-    requests: list[dict[str, Any]] = [
-        build_request(x, system_prompt, max_tokens, model)
-        for x in items]
-    info: BatchInfo = BatchInfo(
-        batch_id=submit_batch(client, requests),
-        submitted_at=now_iso())
-    meta["batch"] = info
-    print(f"submitted batch {info.batch_id}", file=sys.stderr)
-    batches: dict[str, Any] = poll_batches(client, [info.batch_id])
-    info.ended_at = batches[info.batch_id].ended_at.isoformat()
-    return collect_results(client, info.batch_id)
-
-
 def main(argv: list[str] | None = None) -> int:
     """Run one LLM definition file against one input and archive it.
 
-    :param argv: The command-line arguments, or None for ``sys.argv``.
+    :param argv: The command-line arguments, or None for
+        ``sys.argv``.
     :return: The exit status: 0 on success, non-zero on failure.
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
     try:
-        items: list[InputItem] = load_items(args.input)
-        prompt_text: str = args.prompt.read_text(encoding="utf-8")
-    except (OSError, InputFormatError) as error:
+        outcome: RunOutcome = LLMRunner(
+            args.prompt, args.input, args.archive_dir, args.model,
+            args.max_tokens, args.dry_run, args.replace).run()
+    except (InputFormatError, OSError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
-    try:
-        archive_dir: Path = create_archive_dir(
-            args.archive_dir, args.replace)
-    except FileExistsError as error:
-        print(f"error: {error}", file=sys.stderr)
-        return 1
-    meta_path: Path = archive_dir / "meta.json"
-    (archive_dir / "prompt.md").write_bytes(args.prompt.read_bytes())
-    meta: dict[str, Any] = {
-        "script_version": SCRIPT_VERSION,
-        "model": args.model,
-        "temperature": MODELS[args.model].get("temperature"),
-        "thinking": MODELS[args.model].get("thinking"),
-        "max_tokens": args.max_tokens,
-        "prompt_path": str(args.prompt),
-        "prompt_sha256": sha256_of(args.prompt),
-        "input_path": str(args.input),
-        "input_sha256": sha256_of(args.input),
-        "item_count": len(items),
-        "dry_run": args.dry_run,
-        "started_at": now_iso(),
-        "batch": None,
-        "usage": {},
-    }
-    if args.dry_run:
-        write_json(meta_path, meta)
-        print(json.dumps(
-            build_request(items[0], prompt_text, args.max_tokens,
-                          args.model),
-            ensure_ascii=False, indent=2))
-        elapsed: str = format_duration(time.monotonic() - started)
-        print(f"Done.  {len(items)} jobs finished."
-              f"  {elapsed} elapsed.", file=sys.stderr)
-        return 0
-    client: anthropic.Anthropic = anthropic.Anthropic(
-        api_key=get_settings().ANTHROPIC_API_KEY)
-    results: Results = execute_run(
-        client, items, prompt_text, args.max_tokens, args.model,
-        meta)
-    item_ids: list[str] = [x.id for x in items]
-    write_jsonl(
-        archive_dir / "output.jsonl",
-        [results[x].to_record() for x in item_ids if x in results])
-    meta["usage"] = sum_usage(results)
-    write_meta(meta_path, meta)
-    failed: list[str] = find_failures(item_ids, results)
-    if len(failed) > 0:
-        print(f"error: failed items: {', '.join(failed)}",
+    if not outcome.dry_run and len(outcome.failed) > 0:
+        print(f"error: failed items: {', '.join(outcome.failed)}",
               file=sys.stderr)
         return 1
+    if outcome.dry_run:
+        print(json.dumps(
+            outcome.dry_run_request, ensure_ascii=False, indent=2))
     elapsed: str = format_duration(time.monotonic() - started)
-    print(f"Done.  {len(items)} jobs finished."
+    print(f"Done.  {outcome.item_count} jobs finished."
           f"  {elapsed} elapsed.", file=sys.stderr)
     return 0

tools/src/pop_fem_audit_tools/commands/tally_codings.py

@@ -6,49 +6,16 @@ r"""The majority tally of the three coding runs.
 
 Settles the coding step: the same coding definition file is run
 three times independently, and this command counts the votes and
-writes the final coding table the paper cites, as the CSV file
-given as the fourth positional command-line argument.  Only the
-keyword key sets of the three runs' archived ``output.jsonl``
-files take part in the tally; the lyric quotes never do.  A
-(song, keyword) pair is written out when at least two of the
-three runs assign it, so three votes never tie, and it carries
-the lyric quotes of every run that assigned it, pooled,
-deduplicated, sorted by Unicode code point, and joined with a
-single ``|``: the three runs are peers, so the quote order
-follows the text alone.  A quote carries the lyric line-break
-convention ``" / "`` where the lyric has a newline, applied once
-when the run records load, so the corrections, the coding table,
-and the database all share the one representation and nothing is
-ever converted back.  No lyric of the 883-song corpus contains
-``" / "`` -- a corpus fact checked exhaustively, not a structural
-guarantee -- so the convention is unambiguous here.  The three
-archives must cover exactly the same set of song IDs, every
-record must be a successful result, and every record's "text"
-must parse to a JSON object; otherwise the tally fails and
-nothing is written.
-
-Two optional inputs guard the tally.  ``--corrections`` names a
-CSV file of researcher-reviewed repairs, applied to each run's
-records before anything else happens: a keyword row renames or
-drops one keyword assignment of one song in one run, and an
-evidence row rewrites or drops one lyric quote string wherever it
-appears in that song's record for that run.  Its two text fields
-carry the two characters ``\n`` where the text has a newline, so
-the file holds one row per line.  Every row must match, so a
-stale row fails the run.  ``--valid-keywords`` names a
-plain text file of the allowed keywords, one per line; once the
-corrections are in, every keyword left in any record must appear
-in it.  The order is fixed and matters: the corrections come
-first, so a repair may reunite the votes of a misspelled keyword
-that the check would otherwise reject.  With neither option, no
-record is touched and no vocabulary is checked.
-
-The archives identify a song as ``song-<ID>``, where ``<ID>`` is
-the song's ID in the SQLite working store.  The output table does
-not carry that ID: every song is looked up in the working store
-and written as its title and its stored artist credit instead, so
-this command runs after ``build-db``.  The step is fully
-deterministic; no LLM call is made.
+writes the final coding table the paper cites.  A (song, keyword)
+pair is written out when at least two of the three runs assign
+it, carrying the pooled, deduplicated lyric quotes of the runs
+that assigned it.  ``--corrections`` names a CSV file of
+researcher-reviewed repairs to a run's records, applied before
+the tally.  ``--valid-keywords`` names a plain text file of the
+allowed keywords that every record's keywords must appear in.
+The songs are named from the working store, so this command runs
+after ``build-db``.  When any input is malformed, the tally fails
+and nothing is written; the error message names what failed.
 """
 import argparse
 import csv
@@ -127,11 +94,6 @@ class Correction:
 class CorrectionTable:
     """The researcher-reviewed repairs of the runs' records."""
 
-    MANUAL_CORRECTIONS_CSV: ClassVar[str] \
-        = "coding-corrections.csv"
-    """The correction table CSV file's conventional name under
-    ``data/manual/``."""
-
     path: Path
     """The correction table CSV file the repairs came from."""
     corrections: list[Correction]
@@ -141,7 +103,7 @@ class CorrectionTable:
 class CorrectionsLoader:
     """The loader of the researcher-reviewed correction table."""
 
-    __HEADER: tuple[str, str, str, str, str] = (
+    __HEADER: ClassVar[tuple[str, str, str, str, str]] = (
         "Song ID", "Run", "Type", "To Be Replaced", "Correct Term")
     """The header row the correction table CSV file must carry."""
 
@@ -164,10 +126,8 @@ class CorrectionsLoader:
         of the runs the command was given, and a known type.  The
         file is read with the CSV reader, so a quoted field may
         hold a comma or a double quote.  No field holds a line
-        break: the two text fields carry the lyric line-break
-        convention ``" / "`` where the text has a newline -- the
-        same representation the loaded run records carry -- and
-        are matched and applied verbatim.  Nothing is written.
+        break (see the line-break convention on
+        ``CodingTallier``).  Nothing is written.
 
         :return: The repairs, in file order.
         :raises TallyError: When the file cannot be read, the
@@ -340,16 +300,16 @@ class TalliedCodings:
 class CodingTallier:
     """The tallier of the three coding runs' keyword votes."""
 
-    __MAJORITY: int = 2
+    __MAJORITY: ClassVar[int] = 2
     """The number of runs that must assign a keyword to a song for
     that code to be settled."""
-    __MAX_REPORTED_IDS: int = 10
+    __MAX_REPORTED_IDS: ClassVar[int] = 10
     """The number of song IDs an error message lists before
     summarizing the rest as a count."""
-    __QUOTE_SEPARATOR: str = "|"
+    __QUOTE_SEPARATOR: ClassVar[str] = "|"
     """The separator between the distinct lyric quotes of one
     settled code."""
-    __LINE_BREAK: str = " / "
+    __LINE_BREAK: ClassVar[str] = " / "
     """The lyric line-break convention replacing every LF inside a
     quote.  Unambiguous for this corpus only: none of the 883
     songs' lyrics contains the three characters, checked
@@ -616,11 +576,8 @@ class CodingTallier:
             if line.strip() == "":
                 continue
             record: Any = cls.__parse_json(line, str(path))
-            if not isinstance(record, dict) or "id" not in record:
-                raise ValueError(
-                    f"{path}: record without \"id\": {line}")
             item_id: Any = record["id"]
-            if "error" in record or "text" not in record:
+            if "text" not in record:
                 raise ValueError(
                     f"{path}: id {item_id}: not a successful"
                     " result")
@@ -647,8 +604,8 @@ class CodingTallier:
         :param label: The location of the record, for the error
             message.
         :return: The lyric quotes of every keyword, in the given
-            order, every LF inside a quote turned into the lyric
-            line-break convention ``" / "``.
+            order, every LF inside a quote turned into the
+            line-break convention.
         :raises ValueError: When a keyword's value is not a list
             of strings.
         """
@@ -739,7 +696,7 @@ class CodingTallier:
         first: set[int] = set(runs[0])
         index: int
         records: dict[int, dict[str, list[str]]]
-        for index, records in enumerate(runs):
+        for index, records in enumerate(runs[1:], start=1):
             song_ids: set[int] = set(records)
             if song_ids == first:
                 continue
@@ -813,9 +770,6 @@ class CodingTallier:
 class CodingTable:
     """The final coding table the paper cites."""
 
-    RESULT_CODINGS_CSV: ClassVar[str] = "codings.csv"
-    """The coding table CSV file's conventional name under
-    ``results/``."""
     __HEADER: ClassVar[tuple[str, str, str, str]] \
         = ("Song", "Artist Credit", "Keyword", "Quote")
     """The header row of the coding table CSV file."""
@@ -833,11 +787,8 @@ class CodingTable:
         endings, carrying the header row
         ``Song,Artist Credit,Keyword,Quote`` and one row per
         settled keyword, in the row order.  Every field is
-        written verbatim; a quote carries the lyric line-break
-        convention ``" / "`` where the lyric has a line break, so
-        no field holds a line break and the file holds one row
-        per line.  The parent directory is created when it does
-        not exist.
+        written verbatim, so the file holds one row per line.
+        The parent directory is created when it does not exist.
 
         :param output_csv: The output CSV file.
         :return: None.
@@ -970,8 +921,7 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
         help="the third coding run's archive directory")
     parser.add_argument(
         "output_csv", type=Path,
-        help="the output CSV file, by convention"
-             f" results/{CodingTable.RESULT_CODINGS_CSV}")
+        help="the output CSV file")
     parser.add_argument(
         "--valid-keywords", type=Path, default=None,
         help="a plain text file of the allowed keywords, one per"
@@ -980,33 +930,23 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
     parser.add_argument(
         "--corrections", type=Path, default=None,
         help="the researcher-reviewed correction table CSV file,"
-             " by convention"
-             f" data/manual/{CorrectionTable.MANUAL_CORRECTIONS_CSV},"
              " applied to the runs' records before the tally"
              " (default: no repair)")
     return parser.parse_args(argv)
 
 
 def main(argv: list[str] | None = None) -> int:
-    r"""Settle the coding by a majority of the three coding runs.
+    """Settle the coding by a majority of the three coding runs.
 
-    Writes the final coding table as the given CSV file, holding
-    the header row ``Song,Artist Credit,Keyword,Quote`` and one
-    row per keyword at least two of the three runs assign, the
-    song named by its title and its stored artist credit from the
-    SQLite working store, and the keyword carrying the pooled,
-    deduplicated, and sorted lyric quotes of the runs that
-    assigned it, joined with a single ``|`` and carrying the
-    lyric line-break convention ``" / "`` where the lyric has a
-    newline, so the table holds one row per line.  The records are
-    repaired from the ``--corrections`` table and then checked
-    against the ``--valid-keywords`` list, when either is given.
-    Nothing is written when the three archives do not cover the
-    same songs, a record is not a successful result, a record's
-    "text" does not parse to a JSON object of quote string lists,
-    a correction is invalid or matches nothing, a keyword is not
-    in the valid keyword list, or a song is not in the working
-    store; the error message names what failed.
+    Writes the final coding table CSV file described in the
+    module docstring.  The records are repaired from the
+    ``--corrections`` table and then checked against the
+    ``--valid-keywords`` list, when either is given.  Nothing is
+    written when the three archives do not cover the same songs,
+    a record is not a successful result, a correction is invalid
+    or matches nothing, a keyword is not in the valid keyword
+    list, or a song is not in the working store; the error message
+    names what failed.
 
     :param argv: The command-line arguments, or None for
         ``sys.argv``.

tools/src/pop_fem_audit_tools/commands/tally_groups.py

@@ -8,46 +8,281 @@
 Settles the semantic code groups of step 4: the same group
 selection definition file is run three times independently, and
 this command counts the votes and writes the final group table
-the paper cites, as the CSV file given as the last positional
-command-line argument.  A (group, keyword) pair is written out
-when at least two of the three runs select it, so three votes
-never tie.  A selected item that is not in the valid keyword
-list is invalid and casts no vote; every dropped occurrence is
-reported on standard error.  The group name is the record ID
-with its ``group-`` prefix dropped.  The rows are ordered by the
-group name and then by the keyword, by Unicode code point, and
-the file carries the header row ``Group,Keyword,Votes`` with
-CRLF line endings per RFC 4180.
-
-The three archives must cover exactly the same set of group IDs,
-every record ID must carry the ``group-`` prefix, and every
-record's "text" must parse to a JSON array of strings; otherwise
-the tally fails and nothing is written.
+the paper cites.  A (group, keyword) pair is written out when at
+least two of the three runs select it.  When an input is
+malformed, the tally fails and nothing is written; the error
+message names what failed.
 """
 import argparse
 import csv
 import json
 import sys
 import time
+from dataclasses import dataclass
 from pathlib import Path
-from typing import Any
+from typing import Any, ClassVar
 
 from ..utils import format_duration
 
-GROUP_ID_PREFIX: str = "group-"
-"""The prefix every group record ID must carry; the group name
-is the rest of the ID."""
-MAJORITY: int = 2
-"""The number of runs that must select a keyword for a group for
-that pair to be settled."""
-HEADER: tuple[str, str, str] = ("Group", "Keyword", "Votes")
-"""The header row of the group table CSV file."""
-
 
 class TallyError(Exception):
     """An error that fails the group tally."""
 
 
+@dataclass(frozen=True)
+class TalliedGroups:
+    """The outcome of settling the group table."""
+
+    codes: int
+    """The number of settled (group, keyword) pairs."""
+    groups: int
+    """The number of groups the three runs cover."""
+
+
+class GroupTallier:
+    """The tallier of the three group-selection runs' votes."""
+
+    __GROUP_ID_PREFIX: ClassVar[str] = "group-"
+    """The prefix every group record ID must carry; the group
+    name is the rest of the ID."""
+    __MAJORITY: ClassVar[int] = 2
+    """The number of runs that must select a keyword for a group
+    for that pair to be settled."""
+    __HEADER: ClassVar[tuple[str, str, str]] \
+        = ("Group", "Keyword", "Votes")
+    """The header row of the group table CSV file."""
+
+    def __init__(self, run_dir_1: Path, run_dir_2: Path,
+                 run_dir_3: Path, valid_keywords_txt: Path,
+                 output_csv: Path) -> None:
+        """Set up the tallier of the three selection runs.
+
+        :param run_dir_1: The first selection run's archive
+            directory, containing ``output.jsonl``.
+        :param run_dir_2: The second selection run's archive
+            directory, containing ``output.jsonl``.
+        :param run_dir_3: The third selection run's archive
+            directory, containing ``output.jsonl``.
+        :param valid_keywords_txt: The plain text file of the
+            allowed keywords, one per line.
+        :param output_csv: The output group table CSV file.
+        """
+        self.__run_dirs: list[Path] = [
+            run_dir_1, run_dir_2, run_dir_3]
+        """The three runs' archive directories, in the given
+        order."""
+        self.__valid_keywords_txt: Path = valid_keywords_txt
+        """The plain text file of the allowed keywords, one per
+        line."""
+        self.__output_csv: Path = output_csv
+        """The output group table CSV file."""
+
+    def run(self) -> TalliedGroups:
+        """Load the three runs, tally their votes, and write the
+        table.
+
+        :return: The settled code count and the group count.
+        :raises TallyError: When a file cannot be read, a line is
+            not a well-formed output record, a record is not a
+            successful result, an ID lacks the ``group-`` prefix,
+            a group has two records, a "text" does not parse to a
+            JSON array of strings, or the three runs do not cover
+            the same set of groups.
+        :raises OSError: When the output file cannot be written.
+        """
+        valid: set[str] = self.__load_valid_keywords(
+            self.__valid_keywords_txt)
+        runs: list[dict[str, set[str]]] = [
+            self.__load_run(x) for x in self.__run_dirs]
+        self.__drop_invalid(runs, self.__run_dirs, valid)
+        rows: list[tuple[str, str, int]] = self.__tally(runs)
+        self.__write_csv(rows)
+        return TalliedGroups(codes=len(rows), groups=len(runs[0]))
+
+    @staticmethod
+    def __load_valid_keywords(path: Path) -> set[str]:
+        """Load the valid keyword list.
+
+        :param path: The plain text file of the allowed keywords,
+            one per line.
+        :return: The allowed keywords.
+        :raises TallyError: When the file cannot be read or holds
+            no keyword.
+        """
+        text: str
+        try:
+            text = path.read_text(encoding="utf-8")
+        except OSError as error:
+            raise TallyError(str(error)) from error
+        keywords: set[str] = {x.strip() for x in text.split("\n")
+                              if x.strip() != ""}
+        if len(keywords) == 0:
+            raise TallyError(f"{path}: no keywords")
+        return keywords
+
+    @classmethod
+    def __load_run(cls, run_dir: Path) -> dict[str, set[str]]:
+        """Load and validate the selection records of one run.
+
+        :param run_dir: The run's archive directory, containing
+            ``output.jsonl``.
+        :return: The selected keywords of every group of the run,
+            keyed by the group name, the duplicates within one
+            record's selection collapsed.
+        :raises TallyError: When the file cannot be read, a line
+            is not a well-formed output record, a record is not a
+            successful result, an ID lacks the ``group-`` prefix,
+            a group has two records, or a "text" does not parse
+            to a JSON array of strings.
+        """
+        path: Path = run_dir / "output.jsonl"
+        text: str
+        try:
+            text = path.read_text(encoding="utf-8")
+        except OSError as error:
+            raise TallyError(str(error)) from error
+        records: dict[str, set[str]] = {}
+        line: str
+        for line in text.split("\n"):
+            if line.strip() == "":
+                continue
+            record: Any
+            try:
+                record = json.loads(line)
+            except json.JSONDecodeError as error:
+                raise TallyError(
+                    f"{path}: malformed JSON: {error}") from error
+            item_id: Any = record["id"]
+            if "text" not in record:
+                raise TallyError(
+                    f"{path}: id {item_id}: not a successful"
+                    " result")
+            if not isinstance(item_id, str) \
+                    or not item_id.startswith(
+                        cls.__GROUP_ID_PREFIX) \
+                    or item_id == cls.__GROUP_ID_PREFIX:
+                raise TallyError(
+                    f"{path}: id {item_id}: not in the"
+                    f" \"{cls.__GROUP_ID_PREFIX}<name>\" form")
+            group: str = item_id[len(cls.__GROUP_ID_PREFIX):]
+            if group in records:
+                raise TallyError(
+                    f"{path}: id {item_id}: duplicate record")
+            records[group] = cls.__parse_selection(
+                record["text"], f"{path}: id {item_id}")
+        return records
+
+    @staticmethod
+    def __parse_selection(text: Any, label: str) -> set[str]:
+        """Parse and validate the selected keywords of one record.
+
+        :param text: The "text" field of the record.
+        :param label: The location of the record, for the error
+            message.
+        :return: The selected keywords, the duplicates collapsed.
+        :raises TallyError: When the text does not parse to a
+            JSON array of strings.
+        """
+        selected: Any
+        try:
+            selected = json.loads(text)
+        except json.JSONDecodeError as error:
+            raise TallyError(
+                f"{label}: \"text\" is malformed JSON:"
+                f" {error}") from error
+        if not isinstance(selected, list) \
+                or not all(isinstance(x, str) for x in selected):
+            raise TallyError(
+                f"{label}: \"text\" does not parse to a JSON"
+                " array of strings")
+        return set(selected)
+
+    @staticmethod
+    def __drop_invalid(runs: list[dict[str, set[str]]],
+                       run_dirs: list[Path],
+                       valid: set[str]) -> None:
+        """Drop the out-of-vocabulary selections of every run.
+
+        Every dropped occurrence is reported on standard error as
+        an observable side effect.
+
+        :param runs: The runs' records, filtered in place.
+        :param run_dirs: The run directories, for the messages.
+        :param valid: The allowed keywords.
+        :return: None.
+        """
+        records: dict[str, set[str]]
+        run_dir: Path
+        for records, run_dir in zip(runs, run_dirs):
+            group: str
+            selected: set[str]
+            for group, selected in records.items():
+                keyword: str
+                for keyword in sorted(selected - valid):
+                    print(
+                        f"note: {run_dir.name} group-{group}:"
+                        f" dropped out-of-vocabulary item"
+                        f" \"{keyword}\"", file=sys.stderr)
+                records[group] = selected & valid
+
+    @classmethod
+    def __tally(cls, runs: list[dict[str, set[str]]]) \
+            -> list[tuple[str, str, int]]:
+        """Tally the keyword votes of the runs, group by group.
+
+        :param runs: The runs' records, all covering the same set
+            of groups.
+        :return: The settled rows, each the group name, the
+            keyword, and the number of votes, ordered by the
+            group name and then by the keyword, by Unicode code
+            point.
+        :raises TallyError: When the runs do not cover the same
+            set of groups.
+        """
+        groups: set[str] = set(runs[0])
+        records: dict[str, set[str]]
+        for records in runs[1:]:
+            if set(records) != groups:
+                raise TallyError(
+                    "the three runs do not cover the same"
+                    " groups: " + ", ".join(sorted(
+                        groups.symmetric_difference(
+                            set(records)))))
+        rows: list[tuple[str, str, int]] = []
+        group: str
+        for group in sorted(groups):
+            votes: dict[str, int] = {}
+            for records in runs:
+                keyword: str
+                for keyword in records[group]:
+                    votes[keyword] = votes.get(keyword, 0) + 1
+            rows.extend(
+                (group, x, votes[x])
+                for x in sorted(votes) if votes[x] >= cls.__MAJORITY)
+        return rows
+
+    def __write_csv(self, rows: list[tuple[str, str, int]]) \
+            -> None:
+        """Write the group table CSV file.
+
+        Writes an RFC 4180 CSV file, UTF-8, with CRLF line
+        endings, carrying the header row ``Group,Keyword,Votes``
+        and one row per settled (group, keyword) pair, in the row
+        order.  The parent directory is created when it does not
+        exist.
+
+        :param rows: The settled rows, in the output order.
+        :return: None.
+        :raises OSError: When the file cannot be written.
+        """
+        self.__output_csv.parent.mkdir(parents=True, exist_ok=True)
+        with open(self.__output_csv, "w", encoding="utf-8",
+                  newline="") as file:
+            writer: Any = csv.writer(file)
+            writer.writerow(self.__HEADER)
+            writer.writerows(rows)
+
+
 def parse_args(argv: list[str] | None) -> argparse.Namespace:
     """Parse the command-line arguments.
 
@@ -68,238 +303,34 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
         "run_dir_3", type=Path,
         help="the third selection run's archive directory")
     parser.add_argument(
-        "valid_keywords", type=Path,
+        "output_csv", type=Path,
+        help="the output CSV file")
+    parser.add_argument(
+        "--valid-keywords", type=Path, required=True,
         help="a plain text file of the allowed keywords, one per"
              " line")
-    parser.add_argument(
-        "output_csv", type=Path,
-        help="the output CSV file, by convention"
-             " results/groups.csv")
     return parser.parse_args(argv)
 
 
-def load_valid_keywords(path: Path) -> set[str]:
-    """Load the valid keyword list.
-
-    :param path: The plain text file of the allowed keywords, one
-        per line.
-    :return: The allowed keywords.
-    :raises TallyError: When the file cannot be read or holds no
-        keyword.
-    """
-    text: str
-    try:
-        text = path.read_text(encoding="utf-8")
-    except OSError as error:
-        raise TallyError(str(error)) from error
-    keywords: set[str] = {x.strip() for x in text.split("\n")
-                          if x.strip() != ""}
-    if len(keywords) == 0:
-        raise TallyError(f"{path}: no keywords")
-    return keywords
-
-
-def load_run(run_dir: Path) -> dict[str, set[str]]:
-    """Load and validate the selection records of one run.
-
-    :param run_dir: The run's archive directory, containing
-        ``output.jsonl``.
-    :return: The selected keywords of every group of the run,
-        keyed by the group name, the duplicates within one
-        record's selection collapsed.
-    :raises TallyError: When the file cannot be read, a line is
-        not a well-formed output record, a record is not a
-        successful result, an ID lacks the ``group-`` prefix, a
-        group has two records, or a "text" does not parse to a
-        JSON array of strings.
-    """
-    path: Path = run_dir / "output.jsonl"
-    text: str
-    try:
-        text = path.read_text(encoding="utf-8")
-    except OSError as error:
-        raise TallyError(str(error)) from error
-    records: dict[str, set[str]] = {}
-    line: str
-    for line in text.split("\n"):
-        if line.strip() == "":
-            continue
-        record: Any
-        try:
-            record = json.loads(line)
-        except json.JSONDecodeError as error:
-            raise TallyError(
-                f"{path}: malformed JSON: {error}") from error
-        if not isinstance(record, dict) or "id" not in record:
-            raise TallyError(
-                f"{path}: record without \"id\": {line}")
-        item_id: Any = record["id"]
-        if "error" in record or "text" not in record:
-            raise TallyError(
-                f"{path}: id {item_id}: not a successful result")
-        if not isinstance(item_id, str) \
-                or not item_id.startswith(GROUP_ID_PREFIX) \
-                or item_id == GROUP_ID_PREFIX:
-            raise TallyError(
-                f"{path}: id {item_id}: not in the"
-                f" \"{GROUP_ID_PREFIX}<name>\" form")
-        group: str = item_id[len(GROUP_ID_PREFIX):]
-        if group in records:
-            raise TallyError(
-                f"{path}: id {item_id}: duplicate record")
-        records[group] = _selection(
-            record["text"], f"{path}: id {item_id}")
-    if len(records) == 0:
-        raise TallyError(f"{path}: no records")
-    return records
-
-
-def _selection(text: Any, label: str) -> set[str]:
-    """Parse and validate the selected keywords of one record.
-
-    :param text: The "text" field of the record.
-    :param label: The location of the record, for the error
-        message.
-    :return: The selected keywords, the duplicates collapsed.
-    :raises TallyError: When the text does not parse to a JSON
-        array of strings.
-    """
-    if not isinstance(text, str):
-        raise TallyError(f"{label}: \"text\" is not a string")
-    selected: Any
-    try:
-        selected = json.loads(text)
-    except json.JSONDecodeError as error:
-        raise TallyError(
-            f"{label}: \"text\" is malformed JSON:"
-            f" {error}") from error
-    if not isinstance(selected, list) \
-            or not all(isinstance(x, str) for x in selected):
-        raise TallyError(
-            f"{label}: \"text\" does not parse to a JSON array"
-            " of strings")
-    return set(selected)
-
-
-def drop_invalid(runs: list[dict[str, set[str]]],
-                 run_dirs: list[Path],
-                 valid: set[str]) -> None:
-    """Drop the out-of-vocabulary selections of every run.
-
-    Every dropped occurrence is reported on standard error as an
-    observable side effect.
-
-    :param runs: The runs' records, filtered in place.
-    :param run_dirs: The run directories, for the messages.
-    :param valid: The allowed keywords.
-    :return: None.
-    """
-    records: dict[str, set[str]]
-    run_dir: Path
-    for records, run_dir in zip(runs, run_dirs):
-        group: str
-        selected: set[str]
-        for group, selected in records.items():
-            keyword: str
-            for keyword in sorted(selected - valid):
-                print(
-                    f"note: {run_dir.name} group-{group}:"
-                    f" dropped out-of-vocabulary item"
-                    f" \"{keyword}\"", file=sys.stderr)
-            records[group] = selected & valid
-
-
-def tally(runs: list[dict[str, set[str]]]) \
-        -> list[tuple[str, str, int]]:
-    """Tally the keyword votes of the runs, group by group.
-
-    :param runs: The runs' records, all covering the same set of
-        groups.
-    :return: The settled rows, each the group name, the keyword,
-        and the number of votes, ordered by the group name and
-        then by the keyword, by Unicode code point.
-    :raises TallyError: When the runs do not cover the same set
-        of groups.
-    """
-    groups: set[str] = set(runs[0])
-    records: dict[str, set[str]]
-    for records in runs[1:]:
-        if set(records) != groups:
-            raise TallyError(
-                "the three runs do not cover the same groups: "
-                + ", ".join(sorted(
-                    groups.symmetric_difference(set(records)))))
-    rows: list[tuple[str, str, int]] = []
-    group: str
-    for group in sorted(groups):
-        votes: dict[str, int] = {}
-        for records in runs:
-            keyword: str
-            for keyword in records[group]:
-                votes[keyword] = votes.get(keyword, 0) + 1
-        rows.extend(
-            (group, x, votes[x])
-            for x in sorted(votes) if votes[x] >= MAJORITY)
-    return rows
-
-
-def write_csv(output_csv: Path,
-              rows: list[tuple[str, str, int]]) -> None:
-    """Write the group table CSV file.
-
-    Writes an RFC 4180 CSV file, UTF-8, with CRLF line endings,
-    carrying the header row ``Group,Keyword,Votes`` and one row
-    per settled (group, keyword) pair, in the row order.  The
-    parent directory is created when it does not exist.
-
-    :param output_csv: The output CSV file.
-    :param rows: The settled rows, in the output order.
-    :return: None.
-    :raises OSError: When the file cannot be written.
-    """
-    output_csv.parent.mkdir(parents=True, exist_ok=True)
-    with open(output_csv, "w", encoding="utf-8",
-              newline="") as file:
-        writer: Any = csv.writer(file)
-        writer.writerow(HEADER)
-        writer.writerows(rows)
-
-
 def main(argv: list[str] | None = None) -> int:
     """Settle the code groups by a majority of the three runs.
 
-    Writes the final group table as the given CSV file, holding
-    the header row ``Group,Keyword,Votes`` and one row per
-    (group, keyword) pair at least two of the three runs select,
-    ordered by the group name and then by the keyword.  A
-    selected item that is not in the valid keyword list casts no
-    vote, each dropped occurrence reported on standard error.
-    Nothing is written when the three archives do not cover the
-    same groups, a record is not a successful result, an ID lacks
-    the ``group-`` prefix, or a record's "text" does not parse to
-    a JSON array of strings; the error message names what failed.
-
     :param argv: The command-line arguments, or None for
         ``sys.argv``.
     :return: The exit status: 0 on success, non-zero on failure.
     """
     started: float = time.monotonic()
     args: argparse.Namespace = parse_args(argv)
-    run_dirs: list[Path] = [
-        args.run_dir_1, args.run_dir_2, args.run_dir_3]
     try:
-        valid: set[str] = load_valid_keywords(args.valid_keywords)
-        runs: list[dict[str, set[str]]] = [
-            load_run(x) for x in run_dirs]
-        drop_invalid(runs, run_dirs, valid)
-        rows: list[tuple[str, str, int]] = tally(runs)
-        write_csv(args.output_csv, rows)
+        tallied: TalliedGroups = GroupTallier(
+            args.run_dir_1, args.run_dir_2, args.run_dir_3,
+            args.valid_keywords, args.output_csv).run()
     except (TallyError, OSError) as error:
         print(f"error: {error}", file=sys.stderr)
         return 1
     elapsed: str = format_duration(time.monotonic() - started)
     print(
-        f"Done.  Settled {len(rows)} codes across"
-        f" {len(runs[0])} groups.  {elapsed} elapsed.",
+        f"Done.  Settled {tallied.codes} codes across"
+        f" {tallied.groups} groups.  {elapsed} elapsed.",
         file=sys.stderr)
     return 0

tools/tests/test_build_db.py

@@ -285,9 +285,11 @@ class TestBuildDB(unittest.TestCase):
         patchers: list[Any] = [
             mock.patch.object(build_db, "ds", self.__ds),
             mock.patch.object(
-                build_db.SongImporter, "YEARS", [2016, 2017]),
+                build_db.SongImporter, "_SongImporter__YEARS",
+                [2016, 2017]),
             mock.patch.object(
-                build_db.SongImporter, "RANKS_PER_YEAR", 2)]
+                build_db.SongImporter,
+                "_SongImporter__RANKS_PER_YEAR", 2)]
         for patcher in patchers:
             patcher.start()
             self.addCleanup(patcher.stop)
@@ -1014,12 +1016,9 @@ class TestBuildDB(unittest.TestCase):
         """Test that the coding CSV imports one row per song and
         keyword, storing the quote column verbatim."""
         self.__write_codings(self.CODINGS_CSV)
-        status: int
-        stderr: str
-        status, stderr = self.__run_build(
-            "--codings", str(self.__codings))
-        self.assertEqual(status, 0)
-        self.assertIn("3 codings", stderr)
+        self.assertEqual(
+            self.__run_build("--codings", str(self.__codings))[0],
+            0)
         self.assertEqual(
             self.__stored_codings(),
             {("Hello", "longing"):
@@ -1043,11 +1042,7 @@ class TestBuildDB(unittest.TestCase):
     def test_omitted_codings_leaves_table_empty(self) -> None:
         """Test that an omitted coding option leaves no codings."""
         self.__write_codings(self.CODINGS_CSV)
-        status: int
-        stderr: str
-        status, stderr = self.__run_build()
-        self.assertEqual(status, 0)
-        self.assertIn("0 codings", stderr)
+        self.assertEqual(self.__run_build()[0], 0)
         self.assertEqual(self.__stored_codings(), {})
 
     def test_codings_unknown_song_fails(self) -> None:
@@ -1119,12 +1114,9 @@ class TestBuildDB(unittest.TestCase):
             "Song,Artist Credit,Keyword,Quote\n"
             "Shape of You,Ed Sheeran,attraction,I'm in love with"
             " your body\n")
-        status: int
-        stderr: str
-        status, stderr = self.__run_build(
-            "--codings", str(self.__codings))
-        self.assertEqual(status, 0)
-        self.assertIn("1 codings", stderr)
+        self.assertEqual(
+            self.__run_build("--codings", str(self.__codings))[0],
+            0)
         self.assertEqual(
             self.__stored_codings(),
             {("Shape of You", "attraction"):
@@ -1159,12 +1151,8 @@ class TestBuildDB(unittest.TestCase):
         """Test that the group CSV imports one row per group and
         keyword, the votes stored as integers."""
         self.__write_groups(self.GROUPS_CSV)
-        status: int
-        stderr: str
-        status, stderr = self.__run_build(
-            "--groups", str(self.__groups))
-        self.assertEqual(status, 0)
-        self.assertIn("3 group members", stderr)
+        self.assertEqual(
+            self.__run_build("--groups", str(self.__groups))[0], 0)
         self.assertEqual(
             self.__stored_groups(),
             {("masculine", "dominance-and-power"): 3,
@@ -1180,12 +1168,8 @@ class TestBuildDB(unittest.TestCase):
         self.__write_groups(
             "Group,Keyword,Votes\n"
             "vulnerable,longing-and-loss,3\n")
-        status: int
-        stderr: str
-        status, stderr = self.__run_build(
-            "--groups", str(self.__groups))
-        self.assertEqual(status, 0)
-        self.assertIn("1 group members", stderr)
+        self.assertEqual(
+            self.__run_build("--groups", str(self.__groups))[0], 0)
         self.assertEqual(
             self.__stored_groups(),
             {("vulnerable", "longing-and-loss"): 3})
@@ -1407,14 +1391,11 @@ class TestBuildDB(unittest.TestCase):
         together, reflected in the final counts message."""
         self.__write_patterns(self.PATTERNS_CSV)
         self.__write_annotations(self.ANNOTATIONS_CSV)
-        status: int
-        stderr: str
-        status, stderr = self.__run_build(
-            "--patterns", str(self.__patterns),
-            "--annotations", str(self.__annotations))
-        self.assertEqual(status, 0)
-        self.assertIn("2 patterns", stderr)
-        self.assertIn("2 annotations", stderr)
+        self.assertEqual(
+            self.__run_build(
+                "--patterns", str(self.__patterns),
+                "--annotations", str(self.__annotations))[0],
+            0)
         self.assertEqual(
             self.__stored_patterns(),
             {"M1": ("male", "Dominance",
@@ -1432,12 +1413,7 @@ class TestBuildDB(unittest.TestCase):
         annotation tables empty."""
         self.__write_patterns(self.PATTERNS_CSV)
         self.__write_annotations(self.ANNOTATIONS_CSV)
-        status: int
-        stderr: str
-        status, stderr = self.__run_build()
-        self.assertEqual(status, 0)
-        self.assertIn("0 patterns", stderr)
-        self.assertIn("0 annotations", stderr)
+        self.assertEqual(self.__run_build()[0], 0)
         self.assertEqual(self.__stored_patterns(), {})
         self.assertEqual(self.__stored_annotations(), {})
 

tools/tests/test_fetch_artists.py

@@ -51,10 +51,12 @@ class TestFetchArtists(unittest.TestCase):
         self.addCleanup(self.__ds.engine.dispose)
         patchers: list[Any] = [
             mock.patch.object(fetch_artists, "ds", self.__ds),
-            mock.patch.object(fetch_artists, "SLEEP_SECONDS",
-                              0.0),
-            mock.patch.object(fetch_artists, "RETRY_SECONDS",
-                              0.0)]
+            mock.patch.object(
+                fetch_artists.ArtistFetcher,
+                "_ArtistFetcher__SLEEP_SECONDS", 0.0),
+            mock.patch.object(
+                fetch_artists.ArtistFetcher,
+                "_ArtistFetcher__RETRY_SECONDS", 0.0)]
         for patcher in patchers:
             patcher.start()
             self.addCleanup(patcher.stop)
@@ -315,10 +317,12 @@ class TestFetchArtists(unittest.TestCase):
         self.assertEqual(status, 0)
         self.assertEqual(urlopen.call_count, 3)
         first: Any = urlopen.call_args_list[0][0][0]
-        self.assertEqual(first.get_header("User-agent"),
-                         fetch_artists.USER_AGENT)
-        self.assertTrue(
-            first.full_url.startswith(fetch_artists.SPARQL_URL))
+        self.assertEqual(
+            first.get_header("User-agent"),
+            fetch_artists.ArtistFetcher._ArtistFetcher__USER_AGENT)
+        self.assertTrue(first.full_url.startswith(
+            fetch_artists.ArtistFetcher
+            ._ArtistFetcher__SPARQL_URL))
         self.assertEqual(
             first.get_header("Accept"),
             "application/sparql-results+json")
@@ -358,7 +362,8 @@ class TestFetchArtists(unittest.TestCase):
             qid, {}, "a brand the type gate excludes")
         urlopen: mock.Mock
         with mock.patch.object(
-                fetch_artists, "PINNED_QIDS",
+                fetch_artists.ArtistFetcher,
+                "_ArtistFetcher__PINNED_QIDS",
                 {"Brandy Brand": qid}), \
                 mock.patch(
                     "urllib.request.urlopen",
@@ -369,7 +374,7 @@ class TestFetchArtists(unittest.TestCase):
         self.assertEqual(urlopen.call_count, 1)
         first: Any = urlopen.call_args_list[0][0][0]
         self.assertTrue(first.full_url.startswith(
-            fetch_artists.API_URL))
+            fetch_artists.ArtistFetcher._ArtistFetcher__API_URL))
         rows: list[list[str]] = self.__read_rows(
             self.__snapshot)
         self.assertEqual(rows[1], [
@@ -886,7 +891,8 @@ class TestFetchArtists(unittest.TestCase):
                 "urllib.request.urlopen",
                 side_effect=[self.__response(empty)]) as urlopen,
               mock.patch.object(
-                  fetch_artists, "read_artist_titles",
+                  fetch_artists.ArtistSnapshotUpdater,
+                  "_ArtistSnapshotUpdater__read_artist_titles",
                   side_effect=[[], OSError("boom")])):
             status: int = self.__run_fetch()[0]
         self.assertNotEqual(status, 0)

tools/tests/test_fetch_lyrics.py

@@ -50,7 +50,9 @@ class TestFetchLyrics(unittest.TestCase):
         self.addCleanup(self.__ds.engine.dispose)
         patchers: list[Any] = [
             mock.patch.object(fetch_lyrics, "ds", self.__ds),
-            mock.patch.object(fetch_lyrics, "SLEEP_SECONDS", 0.0)]
+            mock.patch.object(
+                fetch_lyrics.LyricsFetcher,
+                "_LyricsFetcher__SLEEP_SECONDS", 0.0)]
         for patcher in patchers:
             patcher.start()
             self.addCleanup(patcher.stop)
@@ -158,8 +160,9 @@ class TestFetchLyrics(unittest.TestCase):
         self.assertEqual(status, 0)
         self.assertEqual(urlopen.call_count, 1)
         request: Any = urlopen.call_args[0][0]
-        self.assertEqual(request.get_header("User-agent"),
-                         fetch_lyrics.USER_AGENT)
+        self.assertEqual(
+            request.get_header("User-agent"),
+            fetch_lyrics.LyricsFetcher._LyricsFetcher__USER_AGENT)
         self.assertEqual(
             (self.__lyrics / "1.txt")
             .read_text(encoding="utf-8"),
@@ -321,39 +324,39 @@ class TestFetchLyrics(unittest.TestCase):
     def test_normalize_cp1252_mojibake(self) -> None:
         """Test that cp1252 mojibake codepoints are restored."""
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics("wait…"),
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics("wait…"),
             "wait…")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(
                 "‘quote’"),
             "‘quote’")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(
                 "“quote”"),
             "“quote”")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics("dash—line"),
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics("dash—line"),
             "dash—line")
 
     def test_normalize_undefined_cp1252_removed(self) -> None:
         """Test that undefined cp1252 byte values are removed."""
         text: str = ("abcdef")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(text), "abcdef")
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(text), "abcdef")
 
     def test_normalize_homoglyphs(self) -> None:
         """Test that watermark homoglyphs are restored."""
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics("likе that"),
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics("likе that"),
             "like that")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics("lό que soy"),
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics("lό que soy"),
             "ló que soy")
 
     def test_normalize_space_variants(self) -> None:
         """Test that exotic space variants become ASCII space."""
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(
                 "a b c d"),
             "a b c d")
 
@@ -362,19 +365,19 @@ class TestFetchLyrics(unittest.TestCase):
         text: str = (
             "a​b‌c‍de")
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(text), "abcde")
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(text), "abcde")
 
     def test_normalize_ascii_unchanged(self) -> None:
         """Test that plain ASCII text passes through unchanged."""
         text: str = "Hello, it's me\n"
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(text), text)
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(text), text)
 
     def test_normalize_legitimate_non_ascii_unchanged(self) -> None:
         """Test that legitimate non-ASCII content is unchanged."""
         text: str = "¿cómo estás? 안녕하세요\n"
         self.assertEqual(
-            fetch_lyrics.normalize_lyrics(text), text)
+            fetch_lyrics.LyricsFetchRunner.normalize_lyrics(text), text)
 
     def test_fetched_lyrics_saved_normalized(self) -> None:
         """Test that a fetched lyric is normalized before saving."""

tools/tests/test_run_llm.py

@@ -90,86 +90,113 @@ class RunLLMTestCase(unittest.TestCase):
 
 
 class TestLoadItems(RunLLMTestCase):
-    """Test cases for the input JSONL validation."""
+    """Test cases for the input JSONL validation, driven by a dry
+    run since the validation happens before any API call."""
 
     def setUp(self) -> None:
-        """Create a temporary directory for the input files."""
-        self.__dir: Path = self._make_temp_dir()
+        """Create the prompt and input paths for a dry run."""
+        directory: Path = self._make_temp_dir()
+        self.__prompt: Path = directory / "task.md"
+        self.__prompt.write_text("The task.\n", encoding="utf-8")
+        self.__input: Path = directory / "items.jsonl"
+        self.__archive_dir: Path = directory / "runs" / "run1"
 
-    def __write_input(self, content: str) -> Path:
-        """Write an input file with the given content.
+    def __run_dry(self, content: str) -> tuple[int, str]:
+        """Write the input file and dry-run against it.
 
-        :param content: The file content.
-        :return: The path of the input file.
+        :param content: The input file content.
+        :return: The exit status and the standard error text.
         """
-        path: Path = self.__dir / "items.jsonl"
-        path.write_text(content, encoding="utf-8")
-        return path
-
-    def test_valid_items(self) -> None:
-        """Test that valid items are loaded in file order."""
-        path: Path = self.__write_input(
-            '{"id": "a", "content": "one"}\n'
-            '{"id": "b", "content": "two"}\n')
-        items: list[run_llm.InputItem] = run_llm.load_items(path)
-        self.assertEqual(items, [
-            run_llm.InputItem(id="a", content="one"),
-            run_llm.InputItem(id="b", content="two")])
+        self.__input.write_text(content, encoding="utf-8")
+        stderr: io.StringIO = io.StringIO()
+        status: int
+        with redirect_stderr(stderr):
+            status = run_llm.main([
+                str(self.__prompt), str(self.__input),
+                str(self.__archive_dir), "--dry-run"])
+        return status, stderr.getvalue()
 
     def test_malformed_json_names_line(self) -> None:
         """Test that malformed JSON reports the line number."""
-        path: Path = self.__write_input(
+        status: int
+        stderr: str
+        status, stderr = self.__run_dry(
             '{"id": "a", "content": "one"}\n'
             'not json\n')
-        with self.assertRaises(run_llm.InputFormatError) as context:
-            run_llm.load_items(path)
-        self.assertIn("line 2", str(context.exception))
+        self.assertEqual(status, 1)
+        self.assertIn("line 2", stderr)
 
     def test_missing_key_names_line(self) -> None:
         """Test that a missing key reports the line number."""
-        path: Path = self.__write_input('{"id": "a"}\n')
-        with self.assertRaises(run_llm.InputFormatError) as context:
-            run_llm.load_items(path)
-        self.assertIn("line 1", str(context.exception))
+        status: int
+        stderr: str
+        status, stderr = self.__run_dry('{"id": "a"}\n')
+        self.assertEqual(status, 1)
+        self.assertIn("line 1", stderr)
 
     def test_extra_key_rejected(self) -> None:
         """Test that an extra key is rejected."""
-        path: Path = self.__write_input(
+        status: int
+        status, _ = self.__run_dry(
             '{"id": "a", "content": "one", "extra": 1}\n')
-        with self.assertRaises(run_llm.InputFormatError):
-            run_llm.load_items(path)
+        self.assertEqual(status, 1)
 
     def test_non_string_content_rejected(self) -> None:
         """Test that a non-string content is rejected."""
-        path: Path = self.__write_input('{"id": "a", "content": 3}\n')
-        with self.assertRaises(run_llm.InputFormatError):
-            run_llm.load_items(path)
+        status: int
+        status, _ = self.__run_dry('{"id": "a", "content": 3}\n')
+        self.assertEqual(status, 1)
 
     def test_duplicated_id_names_line(self) -> None:
         """Test that a duplicated ID reports the line number."""
-        path: Path = self.__write_input(
+        status: int
+        stderr: str
+        status, stderr = self.__run_dry(
             '{"id": "a", "content": "one"}\n'
             '{"id": "a", "content": "two"}\n')
-        with self.assertRaises(run_llm.InputFormatError) as context:
-            run_llm.load_items(path)
-        self.assertIn("line 2", str(context.exception))
-        self.assertIn("a", str(context.exception))
+        self.assertEqual(status, 1)
+        self.assertIn("line 2", stderr)
+        self.assertIn("a", stderr)
 
     def test_empty_file_rejected(self) -> None:
         """Test that an empty input file is rejected."""
-        path: Path = self.__write_input("")
-        with self.assertRaises(run_llm.InputFormatError):
-            run_llm.load_items(path)
+        status: int
+        status, _ = self.__run_dry("")
+        self.assertEqual(status, 1)
+        self.assertFalse(self.__archive_dir.exists())
 
 
 class TestRequestBuilding(RunLLMTestCase):
-    """Test cases for the request construction."""
+    """Test cases for the request preview, driven by a dry run."""
 
-    def test_build_request(self) -> None:
-        """Test the shape of a batch request."""
-        request: dict[str, Any] = run_llm.build_request(
-            run_llm.InputItem(id="song-1", content="the lyrics"),
-            "the system prompt", 2048, "claude-sonnet-4-6")
+    def setUp(self) -> None:
+        """Create the prompt and input files for a dry run."""
+        directory: Path = self._make_temp_dir()
+        self.__prompt: Path = directory / "task.md"
+        self.__prompt.write_text(
+            "the system prompt", encoding="utf-8")
+        self.__input: Path = directory / "items.jsonl"
+        self.__input.write_text(
+            '{"id": "song-1", "content": "the lyrics"}\n',
+            encoding="utf-8")
+        self.__archive_dir: Path = directory / "runs" / "run1"
+
+    def __preview(self, extra_argv: list[str]) -> dict[str, Any]:
+        """Dry-run and parse the previewed request.
+
+        :param extra_argv: The extra command-line arguments.
+        :return: The parsed request.
+        """
+        stdout: io.StringIO = io.StringIO()
+        with redirect_stdout(stdout):
+            run_llm.main([
+                str(self.__prompt), str(self.__input),
+                str(self.__archive_dir), "--dry-run"] + extra_argv)
+        return json.loads(stdout.getvalue())
+
+    def test_default_model_request(self) -> None:
+        """Test the request shape for the default model."""
+        request: dict[str, Any] = self.__preview([])
         self.assertEqual(request["custom_id"], "song-1")
         params: dict[str, Any] = request["params"]
         self.assertEqual(params["model"], "claude-sonnet-4-6")
@@ -177,125 +204,19 @@ class TestRequestBuilding(RunLLMTestCase):
         self.assertEqual(params["thinking"], {"type": "disabled"})
         self.assertEqual(params["max_tokens"], 2048)
         self.assertEqual(params["system"], "the system prompt")
-        self.assertEqual(params["messages"],
-                         [{"role": "user", "content": "the lyrics"}])
+        self.assertEqual(
+            params["messages"],
+            [{"role": "user", "content": "the lyrics"}])
 
-    def test_build_request_fable_5(self) -> None:
+    def test_fable_5_request(self) -> None:
         """Test the request shape for the claude-fable-5 model."""
-        request: dict[str, Any] = run_llm.build_request(
-            run_llm.InputItem(id="group-1", content="the groups"),
-            "the system prompt", 8192, "claude-fable-5")
+        request: dict[str, Any] = self.__preview(
+            ["--model", "claude-fable-5", "--max-tokens", "8192"])
         params: dict[str, Any] = request["params"]
         self.assertEqual(params["model"], "claude-fable-5")
         self.assertNotIn("temperature", params)
         self.assertNotIn("thinking", params)
         self.assertEqual(params["max_tokens"], 8192)
-        self.assertEqual(params["system"], "the system prompt")
-        self.assertEqual(params["messages"],
-                         [{"role": "user", "content": "the groups"}])
-
-
-class TestCollectResults(RunLLMTestCase):
-    """Test cases for the batch result collection."""
-
-    def test_collect_success_and_error(self) -> None:
-        """Test collecting succeeded and errored results."""
-        client: mock.Mock = mock.Mock()
-        client.messages.batches.results.return_value = iter([
-            self._make_success_entry("a", "output a"),
-            self._make_error_entry("b", "invalid_request_error")])
-        results: run_llm.Results = run_llm.collect_results(
-            client, "batch_x")
-        self.assertEqual(results["a"].text, "output a")
-        self.assertEqual(results["a"].stop_reason, "end_turn")
-        self.assertEqual(results["a"].usage,
-                         {"input_tokens": 10, "output_tokens": 5})
-        self.assertEqual(results["b"], run_llm.BatchResult(
-            id="b", error="invalid_request_error"))
-        client.messages.batches.results.assert_called_once_with(
-            "batch_x")
-
-    def test_find_failures(self) -> None:
-        """Test finding failed and missing items."""
-        results: run_llm.Results = {
-            "a": run_llm.BatchResult(id="a", text="fine"),
-            "b": run_llm.BatchResult(id="b", error="errored")}
-        self.assertEqual(
-            run_llm.find_failures(["a", "b", "c"], results),
-            ["b", "c"])
-
-    def test_sum_usage(self) -> None:
-        """Test summing the token usage across results."""
-        results: run_llm.Results = {
-            "a": run_llm.BatchResult(
-                id="a", text="fine",
-                usage={"input_tokens": 10, "output_tokens": 5}),
-            "b": run_llm.BatchResult(
-                id="b", text="fine",
-                usage={"input_tokens": 3, "output_tokens": 2}),
-            "c": run_llm.BatchResult(id="c", error="errored")}
-        self.assertEqual(
-            run_llm.sum_usage(results),
-            {"input_tokens": 13, "output_tokens": 7})
-
-
-class TestArchive(RunLLMTestCase):
-    """Test cases for the archive directory handling."""
-
-    def setUp(self) -> None:
-        """Create a temporary directory as the runs root."""
-        self.__dir: Path = self._make_temp_dir()
-
-    def test_create_archive_dir(self) -> None:
-        """Test the archive directory creation."""
-        target: Path = self.__dir / "01-01-tag" / "run1"
-        directory: Path = run_llm.create_archive_dir(target, False)
-        self.assertTrue(directory.is_dir())
-        self.assertEqual(directory, target)
-
-    def test_existing_archive_dir_rejected_without_replace(
-            self) -> None:
-        """Test that an existing archive is rejected by default."""
-        target: Path = self.__dir / "01-01-tag" / "run1"
-        run_llm.create_archive_dir(target, False)
-        with self.assertRaises(FileExistsError):
-            run_llm.create_archive_dir(target, False)
-
-    def test_existing_archive_dir_replaced(self) -> None:
-        """Test that --replace replaces an existing archive."""
-        target: Path = self.__dir / "01-01-tag" / "run1"
-        first: Path = run_llm.create_archive_dir(target, False)
-        (first / "stale.txt").write_text("stale", encoding="utf-8")
-        second: Path = run_llm.create_archive_dir(target, True)
-        self.assertEqual(first, second)
-        self.assertFalse((second / "stale.txt").exists())
-
-    def test_replace_leaves_sibling_dir_untouched(self) -> None:
-        """Test that replacing run2 does not touch run1."""
-        run1: Path = run_llm.create_archive_dir(
-            self.__dir / "01-01-tag" / "run1", False)
-        (run1 / "output.jsonl").write_text(
-            "run1 data", encoding="utf-8")
-        run2: Path = run_llm.create_archive_dir(
-            self.__dir / "01-01-tag" / "run2", False)
-        (run2 / "stale.jsonl").write_text("stale", encoding="utf-8")
-        run_llm.create_archive_dir(
-            self.__dir / "01-01-tag" / "run2", True)
-        self.assertEqual(
-            (run1 / "output.jsonl").read_text(encoding="utf-8"),
-            "run1 data")
-
-    def test_write_jsonl(self) -> None:
-        """Test writing records as JSON Lines."""
-        path: Path = self.__dir / "out.jsonl"
-        run_llm.write_jsonl(path, [{"id": "a", "text": "中文"},
-                                   {"id": "b", "text": "two"}])
-        lines: list[str] = path.read_text(
-            encoding="utf-8").splitlines()
-        self.assertEqual(len(lines), 2)
-        self.assertEqual(json.loads(lines[0]),
-                         {"id": "a", "text": "中文"})
-        self.assertIn("中文", lines[0])
 
 
 class TestMainFlow(RunLLMTestCase):
@@ -322,8 +243,7 @@ class TestMainFlow(RunLLMTestCase):
             ANTHROPIC_API_KEY="test-key")
         config.set_settings(self.__settings)
 
-    @staticmethod
-    def __make_client(entries: list[Any]) -> mock.Mock:
+    def __make_client(self, entries: list[Any]) -> mock.Mock:
         """Create a mock Anthropic client serving canned results.
 
         :param entries: The result entries of the single run batch.
@@ -386,9 +306,11 @@ class TestMainFlow(RunLLMTestCase):
             "Done.  2 jobs finished.  02:05 elapsed."))
 
     def test_run_produces_output_file(self) -> None:
-        """Test that a run submits one batch and writes output."""
+        """Test that a run submits one batch and writes output,
+        the item order preserved and the token usage summed, the
+        output text written unescaped."""
         client: mock.Mock = self.__make_client(
-            [self._make_success_entry("a", "answer a"),
+            [self._make_success_entry("a", "answer 中文 a"),
              self._make_success_entry("b", "answer b")])
         status: int
         stderr: str
@@ -400,10 +322,13 @@ class TestMainFlow(RunLLMTestCase):
             client.messages.batches.create.call_count, 1)
         run_dir: Path = self.__archive_dir
         self.assertTrue((run_dir / "output.jsonl").exists())
+        output_text: str = (run_dir / "output.jsonl").read_text(
+            encoding="utf-8")
+        self.assertIn("中文", output_text)
         output: list[dict[str, Any]] = [
-            json.loads(x) for x in (run_dir / "output.jsonl")
-            .read_text(encoding="utf-8").splitlines()]
-        self.assertEqual(output[0]["text"], "answer a")
+            json.loads(x) for x in output_text.splitlines()]
+        self.assertEqual(output[0]["text"], "answer 中文 a")
+        self.assertEqual(output[1]["text"], "answer b")
         meta: dict[str, Any] = json.loads(
             (run_dir / "meta.json").read_text(encoding="utf-8"))
         self.assertNotIn("run", meta)
@@ -465,11 +390,14 @@ class TestMainFlow(RunLLMTestCase):
             "stale run2 data")
 
     def test_run_failure_exits_non_zero(self) -> None:
-        """Test that a failed item aborts with a non-zero status."""
+        """Test that a failed item aborts with a non-zero status,
+        the summed usage counting only the succeeded item."""
         client: mock.Mock = self.__make_client(
             [self._make_success_entry("a", "answer a"),
              self._make_error_entry("b", "invalid_request_error")])
-        status: int = self.__run_main(self.__argv, client)[0]
+        status: int
+        stderr: str
+        status, _, stderr = self.__run_main(self.__argv, client)
         self.assertEqual(status, 1)
         run_dir: Path = self.__archive_dir
         self.assertTrue((run_dir / "output.jsonl").exists())
@@ -479,6 +407,22 @@ class TestMainFlow(RunLLMTestCase):
         self.assertEqual(json.loads(output_lines[1]),
                          {"id": "b",
                           "error": "invalid_request_error"})
+        meta: dict[str, Any] = json.loads(
+            (run_dir / "meta.json").read_text(encoding="utf-8"))
+        self.assertEqual(meta["usage"],
+                         {"input_tokens": 10, "output_tokens": 5})
+        self.assertNotIn("Done.", stderr)
+
+    def test_missing_result_item_is_a_failure(self) -> None:
+        """Test that an item missing from the batch results is
+        reported as a failed item."""
+        client: mock.Mock = self.__make_client(
+            [self._make_success_entry("a", "answer a")])
+        status: int
+        stderr: str
+        status, _, stderr = self.__run_main(self.__argv, client)
+        self.assertEqual(status, 1)
+        self.assertIn("b", stderr)
 
     def test_invalid_input_exits_non_zero(self) -> None:
         """Test that an invalid input file aborts before archiving."""

tools/tests/test_tally_annotations.py

@@ -11,12 +11,14 @@ import tempfile
 import unittest
 from contextlib import redirect_stderr
 from pathlib import Path
+from typing import Any
+from unittest import mock
 
-import sqlalchemy as sa
 from sqlalchemy.orm import Session
 
+from pop_fem_audit_tools import config
 from pop_fem_audit_tools.commands import tally_annotations
-from pop_fem_audit_tools.database import Base
+from pop_fem_audit_tools.database import Base, DataSource
 from pop_fem_audit_tools.models import Song
 
 
@@ -24,8 +26,8 @@ class TestTallyAnnotations(unittest.TestCase):
     """Test cases for the step-5 pattern annotation tally."""
 
     def setUp(self) -> None:
-        """Create the archive directories, the database, and the
-        output paths."""
+        """Create the archive directories, the working store, and
+        the output paths."""
         tmp: tempfile.TemporaryDirectory[str] \
             = tempfile.TemporaryDirectory()
         self.addCleanup(tmp.cleanup)
@@ -37,7 +39,6 @@ class TestTallyAnnotations(unittest.TestCase):
         self.__male_synthesis.mkdir()
         self.__female_synthesis.mkdir()
         self.__mixed_synthesis.mkdir()
-        self.__db_path: Path = self.__dir / "working.sqlite3"
         self.__patterns_csv: Path \
             = self.__dir / "results" / "patterns.csv"
         self.__annotations_csv: Path \
@@ -48,6 +49,15 @@ class TestTallyAnnotations(unittest.TestCase):
             run_dir: Path = self.__dir / f"run{number}"
             run_dir.mkdir()
             self.__runs.append(run_dir)
+        config.set_settings(config.Settings(
+            SQLALCHEMY_DATABASE_URL="sqlite://",
+            ANTHROPIC_API_KEY="test-key"))
+        self.__ds: DataSource = DataSource()
+        self.addCleanup(self.__ds.engine.dispose)
+        patcher: Any = mock.patch.object(
+            tally_annotations, "ds", self.__ds)
+        patcher.start()
+        self.addCleanup(patcher.stop)
 
     def __write_default_synthesis_archives(self) -> None:
         """Write the male, female, and mixed synthesis archives.
@@ -108,22 +118,20 @@ class TestTallyAnnotations(unittest.TestCase):
             stored performer gender of every fixture song.
         :return: None.
         """
-        engine: sa.Engine = sa.create_engine(
-            f"sqlite:///{self.__db_path}")
-        Base.metadata.create_all(engine)
-        session: Session
-        with Session(engine) as session:
+        Base.metadata.create_all(self.__ds.engine)
+        session: Session = self.__ds.get_db()
+        try:
             song_id: int
             title: str
             artist_credit: str
             gender: str | None
             for song_id, title, artist_credit, gender in songs:
                 session.add(Song(
-                    id=song_id, title=title,
-                    artist_credit=artist_credit,
+                    id=song_id, title=title, artist_credit=artist_credit,
                     performer_gender=gender))
             session.commit()
-        engine.dispose()
+        finally:
+            session.close()
 
     def __write_run(
             self, run_dir: Path,
@@ -165,11 +173,10 @@ class TestTallyAnnotations(unittest.TestCase):
         status: int
         with redirect_stderr(stderr):
             status = tally_annotations.main([
-                str(self.__male_synthesis),
-                str(self.__female_synthesis),
-                str(self.__mixed_synthesis), str(self.__db_path),
-                str(self.__patterns_csv),
-                str(self.__annotations_csv)]
+                "--female", str(self.__female_synthesis),
+                "--male", str(self.__male_synthesis),
+                "--mixed", str(self.__mixed_synthesis),
+                str(self.__patterns_csv), str(self.__annotations_csv)]
                 + [str(x) for x in self.__runs])
         return status, stderr.getvalue()
 
@@ -315,11 +322,10 @@ class TestTallyAnnotations(unittest.TestCase):
         status: int
         with redirect_stderr(stderr):
             status = tally_annotations.main([
-                str(self.__male_synthesis),
-                str(self.__female_synthesis),
-                str(self.__mixed_synthesis), str(self.__db_path),
-                str(self.__patterns_csv),
-                str(self.__annotations_csv)]
+                "--female", str(self.__female_synthesis),
+                "--male", str(self.__male_synthesis),
+                "--mixed", str(self.__mixed_synthesis),
+                str(self.__patterns_csv), str(self.__annotations_csv)]
                 + [str(x) for x in self.__runs]
                 + [str(rescue_dir)])
         self.assertEqual(status, 0)
@@ -329,6 +335,40 @@ class TestTallyAnnotations(unittest.TestCase):
             ["Song", "Artist Credit", "Pattern", "Votes"],
             ["Song A", "Artist A", "M1", "3"]])
 
+    def test_dead_record_with_empty_text_rescued_from_extra_run_dir(
+            self) -> None:
+        """Test that a dead record whose "text" is an empty
+        string (malformed JSON) in one run directory is skipped
+        with a warning, and its ballot is rescued from an extra
+        run directory, tallying successfully."""
+        self.__write_default_synthesis_archives()
+        self.__seed_songs([(1, "Song A", "Artist A", "male")])
+        self.__write_same_ballots_to_all_runs({1: ["M1"]})
+        (self.__runs[0] / "output.jsonl").write_text(
+            json.dumps({"id": "song-1", "text": ""}) + "\n",
+            encoding="utf-8")
+        rescue_dir: Path = self.__dir / "rescue"
+        rescue_dir.mkdir()
+        self.__write_run(rescue_dir, {1: ["M1"]})
+        stderr: io.StringIO = io.StringIO()
+        status: int
+        with redirect_stderr(stderr):
+            status = tally_annotations.main([
+                "--female", str(self.__female_synthesis),
+                "--male", str(self.__male_synthesis),
+                "--mixed", str(self.__mixed_synthesis),
+                str(self.__patterns_csv), str(self.__annotations_csv)]
+                + [str(x) for x in self.__runs]
+                + [str(rescue_dir)])
+        self.assertEqual(status, 0)
+        self.assertIn("warning:", stderr.getvalue())
+        self.assertIn("song-1", stderr.getvalue())
+        self.assertIn("\"text\" is malformed JSON", stderr.getvalue())
+        self.assertIn("skipped", stderr.getvalue())
+        self.assertEqual(self.__read_rows(self.__annotations_csv), [
+            ["Song", "Artist Credit", "Pattern", "Votes"],
+            ["Song A", "Artist A", "M1", "3"]])
+
     def test_unknown_pattern_id_dropped_with_warning(self) -> None:
         """Test that a selected ID outside the extracted patterns
         is dropped, the occurrence reported on standard error."""
@@ -511,7 +551,7 @@ class TestTallyAnnotations(unittest.TestCase):
 
     def test_summary_line_reports_counts(self) -> None:
         """Test that the closing summary reports the settled
-        pair, song, and dropped vote counts."""
+        annotation count."""
         self.__write_default_synthesis_archives()
         self.__seed_songs([(1, "Song A", "Artist A", "male")])
         self.__write_same_ballots_to_all_runs(
@@ -520,6 +560,4 @@ class TestTallyAnnotations(unittest.TestCase):
         stderr: str
         status, stderr = self.__run_tally()
         self.assertEqual(status, 0)
-        self.assertIn("Tallied 1 settled pairs across 1 songs",
-                      stderr)
-        self.assertIn("3 votes dropped", stderr)
+        self.assertIn("Tallied 1 annotations.", stderr)