paperlint 2.1.0 → 3.1.0

package/eslint-rules/paper-stages.harness.mjs

@@ -45,7 +45,7 @@ const since = () => {
 
 assert.deepEqual(
   Object.keys(stages.rules).sort(),
-  ["author-list", "source", "stages"],
+  ["source", "stages"],
   "rule set changed",
 );
 
@@ -237,120 +237,4 @@ console.log(
   `✓ ${String(since())} assertions passed — paper/source, frozen bytes instead of a sha`,
 );
 
-// ── `paper/author-list`: a shipped paper owes itself a run of the author-list cross-check ────
-//
-// This rule's subject is DIFFERENT from its two neighbors above: those check the declaration
-// against the bytes, this one checks the declaration against a record of a run. What they share
-// is exactly one input, the `stages` field, and that's why the rule lives in this module.
-{
-  const lintAuthors = (name, opts = {}) => {
-    const file = join(FIX, name, "PIPELINE-STATUS.md");
-    const msgs = linter.verify(
-      readFileSync(file, "utf-8"),
-      [
-        {
-          files: ["**/*.md"],
-          plugins: { markdown, paper: stages },
-          language: "markdown/gfm",
-          languageOptions: { frontmatter: "yaml" },
-          rules: { "paper/author-list": ["error", opts] },
-        },
-      ],
-      file,
-    );
-    assert.deepEqual(
-      msgs.filter((m) => m.fatal),
-      [],
-      `${name}: the rule threw`,
-    );
-    return msgs.map((m) => m.message);
-  };
-
-  // ── stays silent where it must ──
-  check(
-    "a run is recorded in the scorecard — silent",
-    lintAuthors("authors-ran").length === 0,
-  );
-  // A draft never asked anyone to read it, so it owes nothing. This is not a carve-out: the
-  // rule's subject is the DEBT of a shipped paper, and an unshipped one has no debt.
-  check(
-    "no stage declared at all — silent, a draft owes nothing",
-    lintAuthors("nothing").length === 0,
-  );
-  // An empty list is not "a stage exists": the record `stages: []` shows up on a paper that was
-  // set up but never submitted anywhere.
-  check(
-    "an empty stage list — silent",
-    linter.verify(
-      "---\nstages: []\n---\n# S\n",
-      [
-        {
-          files: ["**/*.md"],
-          plugins: { markdown, paper: stages },
-          language: "markdown/gfm",
-          languageOptions: { frontmatter: "yaml" },
-          rules: { "paper/author-list": "error" },
-        },
-      ],
-      join(FIX, "x", "PIPELINE-STATUS.md"),
-    ).length === 0,
-  );
-
-  // ── fires on a planted defect ──
-  const owed = lintAuthors("ok");
-  check("a stage is declared, no run — a finding", owed.length === 1);
-  // 🔴 The message must name the CLASS, not just the fact of a miss: otherwise the reader takes
-  // it for a duplicate of the citation-existence check and closes it as noise. The class is
-  // preprint authors under a declared conference, and it is invisible to a check that a
-  // citation merely resolves.
-  check(
-    "and it names the class the cross-check catches, not just the miss",
-    /PREPRINT/.test(owed[0]),
-  );
-
-  // ── the whole reason the move was made ──
-  // The predecessor derived the stage with a REGEX OVER THE SCORECARD'S PROSE. Remeasured
-  // 09-17: for `agenticdev-2026` the prose reads `submitted`, while the frontmatter reads
-  // `submitted, camera-ready`. Here the list comes from the field, so both stages land in the
-  // finding's text.
-  const two = lintAuthors("twice");
-  check(
-    "the stage list in the message comes from the FIELD and carries all of them",
-    two.length === 1 && /submitted\/submitted/.test(two[0]),
-  );
-
-  // ── consumer data stays with the consumer ──
-  // The predecessor hardcoded the path `.claude/skills/verify-citations/...` into the message
-  // text — the address of ONE repository inside a public package.
-  const withCmd = lintAuthors("ok", {
-    command: "node scripts/bib-authors.mjs <paper>",
-  });
-  check(
-    "the run command comes in as an option and lands in the message",
-    /scripts\/bib-authors\.mjs/.test(withCmd[0]),
-  );
-  check(
-    "and without the option the message does not invent a path",
-    !/bib-authors\.mjs/.test(owed[0]),
-  );
-  // The marker is also data: the package cannot know EXACTLY how a given consumer records a run.
-  check(
-    "the marker is configurable — with a different marker the same paper becomes a debtor",
-    lintAuthors("authors-ran", { marker: "no-such-marker" }).length === 1,
-  );
-
-  // ── parsing versus grep: the one case where they diverge ──
-  // 🔴 This assert is the proof of the move to a parser. All the fixtures above pass IDENTICALLY
-  // either way, because their marker sits in a cell. Here it sits in PROSE — "still need to run
-  // bib-authors", an intention, not a record — and grep would read it as evidence of a run. The
-  // evidence must sit in the scorecard.
-  check(
-    "a marker in prose OUTSIDE the table is not a record of a run",
-    lintAuthors("marker-in-prose").length === 1,
-  );
-}
-console.log(
-  `✓ ${String(since())} assertions passed — paper/author-list, the debt of a shipped paper`,
-);
-
 console.log(`✓ ${String(n)} assertions passed in total`);

package/eslint-rules/paper-stages.mjs

@@ -254,126 +254,6 @@ export default {
      * because a stage frozen BEFORE this convention existed cannot be fixed at all — those
      * bytes are gone. Failing a build over unrecoverable history is a gate nobody can clear.
      */
-    /**
-     * `paper/author-list` — a shipped paper OWES ITSELF a run of the author-list cross-check.
-     *
-     * The class this cross-check catches is invisible to an existence check on citations: the
-     * citation exists, the identifier resolves, and the authors are taken from the PREPRINT
-     * while the entry declares a conference. On the live corpus this turned up seven records
-     * across three papers, including a DROPPED LIVING PERSON (`schick2023toolformer` — Eric
-     * Hambro is missing; the NeurIPS version has nine authors, the preprint has eight). Two of
-     * the seven were found on a paper ALREADY SUBMITTED.
-     *
-     * 🔴 WHAT THE MOVE FIXED, and this is a measurement, not taste. The predecessor derived the
-     * declared stage with a REGEX OVER THE PROSE of that same file. Remeasured 2026-09-17 on the
-     * live corpus: for `agenticdev-2026` the prose reads `submitted`, the frontmatter declares
-     * `submitted, camera-ready` — the pattern `/camera-ready (?:uploaded|submitted|shipped)/i`
-     * does not catch the form the stage is actually recorded in. Today's set of findings did not
-     * change from this (both checks only asked "is there ANY stage at all"), but the MESSAGE
-     * printed the wrong list of stages. The subject here is the same `stages` field that
-     * `paper/stages` already checks against the bytes in both directions.
-     *
-     * 🔴 THE MARKER IS LOOKED FOR IN TABLE CELLS, NOT GREPPED OVER THE FILE. The first draft did
-     * `context.sourceCode.text.includes(marker)` and justified it with a comment saying "a
-     * footnote cell has no node of its own". That turned out to be SIMPLY WRONG — a 2026-09-17
-     * measurement showed the markdown parser hands back `table`, `tableRow` and `tableCell`
-     * (twelve cells on a three-row table). The base rule says, word for word, "parse markdown
-     * with a parser".
-     *
-     * Parsing is also STRICTER than grep, and the difference is real: a marker mentioned in
-     * prose outside the scorecard — in a heading, in a paragraph saying "still need to run
-     * bib-authors", in a quote from someone else — no longer counts as a record of a run. To
-     * grep, those three cases are indistinguishable from a genuine record.
-     *
-     * ⚠️ WHAT THIS STILL DOES NOT FIX: inside the cell the evidence is still PROSE, and a run
-     * phrased in different words will not be seen by the rule. The real fix is a frontmatter
-     * field (`gates.cites.ran`), not a smarter text search; that's separate work, touching four
-     * live scorecards.
-     *
-     * So severity is set by the CONSUMER, and the default is not `error`: the proof of a run is
-     * prose, and a false positive at a blocking level costs more than a miss.
-     */
-    "author-list": {
-      meta: {
-        type: "suggestion",
-        docs: {
-          description:
-            "a paper that declares a stage records that the author-list check ran — a class the existence check cannot see",
-        },
-        schema: [
-          {
-            type: "object",
-            properties: {
-              // The run marker in the scorecard. This is consumer data: the package cannot
-              // know EXACTLY how a given consumer records that the cross-check happened.
-              marker: { type: "string" },
-              // What to run. This is a CONSUMER-SPECIFIC PATH, and it has no place in a public
-              // package: the predecessor hardcoded
-              // `.claude/skills/verify-citations/scripts/bib-authors.mjs` right into the message text.
-              command: { type: "string" },
-            },
-            additionalProperties: false,
-          },
-        ],
-        messages: {
-          neverRan:
-            "stage «{{stages}}» is declared, but the scorecard records no author-list run (looked for «{{marker}}» in its table). It catches what an existence check cannot see: the citation resolves, the id resolves, and the authors are the PREPRINT's while the entry declares a conference{{how}}",
-        },
-      },
-      create(context) {
-        const opts = context.options?.[0] ?? {};
-        const marker = opts.marker ?? "bib-authors";
-        const command = opts.command ?? "";
-
-        // The verdict is deferred to the end of the file: the frontmatter node arrives FIRST,
-        // and the table comes after it. Reporting on `yaml` would mean a verdict rendered
-        // without ever seeing the scorecard.
-        let declaredAt = null;
-        let stages = [];
-        let recorded = false;
-
-        return {
-          yaml(node) {
-            let data;
-            try {
-              data = load(node.value ?? "");
-            } catch {
-              return; // `paper/stages` has already reported the unreadable YAML
-            }
-            const raw = data?.stages;
-            if (!Array.isArray(raw)) return;
-            stages = raw.map((r) => r?.stage).filter(Boolean);
-            // One guard, not two: `raw.length === 0` would be a SPECIAL CASE of this same
-            // condition, and a mutation against it would turn out unkillable — the second guard
-            // mutes it. This also covers a non-empty list made of records with no `stage` field.
-            if (stages.length === 0) return; // nothing shipped — nothing is owed
-            declaredAt = node;
-          },
-
-          // The evidence is a SCORECARD CELL, not any occurrence of the string in the file. It
-          // has a node of its own; the first draft claimed otherwise and grepped the whole text.
-          tableCell(node) {
-            if (recorded) return;
-            if (context.sourceCode.getText(node).includes(marker))
-              recorded = true;
-          },
-
-          "root:exit"() {
-            if (!declaredAt || recorded) return;
-            context.report({
-              node: declaredAt,
-              messageId: "neverRan",
-              data: {
-                stages: stages.join("/"),
-                marker,
-                how: command ? `. Run: ${command}` : "",
-              },
-            });
-          },
-        };
-      },
-    },
-
     source: {
       meta: {
         type: "problem",

package/eslint-rules/paper-stages.mutations.mjs

@@ -76,82 +76,6 @@ process.exit(
           ],
         ],
       },
-      {
-        // 🔴 A REGRESSION BACK TO GREP. The rule's first draft did exactly this and justified it
-        // by saying "a footnote cell has no node of its own" — a measurement showed the
-        // opposite: the parser hands back `tableCell`. The mutation is caught by ONE fixture out
-        // of six: in the rest the marker already sits in a cell, so grep and parsing are
-        // indistinguishable. Without `marker-in-prose` this regression would have passed
-        // silently, and the rule would again read an intention as a fact.
-        name: "the evidence is grepped over the WHOLE FILE again",
-        harness: HARNESS,
-        expect: "a marker in prose OUTSIDE the table is not a record of a run",
-        disables:
-          "parsing in favor of a string search: 'still need to run bib-authors' — an intention, " +
-          "not a record — counts as a run again, and the paper silently stops being a debtor",
-        edits: [
-          [
-            RULE,
-            "if (context.sourceCode.getText(node).includes(marker))\n              recorded = true;",
-            "if (context.sourceCode.text.includes(marker))\n              recorded = true;",
-          ],
-        ],
-      },
-      {
-        name: "the rule stops requiring an author cross-check run",
-        harness: HARNESS,
-        expect: "a stage is declared, no run — a finding",
-        disables:
-          "the debt itself: a shipped paper no longer owes anything, and the rule stays silent " +
-          "across the whole corpus — silence is its success state, so from the outside this is " +
-          "indistinguishable",
-        // Target retargeted 09-17: the old line disappeared when the rule moved to parsing, and
-        // the driver honestly said UNUSABLE — "the patch did not land", not "the test is weak".
-        // Now the mutation declares the run recorded before the file is even read.
-        edits: [[RULE, "let recorded = false;", "let recorded = true;"]],
-      },
-      {
-        name: "the exemption for an unshipped paper becomes WIDER than it should",
-        harness: HARNESS,
-        expect: "an empty stage list — silent",
-        disables:
-          "the distinction between 'no stages' and 'there are stages': a draft starts getting a " +
-          "finding, and a rule that scolds drafts gets turned off within a week",
-        edits: [
-          [
-            RULE,
-            "if (stages.length === 0) return; // nothing shipped — nothing is owed",
-            "",
-          ],
-        ],
-      },
-      {
-        name: "the stage list is taken from somewhere OTHER than the field again",
-        harness: HARNESS,
-        expect:
-          "the stage list in the message comes from the FIELD and carries all of them",
-        disables:
-          "the exact reason the move was made. The predecessor derived the stage with a regex " +
-          "over the prose, and on agenticdev printed `submitted` where `submitted, " +
-          "camera-ready` was declared. The mutation brings back a hardcoded list — the set of " +
-          "findings does not change, only the TEXT lies, and without this assert the regression " +
-          "would have passed silently",
-        edits: [[RULE, 'stages: stages.join("/"),', 'stages: "submitted",']],
-      },
-      {
-        name: "a consumer-specific path comes back into the package's text",
-        harness: HARNESS,
-        expect:
-          "the run command comes in as an option and lands in the message",
-        disables:
-          "the boundary 'the mechanism goes in the package, the data stays with the consumer': " +
-          "the command stops arriving as an option. The predecessor hardcoded " +
-          "`.claude/skills/verify-citations/...` — the path of one private repository — right " +
-          "into a public rule's message",
-        edits: [
-          [RULE, 'const command = opts.command ?? "";', 'const command = "";'],
-        ],
-      },
     ],
   }),
 );