feat: source citations with footnotes in the transcript (#21)

src/lib/render.ts

@@ -1,6 +1,8 @@
+import { linkCitations } from "./citations";
 import { CLOSING_FENCE, OPENING_FENCE, mapOutsideCodeSpans, readCodeSpan, repairCodeBlocks } from "./code";
 import { sanitizeInlineHtml } from "./html";
 import { looksLikeMath, renderLatex } from "./latex";
+import type { Source } from "./types";
 
 /**
  * The rendering pass for model output.
@@ -490,6 +492,30 @@ export function renderInlineContent(markdown: string): string {
   return flatten(htmlPass(mathPass(splitSegments(markdown))));
 }
 
+/** What the pane will draw, and what the answer cited so the list can filter. */
+export interface RenderedMarkdown {
+  text: string;
+  /**
+   * The numbers this answer cited that became links.
+   *
+   * Reported rather than worked out again by the caller: the pass already had to
+   * decide which markers were real and which were inside code, and a second reader
+   * of the same text could only disagree with it.
+   */
+  cited: Set<number>;
+}
+
+/** Optional input to the pass. */
+export interface RenderOptions {
+  /**
+   * The turn's sources, so a marker can become a link to the page it names.
+   *
+   * Absent for a question, and absent for an answer in a turn that consulted
+   * nothing, in which case the citation pass is the identity function.
+   */
+  sources?: Source[];
+}
+
 /**
  * The full rendering pass, from what the model wrote to what the pane draws.
  *
@@ -497,6 +523,28 @@ export function renderInlineContent(markdown: string): string {
  * markdown around each message (a blockquote for a question, a rule between
  * exchanges) and none of that should be read as model output.
  */
-export function renderModelOutput(markdown: string): string {
-  return renderInlineContent(repairCodeBlocks(markdown));
+export function renderModelOutput(markdown: string, options: RenderOptions = {}): RenderedMarkdown {
+  const sources = options.sources ?? [];
+  const cited = new Set<number>();
+
+  /**
+   * Maths first, then citations, then markup.
+   *
+   * The order is forced by one collision. A link label has to escape its brackets
+   * or the parser ends the link text early, and `[\[1\]]` is exactly the shape of
+   * LaTeX's own `\[...\]` display delimiter, which the maths pass would eat and
+   * hand back as a bare `1`. So the model's maths is converted before any marker
+   * becomes a link: the citation pass writes final form markdown, which is not
+   * input for anything but the markup pass, and that one only reads angle brackets.
+   */
+  const segments = mathPass(splitSegments(repairCodeBlocks(markdown))).map((segment) => {
+    if (segment.fence || sources.length === 0) return segment;
+
+    const result = linkCitations(segment.lines.join("\n"), sources);
+    for (const index of result.cited) cited.add(index);
+
+    return { fence: false, language: "", lines: result.text.split("\n") };
+  });
+
+  return { text: flatten(htmlPass(segments)), cited };
 }