@fbraza/pi-cite 0.1.0 → 0.3.0

package/src/literature-search.ts

@@ -7,7 +7,6 @@ import {
   type LiteratureSearchDisplayEvent,
   type LiteratureSearchDisplaySearch,
 } from "./rendering.ts";
-import { searchSemanticScholar } from "./semantic-scholar.ts";
 import { formatPaperText, normalizeDoi, unique } from "./shared.ts";
 import { emitProgress, textResult, type TextToolUpdate } from "./tool-output.ts";
 import type { PaperRecord } from "./types.ts";
@@ -17,12 +16,6 @@ export const LITERATURE_SEARCH_PARAMS = Type.Object({
     description:
       "PubMed-ready query using PubMed syntax such as MeSH [mh], title/abstract [tiab], publication type [pt], substance [nm], and Boolean logic.",
   }),
-  semantic_scholar_query: Type.Optional(
-    Type.String({
-      description:
-        "Optional natural-language Semantic Scholar query for supplementary search. If omitted and Semantic Scholar is configured, a simplified query is derived from pubmed_query.",
-    }),
-  ),
   max_results: Type.Optional(
     Type.Number({ description: "Maximum results per provider (default 20)" }),
   ),
@@ -51,27 +44,11 @@ export type LiteratureSearchResult = {
   papers: PaperRecord[];
   providers: {
     pubmed: ProviderExecution;
-    semantic_scholar: ProviderExecution;
   };
   searches: LiteratureSearchDisplaySearch[];
   events: LiteratureSearchDisplayEvent[];
 };
 
-function firstYear(value?: string): number | undefined {
-  const match = value?.match(/^(\d{4})/);
-  return match?.[1] ? Number(match[1]) : undefined;
-}
-
-export function simplifyPubmedQueryForSemanticScholar(query: string): string {
-  const simplified = query
-    .replace(/\[[^\]]+\]/g, " ")
-    .replace(/\b(?:AND|OR|NOT)\b/gi, " ")
-    .replace(/[()"']/g, " ")
-    .replace(/\s+/g, " ")
-    .trim();
-  return simplified || query.trim();
-}
-
 function sourceList(paper: PaperRecord): string[] {
   return unique([
     ...(paper.sources ?? []),
@@ -92,7 +69,6 @@ function dedupeKeys(paper: PaperRecord): string[] {
   const keys = [
     doi ? `doi:${doi}` : undefined,
     paper.pmid ? `pmid:${paper.pmid}` : undefined,
-    paper.s2_id ? `s2:${paper.s2_id}` : undefined,
   ];
   const title = normalizedTitle(paper.title);
   if (title && paper.year) keys.push(`title-year:${title}:${paper.year}`);
@@ -106,7 +82,6 @@ function mergePapers(existing: PaperRecord, incoming: PaperRecord): PaperRecord
     ...existing,
     doi: normalizeDoi(existing.doi) ?? normalizeDoi(incoming.doi),
     pmid: existing.pmid ?? incoming.pmid,
-    s2_id: existing.s2_id ?? incoming.s2_id,
     title: existing.title !== "Untitled" ? existing.title : incoming.title,
     abstract: existing.abstract ?? incoming.abstract,
     authors: unique([...(existing.authors ?? []), ...(incoming.authors ?? [])]),
@@ -117,10 +92,6 @@ function mergePapers(existing: PaperRecord, incoming: PaperRecord): PaperRecord
       ...(incoming.publication_types ?? []),
     ]),
     mesh_terms: unique([...(existing.mesh_terms ?? []), ...(incoming.mesh_terms ?? [])]),
-    citation_count: existing.citation_count ?? incoming.citation_count,
-    tldr: existing.tldr ?? incoming.tldr,
-    open_access_pdf: existing.open_access_pdf ?? incoming.open_access_pdf,
-    external_ids: { ...(incoming.external_ids ?? {}), ...(existing.external_ids ?? {}) },
     source: sources.join(";"),
     sources,
   };
@@ -208,88 +179,10 @@ export async function searchLiterature(
   });
   emitEvent(`PubMed q1 found ${pubmed.count} candidate papers.`);
 
-  const semanticScholarApiKey = process.env.SEMANTIC_SCHOLAR_API_KEY?.trim();
-  let semanticScholar: ProviderExecution = {
-    searched: false,
-    reason: "SEMANTIC_SCHOLAR_API_KEY not configured",
-  };
-  let semanticScholarPapers: PaperRecord[] = [];
-
-  if (semanticScholarApiKey) {
-    const semanticScholarQuery =
-      params.semantic_scholar_query?.trim() ||
-      simplifyPubmedQueryForSemanticScholar(params.pubmed_query);
-
-    events.push({
-      phase: "query_start",
-      provider: "semantic_scholar",
-      query_index: 1,
-      query: semanticScholarQuery,
-    });
-    emitEvent(`Searching Semantic Scholar q1: ${semanticScholarQuery}`);
-
-    try {
-      const semanticScholarResult = await searchSemanticScholar(
-        {
-          query: semanticScholarQuery,
-          max_results: Math.min(100, maxResults),
-          year_from: firstYear(params.date_from),
-          year_to: firstYear(params.date_to),
-        },
-        signal,
-        undefined,
-      );
-      semanticScholarPapers = semanticScholarResult.papers;
-      const semanticScholarDisplayPapers = compactPapersForDisplay(
-        semanticScholarResult.papers,
-      );
-      searches.push({
-        provider: "semantic_scholar",
-        query_index: 1,
-        query: semanticScholarQuery,
-        count: semanticScholarResult.count,
-        papers: semanticScholarDisplayPapers,
-      });
-      events.push({
-        phase: "query_results",
-        provider: "semantic_scholar",
-        query_index: 1,
-        query: semanticScholarQuery,
-        count: semanticScholarResult.count,
-        papers: semanticScholarDisplayPapers,
-      });
-      emitEvent(
-        `Semantic Scholar q1 found ${semanticScholarResult.count} candidate papers.`,
-      );
-      semanticScholar = {
-        searched: true,
-        count: semanticScholarResult.count,
-        query: semanticScholarQuery,
-      };
-    } catch (err) {
-      const message = err instanceof Error ? err.message : String(err);
-      events.push({
-        phase: "query_error",
-        provider: "semantic_scholar",
-        query_index: 1,
-        query: semanticScholarQuery,
-        error: message,
-      });
-      semanticScholar = {
-        searched: false,
-        reason: `Semantic Scholar search failed: ${message}`,
-      };
-      emitEvent(`Semantic Scholar q1 failed: ${message}`);
-    }
-  }
-
   events.push({ phase: "dedupe" });
   emitEvent("Deduplicating literature results...");
 
-  const papers = dedupeLiteraturePapers([
-    ...pubmed.papers,
-    ...semanticScholarPapers,
-  ]);
+  const papers = dedupeLiteraturePapers(pubmed.papers);
   events.push({
     phase: "complete",
     count: papers.length,
@@ -307,7 +200,6 @@ export async function searchLiterature(
         query: pubmed.query ?? params.pubmed_query,
         total: pubmed.total,
       },
-      semantic_scholar: semanticScholar,
     },
     searches,
     events,
@@ -319,7 +211,7 @@ export function createLiteratureSearchTool() {
     name: "literature_search",
     label: "Literature Search",
     description:
-      "Run the literature workflow search: PubMed is always searched first with a PubMed-ready query; Semantic Scholar is searched as supplementary metadata when SEMANTIC_SCHOLAR_API_KEY is configured.",
+      "Run the literature workflow search against PubMed using a PubMed-ready query (MeSH [mh], title/abstract [tiab], publication type [pt], substance [nm], and Boolean logic).",
     parameters: LITERATURE_SEARCH_PARAMS,
     async execute(
       _toolCallId: string,

package/src/rendering.ts

@@ -16,20 +16,19 @@ export type CompactPaperForDisplay = {
   source: string;
   year?: number;
   journal?: string;
-  citation_count?: number;
 };
 
 export type LiteratureSearchDisplayEvent =
   | { phase: "start" }
   | {
       phase: "query_start";
-      provider: "pubmed" | "semantic_scholar";
+      provider: "pubmed";
       query_index: number;
       query: string;
     }
   | {
       phase: "query_results";
-      provider: "pubmed" | "semantic_scholar";
+      provider: "pubmed";
       query_index: number;
       query: string;
       count: number;
@@ -37,7 +36,7 @@ export type LiteratureSearchDisplayEvent =
     }
   | {
       phase: "query_error";
-      provider: "pubmed" | "semantic_scholar";
+      provider: "pubmed";
       query_index: number;
       query: string;
       error: string;
@@ -46,7 +45,7 @@ export type LiteratureSearchDisplayEvent =
   | { phase: "complete"; count: number; papers: CompactPaperForDisplay[] };
 
 export type LiteratureSearchDisplaySearch = {
-  provider: "pubmed" | "semantic_scholar";
+  provider: "pubmed";
   query_index: number;
   query: string;
   count: number;
@@ -107,7 +106,6 @@ export function authorRange(paper: PaperRecord): string {
 export function paperIdentifier(paper: PaperRecord): string {
   if (paper.doi) return `DOI:${paper.doi}`;
   if (paper.pmid) return `PMID:${paper.pmid}`;
-  if (paper.s2_id) return `S2:${paper.s2_id}`;
   return "—";
 }
 
@@ -120,11 +118,7 @@ export function sourceLabel(paper: PaperRecord): string {
       .map((source) => source.trim())
       .filter(Boolean),
   );
-  const hasPubmed = sources.has("pubmed");
-  const hasS2 = sources.has("semantic_scholar");
-  if (hasPubmed && hasS2) return "PM+S2";
-  if (hasPubmed) return "PM";
-  if (hasS2) return "S2";
+  if (sources.has("pubmed")) return "PM";
   return paper.source ?? "—";
 }
 
@@ -136,7 +130,6 @@ export function compactPaperForDisplay(paper: PaperRecord): CompactPaperForDispl
     source: sourceLabel(paper),
     year: paper.year,
     journal: paper.journal,
-    citation_count: paper.citation_count,
   };
 }
 
@@ -144,12 +137,12 @@ export function compactPapersForDisplay(papers: PaperRecord[]): CompactPaperForD
   return papers.map(compactPaperForDisplay);
 }
 
-function providerLabel(provider: "pubmed" | "semantic_scholar"): string {
-  return provider === "pubmed" ? "PubMed" : "Semantic Scholar";
+function providerLabel(provider: "pubmed"): string {
+  return "PubMed";
 }
 
-function providerColor(provider: "pubmed" | "semantic_scholar"): string {
-  return provider === "pubmed" ? "success" : "accent";
+function providerColor(provider: "pubmed"): string {
+  return "success";
 }
 
 export function formatFoundLine(
@@ -168,7 +161,7 @@ export function formatMergedLine(
   theme?: ThemeLike,
 ): string {
   const title = truncateText(paper.title, 72);
-  const source = color(theme, paper.source.includes("S2") ? "accent" : "success", `(${paper.source})`);
+  const source = color(theme, "success", `(${paper.source})`);
   return `  ${color(theme, "success", "+")} ${index + 1}. ${title} ${source}`;
 }
 
@@ -237,7 +230,6 @@ type LiteratureResultDetails = {
   papers?: PaperRecord[];
   providers?: {
     pubmed?: ProviderSearchSummary;
-    semantic_scholar?: ProviderSearchSummary;
   };
   events?: LiteratureSearchDisplayEvent[];
 };
@@ -250,11 +242,9 @@ type ProviderResultDetails = {
 
 function renderCollapsedLiteratureResult(details: LiteratureResultDetails, theme?: ThemeLike): string {
   const pubmed = details?.providers?.pubmed;
-  const s2 = details?.providers?.semantic_scholar;
   const pubmedText = pubmed?.searched ? `PubMed: ${pubmed.count}` : "PubMed: —";
-  const s2Text = s2?.searched ? `S2: ${s2.count}` : "S2: skipped";
   const count = details?.count ?? details?.papers?.length ?? 0;
-  return `${color(theme, "success", "✓")} ${color(theme, "toolTitle", "literature_search")} ${color(theme, "success", pubmedText)} | ${color(theme, "accent", s2Text)} | merged: ${count}`;
+  return `${color(theme, "success", "✓")} ${color(theme, "toolTitle", "literature_search")} ${color(theme, "success", pubmedText)} | merged: ${count}`;
 }
 
 export function renderLiteratureSearchResult(
@@ -284,7 +274,7 @@ export function renderLiteratureSearchResult(
 }
 
 export function renderProviderSearchResult(
-  provider: "pubmed" | "semantic_scholar",
+  provider: "pubmed",
   result: ToolRenderResult<ProviderResultDetails>,
   options: RenderOptions,
   theme?: ThemeLike,
@@ -298,7 +288,7 @@ export function renderProviderSearchResult(
     return terminalText(color(theme, "warning", text));
   }
   if (!options.expanded) {
-    return terminalText(`${color(theme, "success", "✓")} ${color(theme, "toolTitle", provider === "pubmed" ? "pubmed_search" : "semantic_scholar_search")} ${papers.length} papers`);
+    return terminalText(`${color(theme, "success", "✓")} ${color(theme, "toolTitle", "pubmed_search")} ${papers.length} papers`);
   }
   const lines = [
     `${color(theme, providerColor(provider), "→")} ${color(theme, providerColor(provider), providerName)} q1: ${query}`,

package/src/shared.ts

@@ -1,5 +1,3 @@
-import { mkdir, writeFile } from "node:fs/promises";
-import path from "node:path";
 import type { PaperRecord } from "./types.ts";
 
 export const USER_AGENT = "research-skills-literature-tools/0.1 (+https://github.com/fbraza/research-skills)";
@@ -82,22 +80,3 @@ export async function fetchJson<T>(url: string, signal?: AbortSignal, headers?:
 export function formatPaperText(papers: PaperRecord[]): string {
 	return JSON.stringify(papers, null, 2);
 }
-
-export function sanitizeFilename(value: string): string {
-	return value.replace(/[^a-z0-9._-]+/gi, "_").replace(/^_+|_+$/g, "") || "paper";
-}
-
-export async function savePdf(pdfUrl: string, outputDir: string, preferredId: string, signal?: AbortSignal): Promise<string> {
-	await mkdir(outputDir, { recursive: true });
-	const response = await fetch(pdfUrl, {
-		method: "GET",
-		signal,
-		headers: { "user-agent": USER_AGENT, accept: "application/pdf,*/*" },
-		redirect: "follow",
-	});
-	if (!response.ok) throw new Error(`Failed to download PDF (${response.status})`);
-	const bytes = Buffer.from(await response.arrayBuffer());
-	const filePath = path.resolve(outputDir, `${sanitizeFilename(preferredId)}.pdf`);
-	await writeFile(filePath, bytes);
-	return filePath;
-}

package/src/types.ts

@@ -1,7 +1,6 @@
 export type PaperRecord = {
 	pmid?: string;
 	doi?: string;
-	s2_id?: string;
 	title: string;
 	abstract?: string;
 	authors?: string[];
@@ -9,22 +8,10 @@ export type PaperRecord = {
 	year?: number;
 	publication_types?: string[];
 	mesh_terms?: string[];
-	citation_count?: number;
-	tldr?: string;
-	open_access_pdf?: string;
-	external_ids?: Record<string, string>;
 	source?: string;
 	sources?: string[];
 	date?: string;
 	category?: string;
 	version?: string;
 	license?: string;
-	pdf_url?: string;
-};
-
-export type FullTextRouteResult = {
-	source: string;
-	pdf_url?: string;
-	access_note: string;
-	is_preprint?: boolean;
 };