@companion-ai/feynman 0.5.45 → 0.5.47

package/RELEASES.md

@@ -6,6 +6,15 @@ GitHub release notes are generated from the matching `## vX.Y.Z` section in this
 
 ## Unreleased
 
+## v0.5.47 - 2026-10-15
+
+- **pi-web-access 0.41.0.** Sites that turn away AI fetchers can be read by setting your own User-Agent: add `"fetchContent": { "userAgent": "..." }` to `~/.feynman/agent/web-search.json`. A SearXNG instance on your own machine now works without opening every local service to page fetches.
+
+## v0.5.46 - 2026-10-13
+
+- **Recent arXiv papers resolve by DOI.** OpenAlex adds new arXiv preprints days late, so looking up an arXiv DOI (`10.48550/arXiv.<id>`) it doesn't have yet failed. It is now looked up on arXiv itself, with a note.
+- When a topic sent to the arXiv source is written in arXiv's own query syntax (`search_query=all:...`, `submittedDate:[...]`), only the search words are passed on to OpenAlex.
+
 ## v0.5.45 - 2026-10-13
 
 - **Paper lookups recover instead of failing.**

package/extensions/research-tools/science-database-arxiv.ts

@@ -159,6 +159,19 @@ function arxivFeedEntries(feed: Record<string, unknown>): Record<string, unknown
 	return entries;
 }
 
+// Plain search words from a query written in arXiv's API syntax
+// (search_query=all:..., AND submittedDate:[...], &max_results=...).
+export function arxivTopicText(query: string): string {
+	return query
+		.replace(/&?\b(?:max_results|start|sortBy|sortOrder)=[^&\s]*/gi, " ")
+		.replace(/\b(?:AND|OR|ANDNOT)\s+submittedDate:\[[^\]]*\]/gi, " ")
+		.replace(/\bsearch_query[=_:]+/gi, " ")
+		.replace(/\b(?:all|ti|abs|au|cat|co|jr):/gi, " ")
+		.replace(/[&"()]/g, " ")
+		.replace(/\s+/g, " ")
+		.trim();
+}
+
 async function getArxivPapers(query: string): Promise<Record<string, unknown>> {
 	const parsed = parseToolKeyValueQuery(stripGetPapersCommand(query));
 	const requested = (parsed.flags.ids ?? parsed.text).split(/[,\s]+/).map((id) => id.trim()).filter(Boolean).slice(0, MAX_ARXIV_EXACT_RESULTS);
@@ -173,7 +186,7 @@ async function getArxivPapers(query: string): Promise<Record<string, unknown>> {
 	if (!ids.length) {
 		throw new ArxivTopicQueryError(
 			`No arXiv IDs found in "${query}". The arxiv source only looks up papers by ID; search topics with source semanticscholar or openalex.`,
-			parsed.text || stripGetPapersCommand(query),
+			arxivTopicText(parsed.text || stripGetPapersCommand(query)),
 		);
 	}
 	const rows: Record<string, unknown>[] = [];

package/extensions/research-tools/science-databases.ts

@@ -461,6 +461,22 @@ async function searchArxivWithFallback(params: ScienceDatabaseSearchParams): Pro
 	}
 }
 
+// OpenAlex indexes new arXiv preprints days late; arXiv itself answers for its
+// own DOIs (10.48550/arXiv.<id>).
+async function withArxivDoiFallback(
+	params: ScienceDatabaseSearchParams,
+	run: () => Promise<Record<string, unknown>>,
+): Promise<Record<string, unknown>> {
+	try {
+		return await run();
+	} catch (error) {
+		const arxivId = error instanceof Error ? /^OpenAlex has no work for doi:10\.48550\/arxiv\.(.+)$/i.exec(error.message)?.[1] : undefined;
+		if (!arxivId) throw error;
+		const result = await searchArxivWithFallback({ ...params, source: "arxiv", query: arxivId });
+		return { fallbackNote: `OpenAlex has no record of this arXiv DOI yet, so it was looked up on arXiv (${arxivId}).`, ...result };
+	}
+}
+
 async function scienceDatabaseSearch(params: ScienceDatabaseSearchParams): Promise<Record<string, unknown>> {
 	if (params.source === "arxiv") return searchArxivWithFallback(params);
 	if (params.source === "biorxiv") return searchPreprints(params, "biorxiv");
@@ -473,11 +489,11 @@ async function scienceDatabaseSearch(params: ScienceDatabaseSearchParams): Promi
 		return withIndexFallback(semanticScholar, openAlex, (reason) => `Semantic Scholar was unavailable (${reason}); these results are from OpenAlex.`);
 	}
 	if (params.source === "openalex") {
-		return withIndexFallback(
+		return withArxivDoiFallback(params, () => withIndexFallback(
 			openAlex,
 			OPENALEX_LOOKUP_QUERY.test(params.query.trim()) ? undefined : semanticScholar,
 			(reason) => `OpenAlex was unavailable (${reason}); these results are from Semantic Scholar.`,
-		);
+		));
 	}
 	return searchEuropePmc(params);
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@companion-ai/feynman",
-  "version": "0.5.45",
+  "version": "0.5.47",
   "description": "The open source AI research agent.",
   "license": "MIT",
   "type": "module",
@@ -86,7 +86,7 @@
     "pi-btw": "0.8.0",
     "pi-docparser": "4.0.0",
     "pi-subagents": "0.78.0",
-    "pi-web-access": "0.40.0",
+    "pi-web-access": "0.41.0",
     "posthog-node": "^5.53.0"
   },
   "peerDependencies": {