feat(tools): add dependency-free BM25 ranker

knip.json

@@ -27,6 +27,8 @@
 				"!utils/WorkspacePathResolver.ts!",
 				"!test-utils/**!",
 				"!utils/versionToken.ts!",
+				"!services/tools/Bm25Ranker.ts!",
+				"!services/tools/types.ts!",
 				"!core/tools/helpers/toolResultFormatting.ts!"
 			],
 			"ignoreDependencies": [

src/services/tools/Bm25Ranker.ts

@@ -0,0 +1,105 @@
+import { Ranker, ToolDoc } from "./types"
+
+type IndexedDocument = {
+	item: ToolDoc
+	termFrequencies: Map<string, number>
+	length: number
+	index: number
+}
+
+export class Bm25Ranker implements Ranker {
+	private readonly k1 = 1.5
+	private readonly b = 0.75
+	private indexedItems: ToolDoc[] | undefined
+	private documents: IndexedDocument[] = []
+	private documentFrequency = new Map<string, number>()
+	private averageDocumentLength = 0
+
+	rank(query: string, items: ToolDoc[], k: number): ToolDoc[] {
+		const queryTerms = tokenize(query)
+
+		if (queryTerms.length === 0 || items.length === 0 || k <= 0) {
+			return []
+		}
+
+		this.ensureIndex(items)
+
+		const scores = this.documents
+			.map((document) => ({
+				document,
+				score: this.score(document, new Set(queryTerms)),
+			}))
+			.filter(({ score }) => score > 0)
+
+		scores.sort((left, right) => right.score - left.score || left.document.index - right.document.index)
+
+		return scores.slice(0, k).map(({ document }) => document.item)
+	}
+
+	private ensureIndex(items: ToolDoc[]): void {
+		if (this.indexedItems === items) {
+			return
+		}
+
+		this.indexedItems = items
+		this.documentFrequency = new Map<string, number>()
+		this.documents = items.map((item, index) => {
+			const termFrequencies = countTerms(item)
+
+			for (const term of termFrequencies.keys()) {
+				this.documentFrequency.set(term, (this.documentFrequency.get(term) ?? 0) + 1)
+			}
+
+			return {
+				item,
+				termFrequencies,
+				length: Array.from(termFrequencies.values()).reduce((total, count) => total + count, 0),
+				index,
+			}
+		})
+		this.averageDocumentLength =
+			this.documents.reduce((total, document) => total + document.length, 0) / this.documents.length
+	}
+
+	private score(document: IndexedDocument, queryTerms: Set<string>): number {
+		let score = 0
+		const documentCount = this.documents.length
+
+		for (const term of queryTerms) {
+			const termFrequency = document.termFrequencies.get(term)
+
+			if (!termFrequency) {
+				continue
+			}
+
+			const documentFrequency = this.documentFrequency.get(term) ?? 0
+			const inverseDocumentFrequency = Math.log(
+				1 + (documentCount - documentFrequency + 0.5) / (documentFrequency + 0.5),
+			)
+			const normalization = this.k1 * (1 - this.b + this.b * (document.length / this.averageDocumentLength))
+
+			score += inverseDocumentFrequency * ((termFrequency * (this.k1 + 1)) / (termFrequency + normalization))
+		}
+
+		return score
+	}
+}
+
+function tokenize(value: string): string[] {
+	return value
+		.normalize("NFC")
+		.toLowerCase()
+		.split(/[^\p{L}\p{M}\p{N}]+/u)
+		.filter(Boolean)
+}
+
+function countTerms(item: ToolDoc): Map<string, number> {
+	const frequencies = new Map<string, number>()
+	const text = `${item.serverName} ${item.toolName} ${item.description}`
+
+	for (const term of tokenize(text)) {
+		frequencies.set(term, (frequencies.get(term) ?? 0) + 1)
+	}
+
+	return frequencies
+}

src/services/tools/__tests__/Bm25Ranker.spec.ts

@@ -0,0 +1,96 @@
+import { describe, expect, it } from "vitest"
+import { Bm25Ranker } from "../Bm25Ranker"
+import { ToolDoc } from "../types"
+
+const tool = (serverName: string, toolName: string, description: string): ToolDoc => ({
+	serverName,
+	toolName,
+	description,
+})
+
+describe("Bm25Ranker", () => {
+	it("ranks matching MCP tools by BM25 relevance", () => {
+		const items = [
+			tool("postgres", "query", "Send data and query a Postgres database"),
+			tool("jira", "createIssue", "Send messages and create Jira issues"),
+			tool("slack", "postMessage", "Send a Slack message"),
+		]
+
+		expect(new Bm25Ranker().rank("send slack message", items, 3)).toEqual([items[2], items[1], items[0]])
+	})
+
+	it("returns an empty result for empty queries, empty items, and no matches", () => {
+		const ranker = new Bm25Ranker()
+		const items = [tool("slack", "postMessage", "Send a message")]
+
+		expect(ranker.rank("   ", items, 10)).toEqual([])
+		expect(ranker.rank("message", [], 10)).toEqual([])
+		expect(ranker.rank("unrelated", items, 10)).toEqual([])
+	})
+
+	it("truncates results to the requested top-k", () => {
+		const items = [
+			tool("one", "search", "Search records"),
+			tool("two", "search", "Search records"),
+			tool("three", "search", "Search records"),
+		]
+
+		expect(new Bm25Ranker().rank("search", items, 2)).toEqual(items.slice(0, 2))
+		expect(new Bm25Ranker().rank("search", items, 0)).toEqual([])
+	})
+
+	it("preserves input order for equal scores", () => {
+		const items = [tool("first", "lookup", "Find a record"), tool("second", "lookup", "Find a record")]
+
+		expect(new Bm25Ranker().rank("record", items, 10)).toEqual(items)
+	})
+
+	it("tokenizes case-insensitively around punctuation", () => {
+		const matching = tool("Slack-Server", "POST.Message", "Send a message")
+		const nonMatching = tool("calendar", "createEvent", "Create a calendar event")
+
+		expect(new Bm25Ranker().rank("SLACK post message", [nonMatching, matching], 10)).toEqual([matching])
+	})
+
+	it("splits underscore-separated tool names into separate terms", () => {
+		const matching = tool("github", "create_issue", "Open a ticket")
+		const nonMatching = tool("calendar", "list_events", "Show upcoming events")
+
+		expect(new Bm25Ranker().rank("create issue", [nonMatching, matching], 10)).toEqual([matching])
+	})
+
+	it("preserves Unicode letters and numbers in tokens", () => {
+		const russian = tool("погода-сервер", "прогноз", "Прогноз погоды")
+		const arabic = tool("أدوات", "مقياس", "يدعم ٣ بروتوكولات")
+
+		expect(new Bm25Ranker().rank("погода", [arabic, russian], 10)).toEqual([russian])
+		expect(new Bm25Ranker().rank("٣", [russian, arabic], 10)).toEqual([arabic])
+	})
+
+	it("matches composed and decomposed forms of the same accented character", () => {
+		const decomposed = tool("café", "menu", "Liste du café")
+		const composed = tool("café", "menu", "Menu")
+		const other = tool("calendar", "events", "Show events")
+
+		expect(new Bm25Ranker().rank("café", [other, decomposed], 10)).toEqual([decomposed])
+		expect(new Bm25Ranker().rank("café", [other, composed], 10)).toEqual([composed])
+	})
+
+	it("handles tools with empty descriptions", () => {
+		const item = tool("GitHub", "listRepos", "")
+
+		expect(new Bm25Ranker().rank("github repos", [item], 10)).toEqual([item])
+	})
+
+	it("rebuilds only when the items array reference changes", () => {
+		const items = [tool("slack", "send", "Send a message")]
+		const ranker = new Bm25Ranker()
+
+		ranker.rank("send", items, 10)
+		items.push(tool("jira", "create", "Create an issue"))
+		expect(ranker.rank("issue", items, 10)).toEqual([])
+
+		const newItems = items.slice()
+		expect(ranker.rank("issue", newItems, 10)).toEqual([newItems[1]])
+	})
+})

src/services/tools/types.ts

@@ -0,0 +1,9 @@
+export type ToolDoc = {
+	serverName: string
+	toolName: string
+	description: string
+}
+
+export interface Ranker {
+	rank(query: string, items: ToolDoc[], k: number): ToolDoc[]
+}