Merge pull request #255 from pandysp/feat/expose-candidate-limit

feat: expose candidateLimit as MCP tool parameter and CLI flag
This commit is contained in:
Tobias Lütke 2026-03-07 14:28:52 -04:00 committed by GitHub
commit a4b641d8e3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 13 additions and 1 deletions

View File

@ -308,10 +308,13 @@ Intent-aware lex (C++ performance, not sports):
),
limit: z.number().optional().default(10).describe("Max results (default: 10)"),
minScore: z.number().optional().default(0).describe("Min relevance 0-1 (default: 0)"),
candidateLimit: z.number().optional().describe(
"Maximum candidates to rerank (default: 40, lower = faster but may miss results)"
),
collections: z.array(z.string()).optional().describe("Filter to collections (OR match)"),
},
},
async ({ searches, limit, minScore, collections }) => {
async ({ searches, limit, minScore, candidateLimit, collections }) => {
// Map to internal format
const subSearches: StructuredSubSearch[] = searches.map(s => ({
type: s.type,
@ -325,6 +328,7 @@ Intent-aware lex (C++ performance, not sports):
collections: effectiveCollections.length > 0 ? effectiveCollections : undefined,
limit,
minScore,
candidateLimit,
});
// Use first lex or vec query for snippet extraction
@ -655,6 +659,7 @@ export async function startMcpHttpServer(port: number, options?: { quiet?: boole
collections: effectiveCollections.length > 0 ? effectiveCollections : undefined,
limit: params.limit ?? 10,
minScore: params.minScore ?? 0,
candidateLimit: params.candidateLimit,
});
// Use first lex or vec query for snippet extraction

View File

@ -1768,6 +1768,7 @@ type OutputOptions = {
collection?: string | string[]; // Filter by collection name(s)
lineNumbers?: boolean; // Add line numbers to output
context?: string; // Optional context for query expansion
candidateLimit?: number; // Max candidates to rerank (default: 40)
};
// Highlight query terms in text (skip short words < 3 chars)
@ -2177,6 +2178,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
collections: singleCollection ? [singleCollection] : undefined,
limit: opts.all ? 500 : (opts.limit || 10),
minScore: opts.minScore || 0,
candidateLimit: opts.candidateLimit,
hooks: {
onEmbedStart: (count) => {
process.stderr.write(`${c.dim}Embedding ${count} ${count === 1 ? 'query' : 'queries'}...${c.reset}`);
@ -2200,6 +2202,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
collection: singleCollection,
limit: opts.all ? 500 : (opts.limit || 10),
minScore: opts.minScore || 0,
candidateLimit: opts.candidateLimit,
hooks: {
onStrongSignal: (score) => {
process.stderr.write(`${c.dim}Strong BM25 signal (${score.toFixed(2)}) — skipping expansion${c.reset}\n`);
@ -2303,6 +2306,8 @@ function parseCLI() {
from: { type: "string" }, // start line
"max-bytes": { type: "string" }, // max bytes for multi-get
"line-numbers": { type: "boolean" }, // add line numbers to output
// Query options
"candidate-limit": { type: "string", short: "C" },
// MCP HTTP transport options
http: { type: "boolean" },
daemon: { type: "boolean" },
@ -2340,6 +2345,7 @@ function parseCLI() {
all: isAll,
collection: values.collection as string[] | undefined,
lineNumbers: !!values["line-numbers"],
candidateLimit: values["candidate-limit"] ? parseInt(String(values["candidate-limit"]), 10) : undefined,
};
return {
@ -2441,6 +2447,7 @@ function showHelp(): void {
console.log(" --all - Return all matches (pair with --min-score)");
console.log(" --min-score <num> - Minimum similarity score");
console.log(" --full - Output full document instead of snippet");
console.log(" -C, --candidate-limit <n> - Max candidates to rerank (default 40, lower = faster)");
console.log(" --line-numbers - Include line numbers in output");
console.log(" --files | --json | --csv | --md | --xml - Output format");
console.log(" -c, --collection <name> - Filter by one or more collections");