ruvnet/ruflo · error · Error

records must be a non-empty array of

Error message

records must be a non-empty array of {id?, vector, text?}

What it means

Thrown by the agenticow_ingest handler (agenticow-tools.ts:128) when the records argument is not a non-empty array of {id?, vector, text?}. Ingestion is the only way to add vectors to an agenticow memory file, and the tool refuses empty batches so a call cannot succeed while silently doing nothing.

Solutions

1. Wrap a single record in an array: records: [{ vector: [0.1, 0.2], text: 'item' }]
2. Skip the ingest call when your batch logic produced zero records
3. Log batch size before calling so empty batches are visible in traces

Example fix

// before
await callTool('agenticow_ingest', { path: p, records: [] });
// throws: records must be a non-empty array of {id?, vector, text?}

// after
if (batch.length > 0) {
  await callTool('agenticow_ingest', { path: p, dimension: 384, records: batch });
}

if (!Array.isArray(records) || records.length === 0) {
  // nothing to ingest — skip the call instead of erroring
  return { skipped: true, reason: 'empty batch' };
}

const isNonEmptyArray = (v: unknown): v is unknown[] => Array.isArray(v) && v.length > 0;

When it happens

Trigger: Calling agenticow_ingest with records omitted, records: [], or a single record object passed bare instead of wrapped in an array (records: {vector: [...]} instead of records: [{vector: [...]}]).

Common situations: A dedupe or threshold filter upstream emptied the batch before ingest; JSON pipelines that unwrap one-element arrays; a first-call seed script whose data load returned nothing.

Related errors

• at least one candidate is required
• candidate must ingest at least one vector
• label exceeds 256 chars
• label is required
• label may only contain [A-Za-z0-9_.\\-:/@]

AI-assisted analysis of ruvnet/ruflo@fa13ee4ad6 (2026-08-18). Data as JSON: /api/errors/91a4c3cb994fa623. Report an issue: GitHub.

Appendix: source

Thrown at v3/@claude-flow/cli/src/mcp-tools/agenticow-tools.ts:128

              id: { type: 'integer', description: 'Explicit id (auto-assigned when omitted)' },
              vector: { type: 'array', items: { type: 'number' }, description: 'Embedding vector (length must equal the memory dimension)' },
              text: { type: 'string', description: 'Optional payload surfaced on query hits' },
            },
            required: ['vector'],
          },
        },
        dimension: { type: 'integer', description: 'Vector dimension (required only when path does not exist yet)' },
      },
      required: ['path', 'records'],
    },
    handler: async (input) => {
      const api = await loadAgenticow();
      if (!api) return degradedResult('agenticow-not-found');

      const path = resolveMemoryPath(String(input.path));
      const records = input.records as Array<{ id?: number; vector: number[]; text?: string }>;
      if (!Array.isArray(records) || records.length === 0) {
        throw new Error('records must be a non-empty array of {id?, vector, text?}');
      }
      for (const r of records) {
        if (!Array.isArray(r.vector) || r.vector.length === 0) {
          throw new Error('each record requires a non-empty numeric vector');
        }
      }
      const dim = (input.dimension as number | undefined) ?? records[0].vector.length;
      const mem = await openWithLineage(api, path, dim);
      try {
        const result = await mem.ingest(records.map((r) => ({
          ...(typeof r.id === 'number' ? { id: r.id } : {}),
          vector: r.vector,
          ...(r.text !== undefined ? { text: r.text } : {}),
        })));
        await mem.save?.(manifestFor(path));
        return { success: true, path, ingested: result };
      } finally {
        await mem.close?.();

View on GitHub (pinned to fa13ee4ad6)