refactor(memory): run agent recall, memory tools and the server on the memory contract (P1.5)

- Orchestrator, memory tools, context loader and pattern write-back use a
  MemoryStore and a workspace scope instead of MindDB layers; the knowledge
  graph tools, cognify, memory linker and feedback handler are gone (graph
  hidden in v1, ADR-0002).
- The server opens one mem0 store in <dataDir>/memory/, embedded by the
  in-process model on first use, and extracts facts about the user in the
  background with the model the user chose (memoryExtraction setting).
- Legacy .mind memories are copied into the store once, in the background;
  the legacy files are only read.
- Weaver consolidation, harvest, wiki, memory import, memory lanes, vector
  backfill and index reconciliation are removed; agent runs, loops, sub-agent
  results, connector fetch and the failed-turn capture write through the
  contract. Workspace sessions no longer hold a mind handle.
- FileIndexer and the install audit move to waggle.db; recall date helpers and
  the reranker are copied into core.
- The CLI REPL opens the same memory store.
This commit is contained in:
shumeiko.it
2026-10-24 11:56:26 +02:00
parent f3eb6b6652
commit 784ca770b1
86 changed files with 2520 additions and 8444 deletions

View File

@@ -5,7 +5,7 @@ import os from 'node:os';
import path from 'node:path';
import { afterEach, describe, expect, it, vi } from 'vitest';
import { PERSONAL_SCOPE } from '@waggle/memory-contract';
import { createMem0MemoryStore, type TextEmbedder } from '../src/index.js';
import { createMem0MemoryStore, createWordEmbedder, type TextEmbedder } from '../src/index.js';
import { describeMemoryStoreContract } from '../../memory-contract/tests/contract-suite.js';
/** Deterministic bag-of-words embedder: texts that share words get similar vectors. */
@@ -125,4 +125,51 @@ describe('mem0 store — local behaviour', () => {
await new Promise<void>((resolve) => server.close(() => resolve()));
}
});
it('reads a model function on every extraction', async () => {
const models: string[] = [];
const server = http.createServer((req, res) => {
let body = '';
req.on('data', (chunk) => { body += chunk; });
req.on('end', () => {
models.push((JSON.parse(body) as { model: string }).model);
res.setHeader('Content-Type', 'application/json');
res.end(JSON.stringify({
id: 'chatcmpl-test',
object: 'chat.completion',
created: 0,
model: 'any',
choices: [{ index: 0, finish_reason: 'stop', message: { role: 'assistant', content: '{"memory":[]}' } }],
usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 },
}));
});
});
await new Promise<void>((resolve) => server.listen(0, '127.0.0.1', resolve));
const { port } = server.address() as AddressInfo;
try {
let current = 'first-model';
const store = await createMem0MemoryStore({
directory: tempDir(),
embedder: wordEmbedder,
extractionModel: { baseURL: `http://127.0.0.1:${port}/v1`, apiKey: 'test-key', model: () => current },
});
const conversation = [{ role: 'user' as const, content: 'I like tea.' }];
await store.remember({ scope: PERSONAL_SCOPE, conversation });
current = 'second-model';
await store.remember({ scope: PERSONAL_SCOPE, conversation });
expect(models).toEqual(['first-model', 'second-model']);
await store.close();
} finally {
await new Promise<void>((resolve) => server.close(() => resolve()));
}
});
it('ships a word embedder that ranks shared words higher', async () => {
const embedder = createWordEmbedder();
const [tea, coffee, teaAgain] = await embedder.embedBatch(['green tea', 'black coffee', 'tea']);
const dot = (a: ArrayLike<number>, b: ArrayLike<number>) =>
Array.from(a).reduce((sum, value, i) => sum + value * b[i]!, 0);
expect(embedder.dimensions).toBe(256);
expect(dot(tea!, teaAgain!)).toBeGreaterThan(dot(coffee!, teaAgain!));
});
});