feat(memory): add MongoDBMemoryService with Atlas Vector Search support

## Motivation

The community repo has memory service proposals for Valkey (#155/#156), Milvus (#69), Firestore (#38), and SQL backends (#99), but no MongoDB-backed memory service. MongoDB is one of the most widely deployed document databases, and MongoDB Atlas provides native vector search (`$vectorSearch`), making it a natural backend for agent long-term memory with semantic recall.

Related: #31/#32 add a MongoDB *session* service. This proposal is complementary — a `MemoryService` implementation for long-term memory retrieval, not session/state storage. If #32 merges, the two modules together would give ADK users a full MongoDB persistence story.

## Proposed API

A `MongoDBMemoryService` implementing ADK's `BaseMemoryService` interface:

- `add_session_to_memory(session)` — extracts session events, generates embeddings via a pluggable embedding function, and stores documents (`app_name`, `user_id`, `session_id`, `content`, `embedding`, `timestamp`) in a configurable collection
- `search_memory(app_name, user_id, query)` — semantic retrieval via Atlas `$vectorSearch` with top-k limits, similarity threshold, and app/user isolation via pre-filters; falls back to Atlas text search for deployments without a vector index

Configuration options: connection string, database/collection names, embedding function, vector index name, `top_k`, similarity threshold.

## Dependencies

- `pymongo>=4.15,<5.0` (matching the pin in #32) as an optional dependency under a `[mongodb]` extra

## Testing Plan

- Unit tests (mocked client): cover all public methods, edge cases, error conditions
- Integration tests: run against the `mongodb/mongodb-atlas-local` Docker image (supports vector search locally), covering vector similarity search, user/app isolation, top-k limits, distance threshold filtering, metadata preservation, and index idempotency

---

I'd like to implement this myself and will follow the module structure and contribution lifecycle in CONTRIBUTING.md. Happy to adjust the approach based on maintainer feedback.

Commencez par CONTRIBUTING.md et la structure de modules existante autour de l’interface BaseMemoryService. Examinez les méthodes publiques proposées, la dépendance optionnelle à pymongo et le plan de test avec des mocks et Atlas-local Docker. Le travail est considéré comme terminé lorsque le service de mémoire MongoDB couvre les comportements répertoriés en matière de récupération, d’isolation, de filtrage, de métadonnées, d’erreurs et d’index.

Rédigé par le modèle d'indexation à partir du texte de l'issue.