feat(ts-sdk): add Sarvam LLM provider

Summary

The Python SDK supports Sarvam as an LLM provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.

Python reference	mem0/llms/sarvam.py
Registered in (Python)	mem0/utils/factory.py (LLMFactory)
Target file (TypeScript)	mem0-ts/src/oss/src/llms/sarvam.ts
Suggested implementation	OpenAI-compatible endpoint — subclass OpenAILLM with the Sarvam baseURL.

Requirements

• Implement SarvamLLM in mem0-ts/src/oss/src/llms/sarvam.ts, extending LLM (mem0-ts/src/oss/src/llms/base.ts) and mirroring the Python provider's behavior (generateResponse / generateChat).
• Register the "sarvam" provider in mem0-ts/src/oss/src/utils/factory.ts (LLMFactory).
• Add config typing in mem0-ts/src/oss/src/types/.
• Add a unit test under mem0-ts/src/oss/src/tests/.
• No new dependency — reuse the existing openai client with a custom baseURL.
• Update docs under docs/ if this provider is user-facing.

Reference pattern

Mirror an existing TS provider: llms/deepseek.ts (OpenAI-compatible) or llms/openai.ts.

Notes

Confirm the payload against mem0/llms/sarvam.py.

---

Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).