feat: Add CLOVA Studio model provider

• Add ClovaModel class implementing Model abstract base
• Support for HCX-005 model with SSE streaming
• Bearer token authentication (CLOVA_API_KEY)
• Bilingual support (Korean and English)
• Custom SSE parser for CLOVA's response format
• Comprehensive unit and integration tests
• Add clova optional dependency to pyproject.toml

Description

This PR adds support for CLOVA Studio, Naver's Korean language AI platform, to the Strands Agents SDK. CLOVA Studio provides state-of-the-art Korean language models that are optimized for Korean context and nuances.

Key Features

• Native Korean Support: Optimized for Korean language understanding and generation
• Bilingual Capability: Seamlessly handles both Korean and English
• SSE Streaming: Full streaming support with custom parser for CLOVA's response format
• Simple Authentication: Only requires CLOVA_API_KEY (Bearer token)
• Comprehensive Testing: 10 unit tests and 8 integration tests

Implementation Details

The ClovaModel class extends the abstract Model base class and implements:

• stream() method for real-time response streaming
• get_config() and update_config() for dynamic configuration
• Custom SSE parser to handle CLOVA's single-chunk response format
• Support for system prompts and various parameters (temperature, max_tokens, top_p, etc.)

Usage Example

from strands.models.clova import ClovaModel
from strands import Agent

# Initialize CLOVA model
model = ClovaModel(
    api_key="your-clova-api-key",
    model="HCX-005",
    temperature=0.7,
    max_tokens=2048
)

# Create agent with CLOVA
agent = Agent(model=model)

# Use for Korean language tasks
response = await agent.invoke_async("한국의 전통 음식을 소개해주세요")

Related Issues

Closes #802

Documentation PR

Type of Change

New feature

Testing

How have you tested the change?

Test Coverage

• Unit Tests: 10 tests covering all major functionality

  • Model initialization and configuration
  • Streaming response handling
  • Error handling (API failures, missing keys)
  • System prompt support
  • Configuration updates

• Integration Tests: 8 tests with real API

  • Basic streaming functionality
  • Korean and English language support
  • Temperature and token limit parameters
  • Bilingual capabilities
  • Model configuration management

Test Results

# Unit tests
$ hatch test tests/strands/models/test_clova.py
======================== 10 passed, 1 warning in 2.60s =========================

# Integration tests (with API key)
$ hatch run test-integ tests_integ/models/test_model_clova.py
============================== 8 passed in 15.23s ==============================

Verification

• I ran hatch run prepare
• All tests pass successfully
• Code is formatted with hatch fmt
• No new warnings generated

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.