feat: add OpenRouter as one of the default providers

[nabinchha]

closes: #157

TODO:

• Test with an api key

Default model configs after resetting with data-designer config reset

[nabinchha]

[10:15:14] [INFO] 🔁 Preview generation in progress
[10:15:14] [INFO] ✅ Validation passed
[10:15:14] [INFO] ⛓️ Sorting column configs into a Directed Acyclic Graph
[10:15:14] [INFO] 🩺 Running health checks for models...
[10:15:14] [INFO]   |-- 👀 Checking 'openai/text-embedding-3-large' in provider named 'openrouter' for model alias 'openrouter-embedding'...
[10:15:15] [INFO]   |-- ✅ Passed!
[10:15:15] [INFO]   |-- 👀 Checking 'nvidia/nemotron-3-nano-30b-a3b' in provider named 'openrouter' for model alias 'openrouter-text'...
[10:15:17] [INFO]   |-- ✅ Passed!
[10:15:17] [INFO]   |-- 👀 Checking 'openai/gpt-oss-20b' in provider named 'openrouter' for model alias 'openrouter-reasoning'...
[10:15:19] [INFO]   |-- ✅ Passed!
[10:15:19] [INFO]   |-- 👀 Checking 'nvidia/nemotron-nano-12b-v2-vl' in provider named 'openrouter' for model alias 'openrouter-vision'...
[10:15:20] [INFO]   |-- ✅ Passed!
[10:15:20] [INFO] 🌱 Sampling 10 records from seed dataset
[10:15:20] [INFO]   |-- seed dataset size: 10 records
[10:15:20] [INFO]   |-- sampling strategy: ordered
[10:15:20] [INFO] 🎲 Preparing samplers to generate 10 records across 1 columns
[10:15:20] [INFO] (💾 + 💾) Concatenating 2 datasets
[10:15:20] [INFO] Preparing llm-text column generation
[10:15:20] [INFO]   |-- column name: 'greetings'
[10:15:20] [INFO]   |-- model config:
{
    "alias": "openrouter-text",
    "model": "nvidia/nemotron-3-nano-30b-a3b",
    "inference_parameters": {
        "generation_type": "chat-completion",
        "max_parallel_requests": 4,
        "timeout": null,
        "extra_body": null,
        "temperature": 1.0,
        "top_p": 1.0,
        "max_tokens": null
    },
    "provider": "openrouter"
}
[10:15:20] [INFO] 🐙 Processing llm-text column 'greetings' with 4 concurrent workers
[10:15:29] [INFO] Preparing llm-text column generation
[10:15:29] [INFO]   |-- column name: 'summary'
[10:15:29] [INFO]   |-- model config:
{
    "alias": "openrouter-vision",
    "model": "nvidia/nemotron-nano-12b-v2-vl",
    "inference_parameters": {
        "generation_type": "chat-completion",
        "max_parallel_requests": 4,
        "timeout": null,
        "extra_body": null,
        "temperature": 0.85,
        "top_p": 0.95,
        "max_tokens": null
    },
    "provider": "openrouter"
}
[10:15:29] [INFO] 🐙 Processing llm-text column 'summary' with 4 concurrent workers
[10:15:55] [INFO] Preparing llm-text column generation
[10:15:55] [INFO]   |-- column name: 'greetings_reasoning'
[10:15:55] [INFO]   |-- model config:
{
    "alias": "openrouter-reasoning",
    "model": "openai/gpt-oss-20b",
    "inference_parameters": {
        "generation_type": "chat-completion",
        "max_parallel_requests": 4,
        "timeout": null,
        "extra_body": null,
        "temperature": 0.35,
        "top_p": 0.95,
        "max_tokens": null
    },
    "provider": "openrouter"
}
[10:15:55] [INFO] 🐙 Processing llm-text column 'greetings_reasoning' with 4 concurrent workers
[10:16:42] [INFO] Preparing embedding column generation
[10:16:42] [INFO]   |-- column name: 'greetings_embedding'
[10:16:42] [INFO]   |-- model config:
{
    "alias": "openrouter-embedding",
    "model": "openai/text-embedding-3-large",
    "inference_parameters": {
        "generation_type": "embedding",
        "max_parallel_requests": 4,
        "timeout": null,
        "extra_body": null,
        "encoding_format": "float",
        "dimensions": null
    },
    "provider": "openrouter"
}
[10:16:42] [INFO] 🐙 Processing embedding column 'greetings_embedding' with 4 concurrent workers
[10:16:45] [INFO] 📊 Model usage summary:
{
    "openai/text-embedding-3-large": {
        "token_usage": {
            "input_tokens": 1330,
            "output_tokens": 0,
            "total_tokens": 1330
        },
        "request_usage": {
            "successful_requests": 10,
            "failed_requests": 0,
            "total_requests": 10
        },
        "tokens_per_second": 15,
        "requests_per_minute": 7
    },
    "nvidia/nemotron-3-nano-30b-a3b": {
        "token_usage": {
            "input_tokens": 310,
            "output_tokens": 3316,
            "total_tokens": 3626
        },
        "request_usage": {
            "successful_requests": 10,
            "failed_requests": 0,
            "total_requests": 10
        },
        "tokens_per_second": 42,
        "requests_per_minute": 7
    },
    "openai/gpt-oss-20b": {
        "token_usage": {
            "input_tokens": 2153,
            "output_tokens": 20093,
            "total_tokens": 22246
        },
        "request_usage": {
            "successful_requests": 10,
            "failed_requests": 0,
            "total_requests": 10
        },
        "tokens_per_second": 263,
        "requests_per_minute": 7
    },
    "nvidia/nemotron-nano-12b-v2-vl": {
        "token_usage": {
            "input_tokens": 30748,
            "output_tokens": 8737,
            "total_tokens": 39485
        },
        "request_usage": {
            "successful_requests": 10,
            "failed_requests": 0,
            "total_requests": 10
        },
        "tokens_per_second": 467,
        "requests_per_minute": 7
    }
}
[10:16:45] [INFO] 🙈 Dropping columns: ['language']
[10:16:45] [INFO] 📐 Measuring dataset column statistics:
[10:16:45] [INFO]   |-- 🌱 column: 'uuid'
[10:16:45] [INFO]   |-- 🌱 column: 'image_filename'
[10:16:45] [INFO]   |-- 🌱 column: 'base64_image'
[10:16:45] [INFO]   |-- 🌱 column: 'page'
[10:16:45] [INFO]   |-- 🌱 column: 'options'
[10:16:45] [INFO]   |-- 🌱 column: 'source'
[10:16:45] [INFO]   |-- 📝 column: 'greetings'
[10:16:45] [INFO]   |-- 📝 column: 'greetings_reasoning'
[10:16:45] [INFO]   |-- 🧬 column: 'greetings_embedding'
[10:16:45] [INFO]   |-- 📝 column: 'summary'
[10:16:45] [INFO] 👏 Preview complete!