[heydryft]

All Submissions:

• Notify authors: * @agentforce314, @ericleepi314

New Feature Submissions:

• Have you added an explanation of what your changes do and why you'd like us to include them?

Description

Adds Runcrate (https://runcrate.ai) as a row in the OpenAI-compatible ProviderSpec registry. Runcrate serves open-weight models (DeepSeek V4, GLM 5.3, Kimi K2.6, Qwen3 Coder) behind an OpenAI-compatible /v1/chat/completions API with Bearer auth, so it needs no bespoke class.

Changes proposed in this pull request:

• src/providers/openai_compatible_specs.py: runcrate spec, base URL https://api.runcrate.ai/v1, default model deepseek-ai/DeepSeek-V4-Flash, five suggested models, RUNCRATE_API_KEY, aliases run-crate / run_crate
• tests/test_provider_registry.py: runcrate added to EXPECTED_NEW_PROVIDERS and VENDOR_DEFAULTS
• README provider list (and the translated READMEs): add runcrate, count 30 to 31 in the English README

Testing

• python -m pytest -q tests/test_provider_registry.py: 27 passed
• python -m pytest -q tests -k 'provider or registry or login or config': 1324 passed, 5 skipped
• Live: get_provider_class('runcrate')(api_key=...) resolved to RuncrateProvider with base URL https://api.runcrate.ai/v1 and model deepseek-ai/DeepSeek-V4-Flash; chat([...]) returned 'OK' with usage {'input_tokens': 11, 'output_tokens': 27, 'total_tokens': 38}.

This PR was prepared with AI assistance (Claude Code). I work on Runcrate.

[agentforce314]

LGTM

[heydryft]

Thanks @agentforce314 for merging! Glad Runcrate is in the clawcodex OpenAI-compatible registry now.