@@ -355,54 +355,6 @@ it creates. You can customize this behavior with the `attribution` option:
355- `co_authored_by`: When true (default), adds `Co-Authored-By: Crush <crush@charm.land>` to commit messages
355- `co_authored_by`: When true (default), adds `Co-Authored-By: Crush <crush@charm.land>` to commit messages
356- `generated_with`: When true (default), adds `๐ Generated with Crush` line to commit messages and PR descriptions
356- `generated_with`: When true (default), adds `๐ Generated with Crush` line to commit messages and PR descriptions
360โLocal models can also be configured via OpenAI-compatible API. Here are two common examples:
369โ "base_url": "http://localhost:11434/v1/",
370โ "type": "openai-compat",
373โ "name": "Qwen 3 30B",
374โ "id": "qwen3:30b",
375โ "context_window": 256000,
376โ "default_max_tokens": 20000
390โ "name": "LM Studio",
391โ "base_url": "http://localhost:1234/v1/",
392โ "type": "openai-compat",
395โ "name": "Qwen 3 30B",
396โ "id": "qwen/qwen3-30b-a3b-2507",
397โ "context_window": 256000,
398โ "default_max_tokens": 20000
406### Custom Providers
358### Custom Providers
408Crush supports custom provider configurations for both OpenAI-compatible and
360Crush supports custom provider configurations for both OpenAI-compatible and
@@ -521,6 +473,54 @@ To add specific models to the configuration, configure as such:
478+Local models can also be configured via OpenAI-compatible API. Here are two common examples:
487+ "base_url": "http://localhost:11434/v1/",
488+ "type": "openai-compat",
491+ "name": "Qwen 3 30B",
493+ "context_window": 256000,
494+ "default_max_tokens": 20000
508+ "name": "LM Studio",
509+ "base_url": "http://localhost:1234/v1/",
510+ "type": "openai-compat",
513+ "name": "Qwen 3 30B",
514+ "id": "qwen/qwen3-30b-a3b-2507",
515+ "context_window": 256000,
516+ "default_max_tokens": 20000
524## Logging
524## Logging
526Sometimes you need to look at logs. Luckily, Crush logs all sorts of
526Sometimes you need to look at logs. Luckily, Crush logs all sorts of