Add new LLM models to Letta Code by updating models.json and CI test matrices.
npx skills add https://github.com/letta-ai/letta-code --skill adding-models
Please help me install this Agent Skill. Skill: adding-models Source: https://github.com/letta-ai/letta-code/tree/main/.skills/adding-models Command: npx skills add https://github.com/letta-ai/letta-code --skill adding-models
This Skill guides you through adding support for new LLM models to Letta Code, including updating src/models.json, CI test matrices, and model validation. It reduces configuration errors and speeds up onboarding of new providers.
openai/, anthropic/, google_ai/).src/models.json with fields like id, handle, label, description, and provider-specific updateArgs.Use the skill to add a new model by updating the models configuration and ensuring CI validation. Example commands:
src/models.json with a new model entryHigh-intent search queries and answers about installing and using this skill.
Adding a new LLM model involves updating src/models.json with required fields (id, handle, label, description, isFeatured, updateArgs), ensuring the model handle uses the correct provider prefix (e.g., openai/, anthropic/), and running validation to confirm the configuration is correct before deploying.
Required fields are id, handle, label, description, isFeatured, and updateArgs. The handle must follow provider prefix conventions to ensure proper routing and integration with Letta's model discovery system.
Run validation checks to verify the model handle matches the correct provider prefix and that all required metadata fields are populated. Then execute CI tests to confirm the new model integrates correctly with existing toolset mappings and doesn't break compatibility.
Yes. The Skill handles batch model onboarding by allowing you to add multiple entries to models.json with consistent provider prefixes and settings. Validation and CI test matrices scale to cover all new models simultaneously.
Validation will catch the misconfigured handle and prevent it from being registered. Provider prefixes are strictly enforced to maintain consistency across model discovery and toolset routing, reducing integration errors downstream.
Yes. Adding a new model requires extending the CI test matrix to include the new model handle. This ensures comprehensive testing and prevents regressions when the model is integrated into Letta Code's runtime environment.
4lermanValidate and score OpenAPI/Swagger API design documents for linting issues and breaking changes.
melikhanmutluAutomate AI agent evaluation and benchmarking across production pipelines.
dmarinsAutomate CI/CD pipeline configuration and enforcement with GitHub Actions and Terraform.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略