Към всички skills

adding-models

letta-ai · Тестване

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.

Оригинален текст · няма потвърден превод на български

Теми: agent-memory · ai · claude · codex · continual-learning · letta · memgpt · stateful-agents

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md
GitHub хранилище
Звезди на репото
3396
Лиценз
Apache-2.0
Последна проверка на записа
22.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add letta-ai/letta-code

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

Adding Models

This skill guides you through adding a new LLM model to Letta Code.

Quick Reference

Key files:

  • src/agent/remote-model-catalog.ts - Runtime catalog loading and projection
  • src/agent/model-catalog.ts - Model lookup and compatibility aliases
  • .github/workflows/ci.yml - CI test matrix (optional)
  • src/tools/manager.ts - Toolset detection logic (rarely needed)

Workflow

Step 1: Find Valid Model Handles

First identify the agent source. These inputs are deliberately different:

Agent sourceRows shownLabels, presets, and capabilities
Cloud hostedGET /v1/models/catalog onlyGET /v1/models/catalog
Cloud organization BYOKBYOK rows from GET /v1/modelsMatch to catalog metadata using provider metadata and model name; retain the BYOK handle for selection
Localpi-ai inventorypi-ai metadata
Custom App ServerServer runtime inventoryServer runtime metadata

In Cloud mode, never use base/hosted rows from GET /v1/models to filter, supplement, delay, or provide a fallback for the hosted catalog. This once made GPT-4o appear in a selector even though the Cloud catalog deliberately omitted it. GET /v1/models remains necessary for organization-specific BYOK rows.

Query the Cloud hosted catalog to see hosted preset IDs, handles, and capabilities:

curl -s https://api.letta.com/v1/models/catalog | jq '.models[] | [.id, .handle]'

To inspect organization BYOK rows from a Cloud backend, query its model inventory and filter by provider_category:

curl -s https://api.letta.com/v1/models/ \
  | jq '.[] | select(.provider_category == "byok") | [.handle, .provider_type]'

Do not use this response as a second hosted catalog.

Common provider prefixes:

  • anthropic/ - Claude models
  • openai/ - GPT models
  • google_ai/ - Gemini models
  • google_vertex/ - Vertex AI
  • openrouter/ - Various providers

Step 2: Update the Owning Catalog

Letta Code does not bundle a model catalog:

  • Cloud hosted rows and presets come from the server's GET /v1/models/catalog response.
  • Cloud GET /v1/models contributes only organization BYOK rows to selectors.
  • Local model inventory comes from pi-ai and the active provider runtimes.

Add the model at the source that owns it. A hosted preset belongs in the server catalog. A local provider model belongs in pi-ai or that provider's discovery runtime.

Целият SKILL.md в GitHub