* feat: add LiteLLM as AI gateway provider * fix: add litellm to attachments, provider store, utils, and block guards * fix: add frontend model discovery pipeline for litellm provider Add API route, contract, query hook case, and ProviderModelsLoader entry so litellm models are fetched and synced to the store on workspace load, matching the vllm/ollama/openrouter/fireworks pattern. Also fixes defaultModel to empty string and adds litellm/ prefix early-return in blocks/utils.ts (reviewer feedback). * fix: remove azureEndpoint fallback from LiteLLM provider Copy-paste artifact from vLLM provider. LiteLLM should only use LITELLM_BASE_URL, not fall back to azureEndpoint which could cause requests to be routed to the wrong server. * fix(litellm): close audit gaps from PR #4644 - byok.ts: add litellm branch to getApiKeyWithBYOK so workflow block execution can resolve the proxy key instead of throwing "API key is required for litellm ..." - check-api-validation-contracts.ts: bump route baseline 755 -> 756 to account for the new /api/providers/litellm/models route - .env.example: document LITELLM_BASE_URL / LITELLM_API_KEY - copilot edit-workflow validation: include LiteLLM in the list of user-configured prefixed providers shown to the model - providers/utils.ts: drop stray optional-chain on providers.litellm to match the vllm pattern - lint: apply biome formatting fixes (multi-line if, SVG path, multi-line DYNAMIC_MODEL_PROVIDERS) * fix(litellm): final parity gaps from second audit - blocks/utils.ts getModelOptions(): include litellm models in the combined model dropdown — was previously dropping any proxy-discovered models from the agent block model picker. - get-blocks-metadata-tool.ts mockProvidersState: add litellm bucket so the server-side copilot block-metadata fallback can render model options when the providers store is not initialized. - blocks/utils.test.ts: add litellm to mock providers state (initial + beforeEach reset) and add a parallel store-bucket guard test mirroring the vLLM case. - providers/utils.test.ts: add parallel getApiKey test for litellm. * feat(litellm): use official LiteLLM brand icon and color - icons.tsx: replace the placeholder letterform with the official LiteLLM brand mark embedded as a PNG data URI in an SVG image. - models.ts: set color: #040229 on the litellm provider definition to match the brand background. * chore(litellm): validate /v1/models response with shared schema in initialize() Match the API route handler — both code paths now run the same vllmUpstreamResponseSchema.parse() over the upstream /v1/models JSON instead of a raw type-cast, so malformed upstream payloads surface a descriptive ZodError instead of a downstream TypeError. Addresses Greptile review feedback on PR #4739. --------- Co-authored-by: RheagalFire <arishalam121@gmail.com>
Block Documentation Generator
This directory contains scripts to automatically generate documentation for all blocks in the Sim platform.
Available Scripts
generate-docs.ts: Generates documentation for all blocks. Run viabun run generate-docsfromapps/sim, or directly withbun run scripts/generate-docs.tsfrom the repo root.
How It Works
The documentation generator:
- Scans the
apps/sim/blocks/blocks/directory for all block definition files - Extracts metadata from each block including:
- Name, description, and category
- Input and output specifications
- Configuration parameters
- Generates standardized Markdown documentation for each block
- Updates the navigation metadata in
meta.json
Running the Generator
# From the repo root
bun run scripts/generate-docs.ts
Dependencies are managed by Bun workspaces — bun install at the repo root installs everything needed.
CI Integration
The documentation generator runs automatically as part of the CI/CD pipeline whenever changes are pushed to the main branch. The updated documentation is committed back to the repository.
Adding Support for New Block Properties
If you add new properties to block definitions that should be included in the documentation, update the generateMarkdownForBlock function in scripts/generate-docs.ts.
Preserving Manual Content
The documentation generator now supports preserving manually added content when regenerating docs. This allows you to enhance the auto-generated documentation with custom examples, additional context, or any other content without losing your changes when the docs are regenerated.
How It Works
- The generator creates clean documentation without any placeholders or markers
- If you add manual content to a file using special comment markers, that content will be preserved during regeneration
- The manual content is intelligently inserted at the appropriate section when docs are regenerated
Using Manual Content Markers
To add custom content to any tool's documentation, insert MDX comment blocks with section markers:
{/_ MANUAL-CONTENT-START:sectionName _/}
Your custom content here (Markdown formatting supported)
{/_ MANUAL-CONTENT-END _/}
Replace sectionName with one of the supported section names:
intro- Content at the top of the document after the BlockInfoCardusage- Additional usage instructions and examplesconfiguration- Custom configuration detailsoutputs- Additional output information or examplesnotes- Extra notes at the end of the document
Example
To add custom examples to a tool doc:
{/_ MANUAL-CONTENT-START:usage _/}
## Examples
### Basic Usage
```json
{
"parameter": "value",
"anotherParameter": "anotherValue"
}
```
Advanced Configuration
Here's how to use this tool for a specific use case... {/_ MANUAL-CONTENT-END _/}
When the documentation is regenerated, your manual content will be preserved in the appropriate section automatically. The script will not add any placeholders or markers to files by default.