Skip to content

docs: update InvokeLLM model options to match backend #159

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wixysam merged 2 commits into from
Apr 9, 2026
Merged

docs: update InvokeLLM model options to match backend #159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dec2cca
docs: update InvokeLLM model options to match backend
wixysam Apr 9, 2026
1ead2d7
chore: resolve merge conflict, keep correct gemini_3_1_pro (underscores)
wixysam Apr 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions .claude/skills/sdk-docs-writing/references/pipeline-config.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,20 @@ cd docs
mint dev
```

## Running in a git worktree

Git worktrees don't have their own `node_modules`. Before running `npm run create-docs` from a worktree, symlink in the main repo's `node_modules`:

```bash
# If a partial node_modules exists (e.g. from a failed npm install), remove it first
rm -rf /path/to/worktree/javascript-sdk/node_modules

ln -s /Users/samm/Projects/base44-workspace/javascript-sdk/node_modules \
/path/to/worktree/javascript-sdk/node_modules
```

Then `npm run create-docs` works normally from the worktree.

## Pipeline configuration files

| File | Purpose |
Expand Down
4 changes: 2 additions & 2 deletions src/modules/integrations.types.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,9 +48,9 @@ export interface InvokeLLMParams {
prompt: string;
/** Optionally specify a model to override the app-level model setting for this specific call.
*
* Options: `"gpt_5_mini"`, `"gemini_3_flash"`, `"gpt_5"`, `"gemini_3.1_pro"`, `"claude_sonnet_4_6"`, `"claude_opus_4_6"`
* Options: `"gpt_5_mini"`, `"gemini_3_flash"`, `"gpt_5"`, `"gpt_5_4"`, `"gemini_3_1_pro"`, `"claude_sonnet_4_6"`, `"claude_opus_4_6"`
*/
model?: 'gpt_5_mini' | 'gemini_3_flash' | 'gpt_5' | 'gemini_3.1_pro' | 'claude_sonnet_4_6' | 'claude_opus_4_6';
model?: 'gpt_5_mini' | 'gemini_3_flash' | 'gpt_5' | 'gpt_5_4' | 'gemini_3_1_pro' | 'claude_sonnet_4_6' | 'claude_opus_4_6';
/** If set to `true`, the LLM will use Google Search, Maps, and News to gather real-time context before answering.
* @default false
*/
Expand Down
Loading