Skip to content

Llm OpenAI shape #582

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
fretchen merged 5 commits into from
Jul 28, 2026
Merged

Llm OpenAI shape #582

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
216b4a3
try the switch
fretchen Jul 28, 2026
28b3048
Update sc_llm_x402_buyer.ipynb
fretchen Jul 28, 2026
4c368ce
Clean up
fretchen Jul 28, 2026
1602eea
Update sc_llm_x402.ts
fretchen Jul 28, 2026
57694e4
Merge branch 'main' into llm-openai-shape
fretchen Jul 28, 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
5 changes: 5 additions & 0 deletions scw_js/sc_llm_x402.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -373,6 +373,11 @@ export async function handle(event: ScwEvent, _context: unknown): Promise<ScwRes
// advertised (resolved.provider === LLM_PROVIDER), so pricing (getSettleAmount /
// USDC_MAX_PRICE_PER_MESSAGE, which use LLM_PROVIDER) stays correct. When a second
// provider (e.g. ionos) is advertised, per-provider pricing must follow suit here.
// TODO: getSettleAmount() and USDC_MAX_PRICE_PER_MESSAGE (above) are hardcoded to
// LLM_PROVIDER = "mistral" and do NOT use resolved.provider. The moment a second model
// is added to advertisedModelIds(), a request routed to that provider here will still be
// priced/settled at Mistral's rate — fix pricing to key off resolved.provider before
// advertising a second model.
llmData = await callLLMAPI(prompt, useMock, resolved.provider);
} catch (error) {
logger.error({ err: error }, "Error during answer generation");
Expand Down
Loading