4ebe7c9683
MVP demo: one operator-funded API key anyone can plug into an IDE/harness,
running real escrow-per-session marketplace conversations (llm.chat.v1)
behind the standard OpenAI /chat/completions wire shape.
- shared: ChatMessage gains tool role + tool_calls; normalizeChatMessage/
chatMessagesEquivalent keep supplier transcript and gateway mirror
hash-identical for receipts (field presence is part of the identity)
- supplier: /v1/chat/message accepts {messages,tools,tool_choice} alongside
legacy {content}; callOpenAiStream forwards tools, accumulates fragmented
delta.tool_calls, allows content-less tool turns; done frame carries the
assistant message verbatim + finish_reason + usage
- gateway: demo flag on api_keys (additive migration), create-demo-key CLI,
withdraw 403 + hidden deposit address for demo keys, per-IP demo rate
limit (demo keys skip the shared per-key limit), models filtered to chat
capability
- gateway executor (demoChat.ts): transcript-prefix affinity maps stateless
calls onto open sessions, forwards only unseen deltas, transparently
reopens on supplier idle-close; never falls back to one-shot (its settle
path assumes <=1 in-flight escrow per wallet)
- mutex scope: key mutex held only for chain work (open/close); off-chain
turns serialize on per-session locks so replicas serve users concurrently
- sweeper: chat-aware reclaim guard (35min vs 11min) and abandoned-session
cleanup; terminal state confirmed via on-chain queryUtxo (indexer keeps
lineage rows at their old state forever)
- deploy: kimi-chat replicas 2+3 compose files; chat idle timeout 2.5min
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
27 lines
998 B
TypeScript
27 lines
998 B
TypeScript
/**
|
|
* gateway/src/openai/models.ts — GET /openai/v1/models.
|
|
*
|
|
* Distinct models advertised by Active suppliers, in the OpenAI list shape.
|
|
*/
|
|
|
|
import type { Request, Response } from "express";
|
|
import type { GatewayDeps } from "../deps.js";
|
|
import { asyncHandler } from "../middleware/http.js";
|
|
import { requireKey } from "../middleware/apiKeyAuth.js";
|
|
import { listModels } from "../routing/selectSupplier.js";
|
|
import { buildModelsList } from "./shapes.js";
|
|
import { CAPABILITY as CHAT_CAPABILITY } from "./sessions.js";
|
|
|
|
export function makeModelsHandler(deps: GatewayDeps) {
|
|
return asyncHandler(async (req: Request, res: Response) => {
|
|
const keyRow = requireKey(req);
|
|
// Demo keys only reach chat-capable suppliers (session-backed executor).
|
|
const models = await listModels({
|
|
indexerUrl: deps.config.indexerUrl,
|
|
capabilityId: keyRow.demo ? CHAT_CAPABILITY : undefined,
|
|
fetchFn: deps.fetchFn,
|
|
});
|
|
res.status(200).json(buildModelsList(models));
|
|
});
|
|
}
|