luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(opencode-go): route by request format via transports + per-model guard

Browse Source 
opencode-go hard-coded targetFormat: claude per model, so every client
format was force-routed to /messages (Codex/OpenAI clients paid a lossy
Responses->OpenAI->Claude double translation). Declare the existing
upstream multi-endpoint transports [openai, claude, openai-responses]
and guard per model via registry supportedFormats: kimi/glm/mimo only
support /chat/completions, minimax/qwen add /messages, deepseek adds
/responses. Undeclared models keep the upstream default.

Drop the bespoke OpenCodeGoExecutor (its shared _lastModel cache could
cross auth headers between concurrent requests); DefaultExecutor already
consumes runtimeTransport and injects reasoning content.
This commit is contained in:
KiMelody
2026-08-14 16:51:48 +07:00
committed by decolua
parent 27f3710c8b
commit e1115e2839
7 changed files with 129 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
open-sse/handlers/chatCore.js
View File

@@ -6,7 +6,7 @@ import { normalizeClaudePassthrough, anchorClaudeCache } from "../translator/for
import { createStreamController } from "../utils/streamHandler.js";
import { refreshWithRetry } from "../services/tokenRefresh.js";
import { createRequestLogger } from "../utils/requestLogger.js";
import { getModelTargetFormat, getModelStrip, getModelUpstreamId, getModelType, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
import { getModelTargetFormat, getModelSupportedFormats, getModelStrip, getModelUpstreamId, getModelType, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
import { PROVIDERS } from "../config/providers.js";
import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
import { HTTP_STATUS, TOKEN_SAVER_HEADER } from "../config/runtimeConfig.js";
@@ -78,10 +78,20 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
const alias = PROVIDER_ID_TO_ALIAS[provider] || provider;
const modelTargetFormat = getModelTargetFormat(alias, model);
// Multi-endpoint providers: pick transport matching sourceFormat → zero translation
// Multi-endpoint providers: pick transport matching sourceFormat → zero translation.
// Per-model guard: only use the transport when the model declares support for that
// sourceFormat — opencode-go models differ in endpoint support (kimi/glm only do
// /chat/completions), so without this guard a claude-format request would wrongly
// route kimi to /messages.
const modelSupportedFormats = getModelSupportedFormats(alias, model);
const runtimeTransport = resolveTransport(provider, sourceFormat);
const targetFormat = modelTargetFormat || runtimeTransport?.format || getTargetFormat(provider, credentials);
if (runtimeTransport && credentials) credentials.runtimeTransport = runtimeTransport;
// Per-model guard: when a model declares supportedFormats, only use the
// sourceFormat-matched transport if that format is declared (opencode-go models
// differ — kimi/glm only do /chat/completions). Undeclared models keep the
// upstream default (use the transport), preserving behavior for glm/deepseek/...
const useTransport = (!modelSupportedFormats || modelSupportedFormats.includes(sourceFormat)) ? runtimeTransport : null;
const targetFormat = modelTargetFormat || useTransport?.format || getTargetFormat(provider, credentials);
if (useTransport && credentials) credentials.runtimeTransport = useTransport;
const stripList = getModelStrip(alias, model);
const upstreamModel = getModelUpstreamId(alias, model);