feat(opencode-go): route by request format via transports + per-model guard
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
@@ -2,7 +2,7 @@ import { PROVIDERS } from "./providers.js";
|
||||
import REGISTRY from "../providers/registry/index.js";
|
||||
// PROVIDER_MODELS now built from providers/registry (transport + models co-located)
|
||||
import { PROVIDER_MODELS } from "../providers/index.js";
|
||||
import { modelQuotaFamily, modelStrip, modelTargetFormat, normalizeModelId } from "../providers/models/schema.js";
|
||||
import { modelQuotaFamily, modelStrip, modelTargetFormat, modelSupportedFormats, normalizeModelId } from "../providers/models/schema.js";
|
||||
import { CODEX_REVIEW_SUFFIX } from "../providers/models/helpers.js";
|
||||
export { PROVIDER_MODELS };
|
||||
|
||||
@@ -54,6 +54,14 @@ export function getModelTargetFormat(aliasOrId, modelId) {
|
||||
return modelTargetFormat(findModel(models, modelId, aliasOrId));
|
||||
}
|
||||
|
||||
// Declared upstream formats for a model (registry `supportedFormats`). Drives the
|
||||
// per-model guard on the sourceFormat-matched transport; null when undeclared.
|
||||
export function getModelSupportedFormats(aliasOrId, modelId) {
|
||||
const models = PROVIDER_MODELS[aliasOrId];
|
||||
if (!models) return null;
|
||||
return modelSupportedFormats(findModel(models, modelId, aliasOrId));
|
||||
}
|
||||
|
||||
export function getModelType(aliasOrId, modelId) {
|
||||
const models = PROVIDER_MODELS[aliasOrId];
|
||||
if (!models) return null;
|
||||
|
||||
@@ -10,7 +10,6 @@ import { CodexExecutor } from "./codex.js";
|
||||
import { CursorExecutor } from "./cursor.js";
|
||||
import { VertexExecutor } from "./vertex.js";
|
||||
import { OpenCodeExecutor } from "./opencode.js";
|
||||
import { OpenCodeGoExecutor } from "./opencode-go.js";
|
||||
import { GrokWebExecutor } from "./grok-web.js";
|
||||
import { GrokCliExecutor } from "./grok-cli.js";
|
||||
import { PerplexityWebExecutor } from "./perplexity-web.js";
|
||||
@@ -41,7 +40,6 @@ const executors = {
|
||||
vertex: new VertexExecutor("vertex"),
|
||||
"vertex-partner": new VertexExecutor("vertex-partner"),
|
||||
opencode: new OpenCodeExecutor(),
|
||||
"opencode-go": new OpenCodeGoExecutor(),
|
||||
"grok-web": new GrokWebExecutor(),
|
||||
"grok-cli": new GrokCliExecutor(),
|
||||
gcli: new GrokCliExecutor(), // Alias
|
||||
@@ -86,7 +84,6 @@ export { CursorExecutor } from "./cursor.js";
|
||||
export { VertexExecutor } from "./vertex.js";
|
||||
export { DefaultExecutor } from "./default.js";
|
||||
export { OpenCodeExecutor } from "./opencode.js";
|
||||
export { OpenCodeGoExecutor } from "./opencode-go.js";
|
||||
export { GrokWebExecutor } from "./grok-web.js";
|
||||
export { GrokCliExecutor } from "./grok-cli.js";
|
||||
export { PerplexityWebExecutor } from "./perplexity-web.js";
|
||||
|
||||
@@ -1,49 +0,0 @@
|
||||
import { BaseExecutor } from "./base.js";
|
||||
import { PROVIDERS } from "../config/providers.js";
|
||||
import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
|
||||
import { ANTHROPIC_API_VERSION } from "../providers/shared.js";
|
||||
|
||||
// Models that use /zen/go/v1/messages (Anthropic/Claude format + x-api-key auth)
|
||||
const MESSAGES_FORMAT_MODELS = new Set([
|
||||
"minimax-m3",
|
||||
"minimax-m2.7",
|
||||
"minimax-m2.5",
|
||||
"qwen3.7-max",
|
||||
"qwen3.7-plus",
|
||||
"qwen3.6-plus",
|
||||
]);
|
||||
|
||||
const BASE = "https://opencode.ai/zen/go/v1";
|
||||
|
||||
export class OpenCodeGoExecutor extends BaseExecutor {
|
||||
constructor() {
|
||||
super("opencode-go", PROVIDERS["opencode-go"]);
|
||||
}
|
||||
|
||||
// buildUrl runs before buildHeaders in BaseExecutor.execute, cache model here
|
||||
buildUrl(model) {
|
||||
this._lastModel = model;
|
||||
return MESSAGES_FORMAT_MODELS.has(model)
|
||||
? `${BASE}/messages`
|
||||
: `${BASE}/chat/completions`;
|
||||
}
|
||||
|
||||
buildHeaders(credentials, stream = true) {
|
||||
const key = credentials?.apiKey || credentials?.accessToken;
|
||||
const headers = { "Content-Type": "application/json" };
|
||||
|
||||
if (MESSAGES_FORMAT_MODELS.has(this._lastModel)) {
|
||||
headers["x-api-key"] = key;
|
||||
headers["anthropic-version"] = ANTHROPIC_API_VERSION;
|
||||
} else {
|
||||
headers["Authorization"] = `Bearer ${key}`;
|
||||
}
|
||||
|
||||
if (stream) headers["Accept"] = "text/event-stream";
|
||||
return headers;
|
||||
}
|
||||
|
||||
transformRequest(model, body) {
|
||||
return injectReasoningContent({ provider: this.provider, model, body });
|
||||
}
|
||||
}
|
||||
@@ -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);
|
||||
|
||||
|
||||
@@ -38,3 +38,11 @@ export function modelStrip(model) {
|
||||
export function modelTargetFormat(model) {
|
||||
return model?.targetFormat || MODEL_DEFAULTS.targetFormat;
|
||||
}
|
||||
|
||||
// Per-model declared upstream formats (e.g. ["openai", "claude"]). Guards the
|
||||
// sourceFormat-matched transport for multi-endpoint providers whose models differ
|
||||
// in endpoint support (opencode-go: kimi/glm only do /chat/completions, minimax/qwen
|
||||
// also do /messages, deepseek also does /responses).
|
||||
export function modelSupportedFormats(model) {
|
||||
return model?.supportedFormats || null;
|
||||
}
|
||||
|
||||
@@ -22,20 +22,28 @@ export default {
|
||||
baseUrl: "https://opencode.ai/zen/go/v1/chat/completions",
|
||||
headers: {},
|
||||
},
|
||||
// Multi-endpoint: pick the transport matching the client sourceFormat to skip
|
||||
// translation. Guarded per-model by `supportedFormats` (see chatCore) because
|
||||
// opencode-go models differ in endpoint support.
|
||||
transports: [
|
||||
{ format: "openai", baseUrl: "https://opencode.ai/zen/go/v1/chat/completions", auth: { combined: true, header: "Authorization", scheme: "bearer" } },
|
||||
{ format: "claude", baseUrl: "https://opencode.ai/zen/go/v1/messages", auth: { combined: true, header: "x-api-key", scheme: "raw", anthropicVersion: true } },
|
||||
{ format: "openai-responses", baseUrl: "https://opencode.ai/zen/go/v1/responses", auth: { combined: true, header: "Authorization", scheme: "bearer" } },
|
||||
],
|
||||
models: [
|
||||
{ id: "glm-5.2", name: "GLM 5.2" },
|
||||
{ id: "glm-5.1", name: "GLM 5.1" },
|
||||
{ id: "kimi-k2.7-code", name: "Kimi K2.7 Code" },
|
||||
{ id: "kimi-k2.6", name: "Kimi K2.6" },
|
||||
{ id: "deepseek-v4-pro", name: "DeepSeek V4 Pro" },
|
||||
{ id: "deepseek-v4-flash", name: "DeepSeek V4 Flash" },
|
||||
{ id: "mimo-v2.5", name: "MiMo V2.5" },
|
||||
{ id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro" },
|
||||
{ id: "minimax-m3", name: "MiniMax M3", targetFormat: "claude" },
|
||||
{ id: "minimax-m2.7", name: "MiniMax M2.7", targetFormat: "claude" },
|
||||
{ id: "minimax-m2.5", name: "MiniMax M2.5", targetFormat: "claude" },
|
||||
{ id: "qwen3.7-max", name: "Qwen 3.7 Max", targetFormat: "claude" },
|
||||
{ id: "qwen3.7-plus", name: "Qwen 3.7 Plus", targetFormat: "claude" },
|
||||
{ id: "qwen3.6-plus", name: "Qwen 3.6 Plus", targetFormat: "claude" },
|
||||
{ id: "glm-5.2", name: "GLM 5.2", supportedFormats: ["openai"] },
|
||||
{ id: "glm-5.1", name: "GLM 5.1", supportedFormats: ["openai"] },
|
||||
{ id: "kimi-k2.7-code", name: "Kimi K2.7 Code", supportedFormats: ["openai"] },
|
||||
{ id: "kimi-k2.6", name: "Kimi K2.6", supportedFormats: ["openai"] },
|
||||
{ id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", supportedFormats: ["openai", "claude", "openai-responses"] },
|
||||
{ id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", supportedFormats: ["openai", "claude", "openai-responses"] },
|
||||
{ id: "mimo-v2.5", name: "MiMo V2.5", supportedFormats: ["openai"] },
|
||||
{ id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro", supportedFormats: ["openai"] },
|
||||
{ id: "minimax-m3", name: "MiniMax M3", supportedFormats: ["openai", "claude"] },
|
||||
{ id: "minimax-m2.7", name: "MiniMax M2.7", supportedFormats: ["openai", "claude"] },
|
||||
{ id: "minimax-m2.5", name: "MiniMax M2.5", supportedFormats: ["openai", "claude"] },
|
||||
{ id: "qwen3.7-max", name: "Qwen 3.7 Max", supportedFormats: ["openai", "claude"] },
|
||||
{ id: "qwen3.7-plus", name: "Qwen 3.7 Plus", supportedFormats: ["openai", "claude"] },
|
||||
{ id: "qwen3.6-plus", name: "Qwen 3.6 Plus", supportedFormats: ["openai", "claude"] },
|
||||
],
|
||||
};
|
||||
|
||||
@@ -1,71 +1,97 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { PROVIDER_MODELS, getModelTargetFormat } from "../../open-sse/config/providerModels.js";
|
||||
import { OpenCodeGoExecutor } from "../../open-sse/executors/opencode-go.js";
|
||||
import { PROVIDER_MODELS, getModelSupportedFormats } from "../../open-sse/config/providerModels.js";
|
||||
import { PROVIDERS } from "../../open-sse/config/providers.js";
|
||||
import { resolveTransport } from "../../open-sse/services/provider.js";
|
||||
|
||||
const CHAT_MODELS = [
|
||||
"glm-5.2",
|
||||
"glm-5.1",
|
||||
// OpenCode Go docs' endpoint table currently says kimi-k2.7, but its
|
||||
// config example and the live API use kimi-k2.7-code.
|
||||
"kimi-k2.7-code",
|
||||
"kimi-k2.6",
|
||||
"deepseek-v4-pro",
|
||||
"deepseek-v4-flash",
|
||||
"mimo-v2.5",
|
||||
"mimo-v2.5-pro",
|
||||
];
|
||||
// Chat-only models (no /messages, no /responses support on opencode-go)
|
||||
const CHAT_ONLY = ["glm-5.2", "glm-5.1", "kimi-k2.7-code", "kimi-k2.6", "mimo-v2.5", "mimo-v2.5-pro"];
|
||||
// Models that also expose the Anthropic /messages endpoint
|
||||
const CLAUDE_CAPABLE = ["minimax-m3", "minimax-m2.7", "minimax-m2.5", "qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus"];
|
||||
// Models that also expose the OpenAI /responses endpoint
|
||||
const RESPONSES_CAPABLE = ["deepseek-v4-pro", "deepseek-v4-flash"];
|
||||
|
||||
const MESSAGES_MODELS = [
|
||||
"minimax-m3",
|
||||
"minimax-m2.7",
|
||||
"minimax-m2.5",
|
||||
"qwen3.7-max",
|
||||
"qwen3.7-plus",
|
||||
"qwen3.6-plus",
|
||||
];
|
||||
// Mirror of chatCore's per-model transport guard: use the sourceFormat-matched
|
||||
// transport only when the model declares support for that sourceFormat.
|
||||
function pickTransport(provider, sourceFormat, alias, model) {
|
||||
const supported = getModelSupportedFormats(alias, model);
|
||||
const rt = resolveTransport(provider, sourceFormat);
|
||||
return supported?.includes(sourceFormat) ? rt : null;
|
||||
}
|
||||
|
||||
describe("OpenCode Go official model catalog", () => {
|
||||
it("matches the documented OpenCode Go model IDs", () => {
|
||||
const ids = (PROVIDER_MODELS["opencode-go"] || []).map((model) => model.id);
|
||||
|
||||
expect(ids).toEqual([...CHAT_MODELS, ...MESSAGES_MODELS]);
|
||||
describe("OpenCode Go model catalog", () => {
|
||||
it("matches the documented model IDs", () => {
|
||||
const ids = (PROVIDER_MODELS["opencode-go"] || []).map((m) => m.id);
|
||||
expect(ids).toEqual([
|
||||
"glm-5.2", "glm-5.1", "kimi-k2.7-code", "kimi-k2.6",
|
||||
"deepseek-v4-pro", "deepseek-v4-flash",
|
||||
"mimo-v2.5", "mimo-v2.5-pro",
|
||||
"minimax-m3", "minimax-m2.7", "minimax-m2.5",
|
||||
"qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus",
|
||||
]);
|
||||
});
|
||||
});
|
||||
|
||||
it("marks documented Qwen and MiniMax models as Anthropic messages format", () => {
|
||||
for (const model of MESSAGES_MODELS) {
|
||||
expect(getModelTargetFormat("opencode-go", model)).toBe("claude");
|
||||
describe("OpenCode Go per-model supportedFormats", () => {
|
||||
it("declares [openai, claude] for MiniMax + Qwen models", () => {
|
||||
for (const m of CLAUDE_CAPABLE) {
|
||||
expect(getModelSupportedFormats("opencode-go", m)).toEqual(["openai", "claude"]);
|
||||
}
|
||||
});
|
||||
|
||||
it("keeps GLM, Kimi, DeepSeek, and MiMo on OpenAI-compatible chat format", () => {
|
||||
for (const model of CHAT_MODELS) {
|
||||
expect(getModelTargetFormat("opencode-go", model)).toBeNull();
|
||||
it("declares [openai, claude, openai-responses] for DeepSeek models", () => {
|
||||
for (const m of RESPONSES_CAPABLE) {
|
||||
expect(getModelSupportedFormats("opencode-go", m)).toEqual(["openai", "claude", "openai-responses"]);
|
||||
}
|
||||
});
|
||||
|
||||
it("declares [openai] only for chat-only models (GLM/Kimi/MiMo) → guards /messages routing", () => {
|
||||
for (const m of CHAT_ONLY) {
|
||||
expect(getModelSupportedFormats("opencode-go", m)).toEqual(["openai"]);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("OpenCode Go endpoint routing", () => {
|
||||
it("routes Qwen and MiniMax models to the messages endpoint with x-api-key auth", () => {
|
||||
const executor = new OpenCodeGoExecutor();
|
||||
describe("OpenCode Go multi-endpoint transports", () => {
|
||||
it("declares openai / claude / openai-responses transports", () => {
|
||||
const formats = (PROVIDERS["opencode-go"].transports || []).map((t) => t.format);
|
||||
expect(formats).toEqual(["openai", "claude", "openai-responses"]);
|
||||
});
|
||||
|
||||
for (const model of MESSAGES_MODELS) {
|
||||
expect(executor.buildUrl(model)).toBe("https://opencode.ai/zen/go/v1/messages");
|
||||
const headers = executor.buildHeaders({ apiKey: "sk-test" }, false);
|
||||
expect(headers["x-api-key"]).toBe("sk-test");
|
||||
expect(headers["anthropic-version"]).toBeDefined();
|
||||
expect(headers.Authorization).toBeUndefined();
|
||||
it("resolveTransport picks the endpoint matching the client sourceFormat", () => {
|
||||
expect(resolveTransport("opencode-go", "claude").baseUrl).toBe("https://opencode.ai/zen/go/v1/messages");
|
||||
expect(resolveTransport("opencode-go", "openai-responses").baseUrl).toBe("https://opencode.ai/zen/go/v1/responses");
|
||||
expect(resolveTransport("opencode-go", "openai").baseUrl).toBe("https://opencode.ai/zen/go/v1/chat/completions");
|
||||
});
|
||||
|
||||
it("uses x-api-key + anthropicVersion on the claude transport", () => {
|
||||
const t = resolveTransport("opencode-go", "claude");
|
||||
expect(t.auth.header).toBe("x-api-key");
|
||||
expect(t.auth.anthropicVersion).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("OpenCode Go per-model transport guard (chatCore logic)", () => {
|
||||
it("routes MiniMax/Qwen + claude-format client to /messages", () => {
|
||||
for (const m of CLAUDE_CAPABLE) {
|
||||
expect(pickTransport("opencode-go", "claude", "opencode-go", m)?.baseUrl).toBe("https://opencode.ai/zen/go/v1/messages");
|
||||
}
|
||||
});
|
||||
|
||||
it("routes GLM, Kimi, DeepSeek, and MiMo models to chat/completions with bearer auth", () => {
|
||||
const executor = new OpenCodeGoExecutor();
|
||||
it("does NOT route chat-only models to /messages on a claude-format request", () => {
|
||||
for (const m of CHAT_ONLY) {
|
||||
expect(pickTransport("opencode-go", "claude", "opencode-go", m)).toBeNull();
|
||||
}
|
||||
});
|
||||
|
||||
for (const model of CHAT_MODELS) {
|
||||
expect(executor.buildUrl(model)).toBe("https://opencode.ai/zen/go/v1/chat/completions");
|
||||
const headers = executor.buildHeaders({ apiKey: "sk-test" }, false);
|
||||
expect(headers.Authorization).toBe("Bearer sk-test");
|
||||
expect(headers["x-api-key"]).toBeUndefined();
|
||||
expect(headers["anthropic-version"]).toBeUndefined();
|
||||
it("routes DeepSeek + responses-format client to /responses", () => {
|
||||
for (const m of RESPONSES_CAPABLE) {
|
||||
expect(pickTransport("opencode-go", "openai-responses", "opencode-go", m)?.baseUrl).toBe("https://opencode.ai/zen/go/v1/responses");
|
||||
}
|
||||
});
|
||||
|
||||
it("does NOT route MiniMax (no responses support) to /responses", () => {
|
||||
for (const m of CLAUDE_CAPABLE) {
|
||||
expect(pickTransport("opencode-go", "openai-responses", "opencode-go", m)).toBeNull();
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user