Merge pull request #534 from diegosouzapw/release/v2.9.5

chore(release): v2.9.5 — OpenCode providers, embedding fix, CLI masked key fix

CHANGELOG.md

@@ -4,6 +4,24 @@
 
 ---
 
+## [2.9.5] — 2026-03-22
+
+> Sprint: New OpenCode providers, embedding credentials fix, CLI masked key bug, CACHE_TAG_PATTERN fix.
+
+### 🐛 Bug Fixes
+
+- **CLI tools save masked API key to config files** — `claude-settings`, `cline-settings`, and `openclaw-settings` POST routes now accept a `keyId` param and resolve the real API key from DB before writing to disk. `ClaudeToolCard` updated to send `keyId` instead of the masked display string. Fixes #523, #526.
+- **Custom embedding providers: `No credentials` error** — `/v1/embeddings` now tracks `credentialsProviderId` separately from the routing prefix, so credentials are fetched from the matching provider node ID rather than the public prefix string. Fixes a regression where `google/gemini-embedding-001` and similar custom-provider models would always fail with a credentials error. Fixes #532-related. (PR #528 by @jacob2826)
+- **Context cache protection regex misses `\n` prefix** — `CACHE_TAG_PATTERN` in `comboAgentMiddleware.ts` updated to match both literal `\n` (backslash-n) and actual newline U+000A that `combo.ts` streaming injects around the `<omniModel>` tag after fix #515. Fixes #531.
+
+### ✨ New Providers
+
+- **OpenCode Zen** — Free tier gateway at `opencode.ai/zen/v1` with 3 models: `minimax-m2.5-free`, `big-pickle`, `gpt-5-nano`
+- **OpenCode Go** — Subscription service at `opencode.ai/zen/go/v1` with 4 models: `glm-5`, `kimi-k2.5`, `minimax-m2.7` (Claude format), `minimax-m2.5` (Claude format)
+- Both providers use the new `OpencodeExecutor` which routes dynamically to `/chat/completions`, `/messages`, `/responses`, or `/models/{model}:generateContent` based on the requested model. (PR #530 by @kang-heewon)
+
+---
+
 ## [2.9.4] — 2026-03-21
 
 > Sprint: Bug fixes — preserve Codex prompt cache key, fix tagContent JSON escaping, sync expired token status to DB.

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 2.9.4
+  version: 2.9.5
   description: |
     OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
     endpoint that routes requests to multiple AI providers with load balancing,

open-sse/config/embeddingRegistry.ts

@@ -17,6 +17,7 @@ export interface EmbeddingProvider {
 }
 
 export interface EmbeddingProviderNodeRow {
+  id?: string;
   prefix: string;
   name: string;
   baseUrl: string;

open-sse/config/providerRegistry.ts

@@ -495,6 +495,39 @@ export const REGISTRY: Record<string, RegistryEntry> = {
     ],
   },
 
+  "opencode-go": {
+    id: "opencode-go",
+    alias: "opencode-go",
+    format: "openai",
+    executor: "opencode",
+    baseUrl: "https://opencode.ai/zen/go/v1",
+    authType: "apikey",
+    authHeader: "Authorization",
+    authPrefix: "Bearer",
+    models: [
+      { id: "glm-5", name: "GLM-5" },
+      { id: "kimi-k2.5", name: "Kimi K2.5" },
+      { id: "minimax-m2.7", name: "MiniMax M2.7", targetFormat: "claude" },
+      { id: "minimax-m2.5", name: "MiniMax M2.5", targetFormat: "claude" },
+    ],
+  },
+
+  "opencode-zen": {
+    id: "opencode-zen",
+    alias: "opencode-zen",
+    format: "openai",
+    executor: "opencode",
+    baseUrl: "https://opencode.ai/zen/v1",
+    authType: "apikey",
+    authHeader: "Authorization",
+    authPrefix: "Bearer",
+    models: [
+      { id: "minimax-m2.5-free", name: "MiniMax M2.5 Free" },
+      { id: "big-pickle", name: "Big Pickle" },
+      { id: "gpt-5-nano", name: "GPT 5 Nano" },
+    ],
+  },
+
   openrouter: {
     id: "openrouter",
     alias: "openrouter",

open-sse/executors/index.ts

@@ -8,6 +8,7 @@ import { CursorExecutor } from "./cursor.ts";
 import { DefaultExecutor } from "./default.ts";
 import { PollinationsExecutor } from "./pollinations.ts";
 import { CloudflareAIExecutor } from "./cloudflare-ai.ts";
+import { OpencodeExecutor } from "./opencode.ts";
 
 const executors = {
   antigravity: new AntigravityExecutor(),
@@ -22,6 +23,8 @@ const executors = {
   pol: new PollinationsExecutor(), // Alias
   "cloudflare-ai": new CloudflareAIExecutor(),
   cf: new CloudflareAIExecutor(), // Alias
+  "opencode-zen": new OpencodeExecutor("opencode-zen"),
+  "opencode-go": new OpencodeExecutor("opencode-go"),
 };
 
 const defaultCache = new Map();
@@ -47,3 +50,4 @@ export { CursorExecutor } from "./cursor.ts";
 export { DefaultExecutor } from "./default.ts";
 export { PollinationsExecutor } from "./pollinations.ts";
 export { CloudflareAIExecutor } from "./cloudflare-ai.ts";
+export { OpencodeExecutor } from "./opencode.ts";

open-sse/executors/opencode.ts

@@ -0,0 +1,61 @@
+import { BaseExecutor, type ExecuteInput, type ProviderCredentials } from "./base.ts";
+import { PROVIDERS } from "../config/constants.ts";
+import { getModelTargetFormat } from "../config/providerModels.ts";
+
+export class OpencodeExecutor extends BaseExecutor {
+  _requestFormat: string | null = null;
+
+  constructor(provider: string) {
+    super(provider, PROVIDERS[provider] || PROVIDERS.openai);
+  }
+
+  async execute(input: ExecuteInput) {
+    this._requestFormat = getModelTargetFormat(this.provider, input.model) || "openai";
+    try {
+      return await super.execute(input);
+    } finally {
+      this._requestFormat = null;
+    }
+  }
+
+  buildUrl(
+    model: string,
+    stream: boolean,
+    urlIndex = 0,
+    credentials: ProviderCredentials | null = null
+  ) {
+    void urlIndex;
+    void credentials;
+
+    const base = this.config.baseUrl;
+    switch (this._requestFormat) {
+      case "claude":
+        return `${base}/messages`;
+      case "openai-responses":
+        return `${base}/responses`;
+      case "gemini":
+        return `${base}/models/${model}:${stream ? "streamGenerateContent?alt=sse" : "generateContent"}`;
+      default:
+        return `${base}/chat/completions`;
+    }
+  }
+
+  buildHeaders(credentials: ProviderCredentials | null, stream = true) {
+    const headers: Record<string, string> = { "Content-Type": "application/json" };
+    const key = credentials?.apiKey || credentials?.accessToken;
+
+    if (key) {
+      headers["Authorization"] = `Bearer ${key}`;
+    }
+
+    if (this._requestFormat === "claude") {
+      headers["anthropic-version"] = "2023-06-01";
+    }
+
+    if (stream) {
+      headers["Accept"] = "text/event-stream";
+    }
+
+    return headers;
+  }
+}

open-sse/services/comboAgentMiddleware.ts

@@ -34,7 +34,11 @@ interface Message {
 
 // ── Context Caching Tag ─────────────────────────────────────────────────────
 
-const CACHE_TAG_PATTERN = /<omniModel>([^<]+)<\/omniModel>/;
+// Handles both actual newlines (U+000A) and literal \n sequences injected
+// by combo.ts streaming around the <omniModel> tag (#531). Non-global so that
+// .exec() and .test() stay stateless; callers that need full replacement use
+// String.prototype.replace() which replaces all non-overlapping matches.
+const CACHE_TAG_PATTERN = /(?:\\n|\n)?<omniModel>([^<]+)<\/omniModel>(?:\\n|\n)?/;
 
 /**
  * Inject the model tag into the last assistant message (or append a new one).

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "2.9.4",
+  "version": "2.9.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "2.9.4",
+      "version": "2.9.5",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.9.4",
+  "version": "2.9.5",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/app/(dashboard)/dashboard/cli-tools/components/ClaudeToolCard.tsx

@@ -58,8 +58,10 @@ export default function ClaudeToolCard({
   const effectiveConfigStatus = configStatus || batchStatus?.configStatus || null;
 
   useEffect(() => {
+    // (#523) Store the key *id* (not the masked string) so the backend can
+    // resolve the real secret from DB before writing to settings.json.
     if (apiKeys?.length > 0 && !selectedApiKey) {
-      setSelectedApiKey(apiKeys[0].key);
+      setSelectedApiKey(apiKeys[0].id);
     }
   }, [apiKeys, selectedApiKey]);
 
@@ -95,10 +97,11 @@ export default function ClaudeToolCard({
           }
         }
       });
-      // Only set selectedApiKey if it exists in apiKeys list
+      // Restore selected key from file: match token stored in file against known keys
       const tokenFromFile = env.ANTHROPIC_AUTH_TOKEN;
-      if (tokenFromFile && apiKeys?.some((k) => k.key === tokenFromFile)) {
-        setSelectedApiKey(tokenFromFile);
+      if (tokenFromFile) {
+        const matchedKey = apiKeys?.find((k) => k.key === tokenFromFile);
+        if (matchedKey) setSelectedApiKey(matchedKey.id);
       }
     }
   }, [claudeStatus, apiKeys, tool.defaultModels, onModelMappingChange]);
@@ -132,24 +135,27 @@ export default function ClaudeToolCard({
     try {
       const env: any = { ANTHROPIC_BASE_URL: getEffectiveBaseUrl() };
 
-      // Get key from dropdown, fallback to first key or sk_omniroute for localhost
-      const keyToUse =
-        selectedApiKey?.trim() ||
-        (apiKeys?.length > 0 ? apiKeys[0].key : null) ||
-        (!cloudEnabled ? "sk_omniroute" : null);
+      // (#523) Prefer keyId lookup so the backend writes the real key to disk.
+      // Fall back to sk_omniroute for localhost-only setups without a key.
+      const selectedKeyId = selectedApiKey?.trim() || (apiKeys?.length > 0 ? apiKeys[0].id : null);
+      const skOmnirouteFallback = !cloudEnabled ? "sk_omniroute" : null;
 
-      if (keyToUse) {
-        env.ANTHROPIC_AUTH_TOKEN = keyToUse;
+      if (!selectedKeyId && skOmnirouteFallback) {
+        env.ANTHROPIC_AUTH_TOKEN = skOmnirouteFallback;
       }
 
       tool.defaultModels.forEach((model) => {
         const targetModel = modelMappings[model.alias];
         if (targetModel && model.envKey) env[model.envKey] = targetModel;
       });
+
+      const postBody: Record<string, unknown> = { env };
+      if (selectedKeyId) postBody.keyId = selectedKeyId;
+
       const res = await fetch("/api/cli-tools/claude-settings", {
         method: "POST",
         headers: { "Content-Type": "application/json" },
-        body: JSON.stringify({ env }),
+        body: JSON.stringify(postBody),
       });
       const data = await res.json();
       if (res.ok) {
@@ -412,7 +418,7 @@ export default function ClaudeToolCard({
                       className="flex-1 px-2 py-1.5 bg-surface rounded text-xs border border-border focus:outline-none focus:ring-1 focus:ring-primary/50"
                     >
                       {apiKeys.map((key) => (
-                        <option key={key.id} value={key.key}>
+                        <option key={key.id} value={key.id}>
                           {key.key}
                         </option>
                       ))}

src/app/api/cli-tools/claude-settings/route.ts

@@ -12,6 +12,7 @@ import { createBackup } from "@/shared/services/backupService";
 import { saveCliToolLastConfigured, deleteCliToolLastConfigured } from "@/lib/db/cliToolState";
 import { cliSettingsEnvSchema } from "@/shared/validation/schemas";
 import { isValidationFailure, validateBody } from "@/shared/validation/helpers";
+import { getApiKeyById } from "@/lib/localDb";
 
 // Get claude settings path based on OS
 const getClaudeSettingsPath = () => getCliPrimaryConfigPath("claude");
@@ -100,6 +101,22 @@ export async function POST(request: Request) {
     }
     const { env } = validation.data;
 
+    // (#523/#526) If a keyId was provided, resolve the real API key from DB.
+    // The /api/keys list endpoint returns masked key strings — sending those to
+    // disk would save an unusable half-hidden token. Resolving by ID guarantees
+    // we always write the full key value to the config file.
+    const keyId = typeof rawBody?.keyId === "string" ? rawBody.keyId.trim() : null;
+    if (keyId) {
+      try {
+        const keyRecord = await getApiKeyById(keyId);
+        if (keyRecord?.key) {
+          env.ANTHROPIC_AUTH_TOKEN = keyRecord.key as string;
+        }
+      } catch {
+        // Non-critical: fall back to whatever value was in env (e.g. sk_omniroute)
+      }
+    }
+
     const settingsPath = getClaudeSettingsPath();
     const claudeDir = path.dirname(settingsPath);
 

src/app/api/cli-tools/cline-settings/route.ts

@@ -9,6 +9,7 @@ import { createBackup } from "@/shared/services/backupService";
 import { saveCliToolLastConfigured, deleteCliToolLastConfigured } from "@/lib/db/cliToolState";
 import { cliModelConfigSchema } from "@/shared/validation/schemas";
 import { isValidationFailure, validateBody } from "@/shared/validation/helpers";
+import { getApiKeyById } from "@/lib/localDb";
 
 const CLINE_DATA_DIR = path.join(os.homedir(), ".cline", "data");
 const GLOBAL_STATE_PATH = path.join(CLINE_DATA_DIR, "globalState.json");
@@ -125,7 +126,18 @@ export async function POST(request: Request) {
     if (isValidationFailure(validation)) {
       return NextResponse.json({ error: validation.error }, { status: 400 });
     }
-    const { baseUrl, apiKey, model } = validation.data;
+    let { baseUrl, apiKey, model } = validation.data;
+
+    // (#526) Resolve real key from DB if keyId was provided
+    const keyId = typeof rawBody?.keyId === "string" ? rawBody.keyId.trim() : null;
+    if (keyId) {
+      try {
+        const keyRecord = await getApiKeyById(keyId);
+        if (keyRecord?.key) apiKey = keyRecord.key as string;
+      } catch {
+        /* non-critical */
+      }
+    }
 
     // Ensure directory exists
     await fs.mkdir(CLINE_DATA_DIR, { recursive: true });

src/app/api/cli-tools/openclaw-settings/route.ts

@@ -12,6 +12,7 @@ import { createBackup } from "@/shared/services/backupService";
 import { saveCliToolLastConfigured, deleteCliToolLastConfigured } from "@/lib/db/cliToolState";
 import { cliModelConfigSchema } from "@/shared/validation/schemas";
 import { isValidationFailure, validateBody } from "@/shared/validation/helpers";
+import { getApiKeyById } from "@/lib/localDb";
 
 const getOpenClawSettingsPath = () => getCliPrimaryConfigPath("openclaw");
 const getOpenClawDir = () => path.dirname(getOpenClawSettingsPath());
@@ -101,7 +102,18 @@ export async function POST(request: Request) {
     if (isValidationFailure(validation)) {
       return NextResponse.json({ error: validation.error }, { status: 400 });
     }
-    const { baseUrl, apiKey, model } = validation.data;
+    let { baseUrl, apiKey, model } = validation.data;
+
+    // (#526) Resolve real key from DB if keyId was provided
+    const keyId = typeof rawBody?.keyId === "string" ? rawBody.keyId.trim() : null;
+    if (keyId) {
+      try {
+        const keyRecord = await getApiKeyById(keyId);
+        if (keyRecord?.key) apiKey = keyRecord.key as string;
+      } catch {
+        /* non-critical */
+      }
+    }
 
     const openclawDir = getOpenClawDir();
     const settingsPath = getOpenClawSettingsPath();

src/app/api/v1/embeddings/route.ts

@@ -160,6 +160,7 @@ export async function POST(request) {
   // Resolve provider config — dynamic first (local override), then hardcoded
   let providerConfig: EmbeddingProvider | null =
     dynamicProviders.find((dp) => dp.id === provider) || getEmbeddingProvider(provider) || null;
+  let credentialsProviderId = provider;
 
   // #496: Fallback — resolve from ALL provider_nodes (not just localhost)
   // This enables custom embedding models (e.g. google/gemini-embedding-001) whose
@@ -180,6 +181,7 @@ export async function POST(request) {
           authHeader: "bearer",
           models: [],
         };
+        credentialsProviderId = matchingNode.id || provider;
         log.info(
           "EMBED",
           `Resolved custom embedding provider: ${provider} → ${providerConfig.baseUrl}`
@@ -200,7 +202,7 @@ export async function POST(request) {
   // Get credentials — skip for local providers (authType: "none")
   let credentials = null;
   if (providerConfig && providerConfig.authType !== "none") {
-    credentials = await getProviderCredentials(provider);
+    credentials = await getProviderCredentials(credentialsProviderId);
     if (!credentials) {
       return errorResponse(
         HTTP_STATUS.BAD_REQUEST,

src/shared/constants/providers.ts

@@ -496,6 +496,22 @@ export const APIKEY_PROVIDERS = {
     website: "https://tavily.com",
     authHint: "API key from app.tavily.com (format: tvly-...)",
   },
+  "opencode-zen": {
+    id: "opencode-zen",
+    alias: "opencode-zen",
+    name: "OpenCode Zen",
+    icon: "opencode",
+    color: "#6366f1",
+    website: "https://opencode.ai/zen",
+  },
+  "opencode-go": {
+    id: "opencode-go",
+    alias: "opencode-go",
+    name: "OpenCode Go",
+    icon: "opencode",
+    color: "#6366f1",
+    website: "https://opencode.ai/zen/go",
+  },
   alibaba: {
     id: "alibaba",
     alias: "ali",

tests/unit/auth-clear-provider-routes.test.mjs

@@ -106,3 +106,60 @@ test("embeddings route clears stale provider error metadata on success", async (
     globalThis.fetch = originalFetch;
   }
 });
+
+test("embeddings route uses provider node id for compatible provider credentials", async () => {
+  await resetStorage();
+
+  const providerNode = await providersDb.createProviderNode({
+    id: "openai-compatible-responses-google-embeddings",
+    type: "openai-compatible",
+    name: "Gemini Embeddings",
+    prefix: "google",
+    apiType: "responses",
+    baseUrl: "https://generativelanguage.googleapis.com/v1beta/openai",
+  });
+
+  const created = await providersDb.createProviderConnection({
+    provider: providerNode.id,
+    authType: "apikey",
+    email: null,
+    name: "google-compatible-key",
+    apiKey: "google-compatible-test-key",
+    testStatus: "active",
+    lastError: null,
+    lastErrorType: "token_refresh_failed",
+    lastErrorSource: "oauth",
+    errorCode: "refresh_failed",
+    rateLimitedUntil: null,
+    backoffLevel: 2,
+  });
+
+  const originalFetch = globalThis.fetch;
+  globalThis.fetch = async (url, init) => {
+    assert.equal(url, "https://generativelanguage.googleapis.com/v1beta/openai/embeddings");
+    assert.equal(init?.headers?.Authorization, "Bearer google-compatible-test-key");
+    return Response.json({
+      data: [{ object: "embedding", index: 0, embedding: [0.1, 0.2] }],
+      usage: { prompt_tokens: 3, total_tokens: 3 },
+    });
+  };
+
+  try {
+    const request = new Request("http://localhost/v1/embeddings", {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ model: "google/gemini-embedding-001", input: "hello" }),
+    });
+
+    const response = await embeddingsRoute.POST(request);
+    assert.equal(response.status, 200);
+
+    const updated = await readConnection(created.id);
+    assert.equal(updated.testStatus, "active");
+    assert.equal(updated.errorCode, undefined);
+    assert.equal(updated.lastErrorType, undefined);
+    assert.equal(updated.lastErrorSource, undefined);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});

tests/unit/opencode-executor.test.mjs

@@ -0,0 +1,189 @@
+import { afterEach, beforeEach, describe, it } from "node:test";
+import assert from "node:assert/strict";
+
+const { OpencodeExecutor } = await import("../../open-sse/executors/opencode.ts");
+const { PROVIDER_MODELS } = await import("../../open-sse/config/providerModels.ts");
+
+function createMockResponse() {
+  return new Response(JSON.stringify({ ok: true }), {
+    status: 200,
+    headers: { "Content-Type": "application/json" },
+  });
+}
+
+function createInput(model, stream = true, credentials = { apiKey: "test-key" }) {
+  return {
+    model,
+    stream,
+    credentials,
+    body: {
+      model,
+      stream,
+      messages: [{ role: "user", content: "hello" }],
+    },
+  };
+}
+
+function registerModel(provider, model) {
+  PROVIDER_MODELS[provider] = [...(PROVIDER_MODELS[provider] || []), model];
+}
+
+describe("OpencodeExecutor", () => {
+  let zenExecutor;
+  let goExecutor;
+  let fetchCalls;
+  let originalFetch;
+  let originalZenModels;
+  let originalGoModels;
+
+  beforeEach(() => {
+    zenExecutor = new OpencodeExecutor("opencode-zen");
+    goExecutor = new OpencodeExecutor("opencode-go");
+    fetchCalls = [];
+    originalFetch = globalThis.fetch;
+    originalZenModels = [...(PROVIDER_MODELS["opencode-zen"] || [])];
+    originalGoModels = [...(PROVIDER_MODELS["opencode-go"] || [])];
+    globalThis.fetch = async (url, options) => {
+      fetchCalls.push({ url, options });
+      return createMockResponse();
+    };
+  });
+
+  afterEach(() => {
+    globalThis.fetch = originalFetch;
+    PROVIDER_MODELS["opencode-zen"] = originalZenModels;
+    PROVIDER_MODELS["opencode-go"] = originalGoModels;
+  });
+
+  describe("execute", () => {
+    it("routes opencode zen default models to chat completions", async () => {
+      const minimaxResult = await zenExecutor.execute(createInput("minimax-m2.5-free"));
+      assert.equal(minimaxResult.url, "https://opencode.ai/zen/v1/chat/completions");
+      assert.equal(fetchCalls[0].url, "https://opencode.ai/zen/v1/chat/completions");
+
+      const pickleResult = await zenExecutor.execute(createInput("big-pickle"));
+      assert.equal(pickleResult.url, "https://opencode.ai/zen/v1/chat/completions");
+      assert.equal(fetchCalls[1].url, "https://opencode.ai/zen/v1/chat/completions");
+
+      const nanoResult = await zenExecutor.execute(createInput("gpt-5-nano"));
+      assert.equal(nanoResult.url, "https://opencode.ai/zen/v1/chat/completions");
+      assert.equal(fetchCalls[2].url, "https://opencode.ai/zen/v1/chat/completions");
+    });
+
+    it("routes claude target format models to messages endpoint", async () => {
+      const m27Result = await goExecutor.execute(
+        createInput("minimax-m2.7", true, { apiKey: "claude-key" })
+      );
+      assert.equal(m27Result.url, "https://opencode.ai/zen/go/v1/messages");
+      assert.equal(fetchCalls[0].url, "https://opencode.ai/zen/go/v1/messages");
+      assert.equal(m27Result.headers["anthropic-version"], "2023-06-01");
+
+      const m25Result = await goExecutor.execute(
+        createInput("minimax-m2.5", true, { apiKey: "claude-key" })
+      );
+      assert.equal(m25Result.url, "https://opencode.ai/zen/go/v1/messages");
+      assert.equal(fetchCalls[1].url, "https://opencode.ai/zen/go/v1/messages");
+      assert.equal(m25Result.headers["anthropic-version"], "2023-06-01");
+    });
+
+    it("routes openai responses target format models to responses endpoint", async () => {
+      registerModel("opencode-zen", {
+        id: "gpt-5-responses",
+        name: "GPT 5 Responses",
+        targetFormat: "openai-responses",
+      });
+
+      const result = await zenExecutor.execute(createInput("gpt-5-responses"));
+
+      assert.equal(result.url, "https://opencode.ai/zen/v1/responses");
+      assert.equal(fetchCalls[0].url, "https://opencode.ai/zen/v1/responses");
+    });
+
+    it("routes gemini streaming requests to streamGenerateContent", async () => {
+      registerModel("opencode-zen", {
+        id: "gemini-2.5-pro",
+        name: "Gemini 2.5 Pro",
+        targetFormat: "gemini",
+      });
+
+      const result = await zenExecutor.execute(createInput("gemini-2.5-pro"));
+
+      assert.equal(
+        result.url,
+        "https://opencode.ai/zen/v1/models/gemini-2.5-pro:streamGenerateContent?alt=sse"
+      );
+      assert.equal(
+        fetchCalls[0].url,
+        "https://opencode.ai/zen/v1/models/gemini-2.5-pro:streamGenerateContent?alt=sse"
+      );
+    });
+
+    it("routes gemini non streaming requests to generateContent", async () => {
+      registerModel("opencode-zen", {
+        id: "gemini-2.5-pro",
+        name: "Gemini 2.5 Pro",
+        targetFormat: "gemini",
+      });
+
+      const result = await zenExecutor.execute(createInput("gemini-2.5-pro", false));
+
+      assert.equal(result.url, "https://opencode.ai/zen/v1/models/gemini-2.5-pro:generateContent");
+      assert.equal(
+        fetchCalls[0].url,
+        "https://opencode.ai/zen/v1/models/gemini-2.5-pro:generateContent"
+      );
+    });
+
+    it("falls back to chat completions for unknown models", async () => {
+      const result = await zenExecutor.execute(createInput("unknown-model"));
+
+      assert.equal(result.url, "https://opencode.ai/zen/v1/chat/completions");
+      assert.equal(fetchCalls[0].url, "https://opencode.ai/zen/v1/chat/completions");
+    });
+
+    it("builds default headers for standard models", async () => {
+      const result = await zenExecutor.execute(createInput("gpt-5-nano"));
+
+      assert.deepEqual(result.headers, {
+        Authorization: "Bearer test-key",
+        "Content-Type": "application/json",
+        Accept: "text/event-stream",
+      });
+      assert.deepEqual(fetchCalls[0].options.headers, result.headers);
+    });
+
+    it("adds anthropic version for claude target format", async () => {
+      const result = await goExecutor.execute(
+        createInput("minimax-m2.7", true, { apiKey: "claude-key" })
+      );
+
+      assert.deepEqual(result.headers, {
+        Authorization: "Bearer claude-key",
+        "Content-Type": "application/json",
+        "anthropic-version": "2023-06-01",
+        Accept: "text/event-stream",
+      });
+      assert.deepEqual(fetchCalls[0].options.headers, result.headers);
+    });
+
+    it("omits accept header when stream is false", async () => {
+      const result = await zenExecutor.execute(createInput("big-pickle", false));
+
+      assert.deepEqual(result.headers, {
+        Authorization: "Bearer test-key",
+        "Content-Type": "application/json",
+      });
+      assert.deepEqual(fetchCalls[0].options.headers, result.headers);
+    });
+
+    it("omits authorization when credentials are missing", async () => {
+      const result = await zenExecutor.execute(createInput("minimax-m2.5-free", true, null));
+
+      assert.deepEqual(result.headers, {
+        "Content-Type": "application/json",
+        Accept: "text/event-stream",
+      });
+      assert.deepEqual(fetchCalls[0].options.headers, result.headers);
+    });
+  });
+});