From db6bd03e0699357508d72b4effd2fce843585162 Mon Sep 17 00:00:00 2001
From: Aman Ganapathy <84686202+nams1570@users.noreply.github.com>
Date: Mon, 16 Mar 2026 15:35:53 -0700
Subject: [PATCH] [Chore][Fix]: Skip Failing CLI Tests, Rework Failing AI
 Endpoint Validation test (#1258)

### Context
In a [previous PR](https://github.com/stack-auth/stack-auth/pull/1258),
we hardcoded the mode to link because local emulator wasn't in a ready
state yet. Soon after, we started encountering three failing tests on
dev

The three cli tests that were failing on dev were failing because they
required the create mode flag to be set. The hardcode to link made the
create paths unreachable. Since we don't have local emulator working,
allowing users to pass in opts.mode would be bad practice- they'd be
triggering local emulator actions without the local emulator being set
up.

Also, there was a failing AI endpoint test. The unified AI endpoint
tests are set up so that if certain env variables are not present,
certain tests aren't run. In practice, if the openrouter key isn't set,
the tests that require actually processing a full AI endpoint result
without forwarding to prod will be skipped. The failing test was meant
to just check schema validation but it performed a full request instead.

### Summary of Changes
We just skip the tests for now. They'll only become relevant when
"create" is a legitimate workflow, which necessitates the function of
local emulator. There is no regression risk because the flow they're
testing isn't active yet, and so the only thing we could possibly test
is that passing the create mode will invoke a certain function which
isn't helpful at this state.

The unified AI endpoint failing test was reworked, another test
accomplishes the same schema validation effect. We don't lose coverage
by axing the failing test because other AI tests already test valid
request bodies (if they weren't valid, they wouldn't get a response).
---
 .../backend/endpoints/api/v1/ai-query.test.ts | 19 ++-----------------
 apps/e2e/tests/general/cli.test.ts            |  8 +++++---
 2 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/apps/e2e/tests/backend/endpoints/api/v1/ai-query.test.ts b/apps/e2e/tests/backend/endpoints/api/v1/ai-query.test.ts
index 14921e433..cb91d97b5 100644
--- a/apps/e2e/tests/backend/endpoints/api/v1/ai-query.test.ts
+++ b/apps/e2e/tests/backend/endpoints/api/v1/ai-query.test.ts
@@ -114,6 +114,8 @@ describe("AI Query Endpoint - Validation", () => {
   });
 
   it("rejects invalid tool names", async ({ expect }) => {
+    // Deterministic non-AI check: this payload is schema-valid, then rejected by
+    // route-level tool-name validation before any model/provider call.
     const response = await niceBackendFetch("/api/v1/ai/query/generate", {
       method: "POST",
       accessType: "admin",
@@ -196,23 +198,6 @@ describe("AI Query Endpoint - Validation", () => {
     expect(response.body).toMatchObject({ code: "SCHEMA_ERROR", error: expect.stringContaining("messages") });
   });
 
-  it("accepts valid request body with all required fields", async ({ expect }) => {
-    // This will forward to production, so we just verify it doesn't fail validation
-    const response = await niceBackendFetch("/api/v1/ai/query/generate", {
-      method: "POST",
-      accessType: "admin",
-      body: {
-        quality: "dumb",
-        speed: "fast",
-        tools: [],
-        systemPrompt: "command-center-ask-ai",
-        messages: [{ role: "user", content: "test" }],
-      },
-    });
-
-    expect(response.body).not.toMatchObject({ code: "SCHEMA_ERROR" });
-
-  }, 10000); // 60 seconds for AI API call
 });
 
 describeWithAi("AI Query Endpoint - Authentication", () => {
diff --git a/apps/e2e/tests/general/cli.test.ts b/apps/e2e/tests/general/cli.test.ts
index bb8a9ebbd..82d5a7ba1 100644
--- a/apps/e2e/tests/general/cli.test.ts
+++ b/apps/e2e/tests/general/cli.test.ts
@@ -348,7 +348,9 @@ describe("Stack CLI", () => {
 
   // --- init command tests ---
 
-  it("init create writes stack.config.ts with selected apps", async ({ expect }) => {
+  // TODO: Re-enable these create-mode tests once init mode handling is finalized.
+  // We keep these skipped (instead of todo) so the test logic remains visible and easy to re-enable.
+  it.skip("init create writes stack.config.ts with selected apps", async ({ expect }) => {
     const initDir = path.join(tmpDir, "init-create");
     fs.mkdirSync(initDir, { recursive: true });
 
@@ -367,7 +369,7 @@ describe("Stack CLI", () => {
     expect(parsed.apps.installed.teams).toEqual({ enabled: true });
   });
 
-  it("init create with single app", async ({ expect }) => {
+  it.skip("init create with single app", async ({ expect }) => {
     const initDir = path.join(tmpDir, "init-create-single");
     fs.mkdirSync(initDir, { recursive: true });
 
@@ -450,7 +452,7 @@ describe("Stack CLI", () => {
     expect(stderr).toContain("not found");
   });
 
-  it("init outputs setup instructions", async ({ expect }) => {
+  it.skip("init outputs setup instructions", async ({ expect }) => {
     const initDir = path.join(tmpDir, "init-instructions");
     fs.mkdirSync(initDir, { recursive: true });