fix: update provider request resolution to respect custom base URLs and adjust transport logic

Author: Meetpatel006

src/commands/provider/provider.test.tsx

@@ -264,7 +264,7 @@ test('buildCurrentProviderSummary labels generic local openai-compatible provide
   expect(summary.endpointLabel).toBe('http://127.0.0.1:8080/v1')
 })
 
-test('buildCurrentProviderSummary relabels local gpt-5.4 providers to Codex (via Codex transport)', () => {
+test('buildCurrentProviderSummary does not relabel local gpt-5.4 providers as Codex when custom base URL is set', () => {
   const summary = buildCurrentProviderSummary({
     processEnv: {
       CLAUDE_CODE_USE_OPENAI: '1',
@@ -274,9 +274,9 @@ test('buildCurrentProviderSummary relabels local gpt-5.4 providers to Codex (via
     persisted: null,
   })
 
-  expect(summary.providerLabel).toBe('Codex')
+  expect(summary.providerLabel).toBe('Local OpenAI-compatible')
   expect(summary.modelLabel).toBe('gpt-5.4')
-  expect(summary.endpointLabel).toBe('https://chatgpt.com/backend-api/codex')
+  expect(summary.endpointLabel).toBe('http://127.0.0.1:8080/v1')
 })
 
 test('buildCurrentProviderSummary recognizes GitHub Models mode', () => {

src/services/api/codexShim.test.ts

@@ -98,14 +98,14 @@ describe('Codex provider config', () => {
     expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
   })
 
-  test('forces Codex transport when a local non-Codex base URL is explicit', () => {
+  test('does not force Codex transport when a local non-Codex base URL is explicit', () => {
     const resolved = resolveProviderRequest({
       model: 'codexplan',
       baseUrl: 'http://127.0.0.1:8080/v1',
     })
 
-    expect(resolved.transport).toBe('codex_responses')
-    expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
+    expect(resolved.transport).toBe('chat_completions')
+    expect(resolved.baseUrl).toBe('http://127.0.0.1:8080/v1')
     expect(resolved.resolvedModel).toBe('gpt-5.4')
   })
 
@@ -151,14 +151,14 @@ describe('Codex provider config', () => {
     expect(resolved.resolvedModel).toBe('gpt-5.4')
   })
 
-  test('overrides custom base URL for codexplan (e.g., local provider)', () => {
+  test('does not override custom base URL for codexplan (e.g., local provider)', () => {
     process.env.OPENAI_MODEL = 'codexplan'
     process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
     delete process.env.CLAUDE_CODE_USE_GITHUB
 
     const resolved = resolveProviderRequest()
-    expect(resolved.transport).toBe('codex_responses')
-    expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
+    expect(resolved.transport).toBe('chat_completions')
+    expect(resolved.baseUrl).toBe('http://localhost:11434/v1')
   })
 
   test('loads Codex credentials from auth.json fallback', () => {

src/services/api/providerConfig.ts

@@ -395,8 +395,9 @@ export function resolveProviderRequest(options?: {
     descriptor.baseModel === envResolvedCodexModel
   const isCodexAliasModel =
     isOpenAICodexShortcutAlias(requestedModel) || requestedMatchesEnvCodexShortcut
+  const hasUserSetBaseUrl = rawBaseUrl && rawBaseUrl !== DEFAULT_OPENAI_BASE_URL
   const finalBaseUrl =
-    !isGithubMode && isCodexAliasModel
+    !isGithubMode && isCodexAliasModel && !hasUserSetBaseUrl
       ? DEFAULT_CODEX_BASE_URL
       : rawBaseUrl