feat(zai): add Z.AI GLM Coding Plan provider preset (#896)

* feat(zai): add Z.AI GLM Coding Plan provider preset

Add dedicated Z.AI provider support for the GLM Coding Plan, enabling
use of GLM-5.1, GLM-5-Turbo, GLM-4.7, and GLM-4.5-Air models through
the OpenAI-compatible shim with proper thinking mode (reasoning_content),
max_tokens handling, and context window sizing.

* fix(zai): unify GLM max output token limits across casing variants

glm-5/glm-4.7 had conservative 16K max output while GLM-5/GLM-4.7
had 131K. Use consistent Z.AI coding plan limits for all GLM variants.

* fix(zai): restore DashScope GLM limits, enable GLM thinking support

- Restore lowercase glm-5/glm-4.7 to 16_384 max output (DashScope limits)
  while keeping Z.AI coding plan high limits on uppercase GLM-* keys only
- Add GLM model support to modelSupportsThinking() so reasoning_content
  is enabled when using GLM-5.x/GLM-4.7 models on Z.AI

* fix(zai): tighten GLM regexes, fix misleading context window comment

- Use precise regex in thinking.ts: exact GLM model matches only,
  no false positives on glm-50/glm-4, includes glm-4.5-air
- Use uppercase-only match in StartupScreen rawModel fallback so
  DashScope lowercase glm-* models aren't mislabeled as Z.AI
- Clarify context window comment: lowercase glm-5.1/glm-5-turbo/
  glm-4.5-air are Z.AI-specific aliases, not DashScope

* fix(zai): scope GLM detection to Z.AI

* improve readability of max_completion_tokens check

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

src/components/StartupScreen.test.ts

@@ -116,6 +116,11 @@ describe('detectProvider — direct vendor endpoints', () => {
     expect(detectProvider().name).toBe('Mistral')
   })
 
+  test('api.z.ai labels as Z.AI GLM', () => {
+    setupOpenAIMode('https://api.z.ai/api/coding/paas/v4', 'GLM-5.1')
+    expect(detectProvider().name).toBe('Z.AI - GLM')
+  })
+
   test('default OpenAI URL + gpt-4o labels as OpenAI', () => {
     setupOpenAIMode('https://api.openai.com/v1', 'gpt-4o')
     expect(detectProvider().name).toBe('OpenAI')
@@ -149,6 +154,21 @@ describe('detectProvider — rawModel fallback when URL is generic', () => {
     setupOpenAIMode('https://my-proxy.internal/v1', 'mistral-large-latest')
     expect(detectProvider().name).toBe('Mistral')
   })
+
+  test('custom proxy + exact uppercase GLM ID falls back to Z.AI GLM', () => {
+    setupOpenAIMode('https://my-proxy.internal/v1', 'GLM-5.1')
+    expect(detectProvider().name).toBe('Z.AI - GLM')
+  })
+
+  test('custom proxy + lowercase glm ID stays generic OpenAI', () => {
+    setupOpenAIMode('https://my-proxy.internal/v1', 'glm-5.1')
+    expect(detectProvider().name).toBe('OpenAI')
+  })
+
+  test('DashScope lowercase glm ID is not mislabeled as Z.AI', () => {
+    setupOpenAIMode('https://dashscope.aliyuncs.com/compatible-mode/v1', 'glm-5.1')
+    expect(detectProvider().name).toBe('OpenAI')
+  })
 })
 
 // --- Explicit env flags win over URL heuristics ---