Update LLM providers and constants (#1937)

- Updated constants in app/lib/.server/llm/constants.ts
- Modified stream-text functionality in app/lib/.server/llm/stream-text.ts
- Updated Anthropic provider in app/lib/modules/llm/providers/anthropic.ts
- Modified GitHub provider in app/lib/modules/llm/providers/github.ts
- Updated Google provider in app/lib/modules/llm/providers/google.ts
- Modified OpenAI provider in app/lib/modules/llm/providers/openai.ts
- Updated LLM types in app/lib/modules/llm/types.ts
- Modified API route in app/routes/api.llmcall.ts

app/lib/.server/llm/constants.ts

@@ -4,6 +4,44 @@
  */
 export const MAX_TOKENS = 32000;
 
+/*
+ * Provider-specific default completion token limits
+ * Used as fallbacks when model doesn't specify maxCompletionTokens
+ */
+export const PROVIDER_COMPLETION_LIMITS: Record<string, number> = {
+  OpenAI: 16384,
+  Github: 16384, // GitHub Models use OpenAI-compatible limits
+  Anthropic: 128000,
+  Google: 32768,
+  Cohere: 4000,
+  DeepSeek: 8192,
+  Groq: 8192,
+  HuggingFace: 4096,
+  Mistral: 8192,
+  Ollama: 8192,
+  OpenRouter: 8192,
+  Perplexity: 8192,
+  Together: 8192,
+  xAI: 8192,
+  LMStudio: 8192,
+  OpenAILike: 8192,
+  AmazonBedrock: 8192,
+  Hyperbolic: 8192,
+};
+
+/*
+ * Reasoning models that require maxCompletionTokens instead of maxTokens
+ * These models use internal reasoning tokens and have different API parameter requirements
+ */
+export function isReasoningModel(modelName: string): boolean {
+  const result = /^(o1|o3|gpt-5)/i.test(modelName);
+
+  // DEBUG: Test regex matching
+  console.log(`REGEX TEST: "${modelName}" matches reasoning pattern: ${result}`);
+
+  return result;
+}
+
 // limits the number of model responses that can be returned in a single request
 export const MAX_RESPONSE_SEGMENTS = 2;