feat: Display AI reasoning/thinking blocks in chat interface (#152)

* feat: Add reasoning/thinking blocks display in chat interface

* feat: add multi-provider options support and replace custom reasoning UI with AI Elements

* resolve conflicting reasoning configs and correct provider-specific reasoning parameters

* try to solve conflict

* fix: simplify reasoning display and remove unnecessary dependencies

- Remove Streamdown dependency (~5MB) - reasoning is plain text only
- Fix Bedrock providerOptions merging for Claude reasoning configs
- Remove unsupported DeepSeek reasoning configuration
- Clean up unused environment variables (REASONING_BUDGET_TOKENS, REASONING_EFFORT, DEEPSEEK_REASONING_*)
- Remove dead commented code from route.ts

Reasoning blocks contain plain thinking text and don't need markdown/diagram/code rendering.

* feat: comprehensive reasoning support improvements

Major improvements:
- Auto-enable reasoning display for all supported models
- Fix provider-specific reasoning configurations
- Remove unnecessary Streamdown dependency (~5MB)
- Clean up debug logging

Provider changes:
- OpenAI: Auto-enable reasoningSummary for o1/o3/gpt-5 models
- Google: Auto-enable includeThoughts for Gemini 2.5/3 models
- Bedrock: Restrict reasoningConfig to only Claude/Nova (fixes MiniMax error)
- Ollama: Add thinking support for qwen3-like models

Other improvements:
- Remove ENABLE_REASONING toggle (always enabled)
- Fix Bedrock providerOptions merging for Claude
- Simplify reasoning component (plain text rendering)
- Clean up unused environment variables

* fix: critical bugs and documentation gaps in reasoning support

Critical fixes:
- Fix Bedrock shallow merge bug (deep merge preserves anthropicBeta + reasoningConfig)
- Add parseInt validation with parseIntSafe helper (prevents NaN errors)
- Validate all numeric env vars with min/max ranges

Documentation improvements:
- Add BEDROCK_REASONING_BUDGET_TOKENS and BEDROCK_REASONING_EFFORT to env.example
- Add OLLAMA_ENABLE_THINKING to env.example
- Update JSDoc with accurate env var list and ranges

Code cleanup:
- Remove debug console.log statements from route.ts
- Refactor duplicate providerOptions assignments

---------

Co-authored-by: Dayuan Jiang <34411969+DayuanJiang@users.noreply.github.com>
Co-authored-by: Dayuan Jiang <jdy.toh@gmail.com>

app/api/chat/route.ts

@@ -208,13 +208,6 @@ async function handleChatRequest(req: Request): Promise<Response> {
     const isFirstMessage = messages.length === 1
     const isEmptyDiagram = !xml || xml.trim() === "" || isMinimalDiagram(xml)
 
-    // DEBUG: Log cache check conditions
-    console.log("[Cache DEBUG] messages.length:", messages.length)
-    console.log("[Cache DEBUG] isFirstMessage:", isFirstMessage)
-    console.log("[Cache DEBUG] xml length:", xml?.length || 0)
-    console.log("[Cache DEBUG] xml preview:", xml?.substring(0, 200))
-    console.log("[Cache DEBUG] isEmptyDiagram:", isEmptyDiagram)
-
     if (isFirstMessage && isEmptyDiagram) {
         const lastMessage = messages[0]
         const textPart = lastMessage.parts?.find((p: any) => p.type === "text")
@@ -358,7 +351,7 @@ ${lastMessageText}
         model,
         stopWhen: stepCountIs(5),
         messages: allMessages,
-        ...(providerOptions && { providerOptions }),
+        ...(providerOptions && { providerOptions }), // This now includes all reasoning configs
         ...(headers && { headers }),
         // Langfuse telemetry config (returns undefined if not configured)
         ...(getTelemetryConfig({ sessionId: validSessionId, userId }) && {
@@ -394,13 +387,6 @@ ${lastMessageText}
             return null
         },
         onFinish: ({ text, usage }) => {
-            // Log token usage
-            if (usage) {
-                const cachedTokens = (usage as any).cachedInputTokens ?? 0
-                console.log(
-                    `[Token Usage] input: ${usage.inputTokens ?? 0}, cached: ${cachedTokens}, output: ${usage.outputTokens ?? 0}, total: ${(usage.inputTokens ?? 0) + cachedTokens + (usage.outputTokens ?? 0)}`,
-                )
-            }
             // Pass usage to Langfuse (Bedrock streaming doesn't auto-report tokens to telemetry)
             setTraceOutput(text, {
                 promptTokens: usage?.inputTokens,
@@ -488,6 +474,7 @@ IMPORTANT: Keep edits concise:
     })
 
     return result.toUIMessageStreamResponse({
+        sendReasoning: true,
         messageMetadata: ({ part }) => {
             if (part.type === "finish") {
                 const usage = (part as any).totalUsage