Python: Improve DevUI, add Context Inspector view as new tab under traces (#2742)

* Improve DevUI, add Context Inspector view as new tab under traces

* fix mypy errors

* fix: Handle stale MCP connections in DevUI executor

MCP tools can become stale when HTTP streaming responses end - the underlying
stdio streams close but `is_connected` remains True. This causes subsequent
requests to fail with `ClosedResourceError`.

Add `_ensure_mcp_connections()` to detect and reconnect stale MCP tools before
agent execution. This is a workaround for an upstream Agent Framework issue
where connection state isn't properly tracked.

Fixes MCP tools failing on second HTTP request in DevUI.

fixes  #1476 #1515 #2865

* fix #1572 report import dependency errors more clearly

* Ensure there is streaming toggle where users can select streaming vs non streaming mode in devui . Fixes .NET: [Python] DevUI tool call rendering in non-streaming mode?

* remove unused dead code

* improve ux - workflows with agents show a chat component in execution timelien, also ensure magentic final output shows correctly

* update ui build

* update devui to use instrumentation instead of tracing, other instrumentation and type/instance check fixes

python/packages/devui/frontend/src/services/api.ts

@@ -398,7 +398,11 @@ class ApiClient {
   async listConversationItems(
     conversationId: string,
     options?: { limit?: number; after?: string; order?: "asc" | "desc" }
-  ): Promise<{ data: unknown[]; has_more: boolean }> {
+  ): Promise<{
+    data: unknown[];
+    has_more: boolean;
+    metadata?: { traces?: unknown[] };
+  }> {
     const params = new URLSearchParams();
     if (options?.limit) params.set("limit", options.limit.toString());
     if (options?.after) params.set("after", options.after);
@@ -409,7 +413,11 @@ class ApiClient {
       queryString ? `?${queryString}` : ""
     }`;
 
-    return this.request<{ data: unknown[]; has_more: boolean }>(url);
+    return this.request<{
+      data: unknown[];
+      has_more: boolean;
+      metadata?: { traces?: unknown[] };
+    }>(url);
   }
 
   async getConversationItem(
@@ -800,34 +808,68 @@ class ApiClient {
     yield* this.streamOpenAIResponse(openAIRequest, request.conversation_id, signal);
   }
 
-  // REMOVED: Legacy streaming methods - use streamAgentExecutionOpenAI and streamWorkflowExecutionOpenAI instead
+  // ========================================
+  // Non-Streaming Execution Methods
+  // ========================================
 
-  // Non-streaming execution (for testing)
-  async runAgent(
+  // Non-streaming agent execution using /v1/responses with stream=false
+  async runAgentSync(
     agentId: string,
     request: RunAgentRequest
-  ): Promise<{
-    conversation_id: string;
-    result: unknown[];
-    message_count: number;
-  }> {
-    return this.request(`/agents/${agentId}/run`, {
+  ): Promise<import("@/types/openai").OpenAIResponse> {
+    // Check if OAI proxy mode is enabled
+    const { oaiMode } = await import("@/stores").then((m) => ({
+      oaiMode: m.useDevUIStore.getState().oaiMode,
+    }));
+
+    const openAIRequest: AgentFrameworkRequest = {
+      metadata: { entity_id: agentId },
+      input: request.input,
+      stream: false,
+      conversation: request.conversation_id,
+    };
+
+    // Apply OAI mode settings if enabled
+    if (oaiMode.enabled) {
+      openAIRequest.model = oaiMode.model;
+      if (oaiMode.temperature !== undefined) {
+        openAIRequest.temperature = oaiMode.temperature;
+      }
+      if (oaiMode.max_output_tokens !== undefined) {
+        openAIRequest.max_output_tokens = oaiMode.max_output_tokens;
+      }
+    }
+
+    const headers: Record<string, string> = {};
+    if (oaiMode.enabled) {
+      headers["X-Proxy-Backend"] = "openai";
+    }
+
+    return this.request<import("@/types/openai").OpenAIResponse>("/v1/responses", {
       method: "POST",
-      body: JSON.stringify(request),
+      headers,
+      body: JSON.stringify(openAIRequest),
     });
   }
 
-  async runWorkflow(
+  // Non-streaming workflow execution using /v1/responses with stream=false
+  async runWorkflowSync(
     workflowId: string,
     request: RunWorkflowRequest
-  ): Promise<{
-    result: string;
-    events: number;
-    message_count: number;
-  }> {
-    return this.request(`/workflows/${workflowId}/run`, {
+  ): Promise<import("@/types/openai").OpenAIResponse> {
+    const openAIRequest: AgentFrameworkRequest = {
+      metadata: { entity_id: workflowId },
+      input: JSON.stringify(request.input_data || {}),
+      stream: false,
+      conversation: request.conversation_id,
+      extra_body: request.checkpoint_id
+        ? { entity_id: workflowId, checkpoint_id: request.checkpoint_id }
+        : undefined,
+    };
+
+    return this.request<import("@/types/openai").OpenAIResponse>("/v1/responses", {
       method: "POST",
-      body: JSON.stringify(request),
+      body: JSON.stringify(openAIRequest),
     });
   }