text message process works

src/agentCore.jl

@@ -227,8 +227,11 @@ function _agentLoop(agent::yiemAgent)
             else  # _processMessage() done and no followUp message.
               agent.agentEventSink("_agentLoop 4 agent._state.messages length $(length(agent._state.messages))")
               result = agent._state.messages[end]
+              filtered_content = [c for c in result.content if !(c isa reasoningContent)]
               put!(agent.outputChannel, result)
-              agent.agentEventSink(result.content[1].text)
+              if !isempty(filtered_content) && filtered_content[1] isa textContent
+                agent.agentEventSink(filtered_content[1].text)
+              end
               processingTask = nothing        # reset
               newUserMsg = nothing            # reset
               result = nothing                # reset
@@ -381,7 +384,7 @@ function _processMessage(
     # Extract tool calls from LLM response content blocks
     hasToolCalls, toolCallList, assistant_msg = _extractToolCalls(response)
     agentEventSink("hasToolCalls: $hasToolCalls\ntoolCallList: $toolCallList _state.messages length $(length(agentMsgHistory))")
-    agentEventSink(string(assistant_msg))
+    agentEventSink("assistant_msg " * string(assistant_msg))
     agentEventSink("_processMessage 11-1")
 
     # Add assistant message (tool calls or text) to history for next LLM turn
@@ -406,6 +409,7 @@ function _processMessage(
 
       # save toolResults to messages
       for toolResult in toolResultBatch.messages
+        agentEventSink("toolResult " * string(toolResult))
         push!(agentMsgHistory, toolResult)
       end
       agentEventSink("_processMessage 14 _state.messages length $(length(agentMsgHistory))")
@@ -554,7 +558,9 @@ The message is constructed from:
   `(hasToolCalls, toolCallList, message)` where message is `assistantMessageToolCall`
   when tool calls exist, `assistantMessage` otherwise
 
-# Example response = JSON.Object{String, Any}("finish_reason" => "tool_calls", "index" => 0, "message" => JSON.Object{String, Any}("role" => "assistant", "content" => "", "reasoning_content" => "Here's a thinking process:\n\n1.  **Identify User Request**: The user is asking for the weather in Bangkok.\n2.  **Locate Relevant Tool**: I have a `getWeather` function available.\n3.  **Check Function Parameters**:\n   - `city` (required): City and country, e.g., 'San Francisco, CA' or 'Tokyo, Japan'\n   - `units` (optional, default \"celsius\"): Temperature scale (\"celsius\" or \"fahrenheit\")\n4.  **Prepare Parameters**:\n   - `city`: \"Bangkok, Thailand\" (adding country for clarity, though just \"Bangkok\" might work, following the example format is safer)\n   - `units`: Not specified, so I'll use the default (\"celsius\")\n5.  **Execute Tool Call**: Call `getWeather` with `city: \"Bangkok, Thailand\"`\n6.  **Anticipate Response**: The function will return current weather and forecast data for Bangkok. I'll then format it nicely for the user.\n   - *Self-Correction/Verification during thought*: The prompt says \"city: City and country, e.g., 'San Francisco, CA' or 'Tokyo, Japan'\". I'll use \"Bangkok, Thailand\". The `units` parameter is optional, so I'll omit it to use the default.\n   - Proceed with tool call.✅\n", "tool_calls" => Any[JSON.Object{String, Any}("type" => "function", "function" => JSON.Object{String, Any}("name" => "getWeather", "arguments" => "{\"city\":\"Bangkok, Thailand\"}"), "id" => "6fOilR5QPcdppbAAHluhkRyUDu3oWMAL")]))
+# Example
+  1)  llm_useTool = JSON.Object{String, Any}("finish_reason" => "tool_calls", "index" => 0, "message" => JSON.Object{String, Any}("role" => "assistant", "content" => "", "reasoning_content" => "Here's a thinking process:\n\n1.  **Identify User Request**: The user is asking for the weather in Bangkok.\n2.  **Locate Relevant Tool**: I have a `getWeather` function available.\n3.  **Check Function Parameters**:\n   - `city` (required): City and country, e.g., 'San Francisco, CA' or 'Tokyo, Japan'\n   - `units` (optional, default \"celsius\"): Temperature scale (\"celsius\" or \"fahrenheit\")\n4.  **Prepare Parameters**:\n   - `city`: \"Bangkok, Thailand\" (adding country for clarity, though just \"Bangkok\" might work, following the example format is safer)\n   - `units`: Not specified, so I'll use the default (\"celsius\")\n5.  **Execute Tool Call**: Call `getWeather` with `city: \"Bangkok, Thailand\"`\n6.  **Anticipate Response**: The function will return current weather and forecast data for Bangkok. I'll then format it nicely for the user.\n   - *Self-Correction/Verification during thought*: The prompt says \"city: City and country, e.g., 'San Francisco, CA' or 'Tokyo, Japan'\". I'll use \"Bangkok, Thailand\". The `units` parameter is optional, so I'll omit it to use the default.\n   - Proceed with tool call.✅\n", "tool_calls" => Any[JSON.Object{String, Any}("type" => "function", "function" => JSON.Object{String, Any}("name" => "getWeather", "arguments" => "{\"city\":\"Bangkok, Thailand\"}"), "id" => "6fOilR5QPcdppbAAHluhkRyUDu3oWMAL")]))
+  2)  llm_notUseTool = JSON.Object{String, Any}("finish_reason" => "stop", "index" => 0, "message" => JSON.Object{String, Any}("role" => "assistant", "content" => "The weather in London, UK is currently Sunny with a temperature of 22°C.", "reasoning_content" => "The user asked for the weather in London.\nI called the `getWeather` tool for London, UK.\nThe response indicates it's Sunny and 22°C.\nI will convey this information to the user.\n"))
 """
 function _extractToolCalls(response)
     hasToolCalls = false
@@ -642,14 +648,15 @@ function _extractToolCalls(response)
     end
     if reasoning_text isa String
         reasoning_text = reasoning_text
-    elseif reasoning_text isa textContent
+    elseif reasoning_text isa reasoningContent
         reasoning_text = reasoning_text.text
     else
         reasoning_text = ""
     end
-    reasoning_content = !isempty(reasoning_text) ? [textContent(reasoning_text)] : textContent[]
+    reasoning_content = !isempty(reasoning_text) ? [reasoningContent(reasoning_text)] : reasoningContent[]
 
     # Collect content blocks from response.content array (Format 2: OpenAI-style)
+    # or as a plain string (Format 1: LMStudio.jl non-tool-calls response)
     content_from_response = get(response, "content", nothing)
     content_blocks = Vector{messageContent}()
     if content_from_response isa Vector
@@ -662,12 +669,22 @@ function _extractToolCalls(response)
                 elseif get(block, "type", "") == "tool_calls"
                     # tool_calls blocks — don't add text content for these
                 elseif get(block, "type", "") == "reasoning"
-                    push!(content_blocks, textContent(get(block, "text", "")))
+                    push!(content_blocks, reasoningContent(get(block, "text", "")))
                 else
                     push!(content_blocks, textContent(get(block, "text", "")))
                 end
             end
         end
+    elseif content_from_response isa AbstractString && !isempty(content_from_response)
+        push!(content_blocks, textContent(content_from_response))
+    end
+
+    # Format 1 fallback: response["message"]["content"] as plain string
+    if isempty(content_blocks) && msg !== nothing && msg isa AbstractDict
+        msg_content = get(msg, "content", nothing)
+        if msg_content isa AbstractString && !isempty(msg_content)
+            push!(content_blocks, textContent(msg_content))
+        end
     end
 
     # Combine reasoning_content field + content array blocks, deduplicating reasoning

src/type.jl

@@ -4,8 +4,8 @@
            messageContent, agentMessage, agent,
            # Model types
            modelCost, llmModel, llmUsage,
-           # Message content types
+            # Message content types
-           textContent, imageContent,
+            textContent, imageContent, reasoningContent,
             # Message types
             userMessage, assistantMessageToolCall, assistantMessage, toolResultMessage,
             # Tool types
@@ -31,6 +31,13 @@ using GeneralUtils
 
 const Timestamp = DateTime
 
+struct agentToolCall               # A tool invocation from the LLM
+  type::String                              # Always "function"
+  id::String                                # Unique tool call identifier
+  name::String                              # Tool name
+  arguments::Dict{String, Any}              # Parsed tool arguments
+end
+
 # ------------------------------------------------------------------------------------------------ #
 #                                          LLM model info                                          #
 # ------------------------------------------------------------------------------------------------ #
@@ -75,6 +82,10 @@ struct imageContent <: messageContent         # Image message content
     mimeType::String                          # MIME type (e.g., "image/png")
 end
 
+struct reasoningContent <: messageContent    # LLM reasoning/thinking content
+    text::String                              # The reasoning text
+end
+
 
 # ------------------------------------------------------------------------------------------------ #
 #                                           Message types                                          #
@@ -404,14 +415,6 @@ function agentState(
 end
 
 
-struct agentToolCall               # A tool invocation from the LLM
-    type::String                              # Always "function"
-    id::String                                # Unique tool call identifier
-    name::String                              # Tool name
-    arguments::Dict{String, Any}              # Parsed tool arguments
-end
-
-
 """
 Context for preparing the next conversation turn.
 

test/_extractToolCalls.jl

@@ -44,7 +44,7 @@ import YiemAgent.agentCore: _extractToolCalls
         @test assistant_msg.role == "assistant"
         @test assistant_msg.stopReason == "tool_calls"
         @test length(assistant_msg.content) == 1
-        @test assistant_msg.content[1] isa textContent
+        @test assistant_msg.content[1] isa reasoningContent
         @test assistant_msg.content[1].text == "Let me check the weather."
     end
 
@@ -241,7 +241,9 @@ import YiemAgent.agentCore: _extractToolCalls
         @test has_toolcalls == false
         @test length(tc_list) == 0
         @test length(assistant_msg.content) == 2
+        @test assistant_msg.content[1] isa reasoningContent
         @test assistant_msg.content[1].text == "Thinking..."
+        @test assistant_msg.content[2] isa textContent
         @test assistant_msg.content[2].text == "Here's the answer."
     end
 
@@ -307,7 +309,9 @@ import YiemAgent.agentCore: _extractToolCalls
         )
         has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
         @test length(assistant_msg.content) == 2
+        @test assistant_msg.content[1] isa reasoningContent
         @test assistant_msg.content[1].text == "internal thought"
+        @test assistant_msg.content[2] isa textContent
         @test assistant_msg.content[2].text == "output"
     end