update README and mcp

README.md

@@ -4,7 +4,15 @@
 
 # humanus.cpp
 
-Humanus (meaning "human" in Latin) is a lightweight framework inspired by [OpenManus](https://github.com/mannaandpoem/OpenManus) and [mem0](https://github.com/mem0ai/mem0), integrated with the Model Context Protocol (MCP). `humanus.cpp` enables more flexible tool choices, and provides a foundation for building powerful local LLM agents.
+Humanus (meaning "human" in Latin) is a **lightweight C++ framework** inspired by [OpenManus](https://github.com/mannaandpoem/OpenManus) and [mem0](https://github.com/mem0ai/mem0), integrated with the Model Context Protocol (MCP). 
+
+**Key Features:**
+- **C++ Implementation**: Core functionality written in efficient C++ for optimal performance and resource utilization
+- **Lightweight Design**: Minimalist architecture with minimal dependencies, suitable for resource-constrained environments
+- **Cross-platform Compatibility**: Full support for Unix, MacOS, and Windows systems
+- **MCP Protocol Integration**: Seamless integration with Model Context Protocol for standardized tool interactions
+- **Vectorized Memory Storage**: Efficient similarity search based on HNSW algorithm for intelligent context retrieval
+- **Modular Architecture**: Easy to extend and customize, supporting various LLM models and tool integrations
 
 Let's embrace local LLM agents **w/** humanus.cpp!
 
@@ -27,7 +35,7 @@ To set up your custom configuration, follow these steps:
 
 1. Copy all files from `config/example` to `config`.
 2. Replace `base_url`, `api_key`, .etc in `config/config_llm.toml` and other configurations in `config/config*.toml` according to your need.
-    > Note: `llama-server` in [llama.cpp](https://github.com/ggml-org/llama.cpp) also supports embedding models.
+    > Note: `llama-server` in [llama.cpp](https://github.com/ggml-org/llama.cpp) also supports embedding models for vectorized memory.
 3. Fill in `args` after `"@modelcontextprotocol/server-filesystem"` for `filesystem` to control the access to files. For example:
 ```
 [filesystem]
@@ -38,7 +46,6 @@ args = ["-y",
         "/Users/{Username}/Desktop",
         "other/path/to/your/files]
 ```
-4. Ensure all requirements for the MCP servers are installed. For example, run `npx playwright install` first for `playwright`.
 
 ### `mcp_server`
 
@@ -112,7 +119,6 @@ Configure it in Cursor:
 
 > What if add `humanus` to `mcp_servers`? It might be interesting.
 
-
 ## Acknowledgement
 
 <p align="center">

mcp

@@ -1 +1 @@
-Subproject commit 88237f2eaae1dc89b32d2a693ac2bd15fb6ad269
+Subproject commit 3c0a2a730ad9da3da61cd7a35ab8bbe5ff078c11

src/llm.cpp

@@ -315,8 +315,8 @@ json LLM::ask_tool(
     }
 
     // If the logger has a file sink, log the request body
-    if (logger->sinks().size() > 1) {
-        auto file_sink = std::dynamic_pointer_cast<spdlog::sinks::basic_file_sink_mt>(logger->sinks()[1]);
+    for (const auto& sink : logger->sinks()) {
+        auto file_sink = std::dynamic_pointer_cast<spdlog::sinks::basic_file_sink_mt>(sink);
         if (file_sink) {
             file_sink->log(spdlog::details::log_msg(
                 spdlog::source_loc{},
@@ -325,6 +325,24 @@ json LLM::ask_tool(
                 "Failed to get response from LLM. Full request body: " + body_str
             ));
         }
+        auto stderr_sink = std::dynamic_pointer_cast<spdlog::sinks::stderr_color_sink_mt>(sink);
+        if (stderr_sink) {
+            stderr_sink->log(spdlog::details::log_msg(
+                spdlog::source_loc{},
+                logger->name(),
+                spdlog::level::debug,
+                "Failed to get response from LLM. See log file for full request body."
+            ));
+        }
+        auto session_sink = std::dynamic_pointer_cast<SessionSink>(sink);
+        if (session_sink) {
+            session_sink->log(spdlog::details::log_msg(
+                spdlog::source_loc{},
+                logger->name(),
+                spdlog::level::debug,
+                "Failed to get response from LLM. See log file for full request body."
+            ));
+        }
     }
 
     throw std::runtime_error("Failed to get response from LLM");