diff --git a/CHANGELOG.md b/CHANGELOG.md
index 894a8113..a7d125ec 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,12 @@
 # Changelog
 
+## [4.7.2](https://github.com/CopilotC-Nvim/CopilotChat.nvim/compare/v4.7.1...v4.7.2) (2025-09-17)
+
+
+### Bug Fixes
+
+* **chat:** do not create multiple chat isntances ([#1432](https://github.com/CopilotC-Nvim/CopilotChat.nvim/issues/1432)) ([74611b5](https://github.com/CopilotC-Nvim/CopilotChat.nvim/commit/74611b56e813f50e905122387b92fb832ac9616c))
+
 ## [4.7.1](https://github.com/CopilotC-Nvim/CopilotChat.nvim/compare/v4.7.0...v4.7.1) (2025-09-16)
 
 
diff --git a/README.md b/README.md
index 9f1cda76..8da6be23 100644
--- a/README.md
+++ b/README.md
@@ -19,11 +19,12 @@ https://github.com/user-attachments/assets/8cad5643-63b2-4641-a5c4-68bc313f20e6
 CopilotChat.nvim brings GitHub Copilot Chat capabilities directly into Neovim with a focus on transparency and user control.
 
 - 🤖 **Multiple AI Models** - GitHub Copilot (including GPT-4o, Gemini 2.5 Pro, Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Sonnet, o3-mini, o4-mini) + custom providers (Ollama, Mistral.ai). The exact list of available models depends on your [GitHub Copilot settings](https://github.com/settings/copilot/features) and the models provided by GitHub's API.
-- 🔧 **Tool Calling** - LLM can use workspace functions (file reading, git operations, search) with your explicit approval
-- 🔒 **Explicit Control** - Only shares what you specifically request - no background data collection
-- 📝 **Interactive Chat** - Rich UI with completion, diffs, and quickfix integration
+- 🔧 **Tool Calling** - LLM can call workspace functions (file reading, git operations, search) with your explicit approval
+- 🔒 **Privacy First** - Only shares what you explicitly request - no background data collection
+- 📝 **Interactive Chat** - Interactive UI with completion, diffs, and quickfix integration
 - 🎯 **Smart Prompts** - Composable templates and sticky prompts for consistent context
-- ⚡ **Efficient** - Smart token usage with tiktoken counting and history management
+- ⚡ **Token Efficient** - Resource replacement prevents duplicate context, history management via tiktoken counting
+- 🔗 **Scriptable** - Comprehensive Lua API for automation and headless mode operation
 - 🔌 **Extensible** - [Custom functions](https://github.com/CopilotC-Nvim/CopilotChat.nvim/discussions/categories/functions) and [providers](https://github.com/CopilotC-Nvim/CopilotChat.nvim/discussions/categories/providers), plus integrations like [mcphub.nvim](https://github.com/ravitemer/mcphub.nvim)
 
 # Installation
diff --git a/doc/CopilotChat.txt b/doc/CopilotChat.txt
index bf35ba50..b86efef6 100644
--- a/doc/CopilotChat.txt
+++ b/doc/CopilotChat.txt
@@ -1,4 +1,4 @@
-*CopilotChat.txt*        For NVIM v0.8.0        Last change: 2025 September 16
+*CopilotChat.txt*        For NVIM v0.8.0        Last change: 2025 September 17
 
 ==============================================================================
 Table of Contents                              *CopilotChat-table-of-contents*
@@ -41,11 +41,12 @@ CopilotChat.nvim brings GitHub Copilot Chat capabilities directly into Neovim
 with a focus on transparency and user control.
 
 - 🤖 **Multiple AI Models** - GitHub Copilot (including GPT-4o, Gemini 2.5 Pro, Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Sonnet, o3-mini, o4-mini) + custom providers (Ollama, Mistral.ai). The exact list of available models depends on your GitHub Copilot settings <https://github.com/settings/copilot/features> and the models provided by GitHub’s API.
-- 🔧 **Tool Calling** - LLM can use workspace functions (file reading, git operations, search) with your explicit approval
-- 🔒 **Explicit Control** - Only shares what you specifically request - no background data collection
-- 📝 **Interactive Chat** - Rich UI with completion, diffs, and quickfix integration
+- 🔧 **Tool Calling** - LLM can call workspace functions (file reading, git operations, search) with your explicit approval
+- 🔒 **Privacy First** - Only shares what you explicitly request - no background data collection
+- 📝 **Interactive Chat** - Interactive UI with completion, diffs, and quickfix integration
 - 🎯 **Smart Prompts** - Composable templates and sticky prompts for consistent context
-- ⚡ **Efficient** - Smart token usage with tiktoken counting and history management
+- ⚡ **Token Efficient** - Resource replacement prevents duplicate context, history management via tiktoken counting
+- 🔗 **Scriptable** - Comprehensive Lua API for automation and headless mode operation
 - 🔌 **Extensible** - Custom functions <https://github.com/CopilotC-Nvim/CopilotChat.nvim/discussions/categories/functions> and providers <https://github.com/CopilotC-Nvim/CopilotChat.nvim/discussions/categories/providers>, plus integrations like mcphub.nvim <https://github.com/ravitemer/mcphub.nvim>
 
 
diff --git a/lua/CopilotChat/init.lua b/lua/CopilotChat/init.lua
index 98c1c1e6..268405bd 100644
--- a/lua/CopilotChat/init.lua
+++ b/lua/CopilotChat/init.lua
@@ -1100,41 +1100,41 @@ function M.setup(config)
   if M.chat then
     M.chat:close(state.source.bufnr)
     M.chat:delete()
-  end
-
-  M.chat = require('CopilotChat.ui.chat')(M.config, function(bufnr)
-    for name, _ in pairs(M.config.mappings) do
-      map_key(name, bufnr)
-    end
-
-    require('CopilotChat.completion').enable(bufnr, M.config.chat_autocomplete)
+  else
+    M.chat = require('CopilotChat.ui.chat')(M.config, function(bufnr)
+      for name, _ in pairs(M.config.mappings) do
+        map_key(name, bufnr)
+      end
 
-    vim.api.nvim_create_autocmd({ 'BufEnter', 'BufLeave' }, {
-      buffer = bufnr,
-      callback = function(ev)
-        if ev.event == 'BufEnter' then
-          update_source()
-        end
+      require('CopilotChat.completion').enable(bufnr, M.config.chat_autocomplete)
 
-        vim.schedule(function()
-          select.highlight(state.source.bufnr, not (M.config.highlight_selection and M.chat:focused()))
-        end)
-      end,
-    })
-
-    if M.config.insert_at_end then
-      vim.api.nvim_create_autocmd({ 'InsertEnter' }, {
+      vim.api.nvim_create_autocmd({ 'BufEnter', 'BufLeave' }, {
         buffer = bufnr,
-        callback = function()
-          vim.cmd('normal! 0')
-          vim.cmd('normal! G$')
-          vim.v.char = 'x'
+        callback = function(ev)
+          if ev.event == 'BufEnter' then
+            update_source()
+          end
+
+          vim.schedule(function()
+            select.highlight(state.source.bufnr, not (M.config.highlight_selection and M.chat:focused()))
+          end)
         end,
       })
-    end
 
-    finish(true)
-  end)
+      if M.config.insert_at_end then
+        vim.api.nvim_create_autocmd({ 'InsertEnter' }, {
+          buffer = bufnr,
+          callback = function()
+            vim.cmd('normal! 0')
+            vim.cmd('normal! G$')
+            vim.v.char = 'x'
+          end,
+        })
+      end
+
+      finish(true)
+    end)
+  end
 
   for name, prompt in pairs(list_prompts()) do
     if prompt.prompt then
diff --git a/lua/CopilotChat/ui/chat.lua b/lua/CopilotChat/ui/chat.lua
index 267b8aed..8cd08c11 100644
--- a/lua/CopilotChat/ui/chat.lua
+++ b/lua/CopilotChat/ui/chat.lua
@@ -164,7 +164,7 @@ local Chat = class(function(self, config, on_buf_create)
     if not msg or msg == '' then
       self.chat_overlay:restore(self.winnr, self.bufnr)
     else
-      self:overlay({ text = msg })
+      self.chat_overlay:show(msg, self.winnr)
     end
   end)
 end, Overlay)
diff --git a/version.txt b/version.txt
index 7c66fca5..af9764a5 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-4.7.1
+4.7.2