From 7004e4be929b3a627f86f92f13e336c41761d336 Mon Sep 17 00:00:00 2001
From: Meisterlala <6453306+Meisterlala@users.noreply.github.com>
Date: Sun, 7 Jun 2026 18:50:12 +0200
Subject: [PATCH] feat(ai-commit): streamline cold starts and enhance UI stream
 wrapping

Remove unnecessary dummy preloads to reduce API overhead; rely on cache health
checks before loading models. Add dynamic text line wrapping in spinner output
based on terminal width and support explicit request start notifications via
context callbacks.
---
 local/ai-commit/lua/ai-commit/generator.lua   |   5 +
 local/ai-commit/lua/ai-commit/providers.lua   |   6 ++
 local/ai-commit/lua/ai-commit/spinner.lua     | 100 +++++++++++++++++-
 local/ai-provider/lua/ai-provider/init.lua    |   2 +-
 .../lua/ai-provider/providers/ollama.lua      |  34 ++----
 5 files changed, 117 insertions(+), 30 deletions(-)

diff --git a/local/ai-commit/lua/ai-commit/generator.lua b/local/ai-commit/lua/ai-commit/generator.lua
index 8079f50..a8149d9 100644
--- a/local/ai-commit/lua/ai-commit/generator.lua
+++ b/local/ai-commit/lua/ai-commit/generator.lua
@@ -135,6 +135,11 @@ function M.insert()
         table.insert(http_jobs, job)
       end
     end,
+    on_request_start = function()
+      if not done and not aborted then
+        spinner_ui.start_stream_section(spinner)
+      end
+    end,
     on_chunk = function(chunk)
       if not done and not aborted then
         spinner_ui.append_stream(spinner, chunk)
diff --git a/local/ai-commit/lua/ai-commit/providers.lua b/local/ai-commit/lua/ai-commit/providers.lua
index df7a8f5..634ff5c 100644
--- a/local/ai-commit/lua/ai-commit/providers.lua
+++ b/local/ai-commit/lua/ai-commit/providers.lua
@@ -125,6 +125,8 @@ local function complete_ai_provider(source_id, full_prompt, callback, status_cal
       status_callback(action and (action .. ' with ' .. status_model) or ('Loading model ' .. status_model))
     elseif status.phase == 'loaded' then
       status_callback('Loaded model ' .. status_model)
+    elseif status.phase == 'context' then
+      status_callback('Loading prompt context with ' .. status_model)
     elseif status.phase == 'thinking' then
       local suffix = status.tokens_per_second and string.format(' (%.1f t/s)', status.tokens_per_second) or ''
       status_callback((action or 'Thinking') .. ' with ' .. status_model .. suffix)
@@ -136,6 +138,10 @@ local function complete_ai_provider(source_id, full_prompt, callback, status_cal
     end
   end
 
+  if request_context and request_context.on_request_start then
+    request_context.on_request_start(source_id, model)
+  end
+
   ai_provider.chat(provider, {
     source_id = source_id,
     model = model,
diff --git a/local/ai-commit/lua/ai-commit/spinner.lua b/local/ai-commit/lua/ai-commit/spinner.lua
index 15c0d87..362c920 100644
--- a/local/ai-commit/lua/ai-commit/spinner.lua
+++ b/local/ai-commit/lua/ai-commit/spinner.lua
@@ -6,6 +6,72 @@ local M = {}
 
 local frames = { '⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏' }
 
+local function preview_width(bufnr)
+  local win = vim.fn.bufwinid(bufnr)
+  if win ~= -1 then
+    return math.max(20, vim.api.nvim_win_get_width(win) - 4)
+  end
+  return 76
+end
+
+local function split_long_token(token, width)
+  local parts = {}
+  local current = ''
+  local index = 0
+  local length = vim.fn.strchars(token)
+
+  while index < length do
+    local char = vim.fn.strcharpart(token, index, 1)
+    if current ~= '' and vim.fn.strdisplaywidth(current .. char) > width then
+      table.insert(parts, current)
+      current = char
+    else
+      current = current .. char
+    end
+    index = index + 1
+  end
+
+  if current ~= '' then
+    table.insert(parts, current)
+  end
+  return parts
+end
+
+local function wrap_line(line, width)
+  if line == '' or vim.fn.strdisplaywidth(line) <= width then
+    return { line }
+  end
+
+  local wrapped = {}
+  local current = ''
+
+  for token in line:gmatch '%S+%s*' do
+    local candidate = current .. token
+    if current ~= '' and vim.fn.strdisplaywidth(candidate) > width then
+      table.insert(wrapped, (current:gsub('%s+$', '')))
+      current = token
+    else
+      current = candidate
+    end
+
+    if vim.fn.strdisplaywidth(current) > width then
+      local parts = split_long_token(current:gsub('%s+$', ''), width)
+      for index, part in ipairs(parts) do
+        if index < #parts then
+          table.insert(wrapped, part)
+        else
+          current = part
+        end
+      end
+    end
+  end
+
+  if current ~= '' then
+    table.insert(wrapped, (current:gsub('%s+$', '')))
+  end
+  return #wrapped > 0 and wrapped or { line }
+end
+
 local function stop_timer_safe(spinner)
   local timer = spinner and spinner.timer
   if not timer then
@@ -25,13 +91,26 @@ local function stop_timer_safe(spinner)
 end
 
 ---@param spinner table
+---@param bufnr integer
 ---@return table
-local function preview_virt_lines(spinner)
+local function preview_virt_lines(spinner, bufnr)
   local lines = {}
+  local width = preview_width(bufnr)
   for _, line in ipairs(spinner.stream_preview) do
-    table.insert(lines, { { line, 'Comment' } })
+    for _, wrapped in ipairs(wrap_line(line, width)) do
+      table.insert(lines, wrapped)
+    end
+  end
+
+  while #lines > (config.values.preview_lines or 5) do
+    table.remove(lines, 1)
   end
-  return lines
+
+  local virt_lines = {}
+  for _, line in ipairs(lines) do
+    table.insert(virt_lines, { { line, 'Comment' } })
+  end
+  return virt_lines
 end
 
 ---@param bufnr integer
@@ -77,7 +156,7 @@ function M.start(bufnr)
       virt_text = virt_text,
       virt_text_pos = 'eol',
     }
-    local virt_lines = preview_virt_lines(spinner)
+    local virt_lines = preview_virt_lines(spinner, bufnr)
     if #virt_lines > 0 then
       opts.virt_lines = virt_lines
       opts.virt_lines_above = false
@@ -113,11 +192,22 @@ function M.append_stream(spinner, text)
     spinner.stream_preview[#spinner.stream_preview] = (spinner.stream_preview[#spinner.stream_preview] or '') .. chunk
   end
 
-  while #spinner.stream_preview > (config.values.preview_lines or 5) do
+  while #spinner.stream_preview > 200 do
     table.remove(spinner.stream_preview, 1)
   end
 end
 
+---@param spinner table|nil
+function M.start_stream_section(spinner)
+  if not spinner or #spinner.stream_preview == 0 then
+    return
+  end
+
+  if spinner.stream_preview[#spinner.stream_preview] ~= '' then
+    table.insert(spinner.stream_preview, '')
+  end
+end
+
 ---@param spinner table|nil
 ---@param status_text string
 ---@param status_chunks table|nil
diff --git a/local/ai-provider/lua/ai-provider/init.lua b/local/ai-provider/lua/ai-provider/init.lua
index 1091783..a28607c 100644
--- a/local/ai-provider/lua/ai-provider/init.lua
+++ b/local/ai-provider/lua/ai-provider/init.lua
@@ -44,7 +44,7 @@
 
 ---@class AiProviderStatus
 ---@field provider string Provider name.
----@field phase string Standard phase, for example `loading`, `loaded`, `thinking`, `generating`, `done`, or `error`.
+---@field phase string Standard phase, for example `loading`, `loaded`, `context`, `thinking`, `generating`, `done`, or `error`.
 ---@field message string Human-readable status message.
 ---@field model? string Model/profile name.
 ---@field used_model? string Raw provider model name.
diff --git a/local/ai-provider/lua/ai-provider/providers/ollama.lua b/local/ai-provider/lua/ai-provider/providers/ollama.lua
index 8b7b60d..31f2c32 100644
--- a/local/ai-provider/lua/ai-provider/providers/ollama.lua
+++ b/local/ai-provider/lua/ai-provider/providers/ollama.lua
@@ -295,14 +295,7 @@ function M.chat(request)
         end
 
         if code ~= 0 then
-          log.error(
-            'ollama request process failed code='
-              .. tostring(code)
-              .. ' model='
-              .. tostring(raw_model)
-              .. ' error='
-              .. tostring(error_message)
-          )
+          log.error('ollama request process failed code=' .. tostring(code) .. ' model=' .. tostring(raw_model) .. ' error=' .. tostring(error_message))
           if request.callback then
             request.callback(nil, {
               requested_model = selected_model,
@@ -354,12 +347,12 @@ function M.chat(request)
           if request.callback then
             request.callback(nil, meta)
           end
-        emit_status {
-          phase = 'error',
-          message = provider_error,
-          tokens = metrics.eval_count,
-          tokens_per_second = tokens_per_second(metrics.eval_count, metrics.eval_duration),
-        }
+          emit_status {
+            phase = 'error',
+            message = provider_error,
+            tokens = metrics.eval_count,
+            tokens_per_second = tokens_per_second(metrics.eval_count, metrics.eval_duration),
+          }
           return
         end
         if done_reason == 'length' then
@@ -467,14 +460,7 @@ function M.chat(request)
 
         if response.status ~= 200 then
           local error_message = response.error or response.body or 'ollama preload failed'
-          log.error(
-            'ollama preload failed status='
-              .. tostring(response.status)
-              .. ' model='
-              .. tostring(raw_model)
-              .. ' error='
-              .. tostring(error_message)
-          )
+          log.error('ollama preload failed status=' .. tostring(response.status) .. ' model=' .. tostring(raw_model) .. ' error=' .. tostring(error_message))
           if request.callback then
             request.callback(nil, {
               requested_model = selected_model,
@@ -506,8 +492,8 @@ function M.chat(request)
           )
         )
         emit_status {
-          phase = 'generating',
-          message = 'Generating response',
+          phase = 'context',
+          message = 'Loading prompt context',
         }
         job = run_chat()
         if request.register_http_job then
-- 
2.51.2