console_agent 0.7.0 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 662ece5e5732e350b22871c8029421edf06ed4d9f98183f5cee7e95a3c1099f6
-  data.tar.gz: 483642598de39d23ace26f5d90863a8712b8799357c7809b2ba770f2bdc2522a
+  metadata.gz: fdcfb3c48b2f8421b2187980a453b80324e6dec40ab80e8e55aa1a938355c79c
+  data.tar.gz: 12fec02740fde7a87bb81e26dd6857263c96f9ebe5a8402040c72279e882e31f
 SHA512:
-  metadata.gz: 5095d8f4cb0706e84c81be1b4a859de6ac48336ccb9c950feeb0dcf0df676d78fddc53a2314a21cbe6ee9d79b808f5edf0d854f3262b72c5befbb4420d9b979b
-  data.tar.gz: 4c96f0e1664c1357cc7ec3f53aada9d1dcf4e05cbc92e19edfd052b2e99c75d1596d5a49440b8b9478fd576140b36929589a87e009dd971b4599cfa8ab149520
+  metadata.gz: 7af9a3c4fdbdf71abb7452d8e6747ba2b22c64cd08d123b761c5ca7ebb870c3ba9a01e458defe0308dcbf9435ec71879f7f3562503defdfd54e2026d3069679d
+  data.tar.gz: c84e401d6b6f5c6c7840b5d701d3a0e653ba3ea46651141ae5101b2c93bdca35487566786a87e284dbba97f902c5dad597a00b8dc9fce6e1c01885b01e99a48d

data/README.md

@@ -77,15 +77,21 @@ end
 | `/auto` | Toggle auto-execute (skip confirmations) |
 | `/compact` | Compress history into a summary (saves tokens) |
 | `/usage` | Show token stats |
+| `/cost` | Show per-model cost breakdown |
+| `/think` | Upgrade to thinking model (Opus) for the rest of the session |
 | `/debug` | Toggle raw API output |
 | `/name <label>` | Name the session for easy resume |
 
 Prefix input with `>` to run Ruby directly (no LLM round-trip). The result is added to conversation context.
 
+Say "think harder" in any query to auto-upgrade to the thinking model for that session. After 5+ tool rounds, you'll also be prompted to switch.
+
 ## Features
 
 - **Tool use** — AI introspects your schema, models, files, and code to write accurate queries
 - **Multi-step plans** — complex tasks are broken into steps, executed sequentially with `step1`/`step2` references
+- **Two-tier models** — defaults to Sonnet for speed/cost; `/think` upgrades to Opus when you need it
+- **Cost tracking** — `/cost` shows per-model token usage and estimated spend
 - **Memories** — AI saves what it learns about your app across sessions
 - **App guide** — `ai_init` generates a guide injected into every system prompt
 - **Sessions** — name, list, and resume interactive conversations (`ai_setup` to enable)
@@ -98,9 +104,43 @@ ConsoleAgent.configure do |config|
   config.provider = :anthropic       # or :openai
   config.auto_execute = false         # true to skip confirmations
   config.session_logging = true       # requires ai_setup
+  config.model = 'claude-sonnet-4-6'  # model used by /think (default)
+  config.thinking_model = 'claude-opus-4-6'  # model used by /think (default)
+end
+```
+
+The default model is `claude-sonnet-4-6` (Anthropic) or `gpt-5.3-codex` (OpenAI). The thinking model defaults to `claude-opus-4-6` and is activated via `/think` or by saying "think harder".
+
+## Web UI Authentication
+
+The engine mounts a session viewer at `/console_agent`. By default it's open — you can protect it with basic auth or a custom authentication function.
+
+### Basic Auth
+
+```ruby
+ConsoleAgent.configure do |config|
+  config.admin_username = 'admin'
+  config.admin_password = ENV['CONSOLE_AGENT_PASSWORD']
 end
 ```
 
+### Custom Authentication
+
+For apps with their own auth system, pass a proc to `authenticate`. It runs in the controller context, so you have access to `session`, `request`, `redirect_to`, etc.
+
+```ruby
+ConsoleAgent.configure do |config|
+  config.authenticate = proc {
+    user = User.find_by(id: session[:user_id])
+    unless user&.admin?
+      redirect_to '/login'
+    end
+  }
+end
+```
+
+When `authenticate` is set, `admin_username` / `admin_password` are ignored.
+
 ## Requirements
 
 Ruby >= 2.5, Rails >= 5.0, Faraday >= 1.0

data/app/controllers/console_agent/application_controller.rb

@@ -2,19 +2,23 @@ module ConsoleAgent
   class ApplicationController < ActionController::Base
     protect_from_forgery with: :exception
 
-    before_action :authenticate!
+    before_action :console_agent_authenticate!
 
     private
 
-    def authenticate!
-      username = ConsoleAgent.configuration.admin_username
-      password = ConsoleAgent.configuration.admin_password
+    def console_agent_authenticate!
+      if (auth = ConsoleAgent.configuration.authenticate)
+        instance_exec(&auth)
+      else
+        username = ConsoleAgent.configuration.admin_username
+        password = ConsoleAgent.configuration.admin_password
 
-      return unless username && password
+        return unless username && password
 
-      authenticate_or_request_with_http_basic('ConsoleAgent Admin') do |u, p|
-        ActiveSupport::SecurityUtils.secure_compare(u, username) &
-          ActiveSupport::SecurityUtils.secure_compare(p, password)
+        authenticate_or_request_with_http_basic('ConsoleAgent Admin') do |u, p|
+          ActiveSupport::SecurityUtils.secure_compare(u, username) &
+            ActiveSupport::SecurityUtils.secure_compare(p, password)
+        end
       end
     end
   end

data/lib/console_agent/configuration.rb

@@ -2,29 +2,44 @@ module ConsoleAgent
   class Configuration
     PROVIDERS = %i[anthropic openai].freeze
 
-    attr_accessor :provider, :api_key, :model, :max_tokens,
+    PRICING = {
+      'claude-sonnet-4-6' => { input: 3.0 / 1_000_000, output: 15.0 / 1_000_000 },
+      'claude-opus-4-6'   => { input: 15.0 / 1_000_000, output: 75.0 / 1_000_000 },
+      'claude-haiku-4-5-20251001' => { input: 0.80 / 1_000_000, output: 4.0 / 1_000_000 },
+    }.freeze
+
+    DEFAULT_MAX_TOKENS = {
+      'claude-sonnet-4-6' => 16_000,
+      'claude-haiku-4-5-20251001' => 16_000,
+      'claude-opus-4-6'   => 4_096,
+    }.freeze
+
+    attr_accessor :provider, :api_key, :model, :thinking_model, :max_tokens,
                   :auto_execute, :temperature,
                   :timeout, :debug, :max_tool_rounds,
                   :storage_adapter, :memories_enabled,
                   :session_logging, :connection_class,
-                  :admin_username, :admin_password
+                  :admin_username, :admin_password,
+                  :authenticate
 
     def initialize
       @provider     = :anthropic
       @api_key      = nil
       @model        = nil
-      @max_tokens   = 4096
+      @thinking_model = nil
+      @max_tokens   = nil
       @auto_execute = false
       @temperature  = 0.2
       @timeout      = 30
       @debug        = false
-      @max_tool_rounds = 100
+      @max_tool_rounds = 200
       @storage_adapter  = nil
       @memories_enabled = true
       @session_logging  = true
       @connection_class = nil
       @admin_username   = nil
       @admin_password   = nil
+      @authenticate     = nil
     end
 
     def resolved_api_key
@@ -41,6 +56,23 @@ module ConsoleAgent
     def resolved_model
       return @model if @model && !@model.empty?
 
+      case @provider
+      when :anthropic
+        'claude-sonnet-4-6'
+      when :openai
+        'gpt-5.3-codex'
+      end
+    end
+
+    def resolved_max_tokens
+      return @max_tokens if @max_tokens
+
+      DEFAULT_MAX_TOKENS.fetch(resolved_model, 4096)
+    end
+
+    def resolved_thinking_model
+      return @thinking_model if @thinking_model && !@thinking_model.empty?
+
       case @provider
       when :anthropic
         'claude-opus-4-6'

data/lib/console_agent/providers/anthropic.rb

@@ -50,7 +50,7 @@ module ConsoleAgent
 
         body = {
           model: config.resolved_model,
-          max_tokens: config.max_tokens,
+          max_tokens: config.resolved_max_tokens,
           temperature: config.temperature,
           messages: format_messages(messages)
         }

data/lib/console_agent/providers/openai.rb

@@ -50,7 +50,7 @@ module ConsoleAgent
 
         body = {
           model: config.resolved_model,
-          max_tokens: config.max_tokens,
+          max_tokens: config.resolved_max_tokens,
           temperature: config.temperature,
           messages: formatted
         }

data/lib/console_agent/repl.rb

@@ -11,6 +11,7 @@ module ConsoleAgent
       @history = []
       @total_input_tokens = 0
       @total_output_tokens = 0
+      @token_usage = Hash.new { |h, k| h[k] = { input: 0, output: 0 } }
       @input_history = []
     end
 
@@ -209,6 +210,7 @@ module ConsoleAgent
       @history = []
       @total_input_tokens = 0
       @total_output_tokens = 0
+      @token_usage = Hash.new { |h, k| h[k] = { input: 0, output: 0 } }
       @interactive_query = nil
       @interactive_session_id = nil
       @interactive_session_name = nil
@@ -224,7 +226,7 @@ module ConsoleAgent
       name_display = @interactive_session_name ? " (#{@interactive_session_name})" : ""
       # Write banner to real stdout (bypass TeeIO) so it doesn't accumulate on resume
       @interactive_old_stdout.puts "\e[36mConsoleAgent interactive mode#{name_display}. Type 'exit' or 'quit' to leave.\e[0m"
-      @interactive_old_stdout.puts "\e[2m  Auto-execute: #{auto ? 'ON' : 'OFF'} (Shift-Tab or /auto to toggle) | > code to run directly | /usage | /compact | /name <label>\e[0m"
+      @interactive_old_stdout.puts "\e[2m  Auto-execute: #{auto ? 'ON' : 'OFF'} (Shift-Tab or /auto to toggle) | > code | /usage | /cost | /compact | /think | /name <label>\e[0m"
 
       # Bind Shift-Tab to insert /auto command and submit
       if Readline.respond_to?(:parse_and_bind)
@@ -263,6 +265,16 @@ module ConsoleAgent
           next
         end
 
+        if input == '/cost'
+          display_cost_summary
+          next
+        end
+
+        if input == '/think'
+          upgrade_to_thinking_model
+          next
+        end
+
         if input.start_with?('/name')
           name = input.sub('/name', '').strip
           if name.empty?
@@ -314,6 +326,11 @@ module ConsoleAgent
         # Add to Readline history (avoid consecutive duplicates)
         Readline::HISTORY.push(input) unless input == Readline::HISTORY.to_a.last
 
+        # Auto-upgrade to thinking model on "think harder" phrases
+        if input =~ /think\s*harder/i
+          upgrade_to_thinking_model
+        end
+
         @interactive_query ||= input
         @history << { role: :user, content: input }
 
@@ -365,6 +382,20 @@ module ConsoleAgent
     def send_and_execute
       begin
         result, tool_messages = send_query(nil, conversation: @history)
+      rescue Providers::ProviderError => e
+        if e.message.include?("prompt is too long") && @history.length >= 6
+          $stdout.puts "\e[33m  Context limit reached. Auto-compacting history...\e[0m"
+          compact_history
+          begin
+            result, tool_messages = send_query(nil, conversation: @history)
+          rescue Providers::ProviderError => e2
+            $stderr.puts "\e[31m  Still too large after compaction: #{e2.message}\e[0m"
+            return :error
+          end
+        else
+          $stderr.puts "\e[31mConsoleAgent Error: #{e.class}: #{e.message}\e[0m"
+          return :error
+        end
       rescue Interrupt
         $stdout.puts "\n\e[33m  Aborted.\e[0m"
         return :interrupted
@@ -533,8 +564,18 @@ module ConsoleAgent
       last_tool_names = []
 
       exhausted = false
+      thinking_suggested = false
 
       max_rounds.times do |round|
+        if round == 5 && !thinking_suggested && !on_thinking_model?
+          thinking_suggested = true
+          thinking_name = ConsoleAgent.configuration.resolved_thinking_model
+          $stdout.puts "\e[33m  This query is using many tool rounds. Switch to thinking model (#{thinking_name})? [y/N]\e[0m"
+          answer = Readline.readline("  ", false).to_s.strip.downcase
+          if answer == 'y'
+            upgrade_to_thinking_model
+          end
+        end
         if round == 0
           $stdout.puts "\e[2m  Thinking...\e[0m"
         else
@@ -547,8 +588,22 @@ module ConsoleAgent
           $stdout.puts "\e[2m  #{llm_status(round, messages, total_input, last_thinking, last_tool_names)}\e[0m"
         end
 
-        result = with_escape_monitoring do
-          provider.chat_with_tools(messages, tools: tools, system_prompt: active_system_prompt)
+        begin
+          result = with_escape_monitoring do
+            provider.chat_with_tools(messages, tools: tools, system_prompt: active_system_prompt)
+          end
+        rescue Providers::ProviderError => e
+          if e.message.include?("prompt is too long") && messages.length >= 6
+            $stdout.puts "\e[33m  Context limit hit mid-session. Compacting messages...\e[0m"
+            messages = compact_messages(messages)
+            unless @_retried_compact
+              @_retried_compact = true
+              retry
+            end
+          end
+          raise
+        ensure
+          @_retried_compact = nil
         end
         total_input += result.input_tokens || 0
         total_output += result.output_tokens || 0
@@ -776,6 +831,10 @@ module ConsoleAgent
     def track_usage(result)
       @total_input_tokens += result.input_tokens || 0
       @total_output_tokens += result.output_tokens || 0
+
+      model = ConsoleAgent.configuration.resolved_model
+      @token_usage[model][:input] += result.input_tokens || 0
+      @token_usage[model][:output] += result.output_tokens || 0
     end
 
     def display_usage(result, show_session: false)
@@ -883,12 +942,61 @@ module ConsoleAgent
       $stdout.puts "\e[2m[session totals — in: #{@total_input_tokens} | out: #{@total_output_tokens} | total: #{@total_input_tokens + @total_output_tokens}]\e[0m"
     end
 
+    def display_cost_summary
+      if @token_usage.empty?
+        $stdout.puts "\e[2m  No usage yet.\e[0m"
+        return
+      end
+
+      total_cost = 0.0
+      $stdout.puts "\e[36m  Cost estimate:\e[0m"
+
+      @token_usage.each do |model, usage|
+        pricing = Configuration::PRICING[model]
+        input_str = "in: #{format_tokens(usage[:input])}"
+        output_str = "out: #{format_tokens(usage[:output])}"
+
+        if pricing
+          cost = (usage[:input] * pricing[:input]) + (usage[:output] * pricing[:output])
+          total_cost += cost
+          $stdout.puts "\e[2m    #{model}:  #{input_str}  #{output_str}  ~$#{'%.2f' % cost}\e[0m"
+        else
+          $stdout.puts "\e[2m    #{model}:  #{input_str}  #{output_str}  (pricing unknown)\e[0m"
+        end
+      end
+
+      $stdout.puts "\e[36m    Total: ~$#{'%.2f' % total_cost}\e[0m"
+    end
+
+    def upgrade_to_thinking_model
+      config = ConsoleAgent.configuration
+      current = config.resolved_model
+      thinking = config.resolved_thinking_model
+
+      if current == thinking
+        $stdout.puts "\e[36m  Already using thinking model (#{current}).\e[0m"
+      else
+        config.model = thinking
+        @provider = nil
+        $stdout.puts "\e[36m  Switched to thinking model: #{thinking}\e[0m"
+      end
+    end
+
+    def on_thinking_model?
+      config = ConsoleAgent.configuration
+      config.resolved_model == config.resolved_thinking_model
+    end
+
     def warn_if_history_large
       chars = @history.sum { |m| m[:content].to_s.length }
-      return if chars < 50_000 || @compact_warned
 
-      @compact_warned = true
-      $stdout.puts "\e[33m  Conversation is getting large (~#{format_tokens(chars)} chars). Consider running /compact to reduce context size.\e[0m"
+      if chars > 120_000 && @history.length >= 6
+        $stdout.puts "\e[33m  Context growing large (~#{format_tokens(chars)} chars). Auto-compacting...\e[0m"
+        compact_history
+      elsif chars > 50_000 && !@compact_warned
+        @compact_warned = true
+        $stdout.puts "\e[33m  Conversation is getting large (~#{format_tokens(chars)} chars). Consider running /compact to reduce context size.\e[0m"
+      end
     end
 
     def compact_history
@@ -941,6 +1049,22 @@ module ConsoleAgent
       end
     end
 
+    def compact_messages(messages)
+      return messages if messages.length < 6
+
+      to_summarize = messages[0...-4]
+      to_keep = messages[-4..]
+
+      history_text = to_summarize.map { |m| "#{m[:role]}: #{m[:content].to_s[0..500]}" }.join("\n\n")
+
+      summary_result = provider.chat(
+        [{ role: :user, content: "Summarize this conversation context concisely, preserving key facts, IDs, and findings:\n\n#{history_text}" }],
+        system_prompt: "You are a conversation summarizer. Be concise but preserve all actionable information."
+      )
+
+      [{ role: :user, content: "CONTEXT SUMMARY:\n#{summary_result.text}" }] + to_keep
+    end
+
     def display_exit_info
       display_session_summary
       if @interactive_session_id

data/lib/console_agent/version.rb

@@ -1,3 +1,3 @@
 module ConsoleAgent
-  VERSION = '0.7.0'.freeze
+  VERSION = '0.8.0'.freeze
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: console_agent
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.8.0
 platform: ruby
 authors:
 - Cortfr