rubyn-code 0.8.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7696c779b900fe4dca806aa73d7fcca79309ebe58a242d16e2d5309b43d44ec4
-  data.tar.gz: 2d8d4c8905255ce11e98569f86f4c2d788c620ea30c513fd6771b3c58bb98073
+  metadata.gz: d43be98f4e24cc9bc78bc541ed0554731ed88985adb56ec5700d643dc4fd2ba2
+  data.tar.gz: d6adda167ad528fde80900dfb4c5d7114029695c4ae83f814ad2130b2f531781
 SHA512:
-  metadata.gz: c5d2b5f15b21d7e02b2f6c2252248eb6e933337b3f4c491135f5453c1ddf4ce47c48605aaeb6e26180a38324c8effc7a149e528c794ca9391ec8c43febbc2bdb
-  data.tar.gz: 15c9aa06c02dd8c105116b403cba0f36cb5a2b91c8690b66b6320a289011cf6f2986a308fdaacad933fbd221646de84b7f774a47709a7c8409fdc5bddca5b671
+  metadata.gz: 3352ad014212276c17d5a96adb3d3dcf43165dffb77b8a95d01ce22bf3fdd57786abca291c4604e937cef26b070b3d43ae791430da30d84baa49a76e753d8f28
+  data.tar.gz: 767c3be54cee4d94e157dd7ae73287c5306159586f3057eac199175aa0ac79aba3ef35046cc4eef6936c6f80802277bf578e5588c35b2fd8940d8aa58037c07e

data/README.md

@@ -15,7 +15,7 @@
   <a href="https://github.com/MatthewSuttles/rubyn-code/actions/workflows/ci.yml"><img src="https://github.com/MatthewSuttles/rubyn-code/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
 </p>
 
-Refactor controllers, generate idiomatic RSpec, catch N+1 queries, review code for anti-patterns, and build entire features — all context-aware with your schema, routes, and specs. Powered by Claude Opus 4.8, running on your existing Claude subscription.
+Refactor controllers, generate idiomatic RSpec, catch N+1 queries, review code for anti-patterns, and build entire features — all context-aware with your schema, routes, and specs. Powered by Claude Opus 5, running on your existing Claude subscription.
 
 <img width="1230" height="280" alt="image" src="https://github.com/user-attachments/assets/14e07ce8-def0-4a8f-ac89-46661361a4eb" />
 
@@ -31,7 +31,7 @@ Refactor controllers, generate idiomatic RSpec, catch N+1 queries, review code f
 - [Quick Start](#quick-start)
 - [What Can Rubyn Do?](#what-can-rubyn-do)
 - [VS Code Extension](#vs-code-extension)
-- [29 Built-in Tools](#29-built-in-tools)
+- [32 Built-in Tools](#32-built-in-tools)
 - [MCP — External Tool Servers](#mcp--external-tool-servers)
 - [Codebase Indexing](#codebase-indexing)
 - [112 Best Practice Skills](#112-best-practice-skills)
@@ -74,8 +74,8 @@ Refactor controllers, generate idiomatic RSpec, catch N+1 queries, review code f
 Phase 4 ships nine parity features with Claude Code:
 
 - **Extended thinking** — `/think <budget>` toggles per-session reasoning; the Anthropic adapter emits `thinking: {type: 'adaptive'}` on Claude 4.6+ models (`{type: 'enabled', budget_tokens}` on older ones).
-- **Reasoning effort** — `/effort <low|medium|high|xhigh|max>` sets the request-level reasoning depth; the Anthropic adapter emits `output_config: {effort}` on the wire. GA on Claude 4.6+ (Opus 4.6/4.7/4.8, Sonnet 4.6/5, Fable 5); `xhigh` needs Opus 4.7+ / Sonnet 5 / Fable 5. Model default is `high`.
-- **Task budgets (beta)** — the agent loop's remaining token budget is sent as `output_config: {task_budget: {type: 'tokens', total}}` on supported models (Fable 5, Sonnet 5, Opus 4.7/4.8), advisory pacing only — `max_tokens` stays the enforced per-response cap.
+- **Reasoning effort** — `/effort <low|medium|high|xhigh|max>` sets the request-level reasoning depth; the Anthropic adapter emits `output_config: {effort}` on the wire. GA on Claude 4.6+ (Opus 4.6/4.7/4.8/5, Sonnet 4.6/5, Fable 5); `xhigh` needs Opus 4.7+ / Sonnet 5 / Fable 5. Model default is `high`.
+- **Task budgets (beta)** — the agent loop's remaining token budget is sent as `output_config: {task_budget: {type: 'tokens', total}}` on supported models (Fable 5, Sonnet 5, Opus 5, Opus 4.7/4.8), advisory pacing only — `max_tokens` stays the enforced per-response cap.
 - **Image / vision input** — `@chart.png` (and `.jpg` / `.jpeg` / `.gif` / `.webp`) becomes a real image content block attached to the user turn; Anthropic and OpenAI each emit their native shape.
 - **TodoWrite live checklist** — `TodoWrite` tool; the checklist refreshes above the spinner on every tool result so you see in-turn progress at a glance.
 - **Custom-command frontmatter** — `argument-hint`, `allowed-tools`, and `model:` keys in `~/.rubyn-code/commands/*.md`; the loop honors the per-prompt tool restriction and model override.
@@ -215,7 +215,7 @@ Rubyn Code includes a VS Code extension that provides a full IDE experience with
 - Full session management — resume, list, fork, and reset conversations
 - Structured code review feedback with severity ratings
 - IDE config get/set for persistent settings
-- All 29 tools available, including MCP tools
+- All 32 tools available, including MCP tools
 
 **Permission modes:**
 
@@ -226,19 +226,19 @@ Rubyn Code includes a VS Code extension that provides a full IDE experience with
 
 The extension communicates over 19 RPC methods: `initialize`, `prompt`, `cancel`, `review`, `approveToolUse`, `acceptEdit`, `session/*`, `config/*`, `models/list`, `plan/propose`, `plan/interview/*` (chat-resident [megaplan](#megaplan--phased-planning)), `recover_ci`, and `shutdown`.
 
-## 29 Built-in Tools
+## 32 Built-in Tools
 
 | Category | Tools |
 |----------|-------|
 | **File I/O** | `read_file`, `write_file`, `edit_file` |
-| **Search** | `glob`, `grep` |
+| **Search** | `glob`, `grep`, `code_graph` |
 | **Execution** | `bash` (sandboxed, dangerous commands blocked) |
 | **Web** | `web_search`, `web_fetch` |
 | **Git** | `git_status`, `git_diff`, `git_log`, `git_commit` |
 | **Rails** | `rails_generate`, `db_migrate`, `run_specs`, `bundle_install`, `bundle_add` |
 | **Review** | `review_pr` (diff-based best practice code review) |
-| **Agents** | `spawn_agent`, `spawn_teammate`, `background_run` |
-| **Context** | `compact`, `load_skill`, `task` |
+| **Agents** | `spawn_agent`, `spawn_teammate`, `background_run`, `phone_a_friend` |
+| **Context** | `compact`, `load_skill`, `task`, `todo_write` |
 | **Memory** | `memory_search`, `memory_write` |
 | **Teams** | `send_message`, `read_inbox` |
 | **Interactive** | `ask_user` (ask clarifying questions mid-task) |
@@ -518,6 +518,18 @@ rubyn > Send alice a message to write specs for the User model
 
 Teammates run in background threads with their own agent loop and mailbox.
 
+### Phone a Friend (second opinion)
+
+When the agent is stuck or weighing two approaches, the `phone_a_friend` tool asks a *different* model for a one-shot second opinion. The friend is picked for perspective diversity: the top-tier model of another configured provider whose API key is present (a genuinely different model family), falling back to the active provider's top tier. The friend gets no tools and no conversation history — only the question and whatever context the agent chooses to send — and its answer comes back as plain text labeled with the provider and model that gave it.
+
+```
+rubyn > I keep going back and forth on STI vs polymorphic here...
+
+[tool] phone_a_friend
+## Second Opinion — openai/gpt-5.4
+Commit to the polymorphic association. The key reason: ...
+```
+
 ## GOLEM — Autonomous Daemon
 
 GOLEM is an always-on autonomous agent that claims tasks from a queue and works through them independently. It runs a full agent loop per task with access to all tools, MCP servers, and memory.
@@ -691,7 +703,7 @@ Rubyn snapshots a checkpoint at the start of every turn — capturing the conver
 | 2 | Token file | `~/.rubyn-code/tokens.yml` |
 | 3 | Environment | `export ANTHROPIC_API_KEY=sk-ant-...` |
 
-Works with Claude Pro, Max, Team, and Enterprise. Default model: **Claude Opus 4.6**.
+Works with Claude Pro, Max, Team, and Enterprise. Default model: **Claude Opus 5**.
 
 ### OpenAI
 
@@ -709,7 +721,7 @@ Add a provider and its API key in one command:
 /provider add groq https://api.groq.com/openai/v1 --key gsk-xxx --models llama-3.3-70b
 
 # For Anthropic-format proxies (e.g., Bedrock, custom gateways)
-/provider add my-proxy https://proxy.example.com/v1 --format anthropic --key sk-xxx --models claude-sonnet-4-6
+/provider add my-proxy https://proxy.example.com/v1 --format anthropic --key sk-xxx --models claude-sonnet-5
 
 # Update a key later
 /provider set-key groq gsk-new-key
@@ -740,7 +752,7 @@ providers:
     base_url: https://proxy.example.com/v1
     env_key: PROXY_API_KEY
     models:
-      top: claude-sonnet-4-6
+      top: claude-sonnet-5
 ```
 
 Then switch with `/model groq:llama-3.3-70b`.
@@ -767,7 +779,7 @@ Local providers (Ollama, LM Studio) running on `localhost`/`127.0.0.1` don't req
 │  Layer 5:  Skills (112 best practice docs, on-demand loading) │
 │  Layer 4:  Context Management (3-layer compression pipeline)  │
 │  Layer 3:  Permissions (tiered access + deny lists + hooks)   │
-│  Layer 2:  Tool System (29 tools, dispatch map registry)      │
+│  Layer 2:  Tool System (32 tools, dispatch map registry)      │
 │  Layer 1:  THE AGENT LOOP (while tool_use → execute → repeat) │
 └──────────────────────────────────────────────────────────────┘
 ```
@@ -780,7 +792,7 @@ These must match a provider defined in the `providers` section (or a built-in li
 ```yaml
 # ~/.rubyn-code/config.yml (global)
 provider: anthropic              # default provider on startup
-model: claude-opus-4-6           # default model on startup
+model: claude-opus-5             # default model on startup
 permission_mode: allow_read
 session_budget: 5.00
 daily_budget: 10.00
@@ -798,15 +810,15 @@ Rubyn can automatically route tasks to different AI models based on complexity.
 ```yaml
 # ~/.rubyn-code/config.yml
 provider: anthropic
-model: claude-opus-4-6
+model: claude-opus-5
 
 providers:
   anthropic:
     env_key: ANTHROPIC_API_KEY
     models:
       cheap: claude-haiku-4-5      # file search, git ops, formatting
-      mid: claude-sonnet-4-6       # code gen, specs, refactors, reviews
-      top: claude-opus-4-6         # architecture, security, complex work
+      mid: claude-sonnet-5         # code gen, specs, refactors, reviews
+      top: claude-opus-5           # architecture, security, complex work
 
   openai:
     env_key: OPENAI_API_KEY
@@ -838,8 +850,8 @@ providers:
 | Tier | Task types | Default model |
 |------|-----------|---------------|
 | **cheap** | File search, git ops, formatting, summaries | `claude-haiku-4-5` |
-| **mid** | Code generation, specs, refactors, code review, bug fixes | `claude-sonnet-4-6` |
-| **top** | Architecture, security review, complex refactors, planning | `claude-opus-4-6` |
+| **mid** | Code generation, specs, refactors, code review, bug fixes | `claude-sonnet-5` |
+| **top** | Architecture, security review, complex refactors, planning | `claude-opus-5` |
 
 You can also set custom pricing per model so `/cost` reports accurate spending for third-party providers.
 

data/lib/rubyn_code/tools/RUBYN.md

@@ -1,6 +1,6 @@
 # Layer 2: Tools
 
-33 built-in tools that Claude can invoke. The extensibility surface of the system.
+34 built-in tools that Claude can invoke. The extensibility surface of the system.
 
 ## Core Classes
 
@@ -26,7 +26,7 @@
 | Git | `git_commit`, `git_diff`, `git_log`, `git_status` |
 | Web | `web_search`, `web_fetch` |
 | Memory | `memory_search`, `memory_write` |
-| Agents | `spawn_agent`, `spawn_teammate`, `send_message`, `read_inbox` |
+| Agents | `spawn_agent`, `spawn_teammate`, `send_message`, `read_inbox`, `phone_a_friend` |
 | Meta | `compact`, `load_skill`, `task`, `review_pr` |
 
 ## Adding a Tool

data/lib/rubyn_code/tools/executor.rb

@@ -85,6 +85,8 @@ module RubynCode
         when 'spawn_agent', 'spawn_teammate'
           inject_agent_deps(tool)
           tool.db = @db if tool_name == 'spawn_teammate' && tool.respond_to?(:db=)
+        when 'phone_a_friend'
+          tool.llm_client = @llm_client if tool.respond_to?(:llm_client=)
         when 'background_run'
           tool.background_worker = @background_worker if tool.respond_to?(:background_worker=)
         when 'ask_user'

data/lib/rubyn_code/tools/phone_a_friend.rb

@@ -0,0 +1,135 @@
+# frozen_string_literal: true
+
+require_relative 'base'
+require_relative 'registry'
+
+module RubynCode
+  module Tools
+    # Ask a different model for a second opinion. The "friend" is chosen to
+    # maximize perspective diversity: prefer the top-tier model of another
+    # configured provider (a genuinely different model family), and fall back
+    # to the active provider's top-tier model when no other provider has an
+    # API key available. One-shot, no tools, returns plain text.
+    class PhoneAFriend < Base
+      TOOL_NAME = 'phone_a_friend'
+      DESCRIPTION = 'Ask a different model for a second opinion when you are stuck, ' \
+                    'weighing two approaches, or want your reasoning sanity-checked. ' \
+                    'Sends one question (plus optional context) to another model — ' \
+                    'a different provider when one is configured, otherwise the ' \
+                    'top-tier model of the current provider — and returns its answer. ' \
+                    'The friend has no tools and sees nothing except what you send.'
+      PARAMETERS = {
+        question: {
+          type: :string,
+          required: true,
+          description: 'The question to ask. Be specific about what kind of answer you ' \
+                       'need (a decision, a review of reasoning, an alternative approach).'
+        },
+        context: {
+          type: :string,
+          required: false,
+          description: 'Relevant code, error output, or background. The friend sees ' \
+                       'only this — include everything needed to answer well.'
+        }
+      }.freeze
+      RISK_LEVEL = :external
+
+      SYSTEM_PROMPT = <<~PROMPT
+        You are giving a second opinion to another AI coding agent that is working
+        inside a project and has hit a question it wants an outside perspective on.
+        You cannot see the project — only what the agent sent you. Answer directly
+        and concretely: commit to a recommendation, explain the key reason, and
+        flag anything important the agent may have missed. If the provided context
+        is insufficient to answer well, say exactly what is missing.
+      PROMPT
+
+      # Injected by the Executor (active client) and overridable in tests.
+      attr_writer :llm_client, :client_factory
+
+      def execute(question:, context: nil)
+        return 'phone_a_friend: no LLM client available.' unless @llm_client
+
+        provider, model = pick_friend
+        response = call_friend(provider, model, build_message(question, context))
+        answer = extract_text(response)
+        return "phone_a_friend: #{provider}/#{model} returned no text." if answer.empty?
+
+        "## Second Opinion — #{provider}/#{model}\n\n#{answer}"
+      rescue StandardError => e
+        friend = provider ? "#{provider}/#{model}" : 'friend'
+        "phone_a_friend: call to #{friend} failed: #{e.message}"
+      end
+
+      def self.summarize(_output, _args)
+        'asked another model for a second opinion'
+      end
+
+      private
+
+      # Returns [provider, model]. Prefers another provider whose API key is
+      # present; otherwise escalates to the active provider's top tier.
+      def pick_friend
+        active = @llm_client.provider_name
+        other = (known_providers - [active]).find { |p| key_present?(p) }
+        provider = other || active
+        [provider, top_model_for(provider)]
+      end
+
+      def call_friend(provider, model, message)
+        client = provider == @llm_client.provider_name ? @llm_client : friend_client(provider, model)
+        client.chat(
+          messages: [{ role: 'user', content: message }],
+          tools: nil,
+          system: SYSTEM_PROMPT,
+          model: model
+        )
+      end
+
+      def friend_client(provider, model)
+        factory = @client_factory || ->(prov, mod) { LLM::Client.new(provider: prov, model: mod) }
+        factory.call(provider, model)
+      end
+
+      def build_message(question, context)
+        return question if context.to_s.empty?
+
+        "#{question}\n\n## Context\n\n#{context}"
+      end
+
+      def known_providers
+        configured = settings.to_h['providers']
+        names = configured.is_a?(Hash) ? configured.keys : []
+        (names + Config::Settings::DEFAULT_PROVIDER_MODELS.keys).uniq
+      end
+
+      def key_present?(provider)
+        env_key = provider_setting(provider, 'env_key')
+        env_key ? !ENV[env_key].to_s.empty? : false
+      end
+
+      def top_model_for(provider)
+        config_models = provider_setting(provider, 'models')
+        model = config_models['top'] || config_models.values.last if config_models.is_a?(Hash)
+        model || @llm_client.model
+      end
+
+      # Reads a provider key from config.yml, falling back to the built-in
+      # provider defaults for anthropic/openai.
+      def provider_setting(provider, key)
+        value = settings.provider_config(provider)&.fetch(key, nil)
+        value || Config::Settings::DEFAULT_PROVIDER_MODELS.dig(provider, key)
+      end
+
+      def settings
+        @settings ||= Config::Settings.new
+      end
+
+      def extract_text(response)
+        content = response.respond_to?(:content) ? Array(response.content) : []
+        content.select { |b| b.respond_to?(:type) && b.type == 'text' }.map(&:text).join("\n")
+      end
+    end
+
+    Registry.register(PhoneAFriend)
+  end
+end

data/lib/rubyn_code/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RubynCode
-  VERSION = '0.8.0'
+  VERSION = '0.9.0'
 end

data/lib/rubyn_code.rb

@@ -107,6 +107,7 @@ module RubynCode
     autoload :ReadInbox, 'rubyn_code/tools/read_inbox'
     autoload :ReviewPr, 'rubyn_code/tools/review_pr'
     autoload :SpawnAgent, 'rubyn_code/tools/spawn_agent'
+    autoload :PhoneAFriend, 'rubyn_code/tools/phone_a_friend'
     autoload :BackgroundRun, 'rubyn_code/tools/background_run'
     autoload :WebSearch, 'rubyn_code/tools/web_search'
     autoload :WebFetch, 'rubyn_code/tools/web_fetch'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubyn-code
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.9.0
 platform: ruby
 authors:
 - fadedmaturity
@@ -448,6 +448,7 @@ files:
 - lib/rubyn_code/tools/memory_search.rb
 - lib/rubyn_code/tools/memory_write.rb
 - lib/rubyn_code/tools/output_compressor.rb
+- lib/rubyn_code/tools/phone_a_friend.rb
 - lib/rubyn_code/tools/rails_generate.rb
 - lib/rubyn_code/tools/read_file.rb
 - lib/rubyn_code/tools/read_inbox.rb