turnkit 0.2.5 → 0.2.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 271ce272a71a97aa2991a580f36205e4cef8e19466e2e480b0ac6f0f0225d51f
-  data.tar.gz: b9a0503f499d3eb850e7eece6f508b6fbc206d6398263f6005520b7ef716493b
+  metadata.gz: 1c205e6b6c72785350419adfb6515f9b2d213c3eef06c9516a038667bae24842
+  data.tar.gz: 74c72004e3334cafa69071034aaa98c14f98262fe56bee9a69ac058bd70499af
 SHA512:
-  metadata.gz: f8772f25a95c44b2ba3d1a17a3e89d0ba142d862e798cee6daef9c54e04deaa3d8dee77deae48b5a77f7b6051b467a14c355aabf5115b1ce89832a27c87eb1b6
-  data.tar.gz: 9b12cccaa55c8d791168eca90655e3b9db89409b69fe59f8b45d23bef71aeec296c538696af44e484da9884dfde4ace67bbfd81d4a6647783f1f7f299ef0e485
+  metadata.gz: 6df2331b9e594e1c4925113fb39996ace94860181037397e67855afebf479cb128ad83cbc2d76dcb8c2fe85d55ca042624d3f5b5ff3b33ba7cd7b4fdf1dbf62c
+  data.tar.gz: 640c1fdfdbdb08610ba75885e8fb6903c81ecfd90dec5dcf2eeb4462e13ab17de357af6adcc1e5cf18c9fb4622d769151382278481a7b3d178462b80e2e1bfc2

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.2.6 - 2026-06-07
+
+- Add automatic context compaction for long conversations. TurnKit now stores append-only `context_summary` messages and projects compacted history into future model calls while keeping the full transcript durable.
+
 ## 0.2.5 - 2026-06-06
 
 - Add per-agent and per-turn provider thinking configuration.

data/README.md

@@ -4,7 +4,7 @@
 [![Ruby](https://img.shields.io/badge/ruby-%3E%3D%203.1-red.svg)](https://www.ruby-lang.org)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE.md)
 
-Build durable Ruby AI agents with turns, tools, skills, and Rails persistence.
+Build durable Ruby and Rails agents with tools, skills, sub-agents, and persistence.
 
 ## Installation
 
@@ -22,21 +22,12 @@ bundle install
 
 ## Quick Start
 
-Set a provider key. TurnKit uses RubyLLM under the hood and defaults to Anthropic Claude:
+Set an API key:
 
 ```sh
 export ANTHROPIC_API_KEY=...
 ```
 
-| Provider | Env var | Example model |
-| --- | --- | --- |
-| Anthropic | `ANTHROPIC_API_KEY` | `claude-sonnet-4-5` |
-| OpenAI | `OPENAI_API_KEY` | `gpt-4.1-mini` |
-| Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` |
-
-> [!WARNING]
-> TurnKit defaults to `claude-sonnet-4-5`. If `ANTHROPIC_API_KEY` is unset or blank, set `TurnKit.default_model` to a provider you have configured.
-
 Create an agent:
 
 ```ruby
@@ -59,93 +50,78 @@ puts turn.output_text
 
 ### Models
 
-Set the default model:
+Set a model:
 
 ```ruby
-TurnKit.default_model = "claude-sonnet-4-5"
+TurnKit.default_model = "gpt-4.1-mini"
 ```
 
-Use OpenAI:
+Set the matching key:
 
 ```sh
 export OPENAI_API_KEY=...
 ```
 
-Set an OpenAI model:
-
-```ruby
-TurnKit.default_model = "gpt-4.1-mini"
-```
-
-Use Gemini:
+Use these common providers:
 
-```sh
-export GEMINI_API_KEY=...
-```
-
-Set a Gemini model:
+| Provider | Key | Model |
+| --- | --- | --- |
+| Anthropic | `ANTHROPIC_API_KEY` | `claude-sonnet-4-5` |
+| OpenAI | `OPENAI_API_KEY` | `gpt-4.1-mini` |
+| Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` |
+| OpenRouter | `OPENROUTER_API_KEY` | `openrouter/...` |
 
-```ruby
-TurnKit.default_model = "gemini-2.5-flash"
-```
+Expect `TurnKit::ModelAccessError` for obvious key mistakes.
 
-### Thinking
+### Conversations
 
-Enable provider reasoning or extended thinking per agent:
+Create a conversation:
 
 ```ruby
 agent = TurnKit::Agent.new(
-  name: "reasoner",
-  model: "claude-sonnet-4-5",
-  thinking: { budget: 4_000 }
+  name: "writer",
+  instructions: "Write clear release notes."
 )
+
+conversation = agent.conversation(subject: "v1 launch")
 ```
 
-Use effort-based thinking for providers that support it:
+Add context:
 
 ```ruby
-agent = TurnKit::Agent.new(
-  name: "reasoner",
-  model: "gemini-2.5-flash",
-  thinking: { effort: :high }
-)
+conversation.say("Mention faster tool execution.")
 ```
 
-Override or disable thinking for one turn:
+Run the agent:
 
 ```ruby
-conversation = agent.conversation
-conversation.ask("Solve this carefully.", thinking: { budget: 8_000 })
-conversation.ask("Answer quickly.", thinking: nil)
+turn = conversation.run!
+puts turn.output_text
 ```
 
-TurnKit passes `thinking` to RubyLLM as `{ effort:, budget: }`. Anthropic requires `budget`; Gemini and OpenRouter can use `effort`, `budget`, or both depending on the model.
-
-When the provider reports reasoning usage, TurnKit records it as `thinking_tokens` and includes it in usage totals and cost calculation.
+### Prompt Preview
 
-### Conversations
-
-Create a conversation:
+Preview a pending turn:
 
 ```ruby
-agent = TurnKit::Agent.new(
-  name: "writer",
-  instructions: "Write clear release notes."
-)
+turn = conversation.ask("Draft the launch email.", async: true)
+request = turn.preview
 ```
 
-Add context:
+Inspect the request:
 
 ```ruby
-conversation = agent.conversation(subject: "v1 launch")
-conversation.say("Mention faster tool execution.")
+request.model
+request.messages
+request.tool_names
+request.instructions
+request.report
 ```
 
-Run the agent:
+Run the reviewed turn:
 
 ```ruby
-turn = conversation.run!
-puts turn.output_text
+turn.run!
 ```
 
 ### Tools
@@ -156,11 +132,15 @@ Create a tool:
 class SaveReport < TurnKit::Tool
   description "Save a report."
   usage_hint "Use when the user asks to persist a report."
+
   parameter :title, :string, required: true
   parameter :body, :string, required: true
 
   def self.ends_turn? = true
-  def self.completion_message(result) = "Saved #{result.fetch("report_id")}."
+
+  def self.completion_message(result)
+    "Saved #{result.fetch("report_id")}."
+  end
 
   def call(title:, body:, context:)
     { report_id: "rep_1", title: title, body: body }
@@ -168,7 +148,7 @@ class SaveReport < TurnKit::Tool
 end
 ```
 
-Use the tool:
+Register the tool:
 
 ```ruby
 agent = TurnKit::Agent.new(
@@ -178,82 +158,87 @@ agent = TurnKit::Agent.new(
 )
 ```
 
-Ask for tool use:
+Run the tool loop:
 
 ```ruby
 turn = agent.conversation.ask("Save a short status report.")
 puts turn.output_text
 ```
 
-#### Defining application tools
+Rely on TurnKit to validate tools and model-provided arguments.
+
+### Structured Output
 
-Tools are classes, not instances. Namespaced tools work fine, and the default tool name comes from the class name: `Assistant::Tools::WebSearch` becomes `web_search`.
+Define a schema:
 
 ```ruby
-module Assistant
-  module Tools
-    class WebSearch < TurnKit::Tool
-      description "Search the web for current information."
-      usage_hint "Use when current external information is needed."
+schema = {
+  type: "object",
+  properties: {
+    title: { type: "string" },
+    bullets: {
+      type: "array",
+      items: { type: "string" }
+    }
+  },
+  required: ["title", "bullets"]
+}
+```
 
-      parameter :objective, :string, required: true
-      parameter :search_queries, :array, required: false
+Use structured output:
 
-      def call(objective:, search_queries: nil, context:)
-        ParallelClient.new.web_search(
-          objective: objective,
-          search_queries: search_queries
-        )
-      end
-    end
-  end
-end
+```ruby
+agent = TurnKit::Agent.new(
+  name: "writer",
+  output_schema: schema
+)
+
+turn = agent.conversation.ask("Summarize the launch plan.")
+puts turn.output_data
 ```
 
-Register tool classes on the agent:
+Override the schema per turn:
 
 ```ruby
-agent = TurnKit::Agent.new(
-  name: "researcher",
-  tools: [
-    Assistant::Tools::WebSearch,
-    Assistant::Tools::ReadWebPage
-  ]
+conversation.ask(
+  "Return one decision.",
+  output_schema: {
+    type: "object",
+    properties: {
+      decision: { type: "string" }
+    }
+  }
 )
 ```
 
-#### Tool context
+### Events
 
-Every tool receives a `context:` object. Use it for logging, correlation, persistence, and domain scoping:
+Subscribe globally:
 
 ```ruby
-def call(query:, context:)
-  context.turn       # The TurnKit::Turn being run
-  context.execution  # The TurnKit::ToolExecution for this tool call
-
-  { query: query }
+TurnKit.on_event = ->(event) do
+  Rails.logger.info("turnkit.#{event.type}")
 end
 ```
 
-If your application already uses a `context:` keyword for something else, use `turnkit_context:` instead:
+Subscribe per agent:
 
 ```ruby
-def call(query:, turnkit_context:)
-  { turn_id: turnkit_context.turn.id, query: query }
-end
+agent = TurnKit::Agent.new(
+  name: "helper",
+  on_event: ->(event) { puts event.type }
+)
 ```
 
-#### Tool return values
-
-Prefer returning a `Hash`. TurnKit serializes the normalized value as the tool result:
+Subscribe per turn:
 
-| Return value | Stored tool result |
-| --- | --- |
-| `Hash` | Keys are stringified. |
-| `Array` | Wrapped as `{ "items" => [...] }`. |
-| Scalar | Wrapped as `{ "result" => value.to_s }`. |
+```ruby
+turn.run! do |event|
+  puts event.type
+end
+```
 
-Avoid returning arbitrary objects unless you convert them to a plain Hash or Array first.
+Use events for turns, model calls, messages, and tool calls.
 
 ### Skills
 
@@ -283,7 +268,7 @@ writer = TurnKit::Agent.new(
 )
 ```
 
-Delegate to it:
+Register the sub-agent:
 
 ```ruby
 editor = TurnKit::Agent.new(
@@ -299,117 +284,36 @@ turn = editor.conversation.ask("Ask the writer for three headlines.")
 puts turn.output_text
 ```
 
-### Usage and costs
-
-Inspect token usage:
+Use sub-agents for isolated child conversations.
 
-```ruby
-turn.usage.total_tokens
-conversation.usage.total_tokens
-agent.usage.total_tokens
-```
+### Context Compaction
 
-Inspect costs:
+Disable compaction:
 
 ```ruby
-turn.cost.total
-conversation.cost.total
-agent.cost.total
+TurnKit.compaction = false
 ```
 
-Use RubyLLM registry prices by default.
-
-Override model rates:
+Configure compaction:
 
 ```ruby
-TurnKit.cost_rates = {
-  "my-model" => {
-    input: 0.25,
-    output: 1.00,
-    cached_input: 0.05,
-    cache_creation: 0.25
-  }
+TurnKit.compaction = {
+  model: "gpt-4.1-mini",
+  threshold: 0.75,
+  context_limit: 128_000
 }
 ```
 
-Override cost calculation:
+Compact manually:
 
 ```ruby
-TurnKit.cost_calculator = ->(usage, model) do
-  {
-    input: usage.input_tokens * 0.25 / 1_000_000.0,
-    output: usage.output_tokens * 1.00 / 1_000_000.0
-  }
-end
+conversation.compact!(focus: "billing migration")
 ```
 
-Limit turn cost:
+Run the local smoke test:
 
-```ruby
-agent = TurnKit::Agent.new(
-  name: "analyst",
-  cost_limit: 0.25
-)
-```
-
-### Prompt caching
-
-Enable prompt caching:
-
-```ruby
-TurnKit.prompt_cache = :auto
-```
-
-Disable prompt caching:
-
-```ruby
-TurnKit.prompt_cache = :off
-```
-
-Split custom prompts:
-
-```ruby
-agent = TurnKit::Agent.new(
-  name: "cached",
-  system_prompt: [
-    "Stable instructions and tool guidance.",
-    TurnKit::SystemPrompt::CACHE_BOUNDARY,
-    "Dynamic subject and live context."
-  ].join("\n")
-)
-```
-
-### Custom clients
-
-Create a client:
-
-```ruby
-class MyClient < TurnKit::Client
-  def chat(model:, messages:, tools:, instructions:, temperature: nil, thinking: nil, metadata: nil)
-    TurnKit::Result.new(
-      text: "provider response",
-      model: model,
-      usage: TurnKit::Usage.new(
-        input_tokens: 100,
-        output_tokens: 20,
-        cached_tokens: 80,
-        cache_write_tokens: 100
-      )
-    )
-  end
-end
-```
-
-Use the client:
-
-```ruby
-TurnKit.client = MyClient.new
-```
-
-Split cache sections:
-
-```ruby
-stable, dynamic = TurnKit::SystemPrompt.split_cache_boundary(instructions)
+```sh
+ruby script/manual_compaction.rb
 ```
 
 ### Rails
@@ -420,47 +324,18 @@ Install Rails persistence:
 bin/rails generate turnkit:install
 ```
 
-The installer creates:
-
-- `config/initializers/turnkit.rb`
-- `app/models/turnkit/conversation.rb`
-- `app/models/turnkit/turn.rb`
-- `app/models/turnkit/message.rb`
-- `app/models/turnkit/tool_execution.rb`
-- a migration for TurnKit persistence
-
-The generated migration currently uses `ActiveRecord::Migration[7.1]`. In a newer Rails app, update that version if your app requires it, for example `ActiveRecord::Migration[8.1]`.
-
 Run migrations:
 
 ```sh
 bin/rails db:migrate
 ```
 
-Configure Rails:
-
-```ruby
-TurnKit.store = TurnKit::ActiveRecordStore.new
-```
-
-Suggested Rails file layout for your application AI code:
+Use this layout:
 
 ```text
-app/models/assistant/
-  tools/
-    web_search.rb
-    read_web_page.rb
-  skills/
-  prompts/
-```
-
-If you prefer to keep AI infrastructure out of `app/models`, add an autoloaded directory such as:
-
-```text
-app/ai/
-  tools/
-  skills/
-  prompts/
+app/ai/agents/
+app/ai/tools/
+app/ai/skills/
 ```
 
 Reconcile stale turns:
@@ -469,112 +344,63 @@ Reconcile stale turns:
 TurnKit.reconcile_stale!
 ```
 
-#### Debugging Rails persistence
-
-Inspect the latest persisted turn in a Rails console:
+## Options
 
-```ruby
-turn = Turnkit::Turn.order(created_at: :desc).first
-turn.status
-turn.error
-turn.output_text
-```
+| Option | Description |
+| --- | --- |
+| `TurnKit.default_model` | Set the default model. |
+| `TurnKit.client` | Set the model client. |
+| `TurnKit.store` | Set the persistence store. |
+| `TurnKit.max_iterations` | Limit model loop iterations. |
+| `TurnKit.max_depth` | Limit sub-agent depth. |
+| `TurnKit.max_tool_executions` | Limit tool calls per turn. |
+| `TurnKit.timeout` | Limit turn runtime. |
+| `TurnKit.cost_limit` | Limit estimated turn cost. |
+| `TurnKit.compaction` | Configure context compaction. |
+| `TurnKit.on_event` | Subscribe to lifecycle events. |
 
-Check whether the model actually called tools:
+Set options globally:
 
 ```ruby
-Turnkit::ToolExecution
-  .where(turn_uid: turn.uid)
-  .order(:created_at)
-  .map { |execution|
-    {
-      name: execution.tool_name,
-      status: execution.status,
-      arguments: execution.arguments,
-      result_keys: execution.result&.keys,
-      error: execution.error
-    }
-  }
+TurnKit.default_model = "gpt-4.1-mini"
+TurnKit.max_iterations = 25
+TurnKit.timeout = 300
 ```
 
-#### Live smoke test
-
-Use a model whose provider key is configured, then run a real tool-using turn:
+Set options per agent:
 
 ```ruby
-TurnKit.default_model = "gpt-4.1-mini"
-
 agent = TurnKit::Agent.new(
-  name: "researcher",
-  instructions: "Use web_search, then read_web_page, before answering.",
-  tools: [
-    Assistant::Tools::WebSearch,
-    Assistant::Tools::ReadWebPage
-  ]
-)
-
-turn = agent.conversation.ask(
-  "Search for the TurnKit Ruby gem, read the first useful result, then summarize it."
+  name: "engineer",
+  model: "gpt-4.1-mini",
+  max_iterations: 10,
+  max_depth: 2
 )
-
-puts turn.output_text
-
-pp Turnkit::ToolExecution
-  .where(turn_uid: turn.id)
-  .order(:created_at)
-  .pluck(:tool_name, :status, :error)
 ```
 
-## Options
-
-Configure defaults:
+Enable thinking:
 
 ```ruby
-TurnKit.default_model = "claude-sonnet-4-5"
-TurnKit.max_iterations = 25
-TurnKit.timeout = 300
-TurnKit.max_depth = 3
-TurnKit.max_tool_executions = 100
-TurnKit.cost_limit = nil
-TurnKit.cost_rates = {}
-TurnKit.cost_calculator = nil
-TurnKit.prompt_cache = :auto
+agent = TurnKit::Agent.new(
+  name: "reasoner",
+  model: "claude-sonnet-4-5",
+  thinking: { budget: 4_000 }
+)
 ```
 
-Override an agent:
+## Upgrading
+
+Add `output_data` for structured output persistence.
 
 ```ruby
-agent = TurnKit::Agent.new(
-  name: "analyst",
-  model: "gpt-4.1-mini",
-  max_iterations: 10,
-  timeout: 60,
-  cost_limit: 0.25,
-  thinking: { effort: :low }
-)
+add_column :turnkit_turns, :output_data, :json
 ```
 
-| Option | Description |
-| --- | --- |
-| `default_model` | Set the default RubyLLM model. |
-| `client` | Set the model client. |
-| `store` | Set the conversation store. |
-| `max_iterations` | Limit model calls per turn. |
-| `timeout` | Limit seconds per root turn. |
-| `max_tool_executions` | Limit tool calls per root turn. |
-| `cost_limit` | Limit cost per root turn. |
-| `thinking` | Configure provider reasoning or extended thinking per agent. |
-| `cost_rates` | Override prices by model. |
-| `cost_calculator` | Override cost calculation. |
-| `prompt_cache` | Use provider prompt caching. |
+Skip this step for new installs.
 
 ## Contributing
 
-Report bugs and open pull requests on GitHub:
-
-```text
-https://github.com/samuelcouch/turnkit
-```
+Fork the project.
 
 Run tests:
 
@@ -582,6 +408,14 @@ Run tests:
 bundle exec rake test
 ```
 
+Run syntax checks:
+
+```sh
+find lib test examples -type f -name '*.rb' -print0 | xargs -0 ruby -c
+```
+
+Open a pull request.
+
 ## License
 
-See the MIT License.
+Use this gem under the MIT License.