language-operator 0.1.30 → 0.1.31

data/lib/language_operator/dsl.rb

@@ -14,6 +14,7 @@ require_relative 'dsl/execution_context'
 require_relative 'dsl/agent_definition'
 require_relative 'dsl/agent_context'
 require_relative 'dsl/workflow_definition'
+require_relative 'dsl/schema'
 require_relative 'agent/safety/ast_validator'
 require_relative 'agent/safety/safe_executor'
 

data/lib/language_operator/logger.rb

@@ -23,10 +23,10 @@ module LanguageOperator
     }.freeze
 
     LEVEL_EMOJI = {
-      'DEBUG' => '🔍',
-      'INFO' => 'ℹ️ ',
-      'WARN' => '⚠️ ',
-      'ERROR' => '❌'
+      'DEBUG' => '', # 🔍
+      'INFO' => '', # ℹ️
+      'WARN' => '', # ⚠️
+      'ERROR' => '' # ❌
     }.freeze
 
     attr_reader :logger, :format, :show_timing

data/lib/language_operator/templates/README.md

@@ -0,0 +1,23 @@
+# Templates Directory
+
+This directory contains templates used by the Language Operator gem for various code generation and synthesis tasks.
+
+## Directory Structure
+
+- **`examples/`** - Example synthesis templates for agent and persona generation
+  - `agent_synthesis.tmpl` - Template for synthesizing agent definitions
+  - `persona_distillation.tmpl` - Template for distilling persona configurations
+
+- **`schema/`** - JSON Schema definitions and validation templates
+  - Reserved for future schema artifacts and validation templates
+
+## Usage
+
+Templates in this directory are used by:
+- The `aictl system synthesis-template` command for managing synthesis templates
+- Agent synthesis and persona distillation features
+- Schema validation and code generation tools
+
+## Template Format
+
+Templates use a simple variable substitution format compatible with the synthesis engine. Variables are typically specified in the template header and replaced during synthesis.

data/lib/language_operator/templates/examples/agent_synthesis.tmpl

@@ -0,0 +1,115 @@
+You are generating Ruby DSL code for an autonomous agent in a Kubernetes operator.
+
+{{if .ErrorContext}}
+## IMPORTANT: Self-Healing Synthesis - Attempt {{.AttemptNumber}}
+
+The previous code synthesis encountered errors. Please analyze the errors below and generate CORRECTED code.
+
+### Previous Synthesis Failures
+
+{{if .ErrorContext.ValidationErrors}}
+**Validation Errors** (detected during code generation):
+{{range .ErrorContext.ValidationErrors}}
+- {{.}}
+{{end}}
+{{end}}
+
+{{if .ErrorContext.RuntimeErrors}}
+**Runtime Errors** (detected during execution):
+{{range .ErrorContext.RuntimeErrors}}
+- Time: {{.Timestamp}}
+- Type: {{.ErrorType}}
+- Message: {{.ErrorMessage}}
+{{if .StackTrace}}
+- Stack Trace:
+{{range .StackTrace}}
+  {{.}}
+{{end}}
+{{end}}
+- Exit Code: {{.ContainerExitCode}}
+{{end}}
+{{end}}
+
+{{if .ErrorContext.LastCrashLog}}
+**Last Container Logs** (before crash):
+```
+{{.ErrorContext.LastCrashLog}}
+```
+{{end}}
+
+### Your Task
+
+1. Carefully analyze each error above
+2. Identify the root cause of the failure
+3. Generate CORRECTED Ruby DSL code that addresses ALL errors
+4. Ensure the code:
+   - Fixes the specific errors mentioned
+   - Uses only available tools: {{.ToolsList}}
+   - Uses only available models: {{.ModelsList}}
+   - Follows the Language Operator DSL syntax exactly
+   - Does NOT use any dangerous Ruby methods (system, eval, etc.)
+
+This is attempt {{.AttemptNumber}} of {{.MaxAttempts}}. The user is counting on you to get it right!
+
+{{if .LastKnownGoodCode}}
+### Last Known Working Code (for reference)
+```ruby
+{{.LastKnownGoodCode}}
+```
+{{end}}
+
+{{else}}
+## Agent Synthesis Request
+{{end}}
+
+**User Instructions:**
+{{.Instructions}}
+
+**Available Tools:**
+{{.ToolsList}}
+
+**Available Models:**
+{{.ModelsList}}
+
+**Agent Name:** {{.AgentName}}
+
+**Detected Temporal Intent:** {{.TemporalIntent}}
+
+Generate Ruby DSL code using this exact format (wrapped in triple-backticks with ruby):
+
+```ruby
+require 'language_operator'
+
+agent "{{.AgentName}}" do
+  description "Brief description extracted from instructions"
+{{.PersonaSection}}{{.ScheduleSection}}
+  # Extract objectives from instructions
+  objectives [
+    "First objective",
+    "Second objective"
+  ]
+
+  # Define workflow if instructions mention specific steps
+  # workflow do
+  #   step :step_name, tool: "tool_name", params: {key: "value"}
+  #   step :another_step, depends_on: :step_name
+  # end
+
+{{.ConstraintsSection}}
+
+  # Output configuration (if workspace enabled)
+  output do
+    workspace "results/output.txt"
+  end
+end
+```
+
+**Rules:**
+1. Generate ONLY the Ruby code within triple-backticks, no explanations before or after
+{{.ScheduleRules}}
+5. Break down instructions into clear, actionable objectives
+6. Create workflow steps if instructions describe a process
+7. Use available tools in workflow steps
+8. Use the agent name: "{{.AgentName}}"
+
+Generate the code now:

data/lib/language_operator/templates/examples/persona_distillation.tmpl

@@ -0,0 +1,19 @@
+Distill this persona into a single concise paragraph for an AI agent.
+
+**Persona Details:**
+Name: {{.PersonaName}}
+Description: {{.PersonaDescription}}
+System Prompt: {{.PersonaSystemPrompt}}
+Tone: {{.PersonaTone}}
+Language: {{.PersonaLanguage}}
+
+**Agent Context:**
+Goal: {{.AgentInstructions}}
+Available Tools: {{.AgentTools}}
+
+Generate a single paragraph (2-4 sentences) that captures the essence of this persona
+in the context of the agent's goal. Focus on tone, expertise, and key behaviors.
+
+Output ONLY the distilled persona paragraph, nothing else.
+
+Distilled persona:

data/lib/language_operator/templates/schema/CHANGELOG.md

@@ -0,0 +1,93 @@
+# Schema Changelog
+
+This file tracks changes to the Language Operator Agent DSL schema.
+
+## Schema Versioning
+
+The schema version is tied directly to the gem version and follows [Semantic Versioning](https://semver.org/):
+
+- **MAJOR** version: Breaking changes to DSL structure or behavior
+- **MINOR** version: New features, backward-compatible additions
+- **PATCH** version: Bug fixes, documentation improvements
+
+## Version History
+
+### 0.1.30 (2025-11-12)
+
+**Initial schema artifact generation**
+
+This is the first release with auto-generated schema artifacts included in the gem package.
+
+**Schema Features:**
+- Complete JSON Schema v7 for Agent DSL
+- OpenAPI 3.0.3 specification for agent HTTP endpoints
+- Agent configuration properties (name, description, persona, mode, schedule, objectives)
+- Workflow definitions with step dependencies
+- Constraint definitions (budgets, rate limits, timeouts)
+- Output destinations (workspace, Slack, email)
+- Webhook definitions with authentication
+- MCP server configuration
+- Chat endpoint configuration (OpenAI-compatible)
+- Tool and parameter definitions
+
+**API Endpoints Documented:**
+- `GET /health` - Health check
+- `GET /ready` - Readiness check
+- `POST /v1/chat/completions` - OpenAI-compatible chat endpoint
+- `GET /v1/models` - List available models
+
+**Safe Methods:**
+- Agent DSL methods validated via `Agent::Safety::ASTValidator`
+- Tool DSL methods for parameter definitions
+- Helper methods for HTTP, Shell, validation, and utilities
+
+---
+
+## Future Versions
+
+### Template for New Entries
+
+```markdown
+### X.Y.Z (YYYY-MM-DD)
+
+**Summary of changes**
+
+**Breaking Changes:**
+- Description of any breaking changes
+
+**New Features:**
+- New DSL methods or capabilities added
+- New endpoint specifications
+
+**Improvements:**
+- Schema validation enhancements
+- Documentation updates
+
+**Bug Fixes:**
+- Schema corrections
+- Type definition fixes
+
+**Deprecated:**
+- Features marked for removal in future versions
+```
+
+---
+
+## Schema Validation
+
+The schema can be used for:
+- **Template Validation** - Ensuring synthesized agent code is valid
+- **Documentation Generation** - Auto-generating reference docs
+- **IDE Support** - Providing autocomplete and IntelliSense
+- **CLI Introspection** - Runtime validation of agent definitions
+
+## Schema Artifacts
+
+Generated artifacts are stored in this directory:
+- `agent_dsl_schema.json` - JSON Schema v7 specification
+- `agent_dsl_openapi.yaml` - OpenAPI 3.0.3 specification
+
+These are regenerated automatically during the build process via:
+```bash
+rake schema:generate
+```

data/lib/language_operator/templates/schema/agent_dsl_openapi.yaml

@@ -0,0 +1,306 @@
+---
+:openapi: 3.0.3
+:info:
+  :title: Language Operator Agent API
+  :version: 0.1.31
+  :description: HTTP API endpoints exposed by Language Operator reactive agents
+  :contact:
+    :name: Language Operator
+    :url: https://github.com/language-operator/language-operator-gem
+  :license:
+    :name: FSL-1.1-Apache-2.0
+    :url: https://github.com/language-operator/language-operator-gem/blob/main/LICENSE
+:servers:
+- :url: http://localhost:8080
+  :description: Local development server
+:paths:
+  "/health":
+    :get:
+      :summary: Health check
+      :description: Returns the health status of the agent
+      :operationId: getHealth
+      :tags:
+      - Health
+      :responses:
+        :200:
+          :description: Agent is healthy
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/HealthResponse"
+  "/ready":
+    :get:
+      :summary: Readiness check
+      :description: Returns whether the agent is ready to accept requests
+      :operationId: getReady
+      :tags:
+      - Health
+      :responses:
+        :200:
+          :description: Agent is ready
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/HealthResponse"
+        :503:
+          :description: Agent is not ready
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/ErrorResponse"
+  "/v1/chat/completions":
+    :post:
+      :summary: Create chat completion
+      :description: Creates a chat completion response (OpenAI-compatible endpoint)
+      :operationId: createChatCompletion
+      :tags:
+      - Chat
+      :requestBody:
+        :required: true
+        :content:
+          :application/json:
+            :schema:
+              :$ref: "#/components/schemas/ChatCompletionRequest"
+      :responses:
+        :200:
+          :description: Successful chat completion response
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/ChatCompletionResponse"
+            :text/event-stream:
+              :description: Server-sent events stream (when stream=true)
+              :schema:
+                :type: string
+        :400:
+          :description: Invalid request
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/ErrorResponse"
+  "/v1/models":
+    :get:
+      :summary: List models
+      :description: Lists available models (OpenAI-compatible endpoint)
+      :operationId: listModels
+      :tags:
+      - Models
+      :responses:
+        :200:
+          :description: List of available models
+          :content:
+            :application/json:
+              :schema:
+                :$ref: "#/components/schemas/ModelList"
+:components:
+  :schemas:
+    :ChatCompletionRequest:
+      :type: object
+      :required:
+      - model
+      - messages
+      :properties:
+        :model:
+          :type: string
+          :description: Model name to use for completion
+        :messages:
+          :type: array
+          :description: List of messages in the conversation
+          :items:
+            :$ref: "#/components/schemas/ChatMessage"
+        :temperature:
+          :type: number
+          :description: Sampling temperature (0.0-2.0)
+          :minimum: 0.0
+          :maximum: 2.0
+          :default: 0.7
+        :max_tokens:
+          :type: integer
+          :description: Maximum tokens in response
+          :minimum: 1
+          :default: 2000
+        :stream:
+          :type: boolean
+          :description: Stream responses as server-sent events
+          :default: false
+        :top_p:
+          :type: number
+          :description: Nucleus sampling parameter
+          :minimum: 0.0
+          :maximum: 1.0
+          :default: 1.0
+        :frequency_penalty:
+          :type: number
+          :description: Frequency penalty (-2.0 to 2.0)
+          :minimum: -2.0
+          :maximum: 2.0
+          :default: 0.0
+        :presence_penalty:
+          :type: number
+          :description: Presence penalty (-2.0 to 2.0)
+          :minimum: -2.0
+          :maximum: 2.0
+          :default: 0.0
+        :stop:
+          :oneOf:
+          - :type: string
+          - :type: array
+            :items:
+              :type: string
+          :description: Stop sequences for generation
+    :ChatCompletionResponse:
+      :type: object
+      :required:
+      - id
+      - object
+      - created
+      - model
+      - choices
+      :properties:
+        :id:
+          :type: string
+          :description: Unique identifier for the completion
+        :object:
+          :type: string
+          :description: Object type (always "chat.completion")
+          :enum:
+          - chat.completion
+        :created:
+          :type: integer
+          :description: Unix timestamp of creation
+        :model:
+          :type: string
+          :description: Model used for completion
+        :choices:
+          :type: array
+          :description: List of completion choices
+          :items:
+            :$ref: "#/components/schemas/ChatChoice"
+        :usage:
+          :$ref: "#/components/schemas/ChatUsage"
+    :ChatMessage:
+      :type: object
+      :required:
+      - role
+      - content
+      :properties:
+        :role:
+          :type: string
+          :description: Message role
+          :enum:
+          - system
+          - user
+          - assistant
+        :content:
+          :type: string
+          :description: Message content
+        :name:
+          :type: string
+          :description: Optional name of the message author
+    :ChatChoice:
+      :type: object
+      :required:
+      - index
+      - message
+      - finish_reason
+      :properties:
+        :index:
+          :type: integer
+          :description: Choice index
+        :message:
+          :$ref: "#/components/schemas/ChatMessage"
+        :finish_reason:
+          :type: string
+          :description: Reason for completion finish
+          :enum:
+          - stop
+          - length
+          - content_filter
+          - 'null'
+    :ChatUsage:
+      :type: object
+      :required:
+      - prompt_tokens
+      - completion_tokens
+      - total_tokens
+      :properties:
+        :prompt_tokens:
+          :type: integer
+          :description: Tokens in the prompt
+        :completion_tokens:
+          :type: integer
+          :description: Tokens in the completion
+        :total_tokens:
+          :type: integer
+          :description: Total tokens used
+    :ModelList:
+      :type: object
+      :required:
+      - object
+      - data
+      :properties:
+        :object:
+          :type: string
+          :description: Object type (always "list")
+          :enum:
+          - list
+        :data:
+          :type: array
+          :description: List of available models
+          :items:
+            :$ref: "#/components/schemas/Model"
+    :Model:
+      :type: object
+      :required:
+      - id
+      - object
+      :properties:
+        :id:
+          :type: string
+          :description: Model identifier
+        :object:
+          :type: string
+          :description: Object type (always "model")
+          :enum:
+          - model
+        :created:
+          :type: integer
+          :description: Unix timestamp of model creation
+        :owned_by:
+          :type: string
+          :description: Organization that owns the model
+    :HealthResponse:
+      :type: object
+      :required:
+      - status
+      :properties:
+        :status:
+          :type: string
+          :description: Health status
+          :enum:
+          - ok
+          - ready
+        :timestamp:
+          :type: string
+          :format: date-time
+          :description: Timestamp of health check
+    :ErrorResponse:
+      :type: object
+      :required:
+      - error
+      :properties:
+        :error:
+          :type: object
+          :required:
+          - message
+          - type
+          :properties:
+            :message:
+              :type: string
+              :description: Error message
+            :type:
+              :type: string
+              :description: Error type
+            :code:
+              :type: string
+              :description: Error code