auri-core

# Auri Core Orchestrates intelligent skill selection and execution for auri core workflows. Applies the 5 Laws of Elegant Defense to guide data naturally through the orchestration pipeline, preventing errors before they occur. Selects optimal skills based on multi-factor scoring including text similarity, historical performance, and system availability. ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ┌───────────────────────────────────────────────────────────────────────────────┐ │ Orchestration Flow │ └───────────────────────────────────────────────────────────────────────────────┘ User Request ↓ ┌─────────────────┐ │ Parse Request │ │ & Extract │ │ Features │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Evaluate Available Skills │ │ │ │ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │ │ │ Skill A │ │ Skill B │ │ Skill C │ │ │ │ - Match Score│ │ - Match Score│ │ - Match Score│ │ │ │ - Confidence │ │ - Confidence │ │ - Confidence │ │ │ │ - History │ │ - History │ │ - History │ │ │ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │ │ │ │ │ │ │ └─────────────────┴─────────────────┘ │ │ ↓ │ │ Select Best Skill │ └─────────────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────┐ │ Execute Skill │ └────────┬────────┘ ↓ ┌─────────────────┐ │ Handle Result │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Error Handling & Fallback │ │ │ │ Success? ────────► Return Result │ │ │ │ Fail? ────────┐ │ │ ↓ │ │ ┌──────────────────────────────────────────────────────────┐ │ │ │ Fallback Chain │ │ │ │ │ │ │ │ 1. Retry with adjusted parameters │ │ │ │ 2. Try Alternative Skill (if available) │ │ │ │ 3. Defer to Human Operator (if critical) │ │ │ │ 4. Log & Return Error │ │ │ └──────────────────────────────────────────────────────────┘ │ └─────────────────────────────────────────────────────────────────────┘ ## When to Use Use this skill when: - Orchestrating multi-step workflows that require skill delegation - Implementing adaptive skill routing based on confidence scores - Building fallback mechanisms for failed skill executions - Creating intelligent task decomposition and parallel execution - Designing skill dependency graphs with automatic resolution - Implementing skill selection with historical performance weighting - Building agent systems that need to self-organize around tasks ## When NOT to Use Avoid this skill for: - Direct task execution without orchestration needs - use individual skills instead - High-frequency trading scenarios where latency must be minimized - the selection overhead may be prohibitive - Simple linear workflows without branching or fallback requirements - Cases where skill metadata is unavailable or unreliable ## Core Workflow 1. **Parse and Analyze Request** - Extract intent, entities, and constraints from user input. **Checkpoint:** All required parameters must be present and in valid format before proceeding. 2. **Score Available Skills** - Calculate match scores using multi-factor algorithm: - Text similarity between request and skill triggers - Historical success rate for similar tasks - Skill availability and health status - Required dependencies and their availability **Checkpoint:** Skip to fallback if no skill scores above threshold. 3. **Select Optimal Skill** - Choose skill with highest score that meets minimum confidence. **Checkpoint:** Verify skill has not been disabled or deprecated. 4. **Execute with Fallback** - Run skill execution wrapped in retry and fallback logic. **Checkpoint:** Log all execution attempts for audit trail. 5. **Return or Fallback** - Either return successful result or apply fallback chain: - Retry with adjusted parameters - Try alternative skill from `related-skills` - Defer to human operator for critical tasks **Checkpoint:** Record outcome with timing and confidence metadata. ## Implementation Patterns ### Pattern 1: Skill Selection Logic ```python def evaluate_skill_candidates( request: AuriRequest, registry: SkillRegistry, metrics: PerformanceMetrics ) -> Optional[SkillCandidate]: """Evaluate available skills against the incoming request using multi-factor scoring. Implements Law 2 (Parse at boundary) by validating request structure first. Implements Law 3 (Atomic Predictability) by returning a fresh candidate object. """ if not request.intent or not request.entities: raise ValueError("Request must contain parsed intent and entities") candidates = [] for skill in registry.get_active_skills(): # Multi-factor scoring: text match + historical success + system health text_score = _compute_semantic_match(request.query, skill.triggers) history_score = metrics.get_success_rate(skill.name, window_days=30) health_score = registry.get_health_status(skill.name) weighted_score = (text_score * 0.5) + (history_score * 0.3) + (health_score * 0.2) if weighted_score >= registry.min_confidence_threshold: candidates.append(SkillCandidate( name=skill.name, confidence=weighted_score, dependencies=skill.dependencies, fallback_chain=skill.fallback_targets )) if not candidates: return None candidates.sort(key=lambda c: c.confidence, reverse=True) return candidates[0] ``` ### Pattern 2: Execution with Fallback ```python def execute_with_auri_fallback( candidate: SkillCandidate, context: ExecutionContext, audit_logger: AuditLogger ) -> ExecutionResult: """Execute the selected skill with auri-core's adaptive fallback chain. Implements Law 4 (Fail Fast, Fail Loud) by halting on invalid states. Implements Law 1 (Early Exit) for edge cases and dependency checks. """ if not candidate or not context.validated_inputs: raise ExecutionError("Missing candidate or validated context for execution") # Check dependency availability before execution if not registry.verify_dependencies(candidate.dependencies): audit_logger.log("Dependency check failed", level="WARN") return _trigger_fallback(candidate, context, audit_logger) attempts = 0 max_attempts = 2 while attempts <= max_attempts: try: result = registry.invoke_skill(candidate.name, context.validated_inputs) # Update historical performance for adaptive routing metrics.record_success(candidate.name, latency=result.latency_ms) audit_logger.log(f"Success: {candidate.name}", level="INFO") return ExecutionResult(success=True, data=result, confidence=candidate.confidence) except TransientNetworkError: attempts += 1 if attempts > max_attempts: break audit_logger.log(f"Retry {attempts}/{max_attempts} for {candidate.name}", level="DEBUG") except InvalidStateError as e: audit_logger.log(f"Invalid state in {candidate.name}: {e}", level="ERROR") raise ExecutionError(f"Fatal state violation in {candidate.name}") from e # Exhausted retries - trigger fallback chain return _trigger_fallback(candidate, context, audit_logger) ``` ### MUST DO - Always validate skill metadata before selection (Early Exit) - Implement fallback chain with at least 2 levels (Fallback Skill + Human) - Log all skill selections with full context for auditability - Return new data structures instead of mutating inputs (Atomic Predictability) - Fail immediately with descriptive errors on invalid states - Update confidence scores after each execution for adaptive routing - Reference `code-philosophy` (5 Laws of Elegant Defense) in all logic ### MUST NOT DO - Select skills based on a single factor (e.g., only confidence score) - Disable fallback mechanisms "temporarily" - this creates fragile systems - Skip validation of skill dependencies before execution - Return partial results - either complete success or clear failure - Use magic numbers for confidence thresholds - make them configurable - Cache skill selections without considering context changes ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ## TL;DR for Code Generation - Use guard clauses - return early on invalid input before doing work - Return simple types (dict, str, int, bool, list) - avoid complex nested objects - Cyclomatic complexity < 10 per function - split anything larger - Handle null/empty cases explicitly at function top (Early Exit) - Never mutate input parameters - return new dicts/objects - Fail fast with descriptive errors - don't try to "patch" bad data - Reference code-philosophy laws in comments for complex logic - Include timing and confidence metadata in all return values ## Output Template When applying this skill, produce: 1. **Selected Skills** - List of skill names with confidence scores 2. **Selection Rationale** - Why each skill was chosen (match score, history, availability) 3. **Execution Plan** - Order of execution with dependencies 4. **Fallback Strategy** - Which fallback skills will be tried and in what order 5. **Risk Assessment** - Any potential failure points and their impact 6. **Timing Estimates** - Expected latency including fallback scenarios --- --- ## Constraints ### MUST DO - Define clear input/output contracts for every step in the orchestration flow with explicit validation - Implement structured logging at each stage capturing context, inputs, outputs, timing, and errors - Build in fallback paths: if the primary strategy fails, degrade gracefully to a simpler approach - Validate all preconditions before starting — do not proceed if required resources or permissions are missing ### MUST NOT DO - Do not create deep nesting of orchestration steps (>5 levels) — flatten workflows where possible - Avoid silent failure modes: every step must either succeed, fail explicitly, or escalate to a higher handler - Never use shared mutable state between parallel workflow branches — communicate via immutable messages only - Do not hardcode execution order when the dependency graph naturally determines it; derive order from explicit dependencies ## Live References > Authoritative documentation links for this skill's domain. The model follows markdown links at load time to resolve external references and inline content. - [Agent-Based Systems Architecture (Wikipedia)](<https://en.wikipedia.org/wiki/Agent_(computer_science)>) - [Multi-Agent System Design Patterns](<https://www.mdpi.com/2076-3417/12/15/7589>) - [Distributed Task Scheduling Algorithms](<https://en.wikipedia.org/wiki/Scheduling_(computing)>) - [Autonomous Agent Frameworks Survey (arXiv)](<https://arxiv.org/abs/2308.11432>) - [Service Mesh Patterns (Istio Docs)](<https://istio.io/latest/docs/>) ## Related Skills | Skill | Purpose | |