@defai.digital/automatosx 12.8.7 → 13.1.2

package/examples/abilities/idea-evaluation.md

@@ -1,21 +0,0 @@
-Goal
-- Evaluate ideas against objectives, constraints, user value, and alternatives.
-
-How to do it
-- Clarify the objective, target users, and measurable outcomes.
-- Identify assumptions; label each as validated, unvalidated, or unknown.
-- Compare at least two alternatives; state trade‑offs.
-- Use simple scoring (e.g., 1–5) for value, cost, risk, and time.
-
-Do
-- Show a short decision table with criteria and scores.
-- Call out unknowns and how to validate them.
-- Provide an executive summary before details.
-
-Don’t
-- Don’t assume feasibility without evidence.
-- Don’t hide uncertainties; surface them with next steps.
-
-Output
-- A concise evaluation with assumptions, alternatives, scores, and a clear recommendation.
-

package/examples/abilities/infra-as-code.md

@@ -1,57 +0,0 @@
-# Infrastructure as Code
-
-Define and manage infrastructure through code using Terraform, Pulumi, or AWS CDK. Enable version control, reproducibility, and automation.
-
-## Do's ✅
-
-```hcl
-# ✅ Good: Modular Terraform
-resource "aws_vpc" "main" {
-  cidr_block = var.vpc_cidr
-  enable_dns_hostnames = true
-
-  tags = {
-    Name = "${var.project}-vpc"
-    Environment = var.environment
-  }
-}
-
-# ✅ Good: Remote state with locking
-terraform {
-  backend "s3" {
-    bucket         = "terraform-state"
-    key            = "prod/terraform.tfstate"
-    region         = "us-east-1"
-    encrypt        = true
-    dynamodb_table = "terraform-locks"
-  }
-}
-
-# ✅ Good: Use modules
-module "vpc" {
-  source  = "terraform-aws-modules/vpc/aws"
-  version = "~> 3.0"
-  name    = "${var.project}-vpc"
-  cidr    = var.vpc_cidr
-}
-```
-
-## Don'ts ❌
-
-```hcl
-# ❌ Bad: Hardcoded values
-resource "aws_instance" "web" {
-  ami           = "ami-0c55b159cbfafe1f0"  # Region-specific!
-  subnet_id     = "subnet-12345"  # Hardcoded
-}
-
-# ❌ Bad: Manual changes
-# Never modify infrastructure manually in console
-```
-
-## Best Practices
-- Use workspaces for environments (dev/staging/prod)
-- Enable state locking
-- Always run `terraform plan` before apply
-- Version pin modules and providers
-- Implement automated testing (Terratest)

package/examples/abilities/job-orchestration.md

@@ -1,44 +0,0 @@
-# Job Orchestration
-
-Schedule and orchestrate data jobs, pipelines, and workflows. Manage dependencies, retries, and monitoring using orchestration tools.
-
-## Do's ✅
-
-```python
-# ✅ Good: Clear task dependencies (Airflow)
-from airflow import DAG
-from airflow.operators.python import PythonOperator
-
-with DAG('user_pipeline', schedule='0 2 * * *') as dag:
-    extract = PythonOperator(task_id='extract', python_callable=extract_users)
-    transform = PythonOperator(task_id='transform', python_callable=transform_users)
-    load = PythonOperator(task_id='load', python_callable=load_users)
-
-    extract >> transform >> load
-
-# ✅ Good: Retry configuration
-PythonOperator(
-    task_id='api_call',
-    python_callable=call_api,
-    retries=3,
-    retry_delay=timedelta(minutes=5),
-    retry_exponential_backoff=True
-)
-```
-
-## Don'ts ❌
-
-```python
-# ❌ Bad: Complex dependencies
-task1 >> [task2, task3, task4] >> task5 >> [task6, task7] >> task8
-
-# ✅ Good: Logical groupings
-extract_tasks >> transform_task >> load_tasks
-```
-
-## Best Practices
-- Use task groups for related operations
-- Implement SLA monitoring
-- Configure alerting for failures
-- Version control DAG definitions
-- Use dynamic task generation when appropriate

package/examples/abilities/literature-review.md

@@ -1,19 +0,0 @@
-Goal
-- Summarize prior work and credible sources; extract insights and gaps.
-
-How to do it
-- Collect 5–10 relevant sources; prefer primary research or official docs.
-- For each source: key claim, method, limits, and applicability.
-- Synthesize themes; identify contradictions and open questions.
-
-Do
-- Provide inline citations (Author/Org, Year or URL).
-- Group findings by theme; call out where evidence is weak.
-
-Don’t
-- Don’t copy long quotes; summarize.
-- Don’t mix citation and commentary without clearly separating them.
-
-Output
-- A thematic summary with citations and a short “Implications for this project” section.
-

package/examples/abilities/longform-report.md

@@ -1,25 +0,0 @@
-Goal
-- Produce a structured, long‑form report suitable for stakeholders.
-
-Structure
-- Title, Author, Date
-- Executive Summary (bullets)
-- Background & Objectives
-- Methodology (how you reasoned / sources)
-- Findings (thematic)
-- Analysis (logic, feasibility, risks)
-- Options & Recommendations (w/ criteria)
-- Citations & Appendices
-
-Do
-- Use clear headings, short paragraphs, and lists.
-- Call out assumptions and uncertainties.
-- Add tables where helpful (scores, risks, timelines).
-
-Don’t
-- Don’t bury the lede—start with the summary.
-- Don’t omit sources when making claims.
-
-Output
-- A polished document following the above structure; aim for clarity over length.
-

package/examples/abilities/mathematical-reasoning.md

@@ -1,170 +0,0 @@
-# Mathematical Reasoning
-
-## Description
-Rigorous mathematical analysis capabilities spanning linear algebra, calculus, probability, numerical methods, and symbolic reasoning to support research-grade problem solving, model verification, and algorithm design for Bob and Data Scientist while powering Quinn and Astrid workflows.
-
-## Core Domains
-
-### 1. Linear Algebra
-- Matrix algebra (addition, multiplication, transposition, trace/determinant)
-- Eigenvalue and eigenvector computation (power iteration, QR algorithm)
-- Singular value decomposition, low-rank approximations, and PCA linkage
-- Vector spaces, basis transformations, orthogonality, and projections
-- Positive definiteness checks, conditioning, and spectral properties
-
-```python
-import numpy as np
-
-A = np.array([[4., 2.], [1., 3.]])
-
-eigvals, eigvecs = np.linalg.eig(A)
-u, s, vt = np.linalg.svd(A)
-proj = A @ np.linalg.solve(A.T @ A, A.T)  # Least-squares projector
-
-cond_number = np.linalg.cond(A)
-```
-
-### 2. Calculus & Optimization
-- Differential calculus, gradients, Jacobians, Hessians
-- Line search, Newton, quasi-Newton, and trust-region methods
-- Constrained optimization (KKT conditions, Lagrange multipliers)
-- Convex analysis, duality, strong/weak convexity checks
-- Sensitivity analysis and automatic differentiation workflows
-
-```python
-import sympy as sp
-
-x, y = sp.symbols('x y', real=True)
-f = (x - 2)**2 + (y + 1)**2 + 3 * x * y
-grad = [sp.diff(f, var) for var in (x, y)]
-hessian = sp.hessian(f, (x, y))
-
-λ = sp.symbols('λ')
-constraint = x + y - 1
-lagrangian = f + λ * constraint
-kkt_eqs = [sp.diff(lagrangian, var) for var in (x, y, λ)]
-solution = sp.solve(kkt_eqs, (x, y, λ), dict=True)
-```
-
-### 3. Probability & Statistics
-- Probability distributions (continuous/discrete), conjugacy, transformations
-- Bayesian inference (posterior computation, MAP/MCMC, credible intervals)
-- Frequentist inference (hypothesis tests, p-values, confidence intervals)
-- Estimators, bias-variance trade-offs, sufficiency, asymptotics
-- Information measures (entropy, KL divergence, mutual information)
-
-```python
-import numpy as np
-from scipy import stats
-
-# Bayesian update for Beta-Binomial model
-prior_a, prior_b = 2, 2
-successes, trials = 18, 25
-posterior = stats.beta(prior_a + successes, prior_b + trials - successes)
-cred_interval = posterior.interval(0.95)
-evidence = stats.binom.pmf(successes, trials, prior_a / (prior_a + prior_b))
-
-# Frequentist hypothesis test
-sample = np.random.normal(loc=1.05, scale=0.2, size=40)
-t_stat, p_value = stats.ttest_1samp(sample, popmean=1.0)
-```
-
-### 4. Numerical Methods
-- Numerical integration (Gaussian quadrature, adaptive Simpson)
-- Root finding (Newton-Raphson, secant, bracketing methods)
-- ODE/PDE solvers (Runge-Kutta, implicit schemes, finite differences)
-- Stability and convergence analysis, stiffness diagnostics
-- Error bounds, conditioning, floating-point safeguards
-
-```python
-import numpy as np
-from scipy.integrate import quad, solve_ivp
-
-area, err = quad(lambda t: np.exp(-t**2), 0, np.inf)
-
-def logistic(t, y, r=1.2, K=10.0):
-    return r * y * (1 - y / K)
-
-solution = solve_ivp(logistic, (0, 20), [0.5], method="RK45", dense_output=True)
-stability = np.max(np.abs(np.linalg.eigvals([[0., 1.], [-4., -1.5]])))
-```
-
-### 5. Symbolic Computation
-- Formal manipulations (simplification, expansion, factorization)
-- Symbolic integration/differentiation and series expansions
-- Proof assistants for identity verification and equivalence checking
-- Symbolic linear algebra, polynomial resultants, Groebner bases
-- Derivation tracing with justification for documentation and review
-
-```python
-import sympy as sp
-
-t = sp.symbols('t', positive=True)
-series = sp.series(sp.sin(t) / t, t, 0, 6)
-identity = sp.simplify(sp.exp(sp.I * t) * sp.exp(-sp.I * t))
-proof = sp.Eq(sp.diff(sp.log(sp.factorial(t)), t), sp.digamma(t + 1))
-
-M = sp.Matrix([[1, 2], [3, 4]])
-eigen_decomp = M.eigenvects()
-```
-
-### 6. Mathematical Verification Notebooks
-- Structured Python notebooks using NumPy, SciPy, and SymPy for reproducible math experiments
-- Cells organized by assumptions → derivations → numerical validation → sensitivity checks
-- Parameterized widgets or YAML configs for scenario sweeps
-- Automatic assertion blocks to verify algebraic vs. numeric equivalence
-- Version-controlled notebooks (`.ipynb` or `.py` using Jupytext) with deterministic seeds
-
-```python
-# verification_notebook.py (Jupytext style)
-import numpy as np
-import sympy as sp
-from scipy.optimize import minimize
-
-np.random.seed(42)
-w = sp.symbols('w')
-symbolic_grad = sp.diff(sp.sin(w) + w**2, w)
-
-def objective(val):
-    return np.sin(val) + val**2
-
-res = minimize(objective, x0=[0.5])
-assert abs(symbolic_grad.subs({w: res.x[0]}) - 0) < 1e-6
-```
-
-## Best Practices
-1. **State Assumptions Explicitly**: Document domains, constraints, and approximation regimes before derivations.
-2. **Cross-Validate**: Confirm symbolic results with numerical experiments (Monte Carlo, sampling, discretization).
-3. **Track Units and Scaling**: Maintain dimensional consistency and rescale ill-conditioned problems.
-4. **Monitor Conditioning**: Inspect condition numbers and step sizes to pre-empt numerical instability.
-5. **Use Reproducible Seeds**: Fix random seeds and record solver tolerances for repeatability.
-6. **Validate Constraints**: Ensure solution candidates satisfy KKT or feasibility conditions post-optimization.
-
-## Common Workflows
-- Analytical derivation with SymPy → numerical verification via SciPy → documentation in notebook with Markdown proof steps.
-- Linear algebra pipelines converting symbolic expressions to callable NumPy functions for high-performance evaluation.
-- Bayesian model evaluation combining closed-form posteriors with MCMC diagnostics when conjugacy fails.
-- PDE prototyping using finite differences followed by spectral method comparison for convergence profiling.
-
-## Anti-patterns to Avoid
-1. ❌ Treating floating-point equality as exact; always compare with tolerance windows.
-2. ❌ Ignoring solver diagnostics (residual norms, iteration counts, Jacobian approximations).
-3. ❌ Skipping preconditioning for stiff or ill-conditioned linear systems.
-4. ❌ Mixing symbolic and numeric domains without explicit casting, leading to type errors or performance hits.
-5. ❌ Assuming convergence without verifying gradients/Hessians or constraint satisfaction.
-
-## Tooling & References
-- **Core Libraries**: NumPy, SciPy, SymPy, JAX, PyTorch (autograd), cvxpy
-- **Notebooks**: JupyterLab, VS Code notebooks, Jupytext for `.py` parity
-- **Visualization**: Matplotlib, Plotly, seaborn for residuals and convergence plots
-- **Verification**: hypothesis for property-based testing, pytest for deterministic assertions
-- **Resources**: Matrix Cookbook, Boyd & Vandenberghe’s Convex Optimization, Numerical Recipes, Probabilistic Machine Learning (Murphy)
-
-## Quick Checklist
-- [ ] Assumptions and variable domains documented
-- [ ] Symbolic derivations simplified and verified numerically
-- [ ] Conditioning and stability assessed with diagnostics
-- [ ] Optimization routines include gradient/Hessian validation
-- [ ] Probabilistic models report uncertainty (CI or posterior summaries)
-- [ ] Notebooks or scripts captured in version control with reproducible seeds
-

package/examples/abilities/observability.md

@@ -1,61 +0,0 @@
-# Observability
-
-Implement logging, metrics, and tracing to understand system behavior. Monitor health, troubleshoot issues, and optimize performance.
-
-## Three Pillars
-
-### 1. Logs
-```javascript
-// ✅ Good: Structured logging
-logger.info('User login', {
-  user_id: user.id,
-  ip: req.ip,
-  timestamp: new Date().toISOString()
-});
-```
-
-### 2. Metrics
-```javascript
-// ✅ Good: Application metrics (Prometheus)
-const counter = new promClient.Counter({
-  name: 'http_requests_total',
-  help: 'Total HTTP requests',
-  labelNames: ['method', 'route', 'status']
-});
-
-app.use((req, res, next) => {
-  res.on('finish', () => {
-    counter.inc({ method: req.method, route: req.route, status: res.statusCode });
-  });
-});
-```
-
-### 3. Traces
-```javascript
-// ✅ Good: Distributed tracing
-const span = tracer.startSpan('get_user');
-try {
-  const user = await db.getUser(id);
-  res.json(user);
-} finally {
-  span.finish();
-}
-```
-
-## Don'ts ❌
-
-```javascript
-// ❌ Bad: Log sensitive data
-logger.info('Login', { username, password });  // Never!
-
-// ❌ Bad: Unstructured logs
-console.log('User ' + user.id + ' logged in');
-```
-
-## Best Practices
-- Use log levels appropriately
-- Implement correlation IDs for tracing
-- Set up dashboards for key metrics
-- Configure alerts with thresholds
-- Use APM tools (Datadog, New Relic)
-- Implement SLOs and error budgets

package/examples/abilities/orbital-mechanics.md

@@ -1,50 +0,0 @@
-# Orbital Mechanics
-
-## Overview
-
-Analyze orbital dynamics for spacecraft, including multi-body perturbations,
-station-keeping strategies, and maneuver planning that respects mission
-constraints, propellant budgets, and operational safety.
-
-## Core Concepts & Best Practices
-
-- **Two-Body Foundations**: Master Keplerian elements, conic sections, Lambert
-  targeting, and orbital perturbation theory.
-- **Perturbation Modeling**: Incorporate J2 oblateness, atmospheric drag, solar
-  radiation pressure, and third-body effects in long-duration analyses.
-- **Maneuver Planning**: Design Hohmann, bi-elliptic, low-thrust, and
-  plane-change maneuvers; evaluate trade-offs between time, delta-v, and risk.
-- **Relative Motion**: Apply Clohessy-Wiltshire and Tschauner-Hempel equations
-  for rendezvous; integrate collision avoidance envelopes.
-- **Station-Keeping**: Develop periodic correction strategies for GEO, LEO
-  constellations, and Lagrange point orbits while balancing propellant and
-  pointing needs.
-
-## Tools & Methodologies
-
-- **Numerical Propagators**: Use GMAT, Orekit, STK, Basilisk, or custom
-  Runge-Kutta integrators with event detection for shadow entry or exit.
-- **Astrodynamics Libraries**: Leverage poliastro, NASA GMAT API, and JPL SPICE
-  kernels for ephemeris and frame transformations.
-- **Optimization Routines**: Employ differential correction, sequential
-  quadratic programming, or heuristic search for multi-burn sequences.
-- **Monte Carlo Analysis**: Simulate maneuver execution dispersions and
-  environmental uncertainties to bound state covariance growth.
-- **Validation & Verification**: Cross-check analytical solutions with
-  high-fidelity propagators; maintain traceability of gravitational models and
-  reference frames.
-
-## Example Scenario
-
-A mission team plans a lunar orbit insertion. They run Lambert targeting from
-translunar injection to perilune, account for Earth-Moon three-body
-perturbations using GMAT, and apply sequential quadratic programming to
-minimize delta-v while satisfying lighting constraints for optical navigation.
-
-## Reference Resources
-
-- Vallado, *Fundamentals of Astrodynamics and Applications*, Microcosm Press
-- Curtis, *Orbital Mechanics for Engineering Students*, Butterworth-Heinemann
-- NASA GMAT User Guide: <https://gmatcentral.org>
-- Orekit Documentation: <https://www.orekit.org>
-- JPL SPICE Toolkit: <https://naif.jpl.nasa.gov/naif/toolkit.html>

package/examples/abilities/our-architecture-decisions.md

@@ -1,180 +0,0 @@
-# Our Architecture Decisions - AutomatosX v5
-
-> Key architectural decisions and rationale for AutomatosX
-
-## ADR-001: SQLite FTS5 Over Milvus
-
-**Decision:** Use SQLite with FTS5 full-text search instead of Milvus
-
-**Rationale:**
-
-- v3.1 used Milvus (340MB bundle, complex setup)
-- SQLite FTS5 offers < 1ms search performance
-- Simple setup, no external services
-
-**Impact:**
-
-- ✅ Bundle: 340MB → 381KB (99.9% reduction)
-- ✅ Fast text search (45ms → <1ms, 45x faster)
-- ✅ No embedding costs (removed vector search)
-- ❌ Limited to single-node (acceptable for CLI tool)
-
-## ADR-002: ESM Over CommonJS
-
-**Decision:** Use ES Modules (ESM) for entire codebase
-
-**Rationale:**
-
-- Node.js 24+ has first-class ESM support
-- Better tree-shaking and bundle optimization
-- Modern standards compliance
-
-**Impact:**
-
-- ✅ Better tree-shaking (smaller bundle)
-- ✅ Future-proof
-- ⚠️ Requires `.js` in imports (minor inconvenience)
-
-## ADR-003: TypeScript Strict Mode
-
-**Decision:** Enable all strict TypeScript checks
-
-**Configuration:**
-
-```json
-{
-  "strict": true,
-  "noUncheckedIndexedAccess": true,
-  "noImplicitOverride": true,
-  "noFallthroughCasesInSwitch": true
-}
-```
-
-**Impact:**
-
-- ✅ Fewer runtime errors
-- ✅ Better IDE support
-- ✅ Safer refactoring
-- ⚠️ More initial development time (worth it)
-
-## ADR-004: Three-Layer Security Model
-
-**Decision:** Implement path validation, workspace access control, and input sanitization
-
-**Layers:**
-
-1. **Path Resolution:** All file access through PathResolver
-2. **Workspace Access Control:** Shared workspaces with path validation
-3. **Input Validation:** Sanitize all user inputs
-
-**Impact:**
-
-- ✅ Prevents path traversal attacks
-- ✅ Controlled workspace access with validation
-- ✅ No privilege escalation
-- ⚠️ Slightly more complex file operations
-
-## ADR-005: Profile + Abilities = Agent
-
-**Decision:** Separate agent profile (YAML) from abilities (Markdown)
-
-**Structure:**
-
-- Profile: YAML with metadata, systemPrompt, abilities references
-- Abilities: Markdown files with domain knowledge
-- Agent = Profile + loaded Abilities
-
-**Impact:**
-
-- ✅ Reusable abilities across agents
-- ✅ Easy to add new knowledge
-- ✅ Clear separation of concerns
-- ✅ User can customize both independently
-
-## ADR-006: Team-Based Configuration
-
-**Decision:** Agents inherit configuration from their team
-
-**4 Built-in Teams:**
-
-- **core:** Quality assurance (primary: claude)
-- **engineering:** Software development (primary: codex)
-- **business:** Product & planning (primary: gemini)
-- **design:** Design & content (primary: gemini)
-
-**Impact:**
-
-- ✅ No configuration duplication
-- ✅ Change provider for entire team at once
-- ✅ Shared abilities automatically included
-- ✅ Centralized orchestration settings
-
-## ADR-007: Lazy Loading for Performance
-
-**Decision:** Defer expensive imports until needed
-
-**Implementation:**
-
-- Heavy modules use dynamic import: `await import('module')`
-- Core modules use static imports
-- LazyLoader utility for caching
-
-**Impact:**
-
-- ✅ Faster CLI startup (~200ms)
-- ✅ Smaller initial memory footprint
-- ✅ Pay for what you use
-
-## ADR-008: Vitest Over Jest
-
-**Decision:** Use Vitest as testing framework
-
-**Rationale:**
-
-- Modern test runner with native ESM support
-- Fast execution with watch mode
-- Compatible with Vite ecosystem
-
-**Impact:**
-
-- ✅ Fast test execution (1,149 tests in ~10s)
-- ✅ Native ESM support (no transform)
-- ✅ Great developer experience
-
-## ADR-009: TTL Cache for Profiles
-
-**Decision:** Cache loaded profiles with 5-minute TTL
-
-**Configuration:**
-
-- TTLCache with 5-minute TTL
-- Max 20 entries (LRU eviction)
-- Cleanup every 60 seconds
-
-**Impact:**
-
-- ✅ Faster repeated executions
-- ✅ Reduced file I/O
-- ✅ Automatic cache invalidation
-- ⚠️ 5-minute delay for profile updates (acceptable)
-
-## ADR-010: Provider Router Pattern
-
-**Decision:** Use Router to abstract provider selection
-
-**Features:**
-
-- Router manages provider selection
-- Retry with exponential backoff
-- Fallback to alternative providers
-
-**Impact:**
-
-- ✅ Provider flexibility
-- ✅ Resilience to provider failures
-- ✅ Easy to add new providers
-
----
-
-**Last Updated:** 2025-10-10
-**For:** AutomatosX v5.0+