Merge branch 'release/1.3.2'

Author: dermatologist

.agents/skills/conch-generator/README.md

@@ -1,30 +1,24 @@
 # Agent Skills
 
-This directory contains agent skills for AI-powered coding assistants like GitHub Copilot, Claude, and other AI development tools.
+This directory contains agent skills for AI-powered coding assistants.
 
-## What are Agent Skills?
-
-Agent skills are specialized instructions that help AI coding assistants understand how to work with this repository. They provide context, workflows, and best practices specific to this project.
-
-## Available Skills
-
-### OpenMRS Conch Agent Skill (`SKILL.md`)
+### conch-generator skill (`SKILL.md`)
 
 This skill helps AI assistants generate new OpenMRS ESM microfrontends (conch) from this template. It provides comprehensive guidance on:
 
 - Setting up a development environment
 - Scaffolding new microfrontend projects
 - Implementing GenAI-powered features
 - Integrating with the OpenMRS 3.x ecosystem
-- Working with DHTI (Digital Health Technology & Innovation) services
+- Working with DHTI services
 
-**Use this skill when:** You need to create a new DHTI-enabled healthcare application or OpenMRS microfrontend.
+**Use this skill when:** You need to create a OpenMRS microfrontend for DHTI.
 
 ## Examples
 
 The `examples/` directory contains sample feature requests and use cases that demonstrate how to invoke and use these skills effectively.
 
-- `conch-sample-request.md` - Example of creating a glycemic control widget with GenAI integration
+- `conch-sample-request.md` - Example of creating a glycemic control widget with DHTI integration
 
 ## How to Use These Skills
 
@@ -36,7 +30,7 @@ When working with AI coding assistants that support custom skills:
 
 Example invocation:
 ```
-I need to create a new OpenMRS microfrontend using the DHTI template.
+I need to create a new OpenMRS microfrontend for DHTI.
 Please use the OpenMRS Conch Agent Skill with the following requirements:
 [Your feature request here]
 ```

.agents/skills/conch-generator/examples/conch-sample-request.md

@@ -1,7 +1,7 @@
-# Example: Glycemic Control Widget: This example demonstrates how to use the OpenMRS Conch Agent Skill to create a patient-specific widget that integrates GenAI capabilities.
+# Example: Glycemic Control Widget: This example demonstrates how to use the conch-generator Skill to create a patient-specific widget that integrates GenAI capabilities into OpenMRS using DHTI.
 
 * Generate a glycemic-advisor conch.
 * It will display diabetes-related observations for the patient in context with GenAI interpretations and recommendations.
 * This widget will be displayed in the patient chart, conditions tab.
 * This widget will use `glycemic_advisor` DHTI elixir service to get GenAI outputs, by default.
-* If a patient in context is diabetic (i.e., has a Condition resource with code SNOMED CT 44054006), the widget will display the latest HbA1c and Blood Sugar observations for the patient, along with GenAI interpretations and recommendations from the `glycemic_advisor` elixir service.
+* If a patient in context is diabetic (i.e., has a Condition resource with code SNOMED CT 44054006), the widget will display the latest HbA1c and Blood Sugar observations for the patient, along with GenAI interpretations and recommendations from the `glycemic_advisor` DHTI elixir service.

.agents/skills/elixir-generator/README.md

@@ -1,29 +1,28 @@
 # DHTI Elixir Generator Skill
 
-This directory contains an AI agent skill for automatically generating DHTI elixir projects from this template.
+This directory contains an AI agent skill for automatically generating DHTI elixir projects using DHTI.
 
-## Files
+## Directory Structure
 
 - **SKILL.md**: The main skill definition that guides AI agents through the elixir generation process
 - **examples/**: Directory containing example requests and use cases
-  - **basic-request.md**: General guidance and simple examples
+  - **basic-request.md**: A simple example of requesting an elixir for monitoring blood glucose levels
 
 ## How It Works
 
 When an AI agent accesses this skill, it can:
 
-1. Automatically set up a development environment
-2. Scaffold a new DHTI elixir project using cookiecutter
-3. Implement FHIR-based data retrieval
-4. Create LangChain chains for clinical decision support
-5. Generate tests and documentation
+1. Automatically set up a development environment.
+2. Scaffold a new DHTI elixir project.
+3. Implement FHIR-based data retrieval.
+4. Create LangChain chains for clinical decision support,
+5. Generate tests and documentation.
 
 ## Usage
 
 To use this skill with an AI agent:
 
-1. Ensure your AI agent has access to this skills directory
-2. Describe your elixir requirements, including:
+1. Describe your elixir requirements, including:
    - Clinical functionality needed
    - FHIR resources to query
    - Project name and slug (must start with `dhti-elixir-` / `dhti_elixir_`)
@@ -32,10 +31,8 @@ To use this skill with an AI agent:
 ## Example Request
 
 ```
-Please create a DHTI elixir that monitors blood glucose and HbA1c levels
+Please create a DHTI elixir called glycemic_advisor elixir.that monitors blood glucose and HbA1c levels
 for diabetes patients over the last 6 months and provides clinical recommendations.
-Project name: dhti-elixir-glycemic
-Project slug: dhti_elixir_glycemic
 ```
 
 See the `examples/` directory for more detailed examples.
@@ -44,7 +41,6 @@ See the `examples/` directory for more detailed examples.
 
 - The AI agent must have access to execute shell commands
 - The development environment needs Python and `uv` package manager
-- Network access to clone cookiecutter templates
 
 ## Output
 

.agents/skills/start-dhti/README.md

@@ -5,8 +5,6 @@ This directory contains an AI agent skill for orchestrating complete DHTI applic
 ## Overview
 
 The **start-dhti** skill is an orchestration skill that combines:
-- Elixir generation (backend GenAI logic)
-- Conch generation (frontend UI components)
 - Local directory installation (new `-l` flag feature)
 - DHTI server setup and deployment
 
@@ -16,103 +14,62 @@ This skill enables end-to-end development of GenAI healthcare applications withi
 
 - **SKILL.md**: The main skill definition with detailed step-by-step instructions
 - **examples/**: Directory containing complete workflow examples
-  - **quick-start.md**: Quick reference guide for common scenarios
+  - **quick-start.md**: A simple example of generating and starting a DHTI application.
 
 ## How It Works
 
 When an AI agent uses this skill, it will:
 
-1. **Generate Backend (Elixir)**:
-   - Invoke elixir-generator skill to create Python-based GenAI backend
-   - Implements FHIR integration and clinical logic
-   - Creates LangServe-compatible service
-
-2. **Generate Frontend (Conch)**:
-   - Invoke conch-generator skill to create OpenMRS microfrontend
-   - Implements patient-context-aware UI
-   - Integrates with DHTI service
-
-3. **Set Up Infrastructure**:
+1. **Set Up Infrastructure**:
    - Create Docker Compose with necessary services
    - Configure OpenMRS, LangServe, FHIR server, etc.
 
-4. **Install from Local Directories**:
+2. **Install from Local Directories**:
    - Use new `-l` flag to install generated elixir from local directory
    - Use new `-l` flag to install generated conch from local directory
    - Build Docker images for both components
 
-5. **Start and Verify**:
+3. **Start and Verify**:
    - Launch all services with Docker Compose
    - Verify integration and functionality
    - Provide access instructions
 
+4. **Facilitate Hot Reloading**:
+   - Allow developers to make changes to elixir and conch code
+   - Restart services to see updates without rebuilding everything
+
 ## Usage
 
 ### Basic Invocation
 
 ```
-I need to create a complete DHTI application with the following requirements:
-
-Elixir (Backend):
-- [Describe the GenAI functionality, FHIR resources, clinical logic]
-
-Conch (Frontend):
-- [Describe the UI components, patient context, user interactions]
-
 Please use the start-dhti skill to generate, install, and start the complete application.
 ```
 
-### With Specific Requirements
-
-```
-Create a DHTI application for glycemic control monitoring:
-
-Elixir Requirements (build using elixir-generator skill):
-- Monitor blood glucose and HbA1c levels for diabetic patients
-- Query FHIR Observation resources for the last 6 months
-- Use LangChain to analyze trends and provide recommendations
-- Project name: dhti-elixir-glycemic
-- Project slug: dhti_elixir_glycemic
-
-Conch Requirements (build using conch-generator skill):
-- Display glycemic control widget in patient chart conditions tab
-- Show latest HbA1c and blood glucose readings
-- Display AI-generated interpretations and recommendations
-- Project name: openmrs-esm-dhti-glycemic
-- Only show for patients with diabetes diagnosis (SNOMED CT 44054006)
-
-Please use the start-dhti skill to build this application.
-```
-
 ## Prerequisites
 
 Users of this skill need:
 - Node.js >= 18.0.0
 - Docker and Docker Compose
-- Python 3.x
+- Python 3.x (Optional for local development and testing)
 - Sufficient disk space for Docker images (~5-10 GB)
 
 
 ## Troubleshooting
 
 Common issues:
 
-1. **Skill invocation fails**:
-   - Ensure elixir-generator and conch-generator skills are available
-   - Check that all prerequisites are installed
-   - Verify Docker is running
-
-2. **Generation fails**:
+1. **Generation fails**:
    - Check requirements are clear and specific
    - Ensure project names follow conventions
    - Verify network connectivity for cookiecutter
 
-3. **Installation fails**:
+2. **Installation fails**:
    - Verify generated directories exist
    - Check paths are correct (absolute paths recommended)
    - Ensure directory structure matches expected format
 
-4. **Services don't start**:
+3. **Services don't start**:
    - Check port availability (80, 8080, 8000)
    - Verify Docker has sufficient resources
    - Check Docker logs for specific errors

.agents/skills/start-dhti/SKILL.md

@@ -203,8 +203,9 @@ NOTE the `Application link` in the output rather than the final display link.
    - Monitor logs: `docker compose logs -f`
 
 13. **Hand off with the following instructions:**
-   - Use the `Application link`: <<application-link>>
-   - Open this in browser to access the application
+   - Request the user to run `npx dhti-cli elixir start -n <<elixir-name>>` to start the CDS-Hooks container with the elixir.
+   - Display the `Application link`: <<application-link>>
+   - Request to open application link in browser to access it.
 
 ### Phase 9: Clean Up (If Needed)
 

.agents/skills/start-dhti/examples/quick-start.md

@@ -1,18 +1,10 @@
-# Quick Start Guide
+## Minimal for start DHTI with elixir and conch
+Use start-dhti skill to:
+* Spin up dhti with only langserve modules.
+* Install the local elixir glycemic_advisor.
+* Install the local conch esm-glycemic-advisor.
+* Start the docker container.
+* Verify everything is working end to end.
+* Start openmrs and it in browser.
 
-This is a  reference for using the start-dhti skill to create complete DHTI applications.
 
-## Minimal Example
-
-
-Create a simple DHTI application:
-
-1. Spin up dhti with only langserve modules.
-2. Install the elixir from the directory workspace/dhti-elixir/packages/glycemic_advisor.
-3. Install the conch from the directory workspace/openmrs-esm-dhti/packages/esm-glycemic-advisor.
-4. Start the docker container.
-5. Verify everything is working end to end.
-6. Start openmrs and it in browser.
-
-
-Use start-dhti skill.

CHANGELOG.md

@@ -2,10 +2,16 @@
 
 ## [Unreleased](https://github.com/dermatologist/dhti/tree/HEAD)
 
-[Full Changelog](https://github.com/dermatologist/dhti/compare/1.3.0...HEAD)
+[Full Changelog](https://github.com/dermatologist/dhti/compare/1.3.1...HEAD)
+
+**Closed issues:**
+
+- Add additional models [\#123](https://github.com/dermatologist/dhti/issues/123)
 
 **Merged pull requests:**
 
+- Add supported models list to copilot command flag description [\#124](https://github.com/dermatologist/dhti/pull/124) ([Copilot](https://github.com/apps/copilot-swe-agent))
+- Feature/fix skills 3 [\#122](https://github.com/dermatologist/dhti/pull/122) ([dermatologist](https://github.com/dermatologist))
 - Feature/fix start skill 1 [\#121](https://github.com/dermatologist/dhti/pull/121) ([dermatologist](https://github.com/dermatologist))
 - Add GitHub Copilot SDK integration with skill-based streaming AI assistance and stateful conversations [\#120](https://github.com/dermatologist/dhti/pull/120) ([Copilot](https://github.com/apps/copilot-swe-agent))
 - Feature/agent skills 2 [\#118](https://github.com/dermatologist/dhti/pull/118) ([dermatologist](https://github.com/dermatologist))
@@ -33,6 +39,10 @@
 - Feature/bump fix 1 [\#87](https://github.com/dermatologist/dhti/pull/87) ([dermatologist](https://github.com/dermatologist))
 - Feature/copy bootstrap [\#86](https://github.com/dermatologist/dhti/pull/86) ([dermatologist](https://github.com/dermatologist))
 
+## [1.3.1](https://github.com/dermatologist/dhti/tree/1.3.1) (2026-02-14)
+
+[Full Changelog](https://github.com/dermatologist/dhti/compare/1.3.0...1.3.1)
+
 ## [1.3.0](https://github.com/dermatologist/dhti/tree/1.3.0) (2026-02-14)
 
 [Full Changelog](https://github.com/dermatologist/dhti/compare/1.2.0...1.3.0)

README.md

@@ -14,7 +14,7 @@
 > 🚀 Dhanvantari rose out of the water with his four hands, holding a pot full of elixirs.
 
 # DHTI
-*DHTI enables rapid prototyping, sharing, and testing of GenAI healthcare applications inside an EHR, helping experiments move smoothly into practice. DHTI also includes [skills](/.github/skills/) that generate GenAI components from problem‑oriented [prompts](/prompts/e2e-sample.md).*
+*DHTI enables rapid prototyping, sharing, and testing of GenAI healthcare applications inside an EHR, helping experiments move smoothly into practice. DHTI also includes [skills](/.agents/skills/) that generate GenAI components from problem‑oriented [prompts](/.agents/skills/start-dhti/examples/e2e-sample.md).*
 
 ### Why?
 
@@ -32,7 +32,12 @@ DHTI includes ready‑to‑use [skills](/.agents/skills/) that can prompt agenti
 
 Other skills from the open agent skills ecosystem may be useful too! For example, use `npx skills find clinical trial` to find clinical trial related skills. From the results, you can use `npx skills add <skill-name>` to use the skill in your agentic platform. (e.g.`npx skills add anthropics/healthcare@clinical-trial-protocol-skill`)
 
-**🤖 [AI-Powered Workflow with GitHub Copilot SDK:](/notes/COPILOT.md) - WIP**
+## **🤖 [AI-Powered Workflow with GitHub Copilot SDK:](/notes/COPILOT.md) - WIP**
+### Quick example
+```bash
+npx dhti-cli copilot --model gpt-5.3-codex --skill elixir-generator --prompt "Generate an elixir glycemic_advisor that summarizes diabetic patients' latest lab results and medications"
+npx dhti-cli copilot --model gpt-5.3-codex --skill start-dhti --prompt "Start the glycemic_advisor elixir and display in CDS-Hooks sandbox"
+```
 
 ## Try it out
 [[Cheatsheet](/notes/cheatsheet.md) | [Download PDF Cheatsheet](https://nuchange.ca/wp-content/uploads/2026/01/dhti_cheatsheet.pdf)]

package.json

@@ -1,7 +1,7 @@
 {
   "name": "dhti-cli",
   "description": "DHTI CLI",
-  "version": "1.3.1",
+  "version": "1.3.2",
   "author": "Bell Eapen",
   "bin": {
     "dhti-cli": "bin/run.js"