Merge branch 'release/1.3.1' into main

Author: dermatologist

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

@@ -110,6 +110,31 @@ Use this skill when you need to:
     - Use the `useDhti` route from the monorepo (esm-dhti-utils) to call the DHTI service and get GenAI outputs. You need to update the DHTI service route (dhtiRoute) in the config-schema.ts file. If the user has not provided it above, ask for it using a prompt.
     If the user has only provided the DHTI service name, construct the full route as follows: http://localhost:8001/langserve/dhti_elixir_<service-name>/cds-services/dhti-service. Otherwise use the default value as 'http://localhost:8001/langserve/dhti_elixir_schat/cds-services/dhti-service'
 
+### Directory Structure
+
+```
+workspace/
+└── dhti-elixir/
+    └── packages/
+        └── <name>/                # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/dhti_elixir_<name>/   # Main code for the elixir
+            │   ├── chain.py              # Main chain implementation
+            │   ├── bootstrap.py          # Bootstrap/configuration file
+            │   ├── README.md             # Documentation for your elixir
+            │   └── (other files, e.g., __init__.py, utils.py)
+            ├── pyproject.toml            # Add new dependencies here
+            └── tests/
+                └── test_chain.py         # Example test file for chain.py
+└── openmrs-esm-dhti/
+    └── packages/
+        └── esm-dhti-<name>/           # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/   # Main code for the conch with multiple subdirectories.
+            ├── package.json          # Update dependencies and metadata here
+            └── README.md             # Documentation for your conch
+```
+
 ## Implementation Steps
 
     - Start implementing the feature based on your plans. Follow best practices for React and OpenMRS frontend-module development. When you are in doubt refer to the implementation guide here: https://r.jina.ai/https://o3-docs.openmrs.org/docs/frontend-modules/overview. Test your code frequently to ensure it works as expected.

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

@@ -88,6 +88,31 @@ di["dhti_elixir_<<name>>_cds_hook_discovery"] = {  # <- <<name>>
 }
 ```
 
+### Directory Structure
+
+```
+workspace/
+└── dhti-elixir/
+    └── packages/
+        └── <name>/                # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/dhti_elixir_<name>/   # Main code for the elixir
+            │   ├── chain.py              # Main chain implementation
+            │   ├── bootstrap.py          # Bootstrap/configuration file
+            │   ├── README.md             # Documentation for your elixir
+            │   └── (other files, e.g., __init__.py, utils.py)
+            ├── pyproject.toml            # Add new dependencies here
+            └── tests/
+                └── test_chain.py         # Example test file for chain.py
+└── openmrs-esm-dhti/
+    └── packages/
+        └── esm-dhti-<name>/           # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/   # Main code for the conch with multiple subdirectories.
+            ├── package.json          # Update dependencies and metadata here
+            └── README.md             # Documentation for your conch
+```
+
 ## High level functional requirements for chain.py and bootstrap.py implementation
 - **Align with the reference pattern:**
   - Mirror the structure, abstractions, and flow used in the reference chain.py and bootstrap.py.

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

@@ -28,6 +28,31 @@ The user conversation may provide context on the work you have done in the past.
    - Check that Node.js and Docker are installed
    - Verify Docker is running: `docker ps`
 
+2. **Directory Structure**
+
+```
+workspace/
+└── dhti-elixir/
+    └── packages/
+        └── <name>/                # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/dhti_elixir_<name>/   # Main code for the elixir
+            │   ├── chain.py              # Main chain implementation
+            │   ├── bootstrap.py          # Bootstrap/configuration file
+            │   ├── README.md             # Documentation for your elixir
+            │   └── (other files, e.g., __init__.py, utils.py)
+            ├── pyproject.toml            # Add new dependencies here
+            └── tests/
+                └── test_chain.py         # Example test file for chain.py
+└── openmrs-esm-dhti/
+    └── packages/
+        └── esm-dhti-<name>/           # Your generated elixir package
+            ├── notes/todo.md          # Your detailed TODO list and plan
+            ├── src/   # Main code for the conch with multiple subdirectories.
+            ├── package.json          # Update dependencies and metadata here
+            └── README.md             # Documentation for your conch
+```
+
 ### Phase 2: Set Up DHTI Infrastructure
 
 5. **Create Docker Compose Configuration:**

CHANGELOG.md

@@ -2,14 +2,11 @@
 
 ## [Unreleased](https://github.com/dermatologist/dhti/tree/HEAD)
 
-[Full Changelog](https://github.com/dermatologist/dhti/compare/1.2.0...HEAD)
-
-**Closed issues:**
-
-- Build a new command that uses the COPILOT-SDK to interact with DHTI and display results. [\#119](https://github.com/dermatologist/dhti/issues/119)
+[Full Changelog](https://github.com/dermatologist/dhti/compare/1.3.0...HEAD)
 
 **Merged pull requests:**
 
+- 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))
 - Feature/agent skills 1 [\#117](https://github.com/dermatologist/dhti/pull/117) ([dermatologist](https://github.com/dermatologist))
@@ -36,6 +33,14 @@
 - 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))
 
+## [1.3.0](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)
+
+**Closed issues:**
+
+- Build a new command that uses the COPILOT-SDK to interact with DHTI and display results. [\#119](https://github.com/dermatologist/dhti/issues/119)
+
 ## [1.2.0](https://github.com/dermatologist/dhti/tree/1.2.0) (2026-01-24)
 
 [Full Changelog](https://github.com/dermatologist/dhti/compare/1.1.0...1.2.0)

README.md

@@ -28,7 +28,7 @@ Generative AI features are built as [LangServe Apps](https://python.langchain.co
 🚀 Checkout **[Vidhi Recipes](/vidhi/README.md)** for chatbot, RAG, imaging (DICOM) and MCPX for dockerized calculators
 
 #### How (non‑technical / clinical)
-DHTI includes ready‑to‑use [skills](/.github/skills/) that can prompt agentic platforms (e.g., [AntiGravity](https://antigravity.google/), VSCode, or Claude) to generate the GenAI backends and UI components (elixirs and conches) you need. Test these components with synthetic data in OpenMRS or the CDS‑Hooks sandbox, then hand them off to production teams. Because DHTI follows open standards, that handoff (the “valley of death”) becomes smoother and more predictable. Try the [prompts](/.github/skills/start-dhti/examples/e2e-sample.md) in your preferred agentic platform after cloning this repo.
+DHTI includes ready‑to‑use [skills](/.agents/skills/) that can prompt agentic platforms (e.g., [AntiGravity](https://antigravity.google/), VSCode, or Claude) to generate the GenAI backends and UI components (elixirs and conches) you need. Test these components with synthetic data in OpenMRS or the CDS‑Hooks sandbox, then hand them off to production teams. Because DHTI follows open standards, that handoff (the “valley of death”) becomes smoother and more predictable. Try the [prompts](/.agents/skills/start-dhti/examples/e2e-sample.md) in your preferred agentic platform after cloning this repo.
 
 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`)
 

notes/COPILOT.md

@@ -4,11 +4,6 @@
 DHTI now integrates with GitHub Copilot SDK, enabling AI-assisted workflows directly from the command line with **stateful conversations**:
 
 ```bash
-# Interactive AI assistance with auto-skill detection
-npx dhti-cli copilot --prompt "Start the DHTI stack with langserve and ollama"
-
-# Continue the conversation - history is automatically maintained
-npx dhti-cli copilot --prompt "Now add redis to the configuration"
 
 # Use specific skills for specialized tasks
 npx dhti-cli copilot --prompt "Create a patient risk assessment elixir" --skill elixir-generator
@@ -22,6 +17,9 @@ npx dhti-cli copilot --clear-history --prompt "Start a new conversation"
 # Or just clear history without starting a new conversation
 npx dhti-cli copilot --clear-history
 
+# Interactive AI assistance with auto-skill detection
+npx dhti-cli copilot --prompt "Start the DHTI stack with langserve and ollama"
+
 # Available skills: start-dhti, elixir-generator, conch-generator, or auto (default)
 ```
 

package.json

@@ -1,7 +1,7 @@
 {
   "name": "dhti-cli",
   "description": "DHTI CLI",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "author": "Bell Eapen",
   "bin": {
     "dhti-cli": "bin/run.js"

src/commands/copilot.ts

@@ -11,8 +11,7 @@ import {fileURLToPath} from 'node:url'
  * and display results with streaming support.
  */
 export default class Copilot extends Command {
-  static override description =
-    'Interact with DHTI using GitHub Copilot SDK with streaming responses'
+  static override description = 'Interact with DHTI using GitHub Copilot SDK with streaming responses'
 
   static override examples = [
     '<%= config.bin %> <%= command.id %> --prompt "Start the DHTI stack with langserve"',
@@ -77,8 +76,19 @@ export default class Copilot extends Command {
       return 'conch-generator'
     }
 
-    // Default to start-dhti for general setup/orchestration
-    return 'start-dhti'
+    // Use start-dhti if prompt includes 'start', 'show', or 'run'
+    if (lowerPrompt.includes('start') || lowerPrompt.includes('show') || lowerPrompt.includes('run')) {
+      return 'start-dhti'
+    }
+
+    // If none of the skills match, exit asking for a skill name and show available skills
+    const availableSkills = ['start-dhti', 'elixir-generator', 'conch-generator']
+    this.error(
+      `Could not detect the appropriate skill from the prompt.\n` +
+        `Please specify a skill name using --skill.\n` +
+        `Available skills: ${availableSkills.join(', ')}`,
+    )
+    return ''
   }
 
   /**
@@ -245,7 +255,8 @@ export default class Copilot extends Command {
     }
 
     // Build system message with skill instructions
-    let systemMessageContent = 'You are a helpful assistant that can use specific skills to generate components of the DHTI stack based on user prompts.'
+    let systemMessageContent =
+      'You are a helpful assistant that can use specific skills to generate components of the DHTI stack based on user prompts.'
 
     // Add skill-specific instructions
     if (skillContent) {
@@ -322,13 +333,17 @@ export default class Copilot extends Command {
       }
 
       this.saveConversationHistory(conversationHistory)
-      this.log(chalk.dim(`💾 Conversation saved (${conversationHistory.length} messages). Use --clear-history to reset.`))
+      this.log(
+        chalk.dim(`💾 Conversation saved (${conversationHistory.length} messages). Use --clear-history to reset.`),
+      )
     } catch (error) {
       const errorMessage = error instanceof Error ? error.message : String(error)
       this.error(
         chalk.red(`Failed to interact with Copilot SDK: ${errorMessage}\n\n`) +
           chalk.yellow('Troubleshooting:\n') +
-          chalk.yellow('1. Ensure GitHub Copilot CLI is installed: https://docs.github.com/en/copilot/using-github-copilot/using-github-copilot-in-the-command-line\n') +
+          chalk.yellow(
+            '1. Ensure GitHub Copilot CLI is installed: https://docs.github.com/en/copilot/using-github-copilot/using-github-copilot-in-the-command-line\n',
+          ) +
           chalk.yellow('2. Authenticate with: copilot auth login\n') +
           chalk.yellow('3. Verify CLI is working: copilot --version\n'),
       )