Merge pull request #2 from pamelafox/pamela-examples

Add new examples, reorganize files, and improve repo setup

Author: pamelafox

.env.sample

@@ -1,11 +1,8 @@
-# API_HOST can be either azure, ollama, openai, or github:
+# API_HOST can be either azure, openai, or github:
 API_HOST=azure
 # Configure for Azure:
-AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com/openai/v1
+AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
 AZURE_OPENAI_CHAT_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
-# Configure for Ollama:
-OLLAMA_ENDPOINT=http://localhost:11434/v1
-OLLAMA_MODEL=llama3.1
 # Configure for OpenAI.com:
 OPENAI_API_KEY=YOUR-OPENAI-KEY
 OPENAI_MODEL=gpt-3.5-turbo

.gitattributes

@@ -0,0 +1,3 @@
+* text=auto
+*.sh text eol=lf
+*.ps1 text eol=crlf

.github/PULL_REQUEST_TEMPLATE.md

@@ -42,4 +42,4 @@ Verify that the following are valid
 * ...
 
 ## Other Information
-<!-- Add any other helpful information that may be needed here. -->
+<!-- Add any other helpful information that may be needed here. -->

.github/prompts/review_pr_comments.prompt.md

@@ -0,0 +1,136 @@
+---
+name: review_pr_comments
+description: This prompt is used to review comments on an active pull request and decide whether to accept, iterate, or reject the changes suggested in each comment.
+---
+We have received comments on the current active pull request. Together, we will go through each comment one by one and discuss whether to accept the change, iterate on it, or reject the change.
+
+## Steps to follow:
+
+1. Fetch the active pull request: If available, use the `activePullRequest` tool from the `GitHub Pull Requests` toolset to get the details of the active pull request including the comments. If not, use the GitHub MCP server or GitHub CLI to get the details of the active pull request. Fetch both top level comments and inline comments.
+2. Present a list of the comments with a one-sentence summary of each.
+3. One at a time, present each comment in full detail and ask me whether to accept, iterate, or reject the change. Provide your recommendation for each comment based on best practices, code quality, and project guidelines. Await user's decision before proceeding to the next comment. DO NOT make any changes to the code or files until I have responded with my decision for each comment.
+4. If the decision is to accept or iterate, make the necessary code changes to address the comment. If the decision is to reject, provide a brief explanation of why the change was not made.
+5. Wait for user to affirm completion of any code changes made before moving to the next comment.
+6. Reply to each comment on the pull request with the outcome of our discussion (accepted, iterated, or rejected) along with any relevant explanations.
+
+
+## How to reply to PR review comments
+
+This guide explains how to reply directly to inline review comments on GitHub pull requests.
+
+### API Endpoint
+
+To reply to an inline PR comment, use:
+
+```http
+POST /repos/{owner}/{repo}/pulls/{pull_number}/comments/{comment_id}/replies
+```
+
+With body:
+
+```json
+{
+  "body": "Your reply message"
+}
+```
+
+### Using gh CLI
+
+```bash
+gh api repos/{owner}/{repo}/pulls/{pull_number}/comments/{comment_id}/replies \
+  -X POST \
+  -f body="Your reply message"
+```
+
+### Workflow
+
+1. **Get PR comments**: First fetch the PR review comments to get their IDs:
+
+   ```bash
+   gh api repos/{owner}/{repo}/pulls/{pull_number}/comments
+   ```
+
+2. **Identify comment IDs**: Each comment has an `id` field. For threaded comments, use the root comment's `id`.
+
+3. **Post replies**: For each comment you want to reply to:
+
+   ```bash
+   gh api repos/{owner}/{repo}/pulls/{pull_number}/comments/{comment_id}/replies \
+     -X POST \
+     -f body="Fixed in commit abc123"
+   ```
+
+### Example Replies
+
+For accepted changes:
+
+- "Fixed in {commit_sha}"
+- "Accepted - fixed in {commit_sha}"
+
+For rejected changes:
+
+- "Rejected - {reason}"
+- "Won't fix - {explanation}"
+
+For questions:
+
+- "Good catch, addressed in {commit_sha}"
+
+## Notes
+
+- The `comment_id` is the numeric ID from the comment object, NOT the `node_id`
+- Replies appear as threaded responses under the original comment
+- You can reply to any comment, including bot comments (like Copilot reviews)
+
+### Resolving Conversations
+
+To resolve (mark as resolved) PR review threads, use the GraphQL API:
+
+1. **Get thread IDs**: Query for unresolved threads:
+
+   ```bash
+   gh api graphql -f query='
+   query {
+     repository(owner: "{owner}", name: "{repo}") {
+       pullRequest(number: {pull_number}) {
+         reviewThreads(first: 50) {
+           nodes {
+             id
+             isResolved
+             comments(first: 1) {
+               nodes { body path }
+             }
+           }
+         }
+       }
+     }
+   }'
+   ```
+
+2. **Resolve threads**: Use the `resolveReviewThread` mutation:
+
+   ```bash
+   gh api graphql -f query='
+   mutation {
+     resolveReviewThread(input: {threadId: "PRRT_xxx"}) {
+       thread { isResolved }
+     }
+   }'
+   ```
+
+3. **Resolve multiple threads at once**:
+
+   ```bash
+   gh api graphql -f query='
+   mutation {
+     t1: resolveReviewThread(input: {threadId: "PRRT_xxx"}) { thread { isResolved } }
+     t2: resolveReviewThread(input: {threadId: "PRRT_yyy"}) { thread { isResolved } }
+   }'
+   ```
+
+The thread ID starts with `PRRT_` and can be found in the GraphQL query response.
+
+Note: This skill can be removed once the GitHub MCP server has added built-in support for replying to PR review comments and resolving threads.
+See:
+https://github.com/github/github-mcp-server/issues/1323
+https://github.com/github/github-mcp-server/issues/1768

.github/workflows/azure-dev.yaml

@@ -56,4 +56,3 @@ jobs:
         run: azd provision --no-prompt
         env:
           AZD_INITIAL_ENVIRONMENT_CONFIG: ${{ secrets.AZD_INITIAL_ENVIRONMENT_CONFIG }}
-         

CONTRIBUTING.md

@@ -47,7 +47,7 @@ chances of your issue being dealt with quickly:
 * **Suggest a Fix** - if you can't fix the bug yourself, perhaps you can point to what might be
   causing the problem (line of code or commit)
 
-You can file new issues by providing the above information at the corresponding repository's issues link: 
+You can file new issues by providing the above information at the corresponding repository's issues link:
 replace`[organization-name]` and `[repository-name]` in
 `https://github.com/[organization-name]/[repository-name]/issues/new` .
 

LICENSE.md

@@ -18,4 +18,4 @@
     AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
     LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
     OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-    SOFTWARE
+    SOFTWARE

README.md

@@ -162,13 +162,17 @@ You can run the examples in this repository by executing the scripts in the `exa
 
 | Example | Description |
 | ------- | ----------- |
-| [basic.py](examples/basic.py) | Uses Agent Framework to build a basic informational agent. |
-| [tool.py](examples/tool.py) | Uses Agent Framework to build an agent with a single weather tool. |
-| [tools.py](examples/tools.py) | Uses Agent Framework to build a weekend planning agent with multiple tools. |
-| [supervisor.py](examples/supervisor.py) | Uses Agent Framework with a supervisor orchestrating activity and recipe sub-agents. |
-| [magenticone.py](examples/magenticone.py) | Uses Agent Framework to build a MagenticOne agent. |
-| [hitl.py](examples/hitl.py) | Uses Agent Framework with human-in-the-loop (HITL) for tool-enabled agents with human feedback. |
-| [workflow.py](examples/workflow.py) | Uses Agent Framework to build a workflow-based agent. |
+| [agent_basic.py](examples/agent_basic.py) | A basic informational agent. |
+| [agent_tool.py](examples/agent_tool.py) | An agent with a single weather tool. |
+| [agent_tools.py](examples/agent_tools.py) | A weekend planning agent with multiple tools. |
+| [agent_supervisor.py](examples/agent_supervisor.py) | A supervisor orchestrating activity and recipe sub-agents. |
+| [workflow_magenticone.py](examples/workflow_magenticone.py) | A MagenticOne multi-agent workflow. |
+| [workflow_hitl.py](examples/workflow_hitl.py) | Human-in-the-loop (HITL) for tool-enabled agents with human feedback. |
+| [agent_middleware.py](examples/agent_middleware.py) | Agent, chat, and function middleware for logging, timing, and blocking. |
+| [agent_mcp_remote.py](examples/agent_mcp_remote.py) | An agent using a remote MCP server (Microsoft Learn) for documentation search. |
+| [agent_mcp_local.py](examples/agent_mcp_local.py) | An agent connected to a local MCP server (e.g. for expense logging). |
+| [openai_tool_calling.py](examples/openai_tool_calling.py) | Tool calling with the low-level OpenAI SDK, showing manual tool dispatch. |
+| [workflow_basic.py](examples/workflow_basic.py) | A workflow-based agent. |
 
 ## Resources
 

examples/basic.py examples/agent_basic.pyexamples/basic.py renamed to examples/agent_basic.py

@@ -1,50 +1,46 @@
-import asyncio
-import os
-
-from agent_framework import ChatAgent
-from agent_framework.openai import OpenAIChatClient
-from azure.identity.aio import DefaultAzureCredential, get_bearer_token_provider
-from dotenv import load_dotenv
-from rich import print
-
-# Configure OpenAI client based on environment
-load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
-
-async_credential = None
-if API_HOST == "azure":
-    async_credential = DefaultAzureCredential()
-    token_provider = get_bearer_token_provider(async_credential, "https://cognitiveservices.azure.com/.default")
-    client = OpenAIChatClient(
-        base_url=f"{os.environ['AZURE_OPENAI_ENDPOINT']}/openai/v1/",
-        api_key=token_provider,
-        model_id=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
-    )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
-    )
-elif API_HOST == "ollama":
-    client = OpenAIChatClient(
-        base_url=os.environ.get("OLLAMA_ENDPOINT", "http://localhost:11434/v1"),
-        api_key="none",
-        model_id=os.environ.get("OLLAMA_MODEL", "llama3.1:latest"),
-    )
-else:
-    client = OpenAIChatClient(api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini"))
-
-agent = ChatAgent(chat_client=client, instructions="You're an informational agent. Answer questions cheerfully.")
-
-
-async def main():
-    response = await agent.run("Whats weather today in San Francisco?")
-    print(response.text)
-
-    if async_credential:
-        await async_credential.close()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
+import asyncio
+import os
+
+from agent_framework import ChatAgent
+from agent_framework.openai import OpenAIChatClient
+from azure.identity.aio import DefaultAzureCredential, get_bearer_token_provider
+from dotenv import load_dotenv
+from rich import print
+
+# Configure OpenAI client based on environment
+load_dotenv(override=True)
+API_HOST = os.getenv("API_HOST", "github")
+
+async_credential = None
+if API_HOST == "azure":
+    async_credential = DefaultAzureCredential()
+    token_provider = get_bearer_token_provider(async_credential, "https://cognitiveservices.azure.com/.default")
+    client = OpenAIChatClient(
+        base_url=f"{os.environ['AZURE_OPENAI_ENDPOINT']}/openai/v1/",
+        api_key=token_provider,
+        model_id=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
+    )
+elif API_HOST == "github":
+    client = OpenAIChatClient(
+        base_url="https://models.github.ai/inference",
+        api_key=os.environ["GITHUB_TOKEN"],
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+    )
+else:
+    client = OpenAIChatClient(
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+    )
+
+agent = ChatAgent(chat_client=client, instructions="You're an informational agent. Answer questions cheerfully.")
+
+
+async def main():
+    response = await agent.run("Whats weather today in San Francisco?")
+    print(response.text)
+
+    if async_credential:
+        await async_credential.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/agent_mcp_local.py

@@ -0,0 +1,67 @@
+import asyncio
+import logging
+import os
+from datetime import datetime
+
+from agent_framework import ChatAgent, MCPStreamableHTTPTool
+from agent_framework.openai import OpenAIChatClient
+from azure.identity.aio import DefaultAzureCredential, get_bearer_token_provider
+from dotenv import load_dotenv
+from rich import print
+from rich.logging import RichHandler
+
+# Setup logging
+handler = RichHandler(show_path=False, rich_tracebacks=True, show_level=False)
+logging.basicConfig(level=logging.WARNING, handlers=[handler], force=True, format="%(message)s")
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+
+# Configure OpenAI client based on environment
+load_dotenv(override=True)
+API_HOST = os.getenv("API_HOST", "github")
+MCP_SERVER_URL = os.getenv("MCP_SERVER_URL", "http://localhost:8000/mcp/")
+
+async_credential = None
+if API_HOST == "azure":
+    async_credential = DefaultAzureCredential()
+    token_provider = get_bearer_token_provider(async_credential, "https://cognitiveservices.azure.com/.default")
+    client = OpenAIChatClient(
+        base_url=f"{os.environ['AZURE_OPENAI_ENDPOINT']}/openai/v1/",
+        api_key=token_provider,
+        model_id=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
+    )
+elif API_HOST == "github":
+    client = OpenAIChatClient(
+        base_url="https://models.github.ai/inference",
+        api_key=os.environ["GITHUB_TOKEN"],
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+    )
+else:
+    client = OpenAIChatClient(
+        api_key=os.environ["OPENAI_API_KEY"],
+        model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini"),
+    )
+
+
+async def main() -> None:
+    """Run an agent connected to a local MCP server for expense logging."""
+    async with (
+        MCPStreamableHTTPTool(name="Expenses MCP Server", url=MCP_SERVER_URL) as mcp_server,
+        ChatAgent(
+            chat_client=client,
+            instructions=(
+                "You help users with tasks using the available tools. "
+                f"Today's date is {datetime.now().strftime('%Y-%m-%d')}."
+            ),
+            tools=[mcp_server],
+        ) as agent,
+    ):
+        response = await agent.run("yesterday I bought a laptop for $1200 using my visa.")
+        print(response.text)
+
+    if async_credential:
+        await async_credential.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())