mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
westey
bad05a2bdc
* Add initial harness console for python * Add textual to project * Add planning and approval flows with list selector * Address PR comments * Fix list selection bug * Fix PR #6312 round 2 review comments - Escape untrusted agent text with rich.markup.escape() in observers (text_output, planning_output, reasoning_display) to prevent markup injection - Remove non-functional 'Always approve' choices from tool_approval.py (framework lacks CreateAlwaysApproveToolResponse support) - Remove textual from root pyproject.toml dev deps (sample-specific) - Add PEP 723 inline script metadata to harness_research.py - Narrow except Exception to except NoMatches in list_selection.py Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix build error * Fix build errors --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
bad05a2bdc
ยท
2026-06-09 05:48:35 +00:00
History
Harness Agent Samples
This folder demonstrates create_harness_agent โ a factory function that builds a
pre-configured, batteries-included agent by assembling the full agent pipeline
from a chat client.
What is create_harness_agent?
create_harness_agent bundles the following features into a single Agent instance:
| Feature | Description |
|---|---|
| Function invocation | Automatic tool calling loop |
| Per-service-call persistence | History persisted after every model call |
| Compaction | Context-window management (sliding window + tool result compaction) |
| TodoProvider | Todo list management for planning and tracking |
| AgentModeProvider | Plan/execute mode tracking |
| MemoryContextProvider | File-based durable memory (when memory_store provided) |
| SkillsProvider | File-based skill discovery and progressive loading |
| OpenTelemetry | Built-in observability |
Each feature can be disabled or customized via keyword arguments.
Samples
| File | Description |
|---|---|
harness_research.py |
Interactive research assistant with web search and planning workflow |
Running
# Set your Foundry environment variables
export FOUNDRY_PROJECT_ENDPOINT="https://your-project.services.ai.azure.com/api/projects/your-project-name"
export FOUNDRY_MODEL="your-model-deployment-name"
# Authenticate with Azure (required for AzureCliCredential)
az login
# Run the research sample
python samples/02-agents/harness/harness_research.py
Key Concepts
Minimal Setup
create_harness_agent requires only a chat client and token budget parameters:
from agent_framework import create_harness_agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
agent = create_harness_agent(
client=FoundryChatClient(credential=AzureCliCredential()),
max_context_window_tokens=128_000,
max_output_tokens=16_384,
)
Customization
Disable or customize any feature:
agent = create_harness_agent(
client=client,
max_context_window_tokens=128_000,
max_output_tokens=16_384,
name="my-agent",
agent_instructions="Custom instructions here.",
disable_todo=True, # Skip todo management
disable_mode=True, # Skip plan/execute modes
disable_compaction=True, # Skip compaction
)
Plan/Execute Workflow
The AgentModeProvider enables a two-phase workflow:
- Plan mode โ Interactive: the agent asks questions, creates todos, gets approval
- Execute mode โ Autonomous: the agent works through todos independently