mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Eduard van Valkenburg
8091d052d8
Updates third-party dev dependencies across the Python workspace and validates that all runtime dependency bounds still hold at both ends. Dev dependency bumps (root, lab, declarative, durabletask): - uv 0.11.6 -> 0.11.17, ruff 0.15.8 -> 0.15.15, pytest-asyncio 1.3.0 -> 1.4.0, mcp 1.27.0 -> 1.27.2, azure-monitor-opentelemetry 1.8.7 -> 1.8.8, poethepoet 0.42.1 -> 0.46.0, prek 0.3.9 -> 0.4.3, types-python-dateutil and types-PyYaml stub bumps. - Transitive Dependabot items swept via lock: idna 3.11 -> 3.17, pip 26.0.1 -> 26.1.2. Deliberately excluded: - opentelemetry-sdk stays 1.40.0: azure-monitor-opentelemetry (incl. 1.8.8) hard-pins opentelemetry-sdk==1.40. - mypy stays 1.20.0 and pyright stays 1.1.408: the 2.1.0 / 1.1.409 bumps introduce new diagnostics that fail type checking and need dedicated PRs. - rich kept as a range: agentlightning (lab[lightning]) forces rich==13.9.4. Code/formatting changes driven by the ruff upgrade: - devui lifespan now uses try/finally so shutdown cleanup always runs (ruff RUF075). - Removed unused TYPE_CHECKING imports in core and foundry flagged by ruff 0.15.15. - Reapplied ruff 0.15.15 formatting to the files it changed. Validation: validate-dependency-bounds-test "*" passes (31/31 lower + 31/31 upper); typing 62/62; lint 31/31; devui tests pass. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
8091d052d8
ยท
2026-06-01 17:53:56 +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