Skip to content

Lazy-init toolbox MCP connections on first request #46525

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tendau merged 1 commit into from
Apr 24, 2026
Merged

Lazy-init toolbox MCP connections on first request #46525

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 27 additions & 6 deletions ...azure-ai-agentserver-githubcopilot/azure/ai/agentserver/githubcopilot/_copilot_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -679,6 +679,8 @@ def __init__(

# Track MCP bridges for cleanup
self._toolbox_bridges: list = []
self._toolboxes_connected = False
self._toolbox_lock = asyncio.Lock()

# AGENTS.md persona injection — load the project's AGENTS.md and use it
# as the system message so the agent fully embodies its persona
Expand Down Expand Up @@ -834,8 +836,25 @@ async def connect_toolboxes(self):
except Exception:
logger.warning("Failed to connect toolbox %r at %s", name, url, exc_info=True)

async def _ensure_toolboxes(self):
"""Lazily connect to toolbox MCP servers on first request.

Deferred from ``initialize()`` to the first request so that user
context (auth tokens injected by the platform) is available when
the MCP ``initialize`` and ``tools/list`` calls are made. An
``asyncio.Lock`` prevents concurrent initialization from parallel
requests.
"""
if self._toolboxes_connected:
return
async with self._toolbox_lock:
if self._toolboxes_connected:
return
await self.connect_toolboxes()
self._toolboxes_connected = True
Comment thread
tendau marked this conversation as resolved.
Comment thread
tendau marked this conversation as resolved.

async def initialize(self):
"""Discover deployments, configure the model, and connect toolboxes.
"""Discover deployments and configure the model.
Comment thread
tendau marked this conversation as resolved.

Call after construction and before ``run()``. Discovery always runs
to validate the configured model against available deployments and to
Expand All @@ -844,11 +863,10 @@ async def initialize(self):
model is matched against discovered deployments; if not found, the
best available model is auto-selected.

Also connects to any discovered MCP toolbox servers and registers
their tools as regular SDK custom tools.
Toolbox MCP connections are deferred to the first request
(via ``_ensure_toolboxes``) so that platform-injected user context
is available.
"""
Comment thread
tendau marked this conversation as resolved.
# Connect toolbox MCP servers (independent of model discovery)
await self.connect_toolboxes()

resource_url = self._session_config.get("_foundry_resource_url")
if not resource_url:
Expand Down Expand Up @@ -1047,7 +1065,10 @@ async def _load_conversation_history(self, conversation_id: str) -> Optional[str
return None

async def _get_or_create_session(self, conversation_id=None):
"""Override to add conversation history bootstrap on cold start."""
"""Override to add lazy toolbox init and conversation history bootstrap."""
# Lazy-connect toolboxes on first request (deferred from initialize)
await self._ensure_toolboxes()

if conversation_id and conversation_id not in self._sessions:
history = await self._load_conversation_history(conversation_id)
if history:
Expand Down