llama-stack-mirror/llama_stack/providers/inline/agents/meta_reference
Sébastien Han df6ce8befa
fix: only load mcp when enabled in tool_group (#2621)
# What does this PR do?

The agent code is currently importing MCP modules even when MCP isn’t
enabled. Do we consider this worth fixing, or are we treating MCP as a
first-class dependency? I believe we should treat it as such.

If everyone agrees, let’s go ahead and close this.

Note: The current setup breaks if someone builds a distro without
including MCP in tool_group but still serves the agent API.

Also, we should bump the MCP version to support streamable responses, as
SSE is being deprecated.

Signed-off-by: Sébastien Han <seb@redhat.com>
2025-07-04 20:27:05 +05:30
..
__init__.py feat: fine grained access control policy (#2264) 2025-06-03 14:51:12 -07:00
agent_instance.py feat: drop python 3.10 support (#2469) 2025-06-19 12:07:14 +05:30
agents.py feat: Add webmethod for deleting openai responses (#2160) 2025-06-30 11:28:02 +02:00
config.py feat: add list responses API (#2233) 2025-05-23 13:16:48 -07:00
openai_responses.py fix: only load mcp when enabled in tool_group (#2621) 2025-07-04 20:27:05 +05:30
persistence.py fix: AccessDeniedError leads to HTTP 500 instead of error 403 (#2595) 2025-07-03 10:50:49 -07:00
safety.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00