llama-stack-mirror/llama_stack
Sébastien Han 4e5a155dc7
fix: only load mcp when enabled in tool_group
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 11:16:34 +02:00
..
apis docs: Minor spelling fix (#2592) 2025-07-02 20:26:51 -04:00
cli fix: stack build (#2485) 2025-06-20 15:15:43 -07:00
distribution fix: AccessDeniedError leads to HTTP 500 instead of error 403 (#2595) 2025-07-03 10:50:49 -07:00
models fix: finish conversion to StrEnum (#2514) 2025-06-26 08:01:26 +05:30
providers fix: only load mcp when enabled in tool_group 2025-07-04 11:16:34 +02:00
strong_typing chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
templates fix: store configs (#2593) 2025-07-03 10:07:23 -07:00
ui build: Bump version to 0.2.13 2025-06-27 23:56:14 +00:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore: remove nested imports (#2515) 2025-06-26 08:01:05 +05:30
schema_utils.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00