Federico Mariani created CAMEL-23078:
----------------------------------------
Summary: camel-openai MCP improvements
Key: CAMEL-23078
URL: https://issues.apache.org/jira/browse/CAMEL-23078
Project: Camel
Issue Type: Improvement
Components: camel-openai
Affects Versions: 4.18.0
Reporter: Federico Mariani
Implementing https://issues.apache.org/jira/browse/CAMEL-23076 I noticed the
following improvements:
* Parallel tool execution - mcpToolExecutorThreads config, CompletableFuture
for batch calls
When the model returns multiple tool calls in a single response (e.g., "get
weather for London" and "get weather for Paris" simultaneously), they're
currently executed sequentially. This is a per-exchange latency optimization —
with 3 tools at 500ms each, sequential = 1.5s, parallel = ~500ms. It does not
address thread exhaustion under concurrent load; the exchange thread remains
blocked for the full agentic loop regardless. A configurable
mcpToolExecutorThreads (default 1 = sequential, current behavior) would create
a fixed thread pool at endpoint startup, used only for concurrent callTool()
within a single model response.
* Tool list refresh - mcpToolRefreshInterval or SDK toolsChangeConsumer callback
Tools are listed once at doStart() and cached for the lifetime of the route. If
an MCP server adds, removes, or updates tools at runtime, the cached list
becomes stale — the model may try to call tools that no longer exist, or miss
new ones.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
