Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

fix: a minimal fix for json format mismatch in workforce (#2038)

Chen8931e6244f7c
diff --git a/camel/societies/workforce/prompts.py b/camel/societies/workforce/prompts.py
index 72e0dffb2..dce5f2072 100644
--- a/camel/societies/workforce/prompts.py
+++ b/camel/societies/workforce/prompts.py
@@ -67,6 +67,7 @@ Following is the information of the existing worker nodes. The format is <ID>:<d
{child_nodes_info}
==============================
+
You must return the ID of the worker node that you think is most capable of doing the task.
Your response MUST be a valid JSON object containing a single field: 'assignee_id' (a string with the chosen worker node ID).
diff --git a/camel/societies/workforce/workforce.py b/camel/societies/workforce/workforce.py
index db77692c9..4a9018c97 100644
--- a/camel/societies/workforce/workforce.py
+++ b/camel/societies/workforce/workforce.py
@@ -308,7 +308,7 @@ class Workforce(BaseNode):
response = self.coordinator_agent.step(
prompt, response_format=TaskAssignResult
)
- result_dict = json.loads(response.msg.content)
+ result_dict = json.loads(response.msg.content, parse_int=str)
task_assign_result = TaskAssignResult(**result_dict)
return task_assign_result.assignee_id