feat: sequence task workforce

[nitpicker55555]

Description

Support for processing a sequence of tasks in the Workforce, where each task can share context (e.g., results, memory) with others.

• Added process_task_sequence and process_task_sequence_async methods to Workforce
• Introduced shared_context and shared_channel to persist information across tasks
• Each task's result is stored in shared_context with the pattern task_{task.id}
• Compatible with current single-task flow; does not affect process_task

This addresses collaborative task execution as proposed in Issue #1832.

Checklist

• I have read the CONTRIBUTION guide (required)
• I have linked this PR to an issue using the Development section or Fixes #1832 (required)
• I have checked if any dependencies need to be added or updated in pyproject.toml and uv lock
• I have updated the tests accordingly (required for a bug fix or a new feature)
• I have updated the documentation if needed
• I have added examples if this is a new feature

[zjrwtx]

can we add some comments on these?

[zjrwtx]

like step by step run all task ....

[zjrwtx]

thanks @nitpicker55555 ,left some comment

[Wendong-Fan]

Thanks @nitpicker55555 for the contribution, and apologies for the delayed review comment.

The current implementation appears to process a sequence of top-level tasks within the workforce, rather than allowing for a pre-defined, fixed sequence of subtasks for a single overarching goal. As it stands, each task in the sequence is still subject to the workforce's internal decomposition process.

The user's requirement, as I understand it, is to support a scenario where subtasks are explicitly defined and executed in a specific order without further decomposition by the workforce. This would give more direct control over the execution flow.

Maybe allowing the Task to specify which worker node should handle it could offer more granular control. Happy to discuss this further