refactor: adapt listen chat agent to camel callbacks

[fengju0213]

Related Issue

Closes # #1502

Description

Replaces ListenChatAgent's override-based lifecycle hooks with CAMEL's new AgentCallback / AgentEvent framework (camel-ai/camel#XXX).

Before: ListenChatAgent overrode step, astep, _execute_tool, _aexecute_tool to manually emit activate/deactivate actions to the frontend. This duplicated ~400 lines of CAMEL internals (tool dispatch, mask handling, result truncation, error handling) and broke on every upstream change.

After: All lifecycle-to-frontend bridging is handled by ListenChatAgentCallback, a standard AgentCallback that receives events from CAMEL and translates them to Eigent task actions. ListenChatAgent no longer reimplements CAMEL's tool execution or step logic.

Changes

listen_chat_agent.py (-557 / +228)

• Remove overrides of step, astep inner logic — now just wrap super() with set_process_task context and handle streaming re-wrapping
• Remove complete reimplementations of _execute_tool / _aexecute_tool — now delegate to super() with pre/post event emission
• Wire ListenChatAgentCallback + execution_context + execution_context_provider into super().__init__ via CAMEL's new constructor params
• clone() updated to forward CloneContext and preserve new runtime config fields (retry_attempts, retry_delay, callbacks, execution_context, execution_context_provider, summary_window_ratio)

listen_chat_agent_callback.py (+276, new file)

• ListenChatAgentCallback(AgentCallback) — translates 6 CAMEL lifecycle events into Eigent task queue actions:
  • StepStarted → ActionActivateAgentData
  • StepCompleted → ActionDeactivateAgentData (with token count)
  • StepFailed → ActionBudgetNotEnough + ActionDeactivateAgentData
  • ToolStarted → ActionActivateToolkitData
  • ToolCompleted → ActionDeactivateToolkitData
  • ToolFailed → ActionDeactivateToolkitData
• Preserves __listen_toolkit__ decorator skip logic
• Preserves toolkit name resolution chain (attribute → __self__ → nested func.__self__ → fallback mcp_toolkit)
• Includes fallback dataclass definitions for when CAMEL types aren't importable

test_listen_chat_agent.py (-15 / +107)

• Existing step/astep tests updated to assert set_process_task context instead of internal put_queue calls
• New: test_listen_chat_agent_callback_handles_step_events — verifies activate/deactivate queue actions for step lifecycle
• New: test_listen_chat_agent_callback_handles_budget_failure — verifies budget exceeded triggers both ActionBudgetNotEnough and deactivate
• Clone test updated to pass CloneContext

Testing Evidence (REQUIRED)

• I have included human-verified testing evidence in this PR.
• This PR includes frontend/UI changes, and I attached screenshot(s) or screen recording(s).
• No frontend/UI changes in this PR.

What is the purpose of this pull request?

• Bug fix
• New Feature
• Documentation update
• Other

Contribution Guidelines Acknowledgement

• I have read and agree to the Eigent Contribution Guideline

[fengju0213]