feat: add CAMEL-based single agent mode

[4pmtong]

Related Issue

Closes #1561
Closes #1562

Description

This PR adds CAMEL-based Single Agent Mode end to end.

It introduces a single-agent harness built on CAMEL ChatAgent, with config-driven toolkit assembly, observable todo progress, pause/resume/stop support, multi-turn context continuity, and memory snapshot serialization. The implementation reuses CAMEL toolkits where possible and keeps Eigent-specific wrappers thin, mainly for frontend observability and product integration.

Key changes:

• Add Single Agent Mode backend service and agent factory.
• Add config-driven toolkit assembly for CAMEL toolkits, MCP, WebFetch, PlanningWorktree, Skill, Todo, Terminal, File, Human, and AgentToolkit.
• Add depth-limited AgentToolkit support for future sub-agent mode, preventing recursive sub-agent creation.
• Add observable TodoToolkit adapter to emit todo_state events for pending → in_progress → completed UI progress.
• Add memory serialization utilities shared by single-agent and workforce paths.
• Wire frontend session mode selection and request payloads.
• Add Single Agent side panel with todo progress, execution context, and agent folder.
• Align single-agent toolkit execution details with workforce chat-side work log behavior.
• Align Agent Folder file discovery between single-agent and workforce.
• Add task/session mode inference so project switching shows the correct Workforce vs Single Agent UI.
• Fix single-agent token accounting so completed runs no longer show Total: 0.

Testing Evidence (REQUIRED)

Manual UI verification:

Ran Single Agent Mode on a CSV/chart generation task.
Verified todo progress updates through pending → in_progress → completed.
Verified toolkit execution details appear in the chat work log, aligned with workforce behavior.
Verified generated files appear in Agent Folder.
Verified project/session switching displays the correct Workforce vs Single Agent side panel.
Verified completed single-agent runs show non-zero token usage.

• 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