feat: Add Explicit Termination Mechanism for Multi-Agent Workflows (Similar to AutoGen "TERMINATE") #5211

Is your feature request related to a problem? Please describe.

In multi-agent workflows using ADK, agents can sometimes fall into infinite or
long-running loops during collaborative tasks. This happens especially when
orchestration depends only on message passing, with no built-in signal to
indicate that the task is completed.

Other multi-agent frameworks — for example, Microsoft's AutoGen — include
explicit termination mechanisms (e.g., TextMentionTermination,
StopMessageTermination, or custom termination callbacks) that help teams of
agents know when to gracefully stop.

In ADK today, there is no simple built-in mechanism for agents to signal "task
completed," which can lead to runaway conversations, wasted tokens, and stalled
agent workflows.

Describe the solution you'd like

ADK should support a standardized termination mechanism that allows:

• Agents to explicitly signal termination, for example by producing a
  special message type (like StopMessage in AutoGen) that ends the
  conversation.
• Teams to define termination conditions, such as detecting a specific
  keyword ("TERMINATE"), max message counts, function call results, token
  usage, or any other customizable logic.
• External termination control, so applications integrating ADK can stop a
  run programmatically (e.g., a UI "Stop" button).
• Composable termination conditions, allowing multiple rules combined with
  AND/OR logic (similar to AutoGen's
  MaxMessageTermination | TextMentionTermination).

This would give ADK parity with AutoGen's termination system and prevent
infinite loops in multi-agent workflows.

Describe alternatives you've considered

• Custom stop messages in agent prompts — unreliable; agents may not follow
  instructions consistently.
• Max iterations as a safeguard — prevents infinite loops but doesn't allow
  agents to end a task early when done.
• External timeout logic — helps with long runs but doesn't let agents
  indicate intentional completion.

None of these provide the simple, robust, and explicit termination controls that
AutoGen offers.

Additional context

AutoGen's termination system includes the following primitives, all of which
this proposal aims to replicate in ADK:

Cross-repository alignment

This feature is being implemented in parallel across both ADK implementations to
keep them aligned:

• adk-js — Feature request: Feature Request: Add Explicit Termination Mechanism for Multi-Agent Workflows (Similar to AutoGen “TERMINATE”) adk-js#29
• adk-js — Implementation PR (under review): feat: add termination conditions for multi-agent workflows adk-js#193
• adk-python — Implementation PR: feat(agents): add termination conditions for multi-agent workflows #5213

The goal is for both adk-python and adk-js to ship the same termination
primitives with a consistent API surface, so developers can reason about
termination the same way regardless of which SDK they use.