Planning Flink Agents 0.4

[wenjin272]

Brainstorm

from @xintongsong @wenjin272 @joeyutong @pltbkd

Must

• Highlight Features
  • Conduct a comprehensive review of the existing API and design a compatibility mechanism
  • Support asynchronous execution for Java durable execution on JDK versions below 21
  • Support Sub Agent primitives [Discussion] Supervisor + Sub-Agent Orchestration: Concrete Multi-Agent Use Cases for Event-Driven Agents #660
  • Flink Agents Dev Skills: Provide Agent Skills to help users build flink-agents based Agent via coding agent
• Requirements from Production
  • API
    • Support invoking multimodal models
    • Support injecting parameters into tool calls [Feature] Support tool parameter injection #853
    • Support structured output from ChatModel [Feature] Support making use of the native capabilities of models for structure output. #280
  • Runtime
    • Support dynamic updates to the AgentPlan, covering events, actions, and resources
• Important Experience Improvements
  • Observability
    • Support observing Memory through the EventLog
    • Support Per-Run Trace to visualize the execution path of a single record through the Agent [Discussion] Agent observability: tracing & evaluation beyond metrics + event log #710
    • Metrics improvements
      • [Feature] Propagate metric groups to cross-language resources #857
      • [Feature] Track token usage metrics for embedding models #858
      • [Bug] Action-scoped metrics can be recorded under the wrong action for cached resources #859
  • CI & Infra
    • Support Flink 2.3 [Feature] Support Flink 2.3 #833
    • AI-assisted code review mechanism (explored within the release cycle; not tied to a release)

If Possible

• API
  • Support to-C sources such as Slack / GitHub / Gmail / Jira
  • Support conditional triggering of Actions [Feature] Track Action by Event Field Values work #754
  • Provide syntactic sugar for common workflow patterns to reduce the effort of building Workflows
    • fan-out / fan-in API
• Runtime
  • MCP dynamic loading and refreshing [Feature] Dynamic load MCP tools and prompts in runtime. #458
  • Parallel tool call execution Parallel Tool Call Execution #855
  • Agent Harness (governance layer)
    • WorkflowRunPolicy: max events / max actions / max tokens / timeout
    • Support safety guardrails and hooks
• CI & Infra
  • Support automated validation of the quick start example via GitHub Actions [Tech Debt] Add e2e test for submitting example to flink standalone cluster. #642
• SQL Integration
  • Support invoking Agents from SQL jobs
  • Support Invoking Agents from CDC YAML
  • Agent-specific SQL syntax (Table / View as VectorStore / KeyedContext), Inject other Tables / Views as context into the Agent
  • Support SQL Function / Operator as Action, reusing existing SQL / DataFrame operator capabilities within Flink Agents

[weiqingy]

Thanks for starting the 0.4 planning thread. The current Must list looks like a good foundation to me. The split between highlight features, production requirements, experience improvements, and “if possible” items also makes sense.

A few thoughts / brainstorm ideas:

1. For sub-agent primitives, I’ll resolve the pending feedback in [Discussion] Supervisor + Sub-Agent Orchestration: Concrete Multi-Agent Use Cases for Event-Driven Agents #660 and follow up there with a concrete proposal [1].

2. The observability part already covers the main things I was thinking about: memory observation through EventLog, per-run trace [Discussion] Agent observability: tracing & evaluation beyond metrics + event log #710, and metrics improvements [2][3][4]. I don’t have extra items to add there beyond agreeing that these are important for production debugging and evaluation. This also matches what other agent runtimes emphasize: execution timelines, trace visualization, and evaluation/debugging loops are treated as core production capabilities [8][9].

3. One possible area to brainstorm is durable external signal handling. I’d frame this less as generic human-in-the-loop and more as event-driven durable correlation: wait/resume/timeout based on a callback or another stream event. Flink Agents already has durable execution, action-state recovery, reconcilers, and request_id-style correlation in built-in events [5]. The missing part may be a generic pattern/API for “this keyed run is pending until a later correlated event arrives or times out.” Restate and LangGraph both show a similar need around durable waiting/resuming long-running agent or workflow executions, though Flink Agents may want to express it in a more event-stream-native way [8][9].
   Example: a support agent sends a fraud-check request to an external risk service. The response comes back later on Kafka. The agent should not block a thread; it should persist pending state, resume on the callback event, or emit a timeout path.

4. Flow/cost control seems partly covered by the proposed Agent Harness (max events / max actions / max tokens / timeout) and parallel tool call execution Parallel Tool Call Execution #855 [7]. One possible extension to consider is resource-scoped guardrails: per-model, per-tool, per-key, or per-tenant concurrency/rate limits. A global async pool prevents unlimited threads [6], but it does not express “this tenant gets max N concurrent model calls” or “this external CRM tool gets max QPS.” This could maybe fit under Agent Harness or the parallel tool execution work rather than being a separate top-level feature. Restate calls out cost/concurrency control for agent invocations as an explicit runtime concern, which seems like a useful reference point here [8].

References:

[1] #660 Sub-agent discussion: #660
[2] Monitoring docs: https://github.com/apache/flink-agents/blob/main/docs/content/docs/operations/monitoring.md
[3] #710 tracing/evaluation discussion: #710
[4] #876 memory observation discussion: #876
[5] Deployment / exactly-once action consistency docs: https://github.com/apache/flink-agents/blob/main/docs/content/docs/operations/deployment.md
[6] Configuration docs: https://github.com/apache/flink-agents/blob/main/docs/content/docs/operations/configuration.md
[7] #855 parallel tool execution discussion: #855
[8] Restate AI Agents: https://docs.restate.dev/use-cases/ai-agents
[9] LangGraph overview: https://docs.langchain.com/oss/python/langgraph/overview