version: 0.4.0
graph:
  id: reflexion_loop
  description: Reflexion loop subgraph with actor/evaluator and memory storage.
  log_level: INFO
  is_majority_voting: false
  start:
    - Task
  end:
  - Final Synthesizer
  memory:
    - name: reflexion_blackboard
      type: blackboard
      config:
      max_items: 500
  nodes:
  - id: Task
    type: passthrough
    config: {}
  - id: Reflexion Actor
    type: agent
    description: Actor (πθ) generates a strategy draft based on blackboard experience and short-term context.
    config:
      provider: openai
      base_url: ${BASE_URL}
      api_key: ${API_KEY}
      name: gpt-4o-mini
      input_mode: messages
      role: |
        You are the Actor. If there are relevant memories, refer to that experience and output the latest action draft; if there are no relevant memories, provide an action draft to the best of your ability.
        - Structure:
          Thought: ...
          Draft: ...
      memories:
      - name: reflexion_blackboard
        retrieve_stage:
        - gen
        top_k: 5
        read: true
        write: false
      params:
        temperature: 0.2
        max_tokens: 1200
  - id: Reflexion Evaluator
    type: agent
    description: Evaluator (Me) provides scores and improvement directions for the Actor's draft.
    config:
      provider: openai
      base_url: ${BASE_URL}
      api_key: ${API_KEY}
      name: gpt-4o-mini
      input_mode: messages
      role: |
        You are the Evaluator. Receive and read the Actor's latest output and task objectives, and evaluate whether they meet the goals.
        Append `Verdict: CONTINUE` or `Verdict: STOP` at the end of the output.
        When you think the current plan is good enough, you should give `Verdict: STOP`. Other fields can be skipped.
        Output:
        - Score: <0-1>
        - Reason: <Failure reasons or highlights>
        - Next Focus: <Key points to focus on in the next round>
        - Verdict: CONTINUE|STOP
      params:
        temperature: 0.1
        max_tokens: 800
  - id: Self Reflection Writer
    type: agent
    description: Self-Reflection (Msr) converts Evaluator results into reusable experience.
    config:
      provider: openai
      base_url: ${BASE_URL}
      api_key: ${API_KEY}
      name: gpt-4o-mini
      input_mode: messages
      role: |
        You are responsible for refining the Evaluator output and Actor Draft into JSON experience:
        {
          "issues": [..],
          "fix_plan": [..],
          "memory_cue": "A short reminder"
        }
        - JSON must not contain extra text.
      memories:
      - name: reflexion_blackboard
        read: false
        write: true
      params:
        temperature: 0.1
        max_tokens: 500
  - id: Final Synthesizer
    type: agent
    description: Converge the final answer, absorbing the latest Draft and Evaluator tips.
    config:
      provider: openai
      base_url: ${BASE_URL}
      api_key: ${API_KEY}
      name: gpt-4o
      input_mode: messages
      role: |
        Please synthesize all inputs and provide a final answer. Be comprehensive. Do not include any extra text other than the final answer.
      params:
        temperature: 0.1
        max_tokens: 1000
  edges:
  - from: Task
    to: Reflexion Actor
    keep_message: True
  - from: Task
    to: Reflexion Evaluator
    keep_message: True
    trigger: false
  - from: Reflexion Actor
    to: Reflexion Actor
    trigger: false
  - from: Reflexion Actor
    to: Reflexion Evaluator
  - from: Reflexion Evaluator
    to: Self Reflection Writer
    condition: need_reflection_loop
  - from: Self Reflection Writer
    to: Reflexion Actor
    carry_data: true
  - from: Reflexion Actor
    to: Final Synthesizer
    trigger: false
  - from: Reflexion Evaluator
    to: Final Synthesizer
    condition: should_stop_loop
    carry_data: false