{
  "id": "self-evolve",
  "name": "Self Evolve",
  "description": "MemRL-style self-evolving retrieval policy over episodic memory.",
  "uiHints": {
    "embedding.provider": {
      "label": "Embedding Provider",
      "help": "Use OpenAI for semantic embeddings, or hash for local deterministic embeddings."
    },
    "embedding.apiKey": {
      "label": "OpenAI API Key",
      "sensitive": true,
      "placeholder": "sk-proj-..."
    },
    "embedding.model": {
      "label": "Embedding Model",
      "placeholder": "text-embedding-3-small"
    },
    "retrieval.k1": {
      "label": "Phase-A Top K",
      "help": "Top-k candidate count after similarity gating."
    },
    "retrieval.k2": {
      "label": "Phase-B Top K",
      "help": "Final selected memory count injected into context."
    },
    "retrieval.lambda": {
      "label": "Q Weight",
      "help": "Blend ratio between z-normalized similarity and Q-value."
    },
    "retrieval.delta": {
      "label": "Similarity Gate",
      "help": "Minimum cosine similarity for Phase-A candidate admission."
    },
    "learning.alpha": {
      "label": "Learning Rate",
      "help": "Q-learning step size."
    },
    "reward.provider": {
      "label": "Reward Provider",
      "help": "Use an LLM judge over user feedback text."
    },
    "reward.model": {
      "label": "Reward Model",
      "help": "Model used to score user feedback when reward provider is OpenAI."
    },
    "experience.summarizer": {
      "label": "Experience Summarizer",
      "help": "Use an LLM summarizer for procedural memory experience text."
    },
    "experience.model": {
      "label": "Experience Model",
      "help": "Model used to summarize hidden reasoning and tool traces into reusable memory."
    },
    "experience.apiKey": {
      "label": "Experience API Key",
      "sensitive": true,
      "placeholder": "sk-proj-..."
    },
    "runtime.observeTurns": {
      "label": "Observe Turns",
      "help": "First N turns only observe and skip Q-value learning updates."
    },
    "runtime.minAbsReward": {
      "label": "Min |Reward|",
      "help": "Skip learning updates when reward magnitude is too small."
    },
    "runtime.minRewardConfidence": {
      "label": "Min Reward Confidence",
      "help": "Skip learning updates when reward confidence is below this threshold."
    },
    "runtime.learnMode": {
      "label": "Learning Mode",
      "help": "balanced: prefer tool turns and allow very strong no-tool feedback; tools_only: learn only when tools were called; all: learn from every qualified turn."
    },
    "runtime.noToolMinAbsReward": {
      "label": "No-Tool Min |Reward|",
      "help": "In balanced mode, no-tool turns must reach this reward magnitude to learn."
    },
    "runtime.noToolMinRewardConfidence": {
      "label": "No-Tool Min Confidence",
      "help": "In balanced mode, no-tool turns must reach this confidence to learn."
    },
    "runtime.newIntentSimilarityThreshold": {
      "label": "New Intent Similarity Threshold",
      "help": "When a new user prompt similarity is lower than this threshold, close the current task and start a new one."
    },
    "runtime.idleTurnsToClose": {
      "label": "Idle Turns To Close",
      "help": "Close waiting tasks after N non-feedback idle turns."
    },
    "runtime.pendingTtlMs": {
      "label": "Pending TTL (ms)",
      "help": "Close pending tasks when no update is observed for this duration."
    },
    "runtime.maxTurnsPerTask": {
      "label": "Max Turns Per Task",
      "help": "Hard cap of turns accumulated into one learnable task."
    },
    "reward.apiKey": {
      "label": "Reward API Key",
      "sensitive": true,
      "placeholder": "sk-proj-..."
    },
    "learning.gamma": {
      "label": "Discount Factor",
      "help": "Future utility discount for Q update bootstrap term."
    },
    "memory.maxEntries": {
      "label": "Max Memories",
      "help": "Maximum episodic memory entries persisted for this plugin."
    }
  },
  "configSchema": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "embedding": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "provider": {
            "type": "string",
            "enum": ["openai", "hash"]
          },
          "apiKey": {
            "type": "string"
          },
          "baseUrl": {
            "type": "string"
          },
          "model": {
            "type": "string"
          },
          "dimensions": {
            "type": "number",
            "minimum": 16,
            "maximum": 4096
          }
        }
      },
      "retrieval": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "k1": { "type": "number", "minimum": 1, "maximum": 100 },
          "k2": { "type": "number", "minimum": 1, "maximum": 20 },
          "delta": { "type": "number", "minimum": -1, "maximum": 1 },
          "tau": { "type": "number", "minimum": -1, "maximum": 1 },
          "lambda": { "type": "number", "minimum": 0, "maximum": 1 },
          "epsilon": { "type": "number", "minimum": 0, "maximum": 1 }
        }
      },
      "learning": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "alpha": { "type": "number", "minimum": 0.0001, "maximum": 1 },
          "gamma": { "type": "number", "minimum": 0, "maximum": 1 },
          "qInit": { "type": "number", "minimum": -1, "maximum": 1 },
          "rewardSuccess": { "type": "number", "minimum": -1, "maximum": 2 },
          "rewardFailure": { "type": "number", "minimum": -2, "maximum": 1 }
        }
      },
      "memory": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "maxEntries": { "type": "number", "minimum": 20, "maximum": 50000 },
          "maxExperienceChars": { "type": "number", "minimum": 120, "maximum": 12000 },
          "includeFailures": { "type": "boolean" },
          "stateFile": { "type": "string" }
        }
      },
      "reward": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "provider": {
            "type": "string",
            "enum": ["openai"]
          },
          "apiKey": { "type": "string" },
          "baseUrl": { "type": "string" },
          "model": { "type": "string" },
          "temperature": { "type": "number", "minimum": 0, "maximum": 1 }
        }
      },
      "runtime": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "minPromptChars": { "type": "number", "minimum": 1, "maximum": 200 },
          "observeTurns": { "type": "number", "minimum": 0, "maximum": 500 },
          "minAbsReward": { "type": "number", "minimum": 0, "maximum": 1 },
          "minRewardConfidence": { "type": "number", "minimum": 0, "maximum": 1 },
          "learnMode": {
            "type": "string",
            "enum": ["balanced", "tools_only", "all"]
          },
          "noToolMinAbsReward": { "type": "number", "minimum": 0, "maximum": 1 },
          "noToolMinRewardConfidence": { "type": "number", "minimum": 0, "maximum": 1 },
          "newIntentSimilarityThreshold": { "type": "number", "minimum": -1, "maximum": 1 },
          "idleTurnsToClose": { "type": "number", "minimum": 0, "maximum": 20 },
          "pendingTtlMs": { "type": "number", "minimum": 1000, "maximum": 86400000 },
          "maxTurnsPerTask": { "type": "number", "minimum": 1, "maximum": 100 }
        }
      },
      "experience": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "summarizer": {
            "type": "string",
            "enum": ["openai"]
          },
          "apiKey": { "type": "string" },
          "baseUrl": { "type": "string" },
          "model": { "type": "string" },
          "temperature": { "type": "number", "minimum": 0, "maximum": 1 },
          "maxToolEvents": { "type": "number", "minimum": 1, "maximum": 100 },
          "maxRawChars": { "type": "number", "minimum": 200, "maximum": 20000 },
          "maxSummaryChars": { "type": "number", "minimum": 100, "maximum": 4000 }
        }
      }
    }
  }
}