env/dynamics.py

"""
Dynamics - state transition logic for the DebugOps environment.
The agent must perform the correct multi-step fix sequence to resolve
an incident. Wrong actions degrade system metrics.
"""
from __future__ import annotations
from typing import Dict, Any


def apply_action(state: Dict[str, Any], action: str) -> Dict[str, Any]:
    """
    Mutate-and-return state after the agent takes `action`.

    Resolution logic
    ----------------
    Each root cause has a `fix_sequence` list stored inside state.
    The agent must perform each action in order:
      - Correct step  → fix_progress += 1; metrics partially improve
      - Wrong step    → metrics degrade further
      - All steps done → resolved = True, metrics recover
    """
    seq = state["fix_sequence"]
    prog = state["fix_progress"]

    if prog < len(seq) and action == seq[prog]:
        # Correct action
        state["fix_progress"] += 1
        prog += 1

        state["metrics"]["latency"]    *= 0.85
        state["metrics"]["error_rate"] *= 0.80
        state["metrics"]["cpu"]        *= 0.90

        if prog == len(seq):
            state["resolved"] = True
            state["metrics"]["latency"]    = max(state["metrics"]["latency"]    * 0.5, 30)
            state["metrics"]["error_rate"] = max(state["metrics"]["error_rate"] * 0.1, 0.01)
            state["metrics"]["cpu"]        = max(state["metrics"]["cpu"]        * 0.6, 20)

            for svc in state["services"]:
                state["services"][svc] = "healthy"
    else:
        state["metrics"]["latency"]    = min(state["metrics"]["latency"]    * 1.12, 2000)
        state["metrics"]["error_rate"] = min(state["metrics"]["error_rate"] * 1.10, 1.0)
        state["metrics"]["cpu"]        = min(state["metrics"]["cpu"]        * 1.05, 100)

    if not state["resolved"]:
        state["metrics"]["latency"] = min(state["metrics"]["latency"] * 1.03, 2000)
        state["metrics"]["cpu"]     = min(state["metrics"]["cpu"]     * 1.01, 100)

    return state