# input_region.py — Rule-based input region extraction and normalization (T2 & T3)

import re
from lib_py.agents.registry import get_adapter

def extract_input_region(pane_text: str, agent_name: str) -> str:
    """
    Extracts the input area text between horizontal rule separators (─{10,}) for a given agent.
    If rules are absent, falls back to full pane_text to support mocks and unruled panes.
    Strips leading prompt tokens ('>', '❯') and placeholders ('Ask anything...').
    Raises ValueError for unsupported agents (like hermes with no input area facts).
    """
    adapter = get_adapter(agent_name)
    if not adapter or not adapter.input_prompt:
        raise ValueError(f"Agent {agent_name!r} has no input area facts")

    rule_pattern = adapter.input_rule_pattern or r'─{10,}'
    rule_re = re.compile(rule_pattern)
    lines = pane_text.splitlines()
    rule_indices = [i for i, line in enumerate(lines) if rule_re.search(line)]

    if len(rule_indices) >= 2:
        # Exclude the rule lines themselves: lines between rule_indices[-2] + 1 and rule_indices[-1]
        region_lines = lines[rule_indices[-2] + 1:rule_indices[-1]]
    elif len(rule_indices) == 1:
        region_lines = lines[rule_indices[0] + 1:]
    else:
        region_lines = lines

    region_text = "\n".join(region_lines)

    prompt = adapter.input_prompt
    if prompt:
        region_text = re.sub(r'^\s*' + re.escape(prompt) + r'\s*', '', region_text, flags=re.MULTILINE)

    placeholder = adapter.input_placeholder
    if placeholder:
        region_text = region_text.replace(placeholder, '')

    return region_text.strip()