Conflict_Checker/backend/agents/extractors.py

"""Scoped extraction and orientation agents."""

import json
from typing import Dict

from backend import config
from backend.agents.base import AgentResult, AgentScope, AgentUsage, failure
from backend.llm import call_json
from backend.pipeline.extractor import _normalize_sheet
from backend.pipeline.sheet_index import _index_input
from backend.prompts import (
    EXTRACTOR_SYSTEM_PROMPT,
    EXTRACTOR_USER_INSTRUCTION,
    JURISDICTION_SYSTEM_PROMPT,
    JURISDICTION_USER_INSTRUCTION,
    SHEET_INDEX_SYSTEM_PROMPT,
    SHEET_INDEX_USER_INSTRUCTION,
)


# Appended to the extractor instruction on the second-chance retry. Dense plan
# sheets blow the output budget on the full schema; compact mode trades
# per-object verbosity for actually finishing the page.
_COMPACT_RETRY_SUFFIX = """
IMPORTANT - COMPACT RETRY: the first pass did not complete. Keep the SAME JSON
schema, but extract at most 40 objects, prioritizing coordination-relevant
items (equipment, fixtures, devices, keynotes, dimensions, markers/callouts,
schedule rows). Keep descriptions/attributes short; skip review_uses entries
you are unsure about. Finish the JSON - a smaller complete answer beats a
larger truncated one."""


def _wrap_bare_list(parsed, page_number: int):
    """Models sometimes skip the {sheet, objects} wrapper and return a bare
    objects array (especially after truncation repair). Accept it - the sheet
    header falls back to title-block deduction downstream."""
    if isinstance(parsed, list):
        print(f"[Extract] Page {page_number}: wrapping bare objects array "
              f"({len(parsed)} items, no sheet header)")
        return {"sheet": {}, "objects": parsed}
    return parsed


class SheetExtractorAgent:
    name = "sheet_extractor"

    def __init__(self, usage: AgentUsage) -> None:
        self.usage = usage

    def _call(self, instruction: str, page: Dict):
        return call_json(
            system_prompt=EXTRACTOR_SYSTEM_PROMPT,
            user_text=instruction,
            images_b64=[page["base64"]],
            max_tokens=config.EXTRACT_MAX_TOKENS,
            model=config.AGENT_EXTRACT_MODEL,
            usage_tracker=self.usage,
            usage_stage="agent.extract",
            reasoning_effort=config.EXTRACT_REASONING_EFFORT or None,
            reasoning_max_tokens=config.EXTRACT_REASONING_MAX_TOKENS or None,
        )

    def run(self, scope: AgentScope) -> AgentResult:
        try:
            page = scope.payload["page"]
            instruction = EXTRACTOR_USER_INSTRUCTION.replace(
                "{sheet_hint}", str(scope.payload.get("sheet_hint") or "")
            )
            parsed = _wrap_bare_list(self._call(instruction, page),
                                     page["page_number"])
            if not isinstance(parsed, dict):
                # Second chance: same page, compact instructions. Runs only
                # when the full-schema pass returned nothing usable.
                print(f"[Extract] Page {page['page_number']}: full extraction "
                      f"failed, retrying compact")
                parsed = _wrap_bare_list(
                    self._call(instruction + _COMPACT_RETRY_SUFFIX, page),
                    page["page_number"],
                )
            if not isinstance(parsed, dict):
                raise ValueError("no structured extraction returned")
            sheet = _normalize_sheet(parsed, page["page_number"])
            return AgentResult(scope_id=scope.scope_id, artifacts=[sheet])
        except Exception as exc:
            return failure(scope, exc)


class SheetIndexAgent:
    name = "sheet_index"

    def __init__(self, usage: AgentUsage) -> None:
        self.usage = usage

    def run(self, scope: AgentScope) -> AgentResult:
        try:
            sheets = scope.payload.get("sheets") or []
            instruction = SHEET_INDEX_USER_INSTRUCTION.replace(
                "{sheet_index_input}",
                json.dumps(_index_input(sheets), ensure_ascii=True),
            )
            parsed = call_json(
                system_prompt=SHEET_INDEX_SYSTEM_PROMPT,
                user_text=instruction,
                max_tokens=config.SHEET_INDEX_MAX_TOKENS,
                model=config.AGENT_INDEX_MODEL,
                usage_tracker=self.usage,
                usage_stage="agent.sheet_index",
            )
            if isinstance(parsed, list):
                parsed = {"sheet_index": parsed, "missing_expected_sheets": []}
            if not isinstance(parsed, dict):
                raise ValueError("no sheet index returned")
            return AgentResult(scope_id=scope.scope_id, artifacts=[parsed])
        except Exception as exc:
            return failure(scope, exc)


class JurisdictionAgent:
    name = "jurisdiction"

    def __init__(self, usage: AgentUsage) -> None:
        self.usage = usage

    def run(self, scope: AgentScope) -> AgentResult:
        try:
            project_input: Dict = scope.payload.get("project_input") or {}
            instruction = JURISDICTION_USER_INSTRUCTION.replace(
                "{project_input}", json.dumps(project_input, ensure_ascii=True)
            )
            parsed = call_json(
                system_prompt=JURISDICTION_SYSTEM_PROMPT,
                user_text=instruction,
                max_tokens=config.JURISDICTION_MAX_TOKENS,
                model=config.AGENT_JURISDICTION_MODEL,
                usage_tracker=self.usage,
                usage_stage="agent.jurisdiction",
            )
            if not isinstance(parsed, dict):
                raise ValueError("no jurisdiction profile returned")
            profile = parsed.get("project_code_profile")
            artifact = profile if isinstance(profile, dict) else parsed
            return AgentResult(scope_id=scope.scope_id, artifacts=[artifact])
        except Exception as exc:
            return failure(scope, exc)