Conflict_Checker/backend/review/feedback.py

"""Feedback labels: one label artifact per human-review decision, for metrics.

Labels are written twice: job-locally under ``<out_dir>/review/`` (the
auditable record for that run) and, via ``append_shared_feedback``, to the
cross-job store at ``config.REVIEW_FEEDBACK_DIR``. The shared store is
append-only and nothing reads it yet - it exists so that a later pass can prime
a run with what reviewers corrected on previous sets without having to walk
every job directory.
"""

import json
import os
from datetime import datetime, timezone

from backend import config


def _as_dict(value) -> dict:
    return value if isinstance(value, dict) else {}


def decision_to_label(queue_item: dict, decision: dict, job: dict) -> dict:
    """Build one feedback label from a queue item, its decision, and the job.

    All field access is defensive: missing fields degrade to None (or [] for
    models_used) rather than raising.
    """
    queue_item = _as_dict(queue_item)
    decision = _as_dict(decision)
    job = _as_dict(job)
    payload = _as_dict(queue_item.get("payload"))
    summary = _as_dict(_as_dict(job.get("report")).get("summary"))
    return {
        "kind": "review_decision",
        "review_item_id": queue_item.get("review_item_id"),
        "job_id": job.get("job_id"),
        "pipeline_mode": job.get("pipeline_mode"),
        "source_stage": payload.get("source_stage"),
        "category": payload.get("category"),
        "severity": payload.get("severity"),
        "confidence": payload.get("confidence"),
        "decision": decision.get("decision"),
        "reason_code": decision.get("reason_code"),
        # The reviewer's structured corrections. Carried here (and into the
        # cross-job store) so "wrong category" survives as data rather than
        # only as free text on the suppressed issue.
        "category_correction": decision.get("category_correction"),
        "severity_correction": decision.get("severity_correction"),
        "location": payload.get("location"),
        "disciplines": payload.get("disciplines"),
        "sheets": payload.get("sheets"),
        "drawing_type": payload.get("drawing_type"),
        "models_used": summary.get("models_used") or [],
        "created_at": datetime.now(timezone.utc).isoformat(),
    }


def write_label(out_dir: str, label: dict) -> None:
    """Append one label job-locally and to the cross-job store.

    Never raises on I/O failure: a lost label must not fail the save that
    produced it.
    """
    append_shared_feedback(label)
    try:
        review_dir = os.path.join(out_dir, "review")
        os.makedirs(review_dir, exist_ok=True)
        path = os.path.join(review_dir, "feedback_labels.jsonl")
        with open(path, "a", encoding="utf-8") as f:
            f.write(json.dumps(label) + "\n")
    except OSError as e:
        print(f"[Review] feedback label write failed: {e}")


def append_shared_feedback(record: dict) -> None:
    """Append one record to the cross-job feedback store; never raises.

    One JSONL file per record ``kind`` so a reader can pick up decisions and
    chat turns independently. Failure here is logged and swallowed: the
    cross-job roll-up is a convenience, and losing a line must never fail the
    review action that produced it.
    """
    try:
        kind = str(record.get("kind") or "misc")
        os.makedirs(config.REVIEW_FEEDBACK_DIR, exist_ok=True)
        name = "chat_turns.jsonl" if kind == "review_chat_turn" else "decisions.jsonl"
        path = os.path.join(config.REVIEW_FEEDBACK_DIR, name)
        with open(path, "a", encoding="utf-8") as f:
            f.write(json.dumps(record) + "\n")
    except OSError as e:
        print(f"[Review] shared feedback write failed: {e}")


def read_shared_feedback(kind: str = "review_decision") -> list:
    """Read the cross-job store for one record kind, oldest first.

    Corrupt lines are skipped so a partial write cannot hide the rest.
    """
    name = "chat_turns.jsonl" if kind == "review_chat_turn" else "decisions.jsonl"
    path = os.path.join(config.REVIEW_FEEDBACK_DIR, name)
    if not os.path.isfile(path):
        return []
    records = []
    try:
        with open(path, encoding="utf-8") as f:
            for line in f:
                line = line.strip()
                if not line:
                    continue
                try:
                    value = json.loads(line)
                except json.JSONDecodeError:
                    continue
                if isinstance(value, dict):
                    records.append(value)
    except OSError:
        return []
    return records