src/run_history.py

"""
Run history — saves and loads completed pipeline runs as JSON.
Each run is stored at data/output/run_history/run_YYYY-MM-DD_HH-MM-SS.json.
Keeps the full job list so results can be restored in the UI without rerunning.
"""
import json
import logging
from pathlib import Path
from datetime import datetime

log = logging.getLogger("run_history")
HISTORY_DIR = Path("data/output/run_history")


def save_run(jobs: list, run_meta: dict) -> str:
    """
    Save a completed run to history.
    run_meta should include: run_id, excel_path, platforms, roles.
    Returns the history file path, or '' on failure.
    """
    HISTORY_DIR.mkdir(parents=True, exist_ok=True)
    run_id = run_meta.get("run_id") or datetime.now().strftime("%Y-%m-%d_%H-%M-%S")

    high    = sum(1 for j in jobs if j.get("relevance_score", 0) >= 8)
    med     = sum(1 for j in jobs if 6 <= j.get("relevance_score", 0) <= 7)
    resumes = sum(1 for j in jobs if j.get("resume_path"))
    pdfs    = sum(1 for j in jobs if j.get("resume_pdf_path"))

    ats_before = [j["ats_score_before"] for j in jobs
                  if j.get("ats_score_before") not in (None, "", 0)]
    ats_after  = [j["ats_score_after"]  for j in jobs
                  if j.get("ats_score_after")  not in (None, "", 0)]

    record = {
        "run_id":         run_id,
        "date":           datetime.now().strftime("%Y-%m-%d %H:%M"),
        "total_jobs":     len(jobs),
        "high_priority":  high,
        "med_priority":   med,
        "resumes":        resumes,
        "pdfs":           pdfs,
        "avg_ats_before": int(sum(ats_before) / len(ats_before)) if ats_before else 0,
        "avg_ats_after":  int(sum(ats_after)  / len(ats_after))  if ats_after  else 0,
        "platforms":      list(set(j.get("platform", "") for j in jobs if j.get("platform"))),
        "roles":          run_meta.get("roles", []),
        "excel_path":     run_meta.get("excel_path", ""),
        "jobs":           jobs,
    }

    path = HISTORY_DIR / f"run_{run_id}.json"
    try:
        with open(path, "w", encoding="utf-8") as f:
            json.dump(record, f, ensure_ascii=False, default=str)
        log.info(f"Run saved to history: {path}")
        return str(path)
    except Exception as e:
        log.error(f"Failed to save run history: {e}")
        return ""


def list_runs() -> list:
    """
    List all saved runs, newest first.
    Returns list of summary dicts (no jobs key — kept light for UI listing).
    """
    if not HISTORY_DIR.exists():
        return []
    runs = []
    for p in sorted(HISTORY_DIR.glob("run_*.json"), reverse=True):
        try:
            with open(p, "r", encoding="utf-8") as f:
                data = json.load(f)
            summary = {k: v for k, v in data.items() if k != "jobs"}
            summary["_path"] = str(p)
            runs.append(summary)
        except Exception:
            pass
    return runs


def load_run(path: str) -> dict:
    """Load a full run (including jobs list) from a history JSON file."""
    try:
        with open(path, "r", encoding="utf-8") as f:
            return json.load(f)
    except Exception as e:
        log.error(f"Failed to load run {path}: {e}")
        return {}