bin/projekt-matching/projektmatch/stages.py

"""Flow 2 stage functions. Each takes (ctx, cfg) and returns ctx.

ctx["status"]: "ok" -> pipeline continues; "failed" -> all later stages
skip; "rejected" -> only CRM/notify skip; "created" -> set by stage_crm.
"""
from __future__ import annotations

import datetime as dt
import json
import time
from pathlib import Path

import requests
from bs4 import BeautifulSoup

from . import espocrm, llm, mailer, pm_trace, rules
from .mailparse import BROWSER_UA

TEAM_BY_OFFER = {"Projekt": "DesTEngS",
                 "Arbeitnehmer-Angebot": "Arbeitnehmer",
                 "ANÜ": "ANÜ"}
MIN_PAGE_CHARS = 200
QUOTES = str.maketrans({c: "'" for c in "„“”\"«»‹›"})


def run_stage(name, fn, ctx, cfg, **kw):
    if ctx.get("status") == "failed":
        return ctx
    try:
        return fn(ctx, cfg, **kw)
    except Exception as exc:                     # noqa: BLE001
        ctx.update(status="failed", error=f"{name}: {exc}")
        return ctx


def page_text(html):
    """Project text for the LLM: header + description, WITHOUT the skill-tag
    cloud (div.project-body-badges, ~100 entries on some pages — blows the
    requirements list up until the model emits broken JSON) and without
    site chrome. Falls back to whole-page text if div.content is missing."""
    soup = BeautifulSoup(html, "html.parser")
    for tag in soup(["script", "style", "noscript"]):
        tag.decompose()
    root = soup.find("div", class_="content") or soup
    for tag in root.find_all(class_="project-body-badges"):
        tag.decompose()
    # Anführungszeichen -> Apostroph: ein wörtlich übernommenes " beendet den
    # JSON-String vorzeitig und treibt guided decoding in eine Whitespace-
    # Endlosschleife (finish_reason "length", live verifiziert an nproj/3022414)
    return "\n".join(line for line in
                     root.get_text("\n", strip=True).splitlines()
                     if line.strip()).translate(QUOTES)


def stage_fetch(ctx, cfg):
    last = None
    for attempt in range(3):
        try:
            resp = requests.get(ctx["canonical"], timeout=30,
                                headers={"User-Agent": BROWSER_UA})
            resp.raise_for_status()
            text = page_text(resp.text)
            if len(text) < MIN_PAGE_CHARS:
                raise ValueError(
                    f"Seitentext zu kurz ({len(text)} Zeichen) — "
                    f"Login-Wall oder leere Seite?")
            ctx.update(page_text=text[:llm.PAGE_TEXT_LIMIT], status="ok")
            return ctx
        except Exception as exc:                 # noqa: BLE001
            last = exc
            time.sleep(2 * (attempt + 1))
    raise RuntimeError(f"Abruf fehlgeschlagen: {last}")


def stage_extract(ctx, cfg):
    ctx["extract"] = llm.extract_project(cfg.vllm_base, cfg.vllm_model,
                                         ctx["page_text"])
    ctx["projectName"] = ctx["extract"]["projectName"]
    return ctx


def stage_match(ctx, cfg):
    reqs = [{"nr": i + 1, "text": r["text"]}
            for i, r in enumerate(ctx["extract"]["requirements"])
            if r["kat"] in ("Must", "Nice")]
    if not reqs:
        ctx["ratings"] = []
        return ctx
    cv_path = Path(cfg.data_dir) / "vorgaben" / \
        "Lebenslauf_Dr-Ing_Thomas_Langer.md"
    cv_text = cv_path.read_text(encoding="utf-8")
    ctx["ratings"] = llm.match_cv(cfg.vllm_base, cfg.vllm_model, cv_text, reqs)
    return ctx


def stage_rules(ctx, cfg):
    today = dt.date.today()
    rated = {r["nr"]: r["rating"] for r in ctx.get("ratings", [])}
    rows, nr = [], 0
    for req in ctx["extract"]["requirements"]:
        if req["kat"] in ("Must", "Nice"):
            nr += 1
            rating = rated.get(nr, rules.UNKNOWN)
        else:
            rating = rules.eval_misc(req, today)
        rows.append({"kat": req["kat"], "rating": rating, "text": req["text"]})
    rows = rules.order_rows(rows)
    ctx["mustMatch"] = rules.calc_match(rows, "Must")
    ctx["niceMatch"] = rules.calc_match(rows, "Nice")
    ctx["description"] = rules.build_description(rows)
    consider = ctx["mustMatch"] is not None and \
        ctx["mustMatch"] > int(cfg.threshold)
    ctx["decision"] = "consider" if consider else "rejected"
    if not consider:
        ctx["status"] = "rejected"
    return ctx


def stage_crm(ctx, cfg, espo=None):
    if ctx.get("status") != "ok" or ctx.get("decision") != "consider":
        return ctx
    espo = espo or espocrm.EspoClient(cfg.espo_base, cfg.espo_api_key)
    ex = ctx["extract"]
    team = espo.team_id(TEAM_BY_OFFER[ex["offerType"]])
    agency = ex["buyerType"] == "agency"
    account_id = None
    if ex.get("companyName"):
        account_id = espo.ensure_account(
            ex["companyName"], "Reseller" if agency else "Customer")
    contact_id = None
    if ex.get("contactPerson") and account_id:
        first, last = espocrm.split_person(ex["contactPerson"])
        contact_id = espo.ensure_contact(first, last, account_id)
    name = espo.unique_opportunity_name(ex["projectName"])
    payload = {"name": name, "description": ctx["description"],
               "cProjektlink": ctx["canonical"], "teamsIds": [team]}
    if account_id:
        payload["cAccount1Id" if agency else "accountId"] = account_id
    if contact_id:
        payload["contactsIds"] = [contact_id]
    created = espo.create_opportunity(payload)
    oid = created["id"]
    back = espo.get_opportunity(oid)
    problems = []
    if back.get("name") != name:
        problems.append("name")
    if back.get("cProjektlink") != ctx["canonical"]:
        problems.append("cProjektlink")
    if back.get("description") != ctx["description"]:
        problems.append("description")
    if team not in (back.get("teamsIds") or []):
        problems.append("teamsIds")
    if account_id and agency and back.get("cAccount1Id") != account_id:
        problems.append("cAccount1Id")
    if account_id and not agency and back.get("accountId") != account_id:
        problems.append("accountId")
    if problems:
        raise RuntimeError(f"CRM-Verifikation fehlgeschlagen: {problems}")
    ctx.update(status="created", opportunityId=oid, projectName=name,
               crmUrl=f"{cfg.crm_web_base}/#Opportunity/view/{oid}")
    return ctx


def stage_notify(ctx, cfg):
    """Send notification on created; ALWAYS post the Langfuse trace.

    Called directly by the component (not via run_stage), so failed runs
    still get their trace and an SMTP error cannot lose it."""
    try:
        if ctx.get("status") == "created":
            subject = (f"[Projekt-Match] Freelancermap — {ctx['mustMatch']} % — "
                       f"{ctx['projectName']}")
            body = (f"Neues passendes Projekt gefunden.\n\n"
                    f"Projekt: {ctx['projectName']}\n"
                    f"Must-have-Match: {rules.fmt_match(ctx['mustMatch'])}\n"
                    f"Nice-to-have-Match: {rules.fmt_match(ctx.get('niceMatch'))}\n\n"
                    f"CRM-Verkaufschance: {ctx['crmUrl']}\n")
            mailer.send_mail(cfg.imap_user, cfg.imap_password, cfg.notify_to,
                             subject, body)
    except Exception as exc:  # noqa: BLE001
        ctx.update(status="failed", error=f"notify: {exc}")
    pm_trace.post_trace(ctx)
    return ctx


def summary(ctx):
    """Compact JSON result string for TextOutput / Flow 1."""
    keys = ("status", "error", "decision", "mustMatch", "niceMatch",
            "opportunityId", "crmUrl", "projectName", "canonical")
    return json.dumps({k: ctx.get(k) for k in keys}, ensure_ascii=False)