avc-phone-ai/extract.py

"""Post-call appointment extraction.

Instead of unreliable in-call tool-calling (which made llama3.1:8b speak raw JSON),
we let the agent gather appointment details conversationally, then run ONE structured
extraction over the finished transcript and write it to Odoo. Reliable because it's a
single JSON-mode completion, not mid-conversation tool emission.
"""

import json
import re
from datetime import datetime

import httpx
from loguru import logger

from practice import persist_appointment

_EXTRACT_INSTRUCTIONS = (
    "You are reviewing a phone-call transcript between a caller and the receptionist "
    "for an optometry practice. Extract any APPOINTMENT REQUEST the caller made.\n"
    "Respond with ONLY a JSON object with these keys:\n"
    '  "wants_appointment": boolean — true only if the caller asked to book/schedule a visit\n'
    '  "patient_name": string or null — the caller\'s FULL name (first and last) if given\n'
    '  "phone_ok": boolean or null — true if the caller confirmed their caller-ID number is the '
    "best one, false if they said to use a different number, null if it never came up\n"
    '  "alternate_number": string or null — a different callback number the caller gave, digits only\n'
    '  "location": string or null (which office/city)\n'
    '  "reason": string or null — WHY they want to be seen: the visit type OR the eye '
    "problem/symptom they describe. Capture symptoms too (e.g. \"annual eye exam\", \"blurry "
    'vision", "vision loss / blindness", "eye pain", "broken glasses", "red eye"). If they '
    "describe any eye or vision problem, that IS the reason.\n"
    '  "insurance": string or null — the insurance plan the caller named, exactly as they said it\n'
    '  "preferred_time": string or null — the day/time in the caller\'s own words\n'
    '  "resolved_date": string or null — the actual calendar date the caller means as YYYY-MM-DD, '
    "computed from TODAY given below; null if it cannot be determined\n"
    "Use null for anything not clearly stated. Do not invent values."
)


async def extract_and_record(messages, ollama_url, model, call_sid=None, caller_number=None):
    """Extract an appointment from the transcript and persist it. Returns the record
    dict if one was saved, else None."""
    # Build a plain transcript from the conversation (skip the system prompt).
    turns = [
        f"{m['role']}: {m['content']}"
        for m in messages
        if m.get("role") in ("user", "assistant") and isinstance(m.get("content"), str) and m["content"].strip()
    ]
    if not any(m.get("role") == "user" for m in messages):
        return None  # nobody said anything
    transcript = "\n".join(turns)

    base = ollama_url.rstrip("/")
    if base.endswith("/v1"):
        base = base[:-3]

    today = datetime.now().strftime("%A, %B %d, %Y").replace(" 0", " ")
    try:
        async with httpx.AsyncClient(timeout=30) as client:
            r = await client.post(
                f"{base}/api/chat",
                json={
                    "model": model,
                    "format": "json",
                    "stream": False,
                    "options": {"temperature": 0},
                    "messages": [
                        {"role": "system", "content": f"{_EXTRACT_INSTRUCTIONS}\n\nTODAY is {today}."},
                        {"role": "user", "content": f"Transcript:\n{transcript}"},
                    ],
                },
            )
            r.raise_for_status()
            data = json.loads(r.json()["message"]["content"])
    except Exception:
        logger.exception("Appointment extraction call failed")
        return None

    if not data.get("wants_appointment"):
        logger.info("Post-call extraction: no appointment requested")
        return None

    # Don't create near-empty cards from quick hang-ups: require at least a name or a
    # reason. A bare location + caller-ID isn't enough to be worth a worklist card.
    name = (data.get("patient_name") or "").strip()
    reason_raw = (data.get("reason") or "").strip()
    if not name and not reason_raw:
        logger.info("Post-call extraction: appointment intent but no name/reason captured — skipping card")
        return None

    # Callback number: default to the verified Twilio caller-ID. If the caller explicitly
    # declined it (phone_ok == False) and gave a different number, use the one they gave.
    alt = (data.get("alternate_number") or "").strip()
    phone_ok = data.get("phone_ok")
    if phone_ok is False and alt:
        callback = alt
    else:
        callback = caller_number or alt or None
    # If they gave a different number but didn't clearly decline the caller-ID, keep it as a note.
    note_alt = (
        alt and caller_number and callback != alt
        and re.sub(r"\D", "", alt) != re.sub(r"\D", "", caller_number)
    )

    # Preferred time = caller's words, annotated with the resolved calendar date if we got one.
    preferred = (data.get("preferred_time") or "").strip() or None
    resolved = (data.get("resolved_date") or "").strip() or None
    if resolved:
        preferred = f"{preferred} (resolved: {resolved})" if preferred else resolved

    reason = data.get("reason")
    if note_alt:
        reason = f"{reason or ''} (caller also mentioned number: {alt})".strip()

    record = {
        "call_sid": call_sid,
        "patient_name": data.get("patient_name"),
        "callback_number": callback,
        "phone_confirmed": phone_ok,
        "location": data.get("location"),
        "reason": reason,
        "insurance": (data.get("insurance") or "").strip() or None,
        "preferred_time": preferred,
        "source": "post_call_extraction",
    }
    where = persist_appointment(record)
    logger.info(
        f"Post-call appointment saved ({where}): {record['patient_name']} / "
        f"{record['location']} / reason={record['reason']} / ins={record['insurance']} / "
        f"when={record['preferred_time']}"
    )
    return record