Initial commit: avc-phone-ai codebase + CLAUDE.md

extract.py

@@ -0,0 +1,101 @@
+"""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
+
+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\n'
+    '  "callback_number": string or null (digits the caller gave to be called back)\n'
+    '  "location": string or null (which office/city)\n'
+    '  "reason": string or null (e.g. eye exam, broken glasses)\n'
+    '  "preferred_time": string or null (day/time in the caller\'s words)\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]
+
+    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": _EXTRACT_INSTRUCTIONS},
+                        {"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
+
+    # Prefer the verified Twilio caller-ID over a number pulled from the transcript —
+    # the model sometimes invents/echoes a phone number. Keep a genuinely different
+    # spoken number as a note for staff.
+    spoken = (data.get("callback_number") or "").strip()
+    callback = caller_number or spoken or None
+    reason = data.get("reason")
+    if spoken and caller_number and re.sub(r"\D", "", spoken) != re.sub(r"\D", "", caller_number):
+        reason = f"{reason or ''} (caller mentioned alternate number: {spoken})".strip()
+
+    record = {
+        "call_sid": call_sid,
+        "patient_name": data.get("patient_name"),
+        "callback_number": callback,
+        "location": data.get("location"),
+        "reason": reason,
+        "preferred_time": data.get("preferred_time"),
+        "source": "post_call_extraction",
+    }
+    where = persist_appointment(record)
+    logger.info(f"Post-call appointment saved ({where}): {record['patient_name']} / {record['location']}")
+    return record