Files
simbarag/blueprints/imessage/__init__.py
T
ryan 7474055c97 Add iMessage threading, typing indicators, and fix tool-use response extraction
- Native reply threading: inbound replies continue their conversation via
  SendBlue message_handle lookup; standalone messages create a new conversation
- Our responses are sent with reply_to so they thread visually in iMessage
- Typing indicator fires before agent invocation and stops in a finally block
- Add extract_agent_text() to handle list-type AIMessage content and strip
  <think> tokens from Qwen3 — applied to iMessage, WhatsApp, and web chat
- ConversationMessage gains a nullable message_handle field (migration needed)
- /threads command lists recent iMessage conversations

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-09-15 23:10:50 -04:00

369 lines
13 KiB
Python

import os
import hmac
import logging
import functools
import time
from collections import defaultdict
import httpx
from quart import Blueprint, request, jsonify
from blueprints.users.models import User
from blueprints.conversation.logic import (
get_conversation_for_channel,
add_message_to_conversation,
persist_agent_tool_messages,
)
from blueprints.conversation.models import Conversation, ConversationMessage, Speaker
from blueprints.conversation.agents import main_agent
from blueprints.conversation.memory import build_system_prompt_with_memories
from utils.strip_markdown import extract_agent_text, strip_markdown
imessage_blueprint = Blueprint("imessage_api", __name__, url_prefix="/api/imessage")
logger = logging.getLogger(__name__)
# Rate limiting: per-number message timestamps
_rate_limit_store: dict[str, list[float]] = defaultdict(list)
RATE_LIMIT_MAX = int(os.getenv("IMESSAGE_RATE_LIMIT_MAX", "10"))
RATE_LIMIT_WINDOW = int(os.getenv("IMESSAGE_RATE_LIMIT_WINDOW", "60"))
MAX_MESSAGE_LENGTH = 2000
SENDBLUE_API_BASE = "https://api.sendblue.co"
def _get_sendblue_headers() -> dict[str, str]:
return {
"sb-api-key-id": os.getenv("SENDBLUE_API_KEY", ""),
"sb-api-secret-key": os.getenv("SENDBLUE_API_SECRET", ""),
"Content-Type": "application/json",
}
def _check_rate_limit(phone_number: str) -> bool:
"""Check if a phone number has exceeded the rate limit.
Returns True if the request is allowed, False if rate-limited.
"""
now = time.monotonic()
cutoff = now - RATE_LIMIT_WINDOW
timestamps = _rate_limit_store[phone_number]
_rate_limit_store[phone_number] = [t for t in timestamps if t > cutoff]
if len(_rate_limit_store[phone_number]) >= RATE_LIMIT_MAX:
return False
_rate_limit_store[phone_number].append(now)
return True
async def send_imessage(
to_number: str,
content: str,
reply_to_handle: str | None = None,
) -> dict:
"""Send an iMessage via SendBlue API."""
from_number = os.getenv("SENDBLUE_FROM_NUMBER", "")
payload: dict = {
"number": to_number,
"from_number": from_number,
"content": content,
}
if reply_to_handle:
payload["reply_to"] = {"message_handle": reply_to_handle}
async with httpx.AsyncClient() as client:
resp = await client.post(
f"{SENDBLUE_API_BASE}/api/send-message",
headers=_get_sendblue_headers(),
json=payload,
timeout=30,
)
resp.raise_for_status()
return resp.json()
async def send_typing_indicator(
to_number: str,
state: str = "start",
max_duration_ms: int | None = None,
) -> None:
"""Send or stop a typing indicator. Errors are logged and swallowed."""
from_number = os.getenv("SENDBLUE_FROM_NUMBER", "")
payload: dict = {
"number": to_number,
"from_number": from_number,
"state": state,
}
if max_duration_ms is not None:
payload["max_duration_ms"] = max_duration_ms
try:
async with httpx.AsyncClient() as client:
await client.post(
f"{SENDBLUE_API_BASE}/api/send-typing-indicator",
headers=_get_sendblue_headers(),
json=payload,
timeout=10,
)
except Exception as e:
logger.warning(f"Failed to send typing indicator ({state}): {e}")
def validate_sendblue_signature(f):
"""Decorator to validate the SendBlue webhook signing secret."""
@functools.wraps(f)
async def decorated_function(*args, **kwargs):
if os.getenv("SENDBLUE_SIGNATURE_VALIDATION", "true").lower() == "false":
return await f(*args, **kwargs)
secret = os.getenv("SENDBLUE_WEBHOOK_SECRET")
if not secret:
logger.error("SENDBLUE_WEBHOOK_SECRET not set — rejecting request")
return jsonify({"error": "Server misconfigured"}), 500
sig = request.headers.get("sb-signing-secret", "")
if not hmac.compare_digest(sig, secret):
logger.warning("Invalid SendBlue signing secret")
return jsonify({"error": "Unauthorized"}), 403
return await f(*args, **kwargs)
return decorated_function
@imessage_blueprint.route("/webhook", methods=["POST"])
@validate_sendblue_signature
async def webhook():
"""Handle incoming iMessages from SendBlue."""
data = await request.get_json()
if not data:
return jsonify({"error": "Invalid payload"}), 400
from_number = data.get("from_number")
content = data.get("content") or ""
media_url = data.get("media_url")
is_outbound = data.get("is_outbound", False)
# Threading fields from SendBlue
inbound_handle = data.get("message_handle")
reply_to_handle = (data.get("reply_to") or {}).get("message_handle")
originator_handle = (data.get("thread_originator") or {}).get("message_handle")
# Ignore outbound messages (our own replies echoed back)
if is_outbound:
return jsonify({"status": "ignored"}), 200
if not from_number:
return jsonify({"error": "Missing from_number"}), 400
if not content and not media_url:
return jsonify({"error": "Missing content and media_url"}), 400
content = content.strip()
if not content and not media_url:
await send_imessage(
from_number,
"I received an empty message. Please send some text or an image!",
)
return jsonify({"status": "ok"}), 200
# Rate limiting
if not _check_rate_limit(from_number):
logger.warning(f"Rate limit exceeded for {from_number}")
await send_imessage(
from_number,
"You're sending messages too quickly. Please wait a moment and try again.",
)
return jsonify({"status": "rate_limited"}), 200
# Truncate overly long messages
if len(content) > MAX_MESSAGE_LENGTH:
content = content[:MAX_MESSAGE_LENGTH]
logger.info(
f"Truncated long message from {from_number} to {MAX_MESSAGE_LENGTH} chars"
)
logger.info(f"Received iMessage from {from_number}: {content[:100]}")
# Identify or create user
user = await User.filter(imessage_number=from_number).first()
if not user:
allowed_numbers = os.getenv("ALLOWED_IMESSAGE_NUMBERS", "").split(",")
if from_number not in allowed_numbers and "*" not in allowed_numbers:
await send_imessage(
from_number, "Sorry, you are not authorized to use this service."
)
return jsonify({"status": "unauthorized"}), 200
username = f"im_{from_number.lstrip('+')}"
try:
user = await User.create(
username=username,
email=f"{username}@imessage.simbarag.local",
imessage_number=from_number,
auth_provider="imessage",
)
logger.info(f"Created new user for iMessage: {username}")
except Exception as e:
logger.error(f"Failed to create user for {from_number}: {e}")
await send_imessage(
from_number, "Sorry, something went wrong setting up your account."
)
return jsonify({"status": "error"}), 200
# iMessage is restricted to admins
if not user.is_admin():
logger.warning(f"Non-admin user {user.username} attempted iMessage access")
await send_imessage(from_number, "Sorry, this feature is restricted to admins.")
return jsonify({"status": "forbidden"}), 200
# /threads command — list recent iMessage conversations
if content.strip().lower() == "/threads":
threads = (
await Conversation.filter(user=user, channel="imessage")
.order_by("-updated_at")
.limit(5)
)
if not threads:
await send_imessage(from_number, "No threads found.")
else:
lines = ["Your recent threads (most recent first):"]
for i, t in enumerate(threads, 1):
updated = t.updated_at.strftime("%b %-d")
lines.append(f"{i}. {t.name} ({updated})")
lines.append("\nReply to any message to continue its thread.")
await send_imessage(from_number, "\n".join(lines))
return jsonify({"status": "ok"}), 200
# Determine conversation based on iMessage reply threading:
# - Reply to an existing message → continue that conversation
# - New standalone message → start a fresh conversation
try:
if reply_to_handle:
lookup_handle = originator_handle or reply_to_handle
parent_msg = await ConversationMessage.get_or_none(
message_handle=lookup_handle,
conversation__user=user,
conversation__channel="imessage",
)
if parent_msg:
conversation = await Conversation.get(id=parent_msg.conversation_id)
logger.info(
f"Continuing conversation {conversation.id} via reply to {lookup_handle!r}"
)
else:
# Handle not found (pre-migration messages) — fall back to most recent
logger.warning(
f"Reply handle {lookup_handle!r} not in DB; falling back to most recent conversation"
)
conversation = await get_conversation_for_channel(
user=user, channel="imessage"
)
else:
conversation = await Conversation.create(
name="New iMessage",
user=user,
channel="imessage",
)
logger.info(
f"New iMessage conversation {conversation.id} for {user.username}"
)
await conversation.fetch_related("messages")
except Exception as e:
logger.error(f"Failed to get/create conversation for {user.username}: {e}")
await send_imessage(
from_number, "Sorry, something went wrong. Please try again later."
)
return jsonify({"status": "error"}), 200
# Add user message (store the inbound handle for future reply lookups)
await add_message_to_conversation(
conversation=conversation,
message=content,
speaker="user",
user=user,
message_handle=inbound_handle,
)
# Attach image directly to the agent request if present
image_block = None
if media_url:
try:
from utils.image_process import image_content_block
async with httpx.AsyncClient() as client:
resp = await client.get(media_url, timeout=30)
resp.raise_for_status()
image_block = image_content_block(resp.content)
except Exception as e:
logger.error(f"Failed to load iMessage image: {e}")
content = f"{content or ''}\n\n[An image was sent but could not be loaded.]".strip()
# Show typing indicator for up to 2 minutes while the agent processes
await send_typing_indicator(from_number, state="start", max_duration_ms=120_000)
# Build messages payload for LangChain agent
response_text = "Sorry, I'm having trouble thinking right now."
try:
messages = await conversation.messages.all()
recent_messages = list(messages)[-20:]
system_prompt = await build_system_prompt_with_memories(str(user.id))
messages_payload = [{"role": "system", "content": system_prompt}]
for msg in recent_messages[:-1]:
role = "user" if msg.speaker == Speaker.USER else "assistant"
messages_payload.append({"role": role, "content": msg.text})
if image_block:
user_content = [
{"type": "text", "text": content or "The user sent this image."},
image_block,
]
else:
user_content = content
messages_payload.append({"role": "user", "content": user_content})
agent_config = {
"configurable": {"user_id": str(user.id), "is_admin": user.is_admin()}
}
logger.info(f"Invoking LangChain agent with {len(messages_payload)} messages")
response = await main_agent.ainvoke(
{"messages": messages_payload}, config=agent_config
)
response_text = extract_agent_text(response.get("messages", [])[-1].content)
await persist_agent_tool_messages(
conversation, user, response.get("messages", [])
)
except Exception as e:
logger.error(f"Error invoking agent: {e}")
finally:
await send_typing_indicator(from_number, state="stop")
# Send reply threaded under the user's inbound message
send_resp = await send_imessage(
from_number,
strip_markdown(response_text),
reply_to_handle=inbound_handle,
)
outbound_handle = (send_resp or {}).get("message_handle")
await add_message_to_conversation(
conversation=conversation,
message=response_text,
speaker="simba",
user=user,
message_handle=outbound_handle,
)
return jsonify({"status": "ok"}), 200