feat(matrix): land QA follow-ups and refresh docs

- harden Matrix onboarding/chat lifecycle after manual QA
- refresh README and Matrix docs to match current behavior
- add local ignores for runtime artifacts and include current planning/report docs

Closes #7
Closes #9
Closes #14
This commit is contained in:
Mikhail Putilovskij 2026-04-05 19:08:58 +03:00
parent 7fce4c9b3e
commit 6ced154124
35 changed files with 8380 additions and 67 deletions

View file

@ -0,0 +1,511 @@
"""Telegram bot engine.
Handles messages (text, photo, voice), topic management, and Claude CLI integration.
Uses RetryHTTPXRequest for proxy resilience, progressive message editing for streaming.
"""
import asyncio
import json
import logging
import time
from datetime import datetime, timezone
from pathlib import Path
import yaml
from telegram import BotCommand, Update
from telegram.constants import ChatAction, ParseMode
from telegram.error import BadRequest, NetworkError
from telegram.ext import (
Application,
CommandHandler,
ContextTypes,
MessageHandler,
filters,
)
from telegram.request import HTTPXRequest
from core.asr import transcribe
from core.claude_session import send_message as claude_send
from core.config import Config
logger = logging.getLogger(__name__)
# Streaming edit parameters
EDIT_INTERVAL = 1.5 # seconds between message edits
EDIT_MIN_DELTA = 150 # minimum new chars before editing
class RetryHTTPXRequest(HTTPXRequest):
"""HTTPXRequest with retry on ConnectError (SOCKS5 proxy hiccups)."""
MAX_RETRIES = 3
RETRY_DELAY = 2
async def do_request(self, *args, **kwargs):
last_exc = None
for attempt in range(self.MAX_RETRIES):
try:
return await super().do_request(*args, **kwargs)
except NetworkError as e:
if "ConnectError" in str(e):
last_exc = e
if attempt < self.MAX_RETRIES - 1:
logger.warning(
"Telegram ConnectError (attempt %d/%d), retrying in %ds...",
attempt + 1, self.MAX_RETRIES, self.RETRY_DELAY,
)
await asyncio.sleep(self.RETRY_DELAY)
else:
raise
raise last_exc
def build_app(config: Config) -> Application:
"""Build and configure the Telegram Application."""
builder = Application.builder().token(config.bot_token)
# Configure HTTP client with proxy and timeouts
request_kwargs = {
"connect_timeout": 30.0,
"read_timeout": 60.0,
"write_timeout": 60.0,
"pool_timeout": 10.0,
}
if config.proxy:
request_kwargs["proxy"] = config.proxy
request = RetryHTTPXRequest(**request_kwargs)
builder = builder.request(request)
builder = builder.concurrent_updates(True)
app = builder.build()
# Store config in bot_data for handler access
app.bot_data["config"] = config
# Register handlers (order matters — more specific first)
app.add_handler(CommandHandler("start", handle_start))
app.add_handler(CommandHandler("newtopic", handle_new_topic))
app.add_handler(MessageHandler(filters.PHOTO, handle_photo))
app.add_handler(MessageHandler(filters.VOICE | filters.AUDIO, handle_voice))
app.add_handler(MessageHandler(filters.Document.ALL, handle_document))
app.add_handler(MessageHandler(filters.TEXT & ~filters.COMMAND, handle_message))
# Post-init: set bot commands
app.post_init = _post_init
return app
async def _post_init(application: Application) -> None:
"""Set bot commands menu after initialization."""
commands = [
BotCommand("newtopic", "Create a new topic"),
BotCommand("start", "Start / help"),
]
await application.bot.set_my_commands(commands)
logger.info("Bot initialized: @%s", application.bot.username)
def _get_config(context: ContextTypes.DEFAULT_TYPE) -> Config:
return context.bot_data["config"]
def _is_owner(update: Update, config: Config) -> bool:
return update.effective_user and update.effective_user.id == config.owner_id
def _topic_id(update: Update) -> str:
"""Get topic ID from message, or 'general' for the default topic."""
thread_id = update.effective_message.message_thread_id
return str(thread_id) if thread_id else "general"
def _topic_dir(config: Config, topic_id: str) -> Path:
"""Get data directory for a topic."""
d = config.data_dir / "topics" / topic_id
d.mkdir(parents=True, exist_ok=True)
return d
def _log_interaction(config: Config, topic_id: str, user_msg: str, bot_msg: str) -> None:
"""Append interaction to topic log."""
log_file = _topic_dir(config, topic_id) / "log.jsonl"
entry = {
"ts": datetime.now(timezone.utc).isoformat(),
"user": user_msg[:1000],
"bot": bot_msg[:2000],
}
with open(log_file, "a") as f:
f.write(json.dumps(entry, ensure_ascii=False) + "\n")
def _md_to_html(text: str) -> str:
"""Convert common Markdown to Telegram HTML."""
import re
# Escape HTML entities first (but preserve our conversions)
text = text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
# Code blocks: ```lang\n...\n```
text = re.sub(
r"```\w*\n(.*?)```",
lambda m: f"<pre>{m.group(1)}</pre>",
text, flags=re.DOTALL,
)
# Inline code: `...`
text = re.sub(r"`([^`]+)`", r"<code>\1</code>", text)
# Bold: **...**
text = re.sub(r"\*\*(.+?)\*\*", r"<b>\1</b>", text)
# Italic: *...*
text = re.sub(r"\*(.+?)\*", r"<i>\1</i>", text)
# Headers: ## ... → bold line
text = re.sub(r"^#{1,6}\s+(.+)$", r"<b>\1</b>", text, flags=re.MULTILINE)
# Bullet lists: - item → bullet
text = re.sub(r"^- ", "", text, flags=re.MULTILINE)
return text
async def _edit_text_md(message, text: str) -> None:
"""Edit message with HTML formatting, falling back to plain text."""
try:
html = _md_to_html(text)
await message.edit_text(html, parse_mode=ParseMode.HTML)
except BadRequest:
try:
await message.edit_text(text)
except BadRequest:
pass
# Cache of topic labels we've already applied: {topic_id: label}
_applied_labels: dict[str, str] = {}
# Pending questions from Claude: {topic_id: asyncio.Future}
_pending_questions: dict[str, asyncio.Future] = {}
async def _sync_topic_name(update: Update, config: Config, topic_id: str) -> None:
"""Rename Telegram topic if topic-map.yml has a new/changed label."""
if topic_id == "general":
return
topic_map_path = config.data_dir / "topic-map.yml"
if not topic_map_path.exists():
return
try:
with open(topic_map_path) as f:
topic_map = yaml.safe_load(f) or {}
entry = topic_map.get(topic_id) or topic_map.get(int(topic_id))
if not entry or not isinstance(entry, dict):
return
label = entry.get("label")
if not label or _applied_labels.get(topic_id) == label:
return
await update.get_bot().edit_forum_topic(
chat_id=update.effective_chat.id,
message_thread_id=int(topic_id),
name=label[:128],
)
_applied_labels[topic_id] = label
logger.info("Renamed topic %s to: %s", topic_id, label)
except BadRequest as e:
if "not modified" not in str(e).lower():
logger.warning("Failed to rename topic %s: %s", topic_id, e)
_applied_labels[topic_id] = label # don't retry
except Exception as e:
logger.warning("Error reading topic-map.yml: %s", e)
async def handle_start(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle /start command."""
config = _get_config(context)
if not _is_owner(update, config):
return
await update.effective_message.reply_text(
"Ready. Send me a message or use /newtopic to create a topic."
)
async def handle_new_topic(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle /newtopic <name> — create a forum topic."""
config = _get_config(context)
if not _is_owner(update, config):
return
name = " ".join(context.args) if context.args else None
if not name:
await update.effective_message.reply_text("Usage: /newtopic Topic Name")
return
try:
topic = await context.bot.create_forum_topic(
chat_id=update.effective_chat.id,
name=name,
)
tid = str(topic.message_thread_id)
_topic_dir(config, tid)
await context.bot.send_message(
chat_id=update.effective_chat.id,
message_thread_id=topic.message_thread_id,
text=f"Topic created. Send me anything here.",
)
logger.info("Created topic: %s (id=%s)", name, tid)
except BadRequest as e:
logger.error("Failed to create topic: %s", e)
await update.effective_message.reply_text(f"Failed to create topic: {e}")
async def handle_message(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle text messages — send to Claude CLI."""
config = _get_config(context)
if not _is_owner(update, config):
return
tid = _topic_id(update)
user_text = update.effective_message.text
# If Claude is waiting for an answer in this topic, deliver it
if tid in _pending_questions:
future = _pending_questions.pop(tid)
if not future.done():
future.set_result(user_text)
return
# Send typing indicator and placeholder
await context.bot.send_chat_action(
chat_id=update.effective_chat.id,
action=ChatAction.TYPING,
message_thread_id=update.effective_message.message_thread_id,
)
placeholder = await update.effective_message.reply_text("thinking...")
# Streaming state
last_edit_time = 0.0
last_edit_len = 0
async def on_chunk(text_so_far: str):
nonlocal last_edit_time, last_edit_len
now = time.monotonic()
delta = len(text_so_far) - last_edit_len
if delta >= EDIT_MIN_DELTA and (now - last_edit_time) >= EDIT_INTERVAL:
try:
display = _truncate_for_telegram(text_so_far)
await placeholder.edit_text(display)
last_edit_time = now
last_edit_len = len(text_so_far)
except BadRequest:
pass # message not modified or too long
async def on_question(question: str) -> str:
"""Claude asks user a question — send it and wait for reply."""
await update.effective_message.reply_text(f"{question}")
loop = asyncio.get_event_loop()
future = loop.create_future()
_pending_questions[tid] = future
return await future
topic_dir = _topic_dir(config, tid)
try:
response = await claude_send(
config, tid, user_text, on_chunk=on_chunk, on_question=on_question,
)
display = _truncate_for_telegram(response)
await _edit_text_md(placeholder, display)
except RuntimeError as e:
logger.error("Claude error for topic %s: %s", tid, e)
await placeholder.edit_text(f"Error: {e}")
response = f"[error] {e}"
finally:
_pending_questions.pop(tid, None)
await _send_outbox(update, topic_dir)
_log_interaction(config, tid, user_text, response)
await _sync_topic_name(update, config, tid)
async def handle_photo(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle photo messages — save image, send path to Claude."""
config = _get_config(context)
if not _is_owner(update, config):
return
tid = _topic_id(update)
images_dir = _topic_dir(config, tid) / "images"
images_dir.mkdir(exist_ok=True)
# Download the largest photo
photo = update.effective_message.photo[-1]
file = await context.bot.get_file(photo.file_id)
ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
filename = f"{ts}_{photo.file_unique_id}.jpg"
filepath = images_dir / filename
await file.download_to_drive(str(filepath))
caption = update.effective_message.caption or ""
message = f"User sent an image: {filepath}"
if caption:
message += f"\nCaption: {caption}"
# Send typing and placeholder
placeholder = await update.effective_message.reply_text("looking at image...")
try:
response = await claude_send(config, tid, message)
display = _truncate_for_telegram(response)
await _edit_text_md(placeholder, display)
except RuntimeError as e:
logger.error("Claude error for photo in topic %s: %s", tid, e)
await placeholder.edit_text(f"Error: {e}")
response = f"[error] {e}"
_log_interaction(config, tid, f"[photo] {caption}", response)
await _sync_topic_name(update, config, tid)
async def handle_document(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle document messages — save file, send path to Claude."""
config = _get_config(context)
if not _is_owner(update, config):
return
tid = _topic_id(update)
docs_dir = _topic_dir(config, tid) / "documents"
docs_dir.mkdir(exist_ok=True)
doc = update.effective_message.document
file = await context.bot.get_file(doc.file_id)
# Use original filename if available, otherwise generate one
orig_name = doc.file_name or f"{doc.file_unique_id}"
ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
filename = f"{ts}_{orig_name}"
filepath = docs_dir / filename
await file.download_to_drive(str(filepath))
caption = update.effective_message.caption or ""
message = f"User sent a document: {filepath} (name: {orig_name}, size: {doc.file_size} bytes)"
if caption:
message += f"\nCaption: {caption}"
topic_dir = _topic_dir(config, tid)
placeholder = await update.effective_message.reply_text("reading document...")
try:
response = await claude_send(config, tid, message)
display = _truncate_for_telegram(response)
await _edit_text_md(placeholder, display)
except RuntimeError as e:
logger.error("Claude error for document in topic %s: %s", tid, e)
await placeholder.edit_text(f"Error: {e}")
response = f"[error] {e}"
await _send_outbox(update, topic_dir)
_log_interaction(config, tid, f"[document: {orig_name}] {caption}", response)
await _sync_topic_name(update, config, tid)
async def handle_voice(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle voice/audio messages — save file, send path to Claude."""
config = _get_config(context)
if not _is_owner(update, config):
return
tid = _topic_id(update)
voice_dir = _topic_dir(config, tid) / "voice"
voice_dir.mkdir(exist_ok=True)
# Download voice file
voice = update.effective_message.voice or update.effective_message.audio
file = await context.bot.get_file(voice.file_id)
ext = "ogg" if update.effective_message.voice else "mp3"
ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
filename = f"{ts}_{voice.file_unique_id}.{ext}"
filepath = voice_dir / filename
await file.download_to_drive(str(filepath))
topic_dir = _topic_dir(config, tid)
# Transcribe via Whisper if available, otherwise send file path
if config.whisper_url:
placeholder = await update.effective_message.reply_text("transcribing voice...")
try:
text = await transcribe(str(filepath), config.whisper_url)
message = f"[voice message transcription]: {text}"
logger.info("Transcribed voice in topic %s: %d chars", tid, len(text))
# Show transcription to user, then send to Claude
try:
await placeholder.edit_text(f"🎤 {text}")
except BadRequest:
pass
placeholder = await update.effective_message.reply_text("thinking...")
except RuntimeError as e:
logger.error("ASR failed for topic %s: %s", tid, e)
message = f"User sent a voice message: {filepath} (duration: {voice.duration}s)\n(transcription failed: {e})"
else:
message = f"User sent a voice message: {filepath} (duration: {voice.duration}s)"
placeholder = await update.effective_message.reply_text("processing voice...")
try:
response = await claude_send(config, tid, message)
display = _truncate_for_telegram(response)
await _edit_text_md(placeholder, display)
except RuntimeError as e:
logger.error("Claude error for voice in topic %s: %s", tid, e)
await placeholder.edit_text(f"Error: {e}")
response = f"[error] {e}"
await _send_outbox(update, topic_dir)
_log_interaction(config, tid, message, response)
await _sync_topic_name(update, config, tid)
async def _send_outbox(update: Update, topic_dir: Path) -> None:
"""Send files queued in outbox.jsonl by Claude via send-to-user tool."""
outbox = topic_dir / "outbox.jsonl"
if not outbox.exists():
return
entries = []
try:
with open(outbox) as f:
for line in f:
line = line.strip()
if line:
entries.append(json.loads(line))
# Clear outbox
outbox.unlink()
except Exception as e:
logger.error("Failed to read outbox: %s", e)
return
for entry in entries:
fpath = Path(entry.get("path", ""))
ftype = entry.get("type", "document")
caption = entry.get("caption", "") or fpath.name
if not fpath.is_file():
logger.warning("Outbox file not found: %s", fpath)
continue
try:
with open(fpath, "rb") as f:
if ftype == "image":
await update.effective_message.reply_photo(photo=f, caption=caption)
elif ftype == "video":
await update.effective_message.reply_video(video=f, caption=caption)
elif ftype == "audio":
await update.effective_message.reply_voice(voice=f, caption=caption)
else:
await update.effective_message.reply_document(document=f, caption=caption)
logger.info("Sent %s: %s", ftype, fpath.name)
except Exception as e:
logger.error("Failed to send %s %s: %s", ftype, fpath.name, e)
def _truncate_for_telegram(text: str, max_len: int = 4096) -> str:
"""Truncate text to Telegram message limit."""
if len(text) <= max_len:
return text
return text[: max_len - 20] + "\n\n[truncated]"