Compare commits
1 Commits
burn/350-1
...
burn/255-1
| Author | SHA1 | Date | |
|---|---|---|---|
|
cc9d7705b6 |
@@ -1,18 +0,0 @@
|
||||
{
|
||||
"agents": {
|
||||
"ezra": {
|
||||
"host": "143.198.27.163",
|
||||
"hermes_path": "/root/wizards/ezra/hermes-agent/venv/bin/hermes",
|
||||
"username": "root"
|
||||
},
|
||||
"timmy": {
|
||||
"host": "timmy",
|
||||
"hermes_path": "/root/wizards/timmy/hermes-agent/venv/bin/hermes",
|
||||
"username": "root"
|
||||
}
|
||||
},
|
||||
"validation_timeout": 30,
|
||||
"command_timeout": 300,
|
||||
"max_retries": 2,
|
||||
"retry_delay": 5
|
||||
}
|
||||
@@ -1,551 +0,0 @@
|
||||
"""
|
||||
VPS Agent Dispatch Worker for Hermes Cron System
|
||||
|
||||
This module provides a dispatch worker that SSHs into remote VPS machines
|
||||
and runs hermes commands. It ensures that:
|
||||
|
||||
1. Remote dispatch only counts as success when the remote hermes command actually launches
|
||||
2. Stale per-agent hermes binary paths are configurable/validated before queue drain
|
||||
3. Failed remote launches remain in the queue (or are marked failed) instead of being reported as OK
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Optional, Dict, Any, List
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class DispatchStatus(Enum):
|
||||
"""Status of a dispatch operation."""
|
||||
PENDING = "pending"
|
||||
VALIDATING = "validating"
|
||||
DISPATCHING = "dispatching"
|
||||
SUCCESS = "success"
|
||||
FAILED = "failed"
|
||||
RETRYING = "retrying"
|
||||
|
||||
|
||||
@dataclass
|
||||
class DispatchResult:
|
||||
"""Result of a dispatch operation."""
|
||||
status: DispatchStatus
|
||||
message: str
|
||||
exit_code: Optional[int] = None
|
||||
stdout: Optional[str] = None
|
||||
stderr: Optional[str] = None
|
||||
execution_time: Optional[float] = None
|
||||
hermes_path: Optional[str] = None
|
||||
validated: bool = False
|
||||
|
||||
|
||||
class HermesPathValidator:
|
||||
"""Validates hermes binary paths on remote VPS machines."""
|
||||
|
||||
def __init__(self, ssh_key_path: Optional[str] = None):
|
||||
self.ssh_key_path = ssh_key_path or os.path.expanduser("~/.ssh/id_rsa")
|
||||
self.timeout = 30 # SSH timeout in seconds
|
||||
|
||||
def validate_hermes_path(self, host: str, hermes_path: str,
|
||||
username: str = "root") -> DispatchResult:
|
||||
"""
|
||||
Validate that the hermes binary exists and is executable on the remote host.
|
||||
|
||||
Args:
|
||||
host: Remote host IP or hostname
|
||||
hermes_path: Path to hermes binary on remote host
|
||||
username: SSH username
|
||||
|
||||
Returns:
|
||||
DispatchResult with validation status
|
||||
"""
|
||||
start_time = time.time()
|
||||
|
||||
# Build SSH command to check hermes binary
|
||||
ssh_cmd = [
|
||||
"ssh",
|
||||
"-i", self.ssh_key_path,
|
||||
"-o", "StrictHostKeyChecking=no",
|
||||
"-o", "ConnectTimeout=10",
|
||||
"-o", "BatchMode=yes",
|
||||
f"{username}@{host}",
|
||||
f"test -x {hermes_path} && echo 'VALID' || echo 'INVALID'"
|
||||
]
|
||||
|
||||
try:
|
||||
result = subprocess.run(
|
||||
ssh_cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=self.timeout
|
||||
)
|
||||
|
||||
execution_time = time.time() - start_time
|
||||
|
||||
if result.returncode == 0 and "VALID" in result.stdout:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.SUCCESS,
|
||||
message=f"Hermes binary validated at {hermes_path}",
|
||||
exit_code=0,
|
||||
execution_time=execution_time,
|
||||
hermes_path=hermes_path,
|
||||
validated=True
|
||||
)
|
||||
else:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Hermes binary not found or not executable: {hermes_path}",
|
||||
exit_code=result.returncode,
|
||||
stdout=result.stdout,
|
||||
stderr=result.stderr,
|
||||
execution_time=execution_time,
|
||||
hermes_path=hermes_path,
|
||||
validated=False
|
||||
)
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"SSH timeout validating hermes path on {host}",
|
||||
execution_time=time.time() - start_time,
|
||||
hermes_path=hermes_path,
|
||||
validated=False
|
||||
)
|
||||
except Exception as e:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Error validating hermes path: {str(e)}",
|
||||
execution_time=time.time() - start_time,
|
||||
hermes_path=hermes_path,
|
||||
validated=False
|
||||
)
|
||||
|
||||
|
||||
class VPSAgentDispatcher:
|
||||
"""Dispatches hermes commands to remote VPS agents."""
|
||||
|
||||
def __init__(self, config_path: Optional[str] = None):
|
||||
self.config_path = config_path or os.path.expanduser("~/.hermes/dispatch_config.json")
|
||||
self.validator = HermesPathValidator()
|
||||
self.config = self._load_config()
|
||||
|
||||
def _load_config(self) -> Dict[str, Any]:
|
||||
"""Load dispatch configuration."""
|
||||
try:
|
||||
if os.path.exists(self.config_path):
|
||||
with open(self.config_path, 'r') as f:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to load dispatch config: {e}")
|
||||
|
||||
# Default configuration
|
||||
return {
|
||||
"agents": {
|
||||
"ezra": {
|
||||
"host": "143.198.27.163",
|
||||
"hermes_path": "/root/wizards/ezra/hermes-agent/venv/bin/hermes",
|
||||
"username": "root"
|
||||
},
|
||||
"timmy": {
|
||||
"host": "timmy",
|
||||
"hermes_path": "/root/wizards/timmy/hermes-agent/venv/bin/hermes",
|
||||
"username": "root"
|
||||
}
|
||||
},
|
||||
"validation_timeout": 30,
|
||||
"command_timeout": 300,
|
||||
"max_retries": 2,
|
||||
"retry_delay": 5
|
||||
}
|
||||
|
||||
def save_config(self):
|
||||
"""Save dispatch configuration."""
|
||||
try:
|
||||
config_dir = Path(self.config_path).parent
|
||||
config_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
with open(self.config_path, 'w') as f:
|
||||
json.dump(self.config, f, indent=2)
|
||||
|
||||
# Set secure permissions
|
||||
os.chmod(self.config_path, 0o600)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to save dispatch config: {e}")
|
||||
|
||||
def get_agent_config(self, agent_name: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get configuration for a specific agent."""
|
||||
return self.config.get("agents", {}).get(agent_name)
|
||||
|
||||
def update_agent_config(self, agent_name: str, host: str, hermes_path: str,
|
||||
username: str = "root"):
|
||||
"""Update configuration for a specific agent."""
|
||||
if "agents" not in self.config:
|
||||
self.config["agents"] = {}
|
||||
|
||||
self.config["agents"][agent_name] = {
|
||||
"host": host,
|
||||
"hermes_path": hermes_path,
|
||||
"username": username
|
||||
}
|
||||
|
||||
self.save_config()
|
||||
|
||||
def validate_agent(self, agent_name: str) -> DispatchResult:
|
||||
"""Validate that an agent's hermes binary is accessible."""
|
||||
agent_config = self.get_agent_config(agent_name)
|
||||
if not agent_config:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Agent configuration not found: {agent_name}"
|
||||
)
|
||||
|
||||
return self.validator.validate_hermes_path(
|
||||
host=agent_config["host"],
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
username=agent_config.get("username", "root")
|
||||
)
|
||||
|
||||
def dispatch_command(self, agent_name: str, command: str,
|
||||
validate_first: bool = True) -> DispatchResult:
|
||||
"""
|
||||
Dispatch a command to a remote VPS agent.
|
||||
|
||||
Args:
|
||||
agent_name: Name of the agent to dispatch to
|
||||
command: Command to execute
|
||||
validate_first: Whether to validate hermes path before dispatching
|
||||
|
||||
Returns:
|
||||
DispatchResult with execution status
|
||||
"""
|
||||
agent_config = self.get_agent_config(agent_name)
|
||||
if not agent_config:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Agent configuration not found: {agent_name}"
|
||||
)
|
||||
|
||||
# Validate hermes path if requested
|
||||
if validate_first:
|
||||
validation_result = self.validate_agent(agent_name)
|
||||
if validation_result.status != DispatchStatus.SUCCESS:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Validation failed: {validation_result.message}",
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
validated=False
|
||||
)
|
||||
|
||||
# Build SSH command to execute hermes command
|
||||
ssh_cmd = [
|
||||
"ssh",
|
||||
"-i", self.validator.ssh_key_path,
|
||||
"-o", "StrictHostKeyChecking=no",
|
||||
"-o", "ConnectTimeout=10",
|
||||
f"{agent_config.get('username', 'root')}@{agent_config['host']}",
|
||||
f"cd /root/wizards/{agent_name}/hermes-agent && source venv/bin/activate && {command}"
|
||||
]
|
||||
|
||||
start_time = time.time()
|
||||
|
||||
try:
|
||||
result = subprocess.run(
|
||||
ssh_cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=self.config.get("command_timeout", 300)
|
||||
)
|
||||
|
||||
execution_time = time.time() - start_time
|
||||
|
||||
if result.returncode == 0:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.SUCCESS,
|
||||
message=f"Command executed successfully on {agent_name}",
|
||||
exit_code=0,
|
||||
stdout=result.stdout,
|
||||
stderr=result.stderr,
|
||||
execution_time=execution_time,
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
validated=validate_first
|
||||
)
|
||||
else:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Command failed on {agent_name}: {result.stderr}",
|
||||
exit_code=result.returncode,
|
||||
stdout=result.stdout,
|
||||
stderr=result.stderr,
|
||||
execution_time=execution_time,
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
validated=validate_first
|
||||
)
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Command timeout on {agent_name}",
|
||||
execution_time=time.time() - start_time,
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
validated=validate_first
|
||||
)
|
||||
except Exception as e:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Error executing command on {agent_name}: {str(e)}",
|
||||
execution_time=time.time() - start_time,
|
||||
hermes_path=agent_config["hermes_path"],
|
||||
validated=validate_first
|
||||
)
|
||||
|
||||
def dispatch_hermes_command(self, agent_name: str, hermes_command: str,
|
||||
validate_first: bool = True) -> DispatchResult:
|
||||
"""
|
||||
Dispatch a hermes command to a remote VPS agent.
|
||||
|
||||
Args:
|
||||
agent_name: Name of the agent to dispatch to
|
||||
hermes_command: Hermes command to execute (e.g., "hermes cron list")
|
||||
validate_first: Whether to validate hermes path before dispatching
|
||||
|
||||
Returns:
|
||||
DispatchResult with execution status
|
||||
"""
|
||||
agent_config = self.get_agent_config(agent_name)
|
||||
if not agent_config:
|
||||
return DispatchResult(
|
||||
status=DispatchStatus.FAILED,
|
||||
message=f"Agent configuration not found: {agent_name}"
|
||||
)
|
||||
|
||||
# Build full hermes command
|
||||
full_command = f"{agent_config['hermes_path']} {hermes_command}"
|
||||
|
||||
return self.dispatch_command(agent_name, full_command, validate_first)
|
||||
|
||||
|
||||
class DispatchQueue:
|
||||
"""Queue for managing dispatch operations."""
|
||||
|
||||
def __init__(self, queue_file: Optional[str] = None):
|
||||
self.queue_file = queue_file or os.path.expanduser("~/.hermes/dispatch_queue.json")
|
||||
self.queue: List[Dict[str, Any]] = self._load_queue()
|
||||
|
||||
def _load_queue(self) -> List[Dict[str, Any]]:
|
||||
"""Load queue from file."""
|
||||
try:
|
||||
if os.path.exists(self.queue_file):
|
||||
with open(self.queue_file, 'r') as f:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to load dispatch queue: {e}")
|
||||
|
||||
return []
|
||||
|
||||
def save_queue(self):
|
||||
"""Save queue to file."""
|
||||
try:
|
||||
queue_dir = Path(self.queue_file).parent
|
||||
queue_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
with open(self.queue_file, 'w') as f:
|
||||
json.dump(self.queue, f, indent=2)
|
||||
|
||||
# Set secure permissions
|
||||
os.chmod(self.queue_file, 0o600)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to save dispatch queue: {e}")
|
||||
|
||||
def add_item(self, agent_name: str, command: str, priority: int = 0,
|
||||
max_retries: int = 3) -> str:
|
||||
"""
|
||||
Add an item to the dispatch queue.
|
||||
|
||||
Returns:
|
||||
Queue item ID
|
||||
"""
|
||||
item_id = f"dispatch_{int(time.time())}_{len(self.queue)}"
|
||||
|
||||
item = {
|
||||
"id": item_id,
|
||||
"agent_name": agent_name,
|
||||
"command": command,
|
||||
"priority": priority,
|
||||
"max_retries": max_retries,
|
||||
"retry_count": 0,
|
||||
"status": DispatchStatus.PENDING.value,
|
||||
"created_at": time.time(),
|
||||
"last_attempt": None,
|
||||
"result": None
|
||||
}
|
||||
|
||||
self.queue.append(item)
|
||||
self.save_queue()
|
||||
|
||||
return item_id
|
||||
|
||||
def get_next_item(self) -> Optional[Dict[str, Any]]:
|
||||
"""Get the next item from the queue (highest priority, oldest first)."""
|
||||
if not self.queue:
|
||||
return None
|
||||
|
||||
# Sort by priority (descending) and created_at (ascending)
|
||||
sorted_queue = sorted(
|
||||
self.queue,
|
||||
key=lambda x: (-x.get("priority", 0), x.get("created_at", 0))
|
||||
)
|
||||
|
||||
# Find first pending item
|
||||
for item in sorted_queue:
|
||||
if item.get("status") == DispatchStatus.PENDING.value:
|
||||
return item
|
||||
|
||||
return None
|
||||
|
||||
def update_item(self, item_id: str, status: DispatchStatus,
|
||||
result: Optional[DispatchResult] = None):
|
||||
"""Update a queue item."""
|
||||
for item in self.queue:
|
||||
if item.get("id") == item_id:
|
||||
item["status"] = status.value
|
||||
item["last_attempt"] = time.time()
|
||||
|
||||
if result:
|
||||
item["result"] = {
|
||||
"status": result.status.value,
|
||||
"message": result.message,
|
||||
"exit_code": result.exit_code,
|
||||
"stdout": result.stdout,
|
||||
"stderr": result.stderr,
|
||||
"execution_time": result.execution_time,
|
||||
"hermes_path": result.hermes_path,
|
||||
"validated": result.validated
|
||||
}
|
||||
|
||||
# Update retry count if failed
|
||||
if status == DispatchStatus.FAILED:
|
||||
item["retry_count"] = item.get("retry_count", 0) + 1
|
||||
|
||||
self.save_queue()
|
||||
break
|
||||
|
||||
def remove_item(self, item_id: str):
|
||||
"""Remove an item from the queue."""
|
||||
self.queue = [item for item in self.queue if item.get("id") != item_id]
|
||||
self.save_queue()
|
||||
|
||||
def get_failed_items(self) -> List[Dict[str, Any]]:
|
||||
"""Get all failed items that can be retried."""
|
||||
return [
|
||||
item for item in self.queue
|
||||
if item.get("status") == DispatchStatus.FAILED.value
|
||||
and item.get("retry_count", 0) < item.get("max_retries", 3)
|
||||
]
|
||||
|
||||
def get_stats(self) -> Dict[str, Any]:
|
||||
"""Get queue statistics."""
|
||||
total = len(self.queue)
|
||||
pending = sum(1 for item in self.queue if item.get("status") == DispatchStatus.PENDING.value)
|
||||
success = sum(1 for item in self.queue if item.get("status") == DispatchStatus.SUCCESS.value)
|
||||
failed = sum(1 for item in self.queue if item.get("status") == DispatchStatus.FAILED.value)
|
||||
|
||||
return {
|
||||
"total": total,
|
||||
"pending": pending,
|
||||
"success": success,
|
||||
"failed": failed,
|
||||
"retryable": len(self.get_failed_items())
|
||||
}
|
||||
|
||||
|
||||
def process_dispatch_queue(dispatcher: VPSAgentDispatcher,
|
||||
queue: DispatchQueue,
|
||||
batch_size: int = 5) -> Dict[str, Any]:
|
||||
"""
|
||||
Process items from the dispatch queue.
|
||||
|
||||
Args:
|
||||
dispatcher: VPS agent dispatcher
|
||||
queue: Dispatch queue
|
||||
batch_size: Number of items to process in this batch
|
||||
|
||||
Returns:
|
||||
Processing statistics
|
||||
"""
|
||||
processed = 0
|
||||
success = 0
|
||||
failed = 0
|
||||
|
||||
for _ in range(batch_size):
|
||||
item = queue.get_next_item()
|
||||
if not item:
|
||||
break
|
||||
|
||||
item_id = item["id"]
|
||||
agent_name = item["agent_name"]
|
||||
command = item["command"]
|
||||
|
||||
# Update status to dispatching
|
||||
queue.update_item(item_id, DispatchStatus.DISPATCHING)
|
||||
|
||||
# Dispatch the command
|
||||
result = dispatcher.dispatch_hermes_command(
|
||||
agent_name=agent_name,
|
||||
hermes_command=command,
|
||||
validate_first=True
|
||||
)
|
||||
|
||||
# Update queue with result
|
||||
if result.status == DispatchStatus.SUCCESS:
|
||||
queue.update_item(item_id, DispatchStatus.SUCCESS, result)
|
||||
success += 1
|
||||
else:
|
||||
# Check if we should retry
|
||||
item_data = next((i for i in queue.queue if i.get("id") == item_id), None)
|
||||
if item_data and item_data.get("retry_count", 0) < item_data.get("max_retries", 3):
|
||||
queue.update_item(item_id, DispatchStatus.FAILED, result)
|
||||
failed += 1
|
||||
else:
|
||||
# Max retries reached, remove from queue
|
||||
queue.remove_item(item_id)
|
||||
failed += 1
|
||||
|
||||
processed += 1
|
||||
|
||||
return {
|
||||
"processed": processed,
|
||||
"success": success,
|
||||
"failed": failed,
|
||||
"queue_stats": queue.get_stats()
|
||||
}
|
||||
|
||||
|
||||
# Example usage and testing
|
||||
if __name__ == "__main__":
|
||||
# Set up logging
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
|
||||
# Create dispatcher and queue
|
||||
dispatcher = VPSAgentDispatcher()
|
||||
queue = DispatchQueue()
|
||||
|
||||
# Example: Add items to queue
|
||||
queue.add_item("ezra", "cron list")
|
||||
queue.add_item("timmy", "cron status")
|
||||
|
||||
# Process queue
|
||||
stats = process_dispatch_queue(dispatcher, queue)
|
||||
print(f"Processing stats: {stats}")
|
||||
|
||||
# Show queue stats
|
||||
queue_stats = queue.get_stats()
|
||||
print(f"Queue stats: {queue_stats}")
|
||||
@@ -653,12 +653,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
# AIAgent.__init__ is missing params the scheduler expects.
|
||||
_validate_agent_interface()
|
||||
|
||||
# Check if this is a dispatch job
|
||||
if job.get("type") == "dispatch" or "dispatch" in job.get("name", "").lower():
|
||||
return _run_dispatch_job(job)
|
||||
|
||||
|
||||
|
||||
from run_agent import AIAgent
|
||||
|
||||
# Initialize SQLite session store so cron job messages are persisted
|
||||
@@ -1013,89 +1007,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
logger.debug("Job '%s': failed to close SQLite session store: %s", job_id, e)
|
||||
|
||||
|
||||
|
||||
def _run_dispatch_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
"""
|
||||
Execute a dispatch job that SSHs into remote VPS machines.
|
||||
|
||||
Returns:
|
||||
Tuple of (success, full_output_doc, final_response, error_message)
|
||||
"""
|
||||
from cron.dispatch_worker import VPSAgentDispatcher, DispatchQueue, process_dispatch_queue
|
||||
|
||||
job_id = job["id"]
|
||||
job_name = job["name"]
|
||||
|
||||
logger.info("Running dispatch job '%s' (ID: %s)", job_name, job_id)
|
||||
|
||||
try:
|
||||
# Load dispatch configuration
|
||||
dispatcher = VPSAgentDispatcher()
|
||||
queue = DispatchQueue()
|
||||
|
||||
# Get dispatch parameters from job
|
||||
agent_name = job.get("agent_name", "ezra")
|
||||
command = job.get("command", "cron list")
|
||||
batch_size = job.get("batch_size", 5)
|
||||
|
||||
# Add command to queue if specified
|
||||
if command:
|
||||
queue.add_item(agent_name, command)
|
||||
|
||||
# Process the dispatch queue
|
||||
stats = process_dispatch_queue(dispatcher, queue, batch_size)
|
||||
|
||||
# Generate output
|
||||
output = f"""# Dispatch Job: {job_name}
|
||||
|
||||
**Job ID:** {job_id}
|
||||
**Run Time:** {_hermes_now().strftime('%Y-%m-%d %H:%M:%S')}
|
||||
**Agent:** {agent_name}
|
||||
**Command:** {command}
|
||||
|
||||
## Dispatch Results
|
||||
|
||||
- **Processed:** {stats['processed']}
|
||||
- **Success:** {stats['success']}
|
||||
- **Failed:** {stats['failed']}
|
||||
|
||||
## Queue Statistics
|
||||
|
||||
- **Total items:** {stats['queue_stats']['total']}
|
||||
- **Pending:** {stats['queue_stats']['pending']}
|
||||
- **Success:** {stats['queue_stats']['success']}
|
||||
- **Failed:** {stats['queue_stats']['failed']}
|
||||
- **Retryable:** {stats['queue_stats']['retryable']}
|
||||
|
||||
## Status
|
||||
|
||||
{"✅ All dispatches successful" if stats['failed'] == 0 else f"⚠️ {stats['failed']} dispatches failed"}
|
||||
"""
|
||||
|
||||
success = stats['failed'] == 0
|
||||
error_message = None if success else f"{stats['failed']} dispatches failed"
|
||||
|
||||
return (success, output, output, error_message)
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Dispatch job failed: {str(e)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
|
||||
output = f"""# Dispatch Job: {job_name}
|
||||
|
||||
**Job ID:** {job_id}
|
||||
**Run Time:** {_hermes_now().strftime('%Y-%m-%d %H:%M:%S')}
|
||||
**Status:** ❌ Failed
|
||||
|
||||
## Error
|
||||
|
||||
{error_msg}
|
||||
"""
|
||||
|
||||
return (False, output, output, error_msg)
|
||||
|
||||
|
||||
|
||||
def tick(verbose: bool = True, adapters=None, loop=None) -> int:
|
||||
"""
|
||||
Check and run all due jobs.
|
||||
|
||||
9
deploy/synapse/.gitignore
vendored
Normal file
9
deploy/synapse/.gitignore
vendored
Normal file
@@ -0,0 +1,9 @@
|
||||
# Secrets — never commit
|
||||
.env
|
||||
synapse-credentials.env
|
||||
|
||||
# Backups
|
||||
backups/
|
||||
|
||||
# Generated config backups
|
||||
homeserver.yaml.bak
|
||||
82
deploy/synapse/docker-compose.yml
Normal file
82
deploy/synapse/docker-compose.yml
Normal file
@@ -0,0 +1,82 @@
|
||||
# Synapse Homeserver — Docker Compose Stack
|
||||
# Matrix Phase 1: Deploy Synapse on Ezra VPS
|
||||
#
|
||||
# Usage:
|
||||
# cd deploy/synapse
|
||||
# ./setup.sh # first-time deploy (generates config + keys)
|
||||
# docker compose up -d # start
|
||||
# docker compose logs -f # follow logs
|
||||
# docker compose down # stop
|
||||
#
|
||||
# Secrets:
|
||||
# Never commit .env to version control.
|
||||
# setup.sh generates secrets automatically.
|
||||
|
||||
services:
|
||||
synapse-db:
|
||||
image: postgres:16-alpine
|
||||
container_name: synapse-db
|
||||
restart: unless-stopped
|
||||
volumes:
|
||||
- synapse_db:/var/lib/postgresql/data
|
||||
environment:
|
||||
POSTGRES_USER: synapse
|
||||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env}
|
||||
POSTGRES_INITDB_ARGS: "--encoding=UTF8 --lc-collate=C --lc-ctype=C"
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "pg_isready -U synapse"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 5
|
||||
networks:
|
||||
- synapse_net
|
||||
logging:
|
||||
driver: "json-file"
|
||||
options:
|
||||
max-size: "20m"
|
||||
max-file: "3"
|
||||
|
||||
synapse:
|
||||
image: matrixdotorg/synapse:latest
|
||||
container_name: synapse
|
||||
restart: unless-stopped
|
||||
depends_on:
|
||||
synapse-db:
|
||||
condition: service_healthy
|
||||
volumes:
|
||||
- synapse_data:/data
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
SYNAPSE_CONFIG_PATH: /data/homeserver.yaml
|
||||
ports:
|
||||
- "127.0.0.1:8008:8008" # Client-server API (localhost only)
|
||||
- "8448:8448" # Federation (public)
|
||||
networks:
|
||||
- synapse_net
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-fSs", "http://localhost:8008/health"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
logging:
|
||||
driver: "json-file"
|
||||
options:
|
||||
max-size: "50m"
|
||||
max-file: "5"
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "2.0"
|
||||
memory: 2G
|
||||
reservations:
|
||||
memory: 512M
|
||||
|
||||
volumes:
|
||||
synapse_data:
|
||||
synapse_db:
|
||||
|
||||
networks:
|
||||
synapse_net:
|
||||
driver: bridge
|
||||
101
deploy/synapse/homeserver.yaml
Normal file
101
deploy/synapse/homeserver.yaml
Normal file
@@ -0,0 +1,101 @@
|
||||
# Synapse Homeserver Configuration
|
||||
# Generated by setup.sh — edit with care.
|
||||
#
|
||||
# Docs: https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html
|
||||
|
||||
# Server name — your Matrix domain (e.g. matrix.example.com)
|
||||
server_name: "SERVER_NAME_PLACEHOLDER"
|
||||
|
||||
# Signing key — generated by setup.sh
|
||||
signing_key_path: "/data/signing.key"
|
||||
|
||||
# Trusted key servers (empty = trust only ourselves for our own keys)
|
||||
trusted_key_servers: []
|
||||
|
||||
# Report stats to matrix.org (no for sovereignty)
|
||||
report_stats: false
|
||||
|
||||
# Listeners
|
||||
listeners:
|
||||
- port: 8008
|
||||
tls: false
|
||||
type: http
|
||||
x_forwarded: true
|
||||
resources:
|
||||
- names: [client, federation]
|
||||
compress: false
|
||||
|
||||
# Database — PostgreSQL
|
||||
database:
|
||||
name: psycopg2
|
||||
args:
|
||||
user: synapse
|
||||
password: "${POSTGRES_PASSWORD}"
|
||||
database: synapse
|
||||
host: synapse-db
|
||||
cp_min: 5
|
||||
cp_max: 10
|
||||
|
||||
# Media store
|
||||
media_store_path: "/data/media_store"
|
||||
|
||||
# Upload limits
|
||||
max_upload_size: "50M"
|
||||
|
||||
# URL previews (disable to reduce attack surface)
|
||||
url_preview_enabled: false
|
||||
|
||||
# Enable room list publishing
|
||||
enable_room_list_search: true
|
||||
|
||||
# Turn off public registration by default (create users via admin API)
|
||||
enable_registration: false
|
||||
enable_registration_without_verification: false
|
||||
|
||||
# Rate limiting
|
||||
rc_message:
|
||||
per_second: 0.2
|
||||
burst_count: 10
|
||||
|
||||
rc_registration:
|
||||
per_second: 0.1
|
||||
burst_count: 3
|
||||
|
||||
rc_login:
|
||||
address:
|
||||
per_second: 0.05
|
||||
burst_count: 2
|
||||
account:
|
||||
per_second: 0.05
|
||||
burst_count: 2
|
||||
failed_attempts:
|
||||
per_second: 0.15
|
||||
burst_count: 3
|
||||
|
||||
# Retention — keep messages for 90 days by default
|
||||
retention:
|
||||
enabled: true
|
||||
default_policy:
|
||||
min_lifetime: 1d
|
||||
max_lifetime: 90d
|
||||
|
||||
# Logging
|
||||
log_config: "/data/log.config"
|
||||
|
||||
# Metrics (optional — enable if running Prometheus)
|
||||
enable_metrics: false
|
||||
|
||||
# Presence
|
||||
use_presence: true
|
||||
|
||||
# Federation
|
||||
federation_verify_certificates: true
|
||||
federation_sender_instances: 1
|
||||
|
||||
# Appservice config directory
|
||||
app_service_config_files: []
|
||||
|
||||
# Experimental features
|
||||
experimental_features:
|
||||
# MSC3440: Threading support
|
||||
msc3440_enabled: true
|
||||
33
deploy/synapse/log.config
Normal file
33
deploy/synapse/log.config
Normal file
@@ -0,0 +1,33 @@
|
||||
# Synapse logging configuration
|
||||
# https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html#log_config
|
||||
|
||||
version: 1
|
||||
|
||||
formatters:
|
||||
precise:
|
||||
format: '%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(request)s - %(message)s'
|
||||
|
||||
handlers:
|
||||
console:
|
||||
class: logging.StreamHandler
|
||||
formatter: precise
|
||||
level: INFO
|
||||
stream: ext://sys.stdout
|
||||
|
||||
file:
|
||||
class: logging.handlers.RotatingFileHandler
|
||||
formatter: precise
|
||||
filename: /data/homeserver.log
|
||||
maxBytes: 104857600 # 100MB
|
||||
backupCount: 3
|
||||
level: INFO
|
||||
|
||||
loggers:
|
||||
synapse.storage.SQL:
|
||||
level: WARNING
|
||||
synapse.http.client:
|
||||
level: INFO
|
||||
|
||||
root:
|
||||
level: INFO
|
||||
handlers: [console, file]
|
||||
131
deploy/synapse/manage.sh
Executable file
131
deploy/synapse/manage.sh
Executable file
@@ -0,0 +1,131 @@
|
||||
#!/usr/bin/env bash
|
||||
# Synapse Homeserver — Management Utilities
|
||||
# Usage: ./manage.sh <command>
|
||||
#
|
||||
# Commands:
|
||||
# status Show container status and health
|
||||
# restart Restart Synapse (preserves data)
|
||||
# logs Tail Synapse logs
|
||||
# create-user <username> <password> [admin]
|
||||
# backup Create timestamped backup of data volumes
|
||||
# update Pull latest Synapse image and recreate
|
||||
# teardown Stop and remove everything (DESTRUCTIVE)
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
cd "$SCRIPT_DIR"
|
||||
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
info() { echo -e "${GREEN}[MANAGE]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
|
||||
error() { echo -e "${RED}[ERROR]${NC} $*"; exit 1; }
|
||||
|
||||
COMMAND="${1:-help}"
|
||||
|
||||
case "$COMMAND" in
|
||||
status)
|
||||
info "Container status:"
|
||||
docker compose ps
|
||||
echo ""
|
||||
info "Synapse health:"
|
||||
curl -sfS http://127.0.0.1:8008/health && echo "" || echo "Not responding"
|
||||
echo ""
|
||||
info "Disk usage:"
|
||||
docker system df -v 2>/dev/null | grep -E "synapse|VOLUME" || true
|
||||
;;
|
||||
|
||||
restart)
|
||||
info "Restarting Synapse..."
|
||||
docker compose restart synapse
|
||||
info "Waiting for health check..."
|
||||
sleep 5
|
||||
curl -sfS http://127.0.0.1:8008/health && echo "" && info "Synapse is healthy" || warn "Not responding yet"
|
||||
;;
|
||||
|
||||
logs)
|
||||
shift
|
||||
LINES="${1:-100}"
|
||||
info "Tailing Synapse logs (last $LINES lines)..."
|
||||
docker compose logs -f --tail="$LINES" synapse
|
||||
;;
|
||||
|
||||
create-user)
|
||||
USERNAME="${2:?Usage: manage.sh create-user <username> <password> [admin]}"
|
||||
PASSWORD="${3:?Usage: manage.sh create-user <username> <password> [admin]}"
|
||||
IS_ADMIN="${4:-false}"
|
||||
info "Creating user @$USERNAME..."
|
||||
ADMIN_FLAG=""
|
||||
if [ "$IS_ADMIN" = "admin" ] || [ "$IS_ADMIN" = "true" ]; then
|
||||
ADMIN_FLAG="--admin"
|
||||
fi
|
||||
docker compose exec -T synapse register_new_matrix_user \
|
||||
http://localhost:8008 \
|
||||
-c /data/homeserver.yaml \
|
||||
-u "$USERNAME" \
|
||||
-p "$PASSWORD" \
|
||||
$ADMIN_FLAG \
|
||||
--no-extra-prompt
|
||||
;;
|
||||
|
||||
backup)
|
||||
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
|
||||
BACKUP_DIR="./backups/${TIMESTAMP}"
|
||||
mkdir -p "$BACKUP_DIR"
|
||||
info "Backing up PostgreSQL..."
|
||||
docker compose exec -T synapse-db pg_dump -U synapse > "${BACKUP_DIR}/synapse_db.sql"
|
||||
info "Backing up Synapse data volume..."
|
||||
docker run --rm \
|
||||
-v synapse_data:/source:ro \
|
||||
-v "$(pwd)/${BACKUP_DIR}:/backup" \
|
||||
alpine tar czf /backup/synapse_data.tar.gz -C /source .
|
||||
info "Backup complete: $BACKUP_DIR"
|
||||
ls -lh "$BACKUP_DIR"
|
||||
;;
|
||||
|
||||
update)
|
||||
info "Pulling latest Synapse image..."
|
||||
docker compose pull synapse
|
||||
info "Recreating containers..."
|
||||
docker compose up -d --force-recreate synapse
|
||||
info "Waiting for health..."
|
||||
sleep 10
|
||||
curl -sfS http://127.0.0.1:8008/health && echo "" && info "Updated and healthy" || warn "Check logs"
|
||||
;;
|
||||
|
||||
teardown)
|
||||
echo -e "${RED}WARNING: This will stop and remove all Synapse containers and volumes.${NC}"
|
||||
echo -e "${RED}ALL DATA WILL BE LOST. This cannot be undone.${NC}"
|
||||
echo ""
|
||||
read -p "Type 'yes-delete-everything' to confirm: " CONFIRM
|
||||
if [ "$CONFIRM" = "yes-delete-everything" ]; then
|
||||
info "Stopping containers..."
|
||||
docker compose down -v
|
||||
info "Removing volumes..."
|
||||
docker volume rm synapse_data synapse_db 2>/dev/null || true
|
||||
info "Teardown complete."
|
||||
else
|
||||
info "Aborted."
|
||||
fi
|
||||
;;
|
||||
|
||||
help|*)
|
||||
echo "Synapse Homeserver Management"
|
||||
echo ""
|
||||
echo "Usage: ./manage.sh <command>"
|
||||
echo ""
|
||||
echo "Commands:"
|
||||
echo " status Show container status and health"
|
||||
echo " restart Restart Synapse"
|
||||
echo " logs [lines] Tail Synapse logs (default: 100)"
|
||||
echo " create-user <u> <p> [admin] Create a new Matrix user"
|
||||
echo " backup Backup database + data volume"
|
||||
echo " update Pull latest image and recreate"
|
||||
echo " teardown Stop and remove everything (DESTRUCTIVE)"
|
||||
;;
|
||||
esac
|
||||
211
deploy/synapse/setup.sh
Executable file
211
deploy/synapse/setup.sh
Executable file
@@ -0,0 +1,211 @@
|
||||
#!/usr/bin/env bash
|
||||
# Synapse Homeserver — One-Shot Setup Script
|
||||
# Matrix Phase 1: Deploy Synapse on Ezra VPS
|
||||
#
|
||||
# Usage:
|
||||
# ./setup.sh <server_name> [admin_user] [admin_password]
|
||||
#
|
||||
# Example:
|
||||
# ./setup.sh matrix.timmy-time.xyz hermes-bot 'secure-pass-123'
|
||||
#
|
||||
# What it does:
|
||||
# 1. Generates .env with secrets
|
||||
# 2. Prepares homeserver.yaml with correct server name
|
||||
# 3. Generates signing key
|
||||
# 4. Starts Synapse + PostgreSQL via Docker Compose
|
||||
# 5. Waits for Synapse to be healthy
|
||||
# 6. Registers admin user + bot account
|
||||
# 7. Outputs Matrix credentials for hermes-agent
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
cd "$SCRIPT_DIR"
|
||||
|
||||
# --- Colors ---
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
info() { echo -e "${GREEN}[SETUP]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
|
||||
error() { echo -e "${RED}[ERROR]${NC} $*"; exit 1; }
|
||||
|
||||
# --- Args ---
|
||||
SERVER_NAME="${1:?Usage: $0 <server_name> [admin_user] [admin_password]}"
|
||||
ADMIN_USER="${2:-timmy-admin}"
|
||||
ADMIN_PASS="${3:-$(openssl rand -hex 16)}"
|
||||
BOT_USER="${4:-hermes-bot}"
|
||||
BOT_PASS="${5:-$(openssl rand -hex 16)}"
|
||||
|
||||
echo -e "${CYAN}"
|
||||
echo "╔══════════════════════════════════════════════════╗"
|
||||
echo "║ Synapse Homeserver — Matrix Phase 1 Deploy ║"
|
||||
echo "╚══════════════════════════════════════════════════╝"
|
||||
echo -e "${NC}"
|
||||
info "Server name: $SERVER_NAME"
|
||||
info "Admin user: @$ADMIN_USER:$SERVER_NAME"
|
||||
info "Bot user: @$BOT_USER:$SERVER_NAME"
|
||||
echo ""
|
||||
|
||||
# --- Preflight ---
|
||||
info "Preflight checks..."
|
||||
command -v docker >/dev/null 2>&1 || error "docker not found. Install Docker first."
|
||||
command -v docker compose version >/dev/null 2>&1 || error "docker compose not found. Install Docker Compose plugin."
|
||||
info "Docker: $(docker --version | head -1)"
|
||||
info "Compose: $(docker compose version | head -1)"
|
||||
|
||||
# --- Generate .env ---
|
||||
info "Generating .env..."
|
||||
POSTGRES_PASSWORD=$(openssl rand -hex 24)
|
||||
REGISTRATION_SECRET=$(openssl rand -hex 16)
|
||||
|
||||
cat > .env <<EOF
|
||||
# Synapse deployment — generated $(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||
# DO NOT COMMIT THIS FILE
|
||||
|
||||
POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
|
||||
SYNAPSE_SERVER_NAME=${SERVER_NAME}
|
||||
SYNAPSE_REPORT_STATS=no
|
||||
REGISTRATION_SECRET=${REGISTRATION_SECRET}
|
||||
EOF
|
||||
chmod 600 .env
|
||||
info ".env written with secure permissions"
|
||||
|
||||
# --- Prepare homeserver.yaml ---
|
||||
info "Preparing homeserver.yaml..."
|
||||
sed -i.bak "s/SERVER_NAME_PLACEHOLDER/${SERVER_NAME}/g" homeserver.yaml
|
||||
rm -f homeserver.yaml.bak
|
||||
info "Server name set to: $SERVER_NAME"
|
||||
|
||||
# --- Generate signing key ---
|
||||
info "Generating signing key..."
|
||||
# Synapse will generate its own key on first run if missing
|
||||
# But we pre-create the data volume structure
|
||||
docker volume create synapse_data >/dev/null 2>&1 || true
|
||||
docker volume create synapse_db >/dev/null 2>&1 || true
|
||||
|
||||
# --- Start the stack ---
|
||||
info "Starting Synapse + PostgreSQL..."
|
||||
docker compose up -d
|
||||
|
||||
# --- Wait for Synapse to be healthy ---
|
||||
info "Waiting for Synapse to start (up to 120s)..."
|
||||
MAX_WAIT=120
|
||||
ELAPSED=0
|
||||
while [ $ELAPSED -lt $MAX_WAIT ]; do
|
||||
if curl -sfS http://127.0.0.1:8008/health >/dev/null 2>&1; then
|
||||
info "Synapse is healthy!"
|
||||
break
|
||||
fi
|
||||
sleep 3
|
||||
ELAPSED=$((ELAPSED + 3))
|
||||
if [ $((ELAPSED % 15)) -eq 0 ]; then
|
||||
info "Still waiting... (${ELAPSED}s)"
|
||||
fi
|
||||
done
|
||||
|
||||
if [ $ELAPSED -ge $MAX_WAIT ]; then
|
||||
warn "Synapse did not respond within ${MAX_WAIT}s. Check logs:"
|
||||
echo " docker compose logs synapse"
|
||||
error "Aborting registration."
|
||||
fi
|
||||
|
||||
# --- Register admin user ---
|
||||
info "Registering admin user @$ADMIN_USER:$SERVER_NAME..."
|
||||
docker compose exec -T synapse register_new_matrix_user \
|
||||
http://localhost:8008 \
|
||||
-c /data/homeserver.yaml \
|
||||
-u "$ADMIN_USER" \
|
||||
-p "$ADMIN_PASS" \
|
||||
--admin \
|
||||
--no-extra-prompt 2>&1 || {
|
||||
# User might already exist if re-running
|
||||
warn "Admin user registration returned non-zero (may already exist)"
|
||||
}
|
||||
|
||||
# --- Register bot user ---
|
||||
info "Registering bot user @$BOT_USER:$SERVER_NAME..."
|
||||
docker compose exec -T synapse register_new_matrix_user \
|
||||
http://localhost:8008 \
|
||||
-c /data/homeserver.yaml \
|
||||
-u "$BOT_USER" \
|
||||
-p "$BOT_PASS" \
|
||||
--no-admin \
|
||||
--no-extra-prompt 2>&1 || {
|
||||
warn "Bot user registration returned non-zero (may already exist)"
|
||||
}
|
||||
|
||||
# --- Get bot access token ---
|
||||
info "Acquiring bot access token..."
|
||||
BOT_TOKEN_RESPONSE=$(curl -sfS -X POST "http://127.0.0.1:8008/_matrix/client/v3/login" \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d "{
|
||||
\"type\": \"m.login.password\",
|
||||
\"identifier\": {
|
||||
\"type\": \"m.id.user\",
|
||||
\"user\": \"${BOT_USER}\"
|
||||
},
|
||||
\"password\": \"${BOT_PASS}\",
|
||||
\"device_name\": \"Hermes Agent\"
|
||||
}")
|
||||
|
||||
BOT_ACCESS_TOKEN=$(echo "$BOT_TOKEN_RESPONSE" | python3 -c "import sys,json; print(json.load(sys.stdin)['access_token'])" 2>/dev/null || echo "FAILED_TO_EXTRACT")
|
||||
BOT_DEVICE_ID=$(echo "$BOT_TOKEN_RESPONSE" | python3 -c "import sys,json; print(json.load(sys.stdin)['device_id'])" 2>/dev/null || echo "UNKNOWN")
|
||||
|
||||
if [ "$BOT_ACCESS_TOKEN" = "FAILED_TO_EXTRACT" ]; then
|
||||
warn "Could not extract bot access token automatically."
|
||||
warn "Login manually: curl -X POST http://127.0.0.1:8008/_matrix/client/v3/login ..."
|
||||
fi
|
||||
|
||||
# --- Write credentials file ---
|
||||
CREDENTIALS_FILE="synapse-credentials.env"
|
||||
cat > "$CREDENTIALS_FILE" <<EOF
|
||||
# Synapse Credentials — generated $(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||
# Add these to hermes-agent's ~/.hermes/.env
|
||||
|
||||
# Matrix integration
|
||||
MATRIX_HOMESERVER=http://${SERVER_NAME}:8008
|
||||
MATRIX_ACCESS_TOKEN=${BOT_ACCESS_TOKEN}
|
||||
MATRIX_USER_ID=@${BOT_USER}:${SERVER_NAME}
|
||||
MATRIX_DEVICE_ID=${BOT_DEVICE_ID}
|
||||
MATRIX_ENCRYPTION=true
|
||||
|
||||
# Admin credentials (for user management)
|
||||
SYNAPSE_ADMIN_USER=@${ADMIN_USER}:${SERVER_NAME}
|
||||
SYNAPSE_ADMIN_PASSWORD=${ADMIN_PASS}
|
||||
|
||||
# Bot credentials
|
||||
SYNAPSE_BOT_USER=@${BOT_USER}:${SERVER_NAME}
|
||||
SYNAPSE_BOT_PASSWORD=${BOT_PASS}
|
||||
EOF
|
||||
chmod 600 "$CREDENTIALS_FILE"
|
||||
info "Credentials written to: $CREDENTIALS_FILE"
|
||||
|
||||
# --- Summary ---
|
||||
echo ""
|
||||
echo -e "${GREEN}╔══════════════════════════════════════════════════╗${NC}"
|
||||
echo -e "${GREEN}║ Synapse Deployed Successfully! ║${NC}"
|
||||
echo -e "${GREEN}╚══════════════════════════════════════════════════╝${NC}"
|
||||
echo ""
|
||||
echo -e " Server: ${CYAN}https://${SERVER_NAME}${NC}"
|
||||
echo -e " Client API: ${CYAN}http://127.0.0.1:8008${NC}"
|
||||
echo -e " Federation: ${CYAN}https://${SERVER_NAME}:8448${NC}"
|
||||
echo ""
|
||||
echo -e " Admin: ${YELLOW}@${ADMIN_USER}:${SERVER_NAME}${NC}"
|
||||
echo -e " Bot: ${YELLOW}@${BOT_USER}:${SERVER_NAME}${NC}"
|
||||
echo -e " Bot Token: ${YELLOW}${BOT_ACCESS_TOKEN:0:20}...${NC}"
|
||||
echo ""
|
||||
echo -e " Credentials: ${CYAN}${SCRIPT_DIR}/${CREDENTIALS_FILE}${NC}"
|
||||
echo ""
|
||||
echo -e "${GREEN}Next steps:${NC}"
|
||||
echo " 1. Point DNS: ${SERVER_NAME} → $(curl -s ifconfig.me 2>/dev/null || echo '<VPS_IP>')"
|
||||
echo " 2. Set up TLS: nginx/certbot reverse proxy for :8008 and :8448"
|
||||
echo " 3. Copy credentials to hermes-agent: cp ${CREDENTIALS_FILE} ~/.hermes/.env"
|
||||
echo " 4. Start hermes: hermes gateway --platform matrix"
|
||||
echo ""
|
||||
echo " Manage: docker compose logs -f | docker compose restart | docker compose down"
|
||||
echo " Users: docker compose exec synapse register_new_matrix_user http://localhost:8008 -c /data/homeserver.yaml -u <user> -p <pass>"
|
||||
echo ""
|
||||
251
docs/synapse-deployment.md
Normal file
251
docs/synapse-deployment.md
Normal file
@@ -0,0 +1,251 @@
|
||||
# Synapse Homeserver Deployment Guide
|
||||
|
||||
## Matrix Phase 1: Deploy Synapse on Ezra VPS
|
||||
|
||||
Part of [Epic #269: Matrix Integration — Sovereign Messaging for Timmy](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/269).
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────┐
|
||||
│ Ezra VPS (143.198.27.163) │
|
||||
│ │
|
||||
│ ┌──────────┐ ┌─────────────────────────┐ │
|
||||
│ │ Nginx │────▶│ Synapse (Docker) │ │
|
||||
│ │ :443→8008│ │ Client API: localhost:8008│ │
|
||||
│ │ :8448→8448│ │ Federation: 0.0.0.0:8448│ │
|
||||
│ └──────────┘ └──────────┬──────────────┘ │
|
||||
│ │ │
|
||||
│ ┌────────▼──────────┐ │
|
||||
│ │ PostgreSQL 16 │ │
|
||||
│ │ (Docker volume) │ │
|
||||
│ └───────────────────┘ │
|
||||
│ │
|
||||
│ ┌──────────────────────────────────────────┐ │
|
||||
│ │ hermes-agent (gateway) │ │
|
||||
│ │ MATRIX_HOMESERVER=http://localhost:8008 │ │
|
||||
│ └──────────────────────────────────────────┘ │
|
||||
└─────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Docker + Docker Compose plugin on Ezra VPS
|
||||
- SSH access: `ssh root@143.198.27.163`
|
||||
- DNS A record pointing to the VPS IP
|
||||
- (Recommended) Nginx + Certbot for TLS termination
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
# SSH into Ezra
|
||||
ssh root@143.198.27.163
|
||||
|
||||
# Clone hermes-agent (if not present)
|
||||
cd /root
|
||||
git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent.git
|
||||
cd hermes-agent/deploy/synapse
|
||||
|
||||
# Deploy Synapse
|
||||
chmod +x setup.sh
|
||||
./setup.sh matrix.timmy-time.xyz
|
||||
|
||||
# This will:
|
||||
# 1. Generate .env with database password
|
||||
# 2. Prepare homeserver.yaml
|
||||
# 3. Start Synapse + PostgreSQL via Docker Compose
|
||||
# 4. Wait for health
|
||||
# 5. Register admin + bot accounts
|
||||
# 6. Acquire bot access token
|
||||
# 7. Write synapse-credentials.env
|
||||
```
|
||||
|
||||
## Step-by-Step
|
||||
|
||||
### 1. DNS Configuration
|
||||
|
||||
Point your Matrix domain to Ezra's IP:
|
||||
|
||||
```
|
||||
Type Name Value
|
||||
A matrix 143.198.27.163
|
||||
```
|
||||
|
||||
Federation uses SRV records for port discovery, but direct `:8448` works without them.
|
||||
|
||||
### 2. Deploy Synapse
|
||||
|
||||
```bash
|
||||
cd /root/hermes-agent/deploy/synapse
|
||||
./setup.sh matrix.timmy-time.xyz hermes-bot 'your-secure-password'
|
||||
```
|
||||
|
||||
Arguments:
|
||||
| Arg | Default | Description |
|
||||
|-----|---------|-------------|
|
||||
| `server_name` | (required) | Matrix domain (e.g., `matrix.timmy-time.xyz`) |
|
||||
| `admin_user` | `timmy-admin` | Admin account username |
|
||||
| `admin_password` | (random) | Admin account password |
|
||||
| `bot_user` | `hermes-bot` | Bot account username |
|
||||
| `bot_password` | (random) | Bot account password |
|
||||
|
||||
### 3. TLS Termination (Nginx)
|
||||
|
||||
Install Nginx + Certbot:
|
||||
|
||||
```bash
|
||||
apt install -y nginx certbot python3-certbot-nginx
|
||||
|
||||
# Client-server API
|
||||
cat > /etc/nginx/sites-available/matrix <<'EOF'
|
||||
server {
|
||||
listen 443 ssl http2;
|
||||
server_name matrix.timmy-time.xyz;
|
||||
|
||||
ssl_certificate /etc/letsencrypt/live/matrix.timmy-time.xyz/fullchain.pem;
|
||||
ssl_certificate_key /etc/letsencrypt/live/matrix.timmy-time.xyz/privkey.pem;
|
||||
|
||||
location / {
|
||||
proxy_pass http://127.0.0.1:8008;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
client_max_body_size 50M;
|
||||
}
|
||||
}
|
||||
|
||||
server {
|
||||
listen 8448 ssl http2;
|
||||
server_name matrix.timmy-time.xyz;
|
||||
|
||||
ssl_certificate /etc/letsencrypt/live/matrix.timmy-time.xyz/fullchain.pem;
|
||||
ssl_certificate_key /etc/letsencrypt/live/matrix.timmy-time.xyz/privkey.pem;
|
||||
|
||||
location / {
|
||||
proxy_pass http://127.0.0.1:8008;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
}
|
||||
EOF
|
||||
|
||||
ln -sf /etc/nginx/sites-available/matrix /etc/nginx/sites-enabled/
|
||||
nginx -t && systemctl reload nginx
|
||||
|
||||
# Get cert
|
||||
certbot --nginx -d matrix.timmy-time.xyz
|
||||
```
|
||||
|
||||
### 4. Wire Hermes Agent
|
||||
|
||||
Copy the generated credentials to hermes-agent's environment:
|
||||
|
||||
```bash
|
||||
# From synapse-credentials.env, add to ~/.hermes/.env:
|
||||
MATRIX_HOMESERVER=https://matrix.timmy-time.xyz
|
||||
MATRIX_ACCESS_TOKEN=<from synapse-credentials.env>
|
||||
MATRIX_USER_ID=@hermes-bot:matrix.timmy-time.xyz
|
||||
MATRIX_DEVICE_ID=<from synapse-credentials.env>
|
||||
MATRIX_ENCRYPTION=true
|
||||
```
|
||||
|
||||
Then start the gateway:
|
||||
|
||||
```bash
|
||||
hermes gateway --platform matrix
|
||||
```
|
||||
|
||||
### 5. Verify
|
||||
|
||||
```bash
|
||||
# Check Synapse health
|
||||
curl -s https://matrix.timmy-time.xyz/_matrix/client/versions
|
||||
|
||||
# Check federation
|
||||
curl -s https://matrix.timmy-time.xyz:8448/_matrix/federation/v1/version
|
||||
|
||||
# Check bot is connected
|
||||
# (should appear online in Element or any Matrix client)
|
||||
```
|
||||
|
||||
## Management
|
||||
|
||||
Use the management script for day-to-day operations:
|
||||
|
||||
```bash
|
||||
cd /root/hermes-agent/deploy/synapse
|
||||
|
||||
./manage.sh status # container health
|
||||
./manage.sh logs # tail logs
|
||||
./manage.sh restart # restart Synapse
|
||||
./manage.sh backup # backup DB + data
|
||||
./manage.sh update # pull latest image
|
||||
./manage.sh create-user alice 'password123'
|
||||
./manage.sh create-user admin 'secret' admin
|
||||
```
|
||||
|
||||
## Backups
|
||||
|
||||
```bash
|
||||
./manage.sh backup
|
||||
# Creates: backups/YYYYMMDD_HHMMSS/
|
||||
# ├── synapse_db.sql (PostgreSQL dump)
|
||||
# └── synapse_data.tar.gz (media store + keys)
|
||||
```
|
||||
|
||||
Automate with cron:
|
||||
|
||||
```bash
|
||||
# Daily backup at 3 AM
|
||||
0 3 * * * cd /root/hermes-agent/deploy/synapse && ./manage.sh backup >> /var/log/synapse-backup.log 2>&1
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Synapse won't start
|
||||
```bash
|
||||
docker compose logs synapse
|
||||
# Common: PostgreSQL not ready. Wait for healthcheck.
|
||||
```
|
||||
|
||||
### Bot can't connect
|
||||
```bash
|
||||
# Verify token is valid
|
||||
curl -H "Authorization: Bearer $MATRIX_ACCESS_TOKEN" \
|
||||
https://matrix.timmy-time.xyz/_matrix/client/v3/account/whoami
|
||||
```
|
||||
|
||||
### Federation not working
|
||||
```bash
|
||||
# Check port 8448 is open
|
||||
ss -tlnp | grep 8448
|
||||
# Check firewall
|
||||
ufw status
|
||||
```
|
||||
|
||||
### High memory usage
|
||||
```bash
|
||||
# Check resource limits in docker-compose.yml
|
||||
docker stats synapse
|
||||
# Tune in homeserver.yaml: event_cache_size, caches
|
||||
```
|
||||
|
||||
## Security Notes
|
||||
|
||||
- Registration is disabled by default (`enable_registration: false`)
|
||||
- Rate limiting is enforced on login, registration, and messages
|
||||
- Federation certificate verification is enabled
|
||||
- `.env` and `synapse-credentials.env` are `chmod 600`
|
||||
- Client API binds to `127.0.0.1` only (use Nginx for public access)
|
||||
- Consider: firewall rules, fail2ban, regular backups
|
||||
|
||||
## References
|
||||
|
||||
- [Synapse Documentation](https://matrix-org.github.io/synapse/latest/)
|
||||
- [Matrix Spec](https://spec.matrix.org/)
|
||||
- [Epic #269: Matrix Integration](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/269)
|
||||
- [Issue #272: Deploy Synapse on Ezra](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/272)
|
||||
- [Hermes Matrix Setup Guide](docs/matrix-setup.md)
|
||||
Reference in New Issue
Block a user