talkops-helm-mcp-server 0.3.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- helm_mcp_server/__init__.py +4 -0
- helm_mcp_server/config.py +83 -0
- helm_mcp_server/exceptions/__init__.py +18 -0
- helm_mcp_server/exceptions/custom.py +54 -0
- helm_mcp_server/main.py +40 -0
- helm_mcp_server/prompts/__init__.py +33 -0
- helm_mcp_server/prompts/base.py +42 -0
- helm_mcp_server/prompts/installation_prompts.py +69 -0
- helm_mcp_server/prompts/registry.py +33 -0
- helm_mcp_server/prompts/rollback_prompts.py +213 -0
- helm_mcp_server/prompts/security_prompts.py +133 -0
- helm_mcp_server/prompts/troubleshooting_prompts.py +155 -0
- helm_mcp_server/prompts/upgrade_prompts.py +58 -0
- helm_mcp_server/prompts/workflow_prompts.py +180 -0
- helm_mcp_server/resources/__init__.py +29 -0
- helm_mcp_server/resources/base.py +42 -0
- helm_mcp_server/resources/chart_resources.py +117 -0
- helm_mcp_server/resources/helm_resources.py +82 -0
- helm_mcp_server/resources/kubernetes_resources.py +55 -0
- helm_mcp_server/resources/registry.py +38 -0
- helm_mcp_server/resources/static_resources.py +53 -0
- helm_mcp_server/scripts/scrape_helm_best_practices.py +120 -0
- helm_mcp_server/server/__init__.py +10 -0
- helm_mcp_server/server/bootstrap.py +50 -0
- helm_mcp_server/server/core.py +49 -0
- helm_mcp_server/server/middleware.py +130 -0
- helm_mcp_server/services/__init__.py +12 -0
- helm_mcp_server/services/helm_service.py +1882 -0
- helm_mcp_server/services/kubernetes_service.py +429 -0
- helm_mcp_server/services/validation_service.py +206 -0
- helm_mcp_server/static/HELM_BEST_PRACTICES.md +831 -0
- helm_mcp_server/static/HELM_MCP_INSTRUCTIONS.md +190 -0
- helm_mcp_server/static/HELM_WORKFLOW_GUIDE.md +554 -0
- helm_mcp_server/static/__init__.py +0 -0
- helm_mcp_server/tools/__init__.py +31 -0
- helm_mcp_server/tools/base.py +45 -0
- helm_mcp_server/tools/discovery/__init__.py +6 -0
- helm_mcp_server/tools/discovery/chart_discovery.py +307 -0
- helm_mcp_server/tools/installation/__init__.py +6 -0
- helm_mcp_server/tools/installation/chart_management.py +553 -0
- helm_mcp_server/tools/kubernetes/__init__.py +6 -0
- helm_mcp_server/tools/kubernetes/cluster_ops.py +319 -0
- helm_mcp_server/tools/monitoring/__init__.py +6 -0
- helm_mcp_server/tools/monitoring/deployment_monitor.py +183 -0
- helm_mcp_server/tools/registry.py +38 -0
- helm_mcp_server/tools/validation/__init__.py +6 -0
- helm_mcp_server/tools/validation/chart_validation.py +420 -0
- helm_mcp_server/utils/__init__.py +11 -0
- helm_mcp_server/utils/helm_helper.py +70 -0
- talkops_helm_mcp_server-0.3.0.dist-info/METADATA +676 -0
- talkops_helm_mcp_server-0.3.0.dist-info/RECORD +53 -0
- talkops_helm_mcp_server-0.3.0.dist-info/WHEEL +4 -0
- talkops_helm_mcp_server-0.3.0.dist-info/entry_points.txt +2 -0
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
"""Application configuration management."""
|
|
2
|
+
|
|
3
|
+
import os
|
|
4
|
+
from dataclasses import dataclass, field
|
|
5
|
+
from typing import Optional
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
@dataclass
|
|
10
|
+
class HelmConfig:
|
|
11
|
+
"""Helm configuration."""
|
|
12
|
+
timeout: int = 300
|
|
13
|
+
repositories: list[str] = field(default_factory=lambda: ['bitnami'])
|
|
14
|
+
max_concurrent_operations: int = 10
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
@dataclass
|
|
18
|
+
class KubernetesConfig:
|
|
19
|
+
"""Kubernetes configuration."""
|
|
20
|
+
timeout: int = 30
|
|
21
|
+
verify_ssl: bool = True
|
|
22
|
+
connection_pool_size: int = 10
|
|
23
|
+
kubeconfig: Optional[str] = None
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
@dataclass
|
|
27
|
+
class LoggingConfig:
|
|
28
|
+
"""Logging configuration."""
|
|
29
|
+
level: str = 'INFO'
|
|
30
|
+
format: str = 'json'
|
|
31
|
+
file_path: str = './logs/mcp_server.log'
|
|
32
|
+
max_bytes: int = 10485760 # 10MB
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
@dataclass
|
|
36
|
+
class ServerConfig:
|
|
37
|
+
"""MCP server configuration."""
|
|
38
|
+
name: str = 'helm-mcp-server'
|
|
39
|
+
version: str = '0.2.0'
|
|
40
|
+
transport: str = 'http' # http (Streamable HTTP) or stdio
|
|
41
|
+
host: str = '0.0.0.0'
|
|
42
|
+
port: int = 8765 # HTTP/SSE server port
|
|
43
|
+
path: str = '/mcp' # MCP endpoint path
|
|
44
|
+
allow_write: bool = False # Enable write access for mutating operations
|
|
45
|
+
# HTTP server timeout settings (in seconds)
|
|
46
|
+
http_timeout: int = 300 # HTTP request timeout
|
|
47
|
+
http_keepalive_timeout: int = 5 # HTTP keepalive timeout
|
|
48
|
+
http_connect_timeout: int = 60 # HTTP connection timeout
|
|
49
|
+
|
|
50
|
+
helm: HelmConfig = field(default_factory=HelmConfig)
|
|
51
|
+
kubernetes: KubernetesConfig = field(default_factory=KubernetesConfig)
|
|
52
|
+
logging: LoggingConfig = field(default_factory=LoggingConfig)
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
class Config:
|
|
56
|
+
"""Configuration loader."""
|
|
57
|
+
|
|
58
|
+
@staticmethod
|
|
59
|
+
def from_env() -> ServerConfig:
|
|
60
|
+
"""Load configuration from environment variables."""
|
|
61
|
+
return ServerConfig(
|
|
62
|
+
name=os.getenv('MCP_SERVER_NAME', 'helm-mcp-server'),
|
|
63
|
+
version=os.getenv('MCP_SERVER_VERSION', '0.2.0'),
|
|
64
|
+
transport=os.getenv('MCP_TRANSPORT', 'http'),
|
|
65
|
+
host=os.getenv('MCP_HOST', '0.0.0.0'),
|
|
66
|
+
port=int(os.getenv('MCP_PORT', '8765')),
|
|
67
|
+
path=os.getenv('MCP_PATH', '/mcp'),
|
|
68
|
+
allow_write=os.getenv('MCP_ALLOW_WRITE', 'true').lower() == 'true',
|
|
69
|
+
http_timeout=int(os.getenv('MCP_HTTP_TIMEOUT', '300')),
|
|
70
|
+
http_keepalive_timeout=int(os.getenv('MCP_HTTP_KEEPALIVE_TIMEOUT', '5')),
|
|
71
|
+
http_connect_timeout=int(os.getenv('MCP_HTTP_CONNECT_TIMEOUT', '60')),
|
|
72
|
+
helm=HelmConfig(
|
|
73
|
+
timeout=int(os.getenv('HELM_TIMEOUT', '300')),
|
|
74
|
+
),
|
|
75
|
+
kubernetes=KubernetesConfig(
|
|
76
|
+
timeout=int(os.getenv('K8S_TIMEOUT', '30')),
|
|
77
|
+
),
|
|
78
|
+
logging=LoggingConfig(
|
|
79
|
+
level=os.getenv('MCP_LOG_LEVEL', 'INFO'),
|
|
80
|
+
format=os.getenv('MCP_LOG_FORMAT', 'json'),
|
|
81
|
+
),
|
|
82
|
+
)
|
|
83
|
+
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
"""Exception module."""
|
|
2
|
+
|
|
3
|
+
from helm_mcp_server.exceptions.custom import (
|
|
4
|
+
HelmOperationError,
|
|
5
|
+
KubernetesOperationError,
|
|
6
|
+
HelmResourceError,
|
|
7
|
+
HelmResourceNotFoundError,
|
|
8
|
+
HelmValidationError,
|
|
9
|
+
)
|
|
10
|
+
|
|
11
|
+
__all__ = [
|
|
12
|
+
'HelmOperationError',
|
|
13
|
+
'KubernetesOperationError',
|
|
14
|
+
'HelmResourceError',
|
|
15
|
+
'HelmResourceNotFoundError',
|
|
16
|
+
'HelmValidationError',
|
|
17
|
+
]
|
|
18
|
+
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
"""Custom exceptions for Helm MCP server.
|
|
2
|
+
|
|
3
|
+
Following FastMCP exceptions from:
|
|
4
|
+
https://gofastmcp.com/python-sdk/fastmcp-exceptions
|
|
5
|
+
"""
|
|
6
|
+
|
|
7
|
+
from fastmcp.exceptions import (
|
|
8
|
+
FastMCPError,
|
|
9
|
+
ToolError,
|
|
10
|
+
ResourceError,
|
|
11
|
+
NotFoundError,
|
|
12
|
+
ValidationError,
|
|
13
|
+
)
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
class HelmOperationError(ToolError):
|
|
17
|
+
"""Error during Helm operations.
|
|
18
|
+
|
|
19
|
+
Inherits from ToolError for tool-related Helm operations.
|
|
20
|
+
"""
|
|
21
|
+
pass
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
class KubernetesOperationError(ToolError):
|
|
25
|
+
"""Error during Kubernetes operations.
|
|
26
|
+
|
|
27
|
+
Inherits from ToolError for tool-related Kubernetes operations.
|
|
28
|
+
"""
|
|
29
|
+
pass
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
class HelmResourceError(ResourceError):
|
|
33
|
+
"""Error during Helm resource operations.
|
|
34
|
+
|
|
35
|
+
Inherits from ResourceError for resource-related Helm operations.
|
|
36
|
+
"""
|
|
37
|
+
pass
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
class HelmResourceNotFoundError(NotFoundError):
|
|
41
|
+
"""Error when a Helm resource is not found.
|
|
42
|
+
|
|
43
|
+
Inherits from NotFoundError for resource not found scenarios.
|
|
44
|
+
"""
|
|
45
|
+
pass
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
class HelmValidationError(ValidationError):
|
|
49
|
+
"""Error validating Helm chart parameters or values.
|
|
50
|
+
|
|
51
|
+
Inherits from ValidationError for validation-related errors.
|
|
52
|
+
"""
|
|
53
|
+
pass
|
|
54
|
+
|
helm_mcp_server/main.py
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
"""Application entry point."""
|
|
2
|
+
|
|
3
|
+
import sys
|
|
4
|
+
from pathlib import Path
|
|
5
|
+
|
|
6
|
+
# Add project root to Python path for direct execution with uv run
|
|
7
|
+
project_root = Path(__file__).parent.parent
|
|
8
|
+
if str(project_root) not in sys.path:
|
|
9
|
+
sys.path.insert(0, str(project_root))
|
|
10
|
+
|
|
11
|
+
from helm_mcp_server.server.bootstrap import ServerBootstrap
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def main():
|
|
15
|
+
"""Run the MCP server."""
|
|
16
|
+
try:
|
|
17
|
+
mcp, config = ServerBootstrap.initialize()
|
|
18
|
+
|
|
19
|
+
# Run FastMCP server with the configured transport
|
|
20
|
+
if config.transport == 'http':
|
|
21
|
+
# HTTP/Streamable HTTP transport mode (single unified endpoint)
|
|
22
|
+
mcp.run(transport='streamable-http', host=config.host, port=config.port, path=config.path)
|
|
23
|
+
else:
|
|
24
|
+
# STDIO transport mode (default for MCP)
|
|
25
|
+
mcp.run()
|
|
26
|
+
|
|
27
|
+
except KeyboardInterrupt:
|
|
28
|
+
pass
|
|
29
|
+
except Exception as e:
|
|
30
|
+
raise
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
def cli():
|
|
34
|
+
"""CLI entry point for the helm-mcp-server command."""
|
|
35
|
+
main()
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
if __name__ == '__main__':
|
|
39
|
+
cli()
|
|
40
|
+
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
"""Prompts module initialization."""
|
|
2
|
+
|
|
3
|
+
from typing import Dict, Any
|
|
4
|
+
from helm_mcp_server.prompts.registry import PromptRegistry
|
|
5
|
+
from helm_mcp_server.prompts.installation_prompts import InstallationPrompts
|
|
6
|
+
from helm_mcp_server.prompts.troubleshooting_prompts import TroubleshootingPrompts
|
|
7
|
+
from helm_mcp_server.prompts.security_prompts import SecurityPrompts
|
|
8
|
+
from helm_mcp_server.prompts.upgrade_prompts import UpgradePrompts
|
|
9
|
+
from helm_mcp_server.prompts.rollback_prompts import RollbackPrompts
|
|
10
|
+
from helm_mcp_server.prompts.workflow_prompts import WorkflowPrompts
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
def initialize_prompts(service_locator: Dict[str, Any]) -> PromptRegistry:
|
|
14
|
+
"""Initialize all prompt modules.
|
|
15
|
+
|
|
16
|
+
Args:
|
|
17
|
+
service_locator: Dictionary of services
|
|
18
|
+
|
|
19
|
+
Returns:
|
|
20
|
+
Prompt registry with all prompts registered
|
|
21
|
+
"""
|
|
22
|
+
registry = PromptRegistry()
|
|
23
|
+
|
|
24
|
+
# Register prompt groups
|
|
25
|
+
registry.register_prompt(InstallationPrompts(service_locator))
|
|
26
|
+
registry.register_prompt(TroubleshootingPrompts(service_locator))
|
|
27
|
+
registry.register_prompt(SecurityPrompts(service_locator))
|
|
28
|
+
registry.register_prompt(UpgradePrompts(service_locator))
|
|
29
|
+
registry.register_prompt(RollbackPrompts(service_locator))
|
|
30
|
+
registry.register_prompt(WorkflowPrompts(service_locator))
|
|
31
|
+
|
|
32
|
+
return registry
|
|
33
|
+
|
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
"""Base class for all prompts."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from abc import ABC, abstractmethod
|
|
6
|
+
from typing import TYPE_CHECKING, Dict, Any
|
|
7
|
+
|
|
8
|
+
if TYPE_CHECKING:
|
|
9
|
+
from helm_mcp_server.services.helm_service import HelmService
|
|
10
|
+
from helm_mcp_server.services.kubernetes_service import KubernetesService
|
|
11
|
+
from helm_mcp_server.services.validation_service import ValidationService
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
class BasePrompt(ABC):
|
|
15
|
+
"""Abstract base class for all prompts.
|
|
16
|
+
|
|
17
|
+
Subclasses implement specific prompt logic while inheriting
|
|
18
|
+
common patterns like dependency injection.
|
|
19
|
+
"""
|
|
20
|
+
|
|
21
|
+
helm_service: HelmService
|
|
22
|
+
k8s_service: KubernetesService
|
|
23
|
+
validation_service: ValidationService
|
|
24
|
+
|
|
25
|
+
def __init__(self, service_locator: Dict[str, Any]):
|
|
26
|
+
"""Initialize prompt with service locator.
|
|
27
|
+
|
|
28
|
+
Args:
|
|
29
|
+
service_locator: Dictionary of services (helm_service, k8s_service, validation_service, etc.)
|
|
30
|
+
"""
|
|
31
|
+
self.helm_service = service_locator.get('helm_service') # type: ignore[assignment]
|
|
32
|
+
self.k8s_service = service_locator.get('k8s_service') # type: ignore[assignment]
|
|
33
|
+
self.validation_service = service_locator.get('validation_service') # type: ignore[assignment]
|
|
34
|
+
|
|
35
|
+
@abstractmethod
|
|
36
|
+
def register(self, mcp_instance) -> None:
|
|
37
|
+
"""Register prompts with FastMCP instance.
|
|
38
|
+
|
|
39
|
+
Args:
|
|
40
|
+
mcp_instance: FastMCP server instance
|
|
41
|
+
"""
|
|
42
|
+
pass
|
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
"""Installation-related prompts."""
|
|
2
|
+
|
|
3
|
+
from typing import List
|
|
4
|
+
from mcp.types import PromptMessage, TextContent
|
|
5
|
+
from helm_mcp_server.prompts.base import BasePrompt
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class InstallationPrompts(BasePrompt):
|
|
9
|
+
"""Installation prompts."""
|
|
10
|
+
|
|
11
|
+
def register(self, mcp_instance) -> None:
|
|
12
|
+
"""Register prompts with FastMCP."""
|
|
13
|
+
|
|
14
|
+
@mcp_instance.prompt(
|
|
15
|
+
name="helm-installation-guidelines",
|
|
16
|
+
description="Best practices for Helm chart installation",
|
|
17
|
+
)
|
|
18
|
+
def helm_installation_guidelines() -> List[PromptMessage]:
|
|
19
|
+
"""Helm installation guidelines and best practices.
|
|
20
|
+
|
|
21
|
+
This prompt provides guidelines for safe Helm chart installation.
|
|
22
|
+
"""
|
|
23
|
+
return [
|
|
24
|
+
PromptMessage(
|
|
25
|
+
role="user",
|
|
26
|
+
content=TextContent(
|
|
27
|
+
type="text",
|
|
28
|
+
text="""# Helm Installation Best Practices
|
|
29
|
+
|
|
30
|
+
## Pre-Installation Checklist
|
|
31
|
+
- [ ] Verify cluster connectivity and permissions
|
|
32
|
+
- [ ] Review chart documentation and release notes
|
|
33
|
+
- [ ] Validate all required configuration values
|
|
34
|
+
- [ ] Check resource availability (CPU, memory, storage)
|
|
35
|
+
- [ ] Plan for rollback if needed
|
|
36
|
+
- [ ] Verify namespace exists or will be created
|
|
37
|
+
- [ ] Check for conflicting releases or resources
|
|
38
|
+
|
|
39
|
+
## Installation Steps
|
|
40
|
+
1. **Fetch chart metadata** - Get chart info and schema
|
|
41
|
+
2. **Validate configuration** - Check values against schema
|
|
42
|
+
3. **Render manifests** - Preview what will be deployed
|
|
43
|
+
4. **Dry-run** - Test installation without deploying
|
|
44
|
+
5. **Review output** - Check for any warnings or errors
|
|
45
|
+
6. **Get approval** - Ensure stakeholder sign-off
|
|
46
|
+
7. **Install** - Deploy to cluster
|
|
47
|
+
8. **Monitor** - Watch pods and services
|
|
48
|
+
9. **Verify** - Run health checks
|
|
49
|
+
10. **Document** - Record configuration and access info
|
|
50
|
+
|
|
51
|
+
## Common Mistakes to Avoid
|
|
52
|
+
- ❌ Not testing with --dry-run first
|
|
53
|
+
- ❌ Using 'latest' version (pin specific versions)
|
|
54
|
+
- ❌ Ignoring resource limits
|
|
55
|
+
- ❌ Not backing up before upgrades
|
|
56
|
+
- ❌ Installing to production without testing first
|
|
57
|
+
- ❌ Forgetting about persistent volumes
|
|
58
|
+
- ❌ Not setting up monitoring/alerting
|
|
59
|
+
|
|
60
|
+
## Post-Installation
|
|
61
|
+
- Verify all pods are running
|
|
62
|
+
- Check service endpoints are accessible
|
|
63
|
+
- Review logs for any errors
|
|
64
|
+
- Set up monitoring and alerts
|
|
65
|
+
- Document the installation
|
|
66
|
+
- Create runbook for maintenance"""
|
|
67
|
+
)
|
|
68
|
+
)
|
|
69
|
+
]
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
"""Prompt registry for managing all prompts."""
|
|
2
|
+
|
|
3
|
+
from typing import List
|
|
4
|
+
from helm_mcp_server.prompts.base import BasePrompt
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
class PromptRegistry:
|
|
8
|
+
"""Registry for managing prompts.
|
|
9
|
+
|
|
10
|
+
Encapsulates prompt registration and lifecycle.
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
def __init__(self):
|
|
14
|
+
"""Initialize registry."""
|
|
15
|
+
self.prompts: List[BasePrompt] = []
|
|
16
|
+
|
|
17
|
+
def register_prompt(self, prompt: BasePrompt) -> None:
|
|
18
|
+
"""Register a prompt.
|
|
19
|
+
|
|
20
|
+
Args:
|
|
21
|
+
prompt: Prompt instance
|
|
22
|
+
"""
|
|
23
|
+
self.prompts.append(prompt)
|
|
24
|
+
|
|
25
|
+
def register_all_prompts(self, mcp_instance) -> None:
|
|
26
|
+
"""Register all prompts with FastMCP instance.
|
|
27
|
+
|
|
28
|
+
Args:
|
|
29
|
+
mcp_instance: FastMCP server instance
|
|
30
|
+
"""
|
|
31
|
+
for prompt in self.prompts:
|
|
32
|
+
prompt.register(mcp_instance)
|
|
33
|
+
|
|
@@ -0,0 +1,213 @@
|
|
|
1
|
+
"""Rollback-related prompts."""
|
|
2
|
+
|
|
3
|
+
from typing import List
|
|
4
|
+
from mcp.types import PromptMessage, TextContent
|
|
5
|
+
from helm_mcp_server.prompts.base import BasePrompt
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class RollbackPrompts(BasePrompt):
|
|
9
|
+
"""Rollback prompts."""
|
|
10
|
+
|
|
11
|
+
def register(self, mcp_instance) -> None:
|
|
12
|
+
"""Register prompts with FastMCP."""
|
|
13
|
+
|
|
14
|
+
@mcp_instance.prompt(
|
|
15
|
+
name="helm-rollback-procedures",
|
|
16
|
+
description="Step-by-step rollback procedures for Helm releases",
|
|
17
|
+
)
|
|
18
|
+
def helm_rollback_procedures(release_name: str) -> List[PromptMessage]:
|
|
19
|
+
"""Step-by-step rollback procedures for Helm releases.
|
|
20
|
+
|
|
21
|
+
Arguments:
|
|
22
|
+
release_name: Name of the Helm release to rollback
|
|
23
|
+
"""
|
|
24
|
+
return [
|
|
25
|
+
PromptMessage(
|
|
26
|
+
role="user",
|
|
27
|
+
content=TextContent(
|
|
28
|
+
type="text",
|
|
29
|
+
text=f"""# Helm Rollback Procedures: {release_name}
|
|
30
|
+
|
|
31
|
+
## When to Rollback
|
|
32
|
+
|
|
33
|
+
Rollback should be considered when:
|
|
34
|
+
- Upgrade or installation fails
|
|
35
|
+
- Application is not functioning correctly after deployment
|
|
36
|
+
- Critical bugs are discovered in new version
|
|
37
|
+
- Performance degradation occurs
|
|
38
|
+
- Data integrity issues are detected
|
|
39
|
+
|
|
40
|
+
## Pre-Rollback Assessment
|
|
41
|
+
|
|
42
|
+
### Current State
|
|
43
|
+
- [ ] Identify the issue requiring rollback
|
|
44
|
+
- [ ] Check current release status: `helm status {release_name}`
|
|
45
|
+
- [ ] Review release history: `helm history {release_name}`
|
|
46
|
+
- [ ] Document current problems
|
|
47
|
+
- [ ] Assess impact of rollback
|
|
48
|
+
|
|
49
|
+
### Release History
|
|
50
|
+
```bash
|
|
51
|
+
helm history {release_name}
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
This shows all revisions of the release. Identify which revision to rollback to (typically the previous working version).
|
|
55
|
+
|
|
56
|
+
## Rollback Process
|
|
57
|
+
|
|
58
|
+
### Step 1: Review Release History
|
|
59
|
+
```bash
|
|
60
|
+
# List all revisions
|
|
61
|
+
helm history {release_name}
|
|
62
|
+
|
|
63
|
+
# Get details of specific revision
|
|
64
|
+
helm get values {release_name} --revision <revision-number>
|
|
65
|
+
helm get manifest {release_name} --revision <revision-number>
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
### Step 2: Identify Target Revision
|
|
69
|
+
- Review revision numbers
|
|
70
|
+
- Identify last known good revision
|
|
71
|
+
- Verify target revision configuration
|
|
72
|
+
- Check if target revision is stable
|
|
73
|
+
|
|
74
|
+
### Step 3: Perform Rollback
|
|
75
|
+
```bash
|
|
76
|
+
# Rollback to previous revision
|
|
77
|
+
helm rollback {release_name}
|
|
78
|
+
|
|
79
|
+
# Rollback to specific revision
|
|
80
|
+
helm rollback {release_name} <revision-number>
|
|
81
|
+
|
|
82
|
+
# Rollback with wait
|
|
83
|
+
helm rollback {release_name} <revision-number> --wait --timeout 10m
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
### Step 4: Verify Rollback
|
|
87
|
+
```bash
|
|
88
|
+
# Check release status
|
|
89
|
+
helm status {release_name}
|
|
90
|
+
|
|
91
|
+
# Verify pods are running
|
|
92
|
+
kubectl get pods -l app.kubernetes.io/instance={release_name}
|
|
93
|
+
|
|
94
|
+
# Check release history
|
|
95
|
+
helm history {release_name}
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
## Post-Rollback Verification
|
|
99
|
+
|
|
100
|
+
### Immediate Checks
|
|
101
|
+
- [ ] Verify release status shows correct revision
|
|
102
|
+
- [ ] Check all pods are running and healthy
|
|
103
|
+
- [ ] Verify services are accessible
|
|
104
|
+
- [ ] Review pod logs for errors
|
|
105
|
+
- [ ] Check for any error events
|
|
106
|
+
|
|
107
|
+
### Functional Testing
|
|
108
|
+
- [ ] Test application functionality
|
|
109
|
+
- [ ] Verify data integrity
|
|
110
|
+
- [ ] Check service endpoints
|
|
111
|
+
- [ ] Test critical workflows
|
|
112
|
+
- [ ] Monitor application metrics
|
|
113
|
+
|
|
114
|
+
### Monitoring
|
|
115
|
+
- [ ] Watch pod status for 15-30 minutes
|
|
116
|
+
- [ ] Monitor resource usage
|
|
117
|
+
- [ ] Check application logs
|
|
118
|
+
- [ ] Review metrics and alerts
|
|
119
|
+
- [ ] Verify health checks
|
|
120
|
+
|
|
121
|
+
## Rollback Scenarios
|
|
122
|
+
|
|
123
|
+
### Scenario 1: Failed Upgrade
|
|
124
|
+
1. Upgrade failed mid-process
|
|
125
|
+
2. Release is in inconsistent state
|
|
126
|
+
3. Rollback to previous stable revision
|
|
127
|
+
4. Investigate upgrade failure
|
|
128
|
+
5. Fix issues before retrying
|
|
129
|
+
|
|
130
|
+
### Scenario 2: Application Issues
|
|
131
|
+
1. New version has bugs
|
|
132
|
+
2. Application not functioning correctly
|
|
133
|
+
3. Rollback to previous working version
|
|
134
|
+
4. Report issues to chart maintainers
|
|
135
|
+
5. Wait for fix before upgrading again
|
|
136
|
+
|
|
137
|
+
### Scenario 3: Performance Degradation
|
|
138
|
+
1. New version performs worse
|
|
139
|
+
2. Resource usage increased significantly
|
|
140
|
+
3. Rollback to previous version
|
|
141
|
+
4. Analyze performance differences
|
|
142
|
+
5. Optimize before upgrading
|
|
143
|
+
|
|
144
|
+
## Best Practices
|
|
145
|
+
|
|
146
|
+
### Before Rollback
|
|
147
|
+
- ✅ Document the reason for rollback
|
|
148
|
+
- ✅ Review release history carefully
|
|
149
|
+
- ✅ Verify target revision is stable
|
|
150
|
+
- ✅ Backup current state if possible
|
|
151
|
+
- ✅ Notify stakeholders
|
|
152
|
+
|
|
153
|
+
### During Rollback
|
|
154
|
+
- ✅ Use `--wait` flag to ensure completion
|
|
155
|
+
- ✅ Monitor rollback progress
|
|
156
|
+
- ✅ Watch for any errors
|
|
157
|
+
- ✅ Verify each step completes
|
|
158
|
+
|
|
159
|
+
### After Rollback
|
|
160
|
+
- ✅ Document rollback in change log
|
|
161
|
+
- ✅ Investigate root cause
|
|
162
|
+
- ✅ Fix issues before retrying
|
|
163
|
+
- ✅ Update runbooks if needed
|
|
164
|
+
- ✅ Share lessons learned
|
|
165
|
+
|
|
166
|
+
## Troubleshooting Rollback Issues
|
|
167
|
+
|
|
168
|
+
### Rollback Fails
|
|
169
|
+
1. Check release history for available revisions
|
|
170
|
+
2. Verify target revision exists
|
|
171
|
+
3. Check for resource conflicts
|
|
172
|
+
4. Review Kubernetes events
|
|
173
|
+
5. Try manual rollback if needed
|
|
174
|
+
|
|
175
|
+
### Partial Rollback
|
|
176
|
+
1. Check which resources rolled back
|
|
177
|
+
2. Manually fix remaining resources if needed
|
|
178
|
+
3. Verify all components are consistent
|
|
179
|
+
4. Consider full uninstall/reinstall if severe
|
|
180
|
+
|
|
181
|
+
### Data Concerns
|
|
182
|
+
1. Verify data persistence (if applicable)
|
|
183
|
+
2. Check for data corruption
|
|
184
|
+
3. Review backup availability
|
|
185
|
+
4. Consider data migration if needed
|
|
186
|
+
|
|
187
|
+
## Alternative: Manual Rollback
|
|
188
|
+
|
|
189
|
+
If `helm rollback` doesn't work:
|
|
190
|
+
|
|
191
|
+
```bash
|
|
192
|
+
# Get previous revision values
|
|
193
|
+
helm get values {release_name} --revision <previous-revision> > values.yaml
|
|
194
|
+
|
|
195
|
+
# Get previous revision chart version
|
|
196
|
+
helm get manifest {release_name} --revision <previous-revision>
|
|
197
|
+
|
|
198
|
+
# Manually upgrade to previous configuration
|
|
199
|
+
helm upgrade {release_name} <previous-chart-version> --values values.yaml
|
|
200
|
+
```
|
|
201
|
+
|
|
202
|
+
## Prevention
|
|
203
|
+
|
|
204
|
+
To avoid needing rollbacks:
|
|
205
|
+
- Always test upgrades in non-production
|
|
206
|
+
- Review changelogs and breaking changes
|
|
207
|
+
- Use dry-run before actual upgrades
|
|
208
|
+
- Have rollback plan ready
|
|
209
|
+
- Monitor closely after upgrades
|
|
210
|
+
- Keep backups current"""
|
|
211
|
+
)
|
|
212
|
+
)
|
|
213
|
+
]
|