* run pydantic ai agent in bedrock agentcore runtime. requirements file notebook and figures commited. Tested in AWS account
* update description in notebook cells to suit pydantic framework. Agent Image changed to pydantic
* removed image for local architecture, as it is unused in the notebook
* moved pydantic agent code file and noteook to create runtime into 03-integrations
---------
Co-authored-by: Aswathy Prasad <aswpras@amazon.com>
* Add multi-region support for SRE-Agent
- Add AWS region configuration parameter to agent_config.yaml
- Update gateway main.py to validate region matches endpoint URL
- Modify SRE agent to read region from config and pass through function chain
- Update memory client and LLM creation to use configurable region
- Fixes hardcoded us-east-1 region dependencies
Closes#245
* Move architecture file to docs/ and improve setup instructions
- Move sre_agent_architecture.md to docs/ folder for better organization
- Update graph export code to generate architecture file in docs/ folder
- Add automatic docs directory creation if it doesn't exist
- Improve README setup instructions:
- Fix .env.example copy path to use sre_agent folder
- Add note that Amazon Bedrock users don't need to modify .env
- Add START_API_BACKEND variable to conditionally start backend servers
- Useful for workshop environments where backends are already running
* Improve gateway configuration documentation and setup instructions
- Update config.yaml.example to use REGION placeholder instead of hardcoded us-east-1
- Add gateway configuration step to README setup instructions
- Document .cognito_config file in auth.md automated setup section
- Remove duplicate credential_provider_name from config.yaml.example
- Update configuration.md to include .cognito_config in files overview
- Add clear instructions to copy and edit gateway/config.yaml before creating gateway
* Improve IAM role guidance and region handling
- Add clear guidance about IAM role options in gateway/config.yaml.example
- Explain that testing can use current EC2/notebook role
- Recommend dedicated role for production deployments
- Add aws sts get-caller-identity command to help users find their role
- Update deployment scripts to use AWS_REGION env var as fallback
- Scripts now follow: CLI arg -> AWS_REGION env var -> us-east-1 default
* Remove unnecessary individual Cognito ID files
- Remove creation of .cognito_user_pool_id file
- Remove creation of .cognito_client_id file
- Keep only .cognito_config as the single source of truth
- Simplifies configuration management
* Implement region fallback logic for SRE Agent
- Added region fallback chain: agent_config.yaml -> AWS_REGION env -> us-east-1
- Modified agent_config.yaml to comment out region parameter to enable fallback
- Updated multi_agent_langgraph.py with comprehensive fallback implementation
- Added logging to show which region source is being used
- Ensures flexible region configuration without breaking existing deployments
- Maintains backward compatibility while adding multi-region support
notebook referencing "duckduckgo_search" while the requirements is using "ddgs". Updating the code to use "ddgs"
Signed-off-by: dendilaws <dendilaws@gmail.com>
* feat(sre-agent): add OpenTelemetry observability and tracing
- Add OpenTelemetry tracing to supervisor and memory tools
- Configure OTEL collector with Jaeger backend via docker-compose
- Add trace context propagation between supervisor and workers
- Include run-with-tracing.sh helper script for easy tracing setup
- Update blog post with comprehensive observability section
- Add presentation slides for SRE agent capabilities
* docs(sre-agent): replace mermaid diagram with architecture image
- Replace inline mermaid diagram with external architecture PNG image
- Add detailed component descriptions for AgentCore integration
- Image shows complete flow from customer to AgentCore services
* feat(sre-agent): add assets table with demo video and AI podcast links
- Add assets section with clickable links to demo video and AI-generated podcast
- Include descriptions for each asset to help users understand the content
- Position table prominently after the use case details for visibility
* docs(sre-agent): update blog post with latest code snippets and improvements
- Update Dockerfile snippet to include OpenTelemetry instrumentation
- Update invoke_agent_runtime.py snippet with timeout config and memory personalization
- Remove verbose real-time agent execution traces section while keeping key insights
- Simplify cleanup section to show only essential command
- Ensure all code snippets match latest implementation
* style(sre-agent): apply ruff formatting to Python files
- Format code with ruff formatter for consistent style
- Fix whitespace and indentation issues
- Apply standard Python formatting conventions
- Ensure code adheres to project style guidelines
* chore(sre-agent): remove slide files from docs
- Remove presentation slide markdown files
- Clean up docs directory structure
* Update blog post: Change S3 target references to API Endpoint Target
- Updated section heading from 'Deploy S3 targets' to 'Deploy API Endpoint Targets'
- Renamed function from create_s3_target to create_api_endpoint_target
- Updated variable name from s3_target_config to api_target_config
- Clarified that OpenAPI specs are used to create API Endpoint Targets
* Update README assets section with two demo videos
- Renamed first video to 'Demo video 1 (SRE-Agent CLI, VSCode integration)'
- Added 'Demo video 2 (Cursor integration)' with new link
- Clarified descriptions for both demo videos
* Update Demo video 2 description to specify AgentCore Gateway integration
- Changed description to 'Demonstration of AgentCore Gateway with SRE tools integration with Cursor IDE'
- More accurately describes the specific integration being demonstrated
* Update blog post Real-world use cases section with accurate agent behavior
- Changed 'agents work in parallel' to 'agents work sequentially' based on agent.log evidence
- Updated command example to use correct USER_ID environment variable instead of --user-id parameter
- Added comprehensive memory system integration explanation
- Reduced verbosity of trace outputs while maintaining key technical details
- Updated investigation plan and executive summary to match actual agent.log output format
- Added all five AgentCore primitives working together: Gateway, Identity, Runtime, Memory, and Observability
---------
Signed-off-by: Amit Arora <aroraai@amazon.com>
* feat(sre-agent): add OpenTelemetry observability and tracing
- Add OpenTelemetry tracing to supervisor and memory tools
- Configure OTEL collector with Jaeger backend via docker-compose
- Add trace context propagation between supervisor and workers
- Include run-with-tracing.sh helper script for easy tracing setup
- Update blog post with comprehensive observability section
- Add presentation slides for SRE agent capabilities
* docs(sre-agent): replace mermaid diagram with architecture image
- Replace inline mermaid diagram with external architecture PNG image
- Add detailed component descriptions for AgentCore integration
- Image shows complete flow from customer to AgentCore services
* feat(sre-agent): add assets table with demo video and AI podcast links
- Add assets section with clickable links to demo video and AI-generated podcast
- Include descriptions for each asset to help users understand the content
- Position table prominently after the use case details for visibility
* docs(sre-agent): update blog post with latest code snippets and improvements
- Update Dockerfile snippet to include OpenTelemetry instrumentation
- Update invoke_agent_runtime.py snippet with timeout config and memory personalization
- Remove verbose real-time agent execution traces section while keeping key insights
- Simplify cleanup section to show only essential command
- Ensure all code snippets match latest implementation
* style(sre-agent): apply ruff formatting to Python files
- Format code with ruff formatter for consistent style
- Fix whitespace and indentation issues
- Apply standard Python formatting conventions
- Ensure code adheres to project style guidelines
* chore(sre-agent): remove slide files from docs
- Remove presentation slide markdown files
- Clean up docs directory structure
* feat: integrate long-term memory system into SRE agent
- Add AgentCore Memory integration with three memory strategies:
* User preferences (escalation, notification, workflow preferences)
* Infrastructure knowledge (dependencies, patterns, baselines)
* Investigation summaries (timeline, actions, findings)
- Implement memory tools for save/retrieve operations
- Add automatic memory capture through hooks and pattern recognition
- Extend agent state to support memory context
- Integrate memory-aware planning in supervisor agent
- Add comprehensive test coverage for memory functionality
- Create detailed documentation with usage examples
This transforms the SRE agent from stateless to learning assistant
that becomes more valuable over time by remembering user preferences,
infrastructure patterns, and investigation outcomes.
Addresses issue #164
* feat: environment variable config, agent routing fixes, and project organization
- Move USER_ID/SESSION_ID from metadata parsing to environment variables
- Add .memory_id to .gitignore for local memory state
- Update .gitignore to use .scratchpad/ folder instead of .scratchpad.md
- Fix agent routing issues with supervisor prompt and graph node naming
- Add conversation memory tracking for all agents and supervisor
- Improve agent metadata system with centralized constants
- Add comprehensive logging and debugging for agent tool access
- Update deployment script to pass user_id/session_id in payload
- Create .scratchpad/ folder structure for better project organization
* feat: enhance SRE agent with automatic report archiving and error fixes
- Add automatic archiving system for reports by date
- Include user_id in report filenames for better organization
- Fix Pydantic validation error with string-to-list conversion for investigation steps
- Add content length truncation for memory storage to prevent validation errors
- Remove status line from report output for cleaner formatting
- Implement date-based folder organization (YYYY-MM-DD format)
- Add memory content length limits configuration in constants
Key improvements:
- Reports now auto-archive old files when saving new ones
- User-specific filenames: query_user_id_UserName_YYYYMMDD_HHMMSS.md
- Robust error handling for memory content length limits
- Backward compatibility with existing filename formats
* feat: fix memory retrieval system for cross-session searches and user personalization
Key fixes and improvements:
- Fix case preservation in actor_id sanitization (Carol remains Carol, not carol)
- Enable cross-session memory searches for infrastructure and investigation memories
- Add XML parsing support for investigation summaries stored in XML format
- Enhance user preference integration throughout the system
- Add comprehensive debug logging for memory retrieval processes
- Update prompts to support user-specific communication styles and preferences
Memory system now properly:
- Preserves user case in memory namespaces (/sre/users/Carol vs /sre/users/carol)
- Searches across all sessions for planning context vs session-specific for current state
- Parses both JSON and XML formatted investigation memories
- Adapts investigation approach based on user preferences and historical patterns
- Provides context-aware planning using infrastructure knowledge and past investigations
* feat: enhance SRE agent with user-specific memory isolation and anti-hallucination measures
Memory System Improvements:
- Fix memory isolation to retrieve only user-specific memories (Alice doesn't see Carol's data)
- Implement proper namespace handling for cross-session vs session-specific searches
- Add detailed logging for memory retrieval debugging and verification
- Remove verbose success logs, keep only error logs for cleaner output
Anti-Hallucination Enhancements:
- Add tool output validation requirements to agent prompts
- Implement timestamp fabrication prevention (use 2024-* format from backend)
- Require tool attribution for all metrics and findings in reports
- Add backend data alignment patterns for consistent data references
- Update supervisor aggregation prompts to flag unverified claims
Code Organization:
- Extract hardcoded prompts from supervisor.py to external prompt files
- Add missing session_id parameters to SaveInfrastructureTool and SaveInvestigationTool
- Improve memory client namespace documentation and cross-session search logic
- Reduce debug logging noise while maintaining error tracking
Verification Complete:
- Memory isolation working correctly (only user-specific data retrieval)
- Cross-session memory usage properly configured for planning and investigations
- Memory integration confirmed in report generation pipeline
- Anti-hallucination measures prevent fabricated metrics and timestamps
* feat: organize utility scripts in dedicated scripts folder
Script Organization:
- Move manage_memories.py to scripts/ folder with updated import paths
- Move configure_gateway.sh to scripts/ folder with corrected PROJECT_ROOT path
- Copy user_config.yaml to scripts/ folder for self-contained script usage
Path Fixes:
- Update manage_memories.py to import sre_agent module from correct relative path
- Fix .memory_id file path resolution for new script location
- Update configure_gateway.sh PROJECT_ROOT to point to correct parent directory
- Add fallback logic to find user_config.yaml in scripts/ or project root
Script Improvements:
- Update help text and examples to use 'uv run python scripts/' syntax
- Make manage_memories.py executable with proper permissions
- Maintain backward compatibility for custom config file paths
- Self-contained scripts folder with all required dependencies
Verification:
- All scripts work correctly from new location
- Memory management functions operate properly
- Gateway configuration handles paths correctly
- User preferences loading works from scripts directory
* docs: update SSL certificate paths to use /opt/ssl standard location
- Update README.md to reference /opt/ssl for SSL certificate paths
- Update docs/demo-environment.md to use /opt/ssl paths
- Clean up scripts/configure_gateway.sh SSL fallback paths
- Remove duplicate and outdated SSL path references
- Establish /opt/ssl as the standard SSL certificate location
This ensures consistent SSL certificate management across all
documentation and scripts, supporting the established /opt/ssl
directory with proper ubuntu:ubuntu ownership.
* feat: enhance memory system with infrastructure parsing fix and user personalization analysis
Infrastructure Memory Parsing Improvements:
- Fix infrastructure memory parsing to handle both JSON and plain text formats
- Convert plain text memories to structured InfrastructureKnowledge objects
- Change warning logs to debug level for normal text-to-structure conversion
- Ensure all infrastructure memories are now retrievable and usable
User Personalization Documentation:
- Add comprehensive memory system analysis comparing Alice vs Carol reports
- Create docs/examples/ folder with real investigation reports demonstrating personalization
- Document side-by-side communication differences based on user preferences
- Show how same technical incident produces different reports for different user roles
Example Reports Added:
- Alice's technical detailed investigation report (technical role preferences)
- Carol's business-focused executive summary report (executive role preferences)
- Memory system analysis with extensive side-by-side comparisons
This demonstrates the memory system's ability to:
- Maintain technical accuracy while adapting presentation style
- Apply user-specific escalation procedures and communication channels
- Build institutional knowledge about recurring infrastructure patterns
- Personalize identical technical incidents for different organizational roles
* feat: enhance memory system with automatic pattern extraction and improved logging
## Memory System Enhancements
- **Individual agent memory integration**: Every agent response now triggers automatic memory pattern extraction through on_agent_response() hooks
- **Enhanced conversation logging**: Added detailed message breakdown showing USER/ASSISTANT/TOOL message counts and tool names called
- **Fixed infrastructure extraction**: Resolved hardcoded agent name issues by using SREConstants for agent identification
- **Comprehensive memory persistence**: All agent responses and tool executions stored as conversation memory with proper session tracking
## Tool Architecture Clarification
- **Centralized memory access**: Confirmed only supervisor agent has direct access to memory tools (retrieve_memory, save_*)
- **Individual agent focus**: Individual agents have NO memory tools, only domain-specific tools (5 tools each for metrics, logs, k8s, runbooks)
- **Automatic pattern recognition**: Memory capture happens automatically through hooks, not manual tool calls by individual agents
## Documentation Updates
- **Updated memory-system.md**: Comprehensive design documentation reflecting current implementation
- **Added example analyses**: Created flight-booking-analysis.md and api-response-time-analysis.md in docs/examples/
- **Enhanced README.md**: Added memory system overview and personalized investigation examples
- **Updated .gitignore**: Now ignores entire reports/ folder instead of just .md files
## Implementation Improvements
- **Event ID tracking**: All memory operations generate and log event IDs for verification
- **Pattern extraction confirmation**: Logs confirm pattern extraction working for all agent types
- **Memory save verification**: Comprehensive logging shows successful saves across all memory types
- **Script enhancements**: manage_memories.py now handles duplicate removal and improved user management
* docs: enhance memory system documentation with planning agent memory usage examples
- Add real agent.log snippets showing planning agent retrieving and using memory context
- Document XML-structured prompts for improved Claude model interaction
- Explain JSON response format enforcement and infrastructure knowledge extraction
- Add comprehensive logging and monitoring details
- Document actor ID design for proper memory namespace isolation
- Fix ASCII flow diagram alignment for better readability
- Remove temporal framing and present features as current design facts
* docs: add AWS documentation links and clean up memory system documentation
- Add hyperlink to Amazon Bedrock AgentCore Memory main documentation
- Link to Memory Getting Started Guide for the three memory strategies
- Remove Legacy Pattern Recognition section from documentation (code remains)
- Remove Error Handling and Fallbacks section to focus on core functionality
- Keep implementation details in code while streamlining public documentation
* docs: reorganize memory-system.md to eliminate redundancies
- Merged Memory Tool Architecture and Planning sections into unified section
- Consolidated all namespace/actor_id explanations in architecture section
- Combined pattern recognition and memory capture content
- Created dedicated Agent Memory Integration section with examples
- Removed ~15-20% redundant content while improving clarity
- Improved document structure for better navigation
* style: apply ruff formatting and fix code style issues
- Applied ruff auto-formatting to all Python files
- Fixed 383 style issues automatically
- Remaining issues require manual intervention:
- 29 ruff errors (bare except, unused variables, etc.)
- 61 mypy type errors (missing annotations, implicit Optional)
- Verified memory system functionality matches documentation
- Confirmed user personalization working correctly in reports
* docs: make benefits section more succinct in memory-system.md
- Consolidated 12 bullet points into 5 focused benefits
- Removed redundant three-category structure (Users/Teams/Operations)
- Maintained all key value propositions while improving readability
- Reduced section length by ~60% while preserving essential information
* feat: add comprehensive cleanup script with memory deletion
- Added cleanup.sh script to delete all AWS resources (gateway, runtime, memory)
- Integrated memory deletion using bedrock_agentcore MemoryClient
- Added proper error handling and graceful fallbacks
- Updated execution order: servers → gateway → memory → runtime → local files
- Added memory deletion to README.md cleanup instructions
- Includes confirmation prompts and --force option for automation
* fix: preserve .env, .venv, and reports in cleanup script
- Modified cleanup script to only remove AWS-generated configuration files
- Preserved .env files for development continuity
- Preserved .venv directories to avoid reinstalling dependencies
- Preserved reports/ directory containing investigation history
- Files removed: gateway URIs, tokens, agent ARNs, memory IDs only
- Updated documentation to clarify preserved vs removed files
* fix: use correct bedrock-agentcore-control client for gateway operations
- Changed boto3 client from 'bedrock-agentcore' to 'bedrock-agentcore-control'
- Fixes 'list_gateways' method not found error during gateway deletion
- Both gateway and runtime deletion now use the correct control plane client
* docs: add memory system initialization timing guidance
- Added note that memory system takes 10-12 minutes to be ready
- Added steps to check memory status with list command after 10 minutes
- Added instruction to run update command again once memory is ready
- Provides clear workflow for memory system setup and prevents user confusion
* docs: comprehensive documentation update and cleanup
- Remove unused root .env and .env.example files (not referenced by any code)
- Update configuration.md with comprehensive config file documentation
- Add configuration overview table with setup instructions and auto-generation info
- Consolidate specialized-agents.md content into system-components.md
- Update system-components.md with complete AgentCore architecture
- Add detailed sections for AgentCore Runtime, Gateway, and Memory primitives
- Remove cli-reference.md (excessive documentation for limited use)
- Update README.md to reference configuration guide in setup section
- Clean up documentation links and organization
The documentation now provides a clear, consolidated view of the system
architecture and configuration with proper cross-references and setup guidance.
* feat: improve runtime deployment and invocation robustness
- Increase deletion wait time to 150s for agent runtime cleanup
- Add retry logic with exponential backoff for MCP rate limiting (429 errors)
- Add session_id and user_id to agent state for memory retrieval
- Filter out /ping endpoint logs to reduce noise
- Increase boto3 read timeout to 5 minutes for long-running operations
- Add clear error messages for agent name conflicts
- Update README to clarify virtual environment requirement for scripts
- Fix session ID generation to meet 33+ character requirement
These changes improve reliability when deploying and invoking agents,
especially under heavy load or with complex queries that take time.
* chore: remove accidentally committed reports folder
Removed 130+ markdown report files from the reports/ directory that were
accidentally committed. The .gitignore already includes reports/ to prevent
future commits of these generated files.
* fix: Add AWS_REGION fallback for gateway notebooks
Update AWS_DEFAULT_REGION environment variable setting in AgentCore
gateway notebooks to fall back to AWS_REGION when available,
defaulting to us-east-1 if neither is set.
This change ensures compatibility with different AWS environment
configurations and follows SageMaker best practices.
Files modified:
- 01-tutorials/02-AgentCore-gateway/01-transform-lambda-into-mcp-tools/01-gateway-target-lambda.ipynb
- 01-tutorials/02-AgentCore-gateway/02-transform-apis-into-mcp-tools/02-transform-openapi-into-mcp-tools/01-openapis-into-mcp-api-key.ipynb
- 01-tutorials/02-AgentCore-gateway/02-transform-apis-into-mcp-tools/02-transform-openapi-into-mcp-tools/02-openapis-into-mcp-oauth-enterpris-apis.ipynb
- 01-tutorials/02-AgentCore-gateway/02-transform-apis-into-mcp-tools/03-transform-smithyapis-into-mcp-tools/01-s3-smithy-into-mcp-iam.ipynb
Changed: os.environ['AWS_DEFAULT_REGION'] = 'us-east-1'
To: os.environ['AWS_DEFAULT_REGION'] = os.environ.get('AWS_REGION', 'us-east-1')
* adding requirement files for sm run
* adding requirement files for sm run
* renaming gateway folders
* Remove cell execution output
* renaming gateway folders
* changing pip install for gateway search sample
* remove cell outputs
---------
Co-authored-by: Maira Ladeira Tanke <mttanke@amazon.com>
* Add missing credential_provider_name parameter to config.yaml.example
* Fix get_config function to properly parse YAML values with inline comments
* Enhanced get_config to prevent copy-paste whitespace errors in AWS identifiers
* Improve LLM provider configuration and error handling with bedrock as default
* Add OpenAPI templating system and fix hardcoded regions
* Add backend template build to Readme
* delete old yaml files
* Fix Cognito setup with automation script and missing domain creation steps
* docs: Add EC2 instance port configuration documentation
- Document required inbound ports (443, 8011-8014)
- Include SSL/TLS security requirements
- Add AWS security group best practices
- Provide port usage summary table
* docs: Add hyperlinks to prerequisites in README
- Link EC2 port configuration documentation
- Link IAM role authentication setup
- Improve navigation to detailed setup instructions
* docs: Add BACKEND_API_KEY to configuration documentation
- Document gateway environment variables section
- Add BACKEND_API_KEY requirement for credential provider
- Include example .env file format for gateway directory
- Explain usage in create_gateway.sh script
* docs: Add BACKEND_API_KEY to deployment guide environment variables
- Include BACKEND_API_KEY in environment variables reference table
- Mark as required for gateway setup
- Provide quick reference alongside other required variables
* docs: Add BedrockAgentCoreFullAccess policy and trust policy documentation
- Document AWS managed policy BedrockAgentCoreFullAccess
- Add trust policy requirements for bedrock-agentcore.amazonaws.com
- Reorganize IAM permissions for better clarity
- Remove duplicate trust policy section
- Add IAM role requirement to deployment prerequisites
* docs: Document role_name field in gateway config example
- Explain that role_name is used to create and manage the gateway
- Specify BedrockAgentCoreFullAccess policy requirement
- Note trust policy requirement for bedrock-agentcore.amazonaws.com
- Improve clarity for gateway configuration setup
* docs: Add AWS IP address ranges for production security enhancement
- Document AWS IP ranges JSON download for restricting access
- Reference official AWS documentation for IP address ranges
- Provide security alternatives to 0.0.0.0/0 for production
- Include examples of restricted security group configurations
- Enable egress filtering and region-specific access control
* style: Format Python code with black
- Reformat 14 Python files for consistent code style
- Apply PEP 8 formatting standards
- Improve code readability and maintainability
* docs: Update SRE agent prerequisites and setup documentation
- Convert prerequisites section to markdown table format
- Add SSL certificate provider examples (no-ip.com, letsencrypt.org)
- Add Identity Provider (IDP) requirement with setup_cognito.sh reference
- Clarify that all prerequisites must be completed before setup
- Add reference to domain name and cert paths needed for BACKEND_DOMAIN
- Remove Managing OpenAPI Specifications section (covered in use-case setup)
- Add Deployment Guide link to Development to Production section
Addresses issues #171 and #174
* fix: Replace 'AWS Bedrock' with 'Amazon Bedrock' in SRE agent files
- Updated error messages in llm_utils.py
- Updated comments in both .env.example files
- Ensures consistent naming convention across SRE agent codebase
---------
Co-authored-by: dheerajoruganty <dheo@amazon.com>
Co-authored-by: Amit Arora <aroraai@amazon.com>
It should be
"ecr:BatchGetImage",
"ecr:GetDownloadUrlForLayer"
rather than:
"ecr: BatchGetImage",
"ecr: GetDownloadUrlForLayer"
There is an extrac space
Signed-off-by: Dustin Liu <liucong.haonan@gmail.com>
