Skip to content

Feat/agui strands pattern#62

Draft
razkenari wants to merge 2 commits intomainfrom
feat/agui-strands-pattern
Draft

Feat/agui strands pattern#62
razkenari wants to merge 2 commits intomainfrom
feat/agui-strands-pattern

Conversation

@razkenari
Copy link
Contributor

@razkenari razkenari commented Mar 20, 2026 •
edited
Loading

Summary

Adds AG-UI protocol support to FAST with two new agent patterns (agui-strands-agent, agui-langgraph-agent), a shared frontend parser, and restructures the project layout for consistency across all patterns.

Changes

Commit 1: Restructure agent patterns and shared modules

  • Rename patterns/ → agent_patterns/, gateway/ → agentcore_gateway/, tools/ → agentcore_tools/
  • Rewrite strands-agent and langgraph-agent with consistent structure — each pattern now has its own tools/ module (gateway, code_interpreter) and imports shared utilities from utils/
  • Pin all Python dependency versions with == in requirements.txt
  • Fix existing ruff lint issues (import sorting, unused variables, f-string without placeholders)

Commit 2: Add AG-UI agent patterns and frontend support

  • agui-strands-agent: Strands agent wrapped with ag-ui-strands (StrandsAgent). Creates agent per-request to ensure correct Memory scoping and fresh MCP connections.
  • agui-langgraph-agent: LangGraph agent wrapped with copilotkit (LangGraphAGUIAgent). Uses ActorAwareLangGraphAgent subclass to rebuild the graph per-request for fresh Gateway tokens.
  • Frontend AG-UI parser (parsers/agui.ts): Maps AG-UI events (TEXT_MESSAGE_CONTENT, TOOL_CALL_START, etc.) to the shared StreamEvent types. Auto-selected for any pattern with agui- prefix.
  • AG-UI payload format: AgentCoreClient.invoke() automatically sends RunAgentInput (threadId, messages, runId) for agui-* patterns.
  • Documentation: docs/AGUI_INTEGRATION.md — covers architecture, patterns, frontend integration, deployment, and CopilotKit reference.
  • Bump CDK dependencies (@aws-cdk/aws-bedrock-agentcore-alpha, @aws-cdk/aws-bedrock-alpha)
  • Add AGUI protocol comments in backend-stack.ts and config.yaml

Key design decisions

  • Both AG-UI patterns use BedrockAgentCoreApp as the entrypoint (not standalone FastAPI), so AgentCore Runtime headers (WorkloadAccessToken, Authorization, Session-Id) are available for Gateway auth, Memory, and secure user identity extraction from JWT.
  • AG-UI patterns deploy with HTTP protocol — AgentCore Runtime's AGUI protocol flag only changes error formatting (RUN_ERROR events vs HTTP error codes). The agent container handles AG-UI event formatting internally.
  • One parser for all AG-UI patterns — both Strands and LangGraph AG-UI wrappers produce standard AG-UI events, so a single parseAguiChunk parser handles both.
  • CopilotKit kept separate — CopilotKit is referenced in docs as an optional richer frontend.

Testing

  • Deployed and validated both agui-strands-agent and agui-langgraph-agent patterns end-to-end (CDK deploy → AgentCore Runtime → Amplify frontend)
  • Verified: text streaming, tool calls (Gateway + Code Interpreter), Memory persistence, user identity extraction

@github-actions
Copy link

github-actions bot commented Mar 20, 2026 •
edited
Loading

Latest scan for commit: b0c7223 | Updated: 2026-03-21 18:00:30 UTC

Security Scan Results

Scan Metadata

  • Project: ASH
  • Scan executed: 2026-03-21T18:00:15+00:00
  • ASH version: 3.2.2

Summary

Scanner Results

The table below shows findings by scanner, with status based on severity thresholds and dependencies:

Column Explanations:

Severity Levels (S/C/H/M/L/I):

  • Suppressed (S): Security findings that have been explicitly suppressed/ignored and don't affect the scanner's pass/fail status
  • Critical (C): The most severe security vulnerabilities requiring immediate remediation (e.g., SQL injection, remote code execution)
  • High (H): Serious security vulnerabilities that should be addressed promptly (e.g., authentication bypasses, privilege escalation)
  • Medium (M): Moderate security risks that should be addressed in normal development cycles (e.g., weak encryption, input validation issues)
  • Low (L): Minor security concerns with limited impact (e.g., information disclosure, weak recommendations)
  • Info (I): Informational findings for awareness with minimal security risk (e.g., code quality suggestions, best practice recommendations)

Other Columns:

  • Time: Duration taken by each scanner to complete its analysis
  • Action: Total number of actionable findings at or above the configured severity threshold that require attention

Scanner Results:

  • PASSED: Scanner found no security issues at or above the configured severity threshold - code is clean for this scanner
  • FAILED: Scanner found security vulnerabilities at or above the threshold that require attention and remediation
  • MISSING: Scanner could not run because required dependencies/tools are not installed or available
  • SKIPPED: Scanner was intentionally disabled or excluded from this scan
  • ERROR: Scanner encountered an execution error and could not complete successfully

Severity Thresholds (Thresh Column):

  • CRITICAL: Only Critical severity findings cause scanner to fail
  • HIGH: High and Critical severity findings cause scanner to fail
  • MEDIUM (MED): Medium, High, and Critical severity findings cause scanner to fail
  • LOW: Low, Medium, High, and Critical severity findings cause scanner to fail
  • ALL: Any finding of any severity level causes scanner to fail

Threshold Source: Values in parentheses indicate where the threshold is configured:

  • (g) = global: Set in the global_settings section of ASH configuration
  • (c) = config: Set in the individual scanner configuration section
  • (s) = scanner: Default threshold built into the scanner itself

Statistics calculation:

  • All statistics are calculated from the final aggregated SARIF report
  • Suppressed findings are counted separately and do not contribute to actionable findings
  • Scanner status is determined by comparing actionable findings to the threshold
Scanner S C H M L I Time Action Result Thresh
bandit 0 0 0 0 0 0 701ms 0 PASSED MED (g)
cdk-nag 0 0 0 0 0 0 41.4s 0 PASSED MED (g)
cfn-nag 0 0 0 0 0 0 590ms 0 PASSED MED (g)
checkov 0 0 0 0 0 0 6.5s 0 PASSED MED (g)
detect-secrets 0 0 0 0 0 0 1.0s 0 PASSED MED (g)
grype 0 1 0 1 0 0 43.8s 2 FAILED MED (g)
npm-audit 0 0 0 0 0 0 1.1s 0 PASSED MED (g)
opengrep 0 9 0 0 0 0 28.9s 9 FAILED MED (g)
semgrep 0 9 0 0 0 0 20.4s 9 FAILED MED (g)
syft 0 0 0 0 0 0 2.3s 0 PASSED MED (g)

Detailed Findings

Show 20 actionable findings

Finding 1: python.jwt.security.unverified-jwt-decode.unverified-jwt-decode

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: python.jwt.security.unverified-jwt-decode.unverified-jwt-decode
  • Location: agent_patterns/utils/auth.py:66

Description:
Detected JWT token decoded with 'verify=False'. This bypasses any integrity checks for the token which means the token could be tampered with by malicious actors. Ensure that the JWT token is verified.

Code Snippet:

options={"verify_signature": False},

Finding 2: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:126

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const patternDir = path.join(repoRoot, "patterns", pattern)

Finding 3: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:154

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const content = fs.readFileSync(path.join(patternDir, file))

Finding 4: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:154

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const content = fs.readFileSync(path.join(patternDir, file))

Finding 5: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:168

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const requirementsPath = path.join(patternDir, "requirements.txt")

Finding 6: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1005

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const fullPath = path.join(dirPath, entry.name)

Finding 7: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1005

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const fullPath = path.join(dirPath, entry.name)

Finding 8: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1006

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const relativePath = path.join(prefix, entry.name)

Finding 9: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: semgrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1006

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const relativePath = path.join(prefix, entry.name)

Finding 10: python.jwt.security.unverified-jwt-decode.unverified-jwt-decode

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: python.jwt.security.unverified-jwt-decode.unverified-jwt-decode
  • Location: agent_patterns/utils/auth.py:66

Description:
Detected JWT token decoded with 'verify=False'. This bypasses any integrity checks for the token which means the token could be tampered with by malicious actors. Ensure that the JWT token is verified.

Code Snippet:

options={"verify_signature": False},

Finding 11: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:126

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const patternDir = path.join(repoRoot, "patterns", pattern)

Finding 12: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:154

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const content = fs.readFileSync(path.join(patternDir, file))

Finding 13: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:154

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const content = fs.readFileSync(path.join(patternDir, file))

Finding 14: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:168

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const requirementsPath = path.join(patternDir, "requirements.txt")

Finding 15: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1005

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const fullPath = path.join(dirPath, entry.name)

Finding 16: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1005

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const fullPath = path.join(dirPath, entry.name)

Finding 17: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1006

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const relativePath = path.join(prefix, entry.name)

Finding 18: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal

  • Severity: HIGH
  • Scanner: opengrep
  • Rule ID: javascript.lang.security.audit.path-traversal.path-join-resolve-traversal.path-join-resolve-traversal
  • Location: infra-cdk/lib/backend-stack.ts:1006

Description:
Detected possible user input going into a path.join or path.resolve function. This could possibly lead to a path traversal vulnerability, where the attacker can access arbitrary files stored in the file system. Instead, be sure to sanitize or validate user input first.

Code Snippet:

const relativePath = path.join(prefix, entry.name)

Finding 19: GHSA-8gc5-j5rx-235r-fast-xml-parser

  • Severity: HIGH
  • Scanner: grype
  • Rule ID: GHSA-8gc5-j5rx-235r-fast-xml-parser
  • Location: infra-cdk/package-lock.json:1

Description:
A high vulnerability in npm package: fast-xml-parser, version 5.4.1 was found at: /infra-cdk/package-lock.json

Finding 20: GHSA-jp2q-39xq-3w4g-fast-xml-parser

  • Severity: MEDIUM
  • Scanner: grype
  • Rule ID: GHSA-jp2q-39xq-3w4g-fast-xml-parser
  • Location: infra-cdk/package-lock.json:1

Description:
A medium vulnerability in npm package: fast-xml-parser, version 5.4.1 was found at: /infra-cdk/package-lock.json

Report generated by Automated Security Helper (ASH) at 2026-03-21T18:00:09+00:00

@razkenari razkenari force-pushed the feat/agui-strands-pattern branch from c025e1c to a82de42 Compare March 21, 2026 17:15
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Mar 21, 2026
@razkenari razkenari force-pushed the feat/agui-strands-pattern branch 4 times, most recently from 319df32 to 5a790aa Compare March 21, 2026 17:45
@razkenari
refactor: restructure agent patterns and shared modules
58607ba 
- Rename patterns/ to agent_patterns/, gateway/ to agentcore_gateway/, tools/ to agentcore_tools/
- Rewrite strands-agent and langgraph-agent with consistent structure
- Extract gateway and code interpreter tools into per-pattern tools/ modules
- Pin all dependency versions in requirements.txt
@razkenari
feat: add AG-UI agent patterns and frontend support
b0c7223 
- Add agui-langgraph-agent and agui-strands-agent patterns with AG-UI protocol
- Add AG-UI streaming parser for frontend client
- Add AGUI pattern comments and bump CDK dependencies in infra-cdk
@razkenari razkenari force-pushed the feat/agui-strands-pattern branch from 5a790aa to b0c7223 Compare March 21, 2026 17:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

backend docker documentation Improvements or additions to documentation frontend infrastructure

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@razkenari