v1.22.0

[zastrowm]

Release notes: https://github.com/strands-agents/sdk-python/releases/tag/v1.22.0

Major Features

MCP Resource Operations - PR#1117

The MCP client now supports resource operations, enabling agents to list, read, and work with resources provided by MCP servers. This includes static resources, binary resources, and parameterized resource templates.

from strands.tools.mcp import MCPClient

with MCPClient(server_transport) as client:
    # List available resources
    resources = client.list_resources_sync()
    for resource in resources.resources:
        print(f"Resource: {resource.name} at {resource.uri}")
    
    # Read a specific resource
    content = client.read_resource_sync("file://documents/report.txt")
    text = content.contents[0].text
    
    # List resource templates (parameterized resources)
    templates = client.list_resource_templates_sync()
    for template in templates.resourceTemplates:
        print(f"Template: {template.uriTemplate}")

Bedrock Guardrails Latest Message Option - PR#1224

Bedrock models now support the guardrail_latest_message parameter, which sends only the latest user message to AWS Bedrock Guardrails for evaluation instead of the entire conversation history. This reduces token usage and enables conversation recovery after guardrail interventions.

from strands.models.bedrock import BedrockModel

model = BedrockModel(
    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
    guardrail_id="your-guardrail-id",
    guardrail_version="DRAFT",
    guardrail_latest_message=True  # Only evaluate the latest user message
)

See the Bedrock Guardrails documentation for more details.

LiteLLM Non-Streaming Support - PR#512

The LiteLLM model provider now correctly handles non-streaming responses, fixing an issue where stream=False would raise an error. Both streaming and non-streaming modes now work seamlessly.

from strands.models.litellm import LiteLLMModel

# Use non-streaming mode for simpler response handling
model = LiteLLMModel(
    model_id="gpt-3.5-turbo",
    params={"stream": False}
)

# Works correctly now - no more ValueError
agent = Agent(model=model)
result = agent("What is 2+2?")

---

Major Bug Fixes

• Concurrent Agent Invocations - PR#1453
  Fixed critical agent state corruption when multiple concurrent invocations occurred on the same agent instance. A new ConcurrencyException is now raised to prevent concurrent invocations and protect agent state integrity.

• Gemini Empty Stream Handling - PR#1420
  Fixed UnboundLocalError crash when Gemini returns an empty event stream by properly initializing variables before the stream loop.

• Deprecation Warning on Import - PR#1380
  Fixed unwanted deprecation warnings appearing when importing strands by using lazy __getattr__ to emit warnings only when deprecated aliases are actually accessed.

---

What's Changed

• docs: update github agent action to reference S3_SESSION_BUCKET by @dbschmigelski in docs: update github agent action to reference S3_SESSION_BUCKET #1418
• feat: provide extra command content as the the prompt to the agent by @zastrowm in feat: provide extra command content as the the prompt to the agent #1419
• [FEATURE] add MCP resource operations in MCP Tools by @xiehust in [FEATURE] add MCP resource operations in MCP Tools #1117
• fix: import errors for models with optional imports by @mehtarac in fix: import errors for models with optional imports #1384
• add BidiGeminiLiveModel and BidiOpenAIRealtimeModel to the init by @mehtarac in add BidiGeminiLiveModel and BidiOpenAIRealtimeModel to the init #1383
• bidi - async - remove cancelling call by @pgrayy in bidi - async - remove cancelling call #1357
• feat(bedrock): add guardrail_latest_message option by @aiancheruk in feat(bedrock): add guardrail_latest_message option #1224
• fix(gemini): UnboundLocal Exception Fix by @emattiza in fix(gemini): UnboundLocal Exception Fix #1420
• fix! Litellm handle non streaming response fix for issue [BUG] LiteLLM + disable streaming breaks for Azure OpenAI #477 by @schleidl in fix! Litellm handle non streaming response fix for issue #477 #512
• feat(agent-interface): introduce AgentBase Protocol as the interface for agent classes to implement by @awsarron in feat(agent-interface): introduce AgentBase Protocol as the interface for agent classes to implement #1126
• ci: update pytest requirement from <9.0.0,>=8.0.0 to >=8.0.0,<10.0.0 in the dev-dependencies group by @dependabot[bot] in ci: update pytest requirement from <9.0.0,>=8.0.0 to >=8.0.0,<10.0.0 in the dev-dependencies group #1161
• feat: pass invocation_state to model providers by @tirth14 in feat: pass invocation_state to model providers #1414
• Add Security.md file by @yonib05 in Add Security.md file #1454
• chore: Update release notes sop by @zastrowm in chore: Update release notes sop #1456
• fix(integ): make calculator tool more robust to LLM output variations by @cagataycali in fix(integ): make calculator tool more robust to LLM output variations #1445
• fix: resolve string formatting error in MCP client error handling by @cagataycali in fix: resolve string formatting error in MCP client error handling #1446
• bidi - move 3.12 check to nova sonic module by @pgrayy in bidi - move 3.12 check to nova sonic module #1439
• ci: update sphinx requirement from <9.0.0,>=5.0.0 to >=5.0.0,<10.0.0 by @dependabot[bot] in ci: update sphinx requirement from <9.0.0,>=5.0.0 to >=5.0.0,<10.0.0 #1426
• fix: add concurrency protection to prevent parallel invocations from corrupting agent state by @zastrowm in fix: add concurrency protection to prevent parallel invocations from corrupting agent state #1453
• fix(mcp): propagate contextvars to background thread by @cagataycali in fix(mcp): propagate contextvars to background thread #1444
• Update to opus 4.5 by @Unshure in Update to opus 4.5 #1471

New Contributors

• @aiancheruk made their first contribution in feat(bedrock): add guardrail_latest_message option #1224
• @emattiza made their first contribution in fix(gemini): UnboundLocal Exception Fix #1420
• @schleidl made their first contribution in fix! Litellm handle non streaming response fix for issue #477 #512
• @tirth14 made their first contribution in feat: pass invocation_state to model providers #1414

Full Changelog: v1.21.0...v1.22.0