strands-agents/sdk-python v1.35.0

on GitHub

What's Changed

Features

Bedrock Service Tier Support — PR#1799

Amazon Bedrock now offers service tiers (Priority, Standard, Flex) that let you control the trade-off between latency and cost on a per-request basis. BedrockModel accepts a new service_tier configuration field, consistent with how other Bedrock-specific features like guardrails are exposed. When not set, the field is omitted and Bedrock uses its default behavior.

from strands import Agent
from strands.models.bedrock import BedrockModel

# Use "flex" tier for cost-optimized batch processing
model = BedrockModel(
    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
    service_tier="flex",
)
agent = Agent(model=model)

# Use "priority" for latency-sensitive applications
realtime_model = BedrockModel(
    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
    service_tier="priority",
)

Valid values are "default", "priority", and "flex". If a model or region does not support the specified tier, Bedrock returns a ValidationException.

Bug Fixes

• Sliding window conversation manager user-first enforcement — PR#2087: The sliding window could produce a trimmed conversation starting with an assistant message, causing ValidationException on providers that require user-first ordering (including Bedrock Nova). The trim-point validation now ensures the first remaining message always has role == "user". Also fixed a short-circuit logic bug in the toolUse guard that let orphaned tool-use blocks slip through at window boundaries.

• MCP _meta forwarding — PR#1918, PR#2081: Custom metadata per the MCP spec was silently dropped because MCPClient never forwarded the _meta field to ClientSession.call_tool(). Additionally, the OTEL instrumentation used model_dump() instead of model_dump(by_alias=True), serializing the field as "meta" instead of "_meta" and corrupting the payload. Both the direct call_tool and task-augmented execution paths now correctly forward meta.

• Tool exception propagation to OpenTelemetry spans — PR#2046: When a tool raised an exception, the original exception was dropped before reaching end_tool_call_span, causing all tool spans to get StatusCode.OK even on errors. Tool errors now correctly propagate with StatusCode.ERROR, preserving the original exception type and traceback for observability backends like Langfuse.

• Anthropic premature stream termination — PR#2047: The Anthropic provider crashed with AttributeError when the stream terminated before the final message_stop event, because it accessed event.message.usage on event types that lack a .message attribute. Now uses the Anthropic SDK's stream.get_final_message() to read accumulated usage from all received events, gracefully handling premature termination and empty streams.

• Anthropic Pydantic deprecation warnings — PR#2044: Fixed message_stop event handling to avoid Pydantic deprecation warnings.

New Contributors

• @mananpatel320 made their first contribution in #1918
• @opieter-aws made their first contribution in #2044
• @mattdai01 made their first contribution in #2046
• @KKamJi98 made their first contribution in #1906
• @gautamsirdeshmukh made their first contribution in #2047

Full Changelog: v1.34.1...v1.35.0