What's Changed

• feat(hooks): accept callable hook callbacks in Agent constructor by @agent-of-mkmeral in #1992
• fix: handle missing optional fields in non-streaming citation conversion by @agent-of-mkmeral in #2098
• fix(telemetry): add common gen_ai attributes to event loop cycle spans by @giulio-leone in #1973
• fix(telemetry): use per-invocation usage in agent span attributes by @en-yao in #2017
• feat(a2a): add client_config param and deprecate a2a_client_factory by @agent-of-mkmeral in #2103
• fix: clear leaked running loop in MCP client background thread by @mkmeral in #2111
• feat(openai): plumb through cache tokens in metadata events by @Unshure in #2116
• feat(agent): add take_snapshot() and load_snapshot() methods by @zastrowm in #1948
• feat(skills): support loading skills from URLs by @dgallitelli in #2091
• feat: add metadata field to messages for stateful context tracking by @lizradway in #2125
• feat(bidi): support request_state stop_event_loop flag by @agent-of-mkmeral in #1954
• fix: preserve Gemini thought_signature in LiteLLM multi-turn tool calls by @opieter-aws in #2129
• fix(bedrock): normalize empty toolResult content arrays in _format_bedrock_messages by @ghhamel in #2123
• fix(telemetry): remove force_flush in tracer by @poshinchen in #2142

New Contributors

• @en-yao made their first contribution in #2017
• @ghhamel made their first contribution in #2123

Full Changelog: v1.35.0...v1.36.0

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

What's Changed

• fix: fix type imcompatible by @JackYPCOnline in #2018
• fix: isolate langfuse env vars by @lizradway in #2022
• fix: restore explicit span.end() to fix span end_time regression by @zastrowm in #2032
• feat(context): track context tokens by @lizradway in #2009

Full Changelog: v1.34.0...v1.34.1

What's Changed

• chore: remove Cohere from required integ test providers by @zastrowm in #1967
• feat: add AgentAsTool by @notowen333 in #1932
• feat: auto-wrap Agent instances passed in tools list by @agent-of-mkmeral in #1997
• feat(telemetry): emit system prompt on chat spans per GenAI semconv by @sanjeed5 in #1818
• feat(mcp): add support for MCP elicitation -32042 error handling by @Christian-kam in #1745
• fix: ollama input/output token count by @lizradway in #2008
• feat: add stateful model support for server-side conversation management by @pgrayy in #2004
• feat: add built-in tool support for OpenAI Responses API by @pgrayy in #2011
• fix: handle reasoning content in OpenAIResponsesModel request formatting by @pgrayy in #2013

New Contributors

• @notowen333 made their first contribution in #1932
• @agent-of-mkmeral made their first contribution in #1997
• @sanjeed5 made their first contribution in #1818
• @Christian-kam made their first contribution in #1745

Full Changelog: v1.33.0...v1.34.0

Pins litellm<=1.82.6 to supply chain attack - S​upply Chain Attack in litellm 1.82.8 on PyPI

What's Changed

• fix: summarization conversation manager sometimes returns empty response by @Unshure in #1947
• fix: remove agent from swarm test to get more consistency out of it by @Unshure in #1946
• fix: CRITICAL: Hard pin litellm<=1.82.6 to mitigate supply chain attack by @udaymehta in #1961

New Contributors

• @udaymehta made their first contribution in #1961

Full Changelog: v1.32.0...v1.33.0

What's Changed

• fix(event-loop): ensure all cycle metrics include end time and duration by @stephentreacy in #1903
• fix: pin upper bound for mistralai dependency by @mkmeral in #1935
• fix: override end_turn stop reason when streaming response contains toolUse blocks by @atian8179 in #1827

New Contributors

• @stephentreacy made their first contribution in #1903
• @atian8179 made their first contribution in #1827

Full Changelog: v1.31.0...v1.32.0

What's Changed

• feat: pass A2A request context metadata as invocation state by @mkmeral in #1854
• fix: s3session manager bug by @mehtarac in #1915
• fix(graph): only evaluate outbound edges from completed nodes by @giulio-leone in #1846
• fix(openai): always use string content for tool messages by @giulio-leone in #1878
• feat: widen openai dependency to support 2.x for litellm compatibility by @BV-Venky in #1793
• fix: typeError when serializing multimodal prompts with binary content in Graph/Swarm session persistence by @JackYPCOnline in #1870
• fix: lowercase the python language in code snippet by @zastrowm in #1929
• fix: openai repsonses api error handling by @Unshure in #1931

New Contributors

• @BV-Venky made their first contribution in #1793

Full Changelog: v1.30.0...v1.31.0

What's Changed

• feat: add "anthropic" cache strategy to bypass model ID check by @kevmyung in #1808
• feat: serialize tool results as JSON when possible by @clareliguori in #1752
• fix: summary manager using structured output by @pgrayy in #1805
• feat(mcp): expose server instructions from InitializeResult on MCPClient by @ShotaroKataoka in #1814
• fix: added LANGFUSE_BASE_URL check for additinoal attribute by @poshinchen in #1826
• feat(session): add dirty flag to skip unnecessary agent state persistence by @Unshure in #1803
• feat: add public tool_spec setter by @mkmeral in #1822
• feat: add CancellationToken for graceful agent execution cancellation by @jgoyani1 in #1772
• feat(session): optimize session manager initialization by @Unshure in #1829
• fix(mistral): report usage metrics in streaming mode by @jackatorcflo in #1697
• fix(openai_responses): use output_text for assistant messages in multi-turn conversations by @giulio-leone in #1851
• feat(hooks): add resume flag to AfterInvocationEvent by @mkmeral in #1767
• fix: place cache point on last user message instead of assistant by @kevmyung in #1821
• feat(skills): add agent skills as a plugin by @mkmeral in #1755
• feat(steering): move steering from experimental to production by @dbschmigelski in #1853
• fix: break circular references so Agent cleanup doesn't hang with MCPClient by @dbschmigelski in #1830
• fix: Set is_new_session = False at the end of each initialize* method by @mehtarac in #1859

New Contributors

• @ShotaroKataoka made their first contribution in #1814
• @jgoyani1 made their first contribution in #1772
• @jackatorcflo made their first contribution in #1697
• @giulio-leone made their first contribution in #1851

Full Changelog: v1.29.0...v1.30.0

What's Changed

• test: pin virtualenv to <21 for hatch bug by @clareliguori in #1771
• fix(telemetry): added latest semantic conventions as span attributes for langfuse by @poshinchen in #1768
• fix: preserve guardrail_latest_message wrapping after tool execution by @austinmw in #1658
• feat(conversation-manager): improve tool result truncation strategy by @kevmyung in #1756
• feat(plugins): improve plugin creation devex with @hook and @tool decorators by @Unshure in #1740
• ci: bump actions/upload-artifact from 6 to 7 by @dependabot[bot] in #1777
• ci: bump actions/download-artifact from 7 to 8 by @dependabot[bot] in #1776
• fix: throw exceptions from ConcurrentToolExecutor (#1796) by @charles-dyfis-net in #1797
• feat: add OpenAI Responses API model implementation by @notgitika in #975

New Contributors

• @austinmw made their first contribution in #1658

Full Changelog: v1.28.0...v1.29.0

What's Changed

• fix: update region for agentcore in our new account by @afarntrog in #1715
• fix: remove test that fails for python 3.14 by @Unshure in #1717
• feat(hooks): support union types and list of types for add_hook by @Unshure in #1719
• feat: make pyaudio an optional dependency by lazy loading by @mehtarac in #1731
• feat(hooks): add Plugin Protocol for agent extensibility by @Unshure in #1733
• feat: add plugins parameter to Agent by @Unshure in #1734
• refactor(plugins): convert Plugin from Protocol to ABC by @Unshure in #1741
• feat(steering): migrate SteeringHandler from HookProvider to Plugin by @Unshure in #1738
• chore: switch to Sonnet 4.6 for Anthropic provider integ tests by @clareliguori in #1754
• fix: rename init_plugin to init_agent by @Unshure in #1765

Full Changelog: v1.27.0...v1.28.0