Skip to content

loongsuite-python 0.7.0

Choose a tag to compare

View all tags
@sipercai sipercai released this 03 Jul 08:23
v0.7.0
2908834

loongsuite-python 0.7.0

Installation

pip install loongsuite-distro==0.7.0
loongsuite-bootstrap -a install --version 0.7.0

Package Versions

  • loongsuite-* packages: 0.7.0
  • opentelemetry-* packages: 0.60b1

PyPI packages

The following distributions are built and uploaded to PyPI for this release:

  • loongsuite-otel-util-genai
  • loongsuite-distro
  • loongsuite-site-bootstrap
  • loongsuite-instrumentation-agentscope
  • loongsuite-instrumentation-algotune
  • loongsuite-instrumentation-autogen
  • loongsuite-instrumentation-bfclv4
  • loongsuite-instrumentation-claude-agent-sdk
  • loongsuite-instrumentation-claw-eval
  • loongsuite-instrumentation-crewai
  • loongsuite-instrumentation-dashscope
  • loongsuite-instrumentation-deepagents
  • loongsuite-instrumentation-google-adk
  • loongsuite-instrumentation-hermes-agent
  • loongsuite-instrumentation-langchain
  • loongsuite-instrumentation-langgraph
  • loongsuite-instrumentation-litellm
  • loongsuite-instrumentation-mem0
  • loongsuite-instrumentation-microsoft-agent-framework
  • loongsuite-instrumentation-minisweagent
  • loongsuite-instrumentation-openhands
  • loongsuite-instrumentation-qwen-agent
  • loongsuite-instrumentation-qwenpaw
  • loongsuite-instrumentation-slop-code
  • loongsuite-instrumentation-terminus2
  • loongsuite-instrumentation-vita
  • loongsuite-instrumentation-webarena
  • loongsuite-instrumentation-widesearch
  • loongsuite-instrumentation-wildtool

loongsuite-otel-util-genai

Added

  • Propagate agent name through the gen_ai.agent.name Baggage key during
    start_invoke_agent and automatically apply it to nested GenAI child span
    attributes, including LLM, embedding, tool, retrieval, rerank, memory, entry,
    and ReAct step invocations.

loongsuite-instrumentation-agentscope

Added

  • Add version-aware AgentScope v2 middleware instrumentation while preserving
    AgentScope v1 compatibility.

loongsuite-instrumentation-agno

Removed

  • Remove the direct pydantic runtime dependency from Agno instrumentation.

loongsuite-instrumentation-autogen

Added

  • Add Microsoft AutoGen 0.7.x AgentChat instrumentation.
  • Normalize AutoGen native invoke_agent, create_agent, and execute_tool
    spans to LoongSuite GenAI semantic attributes.
  • Add AgentChat LLM spans via opentelemetry-util-genai
    ExtendedTelemetryHandler.

loongsuite-instrumentation-claude-agent-sdk

Added

  • Capture gen_ai.skill.name, gen_ai.skill.id, gen_ai.skill.description
    and gen_ai.skill.version on the execute_tool span of the built-in
    Skill tool. Skill metadata is read best-effort from the project-level
    SKILL.md frontmatter (located via SystemMessage.data.cwd); skill.id
    is reported as claude:project:<skill-name>. Metadata read failures never
    affect the SDK call.

Fixed

  • Capture Claude Agent SDK session IDs on agent, LLM, and tool spans, and
    preserve active caller context so SDK traces attach to existing caller spans
    instead of being forced to independent roots.

loongsuite-instrumentation-crewai

Fixed

  • Keep the authentication-failure test deterministic by using fake provider
    keys instead of empty keys, avoiding fallback live OpenAI calls in CI. (#232)

loongsuite-instrumentation-dashscope

Fixed

  • Capture image and video URI outputs from MultiModalConversation responses.

loongsuite-instrumentation-deepagents

Added

  • Initial DeepAgents instrumentation that marks create_deep_agent graphs so
    LangChain instrumentation emits an AGENT span for the DeepAgents root.
  • DeepAgents skill-load telemetry: when an agent reads a registered skill's
    top-level SKILL.md through the built-in read_file tool, the tool span
    carries gen_ai.skill.name, gen_ai.skill.id,
    gen_ai.skill.description, and gen_ai.skill.version.

loongsuite-instrumentation-hermes-agent

Fixed

  • Create Hermes ENTRY spans for platform-less AIAgent calls by mirroring
    Hermes session source resolution: platform, HERMES_SESSION_SOURCE, then
    cli. This changes no-platform runs from AGENT-only to ENTRY -> AGENT
    while leaving explicit CLI, IM, TUI, and API Server platform paths unchanged;
    disable the Hermes instrumentation if a process must keep no-platform top
    level agent calls as AGENT-only.

loongsuite-instrumentation-langchain

Added

  • Detect DeepAgents skill loads from read_file tool calls that read a
    registered skill's top-level SKILL.md, and populate gen_ai.skill.*
    attributes on the resulting execute_tool span.

Changed

  • Capture OpenAI-style LangGraph and DeepAgents message dictionaries as
    gen_ai.input.messages on root AGENT spans.
  • Preserve structured LangChain tool call arguments when tool inputs do not use
    input or query, which keeps DeepAgents filesystem read_file arguments
    such as file_path available for skill-load telemetry.

loongsuite-instrumentation-microsoft-agent-framework

Added

  • Add Microsoft Agent Framework instrumentation aligned with LoongSuite GenAI semantic conventions. (#229)

loongsuite-instrumentation-qwen-agent

Fixed

  • Record token usage from Qwen-Agent DashScope response metadata on streaming
    and non-streaming chat spans.
  • Roll up child LLM token usage to Qwen-Agent invoke-agent spans, preserve
    nested agent spans, and record only the final agent answer as output.
Assets 3
Loading