version: 发布1.0.0版本

Author: raylchen

CHANGELOG.md

@@ -1 +1,20 @@
-# Change Log
+# Changelog
+
+## [1.0.0](https://github.com/trpc-group/trpc-agent-python/releases/tag/v1.0.0) (2026-04-06)
+
+### Features
+
+* Unified Agent framework with `LlmAgent`, `LangGraphAgent` and `TransferAgent`
+* Multi-agent orchestration with built-in `Chain`, `Parallel`, and `Cycle` patterns, plus Team and nested Team collaboration
+* Human-in-the-loop workflows with pause, review, and resume support for long-running tasks
+* Rich tool ecosystem including built-in file/shell tools, MCP tools, LangChain tools, and extensible third-party integrations
+* Extensible Skill system with local and HTTP distribution, dynamic loading, timeout control, and sandbox execution
+* Code execution support with async runtime and sandbox/container execution options
+* Session and memory services with in-memory, Redis, and SQL backends, including filtering, summarization, and scheduled cleanup
+* RAG and knowledge capabilities through `LangchainKnowledge` with loaders, splitters, embedders, vector stores, retrievers, and prompt templates
+* Evaluation framework with trajectory and response quality assessment, LLM-judge metrics, parallel evaluation, and JSON reporting
+* Service and protocol integrations for A2A, AG-UI, and OpenClaw runtime scenarios
+* OpenClaw runtime capabilities for gateway/chat/ui/deps workflows with pluggable channels, tools, skills, session and memory integration
+* OpenClaw skill dependency management with profile-based inspection and install planning for common runtime environments
+* Observability via tracing support, including end-to-end execution flow, tool-call traces, and cancellation traces
+* Developer experience support with practical examples and DebugServer for local development and validation

dist_pkg.sh

@@ -19,6 +19,6 @@ pip3 install twine
 python -m build
 
 
-twine upload dist/* -r tencent
+twine upload --repository pypi dist/*
 
 

pyproject.toml

@@ -12,9 +12,7 @@ description = "Python LLM agent framework with multi-model support (OpenAI, Anth
 readme = "README.md"
 requires-python = ">=3.10"
 license = {text = "Apache-2.0"}
-authors = [
-    {name = "Tencent", email = "team@tencent.com"}
-]
+authors = [{ name = "Tencent", email = "raylchen@tencent.com" }]
 keywords = ["trpc", "agent", "llm", "ai", "langchain", "langgraph", "mcp", "a2a", "fastapi", "multi-agent", "tool-calling"]
 classifiers = [
     "Development Status :: 3 - Alpha",

run_examples_from_streaming_tool_complex.py

@@ -9,4 +9,4 @@
 This module defines the version information for TRPC Agent
 """
 
-__version__ = '0.1.0'
+__version__ = '1.0.0'