Skip to content

Commit f6aa138

Browse files
SunriseaDavdGao
Sunrisea
and
DavdGao
authored
feat(a2a): support A2A protocol for inter-agent communication (#1027)
--------- Co-authored-by: DavdGao <[email protected]>
1 parent 9a952b7 commit f6aa138

28 files changed

+2468
-72
lines changed

‎.github/workflows/stale.yml‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -21,15 +21,15 @@ jobs:
2121
- uses: actions/stale@v5
2222
with:
2323
repo-token: ${{ secrets.GITHUB_TOKEN }}
24-
stale-issue-message: 'This issue is marked as stale because there has been no activity for 21 days. Remove stale label or add new comments or this issue will be closed in 3 day.'
24+
stale-issue-message: 'This issue is marked as stale because there has been no activity for 60 days. Remove stale label or add new comments or this issue will be closed in 90 day.'
2525
close-issue-message: 'Close this stale issue.'
2626
stale-issue-label: 'stale-issue'
2727
exempt-issue-labels: 'RoadMap,Roadmap'
28-
days-before-stale: 21
29-
days-before-close: 3
28+
days-before-stale: 60
29+
days-before-close: 30
3030

31-
stale-pr-message: 'This PR is marked as stale because there has been no activity for 30 days. Remove stale label or add new comments or this PR will be closed in 5 day.'
31+
stale-pr-message: 'This PR is marked as stale because there has been no activity for 60 days. Remove stale label or add new comments or this PR will be closed in 30 days.'
3232
close-pr-message: 'Close this stale PR.'
3333
stale-pr-label: 'stale-pr'
34-
days-before-pr-stale: 40
35-
days-before-pr-close: 5
34+
days-before-pr-stale: 60
35+
days-before-pr-close: 30

‎README.md‎

Lines changed: 35 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -54,7 +54,8 @@
5454
</p>
5555

5656
## 📢 News
57-
- **[2025-12]** AgentScope supports [TTS(Text-to-Speech)](https://doc.agentscope.io/tutorial/task_tts.html) now! Check our [example]() and [tutorial](https://doc.agentscope.io/tutorial/task_tts.html) for more details.
57+
- **[2025-12]** AgentScope supports [A2A(Agent-to-Agent) protocol](https://doc.agentscope.io/tutorial/task_a2a_protocol.html) now! Check our [example](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent/a2a_agent) and [tutorial](https://doc.agentscope.io/tutorial/task_a2a_protocol.html) for more details.
58+
- **[2025-12]** AgentScope supports [TTS(Text-to-Speech)](https://doc.agentscope.io/tutorial/task_tts.html) now! Check our [example](https://github.com/agentscope-ai/agentscope/tree/main/examples/functionality/tts) and [tutorial](https://doc.agentscope.io/tutorial/task_tts.html) for more details.
5859
- **[2025-11]** AgentScope supports [Anthropic Agent Skill](https://claude.com/blog/skills) now! Check our [example](https://github.com/agentscope-ai/agentscope/tree/main/examples/functionality/agent_skill) and [tutorial](https://doc.agentscope.io/tutorial/task_agent_skill.html) for more details.
5960
- **[2025-11]** AgentScope open-sources [Alias-Agent](https://github.com/agentscope-ai/agentscope-samples/tree/main/alias) for diverse real-world tasks and [Data-Juicer Agent](https://github.com/agentscope-ai/agentscope-samples/tree/main/data_juicer_agent) for data processing.
6061
- **[2025-11]** AgentScope supports [Agentic RL](https://github.com/agentscope-ai/agentscope/tree/main/examples/training/react_agent) via integrating [Trinity-RFT](https://github.com/modelscope/Trinity-RFT) library.
@@ -88,38 +89,39 @@ Easy for beginners, powerful for experts.
8889

8990
Quick overview of important features in **AgentScope 1.0**:
9091

91-
| Module | Feature | Tutorial |
92-
|------------|------------------------------------------------------------------------------------|-------------------------------------------------------------------------|
93-
| model | Support async invocation | [Model](https://doc.agentscope.io/tutorial/task_model.html) |
94-
| | Support reasoning model | |
95-
| | Support streaming/non-streaming returns | |
96-
| tool | Support async/sync tool functions | [Tool](https://doc.agentscope.io/tutorial/task_tool.html) |
97-
| | Support streaming/non-streaming returns | |
98-
| | Support user interruption | |
99-
| | Support post-processing | |
100-
| | Support group-wise tools management | |
101-
| | Support agentic tools management by meta tool | |
102-
| MCP | Support streamable HTTP/SSE/StdIO transport | [MCP](https://doc.agentscope.io/tutorial/task_mcp.html) |
103-
| | Support both **stateful** and **stateless** mode MCP Client | |
104-
| | Support client- & function-level fine-grained control | |
105-
| agent | Support async execution | |
106-
| | Support parallel tool calls | |
107-
| | Support realtime steering interruption and customized handling | |
108-
| | Support automatic state management | |
109-
| | Support agent-controlled long-term memory | |
110-
| | Support agent hooks | |
111-
| tracing | Support OpenTelemetry-based tracing in LLM, tools, agent and formatter | [Tracing](https://doc.agentscope.io/tutorial/task_tracing.html) |
92+
| Module | Feature | Tutorial |
93+
|------------|----------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------|
94+
| model | Support async invocation | [Model](https://doc.agentscope.io/tutorial/task_model.html) |
95+
| | Support reasoning model | |
96+
| | Support streaming/non-streaming returns | |
97+
| tool | Support async/sync tool functions | [Tool](https://doc.agentscope.io/tutorial/task_tool.html) |
98+
| | Support streaming/non-streaming returns | |
99+
| | Support user interruption | |
100+
| | Support post-processing | |
101+
| | Support group-wise tools management | |
102+
| | Support agentic tools management by meta tool | |
103+
| MCP | Support streamable HTTP/SSE/StdIO transport | [MCP](https://doc.agentscope.io/tutorial/task_mcp.html) |
104+
| | Support both **stateful** and **stateless** mode MCP Client | |
105+
| | Support client- & function-level fine-grained control | |
106+
| agent | Support async execution | |
107+
| | Support parallel tool calls | |
108+
| | Support realtime steering interruption and customized handling | |
109+
| | Support automatic state management | |
110+
| | Support agent-controlled long-term memory | |
111+
| | Support agent hooks | |
112+
| tracing | Support OpenTelemetry-based tracing in LLM, tools, agent and formatter | [Tracing](https://doc.agentscope.io/tutorial/task_tracing.html) |
112113
| | Support connecting to third-party tracing platforms (e.g. Alibaba Cloud CloudMonitor, Arize-Phoenix, Langfuse) | |
113-
| memory | Support long-term memory | [Memory](https://doc.agentscope.io/tutorial/task_long_term_memory.html) |
114-
| session | Provide session/application-level automatic state management | [Session](https://doc.agentscope.io/tutorial/task_state.html) |
115-
| evaluation | Provide distributed and parallel evaluation | [Evaluation](https://doc.agentscope.io/tutorial/task_eval.html) |
116-
| formatter | Support multi-agent prompt formatting with tools API | [Prompt Formatter](https://doc.agentscope.io/tutorial/task_prompt.html) |
117-
| | Support truncation-based formatter strategy | |
118-
| plan | Support ReAct-based long-term planning | [Plan](https://doc.agentscope.io/tutorial/task_plan.html) |
119-
| | Support manual plan specification | |
120-
| RAG | Support agentic RAG | [RAG](https://doc.agentscope.io/tutorial/task_rag.html) |
121-
| | Support multimodal RAG | |
122-
| ... | | |
114+
| memory | Support long-term memory | [Memory](https://doc.agentscope.io/tutorial/task_long_term_memory.html) |
115+
| session | Provide session/application-level automatic state management | [Session](https://doc.agentscope.io/tutorial/task_state.html) |
116+
| evaluation | Provide distributed and parallel evaluation | [Evaluation](https://doc.agentscope.io/tutorial/task_eval.html) |
117+
| formatter | Support multi-agent prompt formatting with tools API | [Prompt Formatter](https://doc.agentscope.io/tutorial/task_prompt.html) |
118+
| | Support truncation-based formatter strategy | |
119+
| plan | Support ReAct-based long-term planning | [Plan](https://doc.agentscope.io/tutorial/task_plan.html) |
120+
| | Support manual plan specification | |
121+
| RAG | Support agentic RAG | [RAG](https://doc.agentscope.io/tutorial/task_rag.html) |
122+
| | Support multimodal RAG | |
123+
| A2A | Support A2A agent | [A2A](https://doc.agentscope.io/tutorial/task_a2a.html) |
124+
| ... | | |
123125

124126

125127
## 💬 Contact
@@ -398,6 +400,7 @@ as_studio
398400
- [Deep Research Agent](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent/deep_research_agent)
399401
- [Browser-use Agent](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent/browser_agent)
400402
- [Meta Planner Agent](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent/meta_planner_agent)
403+
- [A2A Agent](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent/a2a_agent)
401404
- Game
402405
- [Nine-player Werewolves](https://github.com/agentscope-ai/agentscope/tree/main/examples/game/werewolves)
403406
- Workflow

0 commit comments

Comments
 (0)