a2a-lite 0.2.4__tar.gz → 0.2.5__tar.gz

{a2a_lite-0.2.4 → a2a_lite-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: a2a-lite
-Version: 0.2.4
+Version: 0.2.5
 Summary: Simplified wrapper for Google's A2A Protocol SDK
 Author: A2A Lite Contributors
 License-Expression: MIT
@@ -29,11 +29,14 @@ Provides-Extra: oauth
 Requires-Dist: pyjwt[crypto]>=2.0; extra == 'oauth'
 Description-Content-Type: text/markdown
 
-# A2A Lite - Python
+# A2A Lite — Python
+
+[![PyPI](https://img.shields.io/pypi/v/a2a-lite?label=PyPI&logo=pypi&logoColor=white)](https://pypi.org/project/a2a-lite/)
+[![GitHub](https://img.shields.io/badge/GitHub-a2a--lite-blue?logo=github)](https://github.com/xvierd/a2a-lite)
 
 **Build A2A agents in 8 lines. Add features when you need them.**
 
-Wraps the official [A2A Python SDK](https://github.com/a2aproject/a2a-python) with a simple, intuitive API.
+Wraps the official [A2A Python SDK](https://github.com/a2aproject/a2a-python) with a simple, decorator-based API. 100% protocol-compatible.
 
 ```python
 from a2a_lite import Agent
@@ -81,7 +84,7 @@ async def multiply(a: int, b: int) -> int:
 agent.run(port=8787)
 ```
 
-### 2. Test it
+### 2. Test it (no HTTP needed)
 
 ```python
 from a2a_lite import Agent, AgentTestClient
@@ -97,7 +100,7 @@ result = client.call("add", a=2, b=3)
 assert result == 5
 ```
 
-### 3. Call it
+### 3. Call it over the network
 
 ```bash
 curl -X POST http://localhost:8787/ \
@@ -120,7 +123,7 @@ curl -X POST http://localhost:8787/ \
 
 ## Progressive Complexity
 
-### Level 1: Basic Skills
+### Level 1 — Basic Skills
 
 ```python
 from a2a_lite import Agent
@@ -134,7 +137,7 @@ async def greet(name: str) -> str:
 agent.run()
 ```
 
-### Level 2: Pydantic Models (Just Works)
+### Level 2 — Pydantic Models
 
 Pass dicts from callers — they're auto-converted to Pydantic models:
 
@@ -160,7 +163,9 @@ async def count_users(users: List[User]) -> int:
     return len(users)
 ```
 
-### Level 3: Streaming (Just Yield)
+### Level 3 — Streaming
+
+Just `yield` instead of `return`:
 
 ```python
 @agent.skill("chat", streaming=True)
@@ -169,7 +174,9 @@ async def chat(message: str):
         yield word + " "
 ```
 
-### Level 4: Middleware
+### Level 4 — Middleware
+
+Cross-cutting concerns without touching skill code:
 
 ```python
 @agent.middleware
@@ -191,7 +198,9 @@ agent.add_middleware(rate_limit_middleware(max_per_minute=60))
 agent.add_middleware(retry_middleware(max_retries=3))
 ```
 
-### Level 5: File Handling
+### Level 5 — File Handling
+
+Accept and return files through the A2A protocol:
 
 ```python
 from a2a_lite import FilePart
@@ -202,7 +211,9 @@ async def summarize(doc: FilePart) -> str:
     return f"Summary: {content[:100]}..."
 ```
 
-### Level 6: Task Tracking
+### Level 6 — Task Tracking
+
+Long-running operations with progress updates:
 
 ```python
 from a2a_lite import TaskContext
@@ -212,14 +223,14 @@ agent = Agent(name="Bot", description="A bot", task_store="memory")
 @agent.skill("process")
 async def process(data: str, task: TaskContext) -> str:
     await task.update("working", "Starting...", progress=0.0)
-
     for i in range(10):
         await task.update("working", f"Step {i}/10", progress=i/10)
-
     return "Done!"
 ```
 
-### Level 7: Authentication
+### Level 7 — Authentication
+
+API keys are hashed in memory using SHA-256 — plaintext keys are never stored.
 
 ```python
 from a2a_lite import Agent, APIKeyAuth
@@ -231,8 +242,6 @@ agent = Agent(
 )
 ```
 
-API keys are hashed in memory using SHA-256 — plaintext keys are never stored.
-
 Other auth providers:
 
 ```python
@@ -261,7 +270,7 @@ async def whoami(auth: AuthResult) -> dict:
     return {"user": auth.identity, "scheme": auth.scheme}
 ```
 
-### Level 8: CORS and Production Mode
+### Level 8 — CORS & Production Mode
 
 ```python
 agent = Agent(
@@ -272,12 +281,24 @@ agent = Agent(
 )
 ```
 
-### Level 9: Completion Hooks
+### Level 9 — Lifecycle Hooks
 
 ```python
+@agent.on_startup
+async def startup():
+    print("Agent starting...")
+
+@agent.on_shutdown
+async def shutdown():
+    print("Agent stopping...")
+
 @agent.on_complete
 async def notify(skill_name, result, ctx):
     print(f"Skill {skill_name} completed with: {result}")
+
+@agent.on_error
+async def handle_error(error: Exception):
+    return {"error": str(error), "type": type(error).__name__}
 ```
 
 ---
@@ -286,7 +307,7 @@ async def notify(skill_name, result, ctx):
 
 ### AgentTestClient
 
-The synchronous test client for use with pytest:
+Synchronous test client for pytest:
 
 ```python
 from a2a_lite import Agent, AgentTestClient
@@ -324,7 +345,7 @@ def test_list_skills():
 
 ### TestResult
 
-Every `client.call()` returns a `TestResult` with:
+Every `client.call()` returns a `TestResult`:
 
 | Property | Description |
 |----------|-------------|
@@ -333,7 +354,7 @@ Every `client.call()` returns a `TestResult` with:
 | `.json()` | Parse text as JSON (raises on invalid JSON) |
 | `.raw_response` | Full A2A response dict |
 
-`TestResult` supports direct equality comparison for simple values (`result == 5`), but use `.data` for subscripting (`result.data["key"]`).
+`TestResult` supports direct equality for simple values (`result == 5`), but use `.data` for subscripting (`result.data["key"]`).
 
 ### AsyncAgentTestClient
 
@@ -365,10 +386,11 @@ def test_streaming():
 ## CLI
 
 ```bash
-a2a-lite init my-agent          # Create new project
-a2a-lite serve agent.py         # Run agent from file
-a2a-lite inspect http://...     # View agent capabilities
-a2a-lite test http://... skill  # Test a skill
+a2a-lite init my-agent          # Scaffold a new project
+a2a-lite serve agent.py         # Run an agent from file
+a2a-lite inspect http://...     # View agent card & skills
+a2a-lite test http://... skill  # Smoke-test a skill
+a2a-lite discover               # Find agents on the local network (mDNS)
 a2a-lite version                # Show version
 ```
 
@@ -427,7 +449,7 @@ Agent(
 
 ### Special Parameter Types
 
-These are auto-injected when detected in skill function signatures:
+Auto-injected when detected in skill function signatures:
 
 | Type | Description |
 |------|-------------|
@@ -444,18 +466,22 @@ These are auto-injected when detected in skill function signatures:
 |---------|---------------|
 | [01_hello_world.py](examples/01_hello_world.py) | Simplest agent (8 lines) |
 | [02_calculator.py](examples/02_calculator.py) | Multiple skills |
+| [03_async_agent.py](examples/03_async_agent.py) | Async operations & lifecycle hooks |
+| [04_multi_agent/](examples/04_multi_agent) | Two agents communicating |
+| [05_with_llm.py](examples/05_with_llm.py) | OpenAI / Anthropic integration |
 | [06_pydantic_models.py](examples/06_pydantic_models.py) | Auto Pydantic conversion |
+| [07_middleware.py](examples/07_middleware.py) | Middleware pipeline |
 | [08_streaming.py](examples/08_streaming.py) | Streaming responses |
-| [09_testing.py](examples/09_testing.py) | Testing your agents |
-| [10_file_handling.py](examples/10_file_handling.py) | Handle files |
+| [09_testing.py](examples/09_testing.py) | Built-in TestClient |
+| [10_file_handling.py](examples/10_file_handling.py) | File upload & processing |
 | [11_task_tracking.py](examples/11_task_tracking.py) | Progress updates |
 | [12_with_auth.py](examples/12_with_auth.py) | Authentication |
 
 ---
 
-## 100% A2A Protocol Compatible
+## A2A Protocol Mapping
 
-A2A Lite wraps the official A2A Python SDK. Every feature maps to real A2A protocol concepts:
+Everything maps directly to the underlying protocol — no magic, no lock-in.
 
 | A2A Lite | A2A Protocol |
 |----------|--------------|
@@ -464,6 +490,7 @@ A2A Lite wraps the official A2A Python SDK. Every feature maps to real A2A proto
 | `TaskContext.update()` | Task lifecycle states |
 | `FilePart` | A2A File parts |
 | `DataPart` | A2A Data parts |
+| `Artifact` | A2A Artifacts |
 | `APIKeyAuth` / `BearerAuth` | Security schemes |
 
 ---

{a2a_lite-0.2.4 → a2a_lite-0.2.5}/README.md

@@ -1,8 +1,11 @@
-# A2A Lite - Python
+# A2A Lite — Python
+
+[![PyPI](https://img.shields.io/pypi/v/a2a-lite?label=PyPI&logo=pypi&logoColor=white)](https://pypi.org/project/a2a-lite/)
+[![GitHub](https://img.shields.io/badge/GitHub-a2a--lite-blue?logo=github)](https://github.com/xvierd/a2a-lite)
 
 **Build A2A agents in 8 lines. Add features when you need them.**
 
-Wraps the official [A2A Python SDK](https://github.com/a2aproject/a2a-python) with a simple, intuitive API.
+Wraps the official [A2A Python SDK](https://github.com/a2aproject/a2a-python) with a simple, decorator-based API. 100% protocol-compatible.
 
 ```python
 from a2a_lite import Agent
@@ -50,7 +53,7 @@ async def multiply(a: int, b: int) -> int:
 agent.run(port=8787)
 ```
 
-### 2. Test it
+### 2. Test it (no HTTP needed)
 
 ```python
 from a2a_lite import Agent, AgentTestClient
@@ -66,7 +69,7 @@ result = client.call("add", a=2, b=3)
 assert result == 5
 ```
 
-### 3. Call it
+### 3. Call it over the network
 
 ```bash
 curl -X POST http://localhost:8787/ \
@@ -89,7 +92,7 @@ curl -X POST http://localhost:8787/ \
 
 ## Progressive Complexity
 
-### Level 1: Basic Skills
+### Level 1 — Basic Skills
 
 ```python
 from a2a_lite import Agent
@@ -103,7 +106,7 @@ async def greet(name: str) -> str:
 agent.run()
 ```
 
-### Level 2: Pydantic Models (Just Works)
+### Level 2 — Pydantic Models
 
 Pass dicts from callers — they're auto-converted to Pydantic models:
 
@@ -129,7 +132,9 @@ async def count_users(users: List[User]) -> int:
     return len(users)
 ```
 
-### Level 3: Streaming (Just Yield)
+### Level 3 — Streaming
+
+Just `yield` instead of `return`:
 
 ```python
 @agent.skill("chat", streaming=True)
@@ -138,7 +143,9 @@ async def chat(message: str):
         yield word + " "
 ```
 
-### Level 4: Middleware
+### Level 4 — Middleware
+
+Cross-cutting concerns without touching skill code:
 
 ```python
 @agent.middleware
@@ -160,7 +167,9 @@ agent.add_middleware(rate_limit_middleware(max_per_minute=60))
 agent.add_middleware(retry_middleware(max_retries=3))
 ```
 
-### Level 5: File Handling
+### Level 5 — File Handling
+
+Accept and return files through the A2A protocol:
 
 ```python
 from a2a_lite import FilePart
@@ -171,7 +180,9 @@ async def summarize(doc: FilePart) -> str:
     return f"Summary: {content[:100]}..."
 ```
 
-### Level 6: Task Tracking
+### Level 6 — Task Tracking
+
+Long-running operations with progress updates:
 
 ```python
 from a2a_lite import TaskContext
@@ -181,14 +192,14 @@ agent = Agent(name="Bot", description="A bot", task_store="memory")
 @agent.skill("process")
 async def process(data: str, task: TaskContext) -> str:
     await task.update("working", "Starting...", progress=0.0)
-
     for i in range(10):
         await task.update("working", f"Step {i}/10", progress=i/10)
-
     return "Done!"
 ```
 
-### Level 7: Authentication
+### Level 7 — Authentication
+
+API keys are hashed in memory using SHA-256 — plaintext keys are never stored.
 
 ```python
 from a2a_lite import Agent, APIKeyAuth
@@ -200,8 +211,6 @@ agent = Agent(
 )
 ```
 
-API keys are hashed in memory using SHA-256 — plaintext keys are never stored.
-
 Other auth providers:
 
 ```python
@@ -230,7 +239,7 @@ async def whoami(auth: AuthResult) -> dict:
     return {"user": auth.identity, "scheme": auth.scheme}
 ```
 
-### Level 8: CORS and Production Mode
+### Level 8 — CORS & Production Mode
 
 ```python
 agent = Agent(
@@ -241,12 +250,24 @@ agent = Agent(
 )
 ```
 
-### Level 9: Completion Hooks
+### Level 9 — Lifecycle Hooks
 
 ```python
+@agent.on_startup
+async def startup():
+    print("Agent starting...")
+
+@agent.on_shutdown
+async def shutdown():
+    print("Agent stopping...")
+
 @agent.on_complete
 async def notify(skill_name, result, ctx):
     print(f"Skill {skill_name} completed with: {result}")
+
+@agent.on_error
+async def handle_error(error: Exception):
+    return {"error": str(error), "type": type(error).__name__}
 ```
 
 ---
@@ -255,7 +276,7 @@ async def notify(skill_name, result, ctx):
 
 ### AgentTestClient
 
-The synchronous test client for use with pytest:
+Synchronous test client for pytest:
 
 ```python
 from a2a_lite import Agent, AgentTestClient
@@ -293,7 +314,7 @@ def test_list_skills():
 
 ### TestResult
 
-Every `client.call()` returns a `TestResult` with:
+Every `client.call()` returns a `TestResult`:
 
 | Property | Description |
 |----------|-------------|
@@ -302,7 +323,7 @@ Every `client.call()` returns a `TestResult` with:
 | `.json()` | Parse text as JSON (raises on invalid JSON) |
 | `.raw_response` | Full A2A response dict |
 
-`TestResult` supports direct equality comparison for simple values (`result == 5`), but use `.data` for subscripting (`result.data["key"]`).
+`TestResult` supports direct equality for simple values (`result == 5`), but use `.data` for subscripting (`result.data["key"]`).
 
 ### AsyncAgentTestClient
 
@@ -334,10 +355,11 @@ def test_streaming():
 ## CLI
 
 ```bash
-a2a-lite init my-agent          # Create new project
-a2a-lite serve agent.py         # Run agent from file
-a2a-lite inspect http://...     # View agent capabilities
-a2a-lite test http://... skill  # Test a skill
+a2a-lite init my-agent          # Scaffold a new project
+a2a-lite serve agent.py         # Run an agent from file
+a2a-lite inspect http://...     # View agent card & skills
+a2a-lite test http://... skill  # Smoke-test a skill
+a2a-lite discover               # Find agents on the local network (mDNS)
 a2a-lite version                # Show version
 ```
 
@@ -396,7 +418,7 @@ Agent(
 
 ### Special Parameter Types
 
-These are auto-injected when detected in skill function signatures:
+Auto-injected when detected in skill function signatures:
 
 | Type | Description |
 |------|-------------|
@@ -413,18 +435,22 @@ These are auto-injected when detected in skill function signatures:
 |---------|---------------|
 | [01_hello_world.py](examples/01_hello_world.py) | Simplest agent (8 lines) |
 | [02_calculator.py](examples/02_calculator.py) | Multiple skills |
+| [03_async_agent.py](examples/03_async_agent.py) | Async operations & lifecycle hooks |
+| [04_multi_agent/](examples/04_multi_agent) | Two agents communicating |
+| [05_with_llm.py](examples/05_with_llm.py) | OpenAI / Anthropic integration |
 | [06_pydantic_models.py](examples/06_pydantic_models.py) | Auto Pydantic conversion |
+| [07_middleware.py](examples/07_middleware.py) | Middleware pipeline |
 | [08_streaming.py](examples/08_streaming.py) | Streaming responses |
-| [09_testing.py](examples/09_testing.py) | Testing your agents |
-| [10_file_handling.py](examples/10_file_handling.py) | Handle files |
+| [09_testing.py](examples/09_testing.py) | Built-in TestClient |
+| [10_file_handling.py](examples/10_file_handling.py) | File upload & processing |
 | [11_task_tracking.py](examples/11_task_tracking.py) | Progress updates |
 | [12_with_auth.py](examples/12_with_auth.py) | Authentication |
 
 ---
 
-## 100% A2A Protocol Compatible
+## A2A Protocol Mapping
 
-A2A Lite wraps the official A2A Python SDK. Every feature maps to real A2A protocol concepts:
+Everything maps directly to the underlying protocol — no magic, no lock-in.
 
 | A2A Lite | A2A Protocol |
 |----------|--------------|
@@ -433,6 +459,7 @@ A2A Lite wraps the official A2A Python SDK. Every feature maps to real A2A proto
 | `TaskContext.update()` | Task lifecycle states |
 | `FilePart` | A2A File parts |
 | `DataPart` | A2A Data parts |
+| `Artifact` | A2A Artifacts |
 | `APIKeyAuth` / `BearerAuth` | Security schemes |
 
 ---

{a2a_lite-0.2.4 → a2a_lite-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "a2a-lite"
-version = "0.2.4"
+version = "0.2.5"
 description = "Simplified wrapper for Google's A2A Protocol SDK"
 readme = "README.md"
 license = "MIT"