You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+14Lines changed: 14 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,19 @@
1
1
# Changelog
2
2
3
+
## 0.11.3 (2026-05-20)
4
+
5
+
Full Changelog: [v0.11.2...v0.11.3](https://github.com/scaleapi/scale-agentex-python/compare/v0.11.2...v0.11.3)
6
+
7
+
### Features
8
+
9
+
* added Pydantic AI sync, async, temporal integration ([#359](https://github.com/scaleapi/scale-agentex-python/issues/359)) ([781dfe1](https://github.com/scaleapi/scale-agentex-python/commit/781dfe172373c2e01fb642b3c98af6908c98218a))
10
+
***api:** add schedule, checkpoints, and deployment endpoints ([53b5c36](https://github.com/scaleapi/scale-agentex-python/commit/53b5c3673e54ee4b49debd049483f1a1d4b0673d))
11
+
12
+
13
+
### Bug Fixes
14
+
15
+
* resolve lint and test failures from new endpoints ([#360](https://github.com/scaleapi/scale-agentex-python/issues/360)) ([bdf129c](https://github.com/scaleapi/scale-agentex-python/commit/bdf129c8ab976ed84aa9932d5585a753280a6a34))
16
+
3
17
## 0.11.2 (2026-05-13)
4
18
5
19
Full Changelog: [v0.11.1...v0.11.2](https://github.com/scaleapi/scale-agentex-python/compare/v0.11.1...v0.11.2)
The sync ACP model uses HTTP request/response for communication. The `@acp.on_message_send` handler receives a message and yields streaming events back to the client.
11
+
12
+
### Pydantic AI Integration
13
+
-**Agent**: A single `pydantic_ai.Agent` that owns the model and tools. No graph required — Pydantic AI runs its own tool-call loop until the model is done.
14
+
-**`@agent.tool_plain`**: Registers a Python function as a tool. Pydantic AI infers the schema from type hints and docstring.
15
+
-**`agent.run_stream_events(...)`**: Yields `AgentStreamEvent`s (PartStartEvent / PartDeltaEvent / PartEndEvent / FunctionToolResultEvent) as the model produces them.
16
+
17
+
### Streaming
18
+
The agent streams tokens and tool-call arguments as they're generated using `convert_pydantic_ai_to_agentex_events()`, which adapts Pydantic AI's stream into AgentEx `TaskMessageUpdate` events. Notably, **tool-call arguments stream as `ToolRequestDelta` tokens** rather than arriving as a single complete payload — a richer experience than what OpenAI Agents SDK currently exposes.
19
+
20
+
## Files
21
+
22
+
| File | Description |
23
+
|------|-------------|
24
+
|`project/acp.py`| ACP server and message handler |
25
+
|`project/agent.py`| Pydantic AI agent + tool registration |
- Multi-turn conversation memory is not wired in this tutorial. Pydantic AI does not ship a checkpointer like LangGraph; to add memory, load prior messages via `adk.messages.list(task_id=...)` and pass them to `agent.run_stream_events(..., message_history=...)`.
46
+
- Reasoning/thinking tokens are not exercised here because `gpt-4o-mini` does not emit `ThinkingPart`s. Swap to a reasoning-capable model (e.g. `openai:o1-mini` via Pydantic AI's appropriate provider) if you want to test that branch end-to-end.
0 commit comments