Skip to content

Commit c287be1

Browse files
Prepare Python SDK v2.2.0 release
1 parent fecdc77 commit c287be1

4 files changed

Lines changed: 25 additions & 5 deletions

File tree

changelog.md

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,26 @@ All notable changes to this project will be documented in this file.
44

55
The format is based on [Keep a Changelog](https://keepachangelog.com/).
66

7+
## [v2.2.0] — 2026-06-05
8+
9+
### Added
10+
11+
- **Expanded provider surface** — Added generated API support for the latest Conversational AI vendors and configuration types, including Dify LLM and Generic Avatar.
12+
- **STT interaction language fields** — Added `interaction_language` support across Speechmatics, Deepgram, Microsoft, Google, Amazon, AssemblyAI, and Sarvam STT wrappers.
13+
- **Deepgram keyterm** — Added `keyterm` support on `DeepgramSTT`, serialized as `asr.params.keyterm`.
14+
15+
### Changed
16+
17+
- **MiniMax managed presets** — MiniMax preset-backed TTS now keeps the preset model as an internal hint while sending only supported partial TTS settings such as `voice_setting.voice_id`.
18+
- **Vertex AI LLM routing**`VertexAILLM` now keeps project and location in the generated endpoint URL instead of duplicating them in `llm.params`.
19+
20+
### Fixed
21+
22+
- **Provider wire keys** — Corrected alias-sensitive TTS payloads so Google TTS emits `VoiceSelectionParams` and `AudioConfig`, Rime TTS emits `modelId`, and Murf TTS preserves `voiceId`.
23+
- **AgentKit request validation** — Start request validation now de-aliases REST-shaped provider dictionaries before constructing generated request models, while still allowing preset and pipeline-backed partial configs.
24+
- **Request body coverage** — Added regression tests for BYOK, preset-backed, mixed preset/BYOK, and pipeline override request shapes across provider configurations.
25+
- **Python docs examples** — Added a docs guard to keep Python examples on snake_case kwargs while allowing documented JSON wire keys.
26+
727
## [v2.1.0] — 2026-06-02
828

929
### Added

compat/agora-agent-server-sdk/pyproject.toml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ name = "agora-agent-server-sdk"
33

44
[tool.poetry]
55
name = "agora-agent-server-sdk"
6-
version = "v2.1.1"
6+
version = "v2.2.0"
77
description = "Compatibility shim for the renamed agora-agents package."
88
readme = "README.md"
99
authors = []
@@ -35,7 +35,7 @@ Repository = 'https://github.com/AgoraIO-Conversational-AI/agent-server-sdk-pyth
3535

3636
[tool.poetry.dependencies]
3737
python = "^3.8"
38-
agora-agents = ">=2.1.1,<3.0.0"
38+
agora-agents = ">=2.2.0,<3.0.0"
3939

4040
[build-system]
4141
requires = ["poetry-core"]

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ name = "agora-agents"
33

44
[tool.poetry]
55
name = "agora-agents"
6-
version = "v2.1.1"
6+
version = "v2.2.0"
77
description = ""
88
readme = "README.md"
99
authors = []

src/agora_agent/core/client_wrapper.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ def __init__(
2626

2727
def get_headers(self) -> typing.Dict[str, str]:
2828
headers: typing.Dict[str, str] = {
29-
"User-Agent": "agora-agents/v2.1.2",
29+
"User-Agent": "agora-agents/v2.2.0",
3030
"X-Fern-Language": "Python",
3131
"X-Fern-SDK-Name": "agora-agents",
32-
"X-Fern-SDK-Version": "v2.1.2",
32+
"X-Fern-SDK-Version": "v2.2.0",
3333
**(self.get_custom_headers() or {}),
3434
}
3535
headers["Authorization"] = httpx.BasicAuth(self._get_username(), self._get_password())._auth_header

0 commit comments

Comments
 (0)