[bot] Instrument cartesia (193,798 weekly downloads)
維護者通常 1 天內回覆
還沒有人認領這個 Issue。
評估
- 難度
- 4/5
- 預估耗時
- 3-5 天
- 新手友好度
- 55/100
- Issue 類型
- 功能
- 描述清晰度
- 基本清楚
- 活躍度
- 活躍
- 技術堆疊
- python
- 領域
- backend, observability
研究方向
Start by comparing the existing integrations in py/src/braintrust/integrations/livekit_agents/ and pipecat/, then review Cartesia's tts.bytes and tts.sse APIs in its upstream documentation. Check py/pyproject.toml for the integration matrix and py/noxfile.py for the corresponding session. Done means a Cartesia integration exists, is registered and tested consistently with the existing agent-framework integrations.
由索引模型根據 Issue 內容生成。
描述
What's missing
cartesia (the official Python SDK for Cartesia's text-to-speech / voice generation API) has no native instrumentation in the Braintrust Python SDK. There is no py/src/braintrust/integrations/cartesia/ directory, no entry in py/pyproject.toml [tool.braintrust.matrix], and no nox session in py/noxfile.py. The SDK exposes execution-oriented TTS generation calls (e.g. Cartesia().tts.bytes(...) / tts.sse(...)) that are commonly composed into voice-agent pipelines — the same category of real-time generation execution Braintrust already instruments for LiveKit Agents and Pipecat, both of which frequently use Cartesia as their TTS backend.
Weekly downloads
193,798 (as of 2026-10-05; https://pypistats.org/api/packages/cartesia/recent)
Braintrust docs status
not_found — searched site:braintrust.dev docs Cartesia; no Braintrust-Cartesia integration docs exist (only unrelated results, including a third-party listing of Cartesia as a market "competitor," which is not an integration reference). No mention in the Braintrust docs (https://www.braintrust.dev/docs).
Upstream sources
- PyPI: https://pypi.org/pypi/cartesia/json (confirmed current
info.version) - GitHub: https://github.com/cartesia-ai/cartesia-python
- Docs: https://docs.cartesia.ai/ (documents the
tts.bytes/tts.sseexecution APIs)
Local repo files inspected
README.md(root) — "Integrations included inbraintrust" table, no Cartesia entrypy/pyproject.toml— grepped forcartesia, no matches in[tool.braintrust.matrix]or dependency groupspy/noxfile.py— grepped forcartesia, no matching sessionpy/src/braintrust/integrations/— nocartesiasubdirectorypy/src/braintrust/integrations/livekit_agents/andpy/src/braintrust/integrations/pipecat/— reviewed; both instrument the agent-framework layer generically and do not add Cartesia-specific span/metric handling- repo-wide grep for
cartesia— no source-code references found outside this audit
Filed by an automated library-gap audit. Please verify before prioritizing.
- 主要語言
- Python
- 星號
- 21
- 分支
- 23
- 平均合併
- 19 小時 23 分鐘
- 30 天內合併 PR
- 97
環境準備
- 提供 Dockerfile 或 Docker Compose 檔案
- 沒有 Pull Request 範本
- 閱讀貢獻指南
從這裡開始
- 先讀完整個 Issue，再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫，在一個分支上完成修改。
- 送出 Pull Request，並在描述裡引用這個 Issue 編號。
braintrustdata/braintrust-sdk-python 的其他 Issue
-
feature python
難度 2/5 1-3 小時 新手友好度 76/100
braintrustdata/braintrust-sdk-python#868 ·
維護者通常 1 天內回覆
-
auto_instrument() creates duplicate LLM spans for Google ADK Gemini calls可能已有人在做 @AbhiPrasad 今天認領。 未關閉bug python
braintrustdata/braintrust-sdk-python#896 · 1 則留言 · 已指派 1 人 ·
維護者通常 1 天內回覆
-
new-integration python
難度 5/5 一週以上 新手友好度 35/100
braintrustdata/braintrust-sdk-python#853 ·
維護者通常 1 天內回覆
-
new-integration python
難度 4/5 3-5 天 新手友好度 52/100
braintrustdata/braintrust-sdk-python#852 ·
維護者通常 1 天內回覆
-
Migrate legacy HTTPConnection callers to the policy-aware Transport incrementally可能已有人在做 @AbhiPrasad 於 7 天前認領。 未關閉python
braintrustdata/braintrust-sdk-python#839 · 已指派 1 人 ·
維護者通常 1 天內回覆
查看 braintrustdata/braintrust-sdk-python 的全部 Issue
相似的 Issue
-
難度 2/5 1-3 小時 新手友好度 70/100
NVIDIA/earth2studio#1241 ·
維護者通常 3 天內回覆
-
docs(types): update the collection binding note now that typed collections shipped in pycubrid 1.9.0未關閉documentation priority: low size: S
難度 2/5 1-3 小時 新手友好度 75/100
cubrid-lab/sqlalchemy-cubrid#768 ·
維護者通常 1 天內回覆
-
bug help wanted
難度 2/5 1-3 小時 新手友好度 75/100
維護者通常 1 天內回覆
-
documentation
難度 1/5 1 小時以內 新手友好度 65/100
ansys/pydpf-core#3547 ·
維護者通常 1 天內回覆
-
good first issue
難度 2/5 1-3 小時 新手友好度 78/100
OktoLabsAI/okto-pulse#114 ·
維護者通常 1 天內回覆