Admission-gate / audit layer for real outbound calls and messages -- worth a PoC?
メンテナーはふだん 5 日以内に返信
まだ誰も着手していません。
評価
- 難易度
- 5/5
- 見積もり時間
- 1週間以上
- 初心者へのやさしさ
- 30/100
調査の方向性
Start by reviewing tools/ and the channel send path, then compare the proposed pre-execution hook with the existing on_error callback in #88. Confirm whether a real outbound Calls or messaging API invocation is exposed there; done would be a scoped, accepted PoC with before/after behavior and an audit trail, if maintainers agree.
索引モデルが issue の本文から書いたものです。
説明
Who we are, up front
We're Tulip (tulip-agents on PyPI) — an open-source agentic AI SDK, Apache-2.0. Pre-GA (currently v2.4.0, actively developed, not a mature/enterprise-proven product) — flagging that plainly. Opening this as an issue first per your CONTRIBUTING.md ("Major Changes should be discussed first in an issue"), not jumping to a PR.
What we noticed
twilio-agent-connect-python gives an agent real, autonomous reach into Twilio's voice and messaging channels — outbound calls (Calls API passthrough, AMD), SMS/messaging sends, handoffs. As far as we can tell from the public repo, there's currently no approval, guardrail, or audit layer between "the agent decided to do this" and "the call/message actually goes out." That's a different risk shape than most agent-tool examples: a wrong tool call here doesn't just corrupt some local state, it places a real call or sends a real message to a real phone number — with real TCPA/consent exposure, real cost, real reputational risk if it dials or texts the wrong person.
We searched the codebase for any existing guardrail/approval/audit concept and didn't find one (could easily be wrong — genuinely asking, not asserting).
What tulip-agents could add
tulip.control.admit() — every proposed action is classified and weighed against a policy before it runs:
benign action (e.g. read-only lookup) -> executes normally
outbound call / SMS to a new/unverified # -> held for a human, never executes
Every decision — allowed or not — lands on a tamper-evident, hash-chained AuditTrail, independent of Twilio's own call/message logs: who initiated it, under what policy, at what time, with what outcome.
Concretely, this would look like wrapping the point where a tool call becomes a real outbound Calls/messaging API invocation (tools/, or a channel's send path) in an admission check — same shape as the on_error callback you added recently (#88), but pre-execution rather than post-hoc.
What this is not
Not a claim that every outbound action needs a human in the loop — most don't, and an admission gate that fires on everything is useless. It's a policy layer: cheap/low-risk actions auto-allow, actions matching risk criteria you define (new number, no prior consent record, high call volume in a short window, whatever your own policy wants) escalate or deny. tulip-agents would be a real dependency of an example only, not a core SDK dependency — same pattern we've used integrating with other projects.
Happy to build a real PoC
Not asking you to take this on faith — happy to build a working example against a real hook point in this SDK (not a toy), verify it end-to-end against a real (test) Twilio account, and show actual before/after behavior: a benign action executing normally, a flagged one genuinely held, with the audit trail to back it up. That's the standard we've held ourselves to on every integration we've built so far.
The ask
Whether this is a real gap from where you sit, and whether it's something worth a PoC at all — happy to narrow scope, adjust the hook point, or hear that it's not a fit. Genuinely asking, not assuming.
- 主要言語
- Python
- スター
- 17
- フォーク
- 11
- 平均マージ
- 5日 19時間
- マージ済み PR(30日)
- 6
環境構築
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
twilio/twilio-agent-connect-python のほかの issue
-
ParticipantResponse.name is required where the API definition marks it nullable, so a nameless participant fails to parse対応中かも @TheeCoderAhmed が 22 日前に担当しました。 オープン
難易度 1/5 1時間未満 初心者へのやさしさ 86/100
twilio/twilio-agent-connect-python#134 ·
メンテナーはふだん 5 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 50/100
twilio/twilio-agent-connect-python#136 ·
メンテナーはふだん 5 日以内に返信
-
難易度 5/5 1週間以上 初心者へのやさしさ 25/100
twilio/twilio-agent-connect-python#135 ·
メンテナーはふだん 5 日以内に返信
-
難易度 4/5 3〜5日 初心者へのやさしさ 45/100
twilio/twilio-agent-connect-python#133 ·
メンテナーはふだん 5 日以内に返信
-
add tac config validations対応中かも @rahulsjha が 4 日前に担当しました。 オープン
難易度 3/5 1〜2日 初心者へのやさしさ 45/100
twilio/twilio-agent-connect-python#70 · コメント 1 件 ·
メンテナーはふだん 5 日以内に返信
twilio/twilio-agent-connect-python の issue をすべて見る
似ている issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 64/100
メンテナーはふだん 1 日以内に返信
-
area:cli area:security enhancement priority:medium size:small
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
RonaldHensbergen/composable-data-stack#1338 ·
メンテナーはふだん 1 日以内に返信
-
area:stdlib effort:S impact:med platform:linux type:bug
難易度 2/5 1〜3時間 初心者へのやさしさ 84/100
メンテナーはふだん 1 日以内に返信
-
automated endpoint-dead needs-curation
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
almanac-data/climate-almanac#139 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
UKGovernmentBEIS/inspect_ai#6695 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信