Plan: AI-configured triggers (Composio-free webhook provider, agent-driven setup) - #5191
Draft
mmabrouk wants to merge 1 commit into
Draft
Plan: AI-configured triggers (Composio-free webhook provider, agent-driven setup)#5191mmabrouk wants to merge 1 commit into
mmabrouk wants to merge 1 commit into
Conversation
Feature plan for a Composio-independent `webhook` trigger provider with agent-driven configuration: verified ingress (5 signature schemes), sandboxed filter/transform + delivery replay, recipe catalog with provider logos reusing the existing catalog UI, new builder-agent ops (incl. request_secret so secret values never enter the conversation), and a v1-vault / v2-egress-substitution secrets model. Claude-Session: https://claude.ai/code/session_01HbtYHq6RCG8mELkWRnBCbK
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
docs/design/ai-configured-triggers/— a planning workspace (per/plan-featureconventions) for a newwebhooktrigger provider that lets self-hosting users create event triggers for GitHub, Telegram, Stripe, Slack, PostHog, etc. without Composio, with the builder agent doing the configuration: picking the verification scheme, registering the webhook upstream, generating the payload→inputs transform, and iterating against real deliveries.Why
Self-hosters shouldn't need a third-party SaaS (and data processor) for triggers. Strategy: MCP covers the actions plane (separate track); this covers the events plane, since MCP has no trigger primitive yet. Composio stays as the managed option — nothing is removed.
Contents
README.md/context.md— overview, goals, key decisions (provider seam reuse, 5 verification schemes, sandboxed expression transforms, secrets-never-in-conversation) and open questionsresearch.md— verified code findings:TriggersGatewayRegistryseam, existingSecretKind.webhook_provider,AppLogo/catalog logo rendering,build_kit.py/static_catalog.pyagent surfaceplan.md— phases A–F with file-level targets; v2 items (poll + MCP-poll provider, vault egress substitution) explicitly deferredagent-instructions.md— drafted op descriptions + static-catalog prose, incl. hard secrets guardrailssecrets-and-ux.md—request_secretout-of-band flow (browser→vault, agent gets slug only), reveal-once panel, catalog/drawer UX so these triggers look first-class (provider logos via existingAppLogo)status.md— open questions waiting on review (expression engine, connection_id shape, logo sourcing, launch recipe set)Review focus
The six questions in
status.md— especially JSONata vs CEL (Q1) and nullable-vs-syntheticconnection_id(Q2), which gate Phase A.https://claude.ai/code/session_01HbtYHq6RCG8mELkWRnBCbK