serverless-vault-bridge
If an assistant can suggest vault changes, where do review, exact confirmation, path safety, and rollback stop quiet writes?
If an assistant can suggest vault changes, where do review, exact confirmation, path safety, and rollback stop quiet writes?
serverless-vault-bridge
Why this article exists
Who owns the mutation if AI can help maintain a knowledge vault and quietly change durable storage behind the user? I built this around that discomfort: the bridge lets an assistant prepare a diff, then forces the final write through exact-content confirmation.
Problem
AI-assisted note systems need safe write boundaries: path safety, API authentication, diff review, digest-bound confirmation, expected base SHA, and conflict handling before storage changes.
What shipped
Cloudflare Worker-compatible runtime, GitHub Contents API storage adapter, ChatGPT Actions OpenAPI, MCP JSON-RPC endpoint, proposal tokens, path policy, CAS conflict handling, and behavior tests.
Evidence
The README names the propose-review-commit tool flow and failure semantics for path traversal, token mismatch, digest mismatch, path mismatch, base SHA mismatch, and CAS conflicts.
Inspect path
Inspect `src/`, `test/`, `wrangler.toml.example`, the OpenAPI schema, and tests for auth, path safety, token binding, CAS conflicts, and MCP parity.
Boundary
It is not a sync engine, database, agent framework, or direct-write API for high-risk automation. It proves a reviewable write boundary, not a full knowledge-management product.
What changed
The important boundary became clearer: not chat versus agent, but suggestion versus commit, with ownership and rollback kept visible.
Next question
Where should approval live when AI can prepare a change but should not own the final mutation?
Open public repository
https://github.com/89325516/serverless-vault-bridge