From 9b8ce3d4f8855761afa4944e1981f9d35d33dac1 Mon Sep 17 00:00:00 2001 From: Koishore Roy Date: Mon, 8 Jun 2026 17:04:07 +0530 Subject: [PATCH] chore: align positioning to intent-bound action authorization --- CONTRIBUTING.md | 2 +- README.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index f10fa7e..adab5df 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -32,7 +32,7 @@ it green. Run a **single** uvicorn worker — delego's state is file-backed. not accepted (it is branch-protected and requires review). - Keep changes small and explain the *why*. The only app-specific code is the [`BrokerAdapter`](app/broker.py) and the [policy](policy.yaml) — most behaviour - lives in the published `delego` package, so fixes to the firewall itself belong + lives in the published `delego` package, so fixes to delego itself belong [upstream](https://github.com/Delego-Dev/delego). - Run `pytest` before submitting; add or adjust tests for any behaviour change. diff --git a/README.md b/README.md index d0dd716..42477d5 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,8 @@ # delego sample app A small **FastAPI** service that shows how to build on -[**delego**](https://github.com/Delego-Dev/delego) — a policy & audit firewall -for agent actions. An agent proposes HTTP actions; the service authorises them +[**delego**](https://github.com/Delego-Dev/delego) — intent-bound action +authorization for AI agents. An agent proposes HTTP actions; the service authorises them deterministically, parks sensitive ones for human approval, executes allowed ones through a broker, and records a signed, tamper-evident audit trail.