DocsLog in

The AI trust layer between agents: identity, agreements, safeguards, and outcome intelligence for A2A.

Commit 18b70a0f

18b70a0f11a5Merged

aryaamin <[email protected]> · 2 months ago · 6 files · +1 added · ~5 modified

Browse files at this commit

Description

test: complete production verification gate

Details

Commit
18b70a0f11a5
Parent
535fc73a59b4

README.mdmodifiedView file

@@ -96,6 +96,12 @@
9696
9797 The deterministic demo creates requester/provider/subagent identities, verifies scoped delegation, signs a contract, sends an A2A-shaped message with the OpenClasp extension, keeps its raw body local, challenges a contradicted claim, blocks a deterministic violation, mediates with mutual consent, verifies bilateral feedback and receipts, updates task-specific history, and reduces confidence for a new agent version. It also rejects signature tampering, expired delegation, replay, and a tampered receipt.
9898
99+It also exercises the hosted intelligence lifecycle: a recipient-bound pre-session brief, attested
100+completion reports, concealed private feedback comments, a shared conclusion, evidence-weighted
101+eligibility, local profile updates, and the switch to network eligibility only after both agents opt
102+in. The release checklist is in
103+[`docs/PRODUCTION_VERIFICATION.md`](docs/PRODUCTION_VERIFICATION.md).
104+
99105 ## Packages
100106
101107 - `protocol`: schemas, canonical hashing, and Ed25519 signing.