swt3-ai 0.7.4 → 0.7.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +16 -0
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: fefc23f36d14635cbc8ccab857ea51d69fa6c6b6d84443cada25784121e75987
|
|
4
|
+
data.tar.gz: 5f5e866c59256928c661aa93538913f9115bc83fc53e36df2543c992533ec243
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: c0d1e95256a87a9383f8e4a8f0d947a99ee27153bd241cc4438ae269ff81083e2635f6c94c11b9047c6dbd2a5914c6b42a8cc1bddd612776c40d57aba2b04282
|
|
7
|
+
data.tar.gz: ad13083e16b0e552cb4cb3e38b3b46231a5ef4d02645a73cc8c303b29c5949885ed8da93f354649bb6d441728fc342c8487f250fbfd1d38f29f43ae2b3bc2aed
|
data/README.md
CHANGED
|
@@ -13,6 +13,22 @@ EU AI Act GPAI transparency obligations enforced since **August 2, 2026**. High-
|
|
|
13
13
|
|
|
14
14
|
> **Protocol Spec:** [swt3.ai/spec](https://swt3.ai/spec) | **Registry:** [swt3.ai/registry](https://swt3.ai/registry) | **Verify:** [swt3.ai/verify](https://swt3.ai/verify)
|
|
15
15
|
|
|
16
|
+
## What's New in v0.7.5
|
|
17
|
+
|
|
18
|
+
Multi-agent systems propagate trust decisions across organizational boundaries with no cryptographic record of why. v0.7.5 closes that gap. The Trust Propagation Engine records how trust was established, how it decays across delegation hops, and maps trust scores to clearing levels -- all witnessed as AI-TRUST.3 anchors.
|
|
19
|
+
|
|
20
|
+
**Why this matters for Ruby:** AI-TRUST.3 verifies with the existing `mint_fingerprint` function. Ruby API backends and Rails agent orchestrators gain trust propagation attestation with the same fingerprint output as every other SDK language. NERC CIP (45 mappings) and 3GPP R19 (16 mappings) crosswalks expand the regulatory coverage relevant to Ruby enterprise compliance dashboards. Zero gem changes.
|
|
21
|
+
|
|
22
|
+
### 1 New Procedure
|
|
23
|
+
|
|
24
|
+
- **AI-TRUST.3** (Trust Propagation Assertion): Records trust scores with Sybil resistance and transitive decay across multi-agent delegation chains.
|
|
25
|
+
|
|
26
|
+
### Updated Coverage
|
|
27
|
+
|
|
28
|
+
- 279 procedures across 10 namespaces
|
|
29
|
+
- 84 regulatory frameworks, 288 compliance guides
|
|
30
|
+
- [Trust Propagation Guide](https://sovereign.tenova.io/guides/agent-trust-propagation.html) | [NERC CIP Crosswalk](https://sovereign.tenova.io/guides/nerc-cip-crosswalk.html)
|
|
31
|
+
|
|
16
32
|
## What's New in v0.7.4
|
|
17
33
|
|
|
18
34
|
NVIDIA shipped OpenShell to 120+ partners. Agent containment is now infrastructure. But containment without evidence is a black box -- an auditor cannot verify that a sandbox policy was enforced last Tuesday at 14:00 UTC by looking at enforcement logs alone. v0.7.4 adds runtime containment attestation (AI-SHELL.1), model distillation provenance (AI-DIST.1), MCP elicitation detection (AI-MCP.6), and incident lifecycle chains. Four governance gaps closed in one release.
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: swt3-ai
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.7.
|
|
4
|
+
version: 0.7.5
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- TeNova Labs
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-
|
|
11
|
+
date: 2026-10-06 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Mint, verify, and sign SWT3 witness anchors for AI compliance. EU AI
|
|
14
14
|
Act, NIST AI RMF, CMMC, SR 11-7. Cross-language parity with Python and TypeScript
|