swt3-ai 0.7.9 → 8.1.0

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.
Files changed (4) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +32 -8
  3. data/lib/swt3_ai.rb +1 -1
  4. metadata +2 -2
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 39703c0dc49680332602a0ae77202efb7cf3f398823bb2a1fe8a74ecd9ca96aa
4
- data.tar.gz: 7e1955bdf141fd621e310eb8da38a38c61a81e0f788d4ca97b4b307370c3f1f2
3
+ metadata.gz: ce3052fed647a41cca977b1f0dff8ffc3bac1c4cc18a831566c343c448c6dd1b
4
+ data.tar.gz: 6f69f4a40becbbae73fccb3b6dfe820c6f7e0a8106476484703b0436ceb0becb
5
5
  SHA512:
6
- metadata.gz: 981239a741062e90fa3eb5767441f07503cdd27158e8e5894ba8fc5a140d0fedda46f83863105376c7a774bf66ff7ad23c08ef4a6d0cc0aabb04ace13c9b3869
7
- data.tar.gz: 43e17b567d617cba8c32d5fea322f1347ed98e43f15639f759abe51f8adf9f1704a0c33a2263a75fec78b47ca99a1609e81479f59e4e31ad5f0a20731ec0591b
6
+ metadata.gz: e9718706cfd04efde1c06129b07da51e42937abf821dbef68fbd974a6639b06af47503f4ee9e39ca8d2a701231fb7c4a0091668eb0fbcb3f6ce06e02590cf3df
7
+ data.tar.gz: d5705c325a05913ec74b570e70e0cb1095c90fc724c354139ff6b0fed11cb1395ac239e3ff37d3930a4b776accf5e86c41ac2ff3220bfa2e1905edb5be4974b0
data/README.md CHANGED
@@ -13,6 +13,30 @@ 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
+ ---
17
+
18
+ ## v8.1.0 -- Hierarchical Milestone Merkle Trees
19
+
20
+ v8.0.0 put AI, infrastructure, and construction evidence into the same Merkle tree. v8.1.0 gives that tree hierarchical structure. A $12M commercial build has phases. A loan underwriting pipeline has stages. A battery manufacturing line has checkpoints. Flat daily Merkle roots cannot express "Phase 2 cannot begin until every milestone in Phase 1 has a passing attestation." Hierarchical milestone trees can.
21
+
22
+ The new three-tier architecture: **Structure > Phase > Milestone**. Each tier has its own domain-separated Merkle root. A single inclusion proof can verify that a specific witness anchor exists within a specific milestone, within a specific phase, within the overall structure -- three levels of cryptographic commitment in one proof.
23
+
24
+ **Why this matters for Ruby:** Rails backends that orchestrate multi-step regulated workflows -- insurance claims processing, KYC onboarding pipelines, pharmaceutical batch records -- now get cryptographic phase gates for free. Your Sidekiq worker completes a step, calls `SWT3.mint_fingerprint` with the milestone's procedure, and the hierarchical tree records exactly which step passed and when. When the compliance team asks "prove that identity verification completed before the credit pull," the answer is a Merkle inclusion proof from the milestone leaf to the structure root. No log correlation across services. No timestamp-matching across queues. One proof, mathematically verified through Ruby's `openssl` standard library.
25
+
26
+ **New in this release:**
27
+ - Three-tier Merkle hashing with domain-separated prefixes
28
+ - Phase-gate enforcement with emergency override and scope amendment support
29
+ - Multi-tier inclusion proofs (milestone > phase > structure)
30
+ - 294 procedures, 93 frameworks, 47 adapters, 11 SDK languages
31
+
32
+ ---
33
+
34
+ ## v8.0.0 -- Full Stack Governance
35
+
36
+ v8.0.0 grows SWT3 beyond AI inference into full stack governance. Your daily Merkle root now covers AI decisions, infrastructure changes, and construction process accountability. 294 procedures, 93 frameworks. Full details in the [Go SDK README](https://github.com/tenova-labs/swt3-ai-go#v080----full-stack-governance).
37
+
38
+ ---
39
+
16
40
  ## What's New in v0.7.9
17
41
 
18
42
  v0.7.9 is the ecosystem adapter release. Four new provider adapters (Groq, Together AI, DeepSeek, Azure OpenAI) and six witnessing guides bring the total adapter count to 47. Every major commercial inference provider now produces witness anchors in the same format -- one evidence stream regardless of which cloud your team chose.
@@ -26,14 +50,14 @@ v0.7.9 is the ecosystem adapter release. Four new provider adapters (Groq, Toget
26
50
 
27
51
  New guides: [OpenAI GPT](https://sovereign.tenova.io/guides/openai-gpt-compliance-witnessing.html) | [Anthropic Claude](https://sovereign.tenova.io/guides/anthropic-claude-compliance-witnessing.html) | [Google Vertex/Gemini](https://sovereign.tenova.io/guides/google-vertex-gemini-compliance-witnessing.html) | [LangChain/LangGraph](https://sovereign.tenova.io/guides/langchain-langgraph-compliance-witnessing.html) | [DeepSeek](https://sovereign.tenova.io/guides/deepseek-gpai-compliance-witnessing.html) | [Groq](https://sovereign.tenova.io/guides/groq-compliance-witnessing.html)
28
52
 
29
- **Why this matters for Ruby:** Rails API backends and Sidekiq workers that aggregate compliance data from multiple providers can now verify anchors from 47 adapters with cross-language fingerprint parity -- zero gem changes. The `@tenova/swt3-mcp` MCP server (75 tools, 78 frameworks) collects anchors from all providers, and every anchor it produces verifies against `SWT3.mint_fingerprint` in this gem. Ruby is the natural choice for compliance dashboards and webhook receivers that consume the MCP server's evidence stream.
53
+ **Why this matters for Ruby:** Rails API backends and Sidekiq workers that aggregate compliance data from multiple providers can now verify anchors from 47 adapters with cross-language fingerprint parity -- zero gem changes. The `@tenova/swt3-mcp` MCP server (75 tools, 93 frameworks) collects anchors from all providers, and every anchor it produces verifies against `SWT3.mint_fingerprint` in this gem. Ruby is the natural choice for compliance dashboards and webhook receivers that consume the MCP server's evidence stream.
30
54
 
31
55
  v0.7.9 also aligns all MCP discovery metadata (`mcp.json`, `agent-card.json`, `llms.txt`, `server.json`) to report identical version numbers and counts. Agent discovery bots and MCP crawlers see consistent metadata everywhere.
32
56
 
33
57
  ### Updated Coverage
34
58
 
35
- - 293 procedures across 10 namespaces
36
- - 78 regulatory frameworks, 340 compliance guides, 47 adapters, 10 SDK languages
59
+ - 294 procedures across 10 namespaces
60
+ - 93 regulatory frameworks, 348 compliance guides, 47 adapters, 11 SDK languages
37
61
 
38
62
  ## What's New in v0.7.8
39
63
 
@@ -66,8 +90,8 @@ Five standards bodies converged on agent governance requirements in Q3-Q4 2026.
66
90
 
67
91
  ### Updated Coverage
68
92
 
69
- - 293 procedures across 10 namespaces
70
- - 78 regulatory frameworks, 340 compliance guides
93
+ - 294 procedures across 10 namespaces
94
+ - 93 regulatory frameworks, 348 compliance guides
71
95
  - [G7 AI-SBOM Crosswalk](https://sovereign.tenova.io/guides/g7-ai-sbom-minimum-elements-crosswalk.html) | [DORA + ECB Crosswalk](https://sovereign.tenova.io/guides/dora-ecb-ai-cyber-crosswalk.html)
72
96
 
73
97
  ## What's New in v0.7.4
@@ -129,7 +153,7 @@ Two gaps closed in one release: harness-layer governance and zero-code MCP compl
129
153
 
130
154
  - 280 procedures across 77 namespaces (was 275/77)
131
155
  - 68 MCP tools (was 63)
132
- - 10 SDK languages with byte-identical output
156
+ - 11 SDK languages with byte-identical output
133
157
  - 77 framework crosswalks, 265 compliance guides
134
158
  - ~3,000 tests passing across 10 languages
135
159
 
@@ -157,7 +181,7 @@ AI does not run in a vacuum. It authenticates with service accounts, runs on har
157
181
 
158
182
  - 266 procedures across 75 namespaces (was 118/64)
159
183
  - 59 MCP tools (was 37)
160
- - 10 SDK languages with byte-identical output
184
+ - 11 SDK languages with byte-identical output
161
185
  - 36 framework crosswalks, 237 compliance guides
162
186
  - ~2,950 tests passing across 5 languages
163
187
 
@@ -198,7 +222,7 @@ The 10th language in the SWT3 ecosystem. Core primitives: fingerprint minting, H
198
222
 
199
223
  ### v0.6.4
200
224
 
201
- Version alignment across 10 SDKs. Pre-inference gate and chain reconstruction added in Python and TypeScript. 214 compliance guides.
225
+ Version alignment across 11 SDKs. Pre-inference gate and chain reconstruction added in Python and TypeScript. 348 compliance guides.
202
226
 
203
227
  ## What You Get
204
228
 
data/lib/swt3_ai.rb CHANGED
@@ -7,5 +7,5 @@ require_relative "swt3_ai/signing"
7
7
  require_relative "swt3_ai/types"
8
8
 
9
9
  module Swt3Ai
10
- VERSION = "0.5.6"
10
+ VERSION = "8.1.0"
11
11
  end
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: 0.7.9
4
+ version: 8.1.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - TeNova Labs
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2026-10-27 00:00:00.000000000 Z
11
+ date: 2026-11-10 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