swt3-ai 0.7.6 → 0.7.9

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 (3) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +45 -6
  3. metadata +3 -3
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 2804165b1d97174addcb0a5b49b9c867d04fa9589ea74c3213d0eb5fbbff1cff
4
- data.tar.gz: 13bc333cb8ad09e7bb6864bf0206df7cf3711388bab8ba620fe8b78e9a606aef
3
+ metadata.gz: 39703c0dc49680332602a0ae77202efb7cf3f398823bb2a1fe8a74ecd9ca96aa
4
+ data.tar.gz: 7e1955bdf141fd621e310eb8da38a38c61a81e0f788d4ca97b4b307370c3f1f2
5
5
  SHA512:
6
- metadata.gz: ff807620f255a338b0f73dd31d47f96324c179d7333870a7f0dddd84e10831c8f73966bd09e4b41cd325e108a9c5eb1736194534166cc4ff71f7b081ded8422a
7
- data.tar.gz: 4ee9df202beb71987f96e6e35ae63469e966c2e9f6a55faa86f0d81501ab9bf3fc3315925f16576d8560d4d0d58e3012a8d691a6021ebb6bdf907c8f5030c5e1
6
+ metadata.gz: 981239a741062e90fa3eb5767441f07503cdd27158e8e5894ba8fc5a140d0fedda46f83863105376c7a774bf66ff7ad23c08ef4a6d0cc0aabb04ace13c9b3869
7
+ data.tar.gz: 43e17b567d617cba8c32d5fea322f1347ed98e43f15639f759abe51f8adf9f1704a0c33a2263a75fec78b47ca99a1609e81479f59e4e31ad5f0a20731ec0591b
data/README.md CHANGED
@@ -5,7 +5,7 @@ Add cryptographic compliance evidence to existing Ruby applications. Three lines
5
5
 
6
6
  # swt3-ai
7
7
 
8
- **SWT3 AI Witness SDK for Ruby**: mint, verify, and sign SWT3 witness anchors with cross-language parity. Uses only `openssl` from the standard library. No native extensions, no C bindings, no dependency risk.
8
+ **SWT3™ AI Witness SDK for Ruby**: mint, verify, and sign SWT3 witness anchors with cross-language parity. Uses only `openssl` from the standard library. No native extensions, no C bindings, no dependency risk.
9
9
 
10
10
  Built for platform engineers who need to bolt compliance witnessing onto production Rails apps, Sidekiq workers, Grape APIs, or any Ruby service that touches AI. Your Python team trains the model; your Ruby infrastructure serves it, monitors it, and proves it followed the rules. When a model drifts at 2am, the anchor chain tells you which model version, which pipeline deployed it, and which policy approved it.
11
11
 
@@ -13,6 +13,45 @@ 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 v0.7.9
17
+
18
+ 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.
19
+
20
+ | Adapter | Provider Tag | Notes |
21
+ |---------|-------------|-------|
22
+ | `wrap_groq` / `wrapGroq` | `groq` | LPU inference with latency capture |
23
+ | `wrap_together` / `wrapTogether` | `together` | Open-weight model serving |
24
+ | `wrap_deepseek` / `wrapDeepSeek` | `deepseek` | R1 reasoning chain witnessing |
25
+ | `wrap_azure_openai` / `wrapAzureOpenAI` | `azure-openai` | Deployment name preservation, content filter detection |
26
+
27
+ 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
+
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.
30
+
31
+ 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
+
33
+ ### Updated Coverage
34
+
35
+ - 293 procedures across 10 namespaces
36
+ - 78 regulatory frameworks, 340 compliance guides, 47 adapters, 10 SDK languages
37
+
38
+ ## What's New in v0.7.8
39
+
40
+ Six new adapters unify evidence collection across IBM watsonx, AWS Bedrock, AWS Strands, and Mistral AI. Organizations running models across multiple cloud providers no longer need to reconcile separate audit trails -- every inference and policy decision produces a witness anchor in the same format regardless of provider.
41
+
42
+ | Provider | Adapter | What it witnesses | Why it matters |
43
+ |----------|---------|-------------------|----------------|
44
+ | IBM watsonx.ai | `wrap_granite` | `generate()`, `generate_text()`, streaming | Enterprise AI on IBM's regulated cloud -- banks and insurers run Granite for document processing |
45
+ | AWS Bedrock Guardrails | `wrap_bedrock_guardrails` | `apply_guardrail()` policy decisions (AI-GRD.1) | Content filtering audit trail -- proves guardrails were active, not just configured |
46
+ | AWS Strands | `wrap_strands` | Agent callable invocations (AI-INF.1) | AWS agent orchestration framework -- 120+ enterprise customers with zero built-in audit |
47
+ | Mistral AI | `wrap_mistral` | `chat.complete()`, `chat.stream()`, async | European sovereign AI -- Mistral runs on EU infrastructure, GPAI compliance required since Aug 2 |
48
+ | NVIDIA NemoClaw | `NemoClawWitness` | Policy engine decisions (AI-GRD.1) | Hardware-level AI governance -- NeMo Guardrails policy decisions witnessed independently |
49
+ | NVIDIA ROSClaw | `ROSClawWitness` | ROS 2 robotics audit log events | Robotics compliance -- EU Machinery Regulation (Jan 2027) requires AI decision evidence in safety-critical robots |
50
+
51
+ Guides: [IBM Granite Adapter](https://sovereign.tenova.io/guides/ibm-granite-watsonx-crosswalk.html) | [AWS Bedrock Guardrails](https://sovereign.tenova.io/guides/aws-bedrock-guardrails-crosswalk.html) | [Mistral AI Adapter](https://sovereign.tenova.io/guides/mistral-ai-governance-crosswalk.html) | [NVIDIA NemoClaw](https://sovereign.tenova.io/guides/nvidia-nemoclaw-governance-crosswalk.html)
52
+
53
+ **Why this matters for Ruby:** Ruby applications that aggregate compliance data from multiple AI providers -- common in fintech and regulated SaaS -- can now verify witness anchors from IBM Granite, AWS Bedrock, and Mistral inferences alongside existing OpenAI and Anthropic anchors. Cross-language fingerprint parity means a Ruby verification service trusts anchors from any SDK language. v0.7.8 brings all SDKs back to version lockstep.
54
+
16
55
  ## What's New in v0.7.6
17
56
 
18
57
  Five standards bodies converged on agent governance requirements in Q3-Q4 2026. v0.7.6 adds three procedures -- delegation chain integrity, scope boundary attestation, and agent interrupt witnessing -- and aligns crosswalks to G7 AI-SBOM, DORA, Singapore Agentic MGF, and the upcoming NIST Agent Profile.
@@ -27,8 +66,8 @@ Five standards bodies converged on agent governance requirements in Q3-Q4 2026.
27
66
 
28
67
  ### Updated Coverage
29
68
 
30
- - 289 procedures across 10 namespaces
31
- - 85 regulatory frameworks, 310 compliance guides
69
+ - 293 procedures across 10 namespaces
70
+ - 78 regulatory frameworks, 340 compliance guides
32
71
  - [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)
33
72
 
34
73
  ## What's New in v0.7.4
@@ -336,10 +375,10 @@ All SWT3 SDKs produce identical fingerprints from the same inputs. A unified aud
336
375
 
337
376
  | Your Stack | SDK | What You Get |
338
377
  |-----------|-----|-------------|
339
- | Python ML pipeline | [swt3-ai (PyPI)](https://pypi.org/project/swt3-ai/) | Full witness pipeline: `wrap(client)`, buffer management, clearing engine, 21 adapters (OpenAI, Anthropic, Bedrock, vLLM, Ollama, LiteLLM, LangChain, CrewAI, etc.) |
378
+ | Python ML pipeline | [swt3-ai (PyPI)](https://pypi.org/project/swt3-ai/) | Full witness pipeline: `wrap(client)`, buffer management, clearing engine, 47 adapters (OpenAI, Anthropic, Bedrock, vLLM, Ollama, LiteLLM, LangChain, CrewAI, Groq, DeepSeek, etc.) |
340
379
  | TypeScript/Node API | [@tenova/swt3-ai (npm)](https://www.npmjs.com/package/@tenova/swt3-ai) | ES6 Proxy wrapping, streaming support, Vercel AI SDK adapter, OTel export |
341
380
  | Rails, Sidekiq, Grape, Hanami | **swt3-ai (this gem)** | Fingerprint, signing, and verification primitives. Embed witnessing into controllers, workers, middleware, or rake tasks |
342
- | MCP-enabled agents | [@tenova/swt3-mcp](https://www.npmjs.com/package/@tenova/swt3-mcp) | 37 MCP tools, transport middleware for zero-code witnessing |
381
+ | MCP-enabled agents | [@tenova/swt3-mcp](https://www.npmjs.com/package/@tenova/swt3-mcp) | 75 MCP tools, transport middleware for zero-code witnessing |
343
382
 
344
383
  Your Python team trains the model and wraps inference with the full pipeline. Your Ruby infrastructure witnesses every downstream decision, API call, and background job that touches the model's output. Same fingerprints, same anchors, same audit trail.
345
384
 
@@ -367,6 +406,6 @@ Your prompts and responses **never leave your infrastructure**. The SDK computes
367
406
 
368
407
  *SWT3: Sovereign Witness Traceability. We don't run your models. We witness them.*
369
408
 
370
- SWT3 and Sovereign Witness Traceability are trademarks of Tenable Nova LLC. Patent pending. Apache 2.0 licensed.
409
+ SWT3, swt3-ai, TeNova, Axiom Sovereign Engine, UCT, and Sovereign Score are trademarks of Tenable Nova LLC. Patent pending. Apache 2.0 licensed.
371
410
 
372
411
  This project is not affiliated with, endorsed by, or sponsored by any third-party AI provider. All third-party trademarks are the property of their respective owners. Use of these names is for identification and interoperability purposes only.
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: 0.7.6
4
+ version: 0.7.9
5
5
  platform: ruby
6
6
  authors:
7
7
  - TeNova Labs
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2026-10-13 00:00:00.000000000 Z
11
+ date: 2026-10-27 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
@@ -53,5 +53,5 @@ rubygems_version: 3.4.20
53
53
  signing_key:
54
54
  specification_version: 4
55
55
  summary: 'SWT3 AI Witness SDK: cryptographic attestation for AI inference and infrastructure
56
- governance. 280 procedures, 9 namespaces, 10 languages, 77 frameworks.'
56
+ governance. 293 procedures, 10 namespaces, 10 languages, 78 frameworks, 47 adapters.'
57
57
  test_files: []