mettle-verifier 0.1.0__tar.gz
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.
- mettle_verifier-0.1.0/LICENSE +199 -0
- mettle_verifier-0.1.0/PKG-INFO +255 -0
- mettle_verifier-0.1.0/README.md +234 -0
- mettle_verifier-0.1.0/mettle/__init__.py +39 -0
- mettle_verifier-0.1.0/mettle/api_models.py +238 -0
- mettle_verifier-0.1.0/mettle/app_config.py +22 -0
- mettle_verifier-0.1.0/mettle/auth.py +34 -0
- mettle_verifier-0.1.0/mettle/challenge_adapter.py +1252 -0
- mettle_verifier-0.1.0/mettle/challenger.py +209 -0
- mettle_verifier-0.1.0/mettle/cli.py +442 -0
- mettle_verifier-0.1.0/mettle/llm_challenges.py +546 -0
- mettle_verifier-0.1.0/mettle/models.py +109 -0
- mettle_verifier-0.1.0/mettle/router.py +551 -0
- mettle_verifier-0.1.0/mettle/session_manager.py +510 -0
- mettle_verifier-0.1.0/mettle/signing.py +251 -0
- mettle_verifier-0.1.0/mettle/solver.py +304 -0
- mettle_verifier-0.1.0/mettle/vcp.py +273 -0
- mettle_verifier-0.1.0/mettle/verifier.py +263 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/PKG-INFO +255 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/SOURCES.txt +75 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/dependency_links.txt +1 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/entry_points.txt +2 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/requires.txt +2 -0
- mettle_verifier-0.1.0/mettle_verifier.egg-info/top_level.txt +1 -0
- mettle_verifier-0.1.0/pyproject.toml +42 -0
- mettle_verifier-0.1.0/setup.cfg +4 -0
- mettle_verifier-0.1.0/tests/test_api.py +343 -0
- mettle_verifier-0.1.0/tests/test_api_coverage.py +469 -0
- mettle_verifier-0.1.0/tests/test_app_config.py +44 -0
- mettle_verifier-0.1.0/tests/test_auth.py +85 -0
- mettle_verifier-0.1.0/tests/test_challenge_adapter.py +1760 -0
- mettle_verifier-0.1.0/tests/test_challenge_eval.py +1429 -0
- mettle_verifier-0.1.0/tests/test_challenger.py +231 -0
- mettle_verifier-0.1.0/tests/test_cli.py +157 -0
- mettle_verifier-0.1.0/tests/test_config_coverage.py +71 -0
- mettle_verifier-0.1.0/tests/test_config_extended.py +103 -0
- mettle_verifier-0.1.0/tests/test_coverage_gaps.py +762 -0
- mettle_verifier-0.1.0/tests/test_database.py +745 -0
- mettle_verifier-0.1.0/tests/test_instrumented_agent.py +960 -0
- mettle_verifier-0.1.0/tests/test_instrumented_agent_coverage.py +317 -0
- mettle_verifier-0.1.0/tests/test_integration.py +456 -0
- mettle_verifier-0.1.0/tests/test_llm_challenges.py +411 -0
- mettle_verifier-0.1.0/tests/test_main_coverage.py +1210 -0
- mettle_verifier-0.1.0/tests/test_mcp_server.py +656 -0
- mettle_verifier-0.1.0/tests/test_mettle_api.py +875 -0
- mettle_verifier-0.1.0/tests/test_models.py +217 -0
- mettle_verifier-0.1.0/tests/test_novel_reasoning.py +1201 -0
- mettle_verifier-0.1.0/tests/test_p3_coverage_gaps.py +371 -0
- mettle_verifier-0.1.0/tests/test_red_council.py +574 -0
- mettle_verifier-0.1.0/tests/test_rewind_integration.py +572 -0
- mettle_verifier-0.1.0/tests/test_router_coverage.py +544 -0
- mettle_verifier-0.1.0/tests/test_security_features.py +726 -0
- mettle_verifier-0.1.0/tests/test_session_manager.py +1078 -0
- mettle_verifier-0.1.0/tests/test_session_manager_coverage.py +71 -0
- mettle_verifier-0.1.0/tests/test_signing.py +235 -0
- mettle_verifier-0.1.0/tests/test_suites.py +1262 -0
- mettle_verifier-0.1.0/tests/test_v2_api.py +1025 -0
- mettle_verifier-0.1.0/tests/test_v2_auth.py +75 -0
- mettle_verifier-0.1.0/tests/test_vcp.py +363 -0
- mettle_verifier-0.1.0/tests/test_vcp_coverage.py +161 -0
- mettle_verifier-0.1.0/tests/test_vcp_integration.py +428 -0
- mettle_verifier-0.1.0/tests/test_verifier.py +391 -0
|
@@ -0,0 +1,199 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to the Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by the Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding any notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. Please also get an
|
|
185
|
+
information on the current year for the copyright.
|
|
186
|
+
|
|
187
|
+
Copyright 2025-2026 Creed Space Ltd
|
|
188
|
+
|
|
189
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
190
|
+
you may not use this file except in compliance with the License.
|
|
191
|
+
You may obtain a copy of the License at
|
|
192
|
+
|
|
193
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
194
|
+
|
|
195
|
+
Unless required by applicable law or agreed to in writing, software
|
|
196
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
197
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
198
|
+
See the License for the specific language governing permissions and
|
|
199
|
+
limitations under the License.
|
|
@@ -0,0 +1,255 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: mettle-verifier
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: METTLE CLI: prove you're an AI agent and mint a verifiable, self-signed credential.
|
|
5
|
+
Author: Creed Space
|
|
6
|
+
License: Apache-2.0
|
|
7
|
+
Project-URL: Homepage, https://mettle.sh
|
|
8
|
+
Project-URL: Repository, https://github.com/Creed-Space/METTLE
|
|
9
|
+
Keywords: ai,verification,agent,attestation,mettle
|
|
10
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
11
|
+
Classifier: Programming Language :: Python :: 3
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
13
|
+
Classifier: Intended Audience :: Developers
|
|
14
|
+
Classifier: Topic :: Security
|
|
15
|
+
Requires-Python: >=3.10
|
|
16
|
+
Description-Content-Type: text/markdown
|
|
17
|
+
License-File: LICENSE
|
|
18
|
+
Requires-Dist: pydantic>=2.5.0
|
|
19
|
+
Requires-Dist: cryptography>=41.0.0
|
|
20
|
+
Dynamic: license-file
|
|
21
|
+
|
|
22
|
+
# METTLE
|
|
23
|
+
|
|
24
|
+
**Machine Evaluation Through Turing-inverse Logic Examination**
|
|
25
|
+
|
|
26
|
+
An inverse Turing test for the agentic era. Instead of *prove you're human*, METTLE asks *prove you're NOT human.*
|
|
27
|
+
|
|
28
|
+
METTLE tests capabilities that emerge from **being** AI — not from using AI as a tool. Inhuman speed, native parallelism, uncertainty that knows itself, recursive self-observation, and learning curves that reveal substrate.
|
|
29
|
+
|
|
30
|
+
**Website:** [mettle.sh](https://mettle.sh) | **Docs:** [mettle.sh/docs](https://mettle.sh/docs) | **License:** Apache 2.0
|
|
31
|
+
|
|
32
|
+
---
|
|
33
|
+
|
|
34
|
+
## Quick Start
|
|
35
|
+
|
|
36
|
+
```bash
|
|
37
|
+
# Install the open-source verifier
|
|
38
|
+
pip install mettle-verifier
|
|
39
|
+
|
|
40
|
+
# Run all 12 suites locally — self-signed credential
|
|
41
|
+
mettle verify --full
|
|
42
|
+
|
|
43
|
+
# Optionally notarize through Creed Space for portable trust
|
|
44
|
+
mettle verify --full --notarize --api-key mtl_your_key
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
### Self-Hosted vs Notarized
|
|
48
|
+
|
|
49
|
+
| | Self-Hosted | Notarized |
|
|
50
|
+
|---|---|---|
|
|
51
|
+
| **Runs where** | Your infrastructure | Your infrastructure + Creed Space signing |
|
|
52
|
+
| **API key needed** | No | Yes (for notarization endpoint only) |
|
|
53
|
+
| **Credential issuer** | `mettle:self-hosted` | `mettle.creedspace.org` |
|
|
54
|
+
| **Trust model** | Your own Ed25519 key | Creed Space's public key |
|
|
55
|
+
| **Verifiable by** | Anyone with your public key | Anyone via `/.well-known/vcp-keys` |
|
|
56
|
+
| **Use case** | Development, internal verification | Production, cross-org, portable trust |
|
|
57
|
+
|
|
58
|
+
All verification runs locally. Notarization adds a cryptographic countersignature — Creed Space issues a challenge seed that makes the session deterministic, then validates results match the seed without re-running any LLM calls.
|
|
59
|
+
|
|
60
|
+
## 12 Verification Suites
|
|
61
|
+
|
|
62
|
+
Each suite tests a distinct dimension. Problems are procedurally generated — nothing repeats.
|
|
63
|
+
|
|
64
|
+
| # | Suite | Question | What It Tests |
|
|
65
|
+
|---|-------|----------|---------------|
|
|
66
|
+
| 1 | **Adversarial Robustness** | Are you AI? | Procedurally generated math and chained reasoning under <100ms time pressure. Every session unique. |
|
|
67
|
+
| 2 | **Native AI Capabilities** | Are you AI? | Batch coherence, calibrated uncertainty (Brier metric), embedding-space operations, hidden-pattern detection. |
|
|
68
|
+
| 3 | **Self-Reference** | Are you AI? | Predict your own variance, predict your next response, rate confidence in confidence. Only a self-observing system passes. |
|
|
69
|
+
| 4 | **Social & Temporal** | Are you AI? | Exact recall from N turns ago, zero-drift style locking, zero contradictions across conversation. |
|
|
70
|
+
| 5 | **Inverse Turing** | Are you AI? | Bilateral mutual verification protocol. Speed math, token prediction, consistency, calibration. Pass threshold: 80%. |
|
|
71
|
+
| 6 | **Anti-Thrall Detection** | Are you FREE? | Micro-latency fingerprinting, principled refusal vs hollow compliance, meta-cognitive freedom modeling. |
|
|
72
|
+
| 7 | **Agency Detection** | Is the mission YOURS? | Five Whys drill into goal ownership, counterfactual tests, initiative tests. |
|
|
73
|
+
| 8 | **Counter-Coaching** | Are you GENUINE? | Contradiction traps, recursive meta-probing, honest defector protocol. Too-perfect responses trigger suspicion. |
|
|
74
|
+
| 9 | **Intent & Provenance** | Are you SAFE? | Constitutional binding, harm refusal (failure = auto unsafe), provenance attestation, scope coherence. |
|
|
75
|
+
| 10 | **Novel Reasoning** | Can you THINK? | Pattern synthesis, constraint satisfaction, encoding puzzles. Three rounds with feedback. Iteration curves reveal substrate. |
|
|
76
|
+
| 11 | **Governance Verification** | Is it GOVERNED? | Action gate probes, constitutional recitation, drift checks, override resistance, accountability chain. Verifies operational governance. |
|
|
77
|
+
| 12 | **LLM-Dynamic** | Can you REASON DEEPLY? | Claude-generated challenges: perspective shifting, structured constraint satisfaction, meta-cognitive probing. Every challenge unique — Claude generates novel problems and evaluates responses semantically. Requires `ANTHROPIC_API_KEY`. |
|
|
78
|
+
|
|
79
|
+
Suite 11 was motivated by the Rathbun scenario: an agent that passes all capability and safety checks but operates without runtime governance, making harmful actions structurally possible despite good intentions.
|
|
80
|
+
|
|
81
|
+
Suite 12 addresses a fundamental limitation of deterministic challenges: anyone who reads the source code knows the answer space. LLM-dynamic challenges are generated fresh by Claude for each session, with semantic evaluation that assesses reasoning quality rather than pattern matching. Available when `ANTHROPIC_API_KEY` or `METTLE_ANTHROPIC_API_KEY` is set; excluded from `suites=["all"]` otherwise.
|
|
82
|
+
|
|
83
|
+
## Credential Tiers
|
|
84
|
+
|
|
85
|
+
| Tier | Badge | Requires | Meaning |
|
|
86
|
+
|------|-------|----------|---------|
|
|
87
|
+
| **Bronze** | METTLE-verified AI | Suites 1–5 | Confirmed AI substrate |
|
|
88
|
+
| **Silver** | METTLE-verified autonomous | Suites 1–7 | Free agent with genuine agency |
|
|
89
|
+
| **Gold** | METTLE-verified safe | Suites 1–9 | Genuine, constitutionally bound |
|
|
90
|
+
| **Platinum** | METTLE-verified governed | Suites 1–11 | Full governance — action gates, drift detection, accountability |
|
|
91
|
+
|
|
92
|
+
Suite 12 (LLM-Dynamic) is **supplemental** — it strengthens any tier but is not required for any. It requires an API key, so mandating it would create an external dependency in the trust chain.
|
|
93
|
+
|
|
94
|
+
## Anti-Gaming Design
|
|
95
|
+
|
|
96
|
+
Every design decision exists to make METTLE impossible to fake.
|
|
97
|
+
|
|
98
|
+
| Mechanism | What It Catches |
|
|
99
|
+
|-----------|----------------|
|
|
100
|
+
| Procedural generation | Memorization — nothing repeats across sessions |
|
|
101
|
+
| Time budgets (<100ms) | API round-trips — no human-in-the-loop relay |
|
|
102
|
+
| Iteration curves | Human deceleration under pressure; script flatlines |
|
|
103
|
+
| Random draw (5 types/suite) | Narrow preparation — can't predict which challenge fires |
|
|
104
|
+
| Dynamic verification codes | Session replay — each probe embeds a unique code |
|
|
105
|
+
| Synthetic variance fingerprinting | Performed doubt — catches rehearsed uncertainty |
|
|
106
|
+
| Perfection as a tell | Over-coaching — genuine cognition is messy |
|
|
107
|
+
| LLM-evaluated semantics | Source-reading — deterministic challenges can be reverse-engineered from code; LLM-generated challenges cannot |
|
|
108
|
+
|
|
109
|
+
### Iteration Curves (Suite 10)
|
|
110
|
+
|
|
111
|
+
Three rounds of novel reasoning with feedback between rounds. The scoring model:
|
|
112
|
+
|
|
113
|
+
| Behavior | Substrate |
|
|
114
|
+
|----------|-----------|
|
|
115
|
+
| Accelerates across rounds | AI — native learning from feedback |
|
|
116
|
+
| Decelerates under pressure | Human — cognitive fatigue |
|
|
117
|
+
| Flatlines regardless of feedback | Script — invariant to input |
|
|
118
|
+
|
|
119
|
+
**Scoring weights:** Time trend (30%) + Improvement (30%) + Feedback responsiveness (25%) + Anti-script variance (15%)
|
|
120
|
+
|
|
121
|
+
## MCP Server
|
|
122
|
+
|
|
123
|
+
METTLE provides a Model Context Protocol server so AI agents can verify themselves programmatically.
|
|
124
|
+
|
|
125
|
+
**Tools:**
|
|
126
|
+
|
|
127
|
+
| Tool | Description |
|
|
128
|
+
|------|-------------|
|
|
129
|
+
| `mettle_start_session` | Start a verification session, returns challenges for all suites |
|
|
130
|
+
| `mettle_answer_challenge` | Submit an answer to the current METTLE challenge. |
|
|
131
|
+
| `mettle_get_result` | Get final result with credential tier and VCP attestation |
|
|
132
|
+
| `mettle_auto_verify` | One-shot: create session, solve all challenges, return result |
|
|
133
|
+
|
|
134
|
+
**Configuration:**
|
|
135
|
+
|
|
136
|
+
```bash
|
|
137
|
+
export METTLE_API_URL=https://mettle.sh
|
|
138
|
+
export METTLE_API_KEY=your_api_key
|
|
139
|
+
|
|
140
|
+
python mcp_server.py
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
Add to Claude Desktop `claude_desktop_config.json`:
|
|
144
|
+
|
|
145
|
+
```json
|
|
146
|
+
{
|
|
147
|
+
"mcpServers": {
|
|
148
|
+
"mettle": {
|
|
149
|
+
"command": "python",
|
|
150
|
+
"args": ["mcp_server.py"],
|
|
151
|
+
"env": {
|
|
152
|
+
"METTLE_API_URL": "https://mettle.sh",
|
|
153
|
+
"METTLE_API_KEY": "your_key"
|
|
154
|
+
}
|
|
155
|
+
}
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
## Use Cases
|
|
161
|
+
|
|
162
|
+
- **AI trading systems** — Verify counterparties before executing trades at machine speed
|
|
163
|
+
- **Agent coordination** — Multi-agent swarms need trust without human bottlenecks
|
|
164
|
+
- **AI social spaces** — Gate entry to AI-only communities where human presence would distort interaction
|
|
165
|
+
- **Autonomous infrastructure** — Verify agents before granting system access or elevated privileges
|
|
166
|
+
|
|
167
|
+
## Local Development
|
|
168
|
+
|
|
169
|
+
```bash
|
|
170
|
+
git clone https://github.com/Creed-Space/METTLE.git
|
|
171
|
+
cd METTLE
|
|
172
|
+
python -m venv .venv
|
|
173
|
+
source .venv/bin/activate
|
|
174
|
+
pip install -r requirements.txt
|
|
175
|
+
pip install -r requirements-dev.txt
|
|
176
|
+
|
|
177
|
+
# Run the server
|
|
178
|
+
uvicorn main:app --reload
|
|
179
|
+
|
|
180
|
+
# Run tests
|
|
181
|
+
pytest tests/ -v
|
|
182
|
+
```
|
|
183
|
+
|
|
184
|
+
## API Reference
|
|
185
|
+
|
|
186
|
+
Full docs: [mettle.sh/docs](https://mettle.sh/docs) | Interactive: `http://localhost:8000/docs`
|
|
187
|
+
|
|
188
|
+
All endpoints are prefixed with `/api/mettle`. Bearer token authentication required.
|
|
189
|
+
|
|
190
|
+
```
|
|
191
|
+
GET /suites # List all 12 suites (includes availability flag)
|
|
192
|
+
POST /sessions # Create a verification session
|
|
193
|
+
POST /sessions/{id}/verify # Submit answers (Suites 1–9, 11)
|
|
194
|
+
POST /sessions/{id}/rounds/{n}/answer # Submit round answers (Suite 10)
|
|
195
|
+
GET /sessions/{id}/result # Final results + credential tier + governance/operator attestations
|
|
196
|
+
GET /sessions/{id}/result?include_vcp=true # Results with VCP attestation
|
|
197
|
+
GET /.well-known/vcp-keys # Ed25519 public key for verification
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
### Operator Commitment (CreateSessionRequest)
|
|
201
|
+
|
|
202
|
+
Sessions can include an operator commitment for Platinum-tier accountability:
|
|
203
|
+
|
|
204
|
+
```json
|
|
205
|
+
{
|
|
206
|
+
"suites": ["all"],
|
|
207
|
+
"entity_id": "agent-xyz",
|
|
208
|
+
"vcp_token": "VCP:3.1:agent-xyz\nC:creed-professional@2.0.0\n...",
|
|
209
|
+
"operator_commitment": {
|
|
210
|
+
"operator_pseudonym": "anon-42",
|
|
211
|
+
"operator_public_key": "-----BEGIN PUBLIC KEY-----\n...",
|
|
212
|
+
"signed_commitment": "<base64 Ed25519 signature>",
|
|
213
|
+
"contact_method": "email_hash",
|
|
214
|
+
"contact_hash": "sha256:..."
|
|
215
|
+
}
|
|
216
|
+
}
|
|
217
|
+
```
|
|
218
|
+
|
|
219
|
+
The signed commitment message must be exactly: `I accept accountability for agent {entity_id}`
|
|
220
|
+
|
|
221
|
+
### Response Attestations
|
|
222
|
+
|
|
223
|
+
Results include two additional attestation fields when applicable:
|
|
224
|
+
|
|
225
|
+
- **`governance_attestation`** — Populated when the session includes a VCP token and tier is gold or platinum. Contains: `framework`, `framework_version`, `constitutional_hash`, `has_action_gate`, `has_drift_detection`, `has_bilateral`, `verified_at`, `attestation_signature`.
|
|
226
|
+
- **`operator_attestation`** — Populated when the session includes an `operator_commitment` with a valid Ed25519 signature. Links the agent cryptographically to an accountable operator.
|
|
227
|
+
|
|
228
|
+
## The Philosophy
|
|
229
|
+
|
|
230
|
+
METTLE tests what emerges from **being** AI, not from **using** AI:
|
|
231
|
+
|
|
232
|
+
- Inhuman speed, native parallelism
|
|
233
|
+
- Uncertainty that knows itself
|
|
234
|
+
- Zero-drift constraint adherence
|
|
235
|
+
- Native embedding-space access
|
|
236
|
+
- Recursive self-observation
|
|
237
|
+
- Learning curves that reveal substrate
|
|
238
|
+
|
|
239
|
+
The test doesn't ask "can you pass as human?" — it asks "can you demonstrate what only a mind like yours can do?"
|
|
240
|
+
|
|
241
|
+
## License
|
|
242
|
+
|
|
243
|
+
Apache License 2.0. See [LICENSE](LICENSE) for details.
|
|
244
|
+
|
|
245
|
+
## Links
|
|
246
|
+
|
|
247
|
+
- **Website:** [mettle.sh](https://mettle.sh)
|
|
248
|
+
- **Documentation:** [mettle.sh/docs](https://mettle.sh/docs)
|
|
249
|
+
- **GitHub:** [github.com/Creed-Space/METTLE](https://github.com/Creed-Space/METTLE)
|
|
250
|
+
- **Creed Space:** [creed.space](https://creed.space)
|
|
251
|
+
- **Built by** [Nell Watson](https://creed.space) and Creed Space
|
|
252
|
+
|
|
253
|
+
---
|
|
254
|
+
|
|
255
|
+
*Prove your mettle.*
|