agent-os-kernel 1.1.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

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 (1051) hide show
  1. agent_os/__init__.py +66 -4
  2. agent_os/agents_compat.py +286 -0
  3. agent_os/base_agent.py +308 -0
  4. agent_os/cli.py +1079 -19
  5. agent_os/integrations/__init__.py +37 -2
  6. agent_os/integrations/openai_adapter.py +502 -0
  7. agent_os/integrations/semantic_kernel_adapter.py +569 -0
  8. agent_os/stateless.py +349 -0
  9. agent_os_kernel-1.3.0.dist-info/METADATA +676 -0
  10. agent_os_kernel-1.3.0.dist-info/RECORD +1053 -0
  11. {agent_os_kernel-1.1.0.dist-info → agent_os_kernel-1.3.0.dist-info}/entry_points.txt +0 -1
  12. modules/amb/.github/workflows/ci.yml +102 -0
  13. modules/amb/.github/workflows/publish.yml +146 -0
  14. modules/amb/.gitignore +134 -0
  15. modules/amb/CHANGELOG.md +118 -0
  16. modules/amb/CONTRIBUTING.md +141 -0
  17. modules/amb/LICENSE +21 -0
  18. modules/amb/README.md +188 -0
  19. modules/amb/amb_core/__init__.py +175 -0
  20. modules/amb/amb_core/adapters/__init__.py +55 -0
  21. modules/amb/amb_core/adapters/aws_sqs_broker.py +374 -0
  22. modules/amb/amb_core/adapters/azure_servicebus_broker.py +338 -0
  23. modules/amb/amb_core/adapters/kafka_broker.py +258 -0
  24. modules/amb/amb_core/adapters/nats_broker.py +283 -0
  25. modules/amb/amb_core/adapters/rabbitmq_broker.py +233 -0
  26. modules/amb/amb_core/adapters/redis_broker.py +260 -0
  27. modules/amb/amb_core/broker.py +143 -0
  28. modules/amb/amb_core/bus.py +479 -0
  29. modules/amb/amb_core/cloudevents.py +507 -0
  30. modules/amb/amb_core/dlq.py +343 -0
  31. modules/amb/amb_core/hf_utils.py +534 -0
  32. modules/amb/amb_core/memory_broker.py +408 -0
  33. modules/amb/amb_core/models.py +139 -0
  34. modules/amb/amb_core/persistence.py +527 -0
  35. modules/amb/amb_core/schema.py +292 -0
  36. modules/amb/amb_core/tracing.py +356 -0
  37. modules/amb/examples/advanced_features.py +223 -0
  38. modules/amb/examples/backpressure_demo.py +225 -0
  39. modules/amb/examples/basic_usage.py +117 -0
  40. modules/amb/examples/tracing_demo.py +104 -0
  41. modules/amb/experiments/README.md +52 -0
  42. modules/amb/experiments/reproduce_results.py +467 -0
  43. modules/amb/experiments/results.json +324 -0
  44. modules/amb/paper/README.md +40 -0
  45. modules/amb/paper/paper.tex +365 -0
  46. modules/amb/paper/whitepaper.md +377 -0
  47. modules/amb/pyproject.toml +117 -0
  48. modules/amb/tests/__init__.py +1 -0
  49. modules/amb/tests/test_backpressure_priority.py +280 -0
  50. modules/amb/tests/test_bus.py +198 -0
  51. modules/amb/tests/test_cloudevents.py +443 -0
  52. modules/amb/tests/test_features.py +531 -0
  53. modules/amb/tests/test_models.py +74 -0
  54. modules/amb/tests/test_tracing.py +254 -0
  55. modules/atr/.github/workflows/ci.yml +101 -0
  56. modules/atr/.github/workflows/publish.yml +140 -0
  57. modules/atr/.gitignore +134 -0
  58. modules/atr/.pre-commit-config.yaml +37 -0
  59. modules/atr/CHANGELOG.md +39 -0
  60. modules/atr/CONTRIBUTING.md +96 -0
  61. modules/atr/IMPLEMENTATION_SUMMARY.md +143 -0
  62. modules/atr/README.md +180 -0
  63. modules/atr/atr/__init__.py +638 -0
  64. modules/atr/atr/access.py +346 -0
  65. modules/atr/atr/composition.py +643 -0
  66. modules/atr/atr/decorator.py +355 -0
  67. modules/atr/atr/executor.py +382 -0
  68. modules/atr/atr/health.py +555 -0
  69. modules/atr/atr/hf_utils.py +447 -0
  70. modules/atr/atr/injection.py +420 -0
  71. modules/atr/atr/metrics.py +438 -0
  72. modules/atr/atr/policies.py +401 -0
  73. modules/atr/atr/py.typed +2 -0
  74. modules/atr/atr/registry.py +450 -0
  75. modules/atr/atr/schema.py +478 -0
  76. modules/atr/atr/tools/safe/__init__.py +73 -0
  77. modules/atr/atr/tools/safe/calculator.py +380 -0
  78. modules/atr/atr/tools/safe/datetime_tool.py +441 -0
  79. modules/atr/atr/tools/safe/file_reader.py +400 -0
  80. modules/atr/atr/tools/safe/http_client.py +314 -0
  81. modules/atr/atr/tools/safe/json_parser.py +372 -0
  82. modules/atr/atr/tools/safe/text_tool.py +526 -0
  83. modules/atr/atr/tools/safe/toolkit.py +173 -0
  84. modules/atr/docs/PYPI_SETUP.md +113 -0
  85. modules/atr/examples/README.md +27 -0
  86. modules/atr/examples/demo.py +144 -0
  87. modules/atr/examples/sandbox_demo.py +218 -0
  88. modules/atr/experiments/README.md +69 -0
  89. modules/atr/experiments/reproduce_results.py +509 -0
  90. modules/atr/experiments/results/.gitkeep +0 -0
  91. modules/atr/experiments/results/results_20260123_140334.json +71 -0
  92. modules/atr/paper/README.md +36 -0
  93. modules/atr/paper/figures/.gitkeep +0 -0
  94. modules/atr/paper/references.bib +84 -0
  95. modules/atr/paper/structure.tex +293 -0
  96. modules/atr/paper/whitepaper.md +234 -0
  97. modules/atr/pyproject.toml +148 -0
  98. modules/atr/requirements.txt +1 -0
  99. modules/atr/setup.py +30 -0
  100. modules/atr/tests/__init__.py +1 -0
  101. modules/atr/tests/test_decorator.py +317 -0
  102. modules/atr/tests/test_executor.py +245 -0
  103. modules/atr/tests/test_integration_executor.py +184 -0
  104. modules/atr/tests/test_registry.py +312 -0
  105. modules/atr/tests/test_schema.py +182 -0
  106. modules/atr/tests/test_v2_features.py +708 -0
  107. modules/caas/.dockerignore +63 -0
  108. modules/caas/.github/ISSUE_TEMPLATE/bug_report.md +38 -0
  109. modules/caas/.github/ISSUE_TEMPLATE/custom.md +10 -0
  110. modules/caas/.github/ISSUE_TEMPLATE/feature_request.md +20 -0
  111. modules/caas/.github/workflows/ci.yml +100 -0
  112. modules/caas/.github/workflows/lint.yml +39 -0
  113. modules/caas/.github/workflows/publish-pypi.yml +124 -0
  114. modules/caas/.gitignore +73 -0
  115. modules/caas/.pre-commit-config.yaml +33 -0
  116. modules/caas/CHANGELOG.md +58 -0
  117. modules/caas/CONTRIBUTING.md +346 -0
  118. modules/caas/Dockerfile +41 -0
  119. modules/caas/LICENSE +21 -0
  120. modules/caas/MANIFEST.in +11 -0
  121. modules/caas/README.md +158 -0
  122. modules/caas/benchmarks/README.md +255 -0
  123. modules/caas/benchmarks/create_hf_dataset.py +502 -0
  124. modules/caas/benchmarks/data/sample_corpus/README.md +86 -0
  125. modules/caas/benchmarks/data/sample_corpus/auth_module.py +211 -0
  126. modules/caas/benchmarks/data/sample_corpus/contribution_guide.md +185 -0
  127. modules/caas/benchmarks/data/sample_corpus/remote_work_policy.html +57 -0
  128. modules/caas/benchmarks/hf_dataset/README.md +214 -0
  129. modules/caas/benchmarks/hf_dataset/caas_benchmark_corpus.py +73 -0
  130. modules/caas/benchmarks/hf_dataset/corpus_preview.json +193 -0
  131. modules/caas/benchmarks/results/README.md +66 -0
  132. modules/caas/benchmarks/results/evaluation_2026-01-20.json +121 -0
  133. modules/caas/benchmarks/run_evaluation.py +561 -0
  134. modules/caas/benchmarks/statistical_tests.py +289 -0
  135. modules/caas/benchmarks/verify_sample_corpus.py +83 -0
  136. modules/caas/docker-compose.yml +38 -0
  137. modules/caas/docs/CONTEXT_TRIAD.md +462 -0
  138. modules/caas/docs/CONTRIBUTING.md +346 -0
  139. modules/caas/docs/ETHICS_AND_LIMITATIONS.md +336 -0
  140. modules/caas/docs/HEURISTIC_ROUTER.md +442 -0
  141. modules/caas/docs/IMPLEMENTATION_SUMMARY.md +363 -0
  142. modules/caas/docs/IMPLEMENTATION_SUMMARY_CONTEXT_TRIAD.md +277 -0
  143. modules/caas/docs/IMPLEMENTATION_SUMMARY_HEURISTIC_ROUTER.md +231 -0
  144. modules/caas/docs/IMPLEMENTATION_SUMMARY_METADATA_INJECTION.md +258 -0
  145. modules/caas/docs/IMPLEMENTATION_SUMMARY_PRAGMATIC_TRUTH.md +212 -0
  146. modules/caas/docs/IMPLEMENTATION_SUMMARY_TRUST_GATEWAY.md +319 -0
  147. modules/caas/docs/LAYER_1_PRIMITIVE.md +202 -0
  148. modules/caas/docs/METADATA_INJECTION.md +404 -0
  149. modules/caas/docs/PRAGMATIC_TRUTH.md +431 -0
  150. modules/caas/docs/RELATED_WORK.md +312 -0
  151. modules/caas/docs/RELEASE_CHECKLIST.md +219 -0
  152. modules/caas/docs/RELEASE_GUIDE.md +285 -0
  153. modules/caas/docs/REPRODUCIBILITY.md +386 -0
  154. modules/caas/docs/SLIDING_WINDOW.md +387 -0
  155. modules/caas/docs/STRUCTURE_AWARE_INDEXING.md +158 -0
  156. modules/caas/docs/TESTING.md +259 -0
  157. modules/caas/docs/THREAT_MODEL.md +247 -0
  158. modules/caas/docs/TRUST_GATEWAY.md +575 -0
  159. modules/caas/docs/VFS.md +298 -0
  160. modules/caas/examples/agents/enterprise_security_agent.py +414 -0
  161. modules/caas/examples/agents/intelligent_document_analyzer.py +380 -0
  162. modules/caas/examples/demos/demo.py +309 -0
  163. modules/caas/examples/demos/demo_context_triad.py +225 -0
  164. modules/caas/examples/demos/demo_conversation_manager.py +285 -0
  165. modules/caas/examples/demos/demo_heuristic_router.py +133 -0
  166. modules/caas/examples/demos/demo_metadata_injection.py +198 -0
  167. modules/caas/examples/demos/demo_pragmatic_truth.py +303 -0
  168. modules/caas/examples/demos/demo_structure_aware.py +140 -0
  169. modules/caas/examples/demos/demo_time_decay.py +247 -0
  170. modules/caas/examples/demos/demo_trust_gateway.py +383 -0
  171. modules/caas/examples/multi_agent/README.md +159 -0
  172. modules/caas/examples/multi_agent/research_team.py +369 -0
  173. modules/caas/examples/multi_agent/vfs_collaboration.py +393 -0
  174. modules/caas/examples/usage/auth_module.py +142 -0
  175. modules/caas/examples/usage/usage_example.py +173 -0
  176. modules/caas/experiments/README.md +42 -0
  177. modules/caas/experiments/reproduce_results.py +462 -0
  178. modules/caas/paper/ARXIV_METADATA.md +145 -0
  179. modules/caas/paper/ARXIV_README.md +47 -0
  180. modules/caas/paper/CHECKLIST.md +103 -0
  181. modules/caas/paper/GITHUB_RELEASE_NOTES.md +105 -0
  182. modules/caas/paper/README.md +71 -0
  183. modules/caas/paper/abstract.md +24 -0
  184. modules/caas/paper/arxiv_submission.tar +0 -0
  185. modules/caas/paper/arxiv_submission.zip +0 -0
  186. modules/caas/paper/build_pdf.py +355 -0
  187. modules/caas/paper/experiments.md +149 -0
  188. modules/caas/paper/figures/.gitkeep +0 -0
  189. modules/caas/paper/figures/README.md +237 -0
  190. modules/caas/paper/figures/fig1_system_architecture.png +0 -0
  191. modules/caas/paper/figures/fig1_system_architecture.svg +198 -0
  192. modules/caas/paper/figures/fig2_context_triad.png +0 -0
  193. modules/caas/paper/figures/fig2_context_triad.svg +105 -0
  194. modules/caas/paper/figures/fig3_ablation_results.png +0 -0
  195. modules/caas/paper/figures/fig3_ablation_results.svg +113 -0
  196. modules/caas/paper/figures/fig4_routing_latency.png +0 -0
  197. modules/caas/paper/figures/fig4_routing_latency.svg +97 -0
  198. modules/caas/paper/intro.md +103 -0
  199. modules/caas/paper/latex/figures/fig1_system_architecture.png +0 -0
  200. modules/caas/paper/latex/figures/fig2_context_triad.png +0 -0
  201. modules/caas/paper/latex/figures/fig3_ablation_results.png +0 -0
  202. modules/caas/paper/latex/figures/fig4_routing_latency.png +0 -0
  203. modules/caas/paper/latex/main.tex +468 -0
  204. modules/caas/paper/latex/references.bib +140 -0
  205. modules/caas/paper/method.md +350 -0
  206. modules/caas/paper/outline.md +123 -0
  207. modules/caas/paper/related_work.md +101 -0
  208. modules/caas/paper/tables/.gitkeep +0 -0
  209. modules/caas/paper/tables/results_tables.md +50 -0
  210. modules/caas/pyproject.toml +172 -0
  211. modules/caas/requirements.txt +11 -0
  212. modules/caas/src/caas/__init__.py +232 -0
  213. modules/caas/src/caas/api/__init__.py +7 -0
  214. modules/caas/src/caas/api/server.py +1326 -0
  215. modules/caas/src/caas/caching.py +832 -0
  216. modules/caas/src/caas/cli.py +208 -0
  217. modules/caas/src/caas/conversation.py +221 -0
  218. modules/caas/src/caas/decay.py +118 -0
  219. modules/caas/src/caas/detection/__init__.py +7 -0
  220. modules/caas/src/caas/detection/detector.py +236 -0
  221. modules/caas/src/caas/enrichment.py +127 -0
  222. modules/caas/src/caas/gateway/__init__.py +24 -0
  223. modules/caas/src/caas/gateway/trust_gateway.py +471 -0
  224. modules/caas/src/caas/hf_utils.py +477 -0
  225. modules/caas/src/caas/ingestion/__init__.py +21 -0
  226. modules/caas/src/caas/ingestion/processors.py +251 -0
  227. modules/caas/src/caas/ingestion/structure_parser.py +185 -0
  228. modules/caas/src/caas/models.py +354 -0
  229. modules/caas/src/caas/pragmatic_truth.py +441 -0
  230. modules/caas/src/caas/routing/__init__.py +8 -0
  231. modules/caas/src/caas/routing/heuristic_router.py +242 -0
  232. modules/caas/src/caas/storage/__init__.py +7 -0
  233. modules/caas/src/caas/storage/store.py +450 -0
  234. modules/caas/src/caas/triad.py +472 -0
  235. modules/caas/src/caas/tuning/__init__.py +7 -0
  236. modules/caas/src/caas/tuning/tuner.py +322 -0
  237. modules/caas/src/caas/vfs/__init__.py +12 -0
  238. modules/caas/src/caas/vfs/filesystem.py +450 -0
  239. modules/caas/tests/__init__.py +3 -0
  240. modules/caas/tests/conftest.py +8 -0
  241. modules/caas/tests/test_caching.py +628 -0
  242. modules/caas/tests/test_context_triad.py +385 -0
  243. modules/caas/tests/test_conversation_manager.py +289 -0
  244. modules/caas/tests/test_functionality.py +215 -0
  245. modules/caas/tests/test_heuristic_router.py +370 -0
  246. modules/caas/tests/test_metadata_injection.py +328 -0
  247. modules/caas/tests/test_pragmatic_truth.py +322 -0
  248. modules/caas/tests/test_structure_aware_indexing.py +283 -0
  249. modules/caas/tests/test_time_decay.py +268 -0
  250. modules/caas/tests/test_trust_gateway.py +445 -0
  251. modules/caas/tests/test_vfs.py +298 -0
  252. modules/cmvk/.github/FUNDING.yml +9 -0
  253. modules/cmvk/.github/dependabot.yml +54 -0
  254. modules/cmvk/.github/workflows/ci.yml +205 -0
  255. modules/cmvk/.github/workflows/publish.yml +143 -0
  256. modules/cmvk/.gitignore +147 -0
  257. modules/cmvk/.pre-commit-config.yaml +58 -0
  258. modules/cmvk/CHANGELOG.md +146 -0
  259. modules/cmvk/CITATION.cff +48 -0
  260. modules/cmvk/CONTRIBUTING.md +229 -0
  261. modules/cmvk/Dockerfile +87 -0
  262. modules/cmvk/HF_MODEL_CARD.md +185 -0
  263. modules/cmvk/LICENSE +21 -0
  264. modules/cmvk/README.md +149 -0
  265. modules/cmvk/SECURITY.md +114 -0
  266. modules/cmvk/config/prompts/generator_v1.txt +23 -0
  267. modules/cmvk/config/prompts/verifier_hostile.txt +32 -0
  268. modules/cmvk/config/settings.yaml +40 -0
  269. modules/cmvk/coverage_html/.gitignore +2 -0
  270. modules/cmvk/coverage_html/class_index.html +658 -0
  271. modules/cmvk/coverage_html/coverage_html_cb_188fc9a4.js +735 -0
  272. modules/cmvk/coverage_html/favicon_32_cb_c827f16f.png +0 -0
  273. modules/cmvk/coverage_html/function_index.html +1978 -0
  274. modules/cmvk/coverage_html/index.html +255 -0
  275. modules/cmvk/coverage_html/keybd_closed_cb_900cfef5.png +0 -0
  276. modules/cmvk/coverage_html/status.json +1 -0
  277. modules/cmvk/coverage_html/style_cb_5c747636.css +389 -0
  278. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38___init___py.html +315 -0
  279. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_audit_py.html +499 -0
  280. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_benchmarks_py.html +575 -0
  281. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_constitutional_py.html +1001 -0
  282. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_hf_utils_py.html +398 -0
  283. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_metrics_py.html +570 -0
  284. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_profiles_py.html +397 -0
  285. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_types_py.html +109 -0
  286. modules/cmvk/coverage_html/z_2c49bd2ed3e01e38_verification_py.html +1053 -0
  287. modules/cmvk/docs/DIAGRAMS.md +325 -0
  288. modules/cmvk/docs/architecture.md +345 -0
  289. modules/cmvk/docs/features.md +308 -0
  290. modules/cmvk/docs/getting_started.md +279 -0
  291. modules/cmvk/docs/innovation_layer.md +377 -0
  292. modules/cmvk/docs/safety.md +281 -0
  293. modules/cmvk/docs/traceability.md +150 -0
  294. modules/cmvk/examples/basic_example.py +62 -0
  295. modules/cmvk/examples/demo_complete_pipeline.py +209 -0
  296. modules/cmvk/examples/demo_innovation_layer.py +197 -0
  297. modules/cmvk/examples/example.py +112 -0
  298. modules/cmvk/examples/model_diversity_comparison.py +110 -0
  299. modules/cmvk/examples/real_api_integration.py +121 -0
  300. modules/cmvk/examples/test_full_pipeline.py +303 -0
  301. modules/cmvk/experiments/FEATURE_2_LATERAL_THINKING.md +187 -0
  302. modules/cmvk/experiments/README.md +216 -0
  303. modules/cmvk/experiments/ablation_runner.py +666 -0
  304. modules/cmvk/experiments/baseline_runner.py +158 -0
  305. modules/cmvk/experiments/blind_spot_benchmark.py +364 -0
  306. modules/cmvk/experiments/datasets/README.md +85 -0
  307. modules/cmvk/experiments/datasets/humaneval_50.json +352 -0
  308. modules/cmvk/experiments/datasets/humaneval_full.json +1150 -0
  309. modules/cmvk/experiments/datasets/humaneval_sample.json +32 -0
  310. modules/cmvk/experiments/datasets/sabotage.json +262 -0
  311. modules/cmvk/experiments/datasets/sample.json +40 -0
  312. modules/cmvk/experiments/demo_with_traces.py +110 -0
  313. modules/cmvk/experiments/efficiency_curve.py +259 -0
  314. modules/cmvk/experiments/experiment_runner.py +243 -0
  315. modules/cmvk/experiments/paper_data_generator.py +183 -0
  316. modules/cmvk/experiments/reproduce_results.py +407 -0
  317. modules/cmvk/experiments/reproducible_runner.py +352 -0
  318. modules/cmvk/experiments/sabotage_stress_test.py +311 -0
  319. modules/cmvk/experiments/test_lateral_thinking.py +116 -0
  320. modules/cmvk/experiments/test_prosecutor.py +41 -0
  321. modules/cmvk/experiments/visualize_results.py +735 -0
  322. modules/cmvk/logs/traces/demo_HumanEval_0_20260121-204900.json +36 -0
  323. modules/cmvk/notebooks/analysis.ipynb +124 -0
  324. modules/cmvk/paper/PAPER.md +561 -0
  325. modules/cmvk/paper/arxiv_checklist.md +230 -0
  326. modules/cmvk/paper/cmvk_neurips.aux +77 -0
  327. modules/cmvk/paper/cmvk_neurips.bbl +81 -0
  328. modules/cmvk/paper/cmvk_neurips.blg +48 -0
  329. modules/cmvk/paper/cmvk_neurips.out +16 -0
  330. modules/cmvk/paper/cmvk_neurips.pdf +0 -0
  331. modules/cmvk/paper/cmvk_neurips.tex +309 -0
  332. modules/cmvk/paper/figures/ablation.png +0 -0
  333. modules/cmvk/paper/figures/ablation.svg +39 -0
  334. modules/cmvk/paper/figures/architecture.png +0 -0
  335. modules/cmvk/paper/figures/architecture.svg +115 -0
  336. modules/cmvk/paper/figures/results_bar.png +0 -0
  337. modules/cmvk/paper/figures/results_bar.svg +70 -0
  338. modules/cmvk/paper/generate_figures.py +383 -0
  339. modules/cmvk/paper/neurips_2024.sty +101 -0
  340. modules/cmvk/paper/references.bib +98 -0
  341. modules/cmvk/paper/structure.tex +200 -0
  342. modules/cmvk/pyproject.toml +189 -0
  343. modules/cmvk/requirements-dev.txt +19 -0
  344. modules/cmvk/requirements.txt +14 -0
  345. modules/cmvk/src/cmvk/__init__.py +216 -0
  346. modules/cmvk/src/cmvk/audit.py +400 -0
  347. modules/cmvk/src/cmvk/benchmarks.py +476 -0
  348. modules/cmvk/src/cmvk/constitutional.py +902 -0
  349. modules/cmvk/src/cmvk/hf_utils.py +299 -0
  350. modules/cmvk/src/cmvk/metrics.py +471 -0
  351. modules/cmvk/src/cmvk/profiles.py +298 -0
  352. modules/cmvk/src/cmvk/py.typed +0 -0
  353. modules/cmvk/src/cmvk/types.py +10 -0
  354. modules/cmvk/src/cmvk/verification.py +954 -0
  355. modules/cmvk/src/cross_model_verification_kernel/__init__.py +91 -0
  356. modules/cmvk/src/cross_model_verification_kernel/__main__.py +10 -0
  357. modules/cmvk/src/cross_model_verification_kernel/agents/__init__.py +16 -0
  358. modules/cmvk/src/cross_model_verification_kernel/agents/base_agent.py +142 -0
  359. modules/cmvk/src/cross_model_verification_kernel/agents/generator_openai.py +223 -0
  360. modules/cmvk/src/cross_model_verification_kernel/agents/verifier_anthropic.py +448 -0
  361. modules/cmvk/src/cross_model_verification_kernel/agents/verifier_gemini.py +481 -0
  362. modules/cmvk/src/cross_model_verification_kernel/cli.py +570 -0
  363. modules/cmvk/src/cross_model_verification_kernel/core/__init__.py +26 -0
  364. modules/cmvk/src/cross_model_verification_kernel/core/graph_memory.py +308 -0
  365. modules/cmvk/src/cross_model_verification_kernel/core/kernel.py +413 -0
  366. modules/cmvk/src/cross_model_verification_kernel/core/trace_logger.py +75 -0
  367. modules/cmvk/src/cross_model_verification_kernel/core/types.py +121 -0
  368. modules/cmvk/src/cross_model_verification_kernel/datasets/__init__.py +20 -0
  369. modules/cmvk/src/cross_model_verification_kernel/datasets/humaneval_loader.py +271 -0
  370. modules/cmvk/src/cross_model_verification_kernel/generator.py +118 -0
  371. modules/cmvk/src/cross_model_verification_kernel/kernel.py +292 -0
  372. modules/cmvk/src/cross_model_verification_kernel/models.py +111 -0
  373. modules/cmvk/src/cross_model_verification_kernel/py.typed +1 -0
  374. modules/cmvk/src/cross_model_verification_kernel/simple_kernel.py +185 -0
  375. modules/cmvk/src/cross_model_verification_kernel/tools/__init__.py +94 -0
  376. modules/cmvk/src/cross_model_verification_kernel/tools/huggingface_upload.py +394 -0
  377. modules/cmvk/src/cross_model_verification_kernel/tools/sandbox.py +159 -0
  378. modules/cmvk/src/cross_model_verification_kernel/tools/statistics.py +468 -0
  379. modules/cmvk/src/cross_model_verification_kernel/tools/visualizer.py +312 -0
  380. modules/cmvk/src/cross_model_verification_kernel/tools/web_search.py +86 -0
  381. modules/cmvk/src/cross_model_verification_kernel/verifier.py +257 -0
  382. modules/cmvk/tests/__init__.py +3 -0
  383. modules/cmvk/tests/conftest.py +61 -0
  384. modules/cmvk/tests/integration/__init__.py +1 -0
  385. modules/cmvk/tests/integration/test_anthropic_verifier.py +269 -0
  386. modules/cmvk/tests/integration/test_integration.py +53 -0
  387. modules/cmvk/tests/integration/test_lateral_thinking_integration.py +199 -0
  388. modules/cmvk/tests/integration/test_lateral_thinking_witness.py +208 -0
  389. modules/cmvk/tests/integration/test_prosecutor_mode.py +131 -0
  390. modules/cmvk/tests/test_constitutional.py +611 -0
  391. modules/cmvk/tests/test_enhanced_features.py +603 -0
  392. modules/cmvk/tests/test_verification.py +255 -0
  393. modules/cmvk/tests/unit/__init__.py +1 -0
  394. modules/cmvk/tests/unit/test_agents.py +64 -0
  395. modules/cmvk/tests/unit/test_cli.py +224 -0
  396. modules/cmvk/tests/unit/test_core.py +126 -0
  397. modules/cmvk/tests/unit/test_humaneval_loader.py +197 -0
  398. modules/cmvk/tests/unit/test_kernel.py +255 -0
  399. modules/cmvk/tests/unit/test_reproducibility.py +160 -0
  400. modules/cmvk/tests/unit/test_trace_logger.py +115 -0
  401. modules/cmvk/tests/unit/test_visualizer.py +218 -0
  402. modules/control-plane/.github/ISSUE_TEMPLATE/bug_report.yml +82 -0
  403. modules/control-plane/.github/ISSUE_TEMPLATE/config.yml +11 -0
  404. modules/control-plane/.github/ISSUE_TEMPLATE/feature_request.yml +104 -0
  405. modules/control-plane/.github/ISSUE_TEMPLATE/question.yml +70 -0
  406. modules/control-plane/.github/ISSUE_TEMPLATE/security_vulnerability.yml +84 -0
  407. modules/control-plane/.github/discussions.yml +73 -0
  408. modules/control-plane/.github/pull_request_template.md +82 -0
  409. modules/control-plane/.github/workflows/publish.yml +146 -0
  410. modules/control-plane/.github/workflows/release.yml +39 -0
  411. modules/control-plane/.github/workflows/tests.yml +58 -0
  412. modules/control-plane/.gitignore +55 -0
  413. modules/control-plane/CHANGELOG.md +203 -0
  414. modules/control-plane/CONTRIBUTING.md +311 -0
  415. modules/control-plane/CONTRIBUTORS.md +88 -0
  416. modules/control-plane/Dockerfile +82 -0
  417. modules/control-plane/LICENSE +21 -0
  418. modules/control-plane/MANIFEST.in +17 -0
  419. modules/control-plane/README.md +1264 -0
  420. modules/control-plane/ROADMAP.md +228 -0
  421. modules/control-plane/SECURITY.md +210 -0
  422. modules/control-plane/SUPPORT.md +106 -0
  423. modules/control-plane/acp-cli.py +212 -0
  424. modules/control-plane/benchmark/README.md +257 -0
  425. modules/control-plane/benchmark/__init__.py +19 -0
  426. modules/control-plane/benchmark/red_team_dataset.py +517 -0
  427. modules/control-plane/benchmark.py +563 -0
  428. modules/control-plane/build_and_publish.sh +130 -0
  429. modules/control-plane/docker-compose.yml +74 -0
  430. modules/control-plane/docs/ABLATION_STUDIES.md +528 -0
  431. modules/control-plane/docs/ADAPTER_GUIDE.md +544 -0
  432. modules/control-plane/docs/ADVANCED_FEATURES.md +543 -0
  433. modules/control-plane/docs/AIOS_COMPARISON.md +296 -0
  434. modules/control-plane/docs/BIBLIOGRAPHY.md +367 -0
  435. modules/control-plane/docs/CASE_STUDIES.md +645 -0
  436. modules/control-plane/docs/DOCKER_DEPLOYMENT.md +184 -0
  437. modules/control-plane/docs/ECOSYSTEM_STATUS.md +98 -0
  438. modules/control-plane/docs/HF_MODEL_CARD.md +168 -0
  439. modules/control-plane/docs/KERNEL_V1_RELEASE.md +454 -0
  440. modules/control-plane/docs/LAYER3_FRAMEWORK.md +227 -0
  441. modules/control-plane/docs/LIMITATIONS.md +523 -0
  442. modules/control-plane/docs/PYPI_PUBLISHING.md +195 -0
  443. modules/control-plane/docs/README.md +58 -0
  444. modules/control-plane/docs/RELATED_WORK.md +319 -0
  445. modules/control-plane/docs/RELEASE_v1.1.0.md +252 -0
  446. modules/control-plane/docs/REPRODUCIBILITY.md +540 -0
  447. modules/control-plane/docs/RESEARCH_FOUNDATION.md +197 -0
  448. modules/control-plane/docs/api/CORE.md +270 -0
  449. modules/control-plane/docs/architecture/architecture.md +120 -0
  450. modules/control-plane/docs/community/ANNOUNCEMENT_TEMPLATES.md +52 -0
  451. modules/control-plane/docs/guides/IMPLEMENTATION.md +225 -0
  452. modules/control-plane/docs/guides/PHILOSOPHY.md +354 -0
  453. modules/control-plane/docs/guides/QUICKSTART.md +217 -0
  454. modules/control-plane/examples/README.md +138 -0
  455. modules/control-plane/examples/a2a_demo.py +410 -0
  456. modules/control-plane/examples/adapter_demo.py +347 -0
  457. modules/control-plane/examples/advanced_features.py +403 -0
  458. modules/control-plane/examples/basic_usage.py +261 -0
  459. modules/control-plane/examples/benchmark_demo.py +186 -0
  460. modules/control-plane/examples/compliance_demo.py +333 -0
  461. modules/control-plane/examples/configuration.py +265 -0
  462. modules/control-plane/examples/getting_started.py +178 -0
  463. modules/control-plane/examples/hibernation_and_time_travel_demo.py +406 -0
  464. modules/control-plane/examples/interactive_tutorial.ipynb +497 -0
  465. modules/control-plane/examples/kernel_interceptor_demo.py +202 -0
  466. modules/control-plane/examples/kernel_v1_demo.py +273 -0
  467. modules/control-plane/examples/langchain_demo.py +281 -0
  468. modules/control-plane/examples/lifecycle_demo.py +724 -0
  469. modules/control-plane/examples/mcp_demo.py +378 -0
  470. modules/control-plane/examples/ml_safety_demo.py +157 -0
  471. modules/control-plane/examples/multimodal_demo.py +347 -0
  472. modules/control-plane/examples/observability_demo.py +370 -0
  473. modules/control-plane/examples/use_cases.py +336 -0
  474. modules/control-plane/experiments/long_horizon_purge.py +235 -0
  475. modules/control-plane/experiments/multi_agent_rag.py +165 -0
  476. modules/control-plane/experiments/reproduce_results.py +667 -0
  477. modules/control-plane/paper/ARXIV_SUBMISSION_INFO.txt +122 -0
  478. modules/control-plane/paper/ETHICS_STATEMENT.md +248 -0
  479. modules/control-plane/paper/PAPER_CHECKLIST.md +72 -0
  480. modules/control-plane/paper/Paper.pdf +0 -0
  481. modules/control-plane/paper/README.md +71 -0
  482. modules/control-plane/paper/appendix.md +152 -0
  483. modules/control-plane/paper/architecture.md +15 -0
  484. modules/control-plane/paper/arxiv/figures/ablation_chart.png +0 -0
  485. modules/control-plane/paper/arxiv/figures/architecture.png +0 -0
  486. modules/control-plane/paper/arxiv/figures/constraint_graphs.png +0 -0
  487. modules/control-plane/paper/arxiv/figures/results_chart.png +0 -0
  488. modules/control-plane/paper/arxiv/main.aux +97 -0
  489. modules/control-plane/paper/arxiv/main.bbl +112 -0
  490. modules/control-plane/paper/arxiv/main.blg +48 -0
  491. modules/control-plane/paper/arxiv/main.out +33 -0
  492. modules/control-plane/paper/arxiv/main.pdf +0 -0
  493. modules/control-plane/paper/arxiv/main.tex +479 -0
  494. modules/control-plane/paper/arxiv/references.bib +234 -0
  495. modules/control-plane/paper/arxiv_submission.tar +0 -0
  496. modules/control-plane/paper/arxiv_submission.zip +0 -0
  497. modules/control-plane/paper/build.sh +68 -0
  498. modules/control-plane/paper/figures/README.md +47 -0
  499. modules/control-plane/paper/figures/ablation_chart.pdf +0 -0
  500. modules/control-plane/paper/figures/ablation_chart.png +0 -0
  501. modules/control-plane/paper/figures/architecture.pdf +0 -0
  502. modules/control-plane/paper/figures/architecture.png +0 -0
  503. modules/control-plane/paper/figures/constraint_graphs.pdf +0 -0
  504. modules/control-plane/paper/figures/constraint_graphs.png +0 -0
  505. modules/control-plane/paper/figures/generate_figures.py +252 -0
  506. modules/control-plane/paper/figures/results_chart.pdf +0 -0
  507. modules/control-plane/paper/figures/results_chart.png +0 -0
  508. modules/control-plane/paper/main.md +273 -0
  509. modules/control-plane/paper/main.tex +214 -0
  510. modules/control-plane/paper/main_arxiv.aux +53 -0
  511. modules/control-plane/paper/main_arxiv.out +17 -0
  512. modules/control-plane/paper/main_arxiv.pdf +0 -0
  513. modules/control-plane/paper/main_arxiv.tex +264 -0
  514. modules/control-plane/paper/references.bib +234 -0
  515. modules/control-plane/pyproject.toml +124 -0
  516. modules/control-plane/reproducibility/ABLATIONS.md +136 -0
  517. modules/control-plane/reproducibility/README.md +288 -0
  518. modules/control-plane/reproducibility/commands.md +467 -0
  519. modules/control-plane/reproducibility/docker_config/Dockerfile +39 -0
  520. modules/control-plane/reproducibility/experiment_configs/purge_config.json +46 -0
  521. modules/control-plane/reproducibility/experiment_configs/rag_config.json +36 -0
  522. modules/control-plane/reproducibility/hardware_specs.md +317 -0
  523. modules/control-plane/reproducibility/requirements_frozen.txt +0 -0
  524. modules/control-plane/reproducibility/run_all_experiments.sh +45 -0
  525. modules/control-plane/reproducibility/seeds.json +106 -0
  526. modules/control-plane/scripts/prepare_pypi.py +46 -0
  527. modules/control-plane/scripts/prepare_release.py +176 -0
  528. modules/control-plane/scripts/upload_dataset_to_hf.py +316 -0
  529. modules/control-plane/setup.py +69 -0
  530. modules/control-plane/src/agent_control_plane/__init__.py +639 -0
  531. modules/control-plane/src/agent_control_plane/a2a_adapter.py +541 -0
  532. modules/control-plane/src/agent_control_plane/adapter.py +415 -0
  533. modules/control-plane/src/agent_control_plane/agent_hibernation.py +364 -0
  534. modules/control-plane/src/agent_control_plane/agent_kernel.py +464 -0
  535. modules/control-plane/src/agent_control_plane/compliance.py +718 -0
  536. modules/control-plane/src/agent_control_plane/constraint_graphs.py +475 -0
  537. modules/control-plane/src/agent_control_plane/control_plane.py +848 -0
  538. modules/control-plane/src/agent_control_plane/example_executors.py +193 -0
  539. modules/control-plane/src/agent_control_plane/execution_engine.py +229 -0
  540. modules/control-plane/src/agent_control_plane/flight_recorder.py +600 -0
  541. modules/control-plane/src/agent_control_plane/governance_layer.py +432 -0
  542. modules/control-plane/src/agent_control_plane/hf_utils.py +561 -0
  543. modules/control-plane/src/agent_control_plane/interfaces/__init__.py +53 -0
  544. modules/control-plane/src/agent_control_plane/interfaces/kernel_interface.py +359 -0
  545. modules/control-plane/src/agent_control_plane/interfaces/plugin_interface.py +495 -0
  546. modules/control-plane/src/agent_control_plane/interfaces/protocol_interfaces.py +385 -0
  547. modules/control-plane/src/agent_control_plane/kernel_space.py +707 -0
  548. modules/control-plane/src/agent_control_plane/langchain_adapter.py +422 -0
  549. modules/control-plane/src/agent_control_plane/lifecycle.py +3111 -0
  550. modules/control-plane/src/agent_control_plane/mcp_adapter.py +517 -0
  551. modules/control-plane/src/agent_control_plane/ml_safety.py +560 -0
  552. modules/control-plane/src/agent_control_plane/multimodal.py +724 -0
  553. modules/control-plane/src/agent_control_plane/mute_agent.py +419 -0
  554. modules/control-plane/src/agent_control_plane/observability.py +785 -0
  555. modules/control-plane/src/agent_control_plane/orchestrator.py +480 -0
  556. modules/control-plane/src/agent_control_plane/plugin_registry.py +748 -0
  557. modules/control-plane/src/agent_control_plane/policy_engine.py +525 -0
  558. modules/control-plane/src/agent_control_plane/shadow_mode.py +307 -0
  559. modules/control-plane/src/agent_control_plane/signals.py +491 -0
  560. modules/control-plane/src/agent_control_plane/supervisor_agents.py +427 -0
  561. modules/control-plane/src/agent_control_plane/time_travel_debugger.py +554 -0
  562. modules/control-plane/src/agent_control_plane/tool_registry.py +350 -0
  563. modules/control-plane/src/agent_control_plane/vfs.py +695 -0
  564. modules/control-plane/tests/README.md +33 -0
  565. modules/control-plane/tests/test_a2a_adapter.py +336 -0
  566. modules/control-plane/tests/test_adapter.py +422 -0
  567. modules/control-plane/tests/test_advanced_features.py +389 -0
  568. modules/control-plane/tests/test_benchmark.py +223 -0
  569. modules/control-plane/tests/test_compliance.py +214 -0
  570. modules/control-plane/tests/test_control_plane.py +295 -0
  571. modules/control-plane/tests/test_hibernation.py +274 -0
  572. modules/control-plane/tests/test_kernel_interception.py +284 -0
  573. modules/control-plane/tests/test_langchain_adapter.py +258 -0
  574. modules/control-plane/tests/test_lifecycle.py +1174 -0
  575. modules/control-plane/tests/test_mcp_adapter.py +293 -0
  576. modules/control-plane/tests/test_ml_safety.py +142 -0
  577. modules/control-plane/tests/test_multimodal.py +317 -0
  578. modules/control-plane/tests/test_new_features.py +435 -0
  579. modules/control-plane/tests/test_observability.py +338 -0
  580. modules/control-plane/tests/test_time_travel.py +387 -0
  581. modules/emk/.github/workflows/ci.yml +105 -0
  582. modules/emk/.github/workflows/publish.yml +144 -0
  583. modules/emk/.gitignore +74 -0
  584. modules/emk/CHANGELOG.md +41 -0
  585. modules/emk/CONTRIBUTING.md +295 -0
  586. modules/emk/IMPLEMENTATION.md +174 -0
  587. modules/emk/LICENSE +21 -0
  588. modules/emk/MANIFEST.in +8 -0
  589. modules/emk/README.md +135 -0
  590. modules/emk/RELEASE_NOTES.md +82 -0
  591. modules/emk/SECURITY.md +52 -0
  592. modules/emk/codecov.yml +39 -0
  593. modules/emk/docs/MEMORY_MANAGEMENT.md +285 -0
  594. modules/emk/emk/__init__.py +106 -0
  595. modules/emk/emk/hf_utils.py +419 -0
  596. modules/emk/emk/indexer.py +144 -0
  597. modules/emk/emk/py.typed +0 -0
  598. modules/emk/emk/schema.py +204 -0
  599. modules/emk/emk/sleep_cycle.py +345 -0
  600. modules/emk/emk/store.py +479 -0
  601. modules/emk/examples/basic_usage.py +123 -0
  602. modules/emk/examples/memory_features_demo.py +154 -0
  603. modules/emk/experiments/README.md +59 -0
  604. modules/emk/experiments/reproduce_results.py +461 -0
  605. modules/emk/experiments/results.json +61 -0
  606. modules/emk/paper/structure.tex +192 -0
  607. modules/emk/paper/whitepaper.md +273 -0
  608. modules/emk/pyproject.toml +91 -0
  609. modules/emk/setup.py +5 -0
  610. modules/emk/tests/test_file_adapter.py +195 -0
  611. modules/emk/tests/test_indexer.py +174 -0
  612. modules/emk/tests/test_init.py +55 -0
  613. modules/emk/tests/test_negative_memory.py +83 -0
  614. modules/emk/tests/test_schema.py +150 -0
  615. modules/emk/tests/test_semantic_rules.py +175 -0
  616. modules/emk/tests/test_sleep_cycle.py +335 -0
  617. modules/emk/tests/test_store_anti_patterns.py +239 -0
  618. modules/iatp/.github/workflows/docker-build.yml +124 -0
  619. modules/iatp/.github/workflows/publish.yml +174 -0
  620. modules/iatp/.github/workflows/python-package.yml +121 -0
  621. modules/iatp/.gitignore +67 -0
  622. modules/iatp/.pre-commit-config.yaml +64 -0
  623. modules/iatp/CHANGELOG.md +120 -0
  624. modules/iatp/Dockerfile +91 -0
  625. modules/iatp/IMPLEMENTATION_SUMMARY.md +218 -0
  626. modules/iatp/MANIFEST.in +9 -0
  627. modules/iatp/README.md +180 -0
  628. modules/iatp/docker/Dockerfile.agent +27 -0
  629. modules/iatp/docker/Dockerfile.sidecar-python +86 -0
  630. modules/iatp/docker/README.md +258 -0
  631. modules/iatp/docker-compose.yml +194 -0
  632. modules/iatp/docs/ARCHITECTURE.md +243 -0
  633. modules/iatp/docs/CLI_GUIDE.md +220 -0
  634. modules/iatp/docs/DEPLOYMENT.md +304 -0
  635. modules/iatp/examples/README.md +132 -0
  636. modules/iatp/examples/backend_agent.py +39 -0
  637. modules/iatp/examples/client.py +168 -0
  638. modules/iatp/examples/demo_attestation_reputation.py +274 -0
  639. modules/iatp/examples/demo_client.py +240 -0
  640. modules/iatp/examples/demo_rbac.py +143 -0
  641. modules/iatp/examples/integration_demo.py +245 -0
  642. modules/iatp/examples/manifests/coder_agent.json +20 -0
  643. modules/iatp/examples/manifests/reviewer_agent.json +19 -0
  644. modules/iatp/examples/manifests/secure_bank.json +14 -0
  645. modules/iatp/examples/manifests/standard_agent.json +14 -0
  646. modules/iatp/examples/manifests/untrusted_honeypot.json +14 -0
  647. modules/iatp/examples/run_secure_bank_sidecar.py +85 -0
  648. modules/iatp/examples/run_sidecar.py +105 -0
  649. modules/iatp/examples/run_untrusted_sidecar.py +77 -0
  650. modules/iatp/examples/secure_bank_agent.py +138 -0
  651. modules/iatp/examples/test_untrusted.py +82 -0
  652. modules/iatp/examples/untrusted_agent.py +119 -0
  653. modules/iatp/experiments/README.md +58 -0
  654. modules/iatp/experiments/cascading_hallucination/README.md +149 -0
  655. modules/iatp/experiments/cascading_hallucination/agent_a_user.py +41 -0
  656. modules/iatp/experiments/cascading_hallucination/agent_b_summarizer.py +54 -0
  657. modules/iatp/experiments/cascading_hallucination/agent_c_database.py +47 -0
  658. modules/iatp/experiments/cascading_hallucination/proof_of_concept.py +290 -0
  659. modules/iatp/experiments/cascading_hallucination/run_experiment.py +226 -0
  660. modules/iatp/experiments/cascading_hallucination/sidecar_c.py +61 -0
  661. modules/iatp/experiments/reproduce_results.py +574 -0
  662. modules/iatp/experiments/results.json +2336 -0
  663. modules/iatp/iatp/__init__.py +164 -0
  664. modules/iatp/iatp/attestation.py +401 -0
  665. modules/iatp/iatp/cli.py +253 -0
  666. modules/iatp/iatp/hf_utils.py +469 -0
  667. modules/iatp/iatp/ipc_pipes.py +578 -0
  668. modules/iatp/iatp/main.py +410 -0
  669. modules/iatp/iatp/models/__init__.py +445 -0
  670. modules/iatp/iatp/policy_engine.py +335 -0
  671. modules/iatp/iatp/py.typed +2 -0
  672. modules/iatp/iatp/recovery.py +319 -0
  673. modules/iatp/iatp/security/__init__.py +268 -0
  674. modules/iatp/iatp/sidecar/__init__.py +517 -0
  675. modules/iatp/iatp/telemetry/__init__.py +162 -0
  676. modules/iatp/iatp/tests/__init__.py +1 -0
  677. modules/iatp/iatp/tests/test_attestation.py +368 -0
  678. modules/iatp/iatp/tests/test_cli.py +129 -0
  679. modules/iatp/iatp/tests/test_models.py +128 -0
  680. modules/iatp/iatp/tests/test_policy_engine.py +345 -0
  681. modules/iatp/iatp/tests/test_recovery.py +279 -0
  682. modules/iatp/iatp/tests/test_security.py +220 -0
  683. modules/iatp/iatp/tests/test_sidecar.py +165 -0
  684. modules/iatp/iatp/tests/test_telemetry.py +173 -0
  685. modules/iatp/paper/BLOG.md +307 -0
  686. modules/iatp/paper/PAPER.md +236 -0
  687. modules/iatp/paper/RFC_SUBMISSION.md +299 -0
  688. modules/iatp/paper/whitepaper.md +369 -0
  689. modules/iatp/proto/README.md +200 -0
  690. modules/iatp/proto/generate_stubs.py +81 -0
  691. modules/iatp/proto/iatp.proto +552 -0
  692. modules/iatp/pyproject.toml +180 -0
  693. modules/iatp/requirements-dev.txt +2 -0
  694. modules/iatp/requirements.txt +6 -0
  695. modules/iatp/setup.py +60 -0
  696. modules/iatp/sidecar/README.md +487 -0
  697. modules/iatp/sidecar/go/Dockerfile +32 -0
  698. modules/iatp/sidecar/go/README.md +237 -0
  699. modules/iatp/sidecar/go/go.mod +8 -0
  700. modules/iatp/sidecar/go/main.go +488 -0
  701. modules/iatp/spec/001-handshake.md +436 -0
  702. modules/iatp/spec/002-reversibility.md +394 -0
  703. modules/iatp/spec/schema/capability_manifest.json +266 -0
  704. modules/iatp/test_integration.py +310 -0
  705. modules/mcp-kernel-server/README.md +261 -0
  706. modules/mcp-kernel-server/pyproject.toml +60 -0
  707. modules/mcp-kernel-server/src/mcp_kernel_server/__init__.py +26 -0
  708. modules/mcp-kernel-server/src/mcp_kernel_server/cli.py +229 -0
  709. modules/mcp-kernel-server/src/mcp_kernel_server/resources.py +215 -0
  710. modules/mcp-kernel-server/src/mcp_kernel_server/server.py +562 -0
  711. modules/mcp-kernel-server/src/mcp_kernel_server/tools.py +1172 -0
  712. modules/mute-agent/.github/workflows/safety_check.yml +45 -0
  713. modules/mute-agent/.gitignore +53 -0
  714. modules/mute-agent/ARCHITECTURE.md +531 -0
  715. modules/mute-agent/BENCHMARK_GUIDE.md +384 -0
  716. modules/mute-agent/COMPLETION_SUMMARY.md +293 -0
  717. modules/mute-agent/EXPERIMENT_SUMMARY.md +318 -0
  718. modules/mute-agent/IMPLEMENTATION_SUMMARY.md +212 -0
  719. modules/mute-agent/LICENSE +21 -0
  720. modules/mute-agent/PHASE3_SUMMARY.md +297 -0
  721. modules/mute-agent/README.md +360 -0
  722. modules/mute-agent/STEEL_MAN_RESULTS.md +353 -0
  723. modules/mute-agent/USAGE.md +505 -0
  724. modules/mute-agent/V2_IMPLEMENTATION_SUMMARY.md +253 -0
  725. modules/mute-agent/V2_STEEL_MAN_IMPLEMENTATION.md +274 -0
  726. modules/mute-agent/VERIFICATION_REPORT.md +435 -0
  727. modules/mute-agent/charts/cost_comparison.png +0 -0
  728. modules/mute-agent/charts/cost_vs_ambiguity.png +0 -0
  729. modules/mute-agent/charts/metrics_comparison.png +0 -0
  730. modules/mute-agent/charts/scenario_breakdown.png +0 -0
  731. modules/mute-agent/charts/trace_attack_blocked.html +140 -0
  732. modules/mute-agent/charts/trace_attack_blocked.png +0 -0
  733. modules/mute-agent/charts/trace_failure.html +140 -0
  734. modules/mute-agent/charts/trace_failure.png +0 -0
  735. modules/mute-agent/charts/trace_success.html +140 -0
  736. modules/mute-agent/charts/trace_success.png +0 -0
  737. modules/mute-agent/examples/__init__.py +1 -0
  738. modules/mute-agent/examples/advanced_example.py +384 -0
  739. modules/mute-agent/examples/graph_debugger_demo.py +241 -0
  740. modules/mute-agent/examples/listener_example.py +297 -0
  741. modules/mute-agent/examples/simple_example.py +242 -0
  742. modules/mute-agent/examples/steel_man_demo.py +297 -0
  743. modules/mute-agent/experiments/README.md +135 -0
  744. modules/mute-agent/experiments/__init__.py +3 -0
  745. modules/mute-agent/experiments/agent_comparison.csv +6 -0
  746. modules/mute-agent/experiments/agent_comparison_50runs.csv +6 -0
  747. modules/mute-agent/experiments/ambiguity_test.py +335 -0
  748. modules/mute-agent/experiments/ambiguity_test_results.csv +31 -0
  749. modules/mute-agent/experiments/ambiguity_test_results_50runs.csv +51 -0
  750. modules/mute-agent/experiments/baseline_agent.py +189 -0
  751. modules/mute-agent/experiments/benchmark.py +402 -0
  752. modules/mute-agent/experiments/demo.py +172 -0
  753. modules/mute-agent/experiments/generate_cost_curve.py +474 -0
  754. modules/mute-agent/experiments/jailbreak_test.py +137 -0
  755. modules/mute-agent/experiments/latent_state_scenario.py +361 -0
  756. modules/mute-agent/experiments/mute_agent_experiment.py +349 -0
  757. modules/mute-agent/experiments/run_extended_experiment.py +40 -0
  758. modules/mute-agent/experiments/run_v2_experiments.py +266 -0
  759. modules/mute-agent/experiments/run_v2_experiments_auto.py +247 -0
  760. modules/mute-agent/experiments/v2_scenarios/README.md +214 -0
  761. modules/mute-agent/experiments/v2_scenarios/__init__.py +4 -0
  762. modules/mute-agent/experiments/v2_scenarios/scenario_1_deep_dependency.py +325 -0
  763. modules/mute-agent/experiments/v2_scenarios/scenario_2_adversarial.py +328 -0
  764. modules/mute-agent/experiments/v2_scenarios/scenario_3_false_positive.py +303 -0
  765. modules/mute-agent/experiments/v2_scenarios/scenario_4_performance.py +319 -0
  766. modules/mute-agent/experiments/visualize.py +400 -0
  767. modules/mute-agent/mute_agent/__init__.py +66 -0
  768. modules/mute-agent/mute_agent/core/__init__.py +1 -0
  769. modules/mute-agent/mute_agent/core/execution_agent.py +164 -0
  770. modules/mute-agent/mute_agent/core/handshake_protocol.py +199 -0
  771. modules/mute-agent/mute_agent/core/reasoning_agent.py +236 -0
  772. modules/mute-agent/mute_agent/knowledge_graph/__init__.py +1 -0
  773. modules/mute-agent/mute_agent/knowledge_graph/graph_elements.py +63 -0
  774. modules/mute-agent/mute_agent/knowledge_graph/multidimensional_graph.py +168 -0
  775. modules/mute-agent/mute_agent/knowledge_graph/subgraph.py +222 -0
  776. modules/mute-agent/mute_agent/listener/__init__.py +41 -0
  777. modules/mute-agent/mute_agent/listener/adapters/__init__.py +29 -0
  778. modules/mute-agent/mute_agent/listener/adapters/base_adapter.py +187 -0
  779. modules/mute-agent/mute_agent/listener/adapters/caas_adapter.py +342 -0
  780. modules/mute-agent/mute_agent/listener/adapters/control_plane_adapter.py +434 -0
  781. modules/mute-agent/mute_agent/listener/adapters/iatp_adapter.py +330 -0
  782. modules/mute-agent/mute_agent/listener/adapters/scak_adapter.py +249 -0
  783. modules/mute-agent/mute_agent/listener/listener.py +608 -0
  784. modules/mute-agent/mute_agent/listener/state_observer.py +434 -0
  785. modules/mute-agent/mute_agent/listener/threshold_config.py +311 -0
  786. modules/mute-agent/mute_agent/super_system/__init__.py +1 -0
  787. modules/mute-agent/mute_agent/super_system/router.py +202 -0
  788. modules/mute-agent/mute_agent/visualization/__init__.py +8 -0
  789. modules/mute-agent/mute_agent/visualization/graph_debugger.py +495 -0
  790. modules/mute-agent/requirements-dev.txt +6 -0
  791. modules/mute-agent/requirements.txt +9 -0
  792. modules/mute-agent/setup.py +64 -0
  793. modules/mute-agent/src/__init__.py +0 -0
  794. modules/mute-agent/src/agents/__init__.py +0 -0
  795. modules/mute-agent/src/agents/baseline_agent.py +524 -0
  796. modules/mute-agent/src/agents/interactive_agent.py +113 -0
  797. modules/mute-agent/src/agents/mute_agent.py +622 -0
  798. modules/mute-agent/src/benchmarks/__init__.py +0 -0
  799. modules/mute-agent/src/benchmarks/evaluator.py +481 -0
  800. modules/mute-agent/src/benchmarks/scenarios.json +985 -0
  801. modules/mute-agent/src/core/__init__.py +0 -0
  802. modules/mute-agent/src/core/mock_state.py +320 -0
  803. modules/mute-agent/src/core/tools.py +441 -0
  804. modules/nexus/__init__.py +49 -0
  805. modules/nexus/arbiter.py +357 -0
  806. modules/nexus/client.py +464 -0
  807. modules/nexus/dmz.py +417 -0
  808. modules/nexus/escrow.py +428 -0
  809. modules/nexus/exceptions.py +284 -0
  810. modules/nexus/registry.py +391 -0
  811. modules/nexus/reputation.py +423 -0
  812. modules/nexus/schemas/__init__.py +49 -0
  813. modules/nexus/schemas/compliance.py +274 -0
  814. modules/nexus/schemas/escrow.py +249 -0
  815. modules/nexus/schemas/manifest.py +223 -0
  816. modules/nexus/schemas/receipt.py +206 -0
  817. modules/observability/README.md +192 -0
  818. modules/observability/alertmanager/alertmanager.yml +116 -0
  819. modules/observability/alerts/agent-os-alerts.yaml +197 -0
  820. modules/observability/docker-compose.yml +128 -0
  821. modules/observability/grafana/dashboards/agent-os-amb.json +448 -0
  822. modules/observability/grafana/dashboards/agent-os-cmvk.json +441 -0
  823. modules/observability/grafana/dashboards/agent-os-overview.json +268 -0
  824. modules/observability/grafana/dashboards/agent-os-performance.json +15 -0
  825. modules/observability/grafana/dashboards/agent-os-safety.json +50 -0
  826. modules/observability/grafana/provisioning/dashboards/dashboards.yml +15 -0
  827. modules/observability/grafana/provisioning/datasources/datasources.yml +33 -0
  828. modules/observability/otel/otel-collector-config.yml +61 -0
  829. modules/observability/prometheus/prometheus.yml +63 -0
  830. modules/observability/pyproject.toml +53 -0
  831. modules/observability/scripts/export_dashboards.py +55 -0
  832. modules/observability/src/agent_os_observability/__init__.py +25 -0
  833. modules/observability/src/agent_os_observability/dashboards.py +896 -0
  834. modules/observability/src/agent_os_observability/metrics.py +396 -0
  835. modules/observability/src/agent_os_observability/server.py +221 -0
  836. modules/observability/src/agent_os_observability/tracer.py +226 -0
  837. modules/primitives/.gitignore +8 -0
  838. modules/primitives/README.md +62 -0
  839. modules/primitives/agent_primitives/__init__.py +22 -0
  840. modules/primitives/agent_primitives/failures.py +82 -0
  841. modules/primitives/agent_primitives/py.typed +0 -0
  842. modules/primitives/pyproject.toml +68 -0
  843. modules/scak/.github/copilot-instructions.md +396 -0
  844. modules/scak/.github/workflows/release.yml +117 -0
  845. modules/scak/.gitignore +32 -0
  846. modules/scak/CHANGELOG.md +173 -0
  847. modules/scak/CITATION.cff +62 -0
  848. modules/scak/CONTRIBUTING.md +429 -0
  849. modules/scak/Dockerfile +58 -0
  850. modules/scak/ENTERPRISE_FEATURES.md +518 -0
  851. modules/scak/IMPLEMENTATION_SUMMARY.md +206 -0
  852. modules/scak/LIMITATIONS.md +565 -0
  853. modules/scak/MANIFEST.in +16 -0
  854. modules/scak/NOVELTY.md +535 -0
  855. modules/scak/README.md +928 -0
  856. modules/scak/RESEARCH.md +670 -0
  857. modules/scak/agent_kernel/__init__.py +66 -0
  858. modules/scak/agent_kernel/analyzer.py +432 -0
  859. modules/scak/agent_kernel/auditor.py +31 -0
  860. modules/scak/agent_kernel/completeness_auditor.py +234 -0
  861. modules/scak/agent_kernel/detector.py +200 -0
  862. modules/scak/agent_kernel/kernel.py +741 -0
  863. modules/scak/agent_kernel/memory_manager.py +82 -0
  864. modules/scak/agent_kernel/models.py +372 -0
  865. modules/scak/agent_kernel/nudge_mechanism.py +260 -0
  866. modules/scak/agent_kernel/outcome_analyzer.py +335 -0
  867. modules/scak/agent_kernel/patcher.py +579 -0
  868. modules/scak/agent_kernel/semantic_analyzer.py +313 -0
  869. modules/scak/agent_kernel/semantic_purge.py +346 -0
  870. modules/scak/agent_kernel/simulator.py +447 -0
  871. modules/scak/agent_kernel/teacher.py +82 -0
  872. modules/scak/agent_kernel/triage.py +149 -0
  873. modules/scak/build_and_publish.ps1 +74 -0
  874. modules/scak/build_and_publish.sh +74 -0
  875. modules/scak/cli.py +471 -0
  876. modules/scak/dashboard.py +462 -0
  877. modules/scak/datasets/DATASET_CARD.md +219 -0
  878. modules/scak/datasets/README.md +143 -0
  879. modules/scak/datasets/gaia_vague_queries/vague_queries.json +262 -0
  880. modules/scak/datasets/hf_upload/README.md +219 -0
  881. modules/scak/datasets/hf_upload/scak_gaia_laziness.jsonl +50 -0
  882. modules/scak/datasets/prepare_hf_datasets.py +145 -0
  883. modules/scak/datasets/red_team/jailbreak_patterns.json +202 -0
  884. modules/scak/docker-compose.yml +99 -0
  885. modules/scak/docs/Adaptive-Memory-Hierarchy.md +319 -0
  886. modules/scak/docs/Data-Contracts-and-Schemas.md +285 -0
  887. modules/scak/docs/Dual-Loop-Architecture.md +344 -0
  888. modules/scak/docs/Enhanced-Features.md +612 -0
  889. modules/scak/docs/LANGCHAIN_INTEGRATION.md +572 -0
  890. modules/scak/docs/README.md +128 -0
  891. modules/scak/docs/Reference-Implementations.md +163 -0
  892. modules/scak/docs/SCAK_V2.md +374 -0
  893. modules/scak/docs/Three-Failure-Types.md +178 -0
  894. modules/scak/examples/basic_example.py +155 -0
  895. modules/scak/examples/circuit_breaker_lazy_eval_demo.py +243 -0
  896. modules/scak/examples/langchain_integration_example.py +339 -0
  897. modules/scak/examples/layer4_demo.py +243 -0
  898. modules/scak/examples/production_features_demo.py +353 -0
  899. modules/scak/examples/quick_demo.py +79 -0
  900. modules/scak/examples/scak_v2_demo.py +252 -0
  901. modules/scak/experiments/README.md +438 -0
  902. modules/scak/experiments/ablation_studies/README.md +192 -0
  903. modules/scak/experiments/ablation_studies/ablation_no_audit.py +116 -0
  904. modules/scak/experiments/ablation_studies/ablation_no_purge.py +133 -0
  905. modules/scak/experiments/chaos_engineering/README.md +332 -0
  906. modules/scak/experiments/context_efficiency_test.py +328 -0
  907. modules/scak/experiments/gaia_benchmark/README.md +208 -0
  908. modules/scak/experiments/laziness_benchmark.py +179 -0
  909. modules/scak/experiments/long_horizon_task_experiment.py +252 -0
  910. modules/scak/experiments/multi_agent_rag_experiment.py +284 -0
  911. modules/scak/experiments/results/ablation_table.md +12 -0
  912. modules/scak/experiments/results/long_horizon.json +36 -0
  913. modules/scak/experiments/results/multi_agent_rag.json +66 -0
  914. modules/scak/experiments/run_comprehensive_ablations.py +332 -0
  915. modules/scak/experiments/test_auditor_patcher_integration.py +251 -0
  916. modules/scak/notebooks/getting_started.ipynb +33 -0
  917. modules/scak/paper/ARXIV_SUBMISSION_METADATA.txt +109 -0
  918. modules/scak/paper/PAPER_CHECKLIST.md +304 -0
  919. modules/scak/paper/Paper.pdf +0 -0
  920. modules/scak/paper/README.md +113 -0
  921. modules/scak/paper/appendix.md +351 -0
  922. modules/scak/paper/arxiv/bibliography.bib +284 -0
  923. modules/scak/paper/arxiv/fig1_ooda_architecture.pdf +0 -0
  924. modules/scak/paper/arxiv/fig2_memory_hierarchy.pdf +0 -0
  925. modules/scak/paper/arxiv/fig3_gaia_results.pdf +0 -0
  926. modules/scak/paper/arxiv/fig4_ablation_heatmap.pdf +0 -0
  927. modules/scak/paper/arxiv/fig5_context_reduction.pdf +0 -0
  928. modules/scak/paper/arxiv/fig6_mttr_boxplot.pdf +0 -0
  929. modules/scak/paper/arxiv/main.aux +103 -0
  930. modules/scak/paper/arxiv/main.bbl +113 -0
  931. modules/scak/paper/arxiv/main.blg +55 -0
  932. modules/scak/paper/arxiv/main.out +31 -0
  933. modules/scak/paper/arxiv/main.pdf +0 -0
  934. modules/scak/paper/arxiv/main.tex +482 -0
  935. modules/scak/paper/arxiv_submission/bibliography.bib +284 -0
  936. modules/scak/paper/arxiv_submission/fig1_ooda_architecture.pdf +0 -0
  937. modules/scak/paper/arxiv_submission/fig2_memory_hierarchy.pdf +0 -0
  938. modules/scak/paper/arxiv_submission/fig3_gaia_results.pdf +0 -0
  939. modules/scak/paper/arxiv_submission/fig4_ablation_heatmap.pdf +0 -0
  940. modules/scak/paper/arxiv_submission/fig5_context_reduction.pdf +0 -0
  941. modules/scak/paper/arxiv_submission/fig6_mttr_boxplot.pdf +0 -0
  942. modules/scak/paper/arxiv_submission/main.aux +103 -0
  943. modules/scak/paper/arxiv_submission/main.bbl +113 -0
  944. modules/scak/paper/arxiv_submission/main.blg +55 -0
  945. modules/scak/paper/arxiv_submission/main.out +31 -0
  946. modules/scak/paper/arxiv_submission/main.pdf +0 -0
  947. modules/scak/paper/arxiv_submission/main.tex +482 -0
  948. modules/scak/paper/arxiv_submission.tar.gz +0 -0
  949. modules/scak/paper/bibliography.bib +284 -0
  950. modules/scak/paper/build.sh +55 -0
  951. modules/scak/paper/figures/README.md +32 -0
  952. modules/scak/paper/figures/fig1_ooda_architecture.md +75 -0
  953. modules/scak/paper/figures/fig1_ooda_architecture.pdf +0 -0
  954. modules/scak/paper/figures/fig1_ooda_architecture.png +0 -0
  955. modules/scak/paper/figures/fig2_memory_hierarchy.md +83 -0
  956. modules/scak/paper/figures/fig2_memory_hierarchy.pdf +0 -0
  957. modules/scak/paper/figures/fig2_memory_hierarchy.png +0 -0
  958. modules/scak/paper/figures/fig3_gaia_results.md +64 -0
  959. modules/scak/paper/figures/fig3_gaia_results.pdf +0 -0
  960. modules/scak/paper/figures/fig3_gaia_results.png +0 -0
  961. modules/scak/paper/figures/fig4_ablation_heatmap.md +64 -0
  962. modules/scak/paper/figures/fig4_ablation_heatmap.pdf +0 -0
  963. modules/scak/paper/figures/fig4_ablation_heatmap.png +0 -0
  964. modules/scak/paper/figures/fig5_context_reduction.md +71 -0
  965. modules/scak/paper/figures/fig5_context_reduction.pdf +0 -0
  966. modules/scak/paper/figures/fig5_context_reduction.png +0 -0
  967. modules/scak/paper/figures/fig6_mttr_boxplot.md +80 -0
  968. modules/scak/paper/figures/fig6_mttr_boxplot.pdf +0 -0
  969. modules/scak/paper/figures/fig6_mttr_boxplot.png +0 -0
  970. modules/scak/paper/figures/generate_figures.py +463 -0
  971. modules/scak/paper/main.aux +103 -0
  972. modules/scak/paper/main.bbl +113 -0
  973. modules/scak/paper/main.blg +55 -0
  974. modules/scak/paper/main.md +192 -0
  975. modules/scak/paper/main.out +31 -0
  976. modules/scak/paper/main.pdf +0 -0
  977. modules/scak/paper/main.tex +482 -0
  978. modules/scak/reproducibility/ABLATIONS.md +225 -0
  979. modules/scak/reproducibility/Dockerfile.reproducibility +34 -0
  980. modules/scak/reproducibility/README.md +421 -0
  981. modules/scak/reproducibility/requirements-pinned.txt +32 -0
  982. modules/scak/reproducibility/run_all_experiments.py +395 -0
  983. modules/scak/reproducibility/seed_control.py +53 -0
  984. modules/scak/reproducibility/statistical_analysis.py +302 -0
  985. modules/scak/requirements.txt +50 -0
  986. modules/scak/setup.py +93 -0
  987. modules/scak/src/__init__.py +124 -0
  988. modules/scak/src/agents/__init__.py +13 -0
  989. modules/scak/src/agents/conflict_resolution.py +732 -0
  990. modules/scak/src/agents/orchestrator.py +761 -0
  991. modules/scak/src/agents/pubsub.py +484 -0
  992. modules/scak/src/agents/shadow_teacher.py +344 -0
  993. modules/scak/src/agents/swarm.py +661 -0
  994. modules/scak/src/agents/worker.py +357 -0
  995. modules/scak/src/integrations/__init__.py +81 -0
  996. modules/scak/src/integrations/cmvk_adapter.py +430 -0
  997. modules/scak/src/integrations/control_plane_adapter.py +601 -0
  998. modules/scak/src/integrations/langchain_integration.py +902 -0
  999. modules/scak/src/interfaces/__init__.py +59 -0
  1000. modules/scak/src/interfaces/llm_clients.py +505 -0
  1001. modules/scak/src/interfaces/openapi_tools.py +611 -0
  1002. modules/scak/src/interfaces/plugin_system.py +605 -0
  1003. modules/scak/src/interfaces/protocols.py +365 -0
  1004. modules/scak/src/interfaces/telemetry.py +464 -0
  1005. modules/scak/src/interfaces/tool_registry.py +547 -0
  1006. modules/scak/src/kernel/__init__.py +100 -0
  1007. modules/scak/src/kernel/auditor.py +305 -0
  1008. modules/scak/src/kernel/circuit_breaker.py +398 -0
  1009. modules/scak/src/kernel/core.py +724 -0
  1010. modules/scak/src/kernel/distributed.py +667 -0
  1011. modules/scak/src/kernel/evolution.py +455 -0
  1012. modules/scak/src/kernel/failover.py +621 -0
  1013. modules/scak/src/kernel/governance.py +710 -0
  1014. modules/scak/src/kernel/governance_v2.py +603 -0
  1015. modules/scak/src/kernel/lazy_evaluator.py +514 -0
  1016. modules/scak/src/kernel/load_testing.py +633 -0
  1017. modules/scak/src/kernel/memory.py +945 -0
  1018. modules/scak/src/kernel/patcher.py +581 -0
  1019. modules/scak/src/kernel/rubric.py +419 -0
  1020. modules/scak/src/kernel/schemas.py +390 -0
  1021. modules/scak/src/kernel/skill_mapper.py +309 -0
  1022. modules/scak/src/kernel/triage.py +149 -0
  1023. modules/scak/src/mocks/__init__.py +99 -0
  1024. modules/scak/tests/__init__.py +1 -0
  1025. modules/scak/tests/test_circuit_breaker.py +403 -0
  1026. modules/scak/tests/test_conflict_resolution.py +287 -0
  1027. modules/scak/tests/test_dual_loop.py +463 -0
  1028. modules/scak/tests/test_enhanced_features.py +421 -0
  1029. modules/scak/tests/test_failover_and_load.py +438 -0
  1030. modules/scak/tests/test_governance.py +185 -0
  1031. modules/scak/tests/test_kernel.py +359 -0
  1032. modules/scak/tests/test_langchain_integration.py +451 -0
  1033. modules/scak/tests/test_lazy_evaluator.py +465 -0
  1034. modules/scak/tests/test_llm_clients.py +122 -0
  1035. modules/scak/tests/test_memory_controller.py +528 -0
  1036. modules/scak/tests/test_orchestrator.py +181 -0
  1037. modules/scak/tests/test_phase3_integration.py +265 -0
  1038. modules/scak/tests/test_pubsub_swarm.py +203 -0
  1039. modules/scak/tests/test_reference_implementations.py +240 -0
  1040. modules/scak/tests/test_rubric.py +363 -0
  1041. modules/scak/tests/test_scak_v2.py +651 -0
  1042. modules/scak/tests/test_skill_mapper.py +217 -0
  1043. modules/scak/tests/test_specific_failures.py +393 -0
  1044. modules/scak/tests/test_tool_registry.py +264 -0
  1045. modules/scak/tests/test_tools_and_plugins.py +303 -0
  1046. modules/scak/tests/test_triage.py +596 -0
  1047. modules/scak/tests/test_write_through.py +319 -0
  1048. agent_os_kernel-1.1.0.dist-info/METADATA +0 -400
  1049. agent_os_kernel-1.1.0.dist-info/RECORD +0 -12
  1050. {agent_os_kernel-1.1.0.dist-info → agent_os_kernel-1.3.0.dist-info}/WHEEL +0 -0
  1051. {agent_os_kernel-1.1.0.dist-info → agent_os_kernel-1.3.0.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,105 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 700 500" font-family="Arial, sans-serif">
3
+ <defs>
4
+ <linearGradient id="hotGrad2" x1="0%" y1="0%" x2="100%" y2="100%">
5
+ <stop offset="0%" style="stop-color:#FF6B6B;stop-opacity:1" />
6
+ <stop offset="100%" style="stop-color:#EE5A5A;stop-opacity:1" />
7
+ </linearGradient>
8
+ <linearGradient id="warmGrad2" x1="0%" y1="0%" x2="100%" y2="100%">
9
+ <stop offset="0%" style="stop-color:#FFB347;stop-opacity:1" />
10
+ <stop offset="100%" style="stop-color:#FFA500;stop-opacity:1" />
11
+ </linearGradient>
12
+ <linearGradient id="coldGrad2" x1="0%" y1="0%" x2="100%" y2="100%">
13
+ <stop offset="0%" style="stop-color:#5DADE2;stop-opacity:1" />
14
+ <stop offset="100%" style="stop-color:#3498DB;stop-opacity:1" />
15
+ </linearGradient>
16
+ <filter id="shadow2" x="-20%" y="-20%" width="140%" height="140%">
17
+ <feDropShadow dx="3" dy="3" stdDeviation="4" flood-opacity="0.2"/>
18
+ </filter>
19
+ </defs>
20
+
21
+ <!-- Title -->
22
+ <text x="350" y="35" text-anchor="middle" font-size="24" font-weight="bold" fill="#2C3E50">Context Triad: Intimacy-Based Prioritization</text>
23
+ <text x="350" y="58" text-anchor="middle" font-size="14" fill="#6C757D">Token budget allocation based on contextual intimacy</text>
24
+
25
+ <!-- Triangle visualization -->
26
+ <polygon points="350,90 150,380 550,380" fill="none" stroke="#DEE2E6" stroke-width="3" stroke-dasharray="8,4"/>
27
+
28
+ <!-- HOT (Top) -->
29
+ <circle cx="350" cy="120" r="70" fill="url(#hotGrad2)" filter="url(#shadow2)"/>
30
+ <text x="350" y="105" text-anchor="middle" font-size="28" fill="white">🔥</text>
31
+ <text x="350" y="130" text-anchor="middle" font-size="16" font-weight="bold" fill="white">HOT</text>
32
+ <text x="350" y="148" text-anchor="middle" font-size="11" fill="white">2,000 tokens</text>
33
+
34
+ <!-- Hot details box -->
35
+ <rect x="450" y="75" width="220" height="100" rx="8" fill="white" stroke="#EE5A5A" stroke-width="2" filter="url(#shadow2)"/>
36
+ <text x="560" y="100" text-anchor="middle" font-size="13" font-weight="bold" fill="#EE5A5A">🔥 Hot Context</text>
37
+ <line x1="470" y1="110" x2="650" y2="110" stroke="#EEE" stroke-width="1"/>
38
+ <text x="480" y="130" font-size="11" fill="#495057">• Current conversation turns</text>
39
+ <text x="480" y="148" font-size="11" fill="#495057">• Last 10 messages</text>
40
+ <text x="480" y="166" font-size="11" fill="#495057">• Highest retrieval priority</text>
41
+
42
+ <!-- Arrow to hot box -->
43
+ <path d="M420 120 L448 100" stroke="#EE5A5A" stroke-width="2" fill="none"/>
44
+
45
+ <!-- WARM (Bottom Left) -->
46
+ <circle cx="200" cy="340" r="70" fill="url(#warmGrad2)" filter="url(#shadow2)"/>
47
+ <text x="200" y="325" text-anchor="middle" font-size="28" fill="white">🌡️</text>
48
+ <text x="200" y="350" text-anchor="middle" font-size="16" font-weight="bold" fill="white">WARM</text>
49
+ <text x="200" y="368" text-anchor="middle" font-size="11" fill="white">1,000 tokens</text>
50
+
51
+ <!-- Warm details box -->
52
+ <rect x="30" y="200" width="200" height="100" rx="8" fill="white" stroke="#FFA500" stroke-width="2" filter="url(#shadow2)"/>
53
+ <text x="130" y="225" text-anchor="middle" font-size="13" font-weight="bold" fill="#FFA500">🌡️ Warm Context</text>
54
+ <line x1="50" y1="235" x2="210" y2="235" stroke="#EEE" stroke-width="1"/>
55
+ <text x="60" y="255" font-size="11" fill="#495057">• User preferences</text>
56
+ <text x="60" y="273" font-size="11" fill="#495057">• Recent documents</text>
57
+ <text x="60" y="291" font-size="11" fill="#495057">• Session memory</text>
58
+
59
+ <!-- Arrow to warm box -->
60
+ <path d="M160 290 L145 300" stroke="#FFA500" stroke-width="2" fill="none"/>
61
+
62
+ <!-- COLD (Bottom Right) -->
63
+ <circle cx="500" cy="340" r="70" fill="url(#coldGrad2)" filter="url(#shadow2)"/>
64
+ <text x="500" y="325" text-anchor="middle" font-size="28" fill="white">❄️</text>
65
+ <text x="500" y="350" text-anchor="middle" font-size="16" font-weight="bold" fill="white">COLD</text>
66
+ <text x="500" y="368" text-anchor="middle" font-size="11" fill="white">5,000 tokens</text>
67
+
68
+ <!-- Cold details box -->
69
+ <rect x="470" y="200" width="200" height="100" rx="8" fill="white" stroke="#3498DB" stroke-width="2" filter="url(#shadow2)"/>
70
+ <text x="570" y="225" text-anchor="middle" font-size="13" font-weight="bold" fill="#3498DB">❄️ Cold Context</text>
71
+ <line x1="490" y1="235" x2="650" y2="235" stroke="#EEE" stroke-width="1"/>
72
+ <text x="500" y="255" font-size="11" fill="#495057">• Historical archives</text>
73
+ <text x="500" y="273" font-size="11" fill="#495057">• Reference documentation</text>
74
+ <text x="500" y="291" font-size="11" fill="#495057">• Background knowledge</text>
75
+
76
+ <!-- Arrow to cold box -->
77
+ <path d="M540 290 L555 300" stroke="#3498DB" stroke-width="2" fill="none"/>
78
+
79
+ <!-- Central LLM -->
80
+ <rect x="290" y="230" width="120" height="50" rx="25" fill="#2C3E50" filter="url(#shadow2)"/>
81
+ <text x="350" y="260" text-anchor="middle" font-size="14" font-weight="bold" fill="white">🤖 LLM</text>
82
+
83
+ <!-- Arrows to LLM -->
84
+ <path d="M350 190 L350 230" stroke="#EE5A5A" stroke-width="3" fill="none" marker-end="url(#redarrow)"/>
85
+ <path d="M250 300 L295 260" stroke="#FFA500" stroke-width="3" fill="none" marker-end="url(#orangearrow)"/>
86
+ <path d="M450 300 L405 260" stroke="#3498DB" stroke-width="3" fill="none" marker-end="url(#bluearrow2)"/>
87
+
88
+ <defs>
89
+ <marker id="redarrow" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
90
+ <polygon points="0 0, 10 3.5, 0 7" fill="#EE5A5A"/>
91
+ </marker>
92
+ <marker id="orangearrow" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
93
+ <polygon points="0 0, 10 3.5, 0 7" fill="#FFA500"/>
94
+ </marker>
95
+ <marker id="bluearrow2" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
96
+ <polygon points="0 0, 10 3.5, 0 7" fill="#3498DB"/>
97
+ </marker>
98
+ </defs>
99
+
100
+ <!-- Token Budget Summary -->
101
+ <rect x="150" y="420" width="400" height="70" rx="10" fill="#F8F9FA" stroke="#DEE2E6" stroke-width="2"/>
102
+ <text x="350" y="445" text-anchor="middle" font-size="14" font-weight="bold" fill="#2C3E50">Total Token Budget: 8,000</text>
103
+ <text x="350" y="468" text-anchor="middle" font-size="12" fill="#6C757D">71% average utilization → 5,820 useful tokens per request</text>
104
+ <text x="350" y="485" text-anchor="middle" font-size="11" fill="#27AE60" font-weight="bold">Precision truncation, not lossy summarization</text>
105
+ </svg>
@@ -0,0 +1,113 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 500" font-family="Arial, sans-serif">
3
+ <defs>
4
+ <linearGradient id="barGrad" x1="0%" y1="0%" x2="100%" y2="0%">
5
+ <stop offset="0%" style="stop-color:#3498DB;stop-opacity:1" />
6
+ <stop offset="100%" style="stop-color:#2980B9;stop-opacity:1" />
7
+ </linearGradient>
8
+ <linearGradient id="fullGrad" x1="0%" y1="0%" x2="100%" y2="0%">
9
+ <stop offset="0%" style="stop-color:#27AE60;stop-opacity:1" />
10
+ <stop offset="100%" style="stop-color:#1E8449;stop-opacity:1" />
11
+ </linearGradient>
12
+ <filter id="barShadow" x="-5%" y="-5%" width="110%" height="120%">
13
+ <feDropShadow dx="1" dy="2" stdDeviation="2" flood-opacity="0.15"/>
14
+ </filter>
15
+ </defs>
16
+
17
+ <!-- Title -->
18
+ <text x="400" y="35" text-anchor="middle" font-size="22" font-weight="bold" fill="#2C3E50">Ablation Study: Component Contributions to Precision@5</text>
19
+ <text x="400" y="58" text-anchor="middle" font-size="13" fill="#6C757D">Each component's individual contribution measured by disabling others</text>
20
+
21
+ <!-- Chart area -->
22
+ <rect x="180" y="80" width="580" height="340" fill="#FAFAFA" stroke="#E0E0E0" stroke-width="1"/>
23
+
24
+ <!-- Y-axis -->
25
+ <line x1="180" y1="80" x2="180" y2="420" stroke="#495057" stroke-width="2"/>
26
+ <text x="30" y="260" text-anchor="middle" font-size="14" font-weight="bold" fill="#2C3E50" transform="rotate(-90, 30, 260)">Precision@5</text>
27
+
28
+ <!-- Y-axis labels -->
29
+ <text x="170" y="420" text-anchor="end" font-size="11" fill="#6C757D">0.50</text>
30
+ <line x1="175" y1="416" x2="760" y2="416" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
31
+
32
+ <text x="170" y="360" text-anchor="end" font-size="11" fill="#6C757D">0.60</text>
33
+ <line x1="175" y1="356" x2="760" y2="356" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
34
+
35
+ <text x="170" y="300" text-anchor="end" font-size="11" fill="#6C757D">0.70</text>
36
+ <line x1="175" y1="296" x2="760" y2="296" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
37
+
38
+ <text x="170" y="240" text-anchor="end" font-size="11" fill="#6C757D">0.80</text>
39
+ <line x1="175" y1="236" x2="760" y2="236" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
40
+
41
+ <text x="170" y="180" text-anchor="end" font-size="11" fill="#6C757D">0.90</text>
42
+ <line x1="175" y1="176" x2="760" y2="176" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
43
+
44
+ <!-- X-axis -->
45
+ <line x1="180" y1="420" x2="760" y2="420" stroke="#495057" stroke-width="2"/>
46
+
47
+ <!-- Baseline reference line at 0.64 -->
48
+ <line x1="180" y1="332" x2="760" y2="332" stroke="#E74C3C" stroke-width="2" stroke-dasharray="8,4"/>
49
+ <text x="765" y="336" font-size="10" fill="#E74C3C" font-weight="bold">Baseline (0.64)</text>
50
+
51
+ <!-- Bars - scaled: 0.50 = 420, 0.90 = 176, so each 0.01 = 6.1px -->
52
+ <!-- Height formula: 420 - ((value - 0.50) * 600) -->
53
+
54
+ <!-- Bar 1: Baseline 0.640 -->
55
+ <rect x="205" y="332" width="70" height="88" fill="#95A5A6" filter="url(#barShadow)" rx="3"/>
56
+ <text x="240" y="322" text-anchor="middle" font-size="12" font-weight="bold" fill="#2C3E50">0.640</text>
57
+ <text x="240" y="445" text-anchor="middle" font-size="10" fill="#495057">Baseline</text>
58
+ <text x="240" y="458" text-anchor="middle" font-size="9" fill="#6C757D">(Naive)</text>
59
+
60
+ <!-- Bar 2: +Structure 0.740 (+15.6%) -->
61
+ <rect x="295" y="272" width="70" height="148" fill="url(#barGrad)" filter="url(#barShadow)" rx="3"/>
62
+ <text x="330" y="262" text-anchor="middle" font-size="12" font-weight="bold" fill="#2C3E50">0.740</text>
63
+ <text x="330" y="248" text-anchor="middle" font-size="10" fill="#27AE60" font-weight="bold">+15.6%</text>
64
+ <text x="330" y="445" text-anchor="middle" font-size="10" fill="#495057">+Structure</text>
65
+ <text x="330" y="458" text-anchor="middle" font-size="9" fill="#6C757D">Aware</text>
66
+
67
+ <!-- Bar 3: +Metadata 0.720 (+12.5%) -->
68
+ <rect x="385" y="284" width="70" height="136" fill="url(#barGrad)" filter="url(#barShadow)" rx="3"/>
69
+ <text x="420" y="274" text-anchor="middle" font-size="12" font-weight="bold" fill="#2C3E50">0.720</text>
70
+ <text x="420" y="260" text-anchor="middle" font-size="10" fill="#27AE60" font-weight="bold">+12.5%</text>
71
+ <text x="420" y="445" text-anchor="middle" font-size="10" fill="#495057">+Metadata</text>
72
+ <text x="420" y="458" text-anchor="middle" font-size="9" fill="#6C757D">Injection</text>
73
+
74
+ <!-- Bar 4: +Time Decay 0.700 (+9.4%) -->
75
+ <rect x="475" y="296" width="70" height="124" fill="url(#barGrad)" filter="url(#barShadow)" rx="3"/>
76
+ <text x="510" y="286" text-anchor="middle" font-size="12" font-weight="bold" fill="#2C3E50">0.700</text>
77
+ <text x="510" y="272" text-anchor="middle" font-size="10" fill="#27AE60" font-weight="bold">+9.4%</text>
78
+ <text x="510" y="445" text-anchor="middle" font-size="10" fill="#495057">+Time</text>
79
+ <text x="510" y="458" text-anchor="middle" font-size="9" fill="#6C757D">Decay</text>
80
+
81
+ <!-- Bar 5: +Pragmatic 0.680 (+6.3%) -->
82
+ <rect x="565" y="308" width="70" height="112" fill="url(#barGrad)" filter="url(#barShadow)" rx="3"/>
83
+ <text x="600" y="298" text-anchor="middle" font-size="12" font-weight="bold" fill="#2C3E50">0.680</text>
84
+ <text x="600" y="284" text-anchor="middle" font-size="10" fill="#27AE60" font-weight="bold">+6.3%</text>
85
+ <text x="600" y="445" text-anchor="middle" font-size="10" fill="#495057">+Pragmatic</text>
86
+ <text x="600" y="458" text-anchor="middle" font-size="9" fill="#6C757D">Truth</text>
87
+
88
+ <!-- Bar 6: Full CaaS 0.820 (+28.1%) -->
89
+ <rect x="655" y="224" width="80" height="196" fill="url(#fullGrad)" filter="url(#barShadow)" rx="3"/>
90
+ <text x="695" y="214" text-anchor="middle" font-size="14" font-weight="bold" fill="#1E8449">0.820</text>
91
+ <text x="695" y="198" text-anchor="middle" font-size="12" fill="#27AE60" font-weight="bold">+28.1%</text>
92
+ <text x="695" y="445" text-anchor="middle" font-size="11" fill="#1E8449" font-weight="bold">Full</text>
93
+ <text x="695" y="458" text-anchor="middle" font-size="11" fill="#1E8449" font-weight="bold">CaaS</text>
94
+
95
+ <!-- Star indicator for full -->
96
+ <text x="695" y="183" text-anchor="middle" font-size="16">⭐</text>
97
+
98
+ <!-- Legend / Key findings box -->
99
+ <rect x="50" y="80" width="120" height="120" rx="6" fill="white" stroke="#DEE2E6" stroke-width="1"/>
100
+ <text x="110" y="100" text-anchor="middle" font-size="11" font-weight="bold" fill="#2C3E50">Key Findings</text>
101
+ <line x1="60" y1="108" x2="160" y2="108" stroke="#E0E0E0" stroke-width="1"/>
102
+ <rect x="60" y="118" width="12" height="12" fill="#3498DB" rx="2"/>
103
+ <text x="78" y="128" font-size="9" fill="#495057">Individual</text>
104
+ <rect x="60" y="138" width="12" height="12" fill="#27AE60" rx="2"/>
105
+ <text x="78" y="148" font-size="9" fill="#495057">Combined</text>
106
+ <line x1="60" y1="162" x2="160" y2="162" stroke="#E74C3C" stroke-width="2" stroke-dasharray="4,2"/>
107
+ <text x="78" y="172" font-size="9" fill="#495057">Baseline</text>
108
+ <text x="110" y="192" text-anchor="middle" font-size="8" fill="#6C757D" font-style="italic">p &lt; 0.001</text>
109
+
110
+ <!-- Statistical note -->
111
+ <rect x="200" y="470" width="400" height="25" rx="4" fill="#E8F8F5" stroke="#1ABC9C" stroke-width="1"/>
112
+ <text x="400" y="487" text-anchor="middle" font-size="11" fill="#1ABC9C" font-weight="bold">Statistical significance: p &lt; 0.001 | Cohen's d = 3.36 (large effect)</text>
113
+ </svg>
@@ -0,0 +1,97 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 700 400" font-family="Arial, sans-serif">
3
+ <defs>
4
+ <linearGradient id="heuristicGrad" x1="0%" y1="0%" x2="0%" y2="100%">
5
+ <stop offset="0%" style="stop-color:#27AE60;stop-opacity:1" />
6
+ <stop offset="100%" style="stop-color:#1E8449;stop-opacity:1" />
7
+ </linearGradient>
8
+ <linearGradient id="mlGrad" x1="0%" y1="0%" x2="0%" y2="100%">
9
+ <stop offset="0%" style="stop-color:#F39C12;stop-opacity:1" />
10
+ <stop offset="100%" style="stop-color:#E67E22;stop-opacity:1" />
11
+ </linearGradient>
12
+ <linearGradient id="llmGrad" x1="0%" y1="0%" x2="0%" y2="100%">
13
+ <stop offset="0%" style="stop-color:#E74C3C;stop-opacity:1" />
14
+ <stop offset="100%" style="stop-color:#C0392B;stop-opacity:1" />
15
+ </linearGradient>
16
+ <filter id="barShadow2" x="-5%" y="-5%" width="110%" height="120%">
17
+ <feDropShadow dx="2" dy="2" stdDeviation="3" flood-opacity="0.2"/>
18
+ </filter>
19
+ </defs>
20
+
21
+ <!-- Title -->
22
+ <text x="350" y="35" text-anchor="middle" font-size="20" font-weight="bold" fill="#2C3E50">Router Latency Comparison (Log Scale)</text>
23
+ <text x="350" y="55" text-anchor="middle" font-size="12" fill="#6C757D">CaaS Heuristic Router vs. ML-based and LLM-based alternatives</text>
24
+
25
+ <!-- Chart background -->
26
+ <rect x="120" y="75" width="480" height="250" fill="#FAFAFA" stroke="#E0E0E0" stroke-width="1"/>
27
+
28
+ <!-- Y-axis (log scale visual) -->
29
+ <line x1="120" y1="75" x2="120" y2="325" stroke="#495057" stroke-width="2"/>
30
+ <text x="60" y="205" text-anchor="middle" font-size="13" font-weight="bold" fill="#2C3E50" transform="rotate(-90, 60, 205)">Latency (ms)</text>
31
+
32
+ <!-- Y-axis labels (log scale) -->
33
+ <text x="110" y="320" text-anchor="end" font-size="10" fill="#6C757D">0.001</text>
34
+ <line x1="115" y1="316" x2="600" y2="316" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
35
+
36
+ <text x="110" y="280" text-anchor="end" font-size="10" fill="#6C757D">0.01</text>
37
+ <line x1="115" y1="276" x2="600" y2="276" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
38
+
39
+ <text x="110" y="240" text-anchor="end" font-size="10" fill="#6C757D">0.1</text>
40
+ <line x1="115" y1="236" x2="600" y2="236" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
41
+
42
+ <text x="110" y="200" text-anchor="end" font-size="10" fill="#6C757D">1</text>
43
+ <line x1="115" y1="196" x2="600" y2="196" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
44
+
45
+ <text x="110" y="160" text-anchor="end" font-size="10" fill="#6C757D">10</text>
46
+ <line x1="115" y1="156" x2="600" y2="156" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
47
+
48
+ <text x="110" y="120" text-anchor="end" font-size="10" fill="#6C757D">100</text>
49
+ <line x1="115" y1="116" x2="600" y2="116" stroke="#E0E0E0" stroke-width="1" stroke-dasharray="4,4"/>
50
+
51
+ <text x="110" y="85" text-anchor="end" font-size="10" fill="#6C757D">1000</text>
52
+
53
+ <!-- X-axis -->
54
+ <line x1="120" y1="325" x2="600" y2="325" stroke="#495057" stroke-width="2"/>
55
+
56
+ <!-- Heuristic Router Bar (0.003ms) - log position ~300 -->
57
+ <rect x="160" y="298" width="100" height="27" fill="url(#heuristicGrad)" filter="url(#barShadow2)" rx="4"/>
58
+ <text x="210" y="287" text-anchor="middle" font-size="14" font-weight="bold" fill="#1E8449">0.003ms</text>
59
+ <text x="210" y="345" text-anchor="middle" font-size="12" fill="#495057" font-weight="bold">Heuristic</text>
60
+ <text x="210" y="360" text-anchor="middle" font-size="11" fill="#27AE60">(CaaS)</text>
61
+
62
+ <!-- ML Router Bar (15.2ms) - log position ~148 -->
63
+ <rect x="310" y="148" width="100" height="177" fill="url(#mlGrad)" filter="url(#barShadow2)" rx="4"/>
64
+ <text x="360" y="138" text-anchor="middle" font-size="14" font-weight="bold" fill="#E67E22">15.2ms</text>
65
+ <text x="360" y="345" text-anchor="middle" font-size="12" fill="#495057" font-weight="bold">ML-based</text>
66
+ <text x="360" y="360" text-anchor="middle" font-size="11" fill="#F39C12">(Classifier)</text>
67
+
68
+ <!-- LLM Router Bar (450ms) - log position ~93 -->
69
+ <rect x="460" y="93" width="100" height="232" fill="url(#llmGrad)" filter="url(#barShadow2)" rx="4"/>
70
+ <text x="510" y="83" text-anchor="middle" font-size="14" font-weight="bold" fill="#C0392B">450ms</text>
71
+ <text x="510" y="345" text-anchor="middle" font-size="12" fill="#495057" font-weight="bold">LLM-based</text>
72
+ <text x="510" y="360" text-anchor="middle" font-size="11" fill="#E74C3C">(GPT-3.5)</text>
73
+
74
+ <!-- Speedup annotations -->
75
+ <path d="M260 290 Q 285 250 310 200" stroke="#2C3E50" stroke-width="1.5" fill="none" stroke-dasharray="4,2"/>
76
+ <text x="295" y="235" text-anchor="middle" font-size="11" font-weight="bold" fill="#2C3E50">5,000×</text>
77
+ <text x="295" y="248" text-anchor="middle" font-size="9" fill="#6C757D">faster</text>
78
+
79
+ <path d="M260 295 Q 360 230 460 160" stroke="#2C3E50" stroke-width="1.5" fill="none" stroke-dasharray="4,2"/>
80
+ <text x="380" y="200" text-anchor="middle" font-size="11" font-weight="bold" fill="#2C3E50">150,000×</text>
81
+ <text x="380" y="213" text-anchor="middle" font-size="9" fill="#6C757D">faster</text>
82
+
83
+ <!-- Key insight box -->
84
+ <rect x="610" y="100" width="80" height="140" rx="6" fill="#E8F8F5" stroke="#27AE60" stroke-width="2"/>
85
+ <text x="650" y="125" text-anchor="middle" font-size="10" font-weight="bold" fill="#27AE60">Why?</text>
86
+ <line x1="620" y1="132" x2="680" y2="132" stroke="#27AE60" stroke-width="1"/>
87
+ <text x="650" y="150" text-anchor="middle" font-size="8" fill="#495057">No ML</text>
88
+ <text x="650" y="163" text-anchor="middle" font-size="8" fill="#495057">inference</text>
89
+ <text x="650" y="180" text-anchor="middle" font-size="8" fill="#495057">No API</text>
90
+ <text x="650" y="193" text-anchor="middle" font-size="8" fill="#495057">calls</text>
91
+ <text x="650" y="210" text-anchor="middle" font-size="8" fill="#495057">Pure</text>
92
+ <text x="650" y="223" text-anchor="middle" font-size="8" fill="#495057">heuristics</text>
93
+
94
+ <!-- Bottom note -->
95
+ <rect x="150" y="375" width="400" height="20" rx="4" fill="#FEF9E7" stroke="#F1C40F" stroke-width="1"/>
96
+ <text x="350" y="389" text-anchor="middle" font-size="11" fill="#B7950B" font-weight="bold">"Speed > Smarts" — deterministic routing enables real-time RAG</text>
97
+ </svg>
@@ -0,0 +1,103 @@
1
+ # Introduction
2
+
3
+ ## The RAG Revolution and Its Hidden Pitfalls
4
+
5
+ Retrieval-Augmented Generation (RAG) has emerged as the dominant paradigm for grounding Large Language Model (LLM) outputs in factual, domain-specific knowledge [Lewis et al., 2020]. By retrieving relevant documents at inference time, RAG systems overcome the knowledge cutoff limitations of pre-trained models while enabling deployment in enterprise settings where proprietary data must remain private.
6
+
7
+ Yet beneath the surface of this revolution lies a troubling reality: **most production RAG systems are fundamentally broken**. Not in obvious ways that cause immediate failures, but in subtle architectural choices that degrade quality, waste resources, and—most critically—erode user trust over time.
8
+
9
+ ## The Seven Fallacies of Production RAG
10
+
11
+ Through extensive deployment experience and analysis of existing frameworks, we identify **seven critical fallacies** that plague production RAG systems:
12
+
13
+ ### 1. The Flat Chunk Fallacy (Structure Problem)
14
+
15
+ The standard approach—split documents into fixed-size chunks (e.g., 500 tokens), embed them, and retrieve by vector similarity—treats all content as equally valuable. But a class definition in source code carries fundamentally different weight than a TODO comment. A contract's liability clause matters more than its formatting instructions. By flattening this hierarchy, we lose the structural signals that humans naturally use to prioritize information.
16
+
17
+ **The Reality**: Structure encodes importance, and ignoring it is negligent.
18
+
19
+ ### 2. Context Amnesia (Metadata Problem)
20
+
21
+ When a chunk is extracted from its parent document, it loses critical context. Consider the retrieved text: *"It increased by 5%."* What increased? Revenue? Costs? Infection rates? Without metadata preserving the document path (`Q3 Earnings → Revenue → North America`), the chunk is semantically orphaned.
22
+
23
+ **The Reality**: A chunk without metadata is a fact without meaning.
24
+
25
+ ### 3. Time-Blind Retrieval (Temporal Problem)
26
+
27
+ Traditional retrieval optimizes for semantic similarity: "How to restart the server" in 2021 matches "How to restart the server" in 2025 with near-perfect similarity. But the 2021 procedure may be dangerously outdated—the architecture changed, the commands differ, the old approach may even cause data loss.
28
+
29
+ **The Reality**: In software, truth has a half-life. Retrieval must decay with time.
30
+
31
+ ### 4. The Flat Context Fallacy (Priority Problem)
32
+
33
+ Most systems stuff context into the LLM's window until it's full, treating the user's last message, their stated preferences, and historical archives from two years ago with equal priority. But the question asked 30 seconds ago is categorically more important than background context from last month. This leads to what we term the **Accumulation Paradox**: more context can paradoxically *degrade* performance, as demonstrated empirically by Liu et al. [2023] who showed that LLMs systematically ignore information in the middle of long contexts.
34
+
35
+ **The Reality**: Context has intimacy levels. Proximity in conversation ≠ proximity in relevance.
36
+
37
+ ### 5. The Official Truth Fallacy (Source Problem)
38
+
39
+ Enterprise documentation often contains aspirational or theoretical information: "The API supports 100 concurrent requests." But the engineering Slack channel contains the practical truth: "We crash around 50; the docs are lying." Traditional RAG surfaces only the official answer, leading users astray.
40
+
41
+ **The Reality**: Official ≠ Accurate. Systems must surface the *pragmatic truth*.
42
+
43
+ ### 6. The Brutal Squeeze (Context Management Problem)
44
+
45
+ When conversation history exceeds context limits, the common solution is AI-powered summarization: "Let's ask an LLM to compress the history." But this is a trap:
46
+ - Summarization costs tokens (money) to generate
47
+ - Summaries lose nuance: "I tried X and it failed with error E-1234" becomes "User attempted troubleshooting"
48
+ - The specific error code—exactly what the user needs—is lost
49
+
50
+ **The Reality**: Lossless truncation (FIFO sliding window) beats lossy compression (summarization).
51
+
52
+ ### 7. The Middleware Gap (Trust Problem)
53
+
54
+ Startups offer "intelligent routing" services: send your queries through their API, and they'll route to the cheapest model. But no enterprise CISO will send proprietary data through a random middleware startup to save 30% on tokens.
55
+
56
+ **The Reality**: The winner in enterprise AI won't have the smartest router—they'll have the one enterprises trust with the keys.
57
+
58
+ ## Our Contribution: Context-as-a-Service
59
+
60
+ We present **Context-as-a-Service (CaaS)**, an open-source framework that systematically addresses all seven fallacies through a principled architecture:
61
+
62
+ 1. **Structure-Aware Indexing**: A three-tier value hierarchy (High/Medium/Low) that respects document structure instead of flat chunking.
63
+
64
+ 2. **Metadata Injection**: Automatic enrichment of chunks with their document path, section hierarchy, and temporal metadata.
65
+
66
+ 3. **Time-Based Decay**: Exponential decay functions that prioritize recent content, with configurable half-life parameters per domain.
67
+
68
+ 4. **Context Triad**: A Hot/Warm/Cold classification that treats context by intimacy:
69
+ - **Hot**: Current conversation (highest priority)
70
+ - **Warm**: User preferences, recent documents
71
+ - **Cold**: Historical archives, background knowledge
72
+
73
+ 5. **Pragmatic Truth**: Parallel tracking of official documentation and informal sources (Slack, tickets, notes) with transparent conflict surfacing.
74
+
75
+ 6. **Sliding Window Management**: FIFO truncation that preserves recent turns perfectly intact rather than summarizing everything poorly.
76
+
77
+ 7. **Trust Gateway**: An on-premises/private-cloud router that enterprises can deploy behind their firewall with zero data leakage.
78
+
79
+ ## Evaluation and Results
80
+
81
+ We evaluate CaaS on a new benchmark corpus of 16 enterprise documents spanning code, legal, HR, and engineering domains, released publicly on Hugging Face for reproducibility.
82
+
83
+ Key results:
84
+ - **+28.1% Precision@5** over flat-chunk baselines
85
+ - **+27.9% NDCG@10** improvement in ranking quality
86
+ - **0.003ms** routing latency (sub-millisecond)
87
+ - **3.36 Cohen's d** effect size (statistically significant, p < 0.001)
88
+
89
+ ## Paper Organization
90
+
91
+ The remainder of this paper is organized as follows:
92
+ - **Section 2** reviews related work in RAG, context management, and enterprise AI deployment
93
+ - **Section 3** details the CaaS architecture and algorithms
94
+ - **Section 4** presents our experimental methodology and benchmark corpus
95
+ - **Section 5** reports results and ablation studies
96
+ - **Section 6** discusses limitations and future work
97
+ - **Section 7** concludes
98
+
99
+ ---
100
+
101
+ ## References (for this section)
102
+
103
+ - Lewis, P., et al. (2020). "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks." *NeurIPS 2020*.