rubik 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (523) hide show
  1. checksums.yaml +7 -0
  2. data/ATTRIBUTION.md +139 -0
  3. data/CHANGELOG.md +236 -0
  4. data/LICENSE +21 -0
  5. data/README.md +269 -0
  6. data/bin/rubik +82 -0
  7. data/lib/rubik/adapter/base.rb +195 -0
  8. data/lib/rubik/adapter/c.rb +36 -0
  9. data/lib/rubik/adapter/crystal.rb +78 -0
  10. data/lib/rubik/adapter/generic.rb +86 -0
  11. data/lib/rubik/adapter/go.rb +36 -0
  12. data/lib/rubik/adapter/node.rb +146 -0
  13. data/lib/rubik/adapter/process.rb +78 -0
  14. data/lib/rubik/adapter/python.rb +30 -0
  15. data/lib/rubik/adapter/registry.rb +81 -0
  16. data/lib/rubik/adapter/ruby.rb +30 -0
  17. data/lib/rubik/adapter/rust.rb +36 -0
  18. data/lib/rubik/adapter/zig.rb +36 -0
  19. data/lib/rubik/adapter.rb +18 -0
  20. data/lib/rubik/ast/body_loader.rb +19 -0
  21. data/lib/rubik/ast/c_extractor.rb +114 -0
  22. data/lib/rubik/ast/cache_store.rb +191 -0
  23. data/lib/rubik/ast/extractor.rb +59 -0
  24. data/lib/rubik/ast/fallback_cleaner.rb +145 -0
  25. data/lib/rubik/ast/go_extractor.rb +148 -0
  26. data/lib/rubik/ast/graph.rb +272 -0
  27. data/lib/rubik/ast/python_extractor.rb +120 -0
  28. data/lib/rubik/ast/ruby_extractor.rb +260 -0
  29. data/lib/rubik/ast/rust_extractor.rb +127 -0
  30. data/lib/rubik/ast/symbol.rb +103 -0
  31. data/lib/rubik/ast/treesitter/base_walker.rb +109 -0
  32. data/lib/rubik/ast/treesitter/c_walker.rb +122 -0
  33. data/lib/rubik/ast/treesitter/go_walker.rb +120 -0
  34. data/lib/rubik/ast/treesitter/python_walker.rb +107 -0
  35. data/lib/rubik/ast/treesitter/rust_walker.rb +130 -0
  36. data/lib/rubik/ast/treesitter/typescript_walker.rb +182 -0
  37. data/lib/rubik/ast/treesitter/zig_walker.rb +109 -0
  38. data/lib/rubik/ast/treesitter_extractor.rb +93 -0
  39. data/lib/rubik/ast/typescript_extractor.rb +283 -0
  40. data/lib/rubik/ast/zig_extractor.rb +116 -0
  41. data/lib/rubik/ast.rb +13 -0
  42. data/lib/rubik/benchmark/runner.rb +224 -0
  43. data/lib/rubik/benchmark/synth_repo.rb +59 -0
  44. data/lib/rubik/benchmark.rb +9 -0
  45. data/lib/rubik/buffer/diff.rb +43 -0
  46. data/lib/rubik/buffer/manager.rb +427 -0
  47. data/lib/rubik/buffer/path_validator.rb +60 -0
  48. data/lib/rubik/buffer/snapshot.rb +99 -0
  49. data/lib/rubik/buffer.rb +10 -0
  50. data/lib/rubik/coeffects.rb +129 -0
  51. data/lib/rubik/concurrency/boundary.rb +74 -0
  52. data/lib/rubik/concurrency/dns_pool.rb +68 -0
  53. data/lib/rubik/concurrency/errors.rb +17 -0
  54. data/lib/rubik/concurrency/event_loop.rb +441 -0
  55. data/lib/rubik/concurrency/join.rb +55 -0
  56. data/lib/rubik/concurrency/process_waiter.rb +55 -0
  57. data/lib/rubik/concurrency/scheduler.rb +84 -0
  58. data/lib/rubik/concurrency/timers.rb +109 -0
  59. data/lib/rubik/concurrency.rb +132 -0
  60. data/lib/rubik/config/deep_ops.rb +80 -0
  61. data/lib/rubik/config/defaults.rb +248 -0
  62. data/lib/rubik/config/model_catalog.rb +93 -0
  63. data/lib/rubik/config/store.rb +155 -0
  64. data/lib/rubik/config.rb +216 -0
  65. data/lib/rubik/context/git_info.rb +84 -0
  66. data/lib/rubik/context/git_lister.rb +37 -0
  67. data/lib/rubik/context/index.rb +134 -0
  68. data/lib/rubik/context/repo_context_reader.rb +121 -0
  69. data/lib/rubik/context/scanner.rb +439 -0
  70. data/lib/rubik/context.rb +11 -0
  71. data/lib/rubik/diagnostics/collector.rb +200 -0
  72. data/lib/rubik/diagnostics/entry.rb +60 -0
  73. data/lib/rubik/diagnostics/parser.rb +107 -0
  74. data/lib/rubik/diagnostics.rb +10 -0
  75. data/lib/rubik/event_bus.rb +56 -0
  76. data/lib/rubik/kernel/dispatcher.rb +171 -0
  77. data/lib/rubik/kernel/dmesg.rb +116 -0
  78. data/lib/rubik/kernel/init.rb +177 -0
  79. data/lib/rubik/kernel/record.rb +85 -0
  80. data/lib/rubik/kernel/unit.rb +160 -0
  81. data/lib/rubik/llm/anthropic.rb +202 -0
  82. data/lib/rubik/llm/chunk_assembler.rb +285 -0
  83. data/lib/rubik/llm/client.rb +526 -0
  84. data/lib/rubik/llm/formatter.rb +450 -0
  85. data/lib/rubik/llm/message_sanitizer.rb +87 -0
  86. data/lib/rubik/llm/ollama.rb +167 -0
  87. data/lib/rubik/llm/openai.rb +21 -0
  88. data/lib/rubik/llm/openai_compatible.rb +216 -0
  89. data/lib/rubik/llm/provider.rb +125 -0
  90. data/lib/rubik/llm/registry.rb +336 -0
  91. data/lib/rubik/llm/router.rb +100 -0
  92. data/lib/rubik/llm.rb +18 -0
  93. data/lib/rubik/log.rb +38 -0
  94. data/lib/rubik/lsp/client.rb +475 -0
  95. data/lib/rubik/lsp/manager.rb +366 -0
  96. data/lib/rubik/lsp.rb +9 -0
  97. data/lib/rubik/mcp/boot_lifecycle.rb +114 -0
  98. data/lib/rubik/mcp/client.rb +169 -0
  99. data/lib/rubik/mcp/errors.rb +11 -0
  100. data/lib/rubik/mcp/manager.rb +619 -0
  101. data/lib/rubik/mcp/proxy_tool.rb +104 -0
  102. data/lib/rubik/mcp/transport/stdio.rb +255 -0
  103. data/lib/rubik/mcp.rb +12 -0
  104. data/lib/rubik/orchestrator/activity_log.rb +75 -0
  105. data/lib/rubik/orchestrator/auto_apply.rb +166 -0
  106. data/lib/rubik/orchestrator/budget_manager.rb +97 -0
  107. data/lib/rubik/orchestrator/continuation_manager.rb +161 -0
  108. data/lib/rubik/orchestrator/finish_message_selector.rb +55 -0
  109. data/lib/rubik/orchestrator/goal_ledger/drift.rb +71 -0
  110. data/lib/rubik/orchestrator/goal_ledger/ledger.rb +399 -0
  111. data/lib/rubik/orchestrator/goal_ledger/observation_projection.rb +179 -0
  112. data/lib/rubik/orchestrator/goal_ledger/patch.rb +268 -0
  113. data/lib/rubik/orchestrator/goal_ledger/schema.rb +123 -0
  114. data/lib/rubik/orchestrator/goal_ledger/validator.rb +361 -0
  115. data/lib/rubik/orchestrator/goal_ledger/verifier.rb +129 -0
  116. data/lib/rubik/orchestrator/goal_ledger/verify_spec.rb +50 -0
  117. data/lib/rubik/orchestrator/goal_ledger.rb +65 -0
  118. data/lib/rubik/orchestrator/goal_state.rb +184 -0
  119. data/lib/rubik/orchestrator/goal_wait.rb +125 -0
  120. data/lib/rubik/orchestrator/loop.rb +388 -0
  121. data/lib/rubik/orchestrator/lsp_feedback.rb +55 -0
  122. data/lib/rubik/orchestrator/maestro_gate.rb +65 -0
  123. data/lib/rubik/orchestrator/provider_recovery.rb +90 -0
  124. data/lib/rubik/orchestrator/provider_resolver.rb +69 -0
  125. data/lib/rubik/orchestrator/shell_deps.rb +85 -0
  126. data/lib/rubik/orchestrator/step_executor.rb +328 -0
  127. data/lib/rubik/orchestrator/stream_manager.rb +118 -0
  128. data/lib/rubik/orchestrator/subagent/activation.rb +65 -0
  129. data/lib/rubik/orchestrator/subagent/budget.rb +108 -0
  130. data/lib/rubik/orchestrator/subagent/completion.rb +61 -0
  131. data/lib/rubik/orchestrator/subagent/concurrency_gate.rb +37 -0
  132. data/lib/rubik/orchestrator/subagent/conversation_id.rb +67 -0
  133. data/lib/rubik/orchestrator/subagent/dependency.rb +398 -0
  134. data/lib/rubik/orchestrator/subagent/instance.rb +384 -0
  135. data/lib/rubik/orchestrator/subagent/lifecycle.rb +118 -0
  136. data/lib/rubik/orchestrator/subagent/messaging.rb +61 -0
  137. data/lib/rubik/orchestrator/subagent/narration.rb +125 -0
  138. data/lib/rubik/orchestrator/subagent/notices.rb +209 -0
  139. data/lib/rubik/orchestrator/subagent/questioner.rb +80 -0
  140. data/lib/rubik/orchestrator/subagent/reaper.rb +98 -0
  141. data/lib/rubik/orchestrator/subagent/resilience.rb +70 -0
  142. data/lib/rubik/orchestrator/subagent/reuse.rb +127 -0
  143. data/lib/rubik/orchestrator/subagent/scoped_registry.rb +79 -0
  144. data/lib/rubik/orchestrator/subagent/step_runner.rb +240 -0
  145. data/lib/rubik/orchestrator/subagent/storage_id.rb +26 -0
  146. data/lib/rubik/orchestrator/subagent/supervisor.rb +327 -0
  147. data/lib/rubik/orchestrator/subagent/transcript_formatter.rb +141 -0
  148. data/lib/rubik/orchestrator/subagent/type_registry.rb +199 -0
  149. data/lib/rubik/orchestrator/subagent_notice_inbox.rb +80 -0
  150. data/lib/rubik/orchestrator/tool_call_id.rb +47 -0
  151. data/lib/rubik/orchestrator/tool_circuit_breaker.rb +91 -0
  152. data/lib/rubik/orchestrator/tool_history.rb +39 -0
  153. data/lib/rubik/orchestrator/turn_executor/subagent_channel.rb +102 -0
  154. data/lib/rubik/orchestrator/turn_executor/user_channel.rb +172 -0
  155. data/lib/rubik/orchestrator/turn_executor.rb +376 -0
  156. data/lib/rubik/orchestrator.rb +11 -0
  157. data/lib/rubik/platform/filesystem.rb +64 -0
  158. data/lib/rubik/platform/io_drain.rb +53 -0
  159. data/lib/rubik/platform/path.rb +210 -0
  160. data/lib/rubik/platform/process.rb +38 -0
  161. data/lib/rubik/platform/sanitize.rb +157 -0
  162. data/lib/rubik/platform.rb +113 -0
  163. data/lib/rubik/plugin/dsl.rb +51 -0
  164. data/lib/rubik/plugin/manager.rb +247 -0
  165. data/lib/rubik/plugin/storage.rb +195 -0
  166. data/lib/rubik/plugin.rb +10 -0
  167. data/lib/rubik/prompt/context_builder.rb +377 -0
  168. data/lib/rubik/prompt/context_compactor.rb +326 -0
  169. data/lib/rubik/prompt/conversation_rows.rb +74 -0
  170. data/lib/rubik/prompt/doctrine.rb +160 -0
  171. data/lib/rubik/prompt/emergency_compactor.rb +81 -0
  172. data/lib/rubik/prompt/services.rb +60 -0
  173. data/lib/rubik/prompt/token_estimator.rb +63 -0
  174. data/lib/rubik/prompt/tool_teachings.rb +78 -0
  175. data/lib/rubik/prompt.rb +13 -0
  176. data/lib/rubik/repair/loop.rb +95 -0
  177. data/lib/rubik/repair.rb +8 -0
  178. data/lib/rubik/repl/ast_warmup.rb +129 -0
  179. data/lib/rubik/repl/command_context.rb +214 -0
  180. data/lib/rubik/repl/command_parser.rb +48 -0
  181. data/lib/rubik/repl/commands/agent.rb +30 -0
  182. data/lib/rubik/repl/commands/agent_context.rb +289 -0
  183. data/lib/rubik/repl/commands/agent_execution.rb +342 -0
  184. data/lib/rubik/repl/commands/agent_models.rb +212 -0
  185. data/lib/rubik/repl/commands/agent_providers.rb +232 -0
  186. data/lib/rubik/repl/commands/base.rb +55 -0
  187. data/lib/rubik/repl/commands/buffer.rb +124 -0
  188. data/lib/rubik/repl/commands/dmesg.rb +87 -0
  189. data/lib/rubik/repl/commands/lsp.rb +235 -0
  190. data/lib/rubik/repl/commands/mcp.rb +194 -0
  191. data/lib/rubik/repl/commands/plugins.rb +208 -0
  192. data/lib/rubik/repl/commands/pruner.rb +71 -0
  193. data/lib/rubik/repl/commands/session.rb +183 -0
  194. data/lib/rubik/repl/commands/skills.rb +111 -0
  195. data/lib/rubik/repl/commands/storage.rb +85 -0
  196. data/lib/rubik/repl/commands/subagents.rb +195 -0
  197. data/lib/rubik/repl/commands/system.rb +85 -0
  198. data/lib/rubik/repl/commands/tasks.rb +120 -0
  199. data/lib/rubik/repl/commands/workspace.rb +443 -0
  200. data/lib/rubik/repl/commands.rb +44 -0
  201. data/lib/rubik/repl/composition.rb +32 -0
  202. data/lib/rubik/repl/config_wiring.rb +142 -0
  203. data/lib/rubik/repl/confirmations.rb +56 -0
  204. data/lib/rubik/repl/hooks.rb +47 -0
  205. data/lib/rubik/repl/input_execution.rb +323 -0
  206. data/lib/rubik/repl/input_loop.rb +213 -0
  207. data/lib/rubik/repl/interrupt_handler.rb +217 -0
  208. data/lib/rubik/repl/lifecycle.rb +410 -0
  209. data/lib/rubik/repl/paste_support.rb +88 -0
  210. data/lib/rubik/repl/pending_notice_queue.rb +60 -0
  211. data/lib/rubik/repl/presentation.rb +132 -0
  212. data/lib/rubik/repl/pruner/brief.rb +101 -0
  213. data/lib/rubik/repl/pruner/gate.rb +279 -0
  214. data/lib/rubik/repl/pruner/harness.rb +236 -0
  215. data/lib/rubik/repl/pruner/rules.rb +316 -0
  216. data/lib/rubik/repl/pruner/service.rb +82 -0
  217. data/lib/rubik/repl/pruner.rb +39 -0
  218. data/lib/rubik/repl/service_catalog.rb +374 -0
  219. data/lib/rubik/repl/setup_factories.rb +66 -0
  220. data/lib/rubik/repl/shell.rb +231 -0
  221. data/lib/rubik/repl/step_formatter.rb +324 -0
  222. data/lib/rubik/repl/tee_io.rb +105 -0
  223. data/lib/rubik/repl/terminal_guard.rb +157 -0
  224. data/lib/rubik/repl/turn_recorder.rb +234 -0
  225. data/lib/rubik/repl.rb +14 -0
  226. data/lib/rubik/runtime/ast_service.rb +78 -0
  227. data/lib/rubik/runtime/context.rb +335 -0
  228. data/lib/rubik/runtime/diagnostic_engine.rb +188 -0
  229. data/lib/rubik/runtime/discovery.rb +342 -0
  230. data/lib/rubik/runtime/fiber.rb +142 -0
  231. data/lib/rubik/runtime/fiber_ordering.rb +52 -0
  232. data/lib/rubik/runtime/fiber_retry_gate.rb +84 -0
  233. data/lib/rubik/runtime/index_service.rb +58 -0
  234. data/lib/rubik/runtime/loop_service.rb +73 -0
  235. data/lib/rubik/runtime/manager.rb +241 -0
  236. data/lib/rubik/runtime/overlay_storage.rb +481 -0
  237. data/lib/rubik/runtime/service_definition.rb +54 -0
  238. data/lib/rubik/runtime/service_registration.rb +33 -0
  239. data/lib/rubik/runtime/task_manager.rb +302 -0
  240. data/lib/rubik/runtime.rb +19 -0
  241. data/lib/rubik/sandbox/driver/base.rb +30 -0
  242. data/lib/rubik/sandbox/driver/bubblewrap.rb +111 -0
  243. data/lib/rubik/sandbox/driver/docker.rb +113 -0
  244. data/lib/rubik/sandbox/driver/podman.rb +98 -0
  245. data/lib/rubik/sandbox/driver/process.rb +190 -0
  246. data/lib/rubik/sandbox/driver.rb +91 -0
  247. data/lib/rubik/sandbox/runner.rb +218 -0
  248. data/lib/rubik/sandbox/shell_resolver.rb +178 -0
  249. data/lib/rubik/sandbox.rb +8 -0
  250. data/lib/rubik/security/blocked_guidance.rb +187 -0
  251. data/lib/rubik/security/classifier/classifier.rb +440 -0
  252. data/lib/rubik/security/classifier/commands/agent-browser.yaml +9 -0
  253. data/lib/rubik/security/classifier/commands/apt.yaml +25 -0
  254. data/lib/rubik/security/classifier/commands/awk.yaml +10 -0
  255. data/lib/rubik/security/classifier/commands/basename.yaml +7 -0
  256. data/lib/rubik/security/classifier/commands/bash-classify.yaml +8 -0
  257. data/lib/rubik/security/classifier/commands/bash.yaml +20 -0
  258. data/lib/rubik/security/classifier/commands/black.yaml +12 -0
  259. data/lib/rubik/security/classifier/commands/brew.yaml +31 -0
  260. data/lib/rubik/security/classifier/commands/builtin.yaml +8 -0
  261. data/lib/rubik/security/classifier/commands/cargo.yaml +114 -0
  262. data/lib/rubik/security/classifier/commands/cat.yaml +7 -0
  263. data/lib/rubik/security/classifier/commands/chgrp.yaml +10 -0
  264. data/lib/rubik/security/classifier/commands/chmod.yaml +10 -0
  265. data/lib/rubik/security/classifier/commands/chown.yaml +10 -0
  266. data/lib/rubik/security/classifier/commands/column.yaml +7 -0
  267. data/lib/rubik/security/classifier/commands/comm.yaml +7 -0
  268. data/lib/rubik/security/classifier/commands/command.yaml +12 -0
  269. data/lib/rubik/security/classifier/commands/cp.yaml +7 -0
  270. data/lib/rubik/security/classifier/commands/crystal.yaml +63 -0
  271. data/lib/rubik/security/classifier/commands/curl.yaml +30 -0
  272. data/lib/rubik/security/classifier/commands/cut.yaml +7 -0
  273. data/lib/rubik/security/classifier/commands/date.yaml +10 -0
  274. data/lib/rubik/security/classifier/commands/df.yaml +7 -0
  275. data/lib/rubik/security/classifier/commands/diff.yaml +7 -0
  276. data/lib/rubik/security/classifier/commands/dig.yaml +7 -0
  277. data/lib/rubik/security/classifier/commands/dirname.yaml +7 -0
  278. data/lib/rubik/security/classifier/commands/docker.yaml +177 -0
  279. data/lib/rubik/security/classifier/commands/du.yaml +7 -0
  280. data/lib/rubik/security/classifier/commands/echo.yaml +7 -0
  281. data/lib/rubik/security/classifier/commands/env.yaml +15 -0
  282. data/lib/rubik/security/classifier/commands/eslint.yaml +12 -0
  283. data/lib/rubik/security/classifier/commands/eval.yaml +8 -0
  284. data/lib/rubik/security/classifier/commands/exec.yaml +12 -0
  285. data/lib/rubik/security/classifier/commands/expand.yaml +7 -0
  286. data/lib/rubik/security/classifier/commands/false.yaml +7 -0
  287. data/lib/rubik/security/classifier/commands/file.yaml +7 -0
  288. data/lib/rubik/security/classifier/commands/find.yaml +25 -0
  289. data/lib/rubik/security/classifier/commands/fmt.yaml +7 -0
  290. data/lib/rubik/security/classifier/commands/fold.yaml +7 -0
  291. data/lib/rubik/security/classifier/commands/free.yaml +7 -0
  292. data/lib/rubik/security/classifier/commands/gawk.yaml +10 -0
  293. data/lib/rubik/security/classifier/commands/gcloud.yaml +979 -0
  294. data/lib/rubik/security/classifier/commands/gh.yaml +615 -0
  295. data/lib/rubik/security/classifier/commands/git.yaml +524 -0
  296. data/lib/rubik/security/classifier/commands/glab-discussion.yaml +21 -0
  297. data/lib/rubik/security/classifier/commands/glab.yaml +807 -0
  298. data/lib/rubik/security/classifier/commands/go.yaml +44 -0
  299. data/lib/rubik/security/classifier/commands/gog.yaml +983 -0
  300. data/lib/rubik/security/classifier/commands/gradle.yaml +92 -0
  301. data/lib/rubik/security/classifier/commands/gradlew.yaml +92 -0
  302. data/lib/rubik/security/classifier/commands/grep.yaml +7 -0
  303. data/lib/rubik/security/classifier/commands/groups.yaml +7 -0
  304. data/lib/rubik/security/classifier/commands/gunzip.yaml +8 -0
  305. data/lib/rubik/security/classifier/commands/gws.yaml +211 -0
  306. data/lib/rubik/security/classifier/commands/gzip.yaml +7 -0
  307. data/lib/rubik/security/classifier/commands/hadolint.yaml +9 -0
  308. data/lib/rubik/security/classifier/commands/halt.yaml +8 -0
  309. data/lib/rubik/security/classifier/commands/head.yaml +7 -0
  310. data/lib/rubik/security/classifier/commands/helm.yaml +129 -0
  311. data/lib/rubik/security/classifier/commands/hostname.yaml +7 -0
  312. data/lib/rubik/security/classifier/commands/id.yaml +7 -0
  313. data/lib/rubik/security/classifier/commands/install.yaml +7 -0
  314. data/lib/rubik/security/classifier/commands/isort.yaml +14 -0
  315. data/lib/rubik/security/classifier/commands/java.yaml +35 -0
  316. data/lib/rubik/security/classifier/commands/javac.yaml +39 -0
  317. data/lib/rubik/security/classifier/commands/join.yaml +7 -0
  318. data/lib/rubik/security/classifier/commands/journalctl.yaml +14 -0
  319. data/lib/rubik/security/classifier/commands/jq.yaml +7 -0
  320. data/lib/rubik/security/classifier/commands/kill.yaml +7 -0
  321. data/lib/rubik/security/classifier/commands/killall.yaml +7 -0
  322. data/lib/rubik/security/classifier/commands/kubectl.yaml +211 -0
  323. data/lib/rubik/security/classifier/commands/less.yaml +7 -0
  324. data/lib/rubik/security/classifier/commands/ln.yaml +7 -0
  325. data/lib/rubik/security/classifier/commands/ls.yaml +7 -0
  326. data/lib/rubik/security/classifier/commands/make.yaml +21 -0
  327. data/lib/rubik/security/classifier/commands/md5sum.yaml +7 -0
  328. data/lib/rubik/security/classifier/commands/mise.yaml +579 -0
  329. data/lib/rubik/security/classifier/commands/mkdir.yaml +8 -0
  330. data/lib/rubik/security/classifier/commands/more.yaml +7 -0
  331. data/lib/rubik/security/classifier/commands/mv.yaml +7 -0
  332. data/lib/rubik/security/classifier/commands/mvn.yaml +83 -0
  333. data/lib/rubik/security/classifier/commands/mvnw.yaml +83 -0
  334. data/lib/rubik/security/classifier/commands/mypy.yaml +9 -0
  335. data/lib/rubik/security/classifier/commands/netstat.yaml +7 -0
  336. data/lib/rubik/security/classifier/commands/nice.yaml +11 -0
  337. data/lib/rubik/security/classifier/commands/nl.yaml +7 -0
  338. data/lib/rubik/security/classifier/commands/node.yaml +20 -0
  339. data/lib/rubik/security/classifier/commands/nohup.yaml +9 -0
  340. data/lib/rubik/security/classifier/commands/npm.yaml +71 -0
  341. data/lib/rubik/security/classifier/commands/npx.yaml +42 -0
  342. data/lib/rubik/security/classifier/commands/nslookup.yaml +7 -0
  343. data/lib/rubik/security/classifier/commands/paste.yaml +7 -0
  344. data/lib/rubik/security/classifier/commands/ping.yaml +7 -0
  345. data/lib/rubik/security/classifier/commands/pip.yaml +33 -0
  346. data/lib/rubik/security/classifier/commands/pip3.yaml +33 -0
  347. data/lib/rubik/security/classifier/commands/pipx.yaml +33 -0
  348. data/lib/rubik/security/classifier/commands/pkill.yaml +7 -0
  349. data/lib/rubik/security/classifier/commands/pnpm.yaml +346 -0
  350. data/lib/rubik/security/classifier/commands/poetry.yaml +97 -0
  351. data/lib/rubik/security/classifier/commands/poweroff.yaml +8 -0
  352. data/lib/rubik/security/classifier/commands/prettier.yaml +13 -0
  353. data/lib/rubik/security/classifier/commands/printenv.yaml +7 -0
  354. data/lib/rubik/security/classifier/commands/printf.yaml +7 -0
  355. data/lib/rubik/security/classifier/commands/ps.yaml +7 -0
  356. data/lib/rubik/security/classifier/commands/pup.yaml +882 -0
  357. data/lib/rubik/security/classifier/commands/pwd.yaml +7 -0
  358. data/lib/rubik/security/classifier/commands/pytest.yaml +7 -0
  359. data/lib/rubik/security/classifier/commands/python.yaml +9 -0
  360. data/lib/rubik/security/classifier/commands/python3.yaml +9 -0
  361. data/lib/rubik/security/classifier/commands/read.yaml +7 -0
  362. data/lib/rubik/security/classifier/commands/readlink.yaml +7 -0
  363. data/lib/rubik/security/classifier/commands/realpath.yaml +7 -0
  364. data/lib/rubik/security/classifier/commands/reboot.yaml +8 -0
  365. data/lib/rubik/security/classifier/commands/rev.yaml +7 -0
  366. data/lib/rubik/security/classifier/commands/rg.yaml +7 -0
  367. data/lib/rubik/security/classifier/commands/rm.yaml +8 -0
  368. data/lib/rubik/security/classifier/commands/rsync.yaml +12 -0
  369. data/lib/rubik/security/classifier/commands/rtk.yaml +140 -0
  370. data/lib/rubik/security/classifier/commands/ruff.yaml +29 -0
  371. data/lib/rubik/security/classifier/commands/rustfmt.yaml +14 -0
  372. data/lib/rubik/security/classifier/commands/scp.yaml +7 -0
  373. data/lib/rubik/security/classifier/commands/sed.yaml +14 -0
  374. data/lib/rubik/security/classifier/commands/seq.yaml +7 -0
  375. data/lib/rubik/security/classifier/commands/sh.yaml +14 -0
  376. data/lib/rubik/security/classifier/commands/sha1sum.yaml +7 -0
  377. data/lib/rubik/security/classifier/commands/sha256sum.yaml +7 -0
  378. data/lib/rubik/security/classifier/commands/shellcheck.yaml +10 -0
  379. data/lib/rubik/security/classifier/commands/shutdown.yaml +8 -0
  380. data/lib/rubik/security/classifier/commands/slack.yaml +113 -0
  381. data/lib/rubik/security/classifier/commands/sleep.yaml +8 -0
  382. data/lib/rubik/security/classifier/commands/snip.yaml +79 -0
  383. data/lib/rubik/security/classifier/commands/sort.yaml +10 -0
  384. data/lib/rubik/security/classifier/commands/ss.yaml +7 -0
  385. data/lib/rubik/security/classifier/commands/ssh.yaml +41 -0
  386. data/lib/rubik/security/classifier/commands/stat.yaml +7 -0
  387. data/lib/rubik/security/classifier/commands/stdbuf.yaml +15 -0
  388. data/lib/rubik/security/classifier/commands/strace.yaml +20 -0
  389. data/lib/rubik/security/classifier/commands/strings.yaml +11 -0
  390. data/lib/rubik/security/classifier/commands/sudo.yaml +24 -0
  391. data/lib/rubik/security/classifier/commands/systemctl.yaml +58 -0
  392. data/lib/rubik/security/classifier/commands/systemd-run.yaml +30 -0
  393. data/lib/rubik/security/classifier/commands/tac.yaml +7 -0
  394. data/lib/rubik/security/classifier/commands/tail.yaml +7 -0
  395. data/lib/rubik/security/classifier/commands/tar.yaml +25 -0
  396. data/lib/rubik/security/classifier/commands/tee.yaml +8 -0
  397. data/lib/rubik/security/classifier/commands/terraform.yaml +70 -0
  398. data/lib/rubik/security/classifier/commands/test.yaml +7 -0
  399. data/lib/rubik/security/classifier/commands/time.yaml +8 -0
  400. data/lib/rubik/security/classifier/commands/timeout.yaml +18 -0
  401. data/lib/rubik/security/classifier/commands/top.yaml +7 -0
  402. data/lib/rubik/security/classifier/commands/touch.yaml +8 -0
  403. data/lib/rubik/security/classifier/commands/tr.yaml +7 -0
  404. data/lib/rubik/security/classifier/commands/traceroute.yaml +7 -0
  405. data/lib/rubik/security/classifier/commands/true.yaml +7 -0
  406. data/lib/rubik/security/classifier/commands/tsc.yaml +16 -0
  407. data/lib/rubik/security/classifier/commands/type.yaml +7 -0
  408. data/lib/rubik/security/classifier/commands/uname.yaml +7 -0
  409. data/lib/rubik/security/classifier/commands/unexpand.yaml +7 -0
  410. data/lib/rubik/security/classifier/commands/uniq.yaml +7 -0
  411. data/lib/rubik/security/classifier/commands/unzip.yaml +10 -0
  412. data/lib/rubik/security/classifier/commands/uptime.yaml +7 -0
  413. data/lib/rubik/security/classifier/commands/uv.yaml +156 -0
  414. data/lib/rubik/security/classifier/commands/wait.yaml +11 -0
  415. data/lib/rubik/security/classifier/commands/wc.yaml +7 -0
  416. data/lib/rubik/security/classifier/commands/wget.yaml +7 -0
  417. data/lib/rubik/security/classifier/commands/whereis.yaml +7 -0
  418. data/lib/rubik/security/classifier/commands/which.yaml +7 -0
  419. data/lib/rubik/security/classifier/commands/whoami.yaml +7 -0
  420. data/lib/rubik/security/classifier/commands/xargs.yaml +26 -0
  421. data/lib/rubik/security/classifier/commands/xmllint.yaml +7 -0
  422. data/lib/rubik/security/classifier/commands/yarn.yaml +72 -0
  423. data/lib/rubik/security/classifier/commands/yes.yaml +7 -0
  424. data/lib/rubik/security/classifier/commands/yq.yaml +10 -0
  425. data/lib/rubik/security/classifier/commands/zip.yaml +8 -0
  426. data/lib/rubik/security/classifier/commands/zsh.yaml +14 -0
  427. data/lib/rubik/security/classifier/database.rb +216 -0
  428. data/lib/rubik/security/classifier/matcher/delegation.rb +190 -0
  429. data/lib/rubik/security/classifier/matcher/options.rb +245 -0
  430. data/lib/rubik/security/classifier/matcher/subcommands.rb +103 -0
  431. data/lib/rubik/security/classifier/matcher.rb +249 -0
  432. data/lib/rubik/security/classifier/models.rb +170 -0
  433. data/lib/rubik/security/classifier/parser.rb +23 -0
  434. data/lib/rubik/security/classifier/parsers/bash.rb +280 -0
  435. data/lib/rubik/security/classifier/parsers/bash_extractors.rb +221 -0
  436. data/lib/rubik/security/classifier/parsers/powershell.rb +185 -0
  437. data/lib/rubik/security/classifier/pwsh_rules.rb +224 -0
  438. data/lib/rubik/security/classifier.rb +25 -0
  439. data/lib/rubik/security/errors.rb +39 -0
  440. data/lib/rubik/security/guard.rb +954 -0
  441. data/lib/rubik/security/redactor.rb +89 -0
  442. data/lib/rubik/security.rb +11 -0
  443. data/lib/rubik/session/manager.rb +331 -0
  444. data/lib/rubik/session/recorder.rb +149 -0
  445. data/lib/rubik/session/replayer.rb +65 -0
  446. data/lib/rubik/session.rb +10 -0
  447. data/lib/rubik/skills/frontmatter.rb +41 -0
  448. data/lib/rubik/skills/manager.rb +223 -0
  449. data/lib/rubik/skills/registry.rb +64 -0
  450. data/lib/rubik/skills/skill.rb +33 -0
  451. data/lib/rubik/skills/storage.rb +77 -0
  452. data/lib/rubik/skills/validator.rb +116 -0
  453. data/lib/rubik/skills.rb +20 -0
  454. data/lib/rubik/storage/folding.rb +23 -0
  455. data/lib/rubik/storage/layout.rb +145 -0
  456. data/lib/rubik/storage/render.rb +97 -0
  457. data/lib/rubik/storage/service.rb +42 -0
  458. data/lib/rubik/storage/store.rb +514 -0
  459. data/lib/rubik/storage/transcript_indexer.rb +116 -0
  460. data/lib/rubik/storage/uri_reader.rb +168 -0
  461. data/lib/rubik/storage/vakanuvis/annal_writer.rb +92 -0
  462. data/lib/rubik/storage/vakanuvis/distill_gate.rb +323 -0
  463. data/lib/rubik/storage/vakanuvis/gate.rb +250 -0
  464. data/lib/rubik/storage/vakanuvis/harness.rb +421 -0
  465. data/lib/rubik/storage/vakanuvis/memory_steward.rb +163 -0
  466. data/lib/rubik/storage/vakanuvis/service.rb +69 -0
  467. data/lib/rubik/storage/vakanuvis/vocabulary.rb +99 -0
  468. data/lib/rubik/storage/vakanuvis/wiki_skeleton.rb +67 -0
  469. data/lib/rubik/storage/vakanuvis.rb +77 -0
  470. data/lib/rubik/storage.rb +29 -0
  471. data/lib/rubik/tools/base.rb +107 -0
  472. data/lib/rubik/tools/builtins/dmesg.rb +74 -0
  473. data/lib/rubik/tools/builtins/exec.rb +293 -0
  474. data/lib/rubik/tools/builtins/files.rb +354 -0
  475. data/lib/rubik/tools/builtins/goal_ledger.rb +89 -0
  476. data/lib/rubik/tools/builtins/grep.rb +281 -0
  477. data/lib/rubik/tools/builtins/interactive.rb +175 -0
  478. data/lib/rubik/tools/builtins/lifecycle.rb +359 -0
  479. data/lib/rubik/tools/builtins/lsp.rb +283 -0
  480. data/lib/rubik/tools/builtins/pruner.rb +88 -0
  481. data/lib/rubik/tools/builtins/runtime.rb +120 -0
  482. data/lib/rubik/tools/builtins/send_message.rb +109 -0
  483. data/lib/rubik/tools/builtins/show_file.rb +84 -0
  484. data/lib/rubik/tools/builtins/skill.rb +72 -0
  485. data/lib/rubik/tools/builtins/storage.rb +232 -0
  486. data/lib/rubik/tools/builtins/subagent.rb +356 -0
  487. data/lib/rubik/tools/builtins/subagent_lifecycle.rb +72 -0
  488. data/lib/rubik/tools/builtins/symbols.rb +209 -0
  489. data/lib/rubik/tools/builtins/synthesis.rb +314 -0
  490. data/lib/rubik/tools/builtins/task.rb +168 -0
  491. data/lib/rubik/tools/builtins/unsynthesize.rb +111 -0
  492. data/lib/rubik/tools/builtins/vakanuvis.rb +161 -0
  493. data/lib/rubik/tools/builtins.rb +30 -0
  494. data/lib/rubik/tools/catalog.rb +70 -0
  495. data/lib/rubik/tools/declaration.rb +90 -0
  496. data/lib/rubik/tools/diagnostic_reporter.rb +283 -0
  497. data/lib/rubik/tools/fuzzy_matcher.rb +172 -0
  498. data/lib/rubik/tools/native_search.rb +180 -0
  499. data/lib/rubik/tools/output.rb +54 -0
  500. data/lib/rubik/tools/preflight_runner.rb +209 -0
  501. data/lib/rubik/tools/registry.rb +247 -0
  502. data/lib/rubik/tools/result.rb +71 -0
  503. data/lib/rubik/tools/services.rb +96 -0
  504. data/lib/rubik/tools/truncator.rb +78 -0
  505. data/lib/rubik/tools/uri_resolver.rb +195 -0
  506. data/lib/rubik/tools.rb +14 -0
  507. data/lib/rubik/ui/approvals.rb +52 -0
  508. data/lib/rubik/ui/banner.rb +43 -0
  509. data/lib/rubik/ui/capability.rb +122 -0
  510. data/lib/rubik/ui/dialog.rb +106 -0
  511. data/lib/rubik/ui/diff_viewer.rb +78 -0
  512. data/lib/rubik/ui/frame.rb +95 -0
  513. data/lib/rubik/ui/markdown_stream.rb +107 -0
  514. data/lib/rubik/ui/panel.rb +98 -0
  515. data/lib/rubik/ui/renderer.rb +206 -0
  516. data/lib/rubik/ui/spinner.rb +120 -0
  517. data/lib/rubik/ui/statusline.rb +134 -0
  518. data/lib/rubik/ui/theme.rb +118 -0
  519. data/lib/rubik/ui.rb +57 -0
  520. data/lib/rubik/uris.rb +101 -0
  521. data/lib/rubik/version.rb +5 -0
  522. data/lib/rubik.rb +65 -0
  523. metadata +770 -0
@@ -0,0 +1,170 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Rubik
4
+ module Security
5
+ module Classifier
6
+ module Classification
7
+ READONLY = :readonly
8
+ LOCAL_EFFECTS = :local_effects
9
+ EXTERNAL_EFFECTS = :external_effects
10
+ UNKNOWN = :unknown
11
+ DANGEROUS = :dangerous
12
+
13
+ SEVERITY_ORDER = {
14
+ READONLY => 0,
15
+ LOCAL_EFFECTS => 1,
16
+ EXTERNAL_EFFECTS => 2,
17
+ UNKNOWN => 3,
18
+ DANGEROUS => 4
19
+ }.freeze
20
+
21
+ def self.severity(classification)
22
+ SEVERITY_ORDER.fetch(normalize(classification), 3)
23
+ end
24
+
25
+ def self.max_severity(*classifications)
26
+ list = classifications.flatten.compact
27
+ return READONLY if list.empty?
28
+
29
+ list.max_by { |c| severity(c) }
30
+ end
31
+
32
+ def self.normalize(val)
33
+ return nil if val.nil?
34
+
35
+ val.to_s.downcase.to_sym
36
+ end
37
+ end
38
+
39
+ module Risk
40
+ LOW = :low
41
+ MEDIUM = :medium
42
+ HIGH = :high
43
+
44
+ SEVERITY_ORDER = { LOW => 0, MEDIUM => 1, HIGH => 2 }.freeze
45
+
46
+ def self.severity(risk)
47
+ SEVERITY_ORDER.fetch(normalize(risk), 2)
48
+ end
49
+
50
+ def self.max_severity(*risks)
51
+ list = risks.flatten.compact
52
+ return LOW if list.empty?
53
+
54
+ list.max_by { |r| severity(r) }
55
+ end
56
+
57
+ def self.normalize(val)
58
+ return nil if val.nil?
59
+
60
+ val.to_s.downcase.to_sym
61
+ end
62
+ end
63
+
64
+ module DelegationMode
65
+ REST_ARE_ARGV = :rest_are_argv
66
+ AFTER_SEPARATOR = :after_separator
67
+ TERMINATED_ARGV = :terminated_argv
68
+ FLAG_VALUE_IS_EXPRESSION = :flag_value_is_expression
69
+ ARGS_ARE_EXPRESSION = :args_are_expression
70
+ end
71
+
72
+ module SubcommandMode
73
+ HIERARCHICAL = :hierarchical
74
+ MATCH_ALL = :match_all
75
+ end
76
+
77
+ Redirect = Data.define(:operator, :target, :affects_classification) do
78
+ def initialize(operator:, target:, affects_classification: false)
79
+ super
80
+ end
81
+ end
82
+
83
+ CommandInvocation = Data.define(
84
+ :argv, :redirects, :position_in_pipeline, :pipeline_length,
85
+ :context, :operator_before, :is_background, :assignments
86
+ ) do
87
+ def initialize(argv:, redirects: [], position_in_pipeline: 0, pipeline_length: 1,
88
+ context: "toplevel", operator_before: nil, is_background: false,
89
+ assignments: [])
90
+ super
91
+ end
92
+ end
93
+
94
+ DelegationConfig = Data.define(
95
+ :mode, :separator, :terminator, :flag,
96
+ :strip_assignments, :skip_leading_positionals, :min_classification
97
+ ) do
98
+ def initialize(mode:, separator: nil, terminator: nil, flag: nil,
99
+ strip_assignments: false, skip_leading_positionals: 0, min_classification: nil)
100
+ super
101
+ end
102
+ end
103
+
104
+ OptionDef = Data.define(
105
+ :takes_value, :aliases, :overrides, :risk,
106
+ :captures_directory, :delegates_to
107
+ ) do
108
+ def initialize(takes_value: false, aliases: [], overrides: nil, risk: nil,
109
+ captures_directory: false, delegates_to: nil)
110
+ super
111
+ end
112
+ end
113
+
114
+ CommandDef = Data.define(
115
+ :command, :description, :alias_of, :aliases, :classification, :risk,
116
+ :global_options, :subcommands, :options, :strict,
117
+ :subcommand_mode, :delegates_to
118
+ ) do
119
+ def initialize(command:, description: nil, alias_of: nil, aliases: [], classification: nil, risk: nil,
120
+ global_options: {}, subcommands: {}, options: {}, strict: true,
121
+ subcommand_mode: :hierarchical, delegates_to: nil)
122
+ super
123
+ end
124
+ end
125
+
126
+ InnerCommandResult = Data.define(
127
+ :delegation_mode, :delegation_source, :command, :argv,
128
+ :classification, :risk, :matched_rule, :inner_commands,
129
+ :ignored_options, :remaining_options, :classification_reason,
130
+ :overriding_option, :options, :positionals, :redirects
131
+ ) do
132
+ # redirects: transport only — the Engine applies all redirect
133
+ # semantics (Engine#apply_inner_redirects); the Matcher never
134
+ # interprets this field.
135
+ def initialize(delegation_mode:, delegation_source:, command:, argv:,
136
+ classification:, risk:, matched_rule: nil, inner_commands: [],
137
+ ignored_options: nil, remaining_options: nil, classification_reason: nil,
138
+ overriding_option: nil, options: nil, positionals: nil, redirects: [])
139
+ super
140
+ end
141
+ end
142
+
143
+ CommandResult = Data.define(
144
+ :command, :argv, :classification, :risk, :matched_rule,
145
+ :inner_commands, :ignored_options, :remaining_options,
146
+ :classification_reason, :overriding_option, :directories,
147
+ :write_paths, :read_paths, :options, :positionals
148
+ ) do
149
+ def initialize(command:, argv:, classification:, risk:, matched_rule: nil,
150
+ inner_commands: [], ignored_options: nil, remaining_options: nil,
151
+ classification_reason: nil, overriding_option: nil, directories: nil,
152
+ write_paths: nil, read_paths: nil, options: nil, positionals: nil)
153
+ super
154
+ end
155
+ end
156
+
157
+ ExpressionResult = Data.define(
158
+ :expression, :classification, :risk, :directories,
159
+ :write_paths, :read_paths, :commands, :redirects, :parse_warnings,
160
+ :classification_reason
161
+ ) do
162
+ def initialize(expression:, classification:, risk:, directories: [],
163
+ write_paths: [], read_paths: [], commands: [],
164
+ redirects: [], parse_warnings: [], classification_reason: nil)
165
+ super
166
+ end
167
+ end
168
+ end
169
+ end
170
+ end
@@ -0,0 +1,23 @@
1
+ # frozen_string_literal: true
2
+
3
+ require_relative "parsers/bash"
4
+ require_relative "parsers/powershell"
5
+ require_relative "../../platform"
6
+
7
+ module Rubik
8
+ module Security
9
+ module Classifier
10
+ module Parser
11
+ def self.parse(expression, shell: nil)
12
+ is_pwsh = shell.to_s.downcase == "powershell" || shell == :pwsh || shell == :powershell
13
+
14
+ if is_pwsh
15
+ Parsers::PowerShell.parse(expression)
16
+ else
17
+ Parsers::Bash.parse(expression)
18
+ end
19
+ end
20
+ end
21
+ end
22
+ end
23
+ end
@@ -0,0 +1,280 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "tree_sitter_language_pack"
4
+ require_relative "../models"
5
+ require_relative "bash_extractors"
6
+
7
+ module Rubik
8
+ module Security
9
+ module Classifier
10
+ module Parsers
11
+ class Bash
12
+ HEREDOC_STRUCTURE_NODES = ["<<", "<<-", "heredoc_start", "heredoc_body", "heredoc_end"].freeze
13
+ LIST_OPERATORS = ["&&", "||"].freeze
14
+
15
+ def self.parser
16
+ Thread.current[:rubik_ts_bash_parser] ||= TreeSitterLanguagePack.get_parser("bash")
17
+ end
18
+
19
+ def self.parse(expression)
20
+ new.parse(expression)
21
+ end
22
+
23
+ def parse(expression)
24
+ tree = self.class.parser.parse(expression)
25
+ warnings = []
26
+ warnings << "tree-sitter reported a syntax error in expression: #{expression.inspect}" if tree.root_node.has_error
27
+
28
+ invocations = walk_node(tree.root_node, expression, context: "toplevel", operator_before: nil)
29
+ [invocations, warnings]
30
+ end
31
+
32
+ private
33
+
34
+ def walk_node(node, expression, context:, operator_before:, pipeline_position: 0, pipeline_length: 1)
35
+ results = []
36
+ case node.kind
37
+ when "program"
38
+ results.concat(walk_children_as_list(node, expression, context: context))
39
+ when "list"
40
+ results.concat(walk_list_node(node, expression, context: context, operator_before: operator_before))
41
+ when "pipeline"
42
+ results.concat(walk_pipeline_node(node, expression, context: context, operator_before: operator_before))
43
+ when "command"
44
+ inv = BashExtractors.extract_command(
45
+ node, expression, context: context, operator_before: operator_before,
46
+ pipeline_position: pipeline_position, pipeline_length: pipeline_length
47
+ )
48
+ results << inv if inv
49
+ results.concat(extract_nested_from_command_args(node, expression))
50
+ when "redirected_statement"
51
+ results.concat(walk_redirected_statement(
52
+ node, expression, context: context, operator_before: operator_before,
53
+ pipeline_position: pipeline_position, pipeline_length: pipeline_length
54
+ ))
55
+ when "subshell"
56
+ results.concat(walk_subshell(node, expression, context: "subshell", operator_before: operator_before))
57
+ when "command_substitution"
58
+ results.concat(walk_compound_inner(node, expression, context: "command_substitution"))
59
+ when "process_substitution"
60
+ results.concat(walk_compound_inner(node, expression, context: "process_substitution"))
61
+ when "test_command"
62
+ inv = BashExtractors.extract_test_command(
63
+ node, expression, context: context, operator_before: operator_before,
64
+ pipeline_position: pipeline_position, pipeline_length: pipeline_length
65
+ )
66
+ results << inv if inv
67
+ when "negated_command"
68
+ BashExtractors.node_children(node).each do |child|
69
+ next if child.kind == "!"
70
+
71
+ results.concat(walk_node(
72
+ child, expression, context: context, operator_before: operator_before,
73
+ pipeline_position: pipeline_position, pipeline_length: pipeline_length
74
+ ))
75
+ end
76
+ else
77
+ BashExtractors.node_children(node).each do |child|
78
+ results.concat(walk_node(
79
+ child, expression, context: context, operator_before: operator_before,
80
+ pipeline_position: pipeline_position, pipeline_length: pipeline_length
81
+ ))
82
+ end
83
+ end
84
+ results
85
+ end
86
+
87
+ def walk_children_as_list(node, expression, context:)
88
+ results = []
89
+ operator_before = nil
90
+ BashExtractors.node_children(node).each do |child|
91
+ if ["\n", ";", "&", ";;"].include?(child.kind)
92
+ if child.kind == ";"
93
+ operator_before = ";"
94
+ elsif child.kind == "&"
95
+ mark_last_background(results)
96
+ operator_before = nil
97
+ end
98
+ next
99
+ end
100
+ results.concat(walk_node(child, expression, context: context, operator_before: operator_before))
101
+ operator_before = nil
102
+ end
103
+ results
104
+ end
105
+
106
+ def walk_list_node(node, expression, context:, operator_before:)
107
+ results = []
108
+ curr_op = operator_before
109
+ BashExtractors.node_children(node).each do |child|
110
+ if ["&&", "||", ";"].include?(child.kind)
111
+ curr_op = child.kind
112
+ next
113
+ elsif child.kind == "&"
114
+ mark_last_background(results)
115
+ curr_op = nil
116
+ next
117
+ elsif child.kind == "\n"
118
+ next
119
+ end
120
+ results.concat(walk_node(child, expression, context: context, operator_before: curr_op))
121
+ curr_op = nil
122
+ end
123
+ results
124
+ end
125
+
126
+ def walk_pipeline_node(node, expression, context:, operator_before:)
127
+ members = flatten_pipeline_members(node)
128
+ results = []
129
+ members.each_with_index do |cmd_node, i|
130
+ op = (i.zero? ? operator_before : nil)
131
+ results.concat(walk_node(
132
+ cmd_node, expression, context: context, operator_before: op,
133
+ pipeline_position: i, pipeline_length: members.size
134
+ ))
135
+ end
136
+ results
137
+ end
138
+
139
+ def walk_redirected_statement(node, expression, context:, operator_before:, pipeline_position:, pipeline_length:)
140
+ redirects = BashExtractors.extract_redirects_from_node(node, expression)
141
+ body_node = BashExtractors.node_children(node).find do |child|
142
+ !["file_redirect", "heredoc_redirect", "herestring_redirect"].include?(child.kind)
143
+ end
144
+ return [] unless body_node
145
+
146
+ followers = heredoc_follower_segments(node)
147
+ followers_pipe_len = followers.sum do |op, child|
148
+ continues_pipeline?(op, child) ? flatten_pipeline_members(child).size : 0
149
+ end
150
+ pipe_len = pipeline_length + followers_pipe_len
151
+
152
+ inner = walk_node(
153
+ body_node, expression, context: context, operator_before: operator_before,
154
+ pipeline_position: pipeline_position, pipeline_length: pipe_len
155
+ )
156
+
157
+ results = []
158
+ redirects_attached = false
159
+ inner.each do |inv|
160
+ if !redirects_attached && inv.position_in_pipeline == pipeline_position
161
+ inv = inv.with(redirects: (inv.redirects + redirects))
162
+ redirects_attached = true
163
+ end
164
+ results << inv
165
+ end
166
+
167
+ results.concat(walk_heredoc_followers(
168
+ followers, expression, context: context,
169
+ pipeline_position: pipeline_position, pipeline_length: pipe_len
170
+ ))
171
+ results
172
+ end
173
+
174
+ def walk_subshell(node, expression, context:, operator_before:)
175
+ results = []
176
+ BashExtractors.node_children(node).each do |child|
177
+ next if ["(", ")"].include?(child.kind)
178
+
179
+ results.concat(walk_node(child, expression, context: context, operator_before: operator_before))
180
+ operator_before = nil
181
+ end
182
+ results
183
+ end
184
+
185
+ def walk_compound_inner(node, expression, context:)
186
+ results = []
187
+ BashExtractors.node_children(node).each do |child|
188
+ next if ["$(", ")", "<(", ">(", "`"].include?(child.kind)
189
+
190
+ results.concat(walk_node(child, expression, context: context, operator_before: nil))
191
+ end
192
+ results
193
+ end
194
+
195
+ def extract_nested_from_command_args(node, expression)
196
+ results = []
197
+ BashExtractors.node_children(node).each do |child|
198
+ if child.kind == "command_name"
199
+ BashExtractors.node_children(child).each do |sub|
200
+ results.concat(BashExtractors.find_nested_substitutions(sub, expression) do |inner_node, ctx|
201
+ walk_compound_inner(inner_node, expression, context: ctx)
202
+ end)
203
+ end
204
+ elsif ["file_redirect", "heredoc_redirect", "herestring_redirect", "variable_assignment"].include?(child.kind)
205
+ next
206
+ else
207
+ results.concat(BashExtractors.find_nested_substitutions(child, expression) do |inner_node, ctx|
208
+ walk_compound_inner(inner_node, expression, context: ctx)
209
+ end)
210
+ end
211
+ end
212
+ results
213
+ end
214
+
215
+ def flatten_pipeline_members(node)
216
+ members = []
217
+ BashExtractors.node_children(node).each do |child|
218
+ next if ["|", "|&"].include?(child.kind)
219
+
220
+ if child.kind == "pipeline"
221
+ members.concat(flatten_pipeline_members(child))
222
+ else
223
+ members << child
224
+ end
225
+ end
226
+ members
227
+ end
228
+
229
+ def heredoc_follower_segments(node)
230
+ segments = []
231
+ heredocs = BashExtractors.node_children(node).select { |c| c.kind == "heredoc_redirect" }
232
+ heredocs.each do |redirect|
233
+ pending_op = nil
234
+ BashExtractors.node_children(redirect).each do |child|
235
+ next if HEREDOC_STRUCTURE_NODES.include?(child.kind)
236
+
237
+ if LIST_OPERATORS.include?(child.kind)
238
+ pending_op = child.kind
239
+ next
240
+ end
241
+ segments << [pending_op, child]
242
+ pending_op = nil
243
+ end
244
+ end
245
+ segments
246
+ end
247
+
248
+ def continues_pipeline?(operator, child)
249
+ operator.nil? && child.kind == "pipeline"
250
+ end
251
+
252
+ def walk_heredoc_followers(segments, expression, context:, pipeline_position:, pipeline_length:)
253
+ results = []
254
+ pos = pipeline_position
255
+ segments.each do |op, child|
256
+ if continues_pipeline?(op, child)
257
+ flatten_pipeline_members(child).each do |member|
258
+ pos += 1
259
+ results.concat(walk_node(
260
+ member, expression, context: context, operator_before: nil,
261
+ pipeline_position: pos, pipeline_length: pipeline_length
262
+ ))
263
+ end
264
+ else
265
+ results.concat(walk_node(child, expression, context: context, operator_before: op))
266
+ end
267
+ end
268
+ results
269
+ end
270
+
271
+ def mark_last_background(results)
272
+ return if results.empty?
273
+
274
+ results[-1] = results.last.with(is_background: true)
275
+ end
276
+ end
277
+ end
278
+ end
279
+ end
280
+ end
@@ -0,0 +1,221 @@
1
+ # frozen_string_literal: true
2
+
3
+ require_relative "../models"
4
+
5
+ module Rubik
6
+ module Security
7
+ module Classifier
8
+ module Parsers
9
+ module BashExtractors
10
+ OPERATORS = [">", ">>", "<", ">&", "&>", "&>>", "<&", "<<", "<<<"].freeze
11
+
12
+ def self.node_children(node)
13
+ (0...node.child_count).map { |i| node.child(i) }
14
+ end
15
+
16
+ def self.node_raw_text(node, expression)
17
+ return "" if node.nil?
18
+
19
+ expression.byteslice(node.start_byte...node.end_byte) || ""
20
+ end
21
+
22
+ def self.node_text(node, expression)
23
+ raw = node_raw_text(node, expression)
24
+ case node.kind
25
+ when "string"
26
+ raw.length >= 2 && raw.start_with?('"') && raw.end_with?('"') ? raw[1..-2] : raw
27
+ when "raw_string", "ansi_c_string"
28
+ if raw.length >= 3 && raw.start_with?("$'") && raw.end_with?("'")
29
+ raw[2..-2]
30
+ elsif raw.length >= 2 && raw.start_with?("'") && raw.end_with?("'")
31
+ raw[1..-2]
32
+ else
33
+ raw
34
+ end
35
+ when "concatenation"
36
+ node_children(node).map { |c| node_text(c, expression) }.join
37
+ else
38
+ raw
39
+ end
40
+ end
41
+
42
+ def self.redirect_affects_classification(operator, target)
43
+ return false if target == File::NULL
44
+ return false if operator.include?(">&") && target =~ /\A\d+\z/
45
+
46
+ return true if [">", ">>", "&>", "&>>"].include?(operator) || (operator.end_with?(">") && !operator.include?("<"))
47
+
48
+ operator.length >= 2 && operator[0] =~ /\d/ && operator.include?(">")
49
+ end
50
+
51
+ def self.extract_redirects_from_node(node, expression)
52
+ redirects = []
53
+ node_children(node).each do |child|
54
+ case child.kind
55
+ when "file_redirect"
56
+ red = parse_file_redirect(child, expression)
57
+ redirects << red if red
58
+ when "heredoc_redirect"
59
+ red = parse_heredoc_redirect(child, expression)
60
+ redirects << red if red
61
+ when "herestring_redirect"
62
+ red = parse_herestring_redirect(child, expression)
63
+ redirects << red if red
64
+ end
65
+ end
66
+ redirects
67
+ end
68
+
69
+ def self.parse_file_redirect(node, expression)
70
+ operator_parts = []
71
+ target = ""
72
+
73
+ node_children(node).each do |child|
74
+ if child.kind == "file_descriptor" || OPERATORS.include?(child.kind)
75
+ operator_parts << node_raw_text(child, expression)
76
+ elsif child.is_named
77
+ target = node_text(child, expression)
78
+ else
79
+ text = node_raw_text(child, expression)
80
+ if OPERATORS.include?(text)
81
+ operator_parts << text
82
+ elsif target.empty?
83
+ target = text
84
+ end
85
+ end
86
+ end
87
+
88
+ operator = operator_parts.join
89
+ if operator.empty?
90
+ full = node_raw_text(node, expression)
91
+ operator = full.split.first || full if full.include?(">") || full.include?("<")
92
+ end
93
+
94
+ affects = redirect_affects_classification(operator, target)
95
+ Redirect.new(operator: operator, target: target, affects_classification: affects)
96
+ end
97
+
98
+ def self.parse_heredoc_redirect(node, expression)
99
+ operator = "<<"
100
+ target = ""
101
+
102
+ node_children(node).each do |child|
103
+ if ["<<", "<<-"].include?(child.kind)
104
+ operator = node_raw_text(child, expression)
105
+ elsif child.kind == "heredoc_start"
106
+ target = node_raw_text(child, expression)
107
+ end
108
+ end
109
+
110
+ Redirect.new(operator: operator, target: target, affects_classification: false)
111
+ end
112
+
113
+ def self.parse_herestring_redirect(node, expression)
114
+ target = ""
115
+ node_children(node).each do |child|
116
+ next if child.kind == "<<<"
117
+
118
+ if child.is_named
119
+ target = node_text(child, expression)
120
+ else
121
+ t = node_raw_text(child, expression)
122
+ target = t if t != "<<<" && target.empty?
123
+ end
124
+ end
125
+
126
+ Redirect.new(operator: "<<<", target: target, affects_classification: false)
127
+ end
128
+
129
+ def self.extract_command(node, expression, context:, operator_before:, pipeline_position:, pipeline_length:)
130
+ argv = []
131
+ assignments = []
132
+ has_command_name = false
133
+
134
+ node_children(node).each do |child|
135
+ case child.kind
136
+ when "variable_assignment"
137
+ if has_command_name
138
+ argv << node_text(child, expression)
139
+ else
140
+ # Pre-command assignment (VAR="value cmd"): kept OUT of
141
+ # argv (allowlist semantics key on the real command) but
142
+ # captured — the Engine classifies command-shaped VALUES
143
+ # as sibling invocations (GIT_SSH_COMMAND payloads).
144
+ assignments << node_raw_text(child, expression)
145
+ end
146
+ when "command_name"
147
+ has_command_name = true
148
+ argv << node_text(child, expression)
149
+ when "file_redirect", "heredoc_redirect", "herestring_redirect", "comment"
150
+ next
151
+ else
152
+ argv << node_text(child, expression)
153
+ end
154
+ end
155
+
156
+ return nil if argv.empty?
157
+
158
+ redirects = extract_redirects_from_node(node, expression)
159
+ CommandInvocation.new(
160
+ argv: argv,
161
+ redirects: redirects,
162
+ position_in_pipeline: pipeline_position,
163
+ pipeline_length: pipeline_length,
164
+ context: context,
165
+ operator_before: operator_before,
166
+ is_background: false,
167
+ assignments: assignments
168
+ )
169
+ end
170
+
171
+ def self.extract_test_command(node, expression, context:, operator_before:, pipeline_position:, pipeline_length:)
172
+ argv = extract_test_tokens(node, expression)
173
+ return nil if argv.empty?
174
+
175
+ CommandInvocation.new(
176
+ argv: argv,
177
+ redirects: [],
178
+ position_in_pipeline: pipeline_position,
179
+ pipeline_length: pipeline_length,
180
+ context: context,
181
+ operator_before: operator_before,
182
+ is_background: false
183
+ )
184
+ end
185
+
186
+ def self.extract_test_tokens(node, expression)
187
+ tokens = []
188
+ node_children(node).each do |child|
189
+ if ["[", "[["].include?(child.kind)
190
+ tokens << node_raw_text(child, expression)
191
+ elsif ["]", "]]"].include?(child.kind)
192
+ next
193
+ elsif child.child_count.positive?
194
+ tokens.concat(extract_test_tokens(child, expression))
195
+ else
196
+ t = node_text(child, expression).strip
197
+ tokens << t unless t.empty?
198
+ end
199
+ end
200
+ tokens
201
+ end
202
+
203
+ def self.find_nested_substitutions(node, expression, &walker)
204
+ results = []
205
+ case node.kind
206
+ when "command_substitution"
207
+ results.concat(walker.call(node, "command_substitution"))
208
+ when "process_substitution"
209
+ results.concat(walker.call(node, "process_substitution"))
210
+ else
211
+ node_children(node).each do |child|
212
+ results.concat(find_nested_substitutions(child, expression, &walker))
213
+ end
214
+ end
215
+ results
216
+ end
217
+ end
218
+ end
219
+ end
220
+ end
221
+ end