argus-testing 0.12.0__tar.gz → 0.12.2__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (198) hide show
  1. {argus_testing-0.12.0 → argus_testing-0.12.2}/.gitignore +1 -0
  2. {argus_testing-0.12.0 → argus_testing-0.12.2}/AGENTS.md +2 -3
  3. {argus_testing-0.12.0 → argus_testing-0.12.2}/CHANGELOG.md +49 -0
  4. {argus_testing-0.12.0 → argus_testing-0.12.2}/CONTRIBUTING.md +7 -7
  5. argus_testing-0.12.2/PKG-INFO +181 -0
  6. {argus_testing-0.12.0 → argus_testing-0.12.2}/PRIVACY.md +29 -1
  7. argus_testing-0.12.2/README.md +137 -0
  8. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/evidence.py +21 -9
  9. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/exports.py +73 -9
  10. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/findings.py +10 -2
  11. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/regression.py +18 -3
  12. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/testgen.py +272 -128
  13. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/verification.py +35 -6
  14. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/verifiers.py +3 -0
  15. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/browser.py +5 -2
  16. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/cli.py +2 -0
  17. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/models.py +2 -0
  18. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/verification.py +23 -2
  19. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/catalog.py +1 -1
  20. {argus_testing-0.12.0 → argus_testing-0.12.2}/docs/agent-protocol.md +40 -7
  21. {argus_testing-0.12.0 → argus_testing-0.12.2}/docs/evaluation.md +1 -1
  22. argus_testing-0.12.0/README.md → argus_testing-0.12.2/docs/usage.md +63 -271
  23. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/response-overhead.json +10 -10
  24. {argus_testing-0.12.0 → argus_testing-0.12.2}/llms-install.md +3 -3
  25. {argus_testing-0.12.0 → argus_testing-0.12.2}/pyproject.toml +2 -2
  26. {argus_testing-0.12.0 → argus_testing-0.12.2}/scripts/check_distributions.py +1 -1
  27. {argus_testing-0.12.0 → argus_testing-0.12.2}/server.json +3 -3
  28. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_distribution_contents.py +6 -4
  29. argus_testing-0.12.2/tests/test_export_guards.py +354 -0
  30. argus_testing-0.12.2/tests/test_export_privacy.py +320 -0
  31. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_export_test.py +81 -33
  32. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_real_app_interactions.py +8 -1
  33. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_regression_cli.py +8 -1
  34. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_release_metadata.py +17 -35
  35. argus_testing-0.12.2/tests/test_verification_contract.py +398 -0
  36. argus_testing-0.12.0/PKG-INFO +0 -764
  37. argus_testing-0.12.0/README.zh-CN.md +0 -334
  38. argus_testing-0.12.0/tests/test_export_guards.py +0 -169
  39. {argus_testing-0.12.0 → argus_testing-0.12.2}/LICENSE +0 -0
  40. {argus_testing-0.12.0 → argus_testing-0.12.2}/SECURITY.md +0 -0
  41. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/__init__.py +0 -0
  42. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/_compat.py +0 -0
  43. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/access.py +0 -0
  44. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/__init__.py +0 -0
  45. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/assets/__init__.py +0 -0
  46. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/assets/dashboard.css +0 -0
  47. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/assets/dashboard.html +0 -0
  48. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/assets/dashboard.js +0 -0
  49. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/journal.py +0 -0
  50. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/logging.py +0 -0
  51. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/monitoring.py +0 -0
  52. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/__init__.py +0 -0
  53. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/common.py +0 -0
  54. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/html.py +0 -0
  55. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/json.py +0 -0
  56. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/junit.py +0 -0
  57. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/privacy.py +0 -0
  58. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/reporter.py +0 -0
  59. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/reporting/sarif.py +0 -0
  60. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/__init__.py +0 -0
  61. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/check_layout_js.js +0 -0
  62. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/extract_elements_js.js +0 -0
  63. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/extract_page_content_js.js +0 -0
  64. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/extract_performance_js.js +0 -0
  65. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/find_visible_element_js.js +0 -0
  66. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/adapters/scripts/inspect_element_js.js +0 -0
  67. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/__init__.py +0 -0
  68. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/actions.py +0 -0
  69. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/capsules.py +0 -0
  70. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/capture.py +0 -0
  71. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/context.py +0 -0
  72. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/coverage.py +0 -0
  73. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/events.py +0 -0
  74. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/expectations.py +0 -0
  75. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/finish.py +0 -0
  76. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/guidance.py +0 -0
  77. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/inspection.py +0 -0
  78. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/journeys.py +0 -0
  79. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/lifecycle.py +0 -0
  80. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/manager.py +0 -0
  81. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/navigation.py +0 -0
  82. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/network_storage.py +0 -0
  83. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/observation.py +0 -0
  84. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/operations.py +0 -0
  85. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/payloads.py +0 -0
  86. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/probes.py +0 -0
  87. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/progress.py +0 -0
  88. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/screen.py +0 -0
  89. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/screenshots.py +0 -0
  90. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/session.py +0 -0
  91. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/telemetry.py +0 -0
  92. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/application/text.py +0 -0
  93. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/bootstrap.py +0 -0
  94. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/cleanup.py +0 -0
  95. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/detector.py +0 -0
  96. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/differ.py +0 -0
  97. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/doctor.py +0 -0
  98. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/__init__.py +0 -0
  99. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/contracts.py +0 -0
  100. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/coverage.py +0 -0
  101. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/detector.py +0 -0
  102. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/findings.py +0 -0
  103. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/domain/replay.py +0 -0
  104. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/__init__.py +0 -0
  105. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/__init__.py +0 -0
  106. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/compat.py +0 -0
  107. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/overhead.py +0 -0
  108. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/results.py +0 -0
  109. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/server.py +0 -0
  110. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/entrypoints/mcp/snapshots.py +0 -0
  111. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/install_check.py +0 -0
  112. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/mcp_server.py +0 -0
  113. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/measurement.py +0 -0
  114. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/models.py +0 -0
  115. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/ports.py +0 -0
  116. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/reporter.py +0 -0
  117. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/resolver.py +0 -0
  118. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/runtime.py +0 -0
  119. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/screen/__init__.py +0 -0
  120. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/screen/backend.py +0 -0
  121. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/screen/permissions.py +0 -0
  122. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/screen/safety.py +0 -0
  123. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/screen/validate.py +0 -0
  124. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/security.py +0 -0
  125. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/settings.py +0 -0
  126. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus/storage.py +0 -0
  127. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/__init__.py +0 -0
  128. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/bench/__init__.py +0 -0
  129. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/bench/__main__.py +0 -0
  130. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/bench/runner.py +0 -0
  131. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/bench/scenarios_buggytasks.py +0 -0
  132. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/bench/scenarios_darkshop.py +0 -0
  133. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/__init__.py +0 -0
  134. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/__main__.py +0 -0
  135. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/adjudication.py +0 -0
  136. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/agent_fixture.py +0 -0
  137. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/browser_baseline.py +0 -0
  138. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/codex_runner.py +0 -0
  139. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/fixture.py +0 -0
  140. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/gateway.py +0 -0
  141. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/models.py +0 -0
  142. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/overhead.py +0 -0
  143. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/scoring.py +0 -0
  144. {argus_testing-0.12.0 → argus_testing-0.12.2}/argus_lab/evaluation/smoke.py +0 -0
  145. {argus_testing-0.12.0 → argus_testing-0.12.2}/docs/architecture.md +0 -0
  146. {argus_testing-0.12.0 → argus_testing-0.12.2}/docs/decisions.md +0 -0
  147. {argus_testing-0.12.0 → argus_testing-0.12.2}/docs/evaluation-0.8.md +0 -0
  148. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/agent-evaluation-optimized-evidence.json +0 -0
  149. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/agent-evaluation-optimized.json +0 -0
  150. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/agent-evaluation-pilot-evidence.json +0 -0
  151. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/agent-evaluation-pilot.json +0 -0
  152. {argus_testing-0.12.0 → argus_testing-0.12.2}/examples/mcp-config.json +0 -0
  153. {argus_testing-0.12.0 → argus_testing-0.12.2}/glama.json +0 -0
  154. {argus_testing-0.12.0 → argus_testing-0.12.2}/human-eye-fixture/app.py +0 -0
  155. {argus_testing-0.12.0 → argus_testing-0.12.2}/test-site/app.py +0 -0
  156. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/__init__.py +0 -0
  157. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/conftest.py +0 -0
  158. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_action_targeting.py +0 -0
  159. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_adjudication.py +0 -0
  160. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_agent_results.py +0 -0
  161. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_agent_workflow.py +0 -0
  162. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_architecture_runtime.py +0 -0
  163. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_bench_report.py +0 -0
  164. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_browser_shadow.py +0 -0
  165. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_codex_evaluation.py +0 -0
  166. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_cross_stack.py +0 -0
  167. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_deprecated_modules.py +0 -0
  168. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_detector_console.py +0 -0
  169. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_detector_network.py +0 -0
  170. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_doctor.py +0 -0
  171. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_evaluation.py +0 -0
  172. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_evidence_provenance.py +0 -0
  173. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_expectation_oracle.py +0 -0
  174. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_final_coverage.py +0 -0
  175. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_final_hardening.py +0 -0
  176. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_form_checkboxes.py +0 -0
  177. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_journal_regression.py +0 -0
  178. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_mcp_compat.py +0 -0
  179. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_mcp_contract.py +0 -0
  180. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_monitoring.py +0 -0
  181. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_replay_minimize.py +0 -0
  182. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_replay_receipt.py +0 -0
  183. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_replay_trace.py +0 -0
  184. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_reporter_badge.py +0 -0
  185. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_reproduction_receipt.py +0 -0
  186. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_resolver.py +0 -0
  187. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_response_efficiency.py +0 -0
  188. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_runtime_limits.py +0 -0
  189. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_screen_permissions.py +0 -0
  190. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_screen_safety.py +0 -0
  191. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_security_boundaries.py +0 -0
  192. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_session_lifecycle.py +0 -0
  193. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_state_capsules.py +0 -0
  194. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_stdio_protocol.py +0 -0
  195. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_storage_cleanup.py +0 -0
  196. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_substrate.py +0 -0
  197. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_verification_efficiency.py +0 -0
  198. {argus_testing-0.12.0 → argus_testing-0.12.2}/tests/test_visual_inspection.py +0 -0
@@ -23,3 +23,4 @@ docs/*
23
23
  !docs/agent-protocol.md
24
24
  !docs/evaluation.md
25
25
  !docs/evaluation-0.8.md
26
+ !docs/usage.md
@@ -1,7 +1,6 @@
1
1
  # Argus — Agent Guide
2
2
 
3
- This file is the short version of the README, aimed at an agent using
4
- Argus through MCP. Argus is a QA capability inside the host's current
3
+ This guide is for an agent using Argus through MCP. Argus is a QA capability inside the host's current
5
4
  task; it does not replace the host agent's identity or authority.
6
5
 
7
6
  ## Setup
@@ -86,7 +85,7 @@ result includes captured stages. See [the protocol](docs/agent-protocol.md).
86
85
  | `verify_persistence(expect, target_text, after_url)` | Forces a fresh GET; returns target presence and the page observation. Check persistence once, repeat only to resolve uncertainty. A matching symptom is not proof of a semantic defect. |
87
86
  | `capsule_save(name, liveness_marker)` / `capsule_restore(name)` | Snapshot cookies and page storage after establishing state through the UI. Restore replaces the captured client state and checks a saved liveness marker when provided; without one, validity remains unverified. It does not reset backend data or guarantee identical application state across journeys. |
88
87
  | `regression_check()` | Re-test the findings journaled in prior runs against the CURRENT build: STILL-PRESENT / NO-LONGER-REPRODUCES / INCONCLUSIVE. "Did my fix land, did anything come back?" |
89
- | `export_test(finding_id, run=False)` | Turn a finding verified by a fresh-load text check into a standalone Playwright test that fails while the bug is present and passes once fixed. Steps it cannot translate are marked TODO; sensitive inputs come from environment variables. `run=true` repeats the journey's writes, so use it only with the user's authority. |
88
+ | `export_test(finding_id, run=False, save_private_values=False)` | Export a standalone Playwright test from a finding verified by a fresh-load text check. Confirm it fails on the symptom before using it in CI. Unsupported steps are marked TODO; 0.12.1 blocks incomplete exports before execution. See the [export protocol](docs/agent-protocol.md#exporting-a-regression-test) for environment variables and package-version limits. `run=true` repeats the journey's writes, so use it only with the user's authority. Only set `save_private_values=true` when the user explicitly requests retaining local replay values; its returned JSON file can contain credentials and must never be published. |
90
89
  | `inspect_element(description)` | Computed styles + ARIA + outerHTML + truncation flag for interactive or visible non-interactive content. |
91
90
  | `check_layout()` | Bounded viewport signals for horizontal overflow, clipped text, small targets, and fixed/sticky overlays. |
92
91
  | `screenshot(name, element="", full_page=False)` | Full viewport, full page, or a tight crop; waits for finite CSS transitions, then returns the image plus its absolute evidence path. |
@@ -1,5 +1,54 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.12.2 - 2026-11-08
4
+
5
+ - Treat intermittent regression receipts as inconclusive instead of fixed.
6
+ - Retain full verification predicates and preconditions privately for journals
7
+ and exports; public receipt text remains a preview. Hash complete predicates
8
+ for deduplication, including URL queries and fragments.
9
+ - Require re-recording legacy journal entries whose verification conditions are
10
+ incomplete. Storage-reset checks remain excluded from automatic regression
11
+ and test export rather than silently dropping the reset.
12
+ - Detect unexpected password login forms while allowing recorded checks of a
13
+ login page itself. Stop ambiguous row selection before replaying its action;
14
+ positional fallbacks require manual translation.
15
+ - Bound exported network waits like live verification. Busy pages can still
16
+ provide positive symptom evidence; unsettled absence stays inconclusive.
17
+
18
+ ## Plugin updates - 2026-11-05
19
+
20
+ - Claude plugin 0.12.2 and Codex plugin 0.12.1 pin the published Argus 0.12.1
21
+ runtime, refresh their dependency locks and document private replay values.
22
+ - Keep raw replay values out of shared artifacts; retention remains opt-in.
23
+
24
+ ## 0.12.1 - 2026-11-05
25
+
26
+ - Keep all application URLs, inputs, locator strings and assertion text out of
27
+ generated regression tests, including unknown query keys and path tokens. Read
28
+ them from environment variables; expose names and step purposes in `required_env`.
29
+ Omit finding prose from file contents and filenames. Preserve base-URL overrides.
30
+ - Add opt-in `save_private_values` for retaining a local, Git-ignored JSON values
31
+ file with owner-only POSIX permissions. Standalone tests can load it through
32
+ `ARGUS_VALUES_FILE`; explicit environment values take precedence. No values file
33
+ is written by default, and values are never included in tool results. Export
34
+ identities reject another test's file or environment before any browser actions.
35
+ - Withhold raw browser and subprocess error output from generated test failures
36
+ and `export_test` results. Keep explicit symptom, incomplete, login-wall and
37
+ missing-variable diagnostics. Missing input values block execution.
38
+ - Stop incomplete exports before browser actions instead of silently skipping
39
+ unsupported steps. `export_test(run=True)` reports `incomplete` without running.
40
+ - Shorten the project overview, move detailed usage and tool profiles to
41
+ `docs/usage.md`, and consolidate public documentation in English.
42
+
43
+ ## Claude plugin 0.12.1 - 2026-10-28
44
+
45
+ - Use `uv run --isolated --locked` without launcher environment overrides.
46
+ Each server gets a temporary environment populated from the existing lock;
47
+ cached downloads are reused and normal exit removes the environment. The
48
+ launcher neither modifies the plugin directory nor uses the host environment.
49
+ - Keep the server pinned to Argus 0.12.0 and preserve all dependency hashes.
50
+ This is a Claude plugin update, not a new Python package or Codex plugin release.
51
+
3
52
  ## 0.12.0 - 2026-10-28
4
53
 
5
54
  - Exported regression tests reject HTTP error pages and login walls instead of
@@ -2,8 +2,6 @@
2
2
 
3
3
  Keep the primary README, code, documentation and release notes in English and
4
4
  focused on product usage, implementation, verification and contribution guidance.
5
- `README.zh-CN.md` is the dedicated translation exception; keep its version,
6
- commands, capabilities and limitations synchronized with the English README.
7
5
 
8
6
  Use Python 3.11 or newer. CI runs 3.11 and 3.12. Browser checks are local and do
9
7
  not call a model provider:
@@ -30,7 +28,7 @@ separate macOS manual check; Linux CI does not claim to test that integration.
30
28
 
31
29
  - Tool arguments, MCP metadata and profile selection: `entrypoints/mcp/`.
32
30
  - A new QA operation: the appropriate `application/` service and `OPERATIONS`
33
- registry; add catalog metadata, both README versions and a protocol test.
31
+ registry; add catalog metadata, the usage reference and a protocol test.
34
32
  - Pure rules and typed data: `domain/`; no browser, MCP or HTTP imports here.
35
33
  - New verification: register an async strategy on `runtime.verifiers`. Return
36
34
  an explicit receipt with `attempted` and a three-state `reproduced` result.
@@ -118,10 +116,12 @@ package, so they move only after PyPI has the new version. Raise the
118
116
  version in both plugin manifests, run `uv lock` in `plugins/claude` and copy its
119
117
  `uv.lock` to `plugins/codex`. Then update the versioned `uvx` commands in both
120
118
  plugin READMEs and skills, including the locked Playwright version, and run
121
- `pytest plugins/tests`. When upgrading the bundles to 0.12, update both launch
122
- checks to require 29 web tools (instead of 28) and include `export_test`.
123
- Hosts update installed plugins only when the manifest
124
- version changes, and the skills' `--doctor` step assumes the web checks added
119
+ `pytest plugins/tests`. Keep both launch checks aligned with the published
120
+ runtime's web tool count and required capabilities, including `export_test`.
121
+ For plugin-only fixes, raise only the affected plugin manifest version; keep
122
+ the published runtime dependency and its lock unchanged. Plugin and runtime
123
+ versions may therefore differ. Hosts update installed plugins only when the
124
+ manifest version changes, and the skills' `--doctor` step assumes the web checks added
125
125
  in 0.12.
126
126
  MCPRush's default listing should expose the 29-tool web profile, not the
127
127
  `evaluation` baseline tools; preserve manually declared schemas when refreshing
@@ -0,0 +1,181 @@
1
+ Metadata-Version: 2.5
2
+ Name: argus-testing
3
+ Version: 0.12.2
4
+ Summary: Testing MCP for coding agents: exercise real user journeys, find bugs, and verify them with evidence and persistence checks
5
+ Project-URL: Homepage, https://yichenwu.dev/projects/argus
6
+ Project-URL: Documentation, https://github.com/chriswu727/argus#readme
7
+ Project-URL: Repository, https://github.com/chriswu727/argus
8
+ Project-URL: Issues, https://github.com/chriswu727/argus/issues
9
+ Author: Yichen Wu
10
+ License: MIT
11
+ License-File: LICENSE
12
+ Keywords: ai-agent,autonomous-testing,browser-testing,bug-finding,claude-code,codex,exploratory-testing,mcp,playwright,qa,qa-engineer,software-testing,testing
13
+ Classifier: Development Status :: 3 - Alpha
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: License :: OSI Approved :: MIT License
16
+ Classifier: Programming Language :: Python :: 3
17
+ Classifier: Topic :: Software Development :: Testing
18
+ Requires-Python: >=3.11
19
+ Requires-Dist: certifi>=2026.10.23
20
+ Requires-Dist: click>=8.0.0
21
+ Requires-Dist: cryptography>=50.0.2
22
+ Requires-Dist: filelock<5,>=4.2.4
23
+ Requires-Dist: mcp[cli]<2.0.0,>=1.30.0
24
+ Requires-Dist: pillow>=13.0.0
25
+ Requires-Dist: playwright>=1.40.0
26
+ Requires-Dist: pydantic>=2.0.0
27
+ Requires-Dist: pyjwt>=2.15.1
28
+ Requires-Dist: rich>=13.0.0
29
+ Requires-Dist: starlette<2,>=0.27
30
+ Requires-Dist: typing-extensions>=4.9
31
+ Requires-Dist: uvicorn<1,>=0.31
32
+ Provides-Extra: dev
33
+ Requires-Dist: httpx<1,>=0.27; extra == 'dev'
34
+ Requires-Dist: mypy<3,>=2.4; extra == 'dev'
35
+ Requires-Dist: pip-audit<3,>=2.9; extra == 'dev'
36
+ Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
37
+ Requires-Dist: pytest>=8.0.0; extra == 'dev'
38
+ Requires-Dist: ruff<0.18,>=0.17; extra == 'dev'
39
+ Provides-Extra: mac
40
+ Requires-Dist: pyobjc-framework-applicationservices>=10.0; (sys_platform == 'darwin') and extra == 'mac'
41
+ Requires-Dist: pyobjc-framework-cocoa>=10.0; (sys_platform == 'darwin') and extra == 'mac'
42
+ Requires-Dist: pyobjc-framework-quartz>=10.0; (sys_platform == 'darwin') and extra == 'mac'
43
+ Description-Content-Type: text/markdown
44
+
45
+ <!-- mcp-name: io.github.chriswu727/argus -->
46
+
47
+ <div align="center">
48
+
49
+ <img src="https://raw.githubusercontent.com/chriswu727/argus/main/assets/argus-icon.png" alt="Argus logo" width="112">
50
+
51
+ # Argus
52
+
53
+ ### Browser testing for your coding agent.
54
+
55
+ [![PyPI](https://img.shields.io/pypi/v/argus-testing?color=1a7f37)](https://pypi.org/project/argus-testing/)
56
+ [![CI](https://github.com/chriswu727/argus/actions/workflows/ci.yml/badge.svg)](https://github.com/chriswu727/argus/actions/workflows/ci.yml)
57
+ [![Python](https://img.shields.io/pypi/pyversions/argus-testing)](https://pypi.org/project/argus-testing/)
58
+ [![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
59
+
60
+ [Quick start](#quick-start) · [What you get](#what-you-get) · [Engineering](#engineering) · [Documentation](#documentation) · [Product page](https://yichenwu.dev/projects/argus)
61
+
62
+ </div>
63
+
64
+ Argus is an [MCP](https://modelcontextprotocol.io/) testing server for Claude Code,
65
+ Codex, Cursor and other coding agents. It gives your existing agent the tools to
66
+ test your app the way a testing engineer works through it: explore user journeys,
67
+ check state after each action, try edge cases, verify suspected failures on a fresh
68
+ load and report with evidence.
69
+ The agent decides what to test; Argus handles browser actions, repeatable checks
70
+ and the results.
71
+
72
+ > Test my web app at http://localhost:3000 and look for bugs.
73
+
74
+ Your agent can explore user flows, inspect what changed after each action and
75
+ recheck suspected failures on a fresh page load. You can also give it specific
76
+ goals, such as testing account settings or checking whether saved data survives
77
+ a refresh.
78
+
79
+ ## What you get
80
+
81
+ - **A report you can act on.** Findings include expected and actual behavior,
82
+ reproduction steps, screenshots and verification results. Reports also show
83
+ which testing goals were exercised, blocked or left unfinished.
84
+ - **A separate verification step.** Argus rechecks the specified symptom before
85
+ marking it reproduced. Observations and inconclusive checks remain distinct
86
+ from reproduced findings.
87
+ - **A regression test to keep.** Supported findings can be exported as standalone
88
+ Playwright tests. Confirm that the test fails on the bug before adding it to
89
+ your suite; it should pass after the behavior is fixed.
90
+
91
+ <div align="center">
92
+ <img src="https://raw.githubusercontent.com/chriswu727/argus/main/assets/report.png" alt="Example Argus report showing findings and reproduction evidence" width="800">
93
+ </div>
94
+
95
+ For example, a task may disappear after deletion but return after a refresh.
96
+ Argus can check that behavior on fresh loads, retain the evidence and export a
97
+ test for the persistence failure. The receipt confirms that symptom; it does
98
+ not identify the root cause or fix the application.
99
+
100
+ Reports are available as **HTML, JSON, JUnit and SARIF**. Test exports currently
101
+ support findings verified through fresh-load text checks. Uploads, restored
102
+ browser state and other unsupported steps require manual translation.
103
+
104
+ ## Quick start
105
+
106
+ Requires **Python 3.11+**, Chromium and an MCP-capable coding agent.
107
+ With [`uv`](https://docs.astral.sh/uv/):
108
+
109
+ ```bash
110
+ uvx --from argus-testing python -m playwright install chromium
111
+ uvx --from argus-testing argus-mcp --doctor
112
+ ```
113
+
114
+ Connect it to **Claude Code**:
115
+
116
+ ```bash
117
+ claude mcp add argus -- uvx --from argus-testing argus-mcp
118
+ ```
119
+
120
+ Or **Codex**:
121
+
122
+ ```bash
123
+ codex mcp add argus -- uvx --from argus-testing argus-mcp
124
+ ```
125
+
126
+ Then ask your agent to test your app. Use test accounts and data you can change:
127
+ replaying a journey can repeat its writes.
128
+
129
+ [Cursor, other MCP clients and troubleshooting](docs/usage.md#quick-start) ·
130
+ [Claude plugin](plugins/claude) · [Codex plugin](plugins/codex)
131
+
132
+ **0.12.2**: regression checks preserve complete verification conditions and treat
133
+ intermittent results as inconclusive. Exported tests stop on missing or ambiguous
134
+ row targets. Regenerate older tests and follow the [journal migration steps](docs/usage.md).
135
+ See the [releases](https://github.com/chriswu727/argus/releases) and
136
+ [changelog](CHANGELOG.md#0122---2026-11-08).
137
+
138
+ ## Engineering
139
+
140
+ Where to start reading the code:
141
+
142
+ - **Verification with explicit outcomes.** A completed tool call is not a passed
143
+ application test. Checks return evidence and a reproduced, not reproduced or
144
+ inconclusive outcome. HTTP errors and login walls stop exported checks from
145
+ treating a missing symptom as a fix.
146
+ - **Recorded actions become reusable tests.** Exports use the controls resolved
147
+ during the session, preserve iframe and row scope, and check the symptom on a
148
+ fresh load. The [export tests](tests/test_export_test.py) exercise both buggy
149
+ and fixed versions of local fixtures.
150
+ - **Separated runtime and adapters.** Session lifecycle, browser
151
+ operations, verification and reporting are separated. The host agent supplies
152
+ the model; Argus does not run its own model loop or require another API key.
153
+ See the [architecture](docs/architecture.md) and [design decisions](docs/decisions.md).
154
+
155
+ Argus is still an alpha project. A fresh load normally retains authentication
156
+ and browser storage; it is not a reset of the backend. A reproduced symptom is
157
+ not proof of complete coverage or of a requirements violation. Generated tests
158
+ and screenshots should be reviewed before sharing, especially with sensitive
159
+ application data. [Privacy details](PRIVACY.md).
160
+
161
+ ## Evaluation
162
+
163
+ The deterministic fixtures cover **34 seeded scenarios**. That measures what
164
+ the tools can exercise with scripted steps, not an agent's bug-discovery rate.
165
+ In a [small paired Codex evaluation](docs/evaluation-0.8.md), both Argus and the
166
+ browser baseline found all 5 predeclared defects. Argus also found one fixture
167
+ defect identified after the run and used more time and tokens. These results
168
+ do not establish general superiority.
169
+
170
+ The [evaluation guide](docs/evaluation.md) documents the method, limits and
171
+ reproduction commands. Browser and unit tests run locally without model calls;
172
+ model-based evaluations are separate and opt-in.
173
+
174
+ ## Documentation
175
+
176
+ - [Usage and tool reference](docs/usage.md) — client setup, profiles, configuration and regression workflows.
177
+ - [Agent protocol](docs/agent-protocol.md) — structured results, evidence and coverage tracking.
178
+ - [Contributing](CONTRIBUTING.md) — local checks and implementation boundaries.
179
+ - [Changelog](CHANGELOG.md) · [Security](SECURITY.md) · [Privacy](PRIVACY.md).
180
+
181
+ Built by [Yichen Wu](https://github.com/chriswu727) · [yichenwu.dev](https://yichenwu.dev)
@@ -32,7 +32,10 @@ credential-bearing URL parameters and headers are redacted in captured requests.
32
32
  All built-in report formats use a common redacted copy of the report data,
33
33
  including visited URLs and nested reproduction evidence. This does not modify
34
34
  the live session or the journal's executable verification conditions. Journals
35
- remain private local artifacts and may retain sensitive verification URLs.
35
+ remain private local artifacts and may retain sensitive verification URLs,
36
+ full assertion text and verification preconditions. The complete execution
37
+ predicate stays separate from the public receipt's text preview; a preview
38
+ is not a substitute for reviewing artifacts before sharing them.
36
39
  Screenshots and unlabeled application-specific secrets still require manual review.
37
40
 
38
41
  Cookie and storage inspection hides values unless the operator enables
@@ -40,6 +43,31 @@ Cookie and storage inspection hides values unless the operator enables
40
43
  capture/restore, which intentionally preserves raw browser state. Local file
41
44
  inputs require approved directories in `ARGUS_FILE_ROOTS`; see [Security](SECURITY.md).
42
45
 
46
+ Since 0.12.1, Argus keeps application URLs, typed/selected values, locator strings and
47
+ assertion text out of generated regression test source. Finding descriptions are
48
+ omitted, and filenames use the run ID and finding index. All application strings
49
+ are supplied through environment variables. The tool returns variable names with
50
+ fixed step/purpose labels, not values; an immediate run passes the values in the
51
+ child environment without writing a values file by default. Only explicit
52
+ `save_private_values=true` retains a raw JSON file in a new local directory;
53
+ POSIX permissions are 0700 for the directory and 0600 for the file. A `.gitignore`
54
+ ignores the directory's contents. This is not encryption and does not protect
55
+ against forced Git adds, archive uploads, backups or access by the local account.
56
+ The file persists until the user deletes it. Never publish it. `ARGUS_VALUES_FILE`
57
+ lets its matching generated test load it without changing the runner's process
58
+ environment. File and environment values require a matching export identity to
59
+ prevent accidentally replaying another test's values.
60
+ Generated exceptions suppress raw
61
+ browser errors; tool results never forward raw subprocess output. These safeguards
62
+ are available in 0.12.1. Earlier 0.12.0 exports parameterize only recognized
63
+ sensitive inputs; regenerate old tests after upgrading.
64
+
65
+ Environment variables are not encrypted or isolated from the local account, child
66
+ processes, debuggers, process dumps or CI administrators. Do not enable runner
67
+ options that dump environments/locals or publish CI secrets, reports or screenshots.
68
+ Review any manual edits to generated tests before sharing them. Export protection
69
+ does not sanitize the separate application evidence described above.
70
+
43
71
  ## Where data can go
44
72
 
45
73
  - The MCP host and its configured model provider receive the Argus tool inputs
@@ -0,0 +1,137 @@
1
+ <!-- mcp-name: io.github.chriswu727/argus -->
2
+
3
+ <div align="center">
4
+
5
+ <img src="https://raw.githubusercontent.com/chriswu727/argus/main/assets/argus-icon.png" alt="Argus logo" width="112">
6
+
7
+ # Argus
8
+
9
+ ### Browser testing for your coding agent.
10
+
11
+ [![PyPI](https://img.shields.io/pypi/v/argus-testing?color=1a7f37)](https://pypi.org/project/argus-testing/)
12
+ [![CI](https://github.com/chriswu727/argus/actions/workflows/ci.yml/badge.svg)](https://github.com/chriswu727/argus/actions/workflows/ci.yml)
13
+ [![Python](https://img.shields.io/pypi/pyversions/argus-testing)](https://pypi.org/project/argus-testing/)
14
+ [![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
15
+
16
+ [Quick start](#quick-start) · [What you get](#what-you-get) · [Engineering](#engineering) · [Documentation](#documentation) · [Product page](https://yichenwu.dev/projects/argus)
17
+
18
+ </div>
19
+
20
+ Argus is an [MCP](https://modelcontextprotocol.io/) testing server for Claude Code,
21
+ Codex, Cursor and other coding agents. It gives your existing agent the tools to
22
+ test your app the way a testing engineer works through it: explore user journeys,
23
+ check state after each action, try edge cases, verify suspected failures on a fresh
24
+ load and report with evidence.
25
+ The agent decides what to test; Argus handles browser actions, repeatable checks
26
+ and the results.
27
+
28
+ > Test my web app at http://localhost:3000 and look for bugs.
29
+
30
+ Your agent can explore user flows, inspect what changed after each action and
31
+ recheck suspected failures on a fresh page load. You can also give it specific
32
+ goals, such as testing account settings or checking whether saved data survives
33
+ a refresh.
34
+
35
+ ## What you get
36
+
37
+ - **A report you can act on.** Findings include expected and actual behavior,
38
+ reproduction steps, screenshots and verification results. Reports also show
39
+ which testing goals were exercised, blocked or left unfinished.
40
+ - **A separate verification step.** Argus rechecks the specified symptom before
41
+ marking it reproduced. Observations and inconclusive checks remain distinct
42
+ from reproduced findings.
43
+ - **A regression test to keep.** Supported findings can be exported as standalone
44
+ Playwright tests. Confirm that the test fails on the bug before adding it to
45
+ your suite; it should pass after the behavior is fixed.
46
+
47
+ <div align="center">
48
+ <img src="https://raw.githubusercontent.com/chriswu727/argus/main/assets/report.png" alt="Example Argus report showing findings and reproduction evidence" width="800">
49
+ </div>
50
+
51
+ For example, a task may disappear after deletion but return after a refresh.
52
+ Argus can check that behavior on fresh loads, retain the evidence and export a
53
+ test for the persistence failure. The receipt confirms that symptom; it does
54
+ not identify the root cause or fix the application.
55
+
56
+ Reports are available as **HTML, JSON, JUnit and SARIF**. Test exports currently
57
+ support findings verified through fresh-load text checks. Uploads, restored
58
+ browser state and other unsupported steps require manual translation.
59
+
60
+ ## Quick start
61
+
62
+ Requires **Python 3.11+**, Chromium and an MCP-capable coding agent.
63
+ With [`uv`](https://docs.astral.sh/uv/):
64
+
65
+ ```bash
66
+ uvx --from argus-testing python -m playwright install chromium
67
+ uvx --from argus-testing argus-mcp --doctor
68
+ ```
69
+
70
+ Connect it to **Claude Code**:
71
+
72
+ ```bash
73
+ claude mcp add argus -- uvx --from argus-testing argus-mcp
74
+ ```
75
+
76
+ Or **Codex**:
77
+
78
+ ```bash
79
+ codex mcp add argus -- uvx --from argus-testing argus-mcp
80
+ ```
81
+
82
+ Then ask your agent to test your app. Use test accounts and data you can change:
83
+ replaying a journey can repeat its writes.
84
+
85
+ [Cursor, other MCP clients and troubleshooting](docs/usage.md#quick-start) ·
86
+ [Claude plugin](plugins/claude) · [Codex plugin](plugins/codex)
87
+
88
+ **0.12.2**: regression checks preserve complete verification conditions and treat
89
+ intermittent results as inconclusive. Exported tests stop on missing or ambiguous
90
+ row targets. Regenerate older tests and follow the [journal migration steps](docs/usage.md).
91
+ See the [releases](https://github.com/chriswu727/argus/releases) and
92
+ [changelog](CHANGELOG.md#0122---2026-11-08).
93
+
94
+ ## Engineering
95
+
96
+ Where to start reading the code:
97
+
98
+ - **Verification with explicit outcomes.** A completed tool call is not a passed
99
+ application test. Checks return evidence and a reproduced, not reproduced or
100
+ inconclusive outcome. HTTP errors and login walls stop exported checks from
101
+ treating a missing symptom as a fix.
102
+ - **Recorded actions become reusable tests.** Exports use the controls resolved
103
+ during the session, preserve iframe and row scope, and check the symptom on a
104
+ fresh load. The [export tests](tests/test_export_test.py) exercise both buggy
105
+ and fixed versions of local fixtures.
106
+ - **Separated runtime and adapters.** Session lifecycle, browser
107
+ operations, verification and reporting are separated. The host agent supplies
108
+ the model; Argus does not run its own model loop or require another API key.
109
+ See the [architecture](docs/architecture.md) and [design decisions](docs/decisions.md).
110
+
111
+ Argus is still an alpha project. A fresh load normally retains authentication
112
+ and browser storage; it is not a reset of the backend. A reproduced symptom is
113
+ not proof of complete coverage or of a requirements violation. Generated tests
114
+ and screenshots should be reviewed before sharing, especially with sensitive
115
+ application data. [Privacy details](PRIVACY.md).
116
+
117
+ ## Evaluation
118
+
119
+ The deterministic fixtures cover **34 seeded scenarios**. That measures what
120
+ the tools can exercise with scripted steps, not an agent's bug-discovery rate.
121
+ In a [small paired Codex evaluation](docs/evaluation-0.8.md), both Argus and the
122
+ browser baseline found all 5 predeclared defects. Argus also found one fixture
123
+ defect identified after the run and used more time and tokens. These results
124
+ do not establish general superiority.
125
+
126
+ The [evaluation guide](docs/evaluation.md) documents the method, limits and
127
+ reproduction commands. Browser and unit tests run locally without model calls;
128
+ model-based evaluations are separate and opt-in.
129
+
130
+ ## Documentation
131
+
132
+ - [Usage and tool reference](docs/usage.md) — client setup, profiles, configuration and regression workflows.
133
+ - [Agent protocol](docs/agent-protocol.md) — structured results, evidence and coverage tracking.
134
+ - [Contributing](CONTRIBUTING.md) — local checks and implementation boundaries.
135
+ - [Changelog](CHANGELOG.md) · [Security](SECURITY.md) · [Privacy](PRIVACY.md).
136
+
137
+ Built by [Yichen Wu](https://github.com/chriswu727) · [yichenwu.dev](https://yichenwu.dev)
@@ -1,5 +1,7 @@
1
1
  from __future__ import annotations
2
2
 
3
+ import hashlib
4
+ import json
3
5
  import re
4
6
  from pathlib import Path
5
7
  from typing import Optional
@@ -64,15 +66,23 @@ def _journal_path(origin: str) -> Path:
64
66
 
65
67
 
66
68
  def _bug_fingerprint(bug: "Bug") -> str:
67
- """Stable identity for cross-run dedup — from the receipt's structural fields
68
- (type + url path + expect + target), never the LLM-authored title, so a
69
- genuinely new bug is never silently collapsed into an old one."""
70
- r = bug.reproduction_receipt or {}
71
- path = urlparse(r.get("at_url") or bug.url or "").path or "/"
72
- return (
73
- f"{bug.type.value}|{path}|{r.get('expect', '')}|"
74
- f"{(r.get('target_text') or '')[:80]}|{r.get('expect_status', '')}"
75
- )
69
+ r = bug.verification_spec or bug.reproduction_receipt or {}
70
+ identity = {
71
+ key: r.get(key)
72
+ for key in (
73
+ "version",
74
+ "kind",
75
+ "at_url",
76
+ "expect",
77
+ "target_text",
78
+ "expect_status",
79
+ "clear_storage",
80
+ "login_page",
81
+ )
82
+ }
83
+ identity["at_url"] = identity["at_url"] or bug.url
84
+ payload = json.dumps(identity, sort_keys=True, ensure_ascii=True)
85
+ return f"{bug.type.value}|{hashlib.sha256(payload.encode()).hexdigest()}"
76
86
 
77
87
 
78
88
  def _journal_entries(origin: str, *, strict: bool = False) -> list:
@@ -109,6 +119,8 @@ def _write_journal(s: "Session") -> None:
109
119
  verify["expect_status"] = expected_status
110
120
  else:
111
121
  verify.update({"expect": expect, "target_text": target})
122
+ if b.verification_spec:
123
+ verify = dict(b.verification_spec)
112
124
  fresh.append(
113
125
  {
114
126
  "fingerprint": _bug_fingerprint(b),