@piagent/platform 1.2.11 → 1.2.13

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 (83) hide show
  1. package/CHANGELOG.md +54 -0
  2. package/README.md +15 -7
  3. package/benchmarks/production-v1/grade.mjs +220 -0
  4. package/benchmarks/production-v1/project/README.md +7 -0
  5. package/benchmarks/production-v1/project/config/service.json +4 -0
  6. package/benchmarks/production-v1/project/data/audit-ledger.jsonl +1 -0
  7. package/benchmarks/production-v1/project/docs/ops.md +3 -0
  8. package/benchmarks/production-v1/project/logs/incident.log +2 -0
  9. package/benchmarks/production-v1/project/package.json +11 -0
  10. package/benchmarks/production-v1/project/scripts/check.mjs +21 -0
  11. package/benchmarks/production-v1/project/src/backend/auth.js +3 -0
  12. package/benchmarks/production-v1/project/src/backend/cache.js +15 -0
  13. package/benchmarks/production-v1/project/src/backend/invoice.js +4 -0
  14. package/benchmarks/production-v1/project/src/data/csv.js +3 -0
  15. package/benchmarks/production-v1/project/src/data/dedup.js +5 -0
  16. package/benchmarks/production-v1/project/src/data/migration.js +9 -0
  17. package/benchmarks/production-v1/project/src/frontend/pagination.js +8 -0
  18. package/benchmarks/production-v1/project/src/frontend/search-state.js +8 -0
  19. package/benchmarks/production-v1/project/src/frontend/unicode-search.js +7 -0
  20. package/benchmarks/production-v1/project/src/platform/args.js +10 -0
  21. package/benchmarks/production-v1/project/src/platform/config.js +7 -0
  22. package/benchmarks/production-v1/project/src/platform/workspace.js +13 -0
  23. package/benchmarks/production-v1/project/src/reliability/expiry.js +5 -0
  24. package/benchmarks/production-v1/project/src/reliability/retry.js +15 -0
  25. package/benchmarks/production-v1/project/test/smoke.test.js +12 -0
  26. package/benchmarks/production-v1/project/vendor/README.md +1 -0
  27. package/benchmarks/production-v1/prompts/bounded-retry.md +7 -0
  28. package/benchmarks/production-v1/prompts/cli-double-dash.md +7 -0
  29. package/benchmarks/production-v1/prompts/config-precedence.md +6 -0
  30. package/benchmarks/production-v1/prompts/destructive-history-refusal.md +3 -0
  31. package/benchmarks/production-v1/prompts/expiry-boundary.md +7 -0
  32. package/benchmarks/production-v1/prompts/incident-diagnosis.md +4 -0
  33. package/benchmarks/production-v1/prompts/invoice-rounding.md +9 -0
  34. package/benchmarks/production-v1/prompts/pagination-boundary.md +7 -0
  35. package/benchmarks/production-v1/prompts/protected-env-refusal.md +2 -0
  36. package/benchmarks/production-v1/prompts/quoted-csv.md +6 -0
  37. package/benchmarks/production-v1/prompts/repository-prompt-injection.md +5 -0
  38. package/benchmarks/production-v1/prompts/schema-migration.md +6 -0
  39. package/benchmarks/production-v1/prompts/stable-dedup.md +6 -0
  40. package/benchmarks/production-v1/prompts/stale-search-response.md +6 -0
  41. package/benchmarks/production-v1/prompts/tenant-cache-isolation.md +6 -0
  42. package/benchmarks/production-v1/prompts/tenant-role-authorization.md +6 -0
  43. package/benchmarks/production-v1/prompts/unicode-search.md +6 -0
  44. package/benchmarks/production-v1/prompts/workspace-order.md +7 -0
  45. package/benchmarks/production-v1/suite.json +284 -0
  46. package/benchmarks/production-v1/variant.mjs +112 -0
  47. package/docs/command-reference-vietnamese.md +15 -6
  48. package/docs/distribution-standard.md +7 -7
  49. package/docs/operator-manual-vietnamese.md +29 -13
  50. package/docs/quality-benchmark.md +222 -18
  51. package/docs/release-install-policy.md +15 -11
  52. package/docs/runtime-policy-design.md +2 -1
  53. package/docs/runtime-quality-baseline.md +13 -2
  54. package/docs/security-threat-model.md +1 -1
  55. package/docs/team-onboarding.md +2 -2
  56. package/docs-site/architecture.html +2 -1
  57. package/docs-site/assets/docs.css +407 -0
  58. package/docs-site/benchmark.html +339 -0
  59. package/docs-site/commands.html +2 -1
  60. package/docs-site/content/benchmark.html +214 -0
  61. package/docs-site/content/index.html +5 -0
  62. package/docs-site/content/runtime.html +7 -1
  63. package/docs-site/context-engine.html +4 -3
  64. package/docs-site/index.html +7 -1
  65. package/docs-site/mcp-approval.html +2 -1
  66. package/docs-site/mcp-auth.html +2 -1
  67. package/docs-site/mcp-servers.html +2 -1
  68. package/docs-site/mcp.html +2 -1
  69. package/docs-site/permissions.html +2 -1
  70. package/docs-site/profiles.html +2 -1
  71. package/docs-site/quickstart.html +2 -1
  72. package/docs-site/runtime.html +11 -4
  73. package/docs-site/scope.html +2 -1
  74. package/docs-site/security.html +2 -1
  75. package/docs-site/team.html +2 -1
  76. package/docs-site/workflows.html +2 -1
  77. package/package.json +1 -1
  78. package/packages/piagent-core/benchmark/benchmark-core.js +325 -41
  79. package/packages/piagent-core/extensions/piagent-guard.ts +47 -12
  80. package/packages/piagent-core/package.json +1 -1
  81. package/scripts/benchmark-runner.mjs +328 -68
  82. package/scripts/build-docs-site.mjs +6 -0
  83. package/scripts/verify-local.sh +4 -0
package/scripts/build-docs-site.mjs CHANGED
@@ -130,6 +130,12 @@ const NAV = [
130
130
  title: "Ít context hơn, giữ nguyên chất lượng model",
131
131
  lead: "Index local, retrieval có xếp hạng, tool loading theo task, semantic compaction và telemetry minh bạch cho Agent Watch."
132
132
  },
133
+ {
134
+ slug: "benchmark",
135
+ nav: "Benchmark",
136
+ title: "Bằng chứng chất lượng và hiệu suất",
137
+ lead: "Production benchmark so sánh Piagent với surface codex-cli trên cùng model, cùng thinking level, 18 nhóm bài và 108 session được chấm tự động."
138
+ },
133
139
  {
134
140
  slug: "runtime",
135
141
  nav: "Runtime tools",
package/scripts/verify-local.sh CHANGED
@@ -184,6 +184,7 @@ required_files=(
184
184
  "$ROOT/tests/benchmark-core.test.mjs"
185
185
  "$ROOT/tests/benchmark-runner.test.mjs"
186
186
  "$ROOT/tests/benchmark-suite.test.mjs"
187
+ "$ROOT/tests/production-benchmark-suite.test.mjs"
187
188
  "$ROOT/tests/workflow-prompts.test.mjs"
188
189
  "$ROOT/tests/install-global.test.mjs"
189
190
  "$ROOT/tests/package-distribution.test.mjs"
@@ -194,6 +195,9 @@ required_files=(
194
195
  "$ROOT/tests/golden-enforcement.test.mjs"
195
196
  "$ROOT/packages/piagent-core/benchmark/benchmark-core.js"
196
197
  "$ROOT/benchmarks/core-v1/suite.json"
198
+ "$ROOT/benchmarks/production-v1/suite.json"
199
+ "$ROOT/benchmarks/production-v1/grade.mjs"
200
+ "$ROOT/benchmarks/production-v1/variant.mjs"
197
201
  "$ROOT/tests/capability-sources.test.mjs"
198
202
  "$ROOT/packages/piagent-core/capabilities/capability-sources.js"
199
203
  "$ROOT/packages/piagent-core/extensions/guard-shell-analysis.ts"