@tea-agent/loop-agent 0.13.0-alpha.0 → 0.13.0

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 (199) hide show
  1. package/AGENTS.md +4 -0
  2. package/CHANGELOG.md +57 -53
  3. package/README.md +12 -3
  4. package/dist/application/dag/generate-task-dag.js +28 -58
  5. package/dist/application/evaluation/candidate-hash.js +75 -0
  6. package/dist/application/evaluation/candidate.js +52 -0
  7. package/dist/application/evaluation/replay.js +289 -0
  8. package/dist/application/evaluation/types.js +130 -0
  9. package/dist/cli/command-definitions.js +17 -4
  10. package/dist/cli/program.js +8 -4
  11. package/dist/commands/eval.js +235 -0
  12. package/dist/commands/init.js +131 -24
  13. package/dist/executors/pi-sdk-executor.js +38 -24
  14. package/dist/executors/shell-executor.js +226 -15
  15. package/dist/executors/shell-presets.js +20 -0
  16. package/dist/executors/shell-verification.js +7 -0
  17. package/dist/governance/manifest-types.js +1 -0
  18. package/dist/infrastructure/evaluation/candidate-store.js +439 -0
  19. package/dist/infrastructure/evaluation/store.js +40 -0
  20. package/dist/task/config-types.js +23 -0
  21. package/dist/worker/observe/routes.js +18 -3
  22. package/dist/worker/observe/spec-evidence.js +1 -1
  23. package/dist/worker/observe/static/dom.js +160 -1
  24. package/dist/worker/observe/static/state.js +14 -0
  25. package/dist/worker/observe/static/views/dag-inspector.js +35 -4
  26. package/dist/worker/observe/static/views/dag.js +9 -0
  27. package/dist/worker/observe/static/views/dashboard.js +702 -445
  28. package/dist/worker/observe/static/views/session-timeline.js +15 -1
  29. package/dist/workflows/dag/backend-test-analysis-contract.js +120 -0
  30. package/dist/workflows/dag/backend-test-case-manifest.js +503 -0
  31. package/dist/workflows/dag/backend-test-execution-contract.js +353 -0
  32. package/dist/workflows/dag/backend-test-result-contract.js +568 -0
  33. package/dist/workflows/dag/decision-envelope.js +57 -2
  34. package/dist/workflows/dag/dynamic-runtime/map.js +90 -2
  35. package/dist/workflows/dag/frontend-implementation-contract.js +240 -0
  36. package/dist/workflows/dag/frontend-project-capability.js +309 -0
  37. package/dist/workflows/dag/frontend-repair.js +341 -0
  38. package/dist/workflows/dag/frontend-risk.js +161 -0
  39. package/dist/workflows/dag/frontend-verification-trace.js +190 -0
  40. package/dist/workflows/dag/init-hybrid.js +2407 -297
  41. package/dist/workflows/dag/node-execution.js +9 -0
  42. package/dist/workflows/dag/prompt.js +9 -0
  43. package/dist/workflows/dag/repair-artifact.js +43 -3
  44. package/dist/workflows/dag/report.js +35 -1
  45. package/dist/workflows/dag/runner.js +28 -2
  46. package/dist/workflows/dag/skill-instructions.js +4 -2
  47. package/dist/workflows/dag/task-demand-routing.js +383 -0
  48. package/dist/workflows/dag/types.js +71 -13
  49. package/dist/workflows/dag/upstream-artifacts.js +1 -0
  50. package/dist/workflows/dag/validate.js +59 -1
  51. package/docs/README.md +6 -3
  52. package/docs/agent-dag-recovery-playbook.md +5 -3
  53. package/docs/agent-dag-runner.md +3 -3
  54. package/docs/architecture/README.md +3 -3
  55. package/docs/architecture/dag-execution.md +1 -1
  56. package/docs/architecture/evolution.md +13 -13
  57. package/docs/architecture/facts-and-state.md +1 -1
  58. package/docs/architecture/runtime-boundaries.md +7 -7
  59. package/docs/architecture/system-overview.md +3 -3
  60. package/docs/architecture/worker-and-feature.md +3 -3
  61. package/docs/design/README.md +124 -42
  62. package/docs/development-principles.md +4 -4
  63. package/docs/exec-plans/active/README.md +12 -11
  64. package/docs/exec-plans/completed/README.md +33 -0
  65. package/docs/feature-workflow.md +114 -39
  66. package/docs/init-surface.manifest.json +30 -3
  67. package/docs/loop-agent-harness.md +9 -8
  68. package/docs/production-readiness.md +1 -1
  69. package/docs/progress/README.md +23 -1
  70. package/docs/reports/README.md +65 -6
  71. package/docs/skills/vetted-skill-registry.md +2 -0
  72. package/docs/templates/agent-dag.schema.json +29 -1
  73. package/docs/templates/agent-dag.supervised-implementation.json +127 -8
  74. package/docs/templates/backend-test-analysis.schema.json +44 -0
  75. package/docs/templates/backend-test-case-manifest.schema.json +190 -0
  76. package/docs/templates/backend-test-dag.classify.prompt.md +75 -0
  77. package/docs/templates/backend-test-dag.generate-pytest.prompt.md +81 -16
  78. package/docs/templates/backend-test-dag.json +311 -40
  79. package/docs/templates/backend-test-dag.retrospect.prompt.md +44 -30
  80. package/docs/templates/backend-test-dag.review-cases.prompt.md +10 -8
  81. package/docs/templates/backend-test-execution.schema.json +133 -0
  82. package/docs/templates/backend-test-result.schema.json +99 -0
  83. package/docs/templates/branch-merge-report.md +93 -0
  84. package/docs/templates/frontend-design-contract.md +9 -0
  85. package/docs/templates/frontend-eval/fixtures/failures/01-type-build-error.md +17 -0
  86. package/docs/templates/frontend-eval/fixtures/failures/02-unit-component-test-fail.md +16 -0
  87. package/docs/templates/frontend-eval/fixtures/failures/03-fixture-schema-drift.md +16 -0
  88. package/docs/templates/frontend-eval/fixtures/failures/04-missing-loading-empty-error-state.md +16 -0
  89. package/docs/templates/frontend-eval/fixtures/failures/05-forbidden-write-writeset-expansion.md +16 -0
  90. package/docs/templates/frontend-eval/fixtures/failures/06-unapproved-dependency-add.md +16 -0
  91. package/docs/templates/frontend-eval/fixtures/failures/07-mock-production-on.md +21 -0
  92. package/docs/templates/frontend-eval/fixtures/functional/01-simple-component-style.md +29 -0
  93. package/docs/templates/frontend-eval/fixtures/functional/02-form-validation.md +28 -0
  94. package/docs/templates/frontend-eval/fixtures/functional/03-list-detail-page.md +28 -0
  95. package/docs/templates/frontend-eval/fixtures/functional/04-api-mock.md +29 -0
  96. package/docs/templates/frontend-eval/fixtures/functional/05-permission-auth-gated-ui.md +27 -0
  97. package/docs/templates/frontend-eval/fixtures/functional/06-ssr-server-client-boundary.md +28 -0
  98. package/docs/templates/frontend-eval/fixtures/functional/07-shared-public-component-api.md +28 -0
  99. package/docs/templates/frontend-eval/fixtures/functional/08-pure-local-no-remote.md +27 -0
  100. package/docs/templates/frontend-eval/metrics.md +138 -0
  101. package/docs/templates/frontend-eval/smoke-targets.md +53 -0
  102. package/docs/templates/frontend-implementation-contract.schema.json +27 -0
  103. package/docs/templates/frontend-task-constraints.md +10 -0
  104. package/docs/templates/frontend-task-requirement.md +9 -0
  105. package/docs/templates/frontend-test-dag.generate-cases.prompt.md +5 -0
  106. package/docs/templates/frontend-test-dag.json +23 -0
  107. package/docs/templates/frontend-test-dag.retrieve-context.prompt.md +3 -0
  108. package/docs/templates/frontend-test-dag.retrospect.prompt.md +3 -0
  109. package/docs/templates/frontend-test-dag.review-cases.prompt.md +3 -0
  110. package/docs/templates/frontend-test-dag.review-execution.prompt.md +3 -0
  111. package/docs/templates/knowledge-graph-bootstrap-dag.json +1 -1
  112. package/docs/templates/knowledge-sync-dag.json +1 -0
  113. package/docs/verification-matrix.md +4 -1
  114. package/examples/decision-gate-agent-dag.json +4 -4
  115. package/examples/hybrid-loop-agent-dag.json +1 -1
  116. package/package.json +2 -2
  117. package/scripts/kb-bootstrap-init-skeleton.sh +2 -1
  118. package/scripts/kb-graph-incremental-prepare.mjs +19 -5
  119. package/scripts/kb-graph-promote.mjs +12 -1
  120. package/skills/ai-engineering-context/SKILL.md +2 -2
  121. package/skills/analyze-product-dependencies/SKILL.md +67 -0
  122. package/skills/analyze-product-dependencies/agents/openai.yaml +4 -0
  123. package/skills/analyze-product-dependencies/references/api-documentation-schema.md +30 -0
  124. package/skills/analyze-product-dependencies/references/dependency-analysis-schema.md +28 -0
  125. package/skills/analyze-product-dependencies/references/example.md +76 -0
  126. package/skills/analyze-product-dependencies/references/forward-test-cases.md +35 -0
  127. package/skills/analyze-product-dependencies/references/input-contract.md +11 -0
  128. package/skills/analyze-product-dependencies/references/scouting-rules.md +61 -0
  129. package/skills/analyze-product-dependencies/scripts/test-validators.mjs +267 -0
  130. package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +101 -0
  131. package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +142 -0
  132. package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +76 -0
  133. package/skills/analyze-product-dependencies/scripts/validation-helpers.mjs +146 -0
  134. package/skills/analyze-product-requirements/SKILL.md +90 -0
  135. package/skills/analyze-product-requirements/agents/openai.yaml +4 -0
  136. package/skills/analyze-product-requirements/references/acceptance-criteria.md +91 -0
  137. package/skills/analyze-product-requirements/references/clarification-and-knowledge.md +56 -0
  138. package/skills/analyze-product-requirements/references/example.md +86 -0
  139. package/skills/analyze-product-requirements/references/forward-test-cases.md +66 -0
  140. package/skills/analyze-product-requirements/references/product-analysis-schema.md +32 -0
  141. package/skills/analyze-product-requirements/references/product-requirement-schema.md +33 -0
  142. package/skills/analyze-product-requirements/references/requirement-clarification-schema.md +35 -0
  143. package/skills/analyze-product-requirements/scripts/test-validators.mjs +193 -0
  144. package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +69 -0
  145. package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +97 -0
  146. package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +98 -0
  147. package/skills/analyze-product-requirements/scripts/validation-helpers.mjs +156 -0
  148. package/skills/browser-tools/SKILL.md +196 -0
  149. package/skills/browser-tools/browser-content.js +103 -0
  150. package/skills/browser-tools/browser-cookies.js +35 -0
  151. package/skills/browser-tools/browser-eval.js +53 -0
  152. package/skills/browser-tools/browser-hn-scraper.js +108 -0
  153. package/skills/browser-tools/browser-nav.js +44 -0
  154. package/skills/browser-tools/browser-pick.js +162 -0
  155. package/skills/browser-tools/browser-screenshot.js +34 -0
  156. package/skills/browser-tools/browser-start.js +86 -0
  157. package/skills/browser-tools/package-lock.json +2556 -0
  158. package/skills/browser-tools/package.json +19 -0
  159. package/skills/frontend-design-review/SKILL.md +6 -1
  160. package/skills/frontend-design-review/references/review-checklist.md +25 -4
  161. package/skills/frontend-implementation/SKILL.md +25 -30
  162. package/skills/frontend-implementation/references/code-standards.md +20 -22
  163. package/skills/frontend-implementation/references/node-contracts.md +17 -53
  164. package/skills/frontend-review/SKILL.md +10 -4
  165. package/skills/frontend-review/references/review-findings.md +8 -3
  166. package/skills/frontend-verification/SKILL.md +22 -9
  167. package/skills/frontend-verification/references/verification-checklist.md +17 -5
  168. package/skills/grill-with-docs/SKILL.md +5 -5
  169. package/skills/grill-with-docs/adr-format.md +3 -3
  170. package/skills/init-capability-evolution/SKILL.md +5 -5
  171. package/skills/loop-agent/SKILL.md +5 -5
  172. package/skills/loop-agent/references/README.md +3 -3
  173. package/skills/loop-agent/references/command-reference.md +98 -24
  174. package/skills/loop-agent/references/docs-converge.md +15 -15
  175. package/skills/loop-agent/references/harness-policy.md +2 -2
  176. package/skills/loop-agent/references/hybrid-dag.md +32 -22
  177. package/skills/loop-agent/references/multi-worktree.md +1 -1
  178. package/skills/loop-agent/references/orchestrator-and-interventions.md +8 -8
  179. package/skills/loop-agent/references/task-workflow.md +1 -1
  180. package/skills/loop-agent/references/verification-and-failure-handling.md +6 -4
  181. package/skills/playwright-cli/SKILL.md +420 -0
  182. package/skills/playwright-cli/references/element-attributes.md +23 -0
  183. package/skills/playwright-cli/references/playwright-tests.md +39 -0
  184. package/skills/playwright-cli/references/request-mocking.md +87 -0
  185. package/skills/playwright-cli/references/running-code.md +241 -0
  186. package/skills/playwright-cli/references/session-management.md +225 -0
  187. package/skills/playwright-cli/references/storage-state.md +275 -0
  188. package/skills/playwright-cli/references/test-generation.md +433 -0
  189. package/skills/playwright-cli/references/tracing.md +139 -0
  190. package/skills/playwright-cli/references/video-recording.md +143 -0
  191. package/skills/playwright-cli-case-generator/SKILL.md +74 -0
  192. package/skills/requesting-code-review/SKILL.md +1 -1
  193. package/skills/systematic-debugging/CREATION-LOG.md +3 -3
  194. package/skills/systematic-debugging/SKILL.md +1 -1
  195. package/skills/systematic-debugging/test-academic.md +1 -1
  196. package/skills/systematic-debugging/test-pressure-1.md +1 -1
  197. package/skills/systematic-debugging/test-pressure-2.md +1 -1
  198. package/skills/systematic-debugging/test-pressure-3.md +1 -1
  199. package/skills/verification-before-completion/SKILL.md +1 -1
@@ -0,0 +1,34 @@
1
+ #!/usr/bin/env node
2
+
3
+ import { tmpdir } from "node:os";
4
+ import { join } from "node:path";
5
+ import puppeteer from "puppeteer-core";
6
+
7
+ const b = await Promise.race([
8
+ puppeteer.connect({
9
+ browserURL: "http://localhost:9222",
10
+ defaultViewport: null,
11
+ }),
12
+ new Promise((_, reject) => setTimeout(() => reject(new Error("timeout")), 5000)),
13
+ ]).catch((e) => {
14
+ console.error("✗ Could not connect to browser:", e.message);
15
+ console.error(" Run: browser-start.js");
16
+ process.exit(1);
17
+ });
18
+
19
+ const p = (await b.pages()).at(-1);
20
+
21
+ if (!p) {
22
+ console.error("✗ No active tab found");
23
+ process.exit(1);
24
+ }
25
+
26
+ const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
27
+ const filename = `screenshot-${timestamp}.png`;
28
+ const filepath = join(tmpdir(), filename);
29
+
30
+ await p.screenshot({ path: filepath });
31
+
32
+ console.log(filepath);
33
+
34
+ await b.disconnect();
@@ -0,0 +1,86 @@
1
+ #!/usr/bin/env node
2
+
3
+ import { spawn, execSync } from "node:child_process";
4
+ import puppeteer from "puppeteer-core";
5
+
6
+ const useProfile = process.argv[2] === "--profile";
7
+
8
+ if (process.argv[2] && process.argv[2] !== "--profile") {
9
+ console.log("Usage: browser-start.js [--profile]");
10
+ console.log("\nOptions:");
11
+ console.log(" --profile Copy your default Chrome profile (cookies, logins)");
12
+ process.exit(1);
13
+ }
14
+
15
+ const SCRAPING_DIR = `${process.env.HOME}/.cache/browser-tools`;
16
+
17
+ // Check if already running on :9222
18
+ try {
19
+ const browser = await puppeteer.connect({
20
+ browserURL: "http://localhost:9222",
21
+ defaultViewport: null,
22
+ });
23
+ await browser.disconnect();
24
+ console.log("✓ Chrome already running on :9222");
25
+ process.exit(0);
26
+ } catch {}
27
+
28
+ // Setup profile directory
29
+ execSync(`mkdir -p "${SCRAPING_DIR}"`, { stdio: "ignore" });
30
+
31
+ // Remove SingletonLock to allow new instance
32
+ try {
33
+ execSync(`rm -f "${SCRAPING_DIR}/SingletonLock" "${SCRAPING_DIR}/SingletonSocket" "${SCRAPING_DIR}/SingletonCookie"`, { stdio: "ignore" });
34
+ } catch {}
35
+
36
+ if (useProfile) {
37
+ console.log("Syncing profile...");
38
+ execSync(
39
+ `rsync -a --delete \
40
+ --exclude='SingletonLock' \
41
+ --exclude='SingletonSocket' \
42
+ --exclude='SingletonCookie' \
43
+ --exclude='*/Sessions/*' \
44
+ --exclude='*/Current Session' \
45
+ --exclude='*/Current Tabs' \
46
+ --exclude='*/Last Session' \
47
+ --exclude='*/Last Tabs' \
48
+ "${process.env.HOME}/Library/Application Support/Google/Chrome/" "${SCRAPING_DIR}/"`,
49
+ { stdio: "pipe" },
50
+ );
51
+ }
52
+
53
+ // Start Chrome with flags to force new instance
54
+ spawn(
55
+ "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome",
56
+ [
57
+ "--remote-debugging-port=9222",
58
+ `--user-data-dir=${SCRAPING_DIR}`,
59
+ "--no-first-run",
60
+ "--no-default-browser-check",
61
+ ],
62
+ { detached: true, stdio: "ignore" },
63
+ ).unref();
64
+
65
+ // Wait for Chrome to be ready
66
+ let connected = false;
67
+ for (let i = 0; i < 30; i++) {
68
+ try {
69
+ const browser = await puppeteer.connect({
70
+ browserURL: "http://localhost:9222",
71
+ defaultViewport: null,
72
+ });
73
+ await browser.disconnect();
74
+ connected = true;
75
+ break;
76
+ } catch {
77
+ await new Promise((r) => setTimeout(r, 500));
78
+ }
79
+ }
80
+
81
+ if (!connected) {
82
+ console.error("✗ Failed to connect to Chrome");
83
+ process.exit(1);
84
+ }
85
+
86
+ console.log(`✓ Chrome started on :9222${useProfile ? " with your profile" : ""}`);