@tea-agent/loop-agent 0.5.0 → 0.7.0

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 (136) hide show
  1. package/AGENTS.md +142 -142
  2. package/CHANGELOG.md +132 -98
  3. package/README.md +195 -195
  4. package/bin/agent-worker.js +22 -22
  5. package/bin/loop-agent.js +21 -21
  6. package/dist/application/dag/args.js +9 -1
  7. package/dist/application/dag/run-dag.js +16 -2
  8. package/dist/cli/command-definitions.js +22 -4
  9. package/dist/cli/help.js +3 -2
  10. package/dist/cli/program.js +7 -5
  11. package/dist/commands/import-prd.js +76 -0
  12. package/dist/commands/init.js +467 -457
  13. package/dist/commands/instructions.js +90 -58
  14. package/dist/commands/loop-benchmark.js +11 -11
  15. package/dist/commands/pi-reuse-benchmark.js +16 -16
  16. package/dist/executors/cursor-executor.js +1 -1
  17. package/dist/executors/dag-pi-executor.js +1 -0
  18. package/dist/executors/pi-sdk-executor.js +63 -1
  19. package/dist/shared/preview.js +39 -0
  20. package/dist/task/config-types.js +3 -0
  21. package/dist/task/runtime.js +27 -27
  22. package/dist/task/source-references.js +221 -0
  23. package/dist/worker/cli.js +62 -1
  24. package/dist/worker/loop-agent/loop-agent-client.js +97 -5
  25. package/dist/worker/materialize/harness-task-materializer.js +166 -5
  26. package/dist/worker/observability/event-store.js +82 -0
  27. package/dist/worker/observability/events.js +79 -0
  28. package/dist/worker/observability/progress-composite.js +33 -0
  29. package/dist/worker/observability/read-model.js +1013 -0
  30. package/dist/worker/observability/snapshot-store.js +43 -0
  31. package/dist/worker/observability/types.js +1 -0
  32. package/dist/worker/observe/paths.js +64 -0
  33. package/dist/worker/observe/routes.js +423 -0
  34. package/dist/worker/observe/server.js +61 -0
  35. package/dist/worker/observe/static/app.js +1419 -0
  36. package/dist/worker/observe/static/index.html +63 -0
  37. package/dist/worker/observe/static/styles.css +613 -0
  38. package/dist/worker/pool/failure-routing.js +41 -6
  39. package/dist/worker/pool/run-store.js +50 -0
  40. package/dist/worker/progress-reporter.js +0 -18
  41. package/dist/worker/run-task/run-task.js +327 -92
  42. package/dist/worker/runner/run-ready.js +112 -4
  43. package/dist/worker/task-spec/schema.js +2 -1
  44. package/dist/workflows/dag/canvas-observer.js +275 -275
  45. package/dist/workflows/dag/event-observer.js +132 -0
  46. package/dist/workflows/dag/init-hybrid.js +182 -21
  47. package/dist/workflows/dag/observer-compose.js +52 -0
  48. package/docs/README.md +75 -72
  49. package/docs/agent-dag-recovery-playbook.md +184 -184
  50. package/docs/agent-dag-runner.md +42 -42
  51. package/docs/architecture/runtime-boundaries.md +162 -147
  52. package/docs/cursor-executor-usage.md +25 -25
  53. package/docs/decisions/README.md +3 -3
  54. package/docs/design/README.md +49 -36
  55. package/docs/development-principles.md +73 -73
  56. package/docs/dynamic-workflow-dag-engine-roadmap.md +1749 -1749
  57. package/docs/exec-plans/README.md +6 -6
  58. package/docs/exec-plans/active/README.md +12 -7
  59. package/docs/exec-plans/completed/README.md +32 -19
  60. package/docs/feature-workflow.md +186 -186
  61. package/docs/harness-methodology-debugging.md +153 -153
  62. package/docs/harness-methodology-tdd.md +130 -130
  63. package/docs/harness-methodology-verification.md +27 -27
  64. package/docs/init-surface.manifest.json +208 -199
  65. package/docs/loop-agent-harness.md +55 -42
  66. package/docs/production-readiness.md +96 -96
  67. package/docs/progress/README.md +3 -3
  68. package/docs/reports/README.md +9 -5
  69. package/docs/skills/README.md +6 -6
  70. package/docs/skills/vetted-skill-registry.md +26 -26
  71. package/docs/templates/adr.md +60 -60
  72. package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
  73. package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
  74. package/docs/templates/agent-dag-decision-gate-dogfood-report.md +117 -117
  75. package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
  76. package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
  77. package/docs/templates/agent-dag-report.schema.json +454 -454
  78. package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
  79. package/docs/templates/agent-dag.base.json +195 -195
  80. package/docs/templates/agent-dag.final-verification.json +190 -190
  81. package/docs/templates/agent-dag.schema.json +316 -316
  82. package/docs/templates/agent-dag.supervised-implementation.json +500 -500
  83. package/docs/templates/exec-plan.md +64 -64
  84. package/docs/templates/feature-spec.md +53 -53
  85. package/docs/templates/hybrid-dag.json +193 -193
  86. package/docs/templates/init-evolution-review.md +33 -33
  87. package/docs/templates/interactive-ui-round2-experiment.md +66 -0
  88. package/docs/templates/production-readiness-checklist.md +57 -57
  89. package/docs/templates/progress-log.md +17 -17
  90. package/docs/templates/project-start-checklist.md +9 -9
  91. package/docs/templates/qa-report.md +48 -48
  92. package/docs/templates/sprint-contract.md +29 -29
  93. package/docs/templates/worker-dogfood-evidence.md +52 -0
  94. package/docs/templates/worker-dogfood-setup.md +48 -0
  95. package/docs/verification-matrix.md +41 -41
  96. package/examples/decision-gate-agent-dag.json +123 -123
  97. package/examples/example-dag.json +51 -51
  98. package/examples/hybrid-loop-agent-dag.json +194 -194
  99. package/harness.json +70 -69
  100. package/package.json +66 -66
  101. package/skills/ai-engineering-context/SKILL.md +48 -48
  102. package/skills/code-review-core/SKILL.md +20 -20
  103. package/skills/codebase-scout/SKILL.md +19 -19
  104. package/skills/init-capability-evolution/SKILL.md +69 -69
  105. package/skills/loop-agent/SKILL.md +149 -147
  106. package/skills/loop-agent/references/README.md +67 -67
  107. package/skills/loop-agent/references/command-reference.md +412 -403
  108. package/skills/loop-agent/references/harness-policy.md +263 -259
  109. package/skills/loop-agent/references/hybrid-dag.md +216 -216
  110. package/skills/loop-agent/references/learned/README.md +21 -21
  111. package/skills/loop-agent/references/long-running-loop.md +59 -59
  112. package/skills/loop-agent/references/model-routing.md +36 -36
  113. package/skills/loop-agent/references/multi-worktree.md +54 -54
  114. package/skills/loop-agent/references/one-shot-runs.md +85 -85
  115. package/skills/loop-agent/references/orchestrator-and-interventions.md +169 -169
  116. package/skills/loop-agent/references/pi-prompt.md +23 -23
  117. package/skills/loop-agent/references/pi-subagent-assisted-mode.md +81 -81
  118. package/skills/loop-agent/references/post-implementation-and-patterns.md +44 -44
  119. package/skills/loop-agent/references/task-workflow.md +89 -84
  120. package/skills/loop-agent/references/verification-and-failure-handling.md +128 -128
  121. package/skills/requesting-code-review/SKILL.md +101 -101
  122. package/skills/requesting-code-review/code-reviewer.md +168 -168
  123. package/skills/systematic-debugging/CREATION-LOG.md +119 -119
  124. package/skills/systematic-debugging/SKILL.md +296 -296
  125. package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
  126. package/skills/systematic-debugging/condition-based-waiting.md +115 -115
  127. package/skills/systematic-debugging/defense-in-depth.md +122 -122
  128. package/skills/systematic-debugging/find-polluter.sh +63 -63
  129. package/skills/systematic-debugging/root-cause-tracing.md +169 -169
  130. package/skills/systematic-debugging/test-academic.md +14 -14
  131. package/skills/systematic-debugging/test-pressure-1.md +58 -58
  132. package/skills/systematic-debugging/test-pressure-2.md +68 -68
  133. package/skills/systematic-debugging/test-pressure-3.md +69 -69
  134. package/skills/test-driven-development/SKILL.md +20 -20
  135. package/skills/verification-before-completion/SKILL.md +154 -154
  136. package/skills/webapp-testing/SKILL.md +19 -19
@@ -1,122 +1,122 @@
1
- # Defense-in-Depth Validation
2
-
3
- ## Overview
4
-
5
- Bug 由 invalid data 引起时,在一处加 validation 感觉足够。但 single check 可被不同 code paths、refactoring 或 mocks 绕过。
6
-
7
- **Core principle:** 在 data 经过的 EVERY layer 验证。使 bug structurally impossible。
8
-
9
- ## Why Multiple Layers
10
-
11
- Single validation:"We fixed the bug"
12
- Multiple layers:"We made the bug impossible"
13
-
14
- 不同 layers 捕获不同 cases:
15
- - Entry validation 捕获 most bugs
16
- - Business logic 捕获 edge cases
17
- - Environment guards 防止 context-specific dangers
18
- - Debug logging 在其他 layers fail 时帮助 forensics
19
-
20
- ## The Four Layers
21
-
22
- ### Layer 1: Entry Point Validation
23
- **Purpose:** 在 API boundary 拒绝 obviously invalid input
24
-
25
- ```typescript
26
- function createProject(name: string, workingDirectory: string) {
27
- if (!workingDirectory || workingDirectory.trim() === '') {
28
- throw new Error('workingDirectory cannot be empty');
29
- }
30
- if (!existsSync(workingDirectory)) {
31
- throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
32
- }
33
- if (!statSync(workingDirectory).isDirectory()) {
34
- throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
35
- }
36
- // ... proceed
37
- }
38
- ```
39
-
40
- ### Layer 2: Business Logic Validation
41
- **Purpose:** 确保 data 对此 operation 有意义
42
-
43
- ```typescript
44
- function initializeWorkspace(projectDir: string, sessionId: string) {
45
- if (!projectDir) {
46
- throw new Error('projectDir required for workspace initialization');
47
- }
48
- // ... proceed
49
- }
50
- ```
51
-
52
- ### Layer 3: Environment Guards
53
- **Purpose:** 在特定 contexts 阻止 dangerous operations
54
-
55
- ```typescript
56
- async function gitInit(directory: string) {
57
- // In tests, refuse git init outside temp directories
58
- if (process.env.NODE_ENV === 'test') {
59
- const normalized = normalize(resolve(directory));
60
- const tmpDir = normalize(resolve(tmpdir()));
61
-
62
- if (!normalized.startsWith(tmpDir)) {
63
- throw new Error(
64
- `Refusing git init outside temp dir during tests: ${directory}`
65
- );
66
- }
67
- }
68
- // ... proceed
69
- }
70
- ```
71
-
72
- ### Layer 4: Debug Instrumentation
73
- **Purpose:** 捕获 forensics context
74
-
75
- ```typescript
76
- async function gitInit(directory: string) {
77
- const stack = new Error().stack;
78
- logger.debug('About to git init', {
79
- directory,
80
- cwd: process.cwd(),
81
- stack,
82
- });
83
- // ... proceed
84
- }
85
- ```
86
-
87
- ## Applying the Pattern
88
-
89
- 找到 bug 时:
90
-
91
- 1. **Trace the data flow** — Bad value 从哪 originate?在哪使用?
92
- 2. **Map all checkpoints** — 列出 data 经过的 every point
93
- 3. **Add validation at each layer** — Entry、business、environment、debug
94
- 4. **Test each layer** — 尝试 bypass layer 1,verify layer 2 捕获
95
-
96
- ## Example from Session
97
-
98
- Bug:Empty `projectDir` 导致 `git init` 在 source code
99
-
100
- **Data flow:**
101
- 1. Test setup → empty string
102
- 2. `Project.create(name, '')`
103
- 3. `WorkspaceManager.createWorkspace('')`
104
- 4. `git init` 在 `process.cwd()` 运行
105
-
106
- **Four layers added:**
107
- - Layer 1: `Project.create()` validates not empty/exists/writable
108
- - Layer 2: `WorkspaceManager` validates projectDir not empty
109
- - Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
110
- - Layer 4: Stack trace logging before git init
111
-
112
- **Result:** All 1847 tests passed,bug impossible to reproduce
113
-
114
- ## Key Insight
115
-
116
- 四层都必要。Testing 中每层捕获 others 遗漏的 bugs:
117
- - 不同 code paths 绕过 entry validation
118
- - Mocks 绕过 business logic checks
119
- - 不同 platforms 的 edge cases 需要 environment guards
120
- - Debug logging 识别 structural misuse
121
-
122
- **Don't stop at one validation point.** 在 every layer 加 checks。
1
+ # Defense-in-Depth Validation
2
+
3
+ ## Overview
4
+
5
+ Bug 由 invalid data 引起时,在一处加 validation 感觉足够。但 single check 可被不同 code paths、refactoring 或 mocks 绕过。
6
+
7
+ **Core principle:** 在 data 经过的 EVERY layer 验证。使 bug structurally impossible。
8
+
9
+ ## Why Multiple Layers
10
+
11
+ Single validation:"We fixed the bug"
12
+ Multiple layers:"We made the bug impossible"
13
+
14
+ 不同 layers 捕获不同 cases:
15
+ - Entry validation 捕获 most bugs
16
+ - Business logic 捕获 edge cases
17
+ - Environment guards 防止 context-specific dangers
18
+ - Debug logging 在其他 layers fail 时帮助 forensics
19
+
20
+ ## The Four Layers
21
+
22
+ ### Layer 1: Entry Point Validation
23
+ **Purpose:** 在 API boundary 拒绝 obviously invalid input
24
+
25
+ ```typescript
26
+ function createProject(name: string, workingDirectory: string) {
27
+ if (!workingDirectory || workingDirectory.trim() === '') {
28
+ throw new Error('workingDirectory cannot be empty');
29
+ }
30
+ if (!existsSync(workingDirectory)) {
31
+ throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
32
+ }
33
+ if (!statSync(workingDirectory).isDirectory()) {
34
+ throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
35
+ }
36
+ // ... proceed
37
+ }
38
+ ```
39
+
40
+ ### Layer 2: Business Logic Validation
41
+ **Purpose:** 确保 data 对此 operation 有意义
42
+
43
+ ```typescript
44
+ function initializeWorkspace(projectDir: string, sessionId: string) {
45
+ if (!projectDir) {
46
+ throw new Error('projectDir required for workspace initialization');
47
+ }
48
+ // ... proceed
49
+ }
50
+ ```
51
+
52
+ ### Layer 3: Environment Guards
53
+ **Purpose:** 在特定 contexts 阻止 dangerous operations
54
+
55
+ ```typescript
56
+ async function gitInit(directory: string) {
57
+ // In tests, refuse git init outside temp directories
58
+ if (process.env.NODE_ENV === 'test') {
59
+ const normalized = normalize(resolve(directory));
60
+ const tmpDir = normalize(resolve(tmpdir()));
61
+
62
+ if (!normalized.startsWith(tmpDir)) {
63
+ throw new Error(
64
+ `Refusing git init outside temp dir during tests: ${directory}`
65
+ );
66
+ }
67
+ }
68
+ // ... proceed
69
+ }
70
+ ```
71
+
72
+ ### Layer 4: Debug Instrumentation
73
+ **Purpose:** 捕获 forensics context
74
+
75
+ ```typescript
76
+ async function gitInit(directory: string) {
77
+ const stack = new Error().stack;
78
+ logger.debug('About to git init', {
79
+ directory,
80
+ cwd: process.cwd(),
81
+ stack,
82
+ });
83
+ // ... proceed
84
+ }
85
+ ```
86
+
87
+ ## Applying the Pattern
88
+
89
+ 找到 bug 时:
90
+
91
+ 1. **Trace the data flow** — Bad value 从哪 originate?在哪使用?
92
+ 2. **Map all checkpoints** — 列出 data 经过的 every point
93
+ 3. **Add validation at each layer** — Entry、business、environment、debug
94
+ 4. **Test each layer** — 尝试 bypass layer 1,verify layer 2 捕获
95
+
96
+ ## Example from Session
97
+
98
+ Bug:Empty `projectDir` 导致 `git init` 在 source code
99
+
100
+ **Data flow:**
101
+ 1. Test setup → empty string
102
+ 2. `Project.create(name, '')`
103
+ 3. `WorkspaceManager.createWorkspace('')`
104
+ 4. `git init` 在 `process.cwd()` 运行
105
+
106
+ **Four layers added:**
107
+ - Layer 1: `Project.create()` validates not empty/exists/writable
108
+ - Layer 2: `WorkspaceManager` validates projectDir not empty
109
+ - Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
110
+ - Layer 4: Stack trace logging before git init
111
+
112
+ **Result:** All 1847 tests passed,bug impossible to reproduce
113
+
114
+ ## Key Insight
115
+
116
+ 四层都必要。Testing 中每层捕获 others 遗漏的 bugs:
117
+ - 不同 code paths 绕过 entry validation
118
+ - Mocks 绕过 business logic checks
119
+ - 不同 platforms 的 edge cases 需要 environment guards
120
+ - Debug logging 识别 structural misuse
121
+
122
+ **Don't stop at one validation point.** 在 every layer 加 checks。
@@ -1,63 +1,63 @@
1
- #!/usr/bin/env bash
2
- # Bisection script to find which test creates unwanted files/state
3
- # Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
4
- # Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
5
-
6
- set -e
7
-
8
- if [ $# -ne 2 ]; then
9
- echo "Usage: $0 <file_to_check> <test_pattern>"
10
- echo "Example: $0 '.git' 'src/**/*.test.ts'"
11
- exit 1
12
- fi
13
-
14
- POLLUTION_CHECK="$1"
15
- TEST_PATTERN="$2"
16
-
17
- echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
18
- echo "Test pattern: $TEST_PATTERN"
19
- echo ""
20
-
21
- # Get list of test files
22
- TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
23
- TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
24
-
25
- echo "Found $TOTAL test files"
26
- echo ""
27
-
28
- COUNT=0
29
- for TEST_FILE in $TEST_FILES; do
30
- COUNT=$((COUNT + 1))
31
-
32
- # Skip if pollution already exists
33
- if [ -e "$POLLUTION_CHECK" ]; then
34
- echo "⚠️ Pollution already exists before test $COUNT/$TOTAL"
35
- echo " Skipping: $TEST_FILE"
36
- continue
37
- fi
38
-
39
- echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
40
-
41
- # Run the test
42
- npm test "$TEST_FILE" > /dev/null 2>&1 || true
43
-
44
- # Check if pollution appeared
45
- if [ -e "$POLLUTION_CHECK" ]; then
46
- echo ""
47
- echo "🎯 FOUND POLLUTER!"
48
- echo " Test: $TEST_FILE"
49
- echo " Created: $POLLUTION_CHECK"
50
- echo ""
51
- echo "Pollution details:"
52
- ls -la "$POLLUTION_CHECK"
53
- echo ""
54
- echo "To investigate:"
55
- echo " npm test $TEST_FILE # Run just this test"
56
- echo " cat $TEST_FILE # Review test code"
57
- exit 1
58
- fi
59
- done
60
-
61
- echo ""
62
- echo "✅ No polluter found - all tests clean!"
63
- exit 0
1
+ #!/usr/bin/env bash
2
+ # Bisection script to find which test creates unwanted files/state
3
+ # Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
4
+ # Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
5
+
6
+ set -e
7
+
8
+ if [ $# -ne 2 ]; then
9
+ echo "Usage: $0 <file_to_check> <test_pattern>"
10
+ echo "Example: $0 '.git' 'src/**/*.test.ts'"
11
+ exit 1
12
+ fi
13
+
14
+ POLLUTION_CHECK="$1"
15
+ TEST_PATTERN="$2"
16
+
17
+ echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
18
+ echo "Test pattern: $TEST_PATTERN"
19
+ echo ""
20
+
21
+ # Get list of test files
22
+ TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
23
+ TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
24
+
25
+ echo "Found $TOTAL test files"
26
+ echo ""
27
+
28
+ COUNT=0
29
+ for TEST_FILE in $TEST_FILES; do
30
+ COUNT=$((COUNT + 1))
31
+
32
+ # Skip if pollution already exists
33
+ if [ -e "$POLLUTION_CHECK" ]; then
34
+ echo "⚠️ Pollution already exists before test $COUNT/$TOTAL"
35
+ echo " Skipping: $TEST_FILE"
36
+ continue
37
+ fi
38
+
39
+ echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
40
+
41
+ # Run the test
42
+ npm test "$TEST_FILE" > /dev/null 2>&1 || true
43
+
44
+ # Check if pollution appeared
45
+ if [ -e "$POLLUTION_CHECK" ]; then
46
+ echo ""
47
+ echo "🎯 FOUND POLLUTER!"
48
+ echo " Test: $TEST_FILE"
49
+ echo " Created: $POLLUTION_CHECK"
50
+ echo ""
51
+ echo "Pollution details:"
52
+ ls -la "$POLLUTION_CHECK"
53
+ echo ""
54
+ echo "To investigate:"
55
+ echo " npm test $TEST_FILE # Run just this test"
56
+ echo " cat $TEST_FILE # Review test code"
57
+ exit 1
58
+ fi
59
+ done
60
+
61
+ echo ""
62
+ echo "✅ No polluter found - all tests clean!"
63
+ exit 0