@tea-agent/loop-agent 0.35.1-beta.0 → 0.35.1-beta.1

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 (168) hide show
  1. package/AGENTS.md +110 -108
  2. package/CHANGELOG.md +16 -26
  3. package/README.md +165 -165
  4. package/bin/agent-worker.js +0 -0
  5. package/bin/loop-agent.js +57 -21
  6. package/dist/application/task-lifecycle/advance.js +0 -1
  7. package/dist/build-stamp.json +6 -0
  8. package/dist/cli/program.js +2 -2
  9. package/dist/commands/cursor-prompt.js +6 -6
  10. package/dist/commands/init-upgrade.js +19 -351
  11. package/dist/commands/init.js +67 -14
  12. package/dist/commands/loop-benchmark.js +11 -11
  13. package/dist/commands/pi-reuse-benchmark.js +16 -16
  14. package/dist/commands/run-dag-progress.js +0 -14
  15. package/dist/commands/task-advance.js +3 -33
  16. package/dist/shared/operator/capabilities.js +1 -38
  17. package/dist/shared/package-metadata.js +32 -0
  18. package/dist/sidecars/cursor-prompt/executor.js +1 -1
  19. package/dist/worker/console/chat/pi-runtime.js +25 -41
  20. package/dist/worker/console/chat/routes.js +4 -27
  21. package/dist/worker/console/operation-runner.js +0 -24
  22. package/dist/worker/console/operator-actions.js +0 -58
  23. package/dist/worker/console/static/assets/index-fsjzREob.js +56 -0
  24. package/dist/worker/console/static/assets/{index-Dups4sSM.css → index-hJqCPs_g.css} +1 -1
  25. package/dist/worker/console/static/index.html +2 -2
  26. package/dist/worker/console/static-src/operator-chat/useChatSessions.js +2 -13
  27. package/dist/worker/console/static-src/operator-chat/useComposer.js +7 -30
  28. package/dist/worker/loop-agent/loop-agent-client.js +13 -0
  29. package/dist/worker/observe/static/copy.js +67 -67
  30. package/dist/worker/observe/static/dag-layout.d.ts +36 -36
  31. package/dist/worker/observe/static/dom.js +220 -220
  32. package/dist/worker/observe/static/relations.js +133 -133
  33. package/dist/worker/observe/static/run-processing.js +148 -148
  34. package/dist/worker/observe/static/views/batch.js +227 -227
  35. package/dist/worker/observe/static/views/failures.js +143 -143
  36. package/dist/worker/observe/static/views/feature.js +492 -492
  37. package/dist/worker/observe/static/views/run.js +453 -453
  38. package/dist/worker/observe/static/views/shell.js +7 -7
  39. package/dist/worker/observe/static/views/timeline.js +163 -163
  40. package/dist/workflows/dag/canvas-observer.js +275 -275
  41. package/dist/workflows/dag/contract-output-registry.js +14 -0
  42. package/dist/workflows/dag/contract-validator-registrations.js +8 -0
  43. package/dist/workflows/dag/dynamic-runtime/shared.js +9 -1
  44. package/dist/workflows/dag/frontend-implementation-contract.js +233 -39
  45. package/dist/workflows/dag/frontend-prewrite-gate.js +364 -61
  46. package/dist/workflows/dag/frontend-repair.js +219 -18
  47. package/dist/workflows/dag/frontend-verification-trace.js +47 -32
  48. package/dist/workflows/dag/init-hybrid.js +41 -24
  49. package/dist/workflows/dag/node-execution.js +89 -0
  50. package/dist/workflows/dag/runner.js +52 -3
  51. package/dist/workflows/dag/scheduler.js +98 -3
  52. package/dist/workflows/dag/types.js +23 -2
  53. package/docs/architecture/evolution.md +73 -73
  54. package/docs/architecture/system-overview.md +100 -100
  55. package/docs/architecture/worker-and-feature.md +122 -122
  56. package/docs/skills/README.md +7 -7
  57. package/docs/templates/adr.md +60 -60
  58. package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
  59. package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
  60. package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
  61. package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
  62. package/docs/templates/agent-dag-report.schema.json +473 -473
  63. package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
  64. package/docs/templates/backend-test-result.schema.json +99 -99
  65. package/docs/templates/evaluation/agents-map-slim-v1.md +87 -87
  66. package/docs/templates/evaluation/agents-map-verbose-v0.md +153 -153
  67. package/docs/templates/feature-spec.md +53 -53
  68. package/docs/templates/frontend-design-contract.md +42 -42
  69. package/docs/templates/frontend-eval/fixtures/failures/01-type-build-error.md +17 -17
  70. package/docs/templates/frontend-eval/fixtures/failures/02-unit-component-test-fail.md +16 -16
  71. package/docs/templates/frontend-eval/fixtures/failures/03-fixture-schema-drift.md +16 -16
  72. package/docs/templates/frontend-eval/fixtures/failures/04-missing-loading-empty-error-state.md +16 -16
  73. package/docs/templates/frontend-eval/fixtures/failures/05-forbidden-write-writeset-expansion.md +16 -16
  74. package/docs/templates/frontend-eval/fixtures/failures/06-unapproved-dependency-add.md +16 -16
  75. package/docs/templates/frontend-eval/fixtures/failures/07-mock-production-on.md +21 -21
  76. package/docs/templates/frontend-eval/fixtures/functional/01-simple-component-style.md +29 -29
  77. package/docs/templates/frontend-eval/fixtures/functional/02-form-validation.md +28 -28
  78. package/docs/templates/frontend-eval/fixtures/functional/03-list-detail-page.md +28 -28
  79. package/docs/templates/frontend-eval/fixtures/functional/04-api-mock.md +29 -29
  80. package/docs/templates/frontend-eval/fixtures/functional/05-permission-auth-gated-ui.md +27 -27
  81. package/docs/templates/frontend-eval/fixtures/functional/06-ssr-server-client-boundary.md +28 -28
  82. package/docs/templates/frontend-eval/fixtures/functional/07-shared-public-component-api.md +28 -28
  83. package/docs/templates/frontend-eval/fixtures/functional/08-pure-local-no-remote.md +27 -27
  84. package/docs/templates/frontend-eval/metrics.md +138 -138
  85. package/docs/templates/frontend-eval/smoke-targets.md +53 -53
  86. package/docs/templates/frontend-task-constraints.md +35 -35
  87. package/docs/templates/frontend-task-requirement.md +70 -70
  88. package/docs/templates/init-evolution-review.md +35 -35
  89. package/docs/templates/init-managed-agents.md +154 -156
  90. package/docs/templates/interactive-ui-round2-experiment.md +66 -66
  91. package/docs/templates/knowledge-graph-bootstrap-dag.json +118 -118
  92. package/docs/templates/knowledge-sync-dag.json +178 -178
  93. package/docs/templates/knowledge-sync-draft.schema.json +71 -71
  94. package/docs/templates/product-line/closeout.yaml +9 -9
  95. package/docs/templates/product-line/design.md +13 -13
  96. package/docs/templates/product-line/links.md +10 -10
  97. package/docs/templates/product-line/requirement.md +17 -17
  98. package/docs/templates/product-line/test-plan.md +7 -7
  99. package/docs/templates/project-start-checklist.md +9 -9
  100. package/docs/templates/qa-report.md +48 -48
  101. package/docs/templates/sprint-contract.md +29 -29
  102. package/docs/templates/worker-dogfood-evidence.md +80 -80
  103. package/docs/templates/worker-dogfood-setup.md +68 -68
  104. package/harness.json +2 -5
  105. package/package.json +2 -2
  106. package/scripts/kb-bootstrap-init-skeleton.sh +0 -0
  107. package/scripts/kb-graph-incremental-prepare.mjs +0 -0
  108. package/scripts/kb-graph-materialize.mjs +105 -105
  109. package/scripts/kb-graph-promote.mjs +164 -164
  110. package/scripts/kb-query.mjs +554 -554
  111. package/skills/agent-worker/SKILL.md +48 -48
  112. package/skills/agent-worker/references/agent-worker-operator.md +159 -159
  113. package/skills/ai-engineering-context/SKILL.md +48 -48
  114. package/skills/analyze-product-dependencies/scripts/test-validators.mjs +0 -0
  115. package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +0 -0
  116. package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +0 -0
  117. package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +0 -0
  118. package/skills/analyze-product-requirements/scripts/compute-source-identity.mjs +0 -0
  119. package/skills/analyze-product-requirements/scripts/test-validators.mjs +0 -0
  120. package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +0 -0
  121. package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +0 -0
  122. package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +0 -0
  123. package/skills/browser-tools/browser-content.js +103 -103
  124. package/skills/browser-tools/browser-cookies.js +35 -35
  125. package/skills/browser-tools/browser-eval.js +53 -53
  126. package/skills/browser-tools/browser-hn-scraper.js +108 -108
  127. package/skills/browser-tools/browser-nav.js +44 -44
  128. package/skills/browser-tools/browser-pick.js +162 -162
  129. package/skills/browser-tools/browser-screenshot.js +34 -34
  130. package/skills/browser-tools/browser-start.js +86 -86
  131. package/skills/browser-tools/package-lock.json +2556 -2556
  132. package/skills/browser-tools/package.json +19 -19
  133. package/skills/code-review-core/SKILL.md +20 -20
  134. package/skills/codebase-scout/SKILL.md +19 -19
  135. package/skills/grill-me/SKILL.md +10 -10
  136. package/skills/local-jacoco-coverage/scripts/run-coverage-analysis.sh +0 -0
  137. package/skills/local-jacoco-coverage/scripts/start-jacoco-agent.sh +0 -0
  138. package/skills/loop-agent/SKILL.md +0 -1
  139. package/skills/loop-agent/references/command-reference.md +639 -641
  140. package/skills/loop-agent/references/docs-converge.md +126 -126
  141. package/skills/loop-agent/references/learned/README.md +21 -21
  142. package/skills/loop-agent/references/pi-prompt.md +23 -23
  143. package/skills/loop-agent/references/pi-subagent-assisted-mode.md +84 -84
  144. package/skills/playwright-cli/references/element-attributes.md +23 -23
  145. package/skills/playwright-cli/references/playwright-tests.md +39 -39
  146. package/skills/playwright-cli/references/request-mocking.md +87 -87
  147. package/skills/playwright-cli/references/running-code.md +241 -241
  148. package/skills/playwright-cli/references/session-management.md +225 -225
  149. package/skills/playwright-cli/references/storage-state.md +275 -275
  150. package/skills/playwright-cli/references/test-generation.md +433 -433
  151. package/skills/requesting-code-review/SKILL.md +101 -101
  152. package/skills/requesting-code-review/code-reviewer.md +168 -168
  153. package/skills/systematic-debugging/CREATION-LOG.md +119 -119
  154. package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
  155. package/skills/systematic-debugging/condition-based-waiting.md +115 -115
  156. package/skills/systematic-debugging/defense-in-depth.md +122 -122
  157. package/skills/systematic-debugging/find-polluter.sh +63 -63
  158. package/skills/systematic-debugging/root-cause-tracing.md +169 -169
  159. package/skills/systematic-debugging/test-academic.md +14 -14
  160. package/skills/systematic-debugging/test-pressure-1.md +58 -58
  161. package/skills/systematic-debugging/test-pressure-2.md +68 -68
  162. package/skills/systematic-debugging/test-pressure-3.md +69 -69
  163. package/skills/using-git-worktrees/SKILL.md +215 -215
  164. package/skills/verification-before-completion/SKILL.md +154 -154
  165. package/skills/webapp-testing/SKILL.md +19 -19
  166. package/dist/worker/console/operation-wait.js +0 -241
  167. package/dist/worker/console/static/assets/index-SjjjZnV3.js +0 -56
  168. package/dist/worker/console/static-src/operator-chat/slash-palette-nav.js +0 -141
@@ -1,71 +1,71 @@
1
- {
2
- "$schema": "https://json-schema.org/draft/2020-12/schema",
3
- "$id": "https://loop-agent.local/schemas/knowledge-sync-draft.schema.json",
4
- "title": "Knowledge Sync Draft",
5
- "description": "Pending package written by knowledge-sync-draft-pi before validate/apply.",
6
- "type": "object",
7
- "additionalProperties": false,
8
- "required": [
9
- "schemaVersion",
10
- "featureId",
11
- "taskId",
12
- "runId",
13
- "finalVerification",
14
- "operations",
15
- "payload",
16
- "gates"
17
- ],
18
- "properties": {
19
- "schemaVersion": { "const": 1 },
20
- "featureId": { "type": "string", "minLength": 1 },
21
- "taskId": { "type": "string", "minLength": 1 },
22
- "runId": { "type": "string", "minLength": 1 },
23
- "headSha": { "type": "string" },
24
- "finalVerification": {
25
- "type": "string",
26
- "enum": ["pass", "fail", "partial", "pass-with-waivers"]
27
- },
28
- "operations": {
29
- "type": "array",
30
- "minItems": 1,
31
- "items": {
32
- "type": "object",
33
- "additionalProperties": false,
34
- "required": ["op", "target", "risk", "reason"],
35
- "properties": {
36
- "op": { "type": "string", "enum": ["upsert", "create", "append"] },
37
- "target": { "type": "string", "minLength": 1 },
38
- "risk": { "type": "string", "enum": ["low", "medium", "high"] },
39
- "reason": { "type": "string", "minLength": 1 }
40
- }
41
- }
42
- },
43
- "payload": {
44
- "type": "object",
45
- "additionalProperties": true,
46
- "properties": {
47
- "acceptanceVerdict": { "type": ["object", "null"] },
48
- "coverageMatrix": { "type": ["object", "null"] },
49
- "caseIndex": { "type": ["object", "null"] },
50
- "automationMap": { "type": ["object", "null"] },
51
- "defects": { "type": ["object", "null"] },
52
- "requirementDelta": { "type": ["object", "string", "null"] },
53
- "retrospectiveRef": { "type": ["string", "null"] },
54
- "evidencePointers": {
55
- "type": "array",
56
- "items": { "type": "string" }
57
- }
58
- }
59
- },
60
- "gates": {
61
- "type": "object",
62
- "additionalProperties": false,
63
- "required": ["requireHumanIfHighRisk", "blockIfFinalVerificationNotPass"],
64
- "properties": {
65
- "requireHumanIfHighRisk": { "type": "boolean" },
66
- "blockIfFinalVerificationNotPass": { "type": "boolean" },
67
- "blockIfCoverageP0Missing": { "type": "boolean" }
68
- }
69
- }
70
- }
71
- }
1
+ {
2
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
3
+ "$id": "https://loop-agent.local/schemas/knowledge-sync-draft.schema.json",
4
+ "title": "Knowledge Sync Draft",
5
+ "description": "Pending package written by knowledge-sync-draft-pi before validate/apply.",
6
+ "type": "object",
7
+ "additionalProperties": false,
8
+ "required": [
9
+ "schemaVersion",
10
+ "featureId",
11
+ "taskId",
12
+ "runId",
13
+ "finalVerification",
14
+ "operations",
15
+ "payload",
16
+ "gates"
17
+ ],
18
+ "properties": {
19
+ "schemaVersion": { "const": 1 },
20
+ "featureId": { "type": "string", "minLength": 1 },
21
+ "taskId": { "type": "string", "minLength": 1 },
22
+ "runId": { "type": "string", "minLength": 1 },
23
+ "headSha": { "type": "string" },
24
+ "finalVerification": {
25
+ "type": "string",
26
+ "enum": ["pass", "fail", "partial", "pass-with-waivers"]
27
+ },
28
+ "operations": {
29
+ "type": "array",
30
+ "minItems": 1,
31
+ "items": {
32
+ "type": "object",
33
+ "additionalProperties": false,
34
+ "required": ["op", "target", "risk", "reason"],
35
+ "properties": {
36
+ "op": { "type": "string", "enum": ["upsert", "create", "append"] },
37
+ "target": { "type": "string", "minLength": 1 },
38
+ "risk": { "type": "string", "enum": ["low", "medium", "high"] },
39
+ "reason": { "type": "string", "minLength": 1 }
40
+ }
41
+ }
42
+ },
43
+ "payload": {
44
+ "type": "object",
45
+ "additionalProperties": true,
46
+ "properties": {
47
+ "acceptanceVerdict": { "type": ["object", "null"] },
48
+ "coverageMatrix": { "type": ["object", "null"] },
49
+ "caseIndex": { "type": ["object", "null"] },
50
+ "automationMap": { "type": ["object", "null"] },
51
+ "defects": { "type": ["object", "null"] },
52
+ "requirementDelta": { "type": ["object", "string", "null"] },
53
+ "retrospectiveRef": { "type": ["string", "null"] },
54
+ "evidencePointers": {
55
+ "type": "array",
56
+ "items": { "type": "string" }
57
+ }
58
+ }
59
+ },
60
+ "gates": {
61
+ "type": "object",
62
+ "additionalProperties": false,
63
+ "required": ["requireHumanIfHighRisk", "blockIfFinalVerificationNotPass"],
64
+ "properties": {
65
+ "requireHumanIfHighRisk": { "type": "boolean" },
66
+ "blockIfFinalVerificationNotPass": { "type": "boolean" },
67
+ "blockIfCoverageP0Missing": { "type": "boolean" }
68
+ }
69
+ }
70
+ }
71
+ }
@@ -1,9 +1,9 @@
1
- schema_version: 1
2
- feature_id: F-YYYY-NNN
3
- status: success
4
- qa_verdict: pass
5
- qa_evidence:
6
- - <run-or-report-path>
7
- owner: <human owner>
8
- decided_at: <ISO-8601 timestamp>
9
- summary: <what shipped and why evidence is sufficient>
1
+ schema_version: 1
2
+ feature_id: F-YYYY-NNN
3
+ status: success
4
+ qa_verdict: pass
5
+ qa_evidence:
6
+ - <run-or-report-path>
7
+ owner: <human owner>
8
+ decided_at: <ISO-8601 timestamp>
9
+ summary: <what shipped and why evidence is sufficient>
@@ -1,13 +1,13 @@
1
- # Design — <Feature title>
2
-
3
- ## Context and boundaries
4
-
5
- Describe existing components, public contracts, trust boundaries, and protected areas.
6
-
7
- ## Proposed change
8
-
9
- Describe the smallest end-to-end path and its failure behavior.
10
-
11
- ## Decisions and alternatives
12
-
13
- Record material trade-offs and link ADRs where needed.
1
+ # Design — <Feature title>
2
+
3
+ ## Context and boundaries
4
+
5
+ Describe existing components, public contracts, trust boundaries, and protected areas.
6
+
7
+ ## Proposed change
8
+
9
+ Describe the smallest end-to-end path and its failure behavior.
10
+
11
+ ## Decisions and alternatives
12
+
13
+ Record material trade-offs and link ADRs where needed.
@@ -1,10 +1,10 @@
1
- # Traceability links
2
-
3
- | Relationship | Link or ID |
4
- |---|---|
5
- | Feature | `F-YYYY-NNN` |
6
- | Acceptance → tests | `AC-FEATURE-001` → `TC-001` |
7
- | Acceptance → tasks | `AC-FEATURE-001` → `BE-001`, `QA-001` |
8
- | Task → worker/DAG run | `<workerRunId>` / `<dagRunId>` |
9
- | Change/MR/PR | `<link>` |
10
- | QA evidence | `<artifact path or link>` |
1
+ # Traceability links
2
+
3
+ | Relationship | Link or ID |
4
+ |---|---|
5
+ | Feature | `F-YYYY-NNN` |
6
+ | Acceptance → tests | `AC-FEATURE-001` → `TC-001` |
7
+ | Acceptance → tasks | `AC-FEATURE-001` → `BE-001`, `QA-001` |
8
+ | Task → worker/DAG run | `<workerRunId>` / `<dagRunId>` |
9
+ | Change/MR/PR | `<link>` |
10
+ | QA evidence | `<artifact path or link>` |
@@ -1,17 +1,17 @@
1
- # <Feature title>
2
-
3
- - Feature ID: `<F-YYYY-NNN>`
4
- - Owner: `<human owner>`
5
- - Outcome: `<user or business outcome>`
6
-
7
- ## In scope
8
-
9
- - `<observable capability>`
10
-
11
- ## Out of scope
12
-
13
- - `<explicit non-goal>`
14
-
15
- ## Constraints
16
-
17
- - `<security, compatibility, cost, or operational boundary>`
1
+ # <Feature title>
2
+
3
+ - Feature ID: `<F-YYYY-NNN>`
4
+ - Owner: `<human owner>`
5
+ - Outcome: `<user or business outcome>`
6
+
7
+ ## In scope
8
+
9
+ - `<observable capability>`
10
+
11
+ ## Out of scope
12
+
13
+ - `<explicit non-goal>`
14
+
15
+ ## Constraints
16
+
17
+ - `<security, compatibility, cost, or operational boundary>`
@@ -1,7 +1,7 @@
1
- # Test plan — <Feature title>
2
-
3
- | Test ID | Acceptance | Level | Scenario | Deterministic command |
4
- |---|---|---|---|---|
5
- | TC-001 | AC-FEATURE-001 | integration | happy path and primary failure | `<project-specific command>` |
6
-
7
- Include negative cases, regression scope, environment assumptions, and evidence locations. Commands must match the target project's real toolchain.
1
+ # Test plan — <Feature title>
2
+
3
+ | Test ID | Acceptance | Level | Scenario | Deterministic command |
4
+ |---|---|---|---|---|
5
+ | TC-001 | AC-FEATURE-001 | integration | happy path and primary failure | `<project-specific command>` |
6
+
7
+ Include negative cases, regression scope, environment assumptions, and evidence locations. Commands must match the target project's real toolchain.
@@ -1,9 +1,9 @@
1
- # 项目开工检查清单
2
-
3
- - [ ] 确认 `pwd`
4
- - [ ] 阅读 `README.md`、`harness.json`,以及 `harness.json.governanceRoot` 指向的 `README.md`
5
- - [ ] 检查 `git status --short --branch`
6
- - [ ] 确定单一工作块
7
- - [ ] 从治理根目录下的 `verification-matrix.md` 选择验证命令
8
- - [ ] 保留无关用户变更
9
- - [ ] 非平凡工作时记录 handoff 证据
1
+ # 项目开工检查清单
2
+
3
+ - [ ] 确认 `pwd`
4
+ - [ ] 阅读 `README.md`、`harness.json`,以及 `harness.json.governanceRoot` 指向的 `README.md`
5
+ - [ ] 检查 `git status --short --branch`
6
+ - [ ] 确定单一工作块
7
+ - [ ] 从治理根目录下的 `verification-matrix.md` 选择验证命令
8
+ - [ ] 保留无关用户变更
9
+ - [ ] 非平凡工作时记录 handoff 证据
@@ -1,48 +1,48 @@
1
- # QA 报告模板
2
-
3
- ## 日期 / 会话
4
-
5
- ## 测试范围
6
-
7
- ## 相关 Contract / Plan
8
-
9
- ## 测试方法
10
-
11
- - 自动化测试:
12
- - 构建 / 类型检查:
13
- - Smoke / 手工路径:
14
- - 其他证据:
15
-
16
- ## Smoke / 手工检查
17
-
18
- - CLI smoke:
19
- - DAG smoke:
20
- - Loop workflow smoke:
21
- - Executor smoke:
22
- - 结果:pass / blocked / fail
23
-
24
- ## 通过标准
25
-
26
- ## 发现项
27
-
28
- | ID | Severity | Finding | Evidence | Suggested Fix |
29
- |----|----------|---------|----------|---------------|
30
-
31
- ## Failure Routing
32
-
33
- | Run / Scenario | Raw Failure | DAG Normalized Category | Product-line Category | Recommended Follow-up | Evidence |
34
- |---|---|---|---|---|---|
35
- | | | | | | |
36
-
37
- ## 新发现的 Bug / 漂移
38
-
39
- - 新发现 bug:
40
- - 发现的契约漂移:
41
- - 发现的文档/测试不一致:
42
-
43
- ## 最终结论
44
-
45
- - 结论:pass / partial / fail
46
- - 结论依据:
47
-
48
- ## 后续项
1
+ # QA 报告模板
2
+
3
+ ## 日期 / 会话
4
+
5
+ ## 测试范围
6
+
7
+ ## 相关 Contract / Plan
8
+
9
+ ## 测试方法
10
+
11
+ - 自动化测试:
12
+ - 构建 / 类型检查:
13
+ - Smoke / 手工路径:
14
+ - 其他证据:
15
+
16
+ ## Smoke / 手工检查
17
+
18
+ - CLI smoke:
19
+ - DAG smoke:
20
+ - Loop workflow smoke:
21
+ - Executor smoke:
22
+ - 结果:pass / blocked / fail
23
+
24
+ ## 通过标准
25
+
26
+ ## 发现项
27
+
28
+ | ID | Severity | Finding | Evidence | Suggested Fix |
29
+ |----|----------|---------|----------|---------------|
30
+
31
+ ## Failure Routing
32
+
33
+ | Run / Scenario | Raw Failure | DAG Normalized Category | Product-line Category | Recommended Follow-up | Evidence |
34
+ |---|---|---|---|---|---|
35
+ | | | | | | |
36
+
37
+ ## 新发现的 Bug / 漂移
38
+
39
+ - 新发现 bug:
40
+ - 发现的契约漂移:
41
+ - 发现的文档/测试不一致:
42
+
43
+ ## 最终结论
44
+
45
+ - 结论:pass / partial / fail
46
+ - 结论依据:
47
+
48
+ ## 后续项
@@ -1,29 +1,29 @@
1
- # Sprint Contract
2
-
3
- ## 目标(Objective)
4
-
5
- 描述有边界的工作块。
6
-
7
- ## 交付物(Deliverables)
8
-
9
- -
10
-
11
- ## 非目标(Non-goals)
12
-
13
- -
14
-
15
- ## 验证(Verification)
16
-
17
- ```bash
18
- bash scripts/check-repo.sh
19
- npm run typecheck
20
- npm test
21
- ```
22
-
23
- Windows 上通过 Git Bash 或已配置的兼容 Bash 运行脚本。实际文件操作用平台原生路径。
24
-
25
- ## 失败条件(Failure Conditions)
26
-
27
- - 必需验证无法运行或失败
28
- - 工作需要超出本 contract 的范围
29
- - 实现改动了无关文件
1
+ # Sprint Contract
2
+
3
+ ## 目标(Objective)
4
+
5
+ 描述有边界的工作块。
6
+
7
+ ## 交付物(Deliverables)
8
+
9
+ -
10
+
11
+ ## 非目标(Non-goals)
12
+
13
+ -
14
+
15
+ ## 验证(Verification)
16
+
17
+ ```bash
18
+ bash scripts/check-repo.sh
19
+ npm run typecheck
20
+ npm test
21
+ ```
22
+
23
+ Windows 上通过 Git Bash 或已配置的兼容 Bash 运行脚本。实际文件操作用平台原生路径。
24
+
25
+ ## 失败条件(Failure Conditions)
26
+
27
+ - 必需验证无法运行或失败
28
+ - 工作需要超出本 contract 的范围
29
+ - 实现改动了无关文件
@@ -1,80 +1,80 @@
1
- # Worker Dogfood Evidence
2
-
3
- ## Sample identity
4
-
5
- | Field | Value |
6
- |---|---|
7
- | Date | |
8
- | Feature / Task | |
9
- | Target repo | disposable path or sanitized reference |
10
- | Controller package/version | |
11
- | Agent-worker package/version (same npm install) | |
12
- | Controller requested entry / real entry | sanitized reference; keep machine-local absolute value in runtime evidence |
13
- | Controller launch command / args prefix | sanitized reference |
14
- | Controller binary SHA-256 | |
15
- | Controller package fingerprint | `sha256:<hex>` |
16
- | Expected controller version / fingerprint | n/a / exact values |
17
- | Provider/model / override | |
18
- | Batch ID | |
19
- | Worker run ID | |
20
- | Retry of worker run ID | n/a / |
21
- | Candidate commit / tarball SHA-256 | n/a / |
22
-
23
- ## Baseline
24
-
25
- - Baseline commit and `git status`:
26
- - Existing failing behavior or missing capability:
27
- - Preflight (`loop-agent --version`, `inspect`, `docs audit`, `check-repo`):
28
-
29
- ## Run evidence
30
-
31
- | Artifact | Path / link | Result |
32
- |---|---|---|
33
- | TaskSpec / source-doc copies | | |
34
- | DAG spec | | |
35
- | DAG report JSON / Markdown | | |
36
- | DAG skill snapshot ref / SHA-256 / mode | | |
37
- | shell verification | | |
38
- | diff | | |
39
- | closeout or Failure Handoff | | |
40
- | morning report | | |
41
- | Observe snapshot / events | | |
42
- | Controller identity in Worker / Task Pool / batch / Feature evidence | | |
43
-
44
- ## Candidate takeover evidence (if applicable)
45
-
46
- | Field | Value / result |
47
- |---|---|
48
- | Candidate isolated slot containment | |
49
- | `loop-agent` entry / binary SHA-256 / reported version | |
50
- | `agent-worker` entry / binary SHA-256 / reported version | |
51
- | Shared package fingerprint | |
52
- | Full init / doctor / inspect / docs audit / target check-repo | |
53
- | `agent-worker` skill and `.agents/skills` mirror hashes | |
54
- | Feature validation / `feature run --dry-run` | |
55
- | DAG executors | expected: `static`, `shell` only |
56
- | PATH trap invocations | expected: none |
57
- | Pi/model executor observed | expected: false; derive from actual DAG nodes |
58
- | Feature dry-run executed tasks | expected: empty |
59
- | Canary verdict / evidence path | |
60
-
61
- Do not use a deterministic canary result as proof that live Pi/model/provider execution succeeded. Record run-owned skill snapshot evidence and any explicitly authorized live run separately.
62
-
63
- ## Acceptance and QA coverage
64
-
65
- | Acceptance | Test case(s) | Test file / verification | Result |
66
- |---|---|---|---|
67
- | | | | |
68
-
69
- ## Failure / retry (if applicable)
70
-
71
- | Raw failure | Product-line category | Recommended follow-up | Root cause evidence | Retry result |
72
- |---|---|---|---|---|
73
- | | | | | |
74
-
75
- ## Conclusion
76
-
77
- - Verdict: pass / fail / blocked
78
- - Review notes:
79
- - Follow-up task(s):
80
- - Evidence limitations (for example deterministic-only, no Pi executor/live takeover):
1
+ # Worker Dogfood Evidence
2
+
3
+ ## Sample identity
4
+
5
+ | Field | Value |
6
+ |---|---|
7
+ | Date | |
8
+ | Feature / Task | |
9
+ | Target repo | disposable path or sanitized reference |
10
+ | Controller package/version | |
11
+ | Agent-worker package/version (same npm install) | |
12
+ | Controller requested entry / real entry | sanitized reference; keep machine-local absolute value in runtime evidence |
13
+ | Controller launch command / args prefix | sanitized reference |
14
+ | Controller binary SHA-256 | |
15
+ | Controller package fingerprint | `sha256:<hex>` |
16
+ | Expected controller version / fingerprint | n/a / exact values |
17
+ | Provider/model / override | |
18
+ | Batch ID | |
19
+ | Worker run ID | |
20
+ | Retry of worker run ID | n/a / |
21
+ | Candidate commit / tarball SHA-256 | n/a / |
22
+
23
+ ## Baseline
24
+
25
+ - Baseline commit and `git status`:
26
+ - Existing failing behavior or missing capability:
27
+ - Preflight (`loop-agent --version`, `inspect`, `docs audit`, `check-repo`):
28
+
29
+ ## Run evidence
30
+
31
+ | Artifact | Path / link | Result |
32
+ |---|---|---|
33
+ | TaskSpec / source-doc copies | | |
34
+ | DAG spec | | |
35
+ | DAG report JSON / Markdown | | |
36
+ | DAG skill snapshot ref / SHA-256 / mode | | |
37
+ | shell verification | | |
38
+ | diff | | |
39
+ | closeout or Failure Handoff | | |
40
+ | morning report | | |
41
+ | Observe snapshot / events | | |
42
+ | Controller identity in Worker / Task Pool / batch / Feature evidence | | |
43
+
44
+ ## Candidate takeover evidence (if applicable)
45
+
46
+ | Field | Value / result |
47
+ |---|---|
48
+ | Candidate isolated slot containment | |
49
+ | `loop-agent` entry / binary SHA-256 / reported version | |
50
+ | `agent-worker` entry / binary SHA-256 / reported version | |
51
+ | Shared package fingerprint | |
52
+ | Full init / doctor / inspect / docs audit / target check-repo | |
53
+ | `agent-worker` skill and `.agents/skills` mirror hashes | |
54
+ | Feature validation / `feature run --dry-run` | |
55
+ | DAG executors | expected: `static`, `shell` only |
56
+ | PATH trap invocations | expected: none |
57
+ | Pi/model executor observed | expected: false; derive from actual DAG nodes |
58
+ | Feature dry-run executed tasks | expected: empty |
59
+ | Canary verdict / evidence path | |
60
+
61
+ Do not use a deterministic canary result as proof that live Pi/model/provider execution succeeded. Record run-owned skill snapshot evidence and any explicitly authorized live run separately.
62
+
63
+ ## Acceptance and QA coverage
64
+
65
+ | Acceptance | Test case(s) | Test file / verification | Result |
66
+ |---|---|---|---|
67
+ | | | | |
68
+
69
+ ## Failure / retry (if applicable)
70
+
71
+ | Raw failure | Product-line category | Recommended follow-up | Root cause evidence | Retry result |
72
+ |---|---|---|---|---|
73
+ | | | | | |
74
+
75
+ ## Conclusion
76
+
77
+ - Verdict: pass / fail / blocked
78
+ - Review notes:
79
+ - Follow-up task(s):
80
+ - Evidence limitations (for example deterministic-only, no Pi executor/live takeover):