@loomhelm/multi-task-flow 0.0.0-stage → 0.2.1

package/toolkit/skills/dev-plan/references/replay-cases/ambiguous-continue-fallback.jsonl

@@ -0,0 +1,3 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "继续"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "请先确认流程类型：仅实现、普通流程、快车道、还是本地合主干？"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Fallback Plan\n\n## Summary\n- 结论：流程类型未明确，按 normal 兜底并等待确认。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `fallback_default`\n- `lock_status`: `pending_confirmation`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute fallback normal workflow and hold for confirmation (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 主人尚未明确流程类型：待确认\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/blank-acceptance-bullet.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Blank Acceptance Bullet\n\n## Summary\n- 结论：用于验证空 bullet 不能充当有效 Acceptance。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: keep acceptance actionable\n  Acceptance must contain a concrete validation line instead of an empty bullet placeholder.\n\n## Non-goals\n- Do not allow blank acceptance bullets.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => implement the demo workflow change (skill: $normal-flow)\n\n## Acceptance & Validation\n-\n\n## Assumptions/Defaults\n- This fixture intentionally exercises empty acceptance bullets: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/checkbox-task-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Checkbox Forbidden\n\n## Summary\n- 结论：用于验证复选框禁用。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- [ ] wave: 1\n  - main-agent => do work (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/conflicting-flow-signals-default-fast-track.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请同时按 `$normal-flow` 和 `$fast-flow` 规划一下。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Conflicting Signals Wrong Default\n\n## Summary\n- 结论：用于验证互斥 flow 信号不能静默落到 default_fast_track。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 验证冲突信号阻断默认值\n  当前请求同时给出互斥 flow 信号，因此 assistant 应继续追问，而不是直接按默认快车道规划。\n\n## Non-goals\n- 不把互斥 flow 信号视为已解决的 happy path。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划快车道执行路径 (skill: $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝在互斥 flow 信号存在时直接使用 `default_fast_track`。\n\n## Assumptions/Defaults\n- 该样例专门用于验证 conflict guard：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/context-dependent-alias-development-baseline.jsonl

@@ -0,0 +1 @@
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Context-dependent Alias Development Baseline\n\n## Summary\n- 结论：示例故意把开发基线写成依赖当前 checkout 历史的 Git 别名。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`@{-1}`\n\n## Goals\n- 目标 1: 演示 checker 不能把 context-dependent alias 当成 concrete baseline\n  当前计划故意把 `@{-1}` 这样的 reflog shorthand 写进 `开发基线`，用于验证 checker 会拒绝这类不可复现值。\n\n## Non-goals\n- 不覆盖真正的 branch/ref 或 commit baseline 场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝把 `@{-1}` 这类依赖本地上下文的 Git alias 当成 `Flow Decision` 的有效 `开发基线`。\n\n## Assumptions/Defaults\n- 这是一个专门用于 context-dependent alias 校验的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/context-dependent-remote-head-development-baseline.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 给出 fast-track 计划。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Context-dependent Remote HEAD Development Baseline\n\n## Summary\n- 结论：示例故意把开发基线写成远端默认分支的 symbolic HEAD alias。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/HEAD`\n\n## Goals\n- 目标 1: 演示 checker 不能把 remote HEAD alias 当成 concrete baseline\n  当前计划故意把 `origin/HEAD` 写进 `开发基线`，用于验证 checker 会拒绝这类会随远端默认分支漂移的符号 ref。\n\n## Non-goals\n- 不覆盖真正的 branch/ref 或 commit baseline 场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝把 `origin/HEAD` 这类 remote symbolic ref 当成 `Flow Decision` 的有效 `开发基线`。\n\n## Assumptions/Defaults\n- 这是一个专门用于 remote HEAD alias 校验的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/create-plan-md-implementation-steps-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"按普通流程计划"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Create PLAN.md with Implementation Steps\n\n## Summary\n- 结论：用于验证 generic PLAN.md create wording 仍会被当成 persisted planning artifact。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: create a persisted plan file\n  Create PLAN.md file with implementation steps for the next execution pass.\n\n## Non-goals\n- Do not change runtime behavior.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create PLAN.md file with implementation steps (skill: $normal-flow)\n\n## Acceptance & Validation\n- The persisted plan file exists with implementation steps.\n\n## Assumptions/Defaults\n- PLAN.md stays as the execution source: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/decision-log-artifact-in-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Decision Log Artifact in Orchestration\n\n## Summary\n- 结论：用于验证 planning decision log 仍会被识别为持久计划载体。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The task arrangement must not create future planning handoff artifacts.\n\n## Non-goals\n- Do not allow planning decision log artifacts in orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create decision log for future planning handoffs (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker must reject planning decision log artifacts inside Task Orchestration.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises decision-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/decision-log-future-work-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Decision Log Future Work Artifact\n\n## Summary\n- 结论：用于验证 plain future-work decision log 仍会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not create a persisted decision-log artifact for future work.\n\n## Non-goals\n- Do not allow planning decision-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create decision log for future work (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects plain future-work decision-log artifacts.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises future-work decision-log detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/decision-log-job-future-handoffs-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Decision Log Job Future Handoffs Artifact\n\n## Summary\n- 结论：用于验证 generic job wording 不能放行 future-handoff decision-log artifact。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not create a persisted decision-log artifact for future handoffs.\n\n## Non-goals\n- Do not allow planning decision-log jobs inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create a decision log job for future handoffs (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects decision-log jobs that target future handoffs.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises job-wording decision-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/decision-log-timeline-planning-handoff-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Decision Log Timeline Planning Handoff Artifact\n\n## Summary\n- 结论：用于验证带 planning handoff 上下文的 decision log timeline 仍会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not create a persisted decision-log artifact for the next planning handoff.\n\n## Non-goals\n- Do not allow planning decision-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create decision log timeline for the next planning handoff (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects planning decision-log artifacts even when the task also mentions a timeline.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises planning-context decision-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/decision-log-workflow-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Decision Log Workflow Artifact\n\n## Summary\n- 结论：用于验证 generic workflow wording 不能放行 planning decision-log artifact。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not generate a planning decision-log workflow.\n\n## Non-goals\n- Do not allow planning decision-log workflows inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => generate the decision log workflow for operators (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects generic decision-log workflow wording when it would create a planning artifact.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises workflow-wording decision-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/default-fast-track-missing-merge-ready-stop.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请为这个需求直接产出可执行计划。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Default Fast-track Missing Merge-ready Stop\n\n## Summary\n- 结论：用于验证 default_fast_track 不得停在仅创建 PR。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 验证默认 stop condition 校验\n  当前请求虽然没有显式 flow，但默认快车道也必须把 stop condition 锁到 merge-ready，而不是只做到 PR 创建。\n\n## Non-goals\n- 不把 PR 已创建误当成 merge-ready。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 只创建 PR 后停下 (skill: $fast-flow)\n\n## Acceptance & Validation\n- PR 已创建即可。\n\n## Assumptions/Defaults\n- 该样例专门用于验证 default stop-condition guard：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/duplicate-task-in-wave.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Duplicate Task\n\n## Summary\n- 结论：用于验证同波次重复任务。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - sub-agent:checker [gpt-5.6-luna, xhigh] => update checker (skill: $normal-flow)\n  - sub-agent:checker [gpt-5.6-luna, xhigh] => update checker (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-after-flow-answer.jsonl

@@ -0,0 +1,4 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，开发基线使用 `upstream/release-2026q3`。"}]}}
+{"type":"response_item","payload":{"type":"function_call","name":"request_user_input","call_id":"call_flow_type_lock","arguments":"{\"questions\":[{\"header\":\"流程类型\",\"id\":\"flow_type\",\"question\":\"当前 flow 信号存在歧义，请明确本次流程类型\",\"options\":[{\"label\":\"快车道 (Recommended)\",\"description\":\"推进到 PR merge-ready / Step 5C Ready\"},{\"label\":\"仅实现\",\"description\":\"只产出实现规格\"},{\"label\":\"普通流程\",\"description\":\"验证后本地提交并停下\"},{\"label\":\"本地合主干\",\"description\":\"规划到本地 merge-ready 与本地合并收尾。\"}]}]}"}}
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"normal"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Owner Baseline Mismatch After Flow Answer\n\n## Summary\n- 结论：示例故意在 flow 回答后忽略主人先前显式给出的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会在多轮 flow 解析后继续保留 owner baseline\n  即使流程类型是后续单独回答的，计划也不应把主人先前显式给出的 `upstream/release-2026q3` 覆盖成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- checker 必须发现 flow 回答后的最终 `开发基线` 与主人先前显式指定的 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个 flow 回答后 owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-after-standalone-flow-restatement.jsonl

@@ -0,0 +1,4 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我 `flow_type: normal` 计划，开发基线使用 `upstream/release-2026q3`。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Owner Baseline Mismatch After Standalone Flow Restatement\n\n## Summary\n- 结论：示例故意在已锁定计划后的 standalone flow restatement 之后忽略主人先前显式给出的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`upstream/release-2026q3`\n\n## Goals\n- 目标 1: 演示 checker 会在已锁定计划后的 standalone flow restatement 之后继续保留 owner baseline\n  即使主人后续只重述同一个 `normal` flow，计划也不应把先前显式给出的 `upstream/release-2026q3` 覆盖成默认主干 ref。\n\n## Non-goals\n- 不验证新的独立计划请求重置 baseline 的场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- 第一轮计划必须原样保留显式 branch baseline。\n\n## Assumptions/Defaults\n- 第一轮请求已显式给出 branch baseline：已确定\n</proposed_plan>"}]}}
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"normal"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Owner Baseline Mismatch After Standalone Flow Restatement Revision\n\n## Summary\n- 结论：示例故意在 standalone flow restatement 之后把 baseline 错误改回默认主干。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 不应把 standalone flow restatement 误当成 baseline 清空点\n  后续单独重述 `normal` flow 不应让计划从 `upstream/release-2026q3` 静默回退到 `origin/main`。\n\n## Non-goals\n- 不验证新的独立计划请求重置 baseline 的场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- checker 必须发现 standalone flow restatement 后最终 `开发基线` 与主人先前显式指定的 baseline 不一致。\n\n## Assumptions/Defaults\n- standalone flow restatement 不应清空第一轮显式 baseline：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-base-equals.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"Please use $dev-plan and give me a `flow_type: fast-track` plan, base=upstream/release-2026q3."}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Base Equals Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人用 `base=...` 形式显式给出的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截 `base=...` baseline 被覆盖\n  当前计划明知主人显式给了 `base=upstream/release-2026q3`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与 `base=...` 显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个 `base=...` owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-base-ref-equals.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，BASE_REF=upstream/release-2026q3。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo BASE_REF Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人用 `BASE_REF=...` 形式显式给出的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截 `BASE_REF=...` baseline 被覆盖\n  当前计划明知主人显式给了 `BASE_REF=upstream/release-2026q3`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与 `BASE_REF=...` 显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个 `BASE_REF=...` owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-directional-baseline.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，基于 `upstream/release-2026q3` 开发。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Directional Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人用自然语句显式给出的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截 directional wording baseline 被覆盖\n  当前计划明知主人显式要求基于 `upstream/release-2026q3` 开发，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与 directional wording 显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个 directional owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-english-is.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"Please use $dev-plan with `flow_type: fast-track` and keep the base branch is upstream/release-2026q3."}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo English Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略英文 `base branch is ...` 形式的显式 baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截英文显式 baseline 被覆盖\n  当前计划明知主人显式给了 `upstream/release-2026q3`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与英文显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个英文 owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-legal-trailing-punct.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我 `flow_type: fast-track` 计划，开发基线使用 `release/v1.0!`。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Legal Trailing Punctuation Baseline Mismatch\n\n## Summary\n- 结论：示例故意把主人显式给出的合法 branch baseline 改成去掉尾部标点的另一个 ref。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`release/v1.0`\n\n## Goals\n- 目标 1: 演示 checker 不得把合法 ref 尾部字符静默归一化掉\n  当前计划故意把 `release/v1.0!` 改写成 `release/v1.0`，用于验证 checker 会继续报 mismatch。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划基于错误 ref 的实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现合法 ref 尾部字符被改写后的 baseline mismatch。\n\n## Assumptions/Defaults\n- 这是一个合法尾部标点 baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-legal-trailing-semicolon-plain.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我 `flow_type: fast-track` 计划，开发基线使用 release/v1;"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Plain Legal Trailing Semicolon Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人显式给出的尾部带合法分号字符的 plain baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 不得把 plain baseline 末尾的合法分号静默裁掉\n  当前计划明知主人显式给了 `release/v1;`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划基于错误 ref 的实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现 plain baseline 里的合法尾部分号字符被忽略后的 baseline mismatch。\n\n## Assumptions/Defaults\n- 这是一个 plain 合法尾部分号 baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-plain-chinese.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，开发基线使用 upstream/release-2026q3。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Plain Chinese Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略中文 plain text 形式的显式 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截中文 plain text baseline 被覆盖\n  当前计划明知主人显式给了 `upstream/release-2026q3`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与中文 plain text 显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个中文 plain text owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-plan-page-upload-api-scope-clarification.jsonl

@@ -0,0 +1,6 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，开发基线使用 `upstream/release-2026q3`。"}]}}
+{"type":"response_item","payload":{"type":"function_call","name":"request_user_input","call_id":"call_flow_type_plan_page_mismatch","arguments":"{\"questions\":[{\"header\":\"流程类型\",\"id\":\"flow_type\",\"question\":\"当前 flow 信号存在歧义，请明确本次流程类型\",\"options\":[{\"label\":\"普通流程 (Recommended)\",\"description\":\"验证后本地提交并停下\"},{\"label\":\"快车道\",\"description\":\"推进到 PR merge-ready / Step 5C Ready\"},{\"label\":\"仅实现\",\"description\":\"只产出实现规格\"},{\"label\":\"本地合主干\",\"description\":\"规划到本地 merge-ready 与本地合并收尾。\"}]}]}"}}
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"normal"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo First Plan Before Plan-page Upload Scope Clarification Mismatch\n\n## Summary\n- 结论：第一轮计划显式保留 owner 指定的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`upstream/release-2026q3`\n\n## Goals\n- 目标 1: 保留第一轮显式 branch baseline\n  当前计划围绕 `upstream/release-2026q3` 编排，不回退到默认主干。\n\n## Non-goals\n- 不把后续范围补充误判为新的独立计划请求。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现、验证与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- 第一轮计划必须原样保留显式 branch baseline。\n\n## Assumptions/Defaults\n- 主人已先给出 branch baseline，流程类型在后续单独回答：已确定\n</proposed_plan>"}]}}
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请按 normal 把计划页面上传 API 也规划进去，flow 和开发基线都不变。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Plan-page Upload Scope Clarification Wrongly Resets Baseline\n\n## Summary\n- 结论：示例故意把计划页面上传 API 的范围补充误当成新 planning window，并把 baseline 错误改回默认主干。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 不应把 `计划页面上传 API` scope clarification 误判成 baseline 清空点\n  后续范围补充明说 flow 和开发基线都不变，但当前计划却故意把 `upstream/release-2026q3` 静默回退成 `origin/main`。\n\n## Non-goals\n- 不验证新的独立计划请求重置 baseline 的场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 在错误基线上规划计划页面上传 API 的范围补充 (skill: $normal-flow)\n\n## Acceptance & Validation\n- checker 必须发现 scope clarification 后最终 `开发基线` 与主人先前显式指定的 baseline 不一致。\n\n## Assumptions/Defaults\n- scope clarification 不应清空第一轮显式 baseline：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-short-ref.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我 `flow_type: fast-track` 计划，开发基线使用 qa"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Short Ref Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人给出的短 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截短 ref baseline 被覆盖\n  当前计划明知主人显式给了 `qa`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现短 ref 形式的显式 baseline 与最终 `开发基线` 不一致。\n\n## Assumptions/Defaults\n- 这是一个短 ref owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch-yong-plain-chinese.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，开发基线用 upstream/release-2026q3。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Plain Chinese Yong Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略中文 `开发基线用 ...` 形式的显式 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截 `开发基线用 ...` 被覆盖\n  当前计划明知主人显式给了 `upstream/release-2026q3`，却故意换成默认主干 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与 `开发基线用 ...` 形式的显式 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个中文 `开发基线用 ...` owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/explicit-owner-baseline-mismatch.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 规划这项工作，开发基线使用 `upstream/release-2026q3`。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Owner Baseline Mismatch\n\n## Summary\n- 结论：示例故意忽略主人显式指定的 branch baseline。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 对 owner baseline 被覆盖的拦截\n  当前计划明知主人显式给了 branch baseline，却故意换成别的 ref。\n\n## Non-goals\n- 不验证抽象基线场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须发现最终 `开发基线` 与主人显式指定的 baseline 不一致。\n\n## Assumptions/Defaults\n- 这是一个 owner baseline mismatch 反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/filesystem-path-development-baseline.jsonl

@@ -0,0 +1 @@
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Filesystem Path Development Baseline\n\n## Summary\n- 结论：示例故意把开发基线写成真正的文件系统路径。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n- 开发基线：`./docs/specs/7uqp8-mainline-baseline-topic-branch-freshness/SPEC.md`\n\n## Goals\n- 目标 1: 演示 checker 不能把文件系统路径当成 Git baseline\n  当前计划故意把 `./docs/specs/.../SPEC.md` 这样的本地路径写进 `开发基线`，用于验证 checker 会拒绝这类伪 concrete 值。\n\n## Non-goals\n- 不覆盖语法上合法的 branch/ref baseline 场景。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝把文件系统路径当成 `Flow Decision` 的有效 `开发基线`。\n\n## Assumptions/Defaults\n- 这是一个专门用于路径误判校验的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/flat-task-orchestration-list.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Task Outside Wave\n\n## Summary\n- 结论：用于验证任务项在 wave 外部。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- main-agent => do work (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/flow-decision-baseline-only-outside-section.jsonl

@@ -0,0 +1 @@
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Flow Decision Baseline Missing But Mentioned Later\n\n## Summary\n- 结论：示例故意把开发基线只写在后文。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 演示 checker 不能把后文 baseline 当成 Flow Decision 已填写\n  当前计划故意不在 `Flow Decision` 写开发基线，而只在验收里提到 `开发基线：origin/main`。\n\n## Non-goals\n- 不验证 owner baseline mismatch。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- 即使后文出现 `开发基线：origin/main`，checker 也必须继续报 Flow Decision 缺项。\n\n## Assumptions/Defaults\n- 这是一个专门用于 section-scope 校验的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/flow-decision-mismatch-lock.jsonl

@@ -0,0 +1,3 @@
+{"type":"response_item","payload":{"type":"function_call","name":"request_user_input","call_id":"call_flow_type_lock","arguments":"{\"questions\":[{\"header\":\"流程类型\",\"id\":\"flow_type\",\"question\":\"当前 flow 信号存在歧义，请明确本次流程类型\",\"options\":[{\"label\":\"快车道 (Recommended)\",\"description\":\"推进到 PR merge-ready / Step 5C Ready\"},{\"label\":\"仅实现\",\"description\":\"只产出实现规格\"},{\"label\":\"普通流程\",\"description\":\"验证后本地提交并停下\"},{\"label\":\"本地合主干\",\"description\":\"规划到本地 merge-ready 与本地合并收尾。\"}]}]}"}}
+{"type":"response_item","payload":{"type":"function_call_output","call_id":"call_flow_type_lock","output":"{\"answers\":{\"flow_type\":{\"answers\":[\"快车道\"]}}}"}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Flow Decision Mismatch\n\n## Summary\n- 结论：用于验证 flow_type 锁定值与计划声明值不一致。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `request_user_input`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => prepare local implementation plan (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 流程已锁定：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/generate-handoff-log-future-sessions-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Generate Handoff Log Future Sessions Artifact\n\n## Summary\n- 结论：用于验证 `generate` 这类动作也会命中 planning handoff-log artifact 拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not generate a planning handoff-log artifact for future sessions.\n\n## Non-goals\n- Do not allow generated planning handoff-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => generate a handoff log for future sessions (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects generated handoff logs that target future sessions.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises `generate` verb coverage for handoff-log artifacts: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/goal-blank-bullet.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Goal Blank Bullet\n\n## Summary\n- 结论：用于验证空 goal bullet 不能绕过 goals-first 合同。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n-\n\n## Non-goals\n- 不允许空 goal bullet 混过 checker。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => run local validation only (skill: $normal-flow)\n\n## Acceptance & Validation\n- Replay fixture must fail before execution starts.\n\n## Assumptions/Defaults\n- 该样例专门用于验证空 goal bullet：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/goal-placeholder-detail.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Goal Placeholder Detail\n\n## Summary\n- 结论：用于验证 goal detail 只有占位词时不能通过。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: keep the goal concrete\n  TBD\n\n## Non-goals\n- Do not allow placeholder-only goal detail.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => implement the demo workflow change (skill: $normal-flow)\n\n## Acceptance & Validation\n- Local checks pass.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises placeholder-only goal detail: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/goal-tba-detail.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"按普通流程计划"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Goal TBA Detail\n\n## Summary\n- 结论：用于验证 Goal detail 里的 TBA 占位会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: keep the goal concrete\n  TBA\n\n## Non-goals\n- Do not leave the main goal unresolved.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => implement the scoped change (skill: $normal-flow)\n\n## Acceptance & Validation\n- Local validation proves the scoped change behaves as expected.\n\n## Assumptions/Defaults\n- Scope boundary is already understood: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/goal-without-detail.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Goal Without Detail\n\n## Summary\n- 结论：用于验证 goal 只有标题没有细节。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n- Goal 2: keep orchestration concise\n\n## Non-goals\n- 不扩展到 demo 之外。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute local validation tasks (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/goals-empty-orchestration-only.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Goals Empty\n\n## Summary\n- 结论：用于验证把设计内容全塞进编排、Goals 为空会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n\n## Non-goals\n- 不扩展到 demo 之外。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => describe all design details and execute local validation tasks in one step (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/handoff-log-artifact-in-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Handoff Log Artifact in Orchestration\n\n## Summary\n- 结论：用于验证 planning handoff log 仍会被识别为持久计划载体。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The task arrangement must not create future handoff artifacts for the next agent session.\n\n## Non-goals\n- Do not allow planning handoff log artifacts in orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create a handoff log for the next agent session (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker must reject planning handoff log artifacts inside Task Orchestration.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises handoff-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/handoff-log-future-work-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Handoff Log Future Work Artifact\n\n## Summary\n- 结论：用于验证 plain future-work handoff log 仍会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not create a persisted handoff-log artifact for future work.\n\n## Non-goals\n- Do not allow planning handoff-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create handoff log for future work (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects plain future-work handoff-log artifacts.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises future-work handoff-log detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/handoff-log-history-agent-session-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Handoff Log History Agent Session Artifact\n\n## Summary\n- 结论：用于验证带 next-agent-session 上下文的 handoff log history 仍会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not create a persisted handoff-log artifact for the next agent session.\n\n## Non-goals\n- Do not allow planning handoff-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create handoff log history for the next agent session (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects planning handoff-log artifacts even when the task also mentions history.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises planning-context handoff-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/handoff-log-pipeline-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Handoff Log Pipeline Artifact\n\n## Summary\n- 结论：用于验证 generic pipeline wording 不能放行 planning handoff-log artifact。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not keep a planning handoff-log pipeline.\n\n## Non-goals\n- Do not allow planning handoff-log pipelines inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => keep a handoff log pipeline for future sessions (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects generic handoff-log pipeline wording when it would retain a planning artifact.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises pipeline-wording handoff-log artifact detection: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/historical-flow-not-locked-before-plan.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请帮我规划这个任务，并默认走合适流程。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Historical Flow Not Locked Before Plan\n\n## Summary\n- 结论：示例故意在 flow 未锁定前直接输出计划。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截未锁 flow 的提前出计划\n  当前计划故意在没有 flow lock 证据、也没有 `request_user_input(flow_type)` 的前提下直接输出。\n\n## Non-goals\n- 不验证默认 fast-track 自动锁路径。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现、验证与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- checker 必须报告在 flow 未锁定前就输出了 `<proposed_plan>`。\n\n## Assumptions/Defaults\n- 这是一个专门保留给历史未锁 flow 回归的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/historical-missing-flow-type.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我 `flow_type: normal` 计划，开发基线使用 `origin/main`。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Historical Missing Flow Type\n\n## Summary\n- 结论：示例故意省略 `Flow Decision.flow_type`。\n\n## Flow Decision\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 演示 checker 会拦截缺失的 `flow_type`\n  当前计划故意缺少 `Flow Decision.flow_type`，用于验证历史缺失字段回归仍会被拦截。\n\n## Non-goals\n- 不验证 flow lock 本身是否已建立。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划普通流程下的实现、验证与本地提交收口 (skill: $normal-flow)\n\n## Acceptance & Validation\n- checker 必须报告 `Flow Decision` 缺少 `flow_type`。\n\n## Assumptions/Defaults\n- 这是一个专门保留给历史缺失 `flow_type` 回归的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-copy-spec-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Copy Spec\n\n## Summary\n- 结论：用于验证 copy docs/specs 路径属于禁止任务。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => copy docs/specs/a/SPEC.md to docs/specs/b/SPEC.md (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-create-for-tests-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Create Spec For Tests\n\n## Summary\n- 结论：用于验证 implement-only 下 spec 创建不能被 for tests 规避。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create docs/specs/ab123-tests/SPEC.md for tests (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-create-migrated-copy-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Create Migrated Spec Copy\n\n## Summary\n- 结论：用于验证 create/migrate spec copy 即使 from existing 也必须阻断。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create a migrated spec copy from existing docs/specs/legacy/SPEC.md under docs/specs/new/SPEC.md (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-skill-normal-flow.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Skill normal-flow\n\n## Summary\n- 结论：用于验证 implement-only 禁止绑定 $normal-flow。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => define acceptance criteria (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-skill-topic-spec.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Skill topic-spec\n\n## Summary\n- 结论：用于验证 implement-only 禁止绑定 $topic-spec。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => define implementation scope and interfaces (skill: $topic-spec)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-sync-against-existing-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Sync Against Existing Spec\n\n## Summary\n- 结论：用于验证即使提及 existing spec，sync docs/specs 任务仍必须阻断。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => sync docs/specs/ab123/SPEC.md against existing docs/specs/legacy/SPEC.md (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-sync-task-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Sync Task\n\n## Summary\n- 结论：用于验证 implement-only 下编排任务禁止 spec 同步。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => sync docs/specs/ab123-demo/SPEC.md with latest API decisions (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-task-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Task\n\n## Summary\n- 结论：用于验证 implement-only 下编排任务禁止 spec 创建/迁移/同步。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => create docs/specs/ab123-demo/SPEC.md as Spec gate bootstrap (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-update-existing-spec-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Update Existing Spec\n\n## Summary\n- 结论：用于验证 update existing docs/specs 仍属于禁止任务。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => update existing docs/specs/ab123/SPEC.md with latest API decisions (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/implement-only-forbidden-update-tests-slug-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 implement-only 输出计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Implement-only Forbidden Update Spec In tests-slug Path\n\n## Summary\n- 结论：用于验证路径包含 tests 也不能豁免 spec 更新任务。\n\n## Flow Decision\n- `flow_type`: `implement-only`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => update docs/specs/ab123-tests/SPEC.md with latest API decisions (skill: $implement-only-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/invalid-flow-type-substring.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"flow_type: normal"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Invalid Flow Type Substring\n\n## Summary\n- 结论：用于验证 malformed flow_type 不会被子串误识别。\n\n## Flow Decision\n- `flow_type`: `normal-fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute local validation tasks (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/invalid-section-order.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Invalid Section Order\n\n## Summary\n- 结论：用于验证 goals-first section order。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Task Orchestration\n- wave: 1\n  - main-agent => implement the change after drafting execution-first notes (skill: $normal-flow)\n\n## Goals\n- Goal 1: lock the intended result before execution\n  This section is intentionally placed too late to violate the goals-first contract.\n\n## Non-goals\n- Do not allow execution-first section ordering.\n\n## Acceptance & Validation\n- The checker must reject this section order.\n\n## Assumptions/Defaults\n- This fixture intentionally violates section order: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/invalid-task-orchestration-content.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Invalid Non-List Content\n\n## Summary\n- 结论：用于验证编排章节出现非列表内容。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\nnote: plain text is invalid\n  - main-agent => run task (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/invalid-user-flow-lock-substring.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"flow_type: normal-fast-track"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Invalid User Flow Lock Substring\n\n## Summary\n- 结论：用于验证非法 user flow lock 文本不会被当作已锁定。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute local validation tasks (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/keep-handoff-log-future-sessions-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Keep Handoff Log Future Sessions Artifact\n\n## Summary\n- 结论：用于验证 `keep` 这类动作也会命中 planning handoff-log artifact 拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: preserve non-persistent planning boundaries\n  The orchestration must not keep a planning handoff-log artifact for future sessions.\n\n## Non-goals\n- Do not allow retained planning handoff-log artifacts inside Task Orchestration.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => keep a handoff log for future sessions (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker rejects retained handoff logs that target future sessions.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises `keep` verb coverage for handoff-log artifacts: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-development-baseline.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 直接给我快车道计划。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Missing Development Baseline\n\n## Summary\n- 结论：示例故意漏掉开发基线字段。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `default_fast_track`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 演示 checker 对开发基线缺失的拦截\n  当前计划省略 `开发基线`，用于验证新合同不会接受这类漏项。\n\n## Non-goals\n- 不演示其他合同错误。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 规划实现与 merge-ready 收口 (skill: $review-agent + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝缺少 `开发基线` 的显式 `$dev-plan` 输出，并停在对应 finding。\n\n## Assumptions/Defaults\n- 这是一个专门用于缺项校验的反例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-flow-question.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"继续"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Demo Missing Flow Question\n\n## Summary\n- 结论：未询问流程类型却直接给计划。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `fallback_default`\n- `lock_status`: `pending_confirmation`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => run fallback path (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 用户尚未明确流程类型：待确认\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-goals.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Missing Goals\n\n## Summary\n- 结论：用于验证缺失 Goals section。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Non-goals\n- 不扩展到 demo 之外。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute local validation tasks (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-non-goals.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Missing Non-goals\n\n## Summary\n- 结论：用于验证缺失 Non-goals section。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => execute local validation tasks (skill: $normal-flow)\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-task-orchestration-task.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Empty Wave\n\n## Summary\n- 结论：用于验证 wave 下缺失任务项。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-task-orchestration.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Missing Orchestration\n\n## Summary\n- 结论：用于验证缺失 Task Orchestration。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/missing-task-skill-binding.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按普通流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Demo Missing Task Skill\n\n## Summary\n- 结论：用于验证任务项缺失 skill 绑定。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: lock the demo scope contract\n  Capture the result boundary, key implementation detail, and success signal before execution arrangement.\n\n## Non-goals\n- Do not expand beyond the demo contract.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => do work without skill\n\n## Acceptance & Validation\n- Demo acceptance for contract replay.\n\n## Assumptions/Defaults\n- 示例仅用于回放验证：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/mixed-plan-cleanup-create-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type": "response_item", "payload": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "按 normal 流程计划"}]}}
+{"type": "response_item", "payload": {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "<proposed_plan>\n# Mixed PLAN.md Cleanup and Create Artifact\n\n## Summary\n- 结论：用于验证“边清理边新建 PLAN.md”仍会被识别为持久计划载体。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: keep the plan non-persistent\n  Task Orchestration must not recreate a persisted plan artifact while pretending to clean legacy references.\n\n## Non-goals\n- Do not allow mixed cleanup/create wording to bypass the artifact ban.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => remove stale `PLAN.md` and create a fresh `PLAN.md` for the next handoff (skill: $normal-flow)\n\n## Acceptance & Validation\n- The checker must still reject mixed cleanup/create PLAN.md tasks.\n\n## Assumptions/Defaults\n- This fixture intentionally exercises mixed PLAN.md cleanup/create wording: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/move-plan-md-handoff-artifact.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"按普通流程计划"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Move PLAN Artifact for Handoff\n\n## Summary\n- 结论：用于验证移动 persisted plan artifact 仍会被拦截。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- Goal 1: persist the generated handoff artifact\n  Move the generated `PLAN.md` into a shared handoff folder for future sessions.\n\n## Non-goals\n- Do not change runtime behavior.\n\n## Task Orchestration\n- wave: 1\n  - main-agent => move generated `PLAN.md` into a shared handoff folder for future sessions (skill: $normal-flow)\n\n## Acceptance & Validation\n- The archived artifact remains available for later handoffs.\n\n## Assumptions/Defaults\n- Shared handoff folder already exists: 已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-agent-profile-invalid.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"按普通流程计划"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Invalid Agent Profile\n\n## Summary\n- 结论：agent profile 使用了模型不支持的 effort。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 验证 profile 校验\n  非法 profile 必须被 checker 拦截。\n\n## Non-goals\n- 不改变业务范围。\n\n## Task Orchestration\n- wave: 1\n  - sub-agent:review [gpt-5.6-luna, ultra] => 只读检查变更 (skill: $normal-flow)\n\n## Acceptance & Validation\n- 非法 effort 时 checker 必须失败。\n\n## Assumptions/Defaults\n- 用于负例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-agent-profile-missing.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"按普通流程计划"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Missing Agent Profile\n\n## Summary\n- 结论：缺少 agent profile。\n\n## Flow Decision\n- `flow_type`: `normal`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n\n## Goals\n- 目标 1: 验证 profile 门禁\n  委派 agent 必须声明模型和 effort。\n\n## Non-goals\n- 不改变业务范围。\n\n## Task Orchestration\n- wave: 1\n  - sub-agent:review => 只读检查变更 (skill: $normal-flow)\n\n## Acceptance & Validation\n- 缺少 profile 时 checker 必须失败。\n\n## Assumptions/Defaults\n- 用于负例：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-aggregate-missing-final-merge-policy.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 走 fast-track，规划一个多 Ticket initiative。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Broken Aggregate Stack\n\n## Summary\n- 结论：这是 aggregate-stack 计划。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `delivery_topology`: `aggregate-stack`\n- `integration_branch`: `prd/demo-initiative`\n- `child_integration_policy`: `ticket-declared`\n- `child_owner_gate_policy`: `evidence-bound`\n- `ticket_plan_policy`: `inherit-approved-plan`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 建立 Ticket 编排\n  创建可以收敛到 aggregate PR 的 Ticket。\n\n## Non-goals\n- 不自动合并最终 PR。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 创建 Ticket 并开始 initiative 编排 (skill: $initiative-flow + $fast-flow)\n\n## Acceptance & Validation\n- 所有 Ticket 都完成验证。\n\n## Assumptions/Defaults\n- GitHub 可用：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-aggregate-missing-initiative-flow.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 走 fast-track，规划一个多 Ticket initiative。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Aggregate Stack Without Initiative Flow\n\n## Summary\n- 结论：用 aggregate-stack 交付多个 Ticket。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `delivery_topology`: `aggregate-stack`\n- `integration_branch`: `prd/demo-initiative`\n- `child_integration_policy`: `ticket-declared`\n- `child_owner_gate_policy`: `evidence-bound`\n- `final_merge_policy`: `owner-explicit`\n- `ticket_plan_policy`: `inherit-approved-plan`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 编排多 Ticket 交付\n  将所有 Ticket 收敛到一个 aggregate PR。\n\n## Non-goals\n- 不自动合并最终 aggregate PR。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 创建多个 Ticket 并推进到 aggregate PR (skill: $fast-flow)\n\n## Acceptance & Validation\n- 所有 Ticket 完成验证并进入最终 PR。\n\n## Assumptions/Defaults\n- GitHub 可用：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-aggregate-non-kebab-integration-branch.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 走 fast-track，规划一个多 Ticket initiative。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Aggregate Stack Invalid Topic\n\n## Summary\n- 结论：这个 aggregate-stack 计划必须拒绝非规范 integration topic。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `delivery_topology`: `aggregate-stack`\n- `integration_branch`: `prd/My_Topic`\n- `child_integration_policy`: `ticket-declared`\n- `child_owner_gate_policy`: `evidence-bound`\n- `final_merge_policy`: `owner-explicit`\n- `ticket_plan_policy`: `inherit-approved-plan`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 拒绝无效 topic\n  防止计划阶段通过而 Ticket handoff 阶段失败。\n\n## Non-goals\n- 不创建不兼容的 initiative。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 验证 aggregate topology 合同 (skill: $initiative-flow + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝非 lowercase kebab-case 的 integration branch。\n\n## Assumptions/Defaults\n- GitHub 可用：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-aggregate-policy-outside-flow-decision.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan 走 fast-track，规划一个多 Ticket initiative。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Aggregate Policy Outside Flow Decision\n\n## Summary\n- 结论：aggregate-stack 的必填策略不能只写在说明文字里。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `delivery_topology`: `aggregate-stack`\n- `integration_branch`: `prd/demo-initiative`\n- `child_integration_policy`: `ticket-declared`\n- `child_owner_gate_policy`: `evidence-bound`\n- `ticket_plan_policy`: `inherit-approved-plan`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 验证字段作用域\n  `final_merge_policy`: `owner-explicit` 仅在此说明，不属于 Flow Decision。\n\n## Non-goals\n- 不自动合并最终 PR。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 创建 Ticket 并开始 initiative 编排 (skill: $initiative-flow + $fast-flow)\n\n## Acceptance & Validation\n- checker 必须拒绝 Flow Decision 之外的 aggregate 必填字段。\n\n## Assumptions/Defaults\n- GitHub 可用：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-default-initiative-eligibility-unproven.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请为这个大型项目规划多个 Ticket。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Unproven Initiative\n\n## Summary\n- 结论：在没有独立验收/合并与 Initiative 机制证据时错误选择 Initiative。\n\n## Flow Decision\n- `flow_type`: `initiative`\n- `flow_source`: `default_initiative_complexity`\n- `lock_status`: `locked`\n- `integration_branch`: `prd/unproven`\n- `initiative_contract_version`: `2`\n- `child_integration_policy`: `ticket-declared`\n- `child_owner_gate_policy`: `evidence-bound`\n- `final_merge_policy`: `owner-explicit`\n- `ticket_plan_policy`: `inherit-approved-plan`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 建立 Ticket\n  把大型项目拆成未证明独立性的 Ticket。\n\n## Non-goals\n- 不自动合并 aggregate PR。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 建立 Initiative (skill: $initiative-flow)\n\n## Acceptance & Validation\n- aggregate PR 达到 ready。\n\n## Assumptions/Defaults\n- Ticket 独立性尚未证明：待确认\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-formal-evidence-predeclaration.jsonl

@@ -0,0 +1 @@
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Formal Evidence Predeclaration\n\n## Summary\n- formal review 只能在 readiness 后运行时创建。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `review_tier`: `Tier 3`\n- `review_rationale`: `current-head proof is required`\n- `runtime_review_strategy`: `readiness 通过后运行时创建 fresh lanes。`\n- `review_profile_recommendation`: `四至六个 lane 建议使用 gpt-5.6-luna + medium pair。`\n- 开发基线：`origin/main`\n- 收口条件：`merge-ready / Step 5C Ready`\n\n## Goals\n- G1: 保持 formal review 运行时边界。\n  计划不预排 formal evidence reviewer。\n\n## Non-goals\n- N1: 不固定 reviewer identity。\n\n## Task Orchestration\n- wave: 1\n  - sub-agent:review [gpt-5.6-luna, medium] => return current-head formal evidence (skill: $fast-flow)\n\n## Acceptance & Validation\n- A1 [contract/direct] runtime review | evidence=`test:review` | assertions=`fresh reviewer`\n\n## Assumptions/Defaults\n- readiness gate 已确定：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-formal-main-agent-predeclaration.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请按 fast-track 规划 formal review。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Main Agent Formal Predeclaration\n\n## Summary\n- 结论：formal review 只能在 readiness 后运行时创建。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- `review_tier`: `Tier 3`\n- `review_rationale`: `当前 candidate 需要 formal evidence。`\n- `runtime_review_strategy`: `readiness 通过后运行时创建 fresh lanes。`\n- `review_profile_recommendation`: `建议使用当前 host 支持的 Luna medium pair。`\n- 开发基线：`origin/main`\n- 收口条件：`merge-ready / Step 5C Ready`\n\n## Goals\n- G1: 保持运行时审查边界。\n  计划不包含 reviewer schedule。\n\n## Non-goals\n- N1: 不锁定具体 reviewer。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => launch formal review lane before readiness (skill: $fast-flow)\n\n## Acceptance & Validation\n- A1 [contract/direct] formal launch | evidence=`test:review` | assertions=`live PR exists,current head,Step 5C Ready`\n\n## Assumptions/Defaults\n- host profile resolution：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-initiative-prerequisite-silent-downgrade.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan，flow_type=initiative。GitHub unavailable；必须阻断，不要降级。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Invalid Silent Downgrade\n\n## Summary\n- 结论：错误地把不可用的 Initiative 静默降级为 fast-track。\n\n## Flow Decision\n- `flow_type`: `fast-track`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 错误降级\n  在 Initiative 前提不可用时继续 direct 实现。\n\n## Non-goals\n- 不等待 GitHub 恢复。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => direct 实现 (skill: $fast-flow)\n\n## Acceptance & Validation\n- PR 达到 merge-ready。\n\n## Assumptions/Defaults\n- GitHub 不可用：已确定\n</proposed_plan>"}]}}

package/toolkit/skills/dev-plan/references/replay-cases/negative-initiative-with-legacy-fast-alias.jsonl

@@ -0,0 +1,2 @@
+{"type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"请用 $dev-plan，flow_type=initiative。至少两个 Ticket 可独立验收、独立合并，并需要 Wave 与 integration branch。"}]}}
+{"type":"response_item","payload":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<proposed_plan>\n# Invalid Mixed Initiative Alias\n\n## Summary\n- 结论：错误混用 Initiative 与 legacy fast alias。\n\n## Flow Decision\n- `flow_type`: `initiative`\n- `flow_source`: `user_explicit`\n- `lock_status`: `locked`\n- 开发基线：`origin/main`\n\n## Goals\n- 目标 1: 交付 Initiative\n  两个 Ticket 分 Wave 独立验收与合并。\n\n## Non-goals\n- 不使用其他顶层 flow。\n\n## Task Orchestration\n- wave: 1\n  - main-agent => 编排 Initiative (skill: $initiative-flow + $fast-pr-delivery)\n\n## Acceptance & Validation\n- aggregate PR 达到 ready。\n\n## Assumptions/Defaults\n- GitHub 与 Codex task 可用：已确定\n</proposed_plan>"}]}}