562 lines
18 KiB
JSON
562 lines
18 KiB
JSON
{
|
||
"directed": true,
|
||
"nodes": [
|
||
{
|
||
"id": "plan:infrastructure-setup",
|
||
"label": "项目基础设施初始化计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:core-agent-adapters-llm",
|
||
"label": "core/agent/ + adapters/llm 基础设施设计",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:core-agent-adapters-llm",
|
||
"label": "core/agent/ + adapters/llm 基础设施实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:tree-module-vertical-slice",
|
||
"label": "建树模块竖切设计:数据结构 + 建树 + 修复 + 迁移",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:tree-module-vertical-slice",
|
||
"label": "建树模块竖切实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:question-gen",
|
||
"label": "question_gen 模块实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:2026-07-07-search-module-design",
|
||
"label": "搜索 Agent 装配层设计(app/search/)",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:2026-07-07-search-module",
|
||
"label": "app/search/ 搜索 Agent 装配层实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:app-harness",
|
||
"label": "app/harness/ 训练循环编排层实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:tree-repair-resilience",
|
||
"label": "建树修复管线:熔断根因修复 + 断点续跑 + 并发改造",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:tree-repair-resilience",
|
||
"label": "建树修复管线三项改造实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:paper-main-figure",
|
||
"label": "论文主图:Self-Evolving Search Agent 推理训练闭环",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "design:question-gen-synth",
|
||
"label": "赛题生成工具设计",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:question-gen-synth",
|
||
"label": "赛题生成工具实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:main-inference-entry",
|
||
"label": "main.py 推理入口 + 初始 Prompt 集设计",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:main-inference-entry",
|
||
"label": "main.py 推理入口 + 初始 Prompt 集实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:agent-runtime-fixes",
|
||
"label": "Spec-1 Agent 执行环境修复(解析容错+步级重试+摘要附实体)",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "design:batch-tree-build",
|
||
"label": "Spec-2 建树批量并行入口",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "design:question-gen-v2",
|
||
"label": "Spec-3 出题管线 v2(失败机理靶向+逐题质量门)",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:agent-runtime-fixes-plan",
|
||
"label": "Spec-1 Agent 执行环境修复实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "finding:eval-spec1check",
|
||
"label": "Harness 评估: Spec-1 修复验证 (infer_spec1check)",
|
||
"type": "finding"
|
||
},
|
||
{
|
||
"id": "plan:batch-tree-build-plan",
|
||
"label": "Spec-2 建树批量并行实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "schema:question-gen-runs",
|
||
"label": "表结构: question_gen_runs(出题批次)",
|
||
"type": "schema"
|
||
},
|
||
{
|
||
"id": "schema:question-gen-items",
|
||
"label": "表结构: question_gen_items(逐题门判定)",
|
||
"type": "schema"
|
||
},
|
||
{
|
||
"id": "metric:qgen-gate-rejection-rate",
|
||
"label": "出题四门总拦截率",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "metric:qgen-regen-convergence",
|
||
"label": "重出收敛率(3轮内过门)",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "metric:qgen-acceptance-rate",
|
||
"label": "最终接受率",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "metric:qgen-answer-uniformity",
|
||
"label": "答案位置分布均匀性",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "plan:2026-07-11-question-gen-v2",
|
||
"label": "出题管线 v2 实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:per-category-pool-strategy",
|
||
"label": "Per-Category Pool Strategy 设计",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:per-category-pool-strategy",
|
||
"label": "Per-Category Pool Strategy 实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:action-recognition-training",
|
||
"label": "Action Recognition 单题型首次训练实验计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:task-type-strategy-framework",
|
||
"label": "TaskTypeStrategy 框架实现计划 (Plan A)",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:action-recognition-strategy",
|
||
"label": "ActionRecognitionStrategy 特化实现计划 (Plan B)",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:maintenance-pool",
|
||
"label": "训练池 Maintenance 正确题自动补入机制",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:maintenance-pool",
|
||
"label": "Maintenance Pool 自动补入实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:grounded-question-gen-phaseA",
|
||
"label": "Grounded Question-Gen Phase A",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:adversarial-question-gen-phaseB",
|
||
"label": "Adversarial Question-Gen Phase B",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:question-gen-v3-phase1-contract",
|
||
"label": "question-gen v3 Phase1 契约地基实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:results-driven-video-split",
|
||
"label": "结果驱动的视频级 train/val/test 切分(替代自造题模块)",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:results-driven-video-split-plan",
|
||
"label": "结果驱动的视频级切分实现计划",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "schema:baseline-diagnosis",
|
||
"label": "表结构: baseline_diagnosis(逐题诊断信号)",
|
||
"type": "schema"
|
||
},
|
||
{
|
||
"id": "schema:split-manifest",
|
||
"label": "表结构: split_manifest(切分冻结溯源)",
|
||
"type": "schema"
|
||
},
|
||
{
|
||
"id": "metric:split-signal-tier-distribution",
|
||
"label": "指标: 诊断信号 tier 分布(T0/T1/T2/uncertain 占比)",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "metric:split-cell-coverage",
|
||
"label": "指标: 48格(task_type×error_type)多样性覆盖率",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "metric:split-floor-and-representativeness",
|
||
"label": "指标: floor 达标率 + test 代表性偏差",
|
||
"type": "metric"
|
||
},
|
||
{
|
||
"id": "design:fix-diagnosis-tree-data-link",
|
||
"label": "修复诊断 tree_data 断链 bug(TRM4→TRM5 迁移 regression)",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:fix-diagnosis-tree-data-link-plan",
|
||
"label": "实现计划: 修复诊断 tree_data 断链 bug",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "design:preflight-fixes",
|
||
"label": "训练前缺陷修复设计",
|
||
"type": "design"
|
||
},
|
||
{
|
||
"id": "plan:preflight-wp1-asset-migration",
|
||
"label": "WP1 资产迁移",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:preflight-wp2-split-wiring",
|
||
"label": "WP2 切分与接线",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:preflight-wp3-train-loop",
|
||
"label": "WP3 训练循环与进化引擎",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "plan:preflight-wp4-resilience",
|
||
"label": "WP4 韧性与持久化",
|
||
"type": "plan"
|
||
},
|
||
{
|
||
"id": "review:preflight-final-review",
|
||
"label": "训练前修复分支终审",
|
||
"type": "review"
|
||
},
|
||
{
|
||
"id": "design:telemetry-concurrency-fix",
|
||
"label": "遥测 SQLite 高并发写锁修复",
|
||
"type": "design"
|
||
}
|
||
],
|
||
"links": [
|
||
{
|
||
"source": "plan:core-agent-adapters-llm",
|
||
"target": "design:core-agent-adapters-llm",
|
||
"relation": "implements",
|
||
"evidence": "计划实现设计文档中定义的全异步 AgentLoop + 四层治理栈",
|
||
"added": "2026-07-07T02:25:32.349931+00:00"
|
||
},
|
||
{
|
||
"source": "plan:tree-module-vertical-slice",
|
||
"target": "design:tree-module-vertical-slice",
|
||
"relation": "implements",
|
||
"evidence": "计划逐 Task 实现设计文档中的 11 个模块",
|
||
"added": "2026-07-07T05:27:02.953166+00:00"
|
||
},
|
||
{
|
||
"source": "plan:question-gen",
|
||
"target": "design:question-gen",
|
||
"relation": "implements",
|
||
"evidence": "实现计划覆盖设计文档的全部需求",
|
||
"added": "2026-07-07T08:32:53.887071+00:00"
|
||
},
|
||
{
|
||
"source": "plan:2026-07-07-search-module",
|
||
"target": "design:2026-07-07-search-module-design",
|
||
"relation": "implements",
|
||
"evidence": "实现搜索 Agent 装配层设计",
|
||
"added": "2026-07-07T09:36:21.467921+00:00"
|
||
},
|
||
{
|
||
"source": "plan:app-harness",
|
||
"target": "design:app-harness-design",
|
||
"relation": "implements",
|
||
"evidence": "实现 2026-07-07-app-harness-design.md 的 14 文件训练循环编排层",
|
||
"added": "2026-07-07T15:45:08.729979+00:00"
|
||
},
|
||
{
|
||
"source": "plan:tree-repair-resilience",
|
||
"target": "design:tree-repair-resilience",
|
||
"relation": "implements",
|
||
"evidence": "实现设计文档的三项改造:遥测加固+断点续跑+并发",
|
||
"added": "2026-07-09T04:08:15.312470+00:00"
|
||
},
|
||
{
|
||
"source": "plan:question-gen-synth",
|
||
"target": "design:question-gen-synth",
|
||
"relation": "implements",
|
||
"evidence": "计划实现设计文档中定义的 synthesizer + factory + CLI 三模块",
|
||
"added": "2026-07-09T09:05:43.697644+00:00"
|
||
},
|
||
{
|
||
"source": "plan:main-inference-entry",
|
||
"target": "design:main-inference-entry",
|
||
"relation": "implements",
|
||
"evidence": "实现设计文档中定义的 main.py + deps_router + skills/v1",
|
||
"added": "2026-07-09T14:43:06.084216+00:00"
|
||
},
|
||
{
|
||
"source": "plan:agent-runtime-fixes-plan",
|
||
"target": "design:agent-runtime-fixes",
|
||
"relation": "implements",
|
||
"evidence": "实现 Spec-1 三处改动 A1/A2/B",
|
||
"added": "2026-07-11T12:06:25.879643+00:00"
|
||
},
|
||
{
|
||
"source": "plan:batch-tree-build-plan",
|
||
"target": "design:batch-tree-build",
|
||
"relation": "implements",
|
||
"evidence": "实现 Spec-2 四任务",
|
||
"added": "2026-07-11T15:07:06.178664+00:00"
|
||
},
|
||
{
|
||
"source": "metric:qgen-gate-rejection-rate",
|
||
"target": "schema:question-gen-items",
|
||
"relation": "measures",
|
||
"evidence": "从 question_gen_items 表 attempt=1 行聚合计算",
|
||
"added": "2026-07-12T02:34:28.728290+00:00"
|
||
},
|
||
{
|
||
"source": "metric:qgen-regen-convergence",
|
||
"target": "schema:question-gen-items",
|
||
"relation": "measures",
|
||
"evidence": "按 slot_id 聚合 final_status 计算收敛率",
|
||
"added": "2026-07-12T02:34:29.858363+00:00"
|
||
},
|
||
{
|
||
"source": "metric:qgen-acceptance-rate",
|
||
"target": "schema:question-gen-runs",
|
||
"relation": "measures",
|
||
"evidence": "直接读取 runs 表 accepted/total_slots",
|
||
"added": "2026-07-12T02:34:30.989357+00:00"
|
||
},
|
||
{
|
||
"source": "schema:question-gen-runs",
|
||
"target": "design:2026-07-11-question-gen-v2",
|
||
"relation": "implements",
|
||
"evidence": "设计 §5 运行时数据要求",
|
||
"added": "2026-07-12T02:34:32.121484+00:00"
|
||
},
|
||
{
|
||
"source": "schema:question-gen-items",
|
||
"target": "design:2026-07-11-question-gen-v2",
|
||
"relation": "implements",
|
||
"evidence": "设计 §5 逐题可追溯要求",
|
||
"added": "2026-07-12T02:34:33.267570+00:00"
|
||
},
|
||
{
|
||
"source": "plan:2026-07-11-question-gen-v2",
|
||
"target": "design:2026-07-11-question-gen-v2",
|
||
"relation": "implements",
|
||
"evidence": "Spec-3 设计的实现计划",
|
||
"added": "2026-07-12T02:57:39.569968+00:00"
|
||
},
|
||
{
|
||
"source": "plan:per-category-pool-strategy",
|
||
"target": "design:per-category-pool-strategy",
|
||
"relation": "implements",
|
||
"evidence": "实现 PoolStrategy Protocol + PerCategoryPoolStrategy 设计",
|
||
"added": "2026-07-13T02:26:58.551190+00:00"
|
||
},
|
||
{
|
||
"source": "plan:action-recognition-training",
|
||
"target": "design:action-recognition-training",
|
||
"relation": "implements",
|
||
"evidence": "计划实现设计文档中的 2 处代码修改 + 实验配置 + 训练脚本",
|
||
"added": "2026-07-14T04:50:15.986586+00:00"
|
||
},
|
||
{
|
||
"source": "plan:task-type-strategy-framework",
|
||
"target": "design:task-type-strategy",
|
||
"relation": "implements",
|
||
"evidence": "Plan A 实现设计中的框架层(Protocol + Base + pipeline 集成)",
|
||
"added": "2026-07-14T09:15:22.951263+00:00"
|
||
},
|
||
{
|
||
"source": "plan:action-recognition-strategy",
|
||
"target": "design:task-type-strategy",
|
||
"relation": "implements",
|
||
"evidence": "Plan B implements design §4: ActionRecognitionStrategy with 6 SubPatterns",
|
||
"added": "2026-07-14T10:34:27.079088+00:00"
|
||
},
|
||
{
|
||
"source": "design:maintenance-pool",
|
||
"target": "design:task-type-strategy",
|
||
"relation": "extends",
|
||
"evidence": "maintenance pool supplements the per-category pool strategy to support SubPattern-targeted training",
|
||
"added": "2026-07-14T14:11:13.527027+00:00"
|
||
},
|
||
{
|
||
"source": "plan:maintenance-pool",
|
||
"target": "design:maintenance-pool",
|
||
"relation": "implements",
|
||
"evidence": "Implements maintenance pool auto-supplement in PerCategoryPoolStrategy",
|
||
"added": "2026-07-14T14:22:44.443012+00:00"
|
||
},
|
||
{
|
||
"source": "plan:grounded-question-gen-phaseA",
|
||
"target": "design:grounded-question-gen-phaseA",
|
||
"relation": "implements",
|
||
"evidence": "Phase A 实现计划",
|
||
"added": "2026-07-14T18:41:35.899803+00:00"
|
||
},
|
||
{
|
||
"source": "plan:adversarial-question-gen-phaseB",
|
||
"target": "design:adversarial-question-gen-phaseB",
|
||
"relation": "implements",
|
||
"evidence": "Phase B 实现计划",
|
||
"added": "2026-07-14T21:09:48.115521+00:00"
|
||
},
|
||
{
|
||
"source": "schema:v3-question-gen-logging",
|
||
"target": "design:question-gen-v3-construction-paradigm",
|
||
"relation": "implements",
|
||
"evidence": "v3 出题运行时数据 schema 实现设计 §12.1",
|
||
"added": "2026-07-15T09:18:41.713855+00:00"
|
||
},
|
||
{
|
||
"source": "plan:question-gen-v3-phase1-contract",
|
||
"target": "design:question-gen-v3-construction-paradigm",
|
||
"relation": "implements",
|
||
"evidence": "Phase1 契约地基",
|
||
"added": "2026-07-15T09:22:08.800078+00:00"
|
||
},
|
||
{
|
||
"source": "plan:results-driven-video-split-plan",
|
||
"target": "design:results-driven-video-split",
|
||
"relation": "implements",
|
||
"evidence": "实现结果驱动视频级切分设计",
|
||
"added": "2026-07-15T15:27:39.569247+00:00"
|
||
},
|
||
{
|
||
"source": "schema:baseline-diagnosis",
|
||
"target": "design:results-driven-video-split",
|
||
"relation": "implements",
|
||
"evidence": "逐题诊断信号表",
|
||
"added": "2026-07-15T15:42:38.107624+00:00"
|
||
},
|
||
{
|
||
"source": "schema:split-manifest",
|
||
"target": "design:results-driven-video-split",
|
||
"relation": "implements",
|
||
"evidence": "切分冻结溯源",
|
||
"added": "2026-07-15T15:42:38.147922+00:00"
|
||
},
|
||
{
|
||
"source": "metric:split-signal-tier-distribution",
|
||
"target": "schema:baseline-diagnosis",
|
||
"relation": "measures",
|
||
"evidence": "tier 分布",
|
||
"added": "2026-07-15T15:42:38.187336+00:00"
|
||
},
|
||
{
|
||
"source": "metric:split-cell-coverage",
|
||
"target": "schema:baseline-diagnosis",
|
||
"relation": "measures",
|
||
"evidence": "48格覆盖",
|
||
"added": "2026-07-15T15:42:38.228857+00:00"
|
||
},
|
||
{
|
||
"source": "metric:split-floor-and-representativeness",
|
||
"target": "schema:split-manifest",
|
||
"relation": "measures",
|
||
"evidence": "floor+代表性",
|
||
"added": "2026-07-15T15:42:38.269455+00:00"
|
||
},
|
||
{
|
||
"source": "design:fix-diagnosis-tree-data-link",
|
||
"target": "design:results-driven-video-split",
|
||
"relation": "informs",
|
||
"evidence": "修复诊断 error_type 污染,恢复 video-split 多样性维真实信号",
|
||
"added": "2026-07-16T01:31:36.665025+00:00"
|
||
},
|
||
{
|
||
"source": "design:fix-diagnosis-tree-data-link",
|
||
"target": "schema:baseline-diagnosis",
|
||
"relation": "refines",
|
||
"evidence": "修正 error_type/evolution_target 列取值不再坍缩",
|
||
"added": "2026-07-16T01:31:37.792648+00:00"
|
||
},
|
||
{
|
||
"source": "plan:fix-diagnosis-tree-data-link-plan",
|
||
"target": "design:fix-diagnosis-tree-data-link",
|
||
"relation": "implements",
|
||
"evidence": "实现修复设计的 5 个 Task",
|
||
"added": "2026-07-16T02:01:19.350441+00:00"
|
||
},
|
||
{
|
||
"source": "plan:preflight-wp1-asset-migration",
|
||
"target": "design:preflight-fixes",
|
||
"relation": "implements",
|
||
"evidence": "四工作包实现训练前缺陷修复设计",
|
||
"added": "2026-07-16T08:32:42.737883+00:00"
|
||
},
|
||
{
|
||
"source": "plan:preflight-wp2-split-wiring",
|
||
"target": "design:preflight-fixes",
|
||
"relation": "implements",
|
||
"evidence": "四工作包实现训练前缺陷修复设计",
|
||
"added": "2026-07-16T08:32:42.822569+00:00"
|
||
},
|
||
{
|
||
"source": "plan:preflight-wp3-train-loop",
|
||
"target": "design:preflight-fixes",
|
||
"relation": "implements",
|
||
"evidence": "四工作包实现训练前缺陷修复设计",
|
||
"added": "2026-07-16T08:32:42.906881+00:00"
|
||
},
|
||
{
|
||
"source": "plan:preflight-wp4-resilience",
|
||
"target": "design:preflight-fixes",
|
||
"relation": "implements",
|
||
"evidence": "四工作包实现训练前缺陷修复设计",
|
||
"added": "2026-07-16T08:32:42.990273+00:00"
|
||
},
|
||
{
|
||
"source": "review:preflight-final-review",
|
||
"target": "design:preflight-fixes",
|
||
"relation": "informs",
|
||
"evidence": "跨 task 终审确认设计 21 项缺陷全部落地 + 4 项集成发现",
|
||
"added": "2026-07-16T11:06:43.709183+00:00"
|
||
}
|
||
]
|
||
} |