wuyang
93 lines
3.2 KiB
JSON
93 lines
3.2 KiB
JSON
[
|
|
{
|
|
"id": "BASE-001",
|
|
"title": "统一 Agent 路径",
|
|
"summary": "删除 Chat / Work 双模式，所有对话通过同一套可观测 Agent Loop；减少前端状态和后端分叉。",
|
|
"area": "product",
|
|
"status": "validated",
|
|
"version": "agent-loop-v3",
|
|
"metrics": ["维护面", "交互一致性"]
|
|
},
|
|
{
|
|
"id": "BASE-002",
|
|
"title": "安全读取并行，变更串行",
|
|
"summary": "连续 parallel_safe 调用并发执行，写文件、命令和状态变更维持模型给出的顺序。",
|
|
"area": "scheduler",
|
|
"status": "baseline",
|
|
"version": "safe-parallel-v1",
|
|
"metrics": ["wall time", "determinism"]
|
|
},
|
|
{
|
|
"id": "BASE-003",
|
|
"title": "最近可见上下文",
|
|
"summary": "清除旧工具详情，按模型字符预算保留最近消息，并注入最多 8 条持久记忆。",
|
|
"area": "context",
|
|
"status": "baseline",
|
|
"version": "recent-visible-v1",
|
|
"metrics": ["token proxy", "task success"]
|
|
},
|
|
{
|
|
"id": "BASE-004",
|
|
"title": "证据驱动的完成判定",
|
|
"summary": "文件、代码和报告任务必须出现写入与后续验证；未解决的命令失败会阻止虚假完成。",
|
|
"area": "reliability",
|
|
"status": "validated",
|
|
"version": "evidence-gate-v1",
|
|
"metrics": ["false completion", "artifact validity"]
|
|
},
|
|
{
|
|
"id": "BASE-005",
|
|
"title": "持久 Python 工具链",
|
|
"summary": "用户依赖安装到 /workspace/.venv；镜像升级保留环境，pipefail 防止安装失败被管道尾部掩盖。",
|
|
"area": "workspace",
|
|
"status": "validated",
|
|
"version": "workspace-python-v2",
|
|
"metrics": ["install success", "restart survival"]
|
|
},
|
|
{
|
|
"id": "EXP-006",
|
|
"title": "基于相关性的记忆召回",
|
|
"summary": "比较固定最近记忆、关键词召回和向量召回对长期偏好遵循、上下文成本与错误注入的影响。",
|
|
"area": "memory",
|
|
"status": "backlog",
|
|
"version": "proposal",
|
|
"metrics": ["recall@k", "task success", "context cost"]
|
|
},
|
|
{
|
|
"id": "EXP-007",
|
|
"title": "依赖感知工具调度",
|
|
"summary": "从显式工具属性推进到调用间读写集分析，评估是否能扩大安全并行范围。",
|
|
"area": "scheduler",
|
|
"status": "backlog",
|
|
"version": "proposal",
|
|
"metrics": ["wall time", "race failures", "parallel ratio"]
|
|
},
|
|
{
|
|
"id": "EXP-008",
|
|
"title": "自适应模型路由",
|
|
"summary": "以任务复杂度和中途失败信号决定 Luna、Terra、Sol 或 DeepSeek，而不是让一次选择锁定整个任务。",
|
|
"area": "model-routing",
|
|
"status": "backlog",
|
|
"version": "proposal",
|
|
"metrics": ["task success", "latency", "API cost"]
|
|
},
|
|
{
|
|
"id": "EXP-009",
|
|
"title": "受限多 Agent 拓扑",
|
|
"summary": "比较单循环、只读并行委派和角色化子 Agent，在复杂代码任务中的收益与上下文整合成本。",
|
|
"area": "delegation",
|
|
"status": "backlog",
|
|
"version": "proposal",
|
|
"metrics": ["task success", "wall time", "tool calls"]
|
|
},
|
|
{
|
|
"id": "EXP-010",
|
|
"title": "上下文压缩与可逆摘要",
|
|
"summary": "在最近消息预算之外保存结构化任务状态，并允许模型按需取回原始证据，减少长任务遗忘。",
|
|
"area": "context",
|
|
"status": "backlog",
|
|
"version": "proposal",
|
|
"metrics": ["long-horizon success", "context cost", "retrieval count"]
|
|
}
|
|
]
|