DeliveryPilot Conduit
Requirement → Code Graph (Stage 1: Repo Index)
未导入仓库
DeliveryPilot Conduit Workspace
从 PM 需求到可提测 PR 的 AI 交付工作台
输入一个自然语言需求,系统会完成澄清、方案拆解、上下文选择、Patch 生成、测试验证和 PR Evidence,并保留可重放的事件证据。
Recommended Next Step
System Health
Workspace Status
Public URL
Official Conduit Repo
Strict Verification
Skill Count
Benchmark Score
Open Reviews
Last Demo Run
Local
Public
Blocked
HTTPS
Last Smoke Test
仓库导入
不会自动下载远程仓库。先把 Conduit 仓库放到本机,然后在这里导入路径。
文件树
0 files
尚未生成索引
仓库概览
package scripts
模块地图
搜索
输入关键字并搜索
交付流水线(Stage 2:Contract → Plan → Location → Evidence)
未创建会话
澄清问题
点击“生成澄清问题”
PRD 契约(可编辑)
方案拆解(JSON,可编辑)
模块定位(Impact Heatmap)
Target Files
点击“模块定位”
Test Files
Do Not Touch
人工边界调整
Evidence Ledger
点击“刷新证据账本”
Observability(P1)
Skill Marketplace(Stage 5)
Skills
点击“刷新 Skill 列表”
Dry Run
Context Strategy Lab(Stage 5)
点击 “Compare Strategies” 生成 minimal / balanced / defensive 对比
Delivery Memory Loop(Stage 5)
Memory Library
Suggestion
说明:建议包含 suggestedSkill / contextStrategy / selectedFiles / excludedFiles / doNotTouch / testStrategy / confidence / reuseDecision,并会写入 workflow events(memory_written / memory_suggested / memory_applied)。
Requirement Benchmark Suite(Stage 5)
Benchmark Cases
点击“刷新 Cases”
Scoreboard
Selected Case Detail
说明:Benchmark v1 目标是评估 Skill/Clarification/PRD/Plan/Context/Cross-stack Gate(coverImage)能力,不要求所有 case 都生成 patch。L3 case 必须体现“先澄清,不直接 patch”。
Demo Scenario Runner
Scenario List
点击 Refresh Scenarios
Run Detail
Step Timeline
运行场景后显示
Evidence Links
说明:Demo Scenario Runner 将 Skill、Context、Memory、Benchmark、Review、Replay 串成可一键运行的回归/演示场景,输出 ordered steps 与 evidenceRefs。
Human Review Workbench(P1)
Summary
Decision(for selected item)
Review Queue
点击 Generate/Refresh
Selected Item Detail
Controlled Replay:Affected Stages + Safety Checks
Artifact Diffs
Replay History
说明:Review Workbench 以 Benchmark 失败/弱点队列为主,支持 approve/reject/request-replay/close;Controlled Replay 支持 request_only、dry_run、execute_downstream 和 rollback,execute 需要人工 approval code。
Evaluation Dashboard(P1)
Benchmark Scoreboard
Capability Metrics
AI Cost Summary
说明:Evaluation Dashboard 聚合 Benchmark Scoreboard、Skill Accuracy、Context Strategy Distribution、Memory Reuse Decisions、Review Queue Open Items、Cross-stack Gate、Replay success rate、Strict verification status、Validation pass rate 和 AI latency/usage/cost。
Governance Policy Engine(P1)
Policies
Policy Input JSON
Decision Summary
说明:Policy Engine 将 scope guard、secret hygiene、cross-stack gate 和 human approval 统一为可审计 policy decisions,并保留 evidenceRefs。
Final Evidence Center(P1)
Coverage Matrix
Verification Commands
Export Result
说明:Final Evidence Center 汇总 official L1、coverImage cross-stack、Memory、Benchmark、Review、Controlled Replay、Observability 和 strict verification 证据,并支持离线 JSON/Markdown/HTML 导出。
Patch Theatre(Stage 3)
Unified Diff
Spec-to-Diff Trace Matrix
生成 patch 后显示
DoNotTouch / Scope Guard
Test Arena(Stage 3)
QA Report(Stage 3)
PR & CI Manager
PR Record
CI Status
说明:package 模式生成 branch / commitSha / patch.diff / pr-summary.md / validation.log / rollback-plan.md;没有真实 GitHub 集成时不会伪造 PR URL,而是记录 GITHUB_PR_BLOCKED。
Preview Deploy(Stage 4)
Deployment Plan
Deployment / Smoke
Native Conduit Preview Adapter
Native Preview Plan / Status
Dependency / Health Check
说明:contract preview 仍是快速稳定路径;native preview 只在真实 health check 通过后显示 URL,否则记录 NATIVE_PREVIEW_BLOCKED,不伪造成功。
Knowledge Flywheel(Stage 4)
Reuse Replay(Stage 4)
Evidence Hub(Stage 4)