weichen
03b4fdabaf
ci / vet-and-test (pull_request) Successful in 42s
Why: The first E4 live comparison regressed badly (toolFailures 10->24, toolCalls 63->166) and the instance transcript shows the loop: tagging kernel read_file/grep results put a trailing [src_N] line on the model's own workspace files, the model treated it as external tampering, and re-read/re-edit cycles cascaded into the read-before- write and file-changed guards. Why: The ledger only ever needed SOURCES - searches always, and workspace reads only under inputs/ (the upload material area). Grep cannot distinguish materials from self-produced files, so it stays untagged. Evidence: go test ./... green; new anchor TestEvidenceLedger OnlyTagsMaterialReads pins the inputs/-only rule; the re-run live comparison follows on the Dev side. Impact: evidenceTools loses read_file/grep; isEvidenceRead gates workspace reads to inputs/; everything else (search tags, escalation reminders, prompts) unchanged. Refs: Dev task feature/agent-e4-escalation-ledger (fix-up of #131).
Agent-System-Backend
对话系统后端：Go 模块化单体，默认构建为单二进制（go:embed 内嵌前端与嵌入式 SQLite 存储）。组合 Agent-Native / Agent-Squad / Agent-Intent 生态，依赖 agent-system-core 契约。
契约与架构见 Agent-System-Documents 设计方案与架构文档；开发规范见 development-guidelines（Dev 仓 development/guidelines）。本仓为 Agent-System 多仓组合的组成部分。