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).
weichen
merged commit ebec49db3d into main2026-10-10 18:22:26 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
E4 修复（#131 的首份 eval 对照暴露回归：工具失败 10→24、调用 63→166，转录实证是 read→edit 循环被 read_file/grep 尾注污染——模型把尾注当外改动反复重读重试）。修复：来源标记只打真来源（检索类 + inputs/ 材料读，新增 isEvidenceRead 判定）；grep 与自产文件读一律不打。附回归锚点 TestEvidenceLedgerOnlyTagsMaterialReads；go test ./... 全绿。重跑 eval 在 Dev 侧。