Point backend at binary write guard and text indexing

Why: pseudo-binary Office writes and unsearchable generated documents
were the two pieces of the closed docx PR that main still needs.

Evidence: backend 3e5699c; go test ./... 19 packages ok. Dev #99 and
Backend #27 are closed as superseded.

Impact: gitlink only. Merge after Dev #113 so the refusal text names
tools that are already on main.

Refs: task feature/binary-doc-index
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-10-01 04:12:26 +00:00
co-authored by Cursor
parent 870f2687cf
commit 90a3a1d722
2 changed files with 8 additions and 7 deletions
+7 -6
View File
@@ -1,16 +1,17 @@
# feature/binary-doc-index 任务卡
任务主记录:<PR 链接,task-finish 时填写>;状态:进行中;owner:weichen
任务主记录:<PR 链接,推送后回填>;状态:进行中;owner:weichen
## 基线与授权
- 权威仓:ssh://git@git-ssh.u1680832.nyat.app:31411/weichen/Agent-System-Dev.git;目标分支:main;R0(initial_base_sha)= 4c4071e5d8e256dd8f82ba9c74efa1effd1e9df3
- 工作区:/home/weichen/projects/Agent-System-Dev-wt-feature-binary-doc-index(worktree);分支:feature/binary-doc-index
- 授权与交付终点:<本次允许的动作与终点;未授权事项写明>
- 授权与交付终点:重放 #99 里仍然有效的两项(写侧护栏、二进制工件抽文本再索引)。不恢复 format=docx。合入顺序在 run_shell/run_python(Dev #113)之后。合入由所有者执行。
## 目标与非目标
<预期结果、受影响入口/模块/契约;明确不做什么。>
- 目标:write_artifact 与 fs_write_file 拒绝 .doc/.docx/.xls/.xlsx/.xlsm/.ppt/.pptx/.pdf,文案指向 run_python + register_artifact。二进制 mime 的工件经 ingest.Parse 抽出文本后才进索引。
- 非目标:不带回 MarkdownToDocx 参数;不改上传路径的解析。
## 同步记录
@@ -20,6 +21,6 @@
## 结果与验证(完成后填写)
- 结果:
- 验证:
- 影响与剩余项:
- 结果:Backend feature/binary-doc-index @ 3e5699c。Dev #99 与 Backend #27 已关闭并注明被 agent-native 路线取代。
- 验证:go test ./... 19 包 ok(含 Office 扩展拒绝、docgen docx 可检索、坏 ZIP 不入库)。
- 影响与剩余项:请在 Dev #113 合入后再合本 PR。