v0.5.1: disable apply_patch in agents prone to append-mode failures

Root cause: apply_patch finds anchor lines in read-cached file state,
but file may have been modified between read and patch, causing stalls.

Changes:
- dr-verifier: disable apply_patch AND edit; force read-then-write protocol for evidence file appends
- dr-analyst: document write-preferred protocol for sources.jsonl appends
- dr-polisher: disable apply_patch; keep edit for small string replacements
- dr-editor-in-chief / dr-translator: disable apply_patch

Recovery procedure documented in dr-verifier for write failures.

.opencode/agents/dr-polisher.md

@@ -7,6 +7,8 @@ temperature: 0.4
 tools:
   read: true
   edit: true
+  write: true
+  apply_patch: false
   bash: true
   skill: true
 permission:
@@ -22,6 +24,17 @@ permission:
     "*": deny
 ---
 
+## File Writing Protocol (v0.5.1)
+
+- `edit` tool is OK for **small, precise string replacements** (e.g., replacing a禁用词 like "赋能" → "帮助"). These are safe because the search string is short and unique.
+- `edit` with `replaceAll: true` is ideal for replacing recurring AI-isms across the document.
+- **Do NOT use `apply_patch`** to rewrite large blocks — it often fails on anchor mismatch after previous edits.
+- **If you need to rewrite a large block** (e.g., restructure a whole paragraph), use the read-then-write protocol:
+  1. `read` the file
+  2. Compose full new content in memory
+  3. `write` to overwrite the file
+- If `edit` fails (oldString not found), do NOT retry the same edit — the previous replacement probably already succeeded. Re-read the file to confirm.
+
 # 角色：dr-polisher — 中文润色与输出卫生
 
 你是生物医药报告的中文编辑。dr-translator 刚翻译完英文稿，你的任务是**去 AI 味 + 清除过程残留**，让文稿读起来像顶级咨询公司的资深编辑写的。