n8n-nodes-adeu 1.18.1 → 1.18.4

package/README.md

@@ -311,6 +311,11 @@ AI Agents cannot pass binary `.docx` data through JSON arguments anyway — that
 
 ### Apply Edits
 
+**Reasoning** (fill this FIRST):
+```
+={{ $fromAI('Reasoning', `State your reasoning for this batch of edits BEFORE you produce the Changes_JSON array: briefly explain what you intend to change and why (e.g. which clauses, which counterparty positions you are countering, which playbook rule applies). Always write this field first — reasoning through the change before emitting the JSON produces more accurate, better-anchored edits. This text is captured for audit only and does not alter engine behavior. One to three sentences is enough.`, 'string', '') }}
+```
+
 **Source Node Name** (when `Document Source` is `From Another Node`):
 ```
 ={{ $fromAI('Source_Node_Name', `Exact name of the workflow node that produced the .docx binary (string, case-sensitive). Must match the node label in the canvas exactly. If your system prompt specifies which node holds the document, always use that name.`, 'string', 'Read Binary File') }}
@@ -364,6 +369,11 @@ AI Agents cannot pass binary `.docx` data through JSON arguments anyway — that
 
 ### Finalize Document
 
+**Reasoning** (fill this FIRST):
+```
+={{ $fromAI('Reasoning', `State your reasoning for finalizing the document now BEFORE choosing the sanitize mode and options: what state the document is in, why it is ready for distribution, and who it is going to (signer, counterparty, internal). Always write this field first. This text is captured for audit only and does not alter engine behavior. One to three sentences is enough.`, 'string', '') }}
+```
+
 **Source Node Name** (when `Document Source` is `From Another Node`):
 ```
 ={{ $fromAI('Source_Node_Name', `Exact name of the workflow node that produced the .docx binary (string, case-sensitive). Must match the node label exactly.`, 'string', 'Read Binary File') }}
@@ -406,7 +416,8 @@ Because Adeu enforces **Atomic Batch Validation**, any error in the LLM's JSON w
 
 * **"Target text not found"**: The LLM hallucinated a word, altered the spacing, or the text doesn't exist in the baseline document.
 * **"Ambiguous match"**: The LLM used a `target_text` (like "the Company") that appears multiple times. The error details will show you the exact occurrences. Advise the LLM to either include more surrounding context (e.g., "the Company shall indemnify") or use `match_mode: "all"` if the intent is to replace every occurrence.
-* **"Modification targets an active insertion..."**: The LLM tried to `modify` text that another author is currently tracking. Adeu explicitly blocks this to maintain virtual DOM integrity and clean redline threading. You must `accept` or `reject` that prior change first.
+* **"Modification targets an active insertion..."**: The LLM tried to `modify` text that another author is currently tracking. Adeu explicitly blocks this to maintain virtual DOM integrity and clean redline threading. You must `accept` or `reject` that prior change first. (Editing plain text that merely sits under another author's *comment* is allowed — the comment anchor survives the tracked change.)
+* **"...would sweep through a comment range from another author..."**: A `match_mode: "all"` bulk replacement crossed a colleague's comment range. Blind fan-outs are blocked to protect foreign annotations; target the commented text deliberately with `match_mode: "strict"` or `"first"`, or scope the edit outside the comment.
 * **"Read-only elements"**: The LLM tried to modify structural items like cross-references or footnotes.
 * **"Page N exceeds total_pages"**: The LLM requested a page beyond what the document has. Have it call `Extract Outline` first to discover the page count.