fix(agent): unambiguous document listing format for LLM parsing

2026-09-01 12:44:53 -04:00
parent c738105932
commit 15a16a8fe0
5 changed files with 81 additions and 40 deletions
@@ -165,7 +165,8 @@ example-record-file.json"), the model can extend its own context with two
 server-side tools — on **grounded** (high-relevance) turns only:

 * **`list_documents`** — lists every indexed document, one
-  `source/path — title` line each (the same order as the Sources page);
+  `source: X | path: Y | title: Z` line each (the same order as the
+  Sources page);
 * **`read_document(source, path)`** — appends the **full** text of
  one more indexed document to the context (never truncated).