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

tests/e2e/mock_llm.py

@@ -65,9 +65,10 @@ Implements just enough of the aipi surface:
         ``call_0``, no arguments), ``finish_reason: "tool_calls"``, no
         content;
       * request 2 (a ``tool``-role catalog result in the messages):
-        parse the FIRST catalog line (``source/path — title`` → split on
-        ``" — "`` → ``rsplit("/", 1)``) and stream a ``tool_calls`` delta
-        calling ``read_document`` on it (id ``call_1``);
+        parse the FIRST catalog line (``source: X | path: Y | title: Z``
+        — the labeled ``source:`` / ``path:`` fields, phase 63) and
+        stream a ``tool_calls`` delta calling ``read_document`` on it
+        (id ``call_1``);
       * request 3 (a ``tool``-role read result in the messages): a
         content answer, deterministic: ``Read <source/path>. <first 80
         chars of the read document's content>`` — so a suite can assert
@@ -269,6 +270,14 @@ TABLE_ANSWER = (
 #: ``_execute_tool``): ``"Document <source/path>:\n<content>"``.
 _READ_RESULT_PREFIX = "Document "
 
+#: One line of the agent's ``list_documents`` output (app.rag.agent
+#: ``_execute_tool``, phase 63): labeled, pipe-delimited fields —
+#: ``source: X | path: Y | title: Z`` — unambiguous for LLM parsing even
+#: when the path contains ``/`` characters.
+_CATALOG_LINE_RE = re.compile(
+    r"^source: (?P<source>.+?) \| path: (?P<path>.+?) \| title: .+$"
+)
+
 
 def _read_results(body: dict[str, Any]) -> list[tuple[str, str]]:
     """The read results in the messages, in order: ``(source/path, content)``.
@@ -291,15 +300,15 @@ def _read_results(body: dict[str, Any]) -> list[tuple[str, str]]:
 
 
 def _catalog_docs(body: dict[str, Any]) -> list[tuple[str, str]]:
-    """Every ``source/path`` in the catalog tool result, in listing order.
+    """Every ``(source, path)`` in the catalog tool result, in listing order.
 
-    Catalog lines are ``source/path — title`` (the agent's
-    ``list_documents`` output): split on ``" — "``, keep the head, and
-    recover ``(source, path)`` with ``rsplit("/", 1)`` (``rpartition``)
-    — the same convention the single-read flow's read step uses. The
-    ``"N documents:"`` header line carries no ``/`` and is skipped; read-
-    result messages are full documents, not listings, and are skipped
-    too.
+    Catalog lines are ``source: X | path: Y | title: Z`` (the agent's
+    ``list_documents`` output — phase 63: labeled, pipe-delimited
+    fields, unambiguous even for paths full of ``/``): the line-level
+    regex recovers the ``source`` and ``path`` fields directly. The
+    ``"N documents:"`` header line matches no line and is skipped;
+    read-result messages are full documents, not listings, and are
+    skipped too.
     """
     docs: list[tuple[str, str]] = []
     for m in _messages(body):
@@ -309,11 +318,9 @@ def _catalog_docs(body: dict[str, Any]) -> list[tuple[str, str]]:
         if content.startswith(_READ_RESULT_PREFIX):
             continue
         for line in content.splitlines():
-            head = line.split(" — ", 1)[0].strip()
-            if "/" in head:
-                source, _, path = head.rpartition("/")
-                if source and path:
-                    docs.append((source, path))
+            match = _CATALOG_LINE_RE.match(line)
+            if match:
+                docs.append((match.group("source"), match.group("path")))
     return docs
 
 
@@ -327,8 +334,8 @@ def _tool_flow(body: dict[str, Any]) -> tuple[str, ...] | None:
       are in the messages yet: the model lists the catalog.
     * ``("read", source, path, "call_1")`` — a ``tool``-role catalog
       result is in the messages: the model reads its FIRST
-      ``source/path — title`` line (split on ``" — "``, then
-      ``rsplit("/", 1)``).
+      ``source: X | path: Y | title: Z`` line (the labeled
+      ``source:`` / ``path:`` fields, phase 63).
     * ``("answer", "source/path", content)`` — a ``tool``-role read
       result (``"Document <source/path>:\n<content>"``) is in the
       messages: the model answers, quoting the read document. Reached