fix(memory): instruct in-turn consolidation + retry on overflow (#41755)

* fix(memory): make overflow errors instruct in-turn consolidation + retry

When bounded memory is full, the add/replace overflow errors now explicitly
tell the model to consolidate (merge/remove/shorten) and retry the write in
the same turn, matching the documented behavior. The replace-overflow path
now also echoes current_entries + usage for parity with add-overflow, so the
model has the same context to act on.

Closes #23378 (working-as-documented; this sharpens runtime to match docs).

* fix(memory): broaden overflow remediation hint beyond 'stale'

Say 'stale or less important' — entries don't have to be stale to be the
right ones to drop when making room.

tools/memory_tool.py

@@ -332,7 +332,9 @@ class MemoryStore:
                     "error": (
                         f"Memory at {current:,}/{limit:,} chars. "
                         f"Adding this entry ({len(content)} chars) would exceed the limit. "
-                        f"Replace or remove existing entries first."
+                        f"Consolidate now: use 'replace' to merge overlapping entries into "
+                        f"shorter ones or 'remove' stale or less important entries (see "
+                        f"current_entries below), then retry this add — all in this turn."
                     ),
                     "current_entries": entries,
                     "usage": f"{current:,}/{limit:,}",
@@ -390,12 +392,17 @@ class MemoryStore:
             new_total = len(ENTRY_DELIMITER.join(test_entries))
 
             if new_total > limit:
+                current = self._char_count(target)
                 return {
                     "success": False,
                     "error": (
                         f"Replacement would put memory at {new_total:,}/{limit:,} chars. "
-                        f"Shorten the new content or remove other entries first."
+                        f"Shorten the new content, or 'remove' other stale or less important "
+                        f"entries to make room (see current_entries below), then retry — all "
+                        f"in this turn."
                     ),
+                    "current_entries": entries,
+                    "usage": f"{current:,}/{limit:,}",
                 }
 
             entries[idx] = new_content