docs: clean up three stale comments from the #32848 audit

- tools/memory_tool.py:20 — 'read' action was intentionally removed
  but the docstring still listed it. Now matches the schema.
- tools/fuzzy_match.py:9 — unicode_normalized was added but the
  chain-count docstring still said '8-strategy'. Now says '9'.
- run_agent.py:1485 — 'See #<TBD>.' placeholder was never filled in.
  Replaced with a backfill note.

Fixes #32848 (parts 3, 4, and 12)

run_agent.py

@@ -1482,7 +1482,7 @@ class AIAgent:
         a raw ``tool`` message and the next user turn lands as
         ``...tool, user, user`` — a protocol-invalid sequence that most
         providers silently reject (returns empty content), causing the
-        empty-retry loop to fire forever. See #<TBD>.
+        empty-retry loop to fire forever. (issue number to be backfilled once filed)
         """
         # Pass 1: strip the flagged scaffolding messages themselves.
         dropped_scaffolding = False

tools/fuzzy_match.py

@@ -6,7 +6,7 @@ Implements a multi-strategy matching chain to robustly find and replace text,
 accommodating variations in whitespace, indentation, and escaping common
 in LLM-generated code.
 
-The 8-strategy chain (inspired by OpenCode), tried in order:
+The 9-strategy chain (inspired by OpenCode), tried in order:
 1. Exact match - Direct string comparison
 2. Line-trimmed - Strip leading/trailing whitespace per line
 3. Whitespace normalized - Collapse multiple spaces/tabs to single space

tools/memory_tool.py

@@ -17,7 +17,7 @@ Entry delimiter: § (section sign). Entries can be multiline.
 Character limits (not tokens) because char counts are model-independent.
 
 Design:
-- Single `memory` tool with action parameter: add, replace, remove, read
+- Single `memory` tool with action parameter: add, replace, remove
 - replace/remove use short unique substring matching (not full text or IDs)
 - Behavioral guidance lives in the tool schema description
 - Frozen snapshot pattern: system prompt is stable, tool responses show live state