docs(agents): refresh comments that referenced the deleted single-agent stack (bucket B6)

After deleting app/agents/new_chat/, several shared-kernel comments still cited
new_chat paths/cycles. Update the two lazy-import comments in middleware to state
the real reason (tools.registry <-> shared.middleware cycle), and repoint dangling
``new_chat/tools/hitl.py`` / ``chat_deepagent`` doc references to their shared
locations. Comment-only; suite unaffected.

surfsense_backend/app/agents/shared/deliverable_wait.py

@@ -1,10 +1,10 @@
 """Shared poll-until-terminal helper for Celery-backed deliverables.
 
-Lives in ``app.agents.shared`` (neutral package, no dependencies on either
-``new_chat`` or ``multi_agent_chat``) so both the flat single-agent tools
-under ``app/agents/new_chat/tools/`` and the multi-agent subagent tools
-under ``app/agents/multi_agent_chat/subagents/builtins/deliverables/tools/``
-can import it without creating a circular dependency.
+Lives in ``app.agents.shared`` (neutral kernel package, no dependency on
+``multi_agent_chat``) so both the shared tools under ``app/agents/shared/tools/``
+and the multi-agent subagent tools under
+``app/agents/multi_agent_chat/subagents/builtins/deliverables/tools/`` can import
+it without creating a circular dependency.
 
 Background
 ----------

surfsense_backend/app/agents/shared/middleware/action_log.py

@@ -39,9 +39,9 @@ if TYPE_CHECKING:  # pragma: no cover - type-only
     from langchain.agents.middleware.types import ToolCallRequest
     from langgraph.types import Command
 
-    # Type-only import: keeping it lazy avoids a module-load cycle through the
-    # frozen single-agent package (new_chat.__init__ -> chat_deepagent ->
-    # middleware shim). Resolves to app.agents.shared.tools once tools migrate.
+    # Type-only import: ToolDefinition is only referenced in annotations, and a
+    # runtime import would close a module-load cycle (tools.registry imports
+    # shared.middleware.dedup_tool_calls).
     from app.agents.shared.tools.registry import ToolDefinition
 
 

surfsense_backend/app/agents/shared/middleware/doom_loop.py

@@ -16,7 +16,7 @@ This ships **OFF by default** until the frontend explicitly handles
 ``context.permission == "doom_loop"`` interrupts.
 
 Wire format: uses SurfSense's existing ``interrupt()`` payload shape
-(see ``app/agents/new_chat/tools/hitl.py``):
+(see ``app/agents/shared/tools/hitl.py``):
 
     {
         "type": "permission_ask",

surfsense_backend/app/agents/shared/middleware/permission.py

@@ -8,7 +8,7 @@ per-thread overrides, and no auto-deny synthesis.
 
 This middleware ports OpenCode's ``packages/opencode/src/permission/index.ts``
 ruleset model on top of SurfSense's existing ``interrupt({type, action,
-context})`` payload shape (see ``app/agents/new_chat/tools/hitl.py``) so
+context})`` payload shape (see ``app/agents/shared/tools/hitl.py``) so
 the frontend keeps working unchanged.
 
 Operation:
@@ -85,7 +85,7 @@ def _default_pattern_resolver(name: str) -> PatternResolver:
 # Translation from the LangChain HITL envelope (what ``stream_resume_chat``
 # sends) to SurfSense's legacy ``decision_type`` shape. ``edit`` keeps the
 # original tool args — tools needing argument edits should use
-# ``request_approval`` from ``app/agents/new_chat/tools/hitl.py``.
+# ``request_approval`` from ``app/agents/shared/tools/hitl.py``.
 _LC_TYPE_TO_PERMISSION_DECISION: dict[str, str] = {
     "approve": "once",
     "reject": "reject",

surfsense_backend/app/agents/shared/middleware/tool_call_repair.py

@@ -118,9 +118,9 @@ class ToolCallNameRepairMiddleware(
                 return call
 
         # Stage 2 — invalid fallback
-        # Local import avoids a module-load cycle through the frozen single-agent
-        # package (new_chat.__init__ -> chat_deepagent -> middleware shim).
-        # Resolves to app.agents.shared.tools once tools migrate.
+        # Local import avoids a module-load cycle: tools.registry imports
+        # shared.middleware (dedup_tool_calls), so importing tools at module
+        # scope here would close the loop.
         from app.agents.shared.tools.invalid_tool import INVALID_TOOL_NAME
 
         if INVALID_TOOL_NAME in registered:

surfsense_backend/app/agents/shared/tools/hitl.py

@@ -44,8 +44,8 @@ logger = logging.getLogger(__name__)
 # change is "no interrupt fires".
 #
 # To re-enable prompting, the future per-search-space rules table
-# (``agent_permission_rules``) takes precedence — see the ``# (future)``
-# layer-3 comment in :mod:`app.agents.new_chat.chat_deepagent`.
+# (``agent_permission_rules``) takes precedence in the permission ruleset
+# layering assembled by the agent factory.
 DEFAULT_AUTO_APPROVED_TOOLS: frozenset[str] = frozenset(
     {
         "create_gmail_draft",