refactor(agents): introduce chat/ category; dissolve top-level agents/shared

Recursive shared-folder rule: a shared/ must be shared by ALL siblings at its
level. The kernel (context, compaction, retry_after, web_search) was shared by
only 2 of the agents -- anonymous_chat + multi_agent_chat -- never by podcaster
or video_presentation. Those 2 are the "chat" category, so their shared code
belongs in that category's shared/, not the top-level one.

  app/agents/anonymous_chat/   -> app/agents/chat/anonymous_chat/
  app/agents/multi_agent_chat/ -> app/agents/chat/multi_agent_chat/
  app/agents/shared/           -> app/agents/chat/shared/   (anon<->mac kernel)

Top-level app/agents/shared/ is gone: nothing was shared across all three
categories (chat / podcaster / video_presentation).

~289 import sites rewritten (app.agents.{anonymous_chat,multi_agent_chat,shared}
-> app.agents.chat.*); all moves are git renames (history preserved).
app/agents/ now: chat/, podcaster/, video_presentation/, runtime/.

surfsense_backend/app/tasks/chat/streaming/agent/builder.py

@@ -9,8 +9,10 @@ from __future__ import annotations
 
 from typing import Any
 
-from app.agents.multi_agent_chat.shared.filesystem_selection import FilesystemSelection
-from app.agents.multi_agent_chat.shared.llm_config import AgentConfig
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import (
+    FilesystemSelection,
+)
+from app.agents.chat.multi_agent_chat.shared.llm_config import AgentConfig
 from app.db import ChatVisibility
 from app.services.connector_service import ConnectorService
 

surfsense_backend/app/tasks/chat/streaming/agent/event_loop.py

@@ -11,8 +11,8 @@ from __future__ import annotations
 from collections.abc import AsyncGenerator
 from typing import Any
 
-from app.agents.multi_agent_chat.shared.filesystem_selection import FilesystemMode
-from app.agents.multi_agent_chat.shared.middleware.kb_persistence import (
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import FilesystemMode
+from app.agents.chat.multi_agent_chat.shared.middleware.kb_persistence import (
     commit_staged_filesystem_state,
 )
 from app.services.new_streaming_service import VercelStreamingService

surfsense_backend/app/tasks/chat/streaming/errors/classifier.py

@@ -7,8 +7,8 @@ import logging
 import time
 from typing import Any, Literal
 
-from app.agents.multi_agent_chat.shared.errors import BusyError
-from app.agents.multi_agent_chat.shared.middleware.busy_mutex import (
+from app.agents.chat.multi_agent_chat.shared.errors import BusyError
+from app.agents.chat.multi_agent_chat.shared.middleware.busy_mutex import (
     get_cancel_state,
     is_cancel_requested,
 )

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/input_state.py

@@ -28,8 +28,8 @@ from langchain_core.messages import HumanMessage
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.future import select
 
-from app.agents.multi_agent_chat.shared.filesystem_selection import FilesystemMode
-from app.agents.multi_agent_chat.shared.mention_resolver import (
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import FilesystemMode
+from app.agents.chat.multi_agent_chat.shared.mention_resolver import (
     resolve_mentions,
     substitute_in_text,
 )

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/llm_capability.py

@@ -15,7 +15,7 @@ tells the user what to change.
 
 from __future__ import annotations
 
-from app.agents.multi_agent_chat.shared.llm_config import AgentConfig
+from app.agents.chat.multi_agent_chat.shared.llm_config import AgentConfig
 from app.observability import otel as ot
 
 

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/orchestrator.py

@@ -29,12 +29,12 @@ from typing import Any, Literal
 
 import anyio
 
-from app.agents.multi_agent_chat import create_multi_agent_chat_deep_agent
-from app.agents.multi_agent_chat.shared.filesystem_selection import (
+from app.agents.chat.multi_agent_chat import create_multi_agent_chat_deep_agent
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import (
     FilesystemMode,
     FilesystemSelection,
 )
-from app.agents.multi_agent_chat.shared.middleware.busy_mutex import end_turn
+from app.agents.chat.multi_agent_chat.shared.middleware.busy_mutex import end_turn
 from app.db import ChatVisibility, async_session_maker
 from app.observability import otel as ot
 from app.services.new_streaming_service import VercelStreamingService
@@ -829,7 +829,7 @@ async def stream_new_chat(
         # downloadable after the Daytona sandbox auto-deletes.
         if stream_result and stream_result.sandbox_files:
             with contextlib.suppress(Exception):
-                from app.agents.multi_agent_chat.shared.sandbox import (
+                from app.agents.chat.multi_agent_chat.shared.sandbox import (
                     is_sandbox_enabled,
                     persist_and_delete_sandbox,
                 )

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/runtime_context.py

@@ -8,7 +8,7 @@ mention lists / request ids / turn ids without rebuilding the graph.
 
 from __future__ import annotations
 
-from app.agents.shared.context import SurfSenseContextSchema
+from app.agents.chat.shared.context import SurfSenseContextSchema
 
 
 def build_new_chat_runtime_context(

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/title_gen.py

@@ -30,7 +30,7 @@ from app.prompts import TITLE_GENERATION_PROMPT
 from app.services.new_streaming_service import VercelStreamingService
 
 if TYPE_CHECKING:
-    from app.agents.multi_agent_chat.shared.llm_config import AgentConfig
+    from app.agents.chat.multi_agent_chat.shared.llm_config import AgentConfig
     from app.services.token_tracking_service import TokenAccumulator
 
 

surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/orchestrator.py

@@ -23,12 +23,12 @@ from uuid import UUID
 
 import anyio
 
-from app.agents.multi_agent_chat import create_multi_agent_chat_deep_agent
-from app.agents.multi_agent_chat.shared.filesystem_selection import (
+from app.agents.chat.multi_agent_chat import create_multi_agent_chat_deep_agent
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import (
     FilesystemMode,
     FilesystemSelection,
 )
-from app.agents.multi_agent_chat.shared.middleware.busy_mutex import end_turn
+from app.agents.chat.multi_agent_chat.shared.middleware.busy_mutex import end_turn
 from app.db import ChatVisibility, async_session_maker
 from app.observability import otel as ot
 from app.services.chat_session_state_service import set_ai_responding

surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/resume_routing.py

@@ -41,7 +41,7 @@ async def build_resume_routing(
     ``surfsense_resume_value`` configurable; parallel siblings each pop their
     own entry so they never race.
     """
-    from app.agents.multi_agent_chat.main_agent.middleware.checkpointed_subagent_middleware.resume_routing import (
+    from app.agents.chat.multi_agent_chat.main_agent.middleware.checkpointed_subagent_middleware.resume_routing import (
         build_lg_resume_map,
         collect_pending_tool_calls,
         slice_decisions_by_tool_call,

surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/runtime_context.py

@@ -7,7 +7,7 @@ can rely on ``runtime.context`` always being populated.
 
 from __future__ import annotations
 
-from app.agents.shared.context import SurfSenseContextSchema
+from app.agents.chat.shared.context import SurfSenseContextSchema
 
 
 def build_resume_chat_runtime_context(

surfsense_backend/app/tasks/chat/streaming/flows/shared/llm_bundle.py

@@ -14,7 +14,7 @@ from typing import Any
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.agents.multi_agent_chat.shared.llm_config import (
+from app.agents.chat.multi_agent_chat.shared.llm_config import (
     AgentConfig,
     create_chat_litellm_from_agent_config,
     create_chat_litellm_from_config,

surfsense_backend/app/tasks/chat/streaming/flows/shared/premium_quota.py

@@ -19,7 +19,7 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING
 from uuid import UUID
 
-from app.agents.multi_agent_chat.shared.llm_config import AgentConfig
+from app.agents.chat.multi_agent_chat.shared.llm_config import AgentConfig
 from app.db import shielded_async_session
 
 if TYPE_CHECKING:

surfsense_backend/app/tasks/chat/streaming/flows/shared/rate_limit_recovery.py

@@ -17,7 +17,7 @@ from typing import Literal
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.agents.multi_agent_chat.shared.middleware.busy_mutex import end_turn
+from app.agents.chat.multi_agent_chat.shared.middleware.busy_mutex import end_turn
 from app.observability import otel as ot
 from app.services.auto_model_pin_service import (
     mark_runtime_cooldown,

surfsense_backend/app/tasks/chat/streaming/flows/shared/stream_loop.py

@@ -15,7 +15,7 @@ from __future__ import annotations
 from collections.abc import AsyncGenerator, Awaitable, Callable
 from typing import Any
 
-from app.agents.multi_agent_chat.shared.filesystem_selection import FilesystemMode
+from app.agents.chat.multi_agent_chat.shared.filesystem_selection import FilesystemMode
 from app.services.new_streaming_service import VercelStreamingService
 from app.tasks.chat.streaming.agent.event_loop import stream_agent_events
 from app.tasks.chat.streaming.shared.stream_result import StreamResult

surfsense_backend/app/tasks/chat/streaming/flows/shared/terminal_error.py

@@ -14,7 +14,7 @@ import traceback
 from collections.abc import Iterator
 from typing import Any, Literal
 
-from app.agents.multi_agent_chat.shared.errors import BusyError
+from app.agents.chat.multi_agent_chat.shared.errors import BusyError
 from app.observability import metrics as ot_metrics, otel as ot
 from app.services.new_streaming_service import VercelStreamingService
 from app.tasks.chat.streaming.errors.classifier import classify_stream_exception

surfsense_backend/app/tasks/chat/streaming/handlers/tool_end.py

@@ -26,7 +26,7 @@ def _unwrap_command_output(raw_output: Any) -> Any:
     """Replace a ``Command`` from a tool return with its inner ``ToolMessage``.
 
     Tools that participate in receipt-style state writes (see
-    ``app.agents.multi_agent_chat.shared.receipts.command.with_receipt``) return a
+    ``app.agents.chat.multi_agent_chat.shared.receipts.command.with_receipt``) return a
     ``Command(update={"messages": [ToolMessage(...)], "receipts": [...]})``.
     LangChain's ``on_tool_end`` event surfaces that ``Command`` verbatim as
     ``data.output``, which the rest of this handler can't introspect: it has

surfsense_backend/app/tasks/chat/streaming/handlers/tools/deliverables/generate_video_presentation/emission.py

@@ -21,7 +21,7 @@ def iter_completion_emission_frames(
     # ``ready`` is the live success status now that the tool waits for the
     # Celery worker to reach a terminal state. ``pending`` is retained as a
     # legacy branch for old saved chats that pre-date the wait-for-terminal
-    # change (see ``app.agents.multi_agent_chat.subagents.builtins.deliverables.deliverable_wait``).
+    # change (see ``app.agents.chat.multi_agent_chat.subagents.builtins.deliverables.deliverable_wait``).
     if status == "ready":
         yield ctx.streaming_service.format_terminal_info(
             f"Video presentation generated successfully: {out.get('title', 'Presentation')}",