These two tools were "shared-by-folder, not shared-by-use": the only live
consumer of shared/tools/{scrape_webpage,update_memory} was the main agent
(the research/memory subagents carry their own local copies; web_search,
by contrast, is genuinely shared with anonymous_chat and stays put).
Move both into main_agent/tools/ (their sole owner). The shared BUILTIN_TOOLS
catalog still lists them for action_log/revert + /agent/tools, now via
deferred-import factories (_build_scrape_webpage_tool, _build_update_memory_tool)
mirroring the create_automation precedent to avoid a multi_agent_chat import
cycle. Removed the now-dead re-exports from shared/tools/__init__.py.
Verified: full unit suite green (2431 passed, 1 skipped).
The main agent only exposes 4 SurfSense tools (web_search, scrape_webpage,
update_memory, create_automation) and delegates connectors/MCP/deliverables
to subagents. Yet it built those 4 by importing and iterating the 900-line,
connector-laden shared BUILTIN_TOOLS via build_tools_async.
Introduce app/agents/multi_agent_chat/main_agent/tools/registry.py owning
just those 4 factories, and switch runtime/factory.py to build_main_agent_tools.
Binding order is preserved (scrape_webpage, web_search, create_automation,
update_memory) to match prior behavior exactly.
shared/tools/registry.py BUILTIN_TOOLS is intentionally unchanged: it remains
the app-wide tool *metadata* catalog used by action_log (revert/dedup
resolvers for subagent-executed connector tools) and the /agent/tools
listing endpoint.
Verified: full unit suite green (2431 passed, 1 skipped); import-all guard ok.
Eliminate the top-level multi_agent_chat/middleware/ package so each slice
owns its middleware (vertical-slice colocation):
- middleware/shared/ -> shared/middleware/ (cross-slice middleware)
- middleware/subagent/ -> subagents/shared/middleware/ (subagent stack)
- main_agent/middleware/ already colocated in Slice A
The moved shared/ subtree is internally consistent (all relative imports
stay within it), so only external absolute refs were rewritten. The
subagent stack's ..shared.* relatives were promoted to absolute paths to
the new shared/middleware/ location.
multi_agent_chat/ root is now: main_agent/, shared/, subagents/.
Verified: 2430 unit tests pass, 1 skipped (baseline unchanged).
Vertical-slice colocation: all main-agent code should live under
main_agent/ instead of being split across a parallel middleware/main_agent
tree. Move multi_agent_chat/middleware/main_agent/ -> main_agent/middleware/
and its assembler middleware/stack.py -> main_agent/middleware/stack.py, so
the main-agent slice is self-contained (graph, runtime, system_prompt, tools,
middleware).
Genuinely cross-slice middleware (middleware/shared/, middleware/subagent/)
stays under multi_agent_chat/middleware/ for a later slice; the moved builders
now reference it via absolute imports.
Pure move + import rewrite (git-tracked renames). Verified: full unit suite
green (2430 passed, 1 skipped), including test_import_all and the
checkpointed-subagent middleware suite.
The single-agent-era filesystem middleware (app/agents/shared/middleware/
filesystem.py, ~2000 lines) was never instantiated in production, yet three
unit suites validated it — an illusory guardrail while the live decomposed
middleware (multi_agent_chat/middleware/shared/filesystem) was unguarded.
Close the gap before reorganizing the agents module:
- Add 14 integration tests driving live B's tools in desktop mode (real
on-disk effects) and cloud mode (in-state staging, namespace policy).
- Port all high-value dead-twin assertions onto the live path: cloud rm/rmdir
staging + guard rails, KBPostgresBackend delete-view filter, mode-scoped
system prompt, cwd/relative/namespace resolution, multi-root mount
normalization.
- Delete dead twin filesystem.py, drop its __init__ re-export, and retire its
3 dead-twin tests.
Verified: test_import_all + middleware unit + FS integration all green.
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.
With multi-agent the only live factory (B1), the single-agent stack is dead.
Remove app/agents/new_chat/ entirely: chat_deepagent.py, subagents/, and all
re-export shims (errors/context/llm_config/permissions/tools/middleware/...) that
existed only to serve frozen single-agent code. Live code already imports the
shared kernel (app.agents.shared.*) directly.
Tests: delete single-agent-only suites (test_resolve_prompt_model_name,
test_specialized_subagents) and the chat_deepagent source-shape contract assertion;
repoint test_scoped_model_fallback to the shared middleware path. Suite green
(2710 passed).
The anonymous / free-chat agent is a distinct live agent (not part of the
single-agent stack and not shared infrastructure), so it gets its own top-level
package app/agents/anonymous_chat/ (sibling to multi_agent_chat). Moved
new_chat/anonymous_agent.py -> anonymous_chat/agent.py with a package __init__
re-exporting create_anonymous_chat_agent + build_anonymous_system_prompt.
Repointed its only new_chat import (the context shim) to app.agents.shared.context
and updated the single importer (anonymous_chat_routes). The test_import_all
guard auto-discovers the new package via pkgutil.walk_packages, so it is covered.
Three live shared leaves discovered while taking stock after slice 7 (all are
consumed by the multi-agent stack and/or live routes, not single-agent-only):
- connector_searchable_types -> shared + shim (multi-agent factory uses it)
- agent_cache -> shared + shim (multi-agent runtime/agent_cache uses it)
- system_prompt + prompts/ (42 .md fragments) -> shared together + shim.
Repointed composer's _PROMPTS_PACKAGE to app.agents.shared.prompts so
importlib.resources fragment loading keeps working; system_prompt's relative
".prompts.composer" import is preserved by moving both as a unit.
Each keeps a re-export shim for the frozen chat_deepagent. After this slice,
new_chat/ holds only the frozen single-agent stack (chat_deepagent, subagents/,
__init__) plus shims.
- skills/ (builtin SKILL.md assets) has zero Python importers; it is read by
filesystem path only. Moved the dir and restored
skills_backends._default_builtin_root() to the clean
parent.parent / "skills" / "builtin" form (undoing the transient path from 5c).
- plugin_loader.py -> shared (frozen chat_deepagent uses it -> re-export shim).
- plugins/ package -> shared (year_substituter rewired to shared.plugin_loader;
docstring entry-point example updated to the shared dotted path). No shim
needed (only a test imported it). Plugin discovery is via importlib entry
points (group "surfsense.plugins"), not dotted-path import, and nothing is
registered in pyproject, so the move does not affect runtime discovery.
Relocate the entire new_chat/tools/ package (62 files incl. registry, hitl, MCP
cluster, and all connector subpackages: gmail/slack/discord/teams/drive/etc.)
to the shared kernel. The package turned out to be a clean cohesive cluster:
its only references to non-tools new_chat modules were comments, and its
middleware deps were already flipped to shared in slice 5c.
Flip 33 live importers (multi-agent, flows, routes, services, anonymous_agent,
tests). Re-export shims remain for the frozen single-agent stack: a package
__init__ mirroring the public surface (new_chat.__init__ imports it) plus
invalid_tool + registry submodule shims (chat_deepagent imports those).
Resolves slice 5c's two transient back-edges: shared/middleware/action_log
(TYPE_CHECKING ToolDefinition) and tool_call_repair (local INVALID_TOOL_NAME)
now point at app.agents.shared.tools.
Completes slice 5. filesystem_backends was deferred from 3b because it depends
on middleware.{kb_postgres_backend,multi_root_local_folder_backend}; those moved
to shared in 5c, so it now relocates cleanly. Flip the 2 non-frozen importers
(multi-agent factory + test); a re-export shim remains for the frozen
chat_deepagent (build_backend_resolver).
Relocate the entire new_chat/middleware/ package to the shared kernel as one
cohesive unit (it is live shared infrastructure: the multi-agent stack wraps
nearly every middleware via multi_agent_chat/middleware/main_agent/*, and
anonymous_agent consumes it too). Flip 69 live importers across both the
package-path and submodule-path forms.
Shims left for the frozen single-agent stack: a package __init__ re-export plus
submodule shims for permission, skills_backends, and scoped_model_fallback
(the three imported via submodule path by chat_deepagent/subagents).
Cycle break: importing shared.middleware previously reached back into
new_chat.tools at module load, which dragged in new_chat.__init__ ->
chat_deepagent -> the middleware shim -> half-initialized shared.middleware.
Made action_log's ToolDefinition import TYPE_CHECKING-only and
tool_call_repair's INVALID_TOOL_NAME import function-local. These tools-package
back-edges fully resolve in slice 6.
Asset note: skills_backends._default_builtin_root now walks to
app/agents/new_chat/skills/builtin (the skills/ tree migrates in slice 7).
Two independent leaf modules (no intra-new_chat deps, no frozen importer),
consumed only by flows/routes/tests. Flipped 8 importers across both the
dotted-path and module-style (from app.agents.new_chat import mention_resolver)
forms. No shims needed.
Two pure leaf modules with no intra-new_chat deps and no frozen importer.
Moving them now (before the middleware package) pre-empts two shared->new_chat
back-edges that the middleware move would otherwise create
(knowledge_search->utils, kb_postgres_backend->document_xml).
Relocate the mutually-dependent LLM config layer and the LiteLLM prompt-caching
helper to the shared kernel as one unit, rewiring their internal cross-reference
to the shared paths. Flip 21 non-frozen importers. Re-export shims remain at
new_chat/{llm_config,prompt_caching}.py for the frozen single-agent stack
(chat_deepagent); they will be removed when that stack is retired.
Relocate the permission evaluator (wildcard matcher + rule evaluation) to the
shared kernel and flip 43 non-frozen importers. A re-export shim remains at
new_chat/permissions.py for the frozen single-agent stack (chat_deepagent and
subagents/{config,providers/linear,providers/slack}); it will be removed when
that stack is retired.
Relocate three leaf filesystem-cluster modules to the shared kernel and flip
all 38 importers. No re-export shims needed (no frozen single-agent importer).
This also resolves the pre-existing shared->new_chat back-edge from
shared/receipt_command.py onto filesystem_state.
filesystem_backends is intentionally deferred to slice 5: it depends on
new_chat middleware (kb_postgres_backend, multi_root_local_folder_backend)
that have not yet moved, so relocating it now would create a shared->new_chat edge.
Promote the filesystem mode contracts (FilesystemMode, FilesystemSelection,
ClientPlatform, LocalFilesystemMount) out of `new_chat` into the cross-agent
`app/agents/shared` kernel.
Pure leaf consumed across the whole multi-agent filesystem middleware/tool tree,
the chat flows/monolith, routes and tests. git mv (content unchanged) + flipped
all ~48 importers. A re-export shim remains at new_chat/filesystem_selection.py
only for the not-yet-retired single-agent (chat_deepagent).
Also updated the stream parity test's annotation normalizer to strip the new
app.agents.shared.filesystem_selection. prefix (the dataclasses' __module__
changed with the move), keeping monolith<->flows signature parity intact.
Behavior-preserving: only import paths change. 1326 tests green.
Promote the agent feature-flag resolver (AgentFeatureFlags / get_flags) out of
`new_chat` into the cross-agent `app/agents/shared` kernel.
feature_flags is a pure leaf consumed across the multi-agent middleware stack,
the chat routes, and tests. Moved it via git mv (content unchanged) and flipped
all 37 importers to app.agents.shared.feature_flags. A thin re-export shim
remains at new_chat/feature_flags.py only for the not-yet-retired single-agent
(chat_deepagent); it goes away with the single-agent deletion.
Behavior-preserving: only import paths change. 1243 tests green.
Continue promoting the shared agent toolkit out of `new_chat` into the
cross-agent `app/agents/shared` kernel.
- state_reducers.py: clean move (no single-agent importer); all 7 importers
flipped to app.agents.shared.state_reducers.
- context.py: moved to app.agents.shared.context; flipped the multi-agent,
app, automations, chat-flows and monolith importers. A thin re-export shim
remains at new_chat/context.py because the not-yet-retired single-agent
(chat_deepagent) and the new_chat package __init__ still import it; the shim
goes away with the single-agent deletion.
- Updated the stream parity test's annotation normalizer to strip the new
app.agents.shared.context. prefix (SurfSenseContextSchema.__module__ changed
with the move), keeping monolith<->flows signature parity intact.
Behavior-preserving: definitions unchanged; only import paths move. 1219 tests green.
First slice of promoting the shared agent toolkit out of the misnamed
`new_chat` package into the cross-agent `app/agents/shared` kernel.
`errors.py` is a leaf module (no intra-package deps) consumed by the
multi-agent chat, the chat streaming flows/monolith, and tests — i.e. it is
shared infrastructure, not single-agent code. Moved it verbatim to
`app.agents.shared.errors` and flipped all 12 importers. No re-export shim
remains since zero importers needed it.
Behavior-preserving: identical class/enum definitions; only the import path
changes. 1208 agent + chat-task tests green.
The multi-agent factory reached into the single-agent factory module
(chat_deepagent) for `_map_connectors_to_searchable_types`. Move this
agent-agnostic helper (and its two lookup tables) into a dedicated
`connector_searchable_types` module and point both factories at it.
Behavior-preserving: the function body is unchanged; only its home and
visibility (now public `map_connectors_to_searchable_types`) change. This
removes the cross-dependency on the dying single-agent module so it can be
retired later without breaking the multi-agent path.
- Enhanced lambda function formatting in `_after_commit` for better clarity.
- Simplified generator expression in `_match_condition` for improved readability.
- Streamlined function signature in `_eligible` for consistency.
- Updated imports and refactored anonymous chat routes to use a new agent creation method.
- Added a new function `_load_anon_document` to handle document loading from Redis.
- Improved UI components by replacing legacy structures with modern alternatives, including alerts and separators.
- Refactored quota-related components to utilize new alert structures for better user feedback.
- Cleaned up unused variables and optimized component states for performance.
- Removed the eligibility gate for model selection in the automation creation process, allowing users to choose models directly in the builder.
- Updated the `AutomationBuilderForm` to incorporate model selection logic, ensuring that selected models are validated and preserved during automation creation and editing.
- Simplified the `AutomationsContent` and `AutomationNewContent` components by eliminating unnecessary eligibility checks and alerts.
- Enhanced the user experience by integrating model selection directly into the automation approval process, ensuring that only billable models are used.
- Refactored related tests to cover new model selection behavior and ensure proper validation of user-selected models.
- Added model eligibility checks to ensure automations can only use billable models (premium or BYOK).
- Introduced new API endpoint to report model eligibility status for search spaces.
- Updated frontend components to display eligibility alerts and disable creation options when models are not billable.
- Enhanced automation creation forms to reflect model eligibility, preventing users from submitting invalid configurations.
- Implemented server-side logic to capture and preserve model preferences across automation edits, ensuring consistent behavior during execution.
- Deleted the `search_surfsense_docs` tool and its associated files, streamlining the agent's toolset.
- Updated various components and prompts to remove references to the now-removed tool, ensuring consistency across the codebase.
- Adjusted documentation to direct users to the SurfSense documentation link for product-related queries instead.
Closes the create loop in chat: the agent describes user intent → the
drafter sub-LLM produces an AutomationCreate JSON → this card surfaces
a structured preview → approve persists; reject cancels. Edits flow
through chat refinement (re-call with a refined intent), not in-card,
so the card stays simple and the multi-turn checkpointer carries the
context.
Tool UI (components/tool-ui/automation/):
- create-automation.tsx — entry dispatcher + ApprovalCard chrome
(pending/processing/complete/rejected via useHitlPhase) + SavedCard
(links to the detail page) + InvalidCard (lists drafter validation
issues) + ErrorCard (verbatim message). Rejection result is hidden
because the approval card itself shows the rejected phase inline.
- automation-draft-preview.tsx — structured preview body: name +
description + goal, triggers (humanised cron + tz + static-input
keys), plan steps (step_id → action), and a collapsible raw JSON
for power users.
Wiring:
- components/tool-ui/index.ts — re-export.
- features/chat-messages/timeline/tool-registry/registry.ts —
register create_automation → CreateAutomationToolUI (dynamic import,
same pattern as other connector tools).
- contracts/enums/toolIcons.tsx — Workflow icon + "Create automation"
display name so fallback chrome (and timeline headers) are honest.
Shared util:
- lib/automations/describe-cron.ts — lifted from the route slice's
lib/ folder since both the dashboard slice and the new approval card
now render schedule descriptions. Slice imports updated; the now-
empty slice lib/ folder is gone.
Backend prompt fragments:
- main_agent/system_prompt/.../create_automation/description.md and
the tool's docstring no longer promise in-card edits. They make the
refinement path explicit: if the user wants changes after seeing the
draft, they reply in chat and the agent calls the tool again with a
refined intent.
v1 deliberately excludes:
- In-card edit form / right-side edit panel — defer until we see real
demand. The chat refinement loop covers the common case.
- approve_always / persistent allow rules — automations are a single
artifact, not a repeated mutation, so the "trust this kind of call"
affordance doesn't apply.
Single tool exposed to the main agent. The main agent passes a natural-language
`intent`; a focused drafter sub-LLM turns it into a full AutomationCreate JSON;
that JSON is surfaced via request_approval (action_type "automation_create") so
the user can edit/approve it on a frontend card; on approval the tool persists
via AutomationService. Three phases, one tool call.
Scope split:
- main agent sees only `intent: str` (no schema knowledge leaks into the calling
graph) — prompt fragments scoped accordingly.
- drafter sub-LLM owns the schema + few-shot intent→JSON examples — lives in
the generating graph's prompt (tools/automation/prompt.py).
Files:
- main_agent/tools/automation/{create.py, prompt.py, __init__.py}: new tool
+ drafter system prompt with two few-shot intent→JSON examples.
- system_prompt/prompts/tools/create_automation/{description.md, example.md}:
intent-only guidance for the main agent.
- main_agent/tools/index.py: add create_automation to the main-agent allowlist.
- new_chat/tools/registry.py: deferred-import factory to break the
multi_agent_chat ↔ registry cycle; one ToolDefinition entry.
- Added new environment variables for controlling task execution limits, including `SURFSENSE_SUBAGENT_INVOKE_TIMEOUT_SECONDS`, `SURFSENSE_TASK_BATCH_CONCURRENCY`, and `SURFSENSE_TASK_BATCH_MAX_SIZE`.
- Updated documentation to reflect new batch processing capabilities for `task` calls, allowing for concurrent execution of multiple subagent tasks.
- Improved error handling and receipt generation for deliverables, ensuring consistent feedback on task status.
- Refactored middleware to incorporate search space ID for better task management.
The citations fix (cacb27e0) added a "Chunk citations in your prose"
section to system_prompt_desktop.md telling the KB subagent to always
leave `evidence.chunk_ids` null and emit no `[citation:...]` markers in
desktop mode, but left the pre-existing line declaring that
`chunk_ids` apply to `<priority_documents>` hits. The two rules
contradicted each other; the model picked one per turn.
Strike the stale conditional clause and point at the dedicated section
as the single source of truth. Matches the parallel line in
system_prompt_cloud.md and the already-consistent
system_prompt_readonly_desktop.md.
Resolves: surfsense_backend/app/agents/new_chat/middleware/memory_injection.py
- Took both imports: upstream moved MEMORY_HARD_LIMIT/SOFT_LIMIT to
app.services.memory; kept our perf-logger import for timing.
Pulls in upstream changes:
- Memory document feature (services/memory refactor, removal of
app.agents.new_chat.memory_extraction and background extraction in
stream_new_chat — agent now drives memory via update_memory tool).
- BACKEND_URL env refactor across web tool-ui/editor/chat/dashboard/lib.
- GitHub Actions backend test workflow + pre-commit biome bump.
- Token-display polish in MessageInfoDropdown; save_memory no-update
sentinel.
Verified: 1723 unit tests pass, ruff clean. No semantic regression in
stream_new_chat (their memory-extraction deletion and our preflight
removal touch different functions).
Collapse the invalidate + warmup pair into a single
refresh_mcp_tools_cache_for_connector(connector_id, search_space_id)
helper and scope live discovery to the one connector that changed
instead of the whole search space.
- new mcp_tool.discover_single_mcp_connector: load one connector,
refresh OAuth if needed, force live MCP discovery so its cached_tools
row is rewritten; returned wrappers are discarded since the in-process
LRU is rebuilt lazily on the next user query
- mcp_tools_cache.refresh_mcp_tools_cache_for_connector: synchronously
evicts the per-space LRU (LRU keys cannot scope finer) and schedules
the per-connector prefetch via loop.create_task
- routes (OAuth callback, MCP POST, MCP PUT) collapse their two
back-to-back calls into a single refresh call; DELETE handlers keep
using bare invalidate_mcp_tools_cache (nothing to prefetch)
No new automated tests: the new functions are I/O glue (DB + network)
where mocked unit tests would test implementation rather than behavior.
The existing 9 unit tests for the cached_tools data shape are unchanged.
Skip the ~1-3s MCP initialize + list_tools handshake on every cache miss
by reading tool definitions from the connector row we already load. Lazy
populate on first miss, self-heal on corrupt cache, zero schema migration.
Splits the OpenAI-family gate into per-param predicates so AZURE and
AZURE_OPENAI configs now receive prompt_cache_key for backend routing
affinity (Microsoft auto-caches GPT-4o+ deployments at >=1024 tokens;
the key clusters same-prefix requests on the same GPU pool and raises
hit rate on turn 2+). prompt_cache_retention stays opted out for Azure
because litellm 1.83.14's Azure transformer would drop it silently;
revisit when Azure's supported params list is updated.
