feat: durable background execution + HITL suspend/resume schema - #13633
Merged
Conversation
Rebased onto release-1.10.0. The base independently rebuilt the v2 workflows backend (RBAC, body globals, share-aware fetch); keep our forward design and conform its auth to that work: 1. Auth: keep get_current_user_for_workflow (session-or-API-key authN that does not hold a DB connection during the inline run, avoiding the SQLite lock contention api_key_security would cause) and enforce the base's RBAC on top: ensure_flow_permission(EXECUTE) before run, (READ) before status reconstruct, with widen_for_shares fetch. 2. Port the base's request-body globals onto the v2 WorkflowRunRequest. The X-LANGFLOW-GLOBAL-VAR-* headers stay supported (the Responses API passes globals that way); body globals win on conflict. Converters echo the effective globals via effective_globals. 3. Public endpoint keeps the v1 build_public_tmp posture (access_type==PUBLIC, run-as-owner); RBAC applies to the authenticated endpoint only. 4. Preserve the base's post-build KB-cache invalidation in the AG-UI build path. The endpoint, AG-UI bridge, pluggable stream adapters, public endpoint, and re-attach are unchanged.
The synchronous /api/v2/workflows response keyed every result under its component id, so reading the answer meant knowing an id you can't predict. Surface two additive fields: - output_text: the flow's single text answer (ChatOutput/TextOutput). None when the flow has zero or multiple text outputs, so callers read outputs rather than the shortcut guessing which channel is the answer. - session_id: echoes the resolved session so chat/memory callers can continue the same thread (v1 /run returned this; v2 had dropped it). outputs is unchanged, so this is non-breaking.
…ponse
Pin the sync-response shortcuts on the v2 workflows endpoint:
- output_text surfaces the lone ChatOutput/TextOutput text and stays None for
non-output message nodes, data-only flows, and multi-text flows
- session_id echoes the resolved session; the error response exposes neither
- each outputs entry exposes only {type, status, content, metadata}, with the
component id carried by the dict key
Also drop the component_id kwarg the converter passed to ComponentOutput, which
has no such field and silently dropped it.
Replace the flat output_text shortcut with an `output` object carrying the resolved text answer plus a `reason` that explains why it resolved that way (single/multiple/none/non_string/failed), so a null answer is always diagnosable instead of silently None. `reason` follows the LLM-domain finish_reason/stop_reason convention, distinct from the lifecycle status. Also add `display_name` to each ComponentOutput (the stable component id stays the dict key) and a computed `has_errors` flag derived from errors.
Let a sync caller name the output(s) they want via output_ids so output.text resolves deterministically (reason=single) on multi-output flows instead of going null. Selection is steer-only: it picks the answer among the named outputs without filtering the outputs map. Invalid ids are rejected with 422 before the flow runs (and before any job row is created), so a typo costs no compute. Resolution considers selected outputs that actually fired, so branching flows resolve to whichever candidate ran.
Give v2-workflows sync and the langflow stream protocol one parser. The stream now emits a normalized "output" event per terminal output carrying an OutputEvent (the ComponentOutput shape sync returns in outputs[id], plus component_id). A shared build_component_output() backs both the sync converter and the adapter, and the build loop ships authoritative vertex metadata as an additive output_meta key on end_vertex (existing consumers read build_data and ignore it). This is access-pattern parity (one parser, same fields, same terminal set), not byte-identical content: the stream reuses the v1 build path whose display serialization differs from sync's run_graph output.
…ackend) Turns v2 mode:background into a durable, in-API background execution service behind a BackgroundExecutionService facade. Adds the store layer (result/error columns, job_events durable milestone log, execution_signals control, heartbeat/lease, 3 migrations), the default backend (bounded executor, runner, in-memory live bus, liveness-aware single-flight orphan sweep), the v2 endpoint rewiring, and the real-instance test harness. Needs no new infra; works on the SQLite single-process install. The redis-scaled worker backend is stacked on top in a follow-up PR.
The hard_proof marker name was a vibe word that said nothing about what the tests need. Rename it to real_services everywhere: the pytest marker registration, the *_hard_proof.py test files, the Makefile target (real_services_tests), the -m selector in migration-validation.yml, and the CI job. real_services says what these tests require: real Postgres + Redis + worker subprocesses. (integration was already taken for the external-API suite under tests/integration.)
…kflows-agui # Conflicts: # src/frontend/src/stores/flowStore.ts
The v2 public endpoint only ran validate_flow_for_current_settings and skipped validate_public_flow_no_code_execution, which the v1 build_public_tmp path applies. A public flow containing a Python interpreter/REPL (or the legacy Python Code Structured tool, Smart Transform lambda) was therefore an unauthenticated server-side code-execution primitive (report H1-3754930). Mirror v1: import the validator and call it right after the public-access gate. PublicFlowValidationError subclasses CustomComponentValidationError, so the existing handler already sanitizes it to a 400 'This flow cannot be executed.' without leaking the blocked component class names. Add a non-mocking test that builds a public flow with a real PythonREPLComponent and asserts the sanitized 400 (verified RED: returns 200 without the gate). LE-1389
…rtex builds A completed background job's GET status 500'd with 'No vertex builds found for job_id'. The background build path differed from the sync path twice: 1. generate_flow_events minted a fresh run_id instead of using job_id, so vertex builds were keyed by an id the status query never uses. Thread run_id through _stream_event_frames -> generate_flow_events and pass job_id from the background buffer so graph.run_id == job_id (the sync path already does graph.set_run_id(job_id)). 2. The SSE build loop (build_vertices) only persisted builds when log_builds was set and never passed job_id. Tie log_builds to job-tracked runs (run_id present) and pass job_id=graph.run_id on the persist call. Job-tracked runs also persist streaming terminal vertices so reconstruction is complete; the live build path (run_id is None) keeps its original behavior, so the v1 build path is unchanged. Test: a real background run polled to completion, then GET status asserts a reconstructed 200 (verified RED: 500 'No vertex builds found' before the fix). Covers the non-streaming flow. v1 build path unchanged (35 build tests pass); AG-UI suite 46 pass. LE-1389
Adopt 1.11.0's composed group-mixin Settings for lfx settings/base.py (all v2 settings already present in the new groups); port the Python 3.14 cors_origins ['*']->'*' fix into groups/security.py.
…ows-bg-default Port the 6 background-execution settings and background_backend_is_scaled into 1.11.0's RuntimeSettings group mixin; union the BACKGROUND_EXECUTION_SERVICE / TELEMETRY_WRITER_SERVICE additions in schema.py and deps.py.
… of dropping them Parallel components stream tokens for different message ids interleaved. The translator tracked a single open message: the first foreign token closed the open message and tombstoned its id, so every later event for it was dropped and its remaining text never reached the client. Tokens for a message that cannot take the wire now buffer until the open message genuinely ends (its add_message finalizer), then flush in arrival order; complete messages landing mid-stream buffer the same way instead of interleaving a second START. end/error drain all buffers before the terminal event. The wire still carries at most one open text message, so the stream stays AG-UI-conformant.
… purge removed buffers A partial add_message re-fire (the agent path emits these at tool start/end for a message it is still streaming) was treated as the finalizer: it closed and tombstoned the id, so the post-tool answer was dropped. Only a non-partial add_message finalizes now; state defaults to complete, so payloads without properties are unchanged. remove_message now purges a buffered message and tombstones its id, so text the backend retracted is not flushed to the client later.
…ai/langflow into codex/v2-workflows-agui-merge # Conflicts: # src/backend/base/langflow/api/v2/agui_translator.py # src/backend/tests/unit/api/v2/test_agui_translator.py
Contributor
|
Important Review skippedToo many files! This PR contains 228 files, which is 78 over the limit of 150. To get a review, narrow the scope: Upgrade to a paid plan to raise the limit. ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (228)
You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
|
✅ Migration Validation Passed All migrations follow the Expand-Contract pattern correctly. |
Cristhianzl
changed the base branch from
release-1.11.0
to
feat/v2-workflows-agui
June 12, 2026 17:00
erichare
requested changes
Jul 13, 2026
Member
There was a problem hiding this comment.
@Cristhianzl can you take a look at these comments? Thanks!
-
[P1] Resume bypasses current flow permissions. The [resume route](
) checks job ownership but never reauthorizeslangflow/src/backend/base/langflow/api/v2/workflow.py
Lines 892 to 918 in 0b1e540
FlowAction.EXECUTE. A user whose shared access is revoked after suspension can still resume and execute the remaining flow. -
[P1] Tool-approval request IDs are reused. Every approval from one Agent run gets the same
[component_id:run_id](https://github.com/langflow-ai/langflow/blob/0b1e54003535b25e3067da2a34be3f0385d0db51/src/lfx/src/lfx/components/models_and_agents/agent_helpers/tool_approval.py#L85). A delayed retry for approval N can therefore be accepted during approval N+1, applying a decision to a different tool call. Include the LangGraph interrupt ID or another per-pause nonce. -
[P2] Answered cards are not recognized after reload.
[cardAlreadyAnswered](https://github.com/langflow-ai/langflow/blob/0b1e54003535b25e3067da2a34be3f0385d0db51/src/frontend/src/controllers/API/agui/human-input-card.ts#L100-L121)searches for a synthetic outer message ID, but persisted messages reload with a database UUID. A regression test using the persisted shape returnsfalse, allowing the replayed pause to surface another actionable card. Match the nestedhuman_input.request_idinstead. -
[P2] The configured timeout never autonomously takes the fallback path. The [component promises fallback after the timeout](
), but timeout handling only reroutes a response received after expiry. With no response, the job remains suspended indefinitely. This needs a durable wakeup or different user-facing semantics.langflow/src/lfx/src/lfx/components/flow_controls/human_input.py
Lines 52 to 63 in 0b1e540
-
[P2] Card completion can target the next pause. The route enqueues the continuation before calling
[mark_card_answered](https://github.com/langflow-ai/langflow/blob/0b1e54003535b25e3067da2a34be3f0385d0db51/src/backend/base/langflow/api/v2/hitl.py#L140-L159), whilemark_card_answeredignoresrequest_idand uses a mutablecard_message_id. If the continuation reaches another pause first, the first decision stamps the second card.
Member
Author
|
Thanks for the careful review @erichare — these were great catches. Quick status: 1, 2, 3 and 5 are being fixed (pushing shortly):
On 4, I'd like to push back a little — the behavior is intentional, though I agree the component copy oversold it. The node timeout is deliberately lazy: Making the node timeout fire the fallback branch on its own would need a durable per-node timer that survives restarts and doesn't race a human decision landing at the same instant — real infrastructure I'd rather not bolt onto a PR this size. What I've done here instead is fix the component's info text so it no longer promises autonomous fallback, and I'll file a follow-up ticket for a durable wakeup that actually takes the fallback path on expiry. If you feel strongly it should land together, happy to discuss. |
Contributor
|
Build successful! ✅ |
1 similar comment
Contributor
|
Build successful! ✅ |
# Conflicts: # src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json # src/backend/base/langflow/initial_setup/starter_projects/Content Aggregator.json # src/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.json # src/backend/base/langflow/initial_setup/starter_projects/Deep Research Agent.json # src/backend/base/langflow/initial_setup/starter_projects/Document Q&A.json # src/backend/base/langflow/initial_setup/starter_projects/Financial Report Parser.json # src/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.json # src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json # src/backend/base/langflow/initial_setup/starter_projects/Market Research.json # src/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.json # src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json # src/backend/base/langflow/initial_setup/starter_projects/Multi Agent Flow.json # src/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json # src/backend/base/langflow/initial_setup/starter_projects/Price Deal Finder.json # src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.json # src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json # src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents.json # src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json # src/backend/base/langflow/initial_setup/starter_projects/Social Media Agent.json # src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json # src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json # src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json # src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json # src/backend/base/langflow/initial_setup/starter_projects/Youtube Analysis.json # src/lfx/src/lfx/_assets/component_index.json
Contributor
|
Build successful! ✅ |
Contributor
|
Build successful! ✅ |
Contributor
|
Build successful! ✅ |
1 similar comment
Contributor
|
Build successful! ✅ |
Contributor
|
Build successful! ✅ |
1 similar comment
Contributor
|
Build successful! ✅ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Objective
Open the human-in-the-loop groundwork (LE-1437) on release-1.11.0: a durable background-execution substrate whose jobs can later suspend for human input and resume without losing state.