When a session crashes mid working-step (e.g. build.publish; the async advance
raised and released the lock), it was a locked dead-end: working states surface
no UI actions and the composer locked with no way forward.
- Surface a RecoveryRef offer (can_continue=Retry, can_restart=Start over,
recovery_class="") on an interrupted working-state view -- built directly so a
real drift class still wins.
- Allow recovery_continue / recovery_restart at an interrupted working state in
_internal_action_allowed. recovery_continue returns the working state
(non-settled) so the runner re-runs the stalled handler; recovery_restart
resets working fields and re-enters the entry state -- both reuse existing
recovery machinery, no new action kinds / no runner change.
Adds unit tests (offer surfaced, allowance) + regression tests (recovery_continue
re-runs handle_publish and advances; recovery_restart resets to entry state;
repeat-failure re-surfaces the offer with no wedge).
This reconciler was reviewed as a standalone plan on the pre-merge base; here it
is re-applied onto feat/dify-builder after PR #41677 merged in the reworked
service.py + _internal_action_allowed gate (which makes the allowance necessary).
The apply_repair idempotency + delete-guard commits (safe fix.apply Retry) land
alongside it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
apply_repair's already-present filter (added for interrupted-step Retry
idempotency) compared create_node/connect intents against before_graph
alone, with no awareness of delete_node intents in the same batch. A
from-scratch build sends delete_node(placeholder_start) + create_node(same
id) in one apply_repair call to replace the canvas's default placeholder
start with the generator's own start node -- the filter dropped the
create_node as "already present" while the delete_node still ran, deleting
the start node with no re-create, so the following connect raised
ValueError: node not found. Mirror handlers_build.py's existing M2 guard:
subtract in-batch delete_node targets from the present-node/edge sets
before filtering, so a delete+recreate of the same id in one batch survives.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Drops create_node intents whose id already exists and connect intents whose
edge already exists (referenced against the original draft graph), so a
fix.apply Retry re-applying the same intents is a clean no-op instead of a
duplicate/ValueError. graph_ops validation (raise on a genuinely fresh
duplicate id) is preserved.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
progress_bus.subscribe() eagerly enters the pub/sub subscription (opening a
Redis connection + starting a listener thread) BEFORE the SSE generator
exists, so the subscribe completes before the Celery advance can publish.
But the only close() lived in the generator's finally -- which Python does
not run if the generator is never started. A streaming Response dropped
before its first frame (client aborted, or an after_request/teardown error)
therefore leaked the connection + thread until process restart.
stream_advance_frames now returns a small _ClosingFrameStream wrapper whose
close() closes the subscription directly (idempotent); the WSGI server calls
close() on the response iterable even on early disconnect, so cleanup fires
regardless of iteration. The inner generator keeps its own finally for the
iterated/disconnect paths, so this is strictly additive -- no happy-path
change. All seven call sites get it unchanged.
Adds a regression test (never-iterated stream -> close() -> subscription closed).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two paths ended a streaming advance without a terminal `state`/`error`
frame, leaving the SSE client stalled to the deadline with a stale held
version -> its next action 409s:
1. advance_session published the terminal `state` frame outside the
try/finally and unguarded. If the post-advance view projection
(get_session_view -> read_graph) or the publish itself raised after a
SUCCESSFUL advance, the exception escaped and no terminal frame was
sent. Guard it and fall back to a terminal `error` frame.
2. submit_action_stream emitted a terminal `state` frame on settle only
for `message`. `update_model` also settles synchronously while bumping
the version, so it now emits one too -- otherwise the FE keeps the old
version and 409s on its next action.
Adds regression tests for both (projection-failure -> error frame;
update_model -> state frame).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
WorkflowService.publish_workflow returns a single Workflow (-> Workflow), but
dify_port.publish still unpacked it as (workflow, retirement_candidates) -- a
stale signature. Every other caller was updated when the return type changed
(via the main merge); only the Dify Builder port was missed, so every publish
crashed with "TypeError: cannot unpack non-iterable Workflow object", surfaced
to the user as a generic "step failed" SSE frame.
Assign the single return value (retirement_candidates was unused anyway). The
existing test_dify_port publish test mocked publish_workflow as a 2-tuple, which
masked the bug -- corrected it to the real -> Workflow signature so it now guards
the regression.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A build for a workflow app whose goal reads like a chatbot produced an empty
canvas while the assistant reported "Workflow built on the canvas.": the plan
was chatbot-shaped, build_nodes fed it to the generator (mode="workflow"), the
LLM emitted a chatflow graph (answer node / no end node), the generator
rejected it as MISSING_TERMINAL -- a class it does NOT retry -- and build_nodes
swallowed the error into []. handle_plan_approval then treated [] as a
successful build: it deleted the placeholder start and advanced to
build.execution, leaving nothing on the canvas.
Two parts:
1. build_nodes now prepends an explicit workflow-topology directive (one
start + >=1 end node, no answer nodes) to the generator instruction, and
retries ONCE on an error/empty result with the specific error fed back as
a corrective nudge -- covering the terminal-node failure the shared
generator skips.
2. handle_plan_approval refuses to fake success: when build_nodes yields zero
create_node intents it surfaces an honest error and stays in
build.plan_approval (retryable) without deleting the placeholder, instead
of emptying the canvas and claiming a build. A loop-back re-approve still
returns the fixed create intents (only filtered as already-present), so
zero create intents unambiguously means a genuine generation failure.
Adds regression tests for both. Note: part 1 improves LLM reliability
(verifiable live); part 2 is the deterministic guarantee against the
false-success empty canvas.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
It was stubbed to [] in LlmBuilderAgent, canned in PlaceholderAgent, and never
called by any handler — the Build failure path reuses Fix cognition (diagnose +
propose_repair). Removed from the DifyBuilderAgent Protocol, both implementations,
and all test doubles.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Final consolidated fix wave from whole-branch review of the Real Build +
Edit Cognition slice:
- _ground now overwrites the model dict on ANY create_node whose config
carries a model dict (llm, question-classifier, parameter-extractor),
not just "llm", so a drifted/hallucinated provider/name on those other
node types no longer flows through ungrounded.
- to_intents now carries a generator edge's sourceHandle/targetHandle
into the connect intent's args (source_handle/target_handle) so
branching nodes (if-else, question-classifier) wire onto the correct
port instead of collapsing onto the default handle; edges without
handles still produce bare {from_node, to_node} args.
- Cleared the 17 ruff errors (PT018/E302/E306/E501) across the slice's
test files by splitting composite asserts, adding missing blank
lines, and wrapping long lines -- no assertions weakened, no noqa.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
analyze_impact/propose_edit_plan/build_edit_intents now call
services.dify_builder.agent.edit.* via _model_or_none() instead of
delegating to the canned PlaceholderAgent. 9 of the Protocol's 14
Build/Edit/Fix methods now use real LLM cognition; only
generate_mock_inputs and propose_build_repair (returns []) remain
deferred pending the live-test step.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
analyze_impact could raise on a non-list target_node_ids from the LLM (no
isinstance guard, unlike fields/values) -- violated the never-crash
contract. Guard it the same way. Also collapse the fake models' invoke_llm
signatures to **_kwargs (underscore-prefixed, no noqa) per the ARG lint
constraint, and pin two more malformed-shape degrade paths
(build_edit_intents non-list intents, propose_edit_plan non-list plan).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
handle_test_and_repair's AssistantTurnItem.cards was unconditional even
though error/change_set cards are now only appended when
propose_build_repair returns intents -- the manifest claimed cards that
were never attached in the neutral (empty-repair) path. Make cards
conditional to match what's actually appended, and assert it in both
branches.
Remove three noqa comments added in the prior commit that suppressed
ARG001/ARG005 on new test code (the global constraint disallows noqa
for non-enabled rules); switch the genuinely-unused monkeypatch
args/lambda params to underscore-prefixed names instead, and drop a
build_nodes monkeypatch that exercised nothing. Add
test_remaining_build_methods_thread_model_and_tenant_args to cover
propose_plan_v1/discover_resources/bind_resources/build_nodes/
learn_from_build's model/tenant_id/model_config threading, matching
the existing analyze_goal coverage.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
LlmBuilderAgent's 6 Build methods (analyze_goal, propose_plan_v1,
discover_resources, bind_resources, build_nodes, learn_from_build) now
delegate to services.dify_builder.agent.build instead of the canned
PlaceholderAgent. propose_build_repair returns [] -- there's no real
failure signal to diagnose until the live test step is de-canned.
handle_test_and_repair now conditions the error card + apply_repair on
a non-empty propose_build_repair result: placeholder mode keeps today's
"found and fixed" arc, while real cognition (which never reports a
failure yet) emits a neutral "no issues found" review summary instead
of a fake error/fix on a hardcoded node id that real build_nodes
wouldn't have generated anyway.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Grounding only overwrites provider+name on an llm node's model dict now,
preserving whatever mode/completion_params the generator produced instead
of synthesizing a temperature when none was present. knowledge-retrieval
grounding now assigns each node its own dataset_ids list copy instead of
aliasing one shared list across every KB node in the graph.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Fix S110: replace bare except-pass with explicit degrade behavior
- Fix E501: wrap long function signatures to <=120 chars
- Fix I001: sort imports in test file (resources to top)
- Fix PT018: split composite assertions into separate statements
- Add _BoomInstance for provider-error testing
- Add 5 degrade tests (analyze_goal, propose_plan_v1 x2, discover_resources, learn_from_build)
- Remove unused _KIND_BY_PREFIX dict
- Add noqa comments for test mock arguments
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Only map the first start-type node to canonical 'start'; additional starts
retain their original ids to prevent collisions and ambiguous intents.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>