fix: workflow incorrectly marked as completed while nodes are still executing#26
Conversation
Code Review by Qodo
1. print() in propagate_skip_from_edge()
|
![qodo-code-review[bot]](https://avatars.githubusercontent.com/in/484649?s=60&v=4){kind=small}
| if edge_states["has_taken"]: | ||
| # Enqueue node | ||
| # Start execution and enqueue node | ||
| print(f"Starting execution for node: {downstream_node_id}") |
There was a problem hiding this comment.
1. print() in propagate_skip_from_edge() 📘 Rule violation ✧ Quality
• The backend workflow traversal code emits output via print(), which bypasses the project’s logging system and makes production diagnostics/auditing inconsistent. • This violates the requirement to use a module-level logger = logging.getLogger(__name__) and log through that logger instead of print() in non-test code. • Using print() also makes it harder to control log levels, routing, and formatting across environments.
Agent prompt
## Issue description
`api/core/workflow/graph_engine/graph_traversal/skip_propagator.py` uses `print()` in production code. Compliance requires using Python `logging` with a module-level `logger = logging.getLogger(__name__)` and no `print()` statements.
## Issue Context
The message is emitted when an incoming edge is taken and execution is started/enqueued. This should be a structured, level-controlled log entry.
## Fix Focus Areas
- api/core/workflow/graph_engine/graph_traversal/skip_propagator.py[59-64]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
Comment on lines
81
to
+86
| # Mark all outgoing edges as skipped and propagate | ||
| outgoing_edges = self._graph.get_outgoing_edges(node_id) | ||
| for edge in outgoing_edges: | ||
| self._state_manager.mark_edge_skipped(edge.id) | ||
| # Recursively propagate skip | ||
| self.propagate_skip_from_edge(edge.id) | ||
| self._state_manager.mark_edge_skipped(edge.id) |
There was a problem hiding this comment.
2. Skip recursion blocked 🐞 Bug ✓ Correctness
• _propagate_skip_to_node() now calls propagate_skip_from_edge() before marking the outgoing edge as SKIPPED, so the downstream node’s incoming edge can still be UNKNOWN when analyzed. • Because propagate_skip_from_edge() hard-stops on any UNKNOWN incoming edge, skip propagation can terminate prematurely and never reach deeper downstream nodes. • Result: nodes that should be skipped can remain UNKNOWN (and may later execute or keep the workflow in an inconsistent state).
Agent prompt
### Issue description
`_propagate_skip_to_node()` recurses into `propagate_skip_from_edge()` before marking the outgoing edge as SKIPPED. Since `propagate_skip_from_edge()` stops when any incoming edge is UNKNOWN, this can block skip propagation and leave downstream nodes unskipped.
### Issue Context
Skip propagation relies on `GraphStateManager.analyze_edge_states()` reading real `edge.state`. If the edge hasn’t been marked SKIPPED yet, downstream nodes can observe UNKNOWN and propagation halts.
### Fix Focus Areas
- api/core/workflow/graph_engine/graph_traversal/skip_propagator.py[81-87]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
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
1 participant
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.
Benchmark PR from agentic-review-benchmarks#13