Repository navigation
fix(client): give each graph() run its own run id - #132
Merged
cursor[bot] merged 5 commits intoOct 15, 2026
Merged
Conversation
graph() caches the built graph per context so repeated runs skip re-evaluating every node's flag. The build also created the graph's track data, run id included, so every run for the same context reported the same runId on its $ld:ai:graph:* events. Each run now copies the cached track data with a fresh runId and passes it to route and stream_route through their opts, so the node, handoff and graph-level events of one run share one id and the next run gets another. The flag evaluations stay cached.
Contributor
Author
|
bugbot run |
apucacao
added this pull request to stack #151
October 9, 2026 15:58
Contributor
Author
|
bugbot run |
Contributor
Author
|
bugbot run |
Each run's launchdarkly.graph span must carry the runId of that run's graph-level events, for both invoke and stream, and the two runs' spans must carry different ids.
Contributor
Author
|
bugbot run |
Contributor
Author
|
bugbot run |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ Bugbot reviewed your changes and found no new issues!
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit a5e9ad3. Configure here.
jeffdupont
reviewed
Oct 14, 2026
jeffdupont
left a comment
jeffdupont
left a comment
Contributor
There was a problem hiding this comment.
Verified this fixes the run-id blocker on #121.
- Each
invokeandstreamnow mints a freshrunIdafter the cache lookup (graph.py:945,:1182). The span attribute and all 8 handoff events read it, so Bugbot's #121 finding (graph.py:944) is covered too. TestGraphRunIdfails on #121'sgraph.py(both modes) and passes here. Full client suite: 1533 passed, 1 skipped.
I'll approve once this is out of draft. Simplest path: merge this into fix/native-graph-span-identity so #121 lands with it, then I approve #121.
apucacao
marked this pull request as ready for review
October 14, 2026 18:00
jeffdupont
approved these changes
Oct 15, 2026
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
2 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.
Summary
Running the same
graph()twice for the same context reported both runs under one run id, so separate runs looked like one in the$ld:ai:graph:*events.graph()caches the built graph per context so it doesn't re-evaluate every node's flag on each call. The run id was created in that build, so it was cached too. Each run now gets a fresh id. Every graph event within a run still shares it, and the flag evaluations stay cached.Builds on #121. In JS the same fix is part of launchdarkly/js-ai-sdk#101.
Testing
test_graph_stream.py, for bothinvokeandstream: two runs on onegraph()instance and context get different ids, and all graph events in a run (node, handoff, success) share one. It fails on main.Note
Overview
Fixes duplicate
runIdwhen reusing a cachedgraph()build: separateinvoke/streamcalls on the same instance and context no longer look like one run in$ld:ai:graph:*analytics and OTel.Each run now mints a fresh
runIdat execution time (merged into track data from the cached build) and passes it into routing via_run_track_datain route/stream opts. Handoff success/failure events emitted from the cached graph definition read that per-run payload instead of the build-time id. Graph caching per context is unchanged.Adds
TestGraphRunIdfor bothinvokeandstream: two runs get distinct ids, and all graph events plus thelaunchdarkly.graphspan share one id per run.Reviewed by Cursor Bugbot for commit a5e9ad3. Bugbot is set up for automated code reviews on this repo. Configure here.