feat: Add evaluations support to ManagedAgent.run()#153
Draft
jsonbailey wants to merge 3 commits intojb/aic-2174/langchain-graph-runnerfrom
Draft
feat: Add evaluations support to ManagedAgent.run()#153jsonbailey wants to merge 3 commits intojb/aic-2174/langchain-graph-runnerfrom
jsonbailey wants to merge 3 commits intojb/aic-2174/langchain-graph-runnerfrom
Conversation
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
4f29d99 to
0ea4a04
Compare
jsonbailey
changed the base branch from
jb/aic-2388/enrich-metrics
to
jb/aic-2174/langchain-graph-runner
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
0539ba1 to
404670d
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
0ea4a04 to
04e80a8
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
404670d to
f132154
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
04e80a8 to
29ced10
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
f132154 to
eb1004c
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
29ced10 to
c343602
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
eb1004c to
8a049e2
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
c343602 to
1a24a4f
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
8a049e2 to
cea3780
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
1a24a4f to
78a7ded
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
cea3780 to
f27f9b8
Compare
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
38951a6 to
52756c7
Compare
jsonbailey
force-pushed
the
jb/aic-2174/langchain-graph-runner
branch
from
f27f9b8 to
d892533
Compare
Wire judge evaluations into ManagedAgent.run() via an asyncio.Task, mirroring ManagedModel.run(). Awaiting result.evaluations guarantees both evaluation and tracker.track_judge_result() complete. run() returns immediately; the evaluations task resolves asynchronously. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Mirror the managed_model.py fix in managed_agent.py: wrap tracker.track_judge_result() in try/except so a tracking failure does not destroy successfully computed evaluation results, and log a warning when a judge evaluation fails (r.success is False) so failures are visible rather than silently skipped.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
jsonbailey
force-pushed
the
jb/aic-2174/agent-evaluations
branch
from
52756c7 to
ff2de9a
Compare
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.
Summary
ManagedAgent.run()viaasyncio.Task, mirroringManagedModel.run()(PR 7 / PR 8)run()returns immediately;await result.evaluationsguarantees both evaluation andtracker.track_judge_result()completeai_config.evaluator.evaluate(input, content)— resolves to empty list withEvaluator.noop()success=False) do NOT calltrack_judge_result()Depends on
Test plan
uv run pytest packages/sdk/server-ai/tests/)TestManagedAgentEvaluationstests: run returns before evaluations resolve, collect results, tracking fires on await, noop evaluator returns empty list, failed results not tracked🤖 Generated with Claude Code