feat: add suspend/resume support for RPA invocations in evaluations #1083
Conversation
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
github-actions
bot
added
test:uipath-langchain
Contributor
Author
Quick Testing GuideInstall the Dev Versionpip install git+https://github.com/UiPath/[email protected]Run Quick Testcd samples/event-trigger
# Test 1: Direct runtime test
python -c "
import asyncio
from uipath.functions.runtime import UiPathFunctionsRuntime
async def test():
runtime = UiPathFunctionsRuntime(
'test_suspend_resume_agent.py',
'main',
'test_suspend_resume_agent'
)
result = await runtime.execute({'query': 'Test'})
print(f'✓ Status: {result.status}')
print(f'✓ Has Trigger: {result.trigger is not None}')
if result.trigger:
print(f'✓ Process: {result.trigger.payload[\"process_name\"]}')
asyncio.run(test())
"
# Test 2: Evaluation test
uipath eval test_suspend_resume_agent evaluations/test_suspend_resume.json --output-file test_output.json
cat test_output.json | python -m json.tool | grep -A 5 "status"Expected Results✅ Status: Key Files Changed
Tag: |
Chibionos
changed the title
Chibionos
force-pushed
the
investigate-rpa-samples
branch
from
0a124f0 to
a35d2a5
Compare
Contributor
|
Just to understand, so the |
cristipufu
reviewed
Jan 14, 2026
| from uipath.runtime.errors import ( | ||
| UiPathErrorCategory, | ||
| UiPathErrorCode, | ||
| UiPathErrorContract, |
Member
There was a problem hiding this comment.
you need to undo everything in this file (this is used for arbitrary python code, no langgraph deps)
|
|
||
| result = UiPathRuntimeResult( | ||
| output={**results.model_dump(by_alias=True)}, | ||
| status=UiPathRuntimeStatus.SUCCESSFUL, |
Member
There was a problem hiding this comment.
if the runtime is suspended, you need to pass the result as suspended to the serverless exector
This commit consolidates changes for suspend/resume functionality: - Add suspend/resume support for RPA invocations in evaluations - Add --resume option and trigger pass-through to eval runtime - Add comprehensive logging for suspend/resume detection - Add architecture documentation for interrupt/suspend/resume patterns - Add Claude Code skills for agents - Add content_tokens and argument_properties to agent model - Expose more configs in manager - Add documents samples - Fix linting issues in functions runtime - Remove deprecated hello-world sample - Update evaluation spans with output attributes and metadata 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Chibionos
force-pushed
the
investigate-rpa-samples
branch
from
a35d2a5 to
c2548d0
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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
Adds support for suspend/resume pattern in evaluation runtime, enabling agents to suspend execution when invoking RPA processes and resume after completion.
Key Changes
Suspend Detection (_runtime.py)
UiPathRuntimeStatus.SUSPENDEDafter agent executionResume Support (cli_eval.py)
--resumeflag to evaluation CLITrigger Pass-Through
interruptId: Unique interrupt identifiertriggerType: Type of trigger (e.g., "Api")payload: InvokeProcess details (process name, input arguments, folder path)Comprehensive Logging
Testing
Testing is done via the sample agent in the companion PR: UiPath/uipath-langchain-python#397
Related
Companion PR for sample agent: UiPath/uipath-langchain-python#397