[Inference] Reasoning util improvements #234724
Merged
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
dgieselaar
force-pushed
the
reasoning-util-improvements
branch
3 times, most recently
from
12bca28 to
e955e80
Compare
dgieselaar
added
release_note:skip
dgieselaar
force-pushed
the
reasoning-util-improvements
branch
from
904b2e4 to
2a54209
Compare
pgayvallet
approved these changes
Sep 15, 2025
botelastic
bot
added
ci:project-deploy-observability
Contributor
|
Pinging @elastic/obs-ai-assistant (Team:Obs AI Assistant) |
Contributor
🤖 GitHub commentsExpand to view the GitHub comments
Just comment with:
|
sorenlouv
approved these changes
Sep 15, 2025
Contributor
⏳ Build in-progress
Failed CI StepsTest Failures
History
|
CAWilson94
pushed a commit
to CAWilson94/kibana
that referenced
this pull request
Sep 24, 2025
Various improvements for the `executeAsReasoningAgent` helper: - add `finalToolChoice` to formalize the concept of having a tool call that is required for the definitive output - change from PLAN > GATHER > REFLECT to GOAL > REFLECT > PLAN to have the LLM continuously focus on the goal of the task - remove all content after reasoning markers to prevent the LLM from producing definitive output at the wrong time (we should use `stopSequences` for this in the near future) - add tests
niros1
pushed a commit
that referenced
this pull request
Sep 30, 2025
Various improvements for the `executeAsReasoningAgent` helper: - add `finalToolChoice` to formalize the concept of having a tool call that is required for the definitive output - change from PLAN > GATHER > REFLECT to GOAL > REFLECT > PLAN to have the LLM continuously focus on the goal of the task - remove all content after reasoning markers to prevent the LLM from producing definitive output at the wrong time (we should use `stopSequences` for this in the near future) - add tests
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Various improvements for the
executeAsReasoningAgenthelper:finalToolChoiceto formalize the concept of having a tool call that is required for the definitive outputstopSequencesfor this in the near future)