Tidy comments, remove serve.py, sharpen teacher prompt#2
Merged
Conversation
calibrate_temperature said the search range was [0.05, 20]; it is [0.5, 20.0]. threshold_analysis hard-coded "124-row holdout"; use the actual count. Drop a few export_onnx labels that restated the next call.
It was a docstring and a TODO, nothing imported it, and Aegis runs the model in-process via ONNX. Drop the serve optional-deps extra with it.
State the agent>memory>integration>find_action>chat priority as the residual tie-break, make the memory source rule explicit, cover implied multi-step under agent, and strip disfluency before classifying.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Cleanup follow-ups after PR #1 merged: a couple of comments had gone stale,
serve.pywas an unbuilt stub, and the teacher prompt under-encoded thetaxonomy's tie-break rules (which risks inconsistent training labels).
What
calibrate_temperature's search range ([0.05, 20] ->[0.5, 20.0]) and
threshold_analysis's hard-coded "124-row holdout".serve.py(a docstring + TODO, imported by nothing; Aegis runs themodel in-process via ONNX) and its now-unused
servedeps extra.docs/taxonomy.md: state theagent>memory>integration>find_action>chat priority as the residual tie-break,
make the memory source rule explicit, cover implied multi-step under agent,
and strip disfluency before classifying.
Test plan
uv run ruff checkclean,unittest discover -s tests13 pass.