Tier 3: LLM agent experience improvements#33
Merged
kavanaghpatrick merged 15 commits intomainfrom Mar 8, 2026
Merged
Conversation
Spec artifacts: - research.md: feasibility analysis and codebase exploration - requirements.md: user stories and acceptance criteria - design.md: architecture and technical decisions - tasks.md: POC-first implementation plan Ready for implementation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
All five features verified end-to-end: 1. Numpy shim transpiles np.* code 2. Auto-parallelization with n=100 returns 100 results 3. Stats include median and histogram 4. Error messages include actionable suggestions 5. Source maps populated on instructions 831 tests passing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Filter NaN/inf values in compute_stats() before computation - Add catch-all error for unsupported np.<func>() and np.<attr> - Guard auto-parallelization against empty/whitespace source - Source map bounds check already correct (no change needed) - Histogram with single unique value already handled (no change needed) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
import numpy as np+np.random.random(),np.sqrt(),np.pi, etc. into supportedmath/randomequivalentsexecute_python(source, n=10000)emojiasm/stats.pywithcompute_stats()— adds median and histogram, replaces duplicated code in inference.py and gpu.pyarr = [0.0] * Nfor fixed-size arrays")Closes #29
Test plan
np.random.random(),np.sqrt(),np.pi,np.abs(),np.sin/cos/exp/log()🤖 Generated with Claude Code