Skip to content

Feature/476 llm test generation#580

Open
oraimoitel wants to merge 4 commits into
Traqora:mainfrom
oraimoitel:feature/476-llm-test-generation
Open

Feature/476 llm test generation#580
oraimoitel wants to merge 4 commits into
Traqora:mainfrom
oraimoitel:feature/476-llm-test-generation

Conversation

@oraimoitel

@oraimoitel oraimoitel commented Jul 25, 2026

Copy link
Copy Markdown

Closes #468


Closes #574


Closes #467


Closes #476


Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context.

Fixes # (issue)

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • Any dependent changes have been merged and published in downstream modules

AstroML Dev added 4 commits July 25, 2026 08:55
- Add LLM feature definitions (embeddings, scores, meta)
- Add embedding feature computers (transaction, account, alert)
- Add scoring feature computers (fraud, confidence, uncertainty)
- Add LLM feature generator orchestration
- Add LLM feature integration layer with materialized views
- Add feature computation using LLM providers
- Add pipeline integration for LLM features
- Update features/ and llm/ package exports

Closes Traqora#467
- Add entry point group in pyproject.toml for astroml.feature_computers
- Add plugin discovery in FeatureRegistry via importlib.metadata
- Add plugin discovery in ComputationEngine for BaseFeatureComputer plugins
- Add plugin validation (required methods check)
- Add plugin registration API with source tracking
- Add example external plugin in examples/plugin_example.py
- Add list_plugin_computers() API to ComputationEngine

Closes Traqora#574
- Add fine-tuning pipeline orchestration with data prep, training, eval
- Add dataset preparation with validation, splitting, and formatting
- Add trainer wrapper supporting OpenAI, Anthropic, and LoRA/QLoRA
- Add evaluator with baseline comparison and A/B testing
- Add fine-tuned model registry with versioning and rollback
- Add default fine-tuning config YAML for all targets
- Support fraud explanation, SQL gen, transaction classification, chatbot

Closes Traqora#468
- Add test generation orchestrator with multiple test types
- Add code analysis strategy (function extraction, branch detection)
- Add docstring parsing strategy (examples, params, return values)
- Add type-based strategy (hypothesis strategies, boundary values)
- Add assertion generator with templates and type mapping
- Add fixture generator (pytest, SQLAlchemy, mocks)
- Add test quality reviewer with scoring and suggestions
- Add CLI tool for test generation
- Support unit, integration, property-based, edge case, regression tests

Closes Traqora#476
@oraimoitel

Copy link
Copy Markdown
Author

Closes #580

@drips-wave

drips-wave Bot commented Jul 25, 2026

Copy link
Copy Markdown

@oraimoitel Great news! 🎉 Based on an automated assessment of this PR, the linked Wave issue(s) no longer count against your application limits.

You can now already apply to more issues while waiting for a review of this PR. Keep up the great work! 🚀

Learn more about application limits

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

1 participant