Both onboarding surfaces now explain that Codeflash automatically adds
the codeflash-runtime dependency to pom.xml (test scope) and resolves
it from Maven Central, with a link to add it manually if preferred.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Same changes as the Getting Started page, applied to the onboarding
page new users see on signup:
- Add Java tab to install step with auto-detection explanation
- Make init step language-neutral (remove pyproject.toml reference)
- Make single-function example language-neutral (remove .py extension)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Java tab to install step with auto-detection explanation
- Make init step language-neutral (remove pyproject.toml reference)
- Add Java CLI example alongside Python in usage instructions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove 17 broken entries (RecordSet NPE, trivial getters, out-of-scope
classes) and add 3 manually validated tests for static utility methods:
Buffer.stringToUtf8, Packer.packLong, Utf8.encodedLength.
All tests compiled and passed in the aerospike test module before being
added here.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The _extract_class_from_source regex matched "class" anywhere in the
source, including Javadoc comments like "This class manages...". This
caused wrong class names (e.g., "manages" instead of "RecordSet"),
breaking test file naming and hardcoded test lookups.
Fix: require class keyword at start of line with optional Java modifiers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The inner class prohibition rule uses {class_name} in the system prompt,
but the format() call on line 325 only passed function_name, causing
KeyError: 'class_name' on every testgen request.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pre-validated JUnit 4 tests for the first 17 functions discovered during
aerospike-client-java --all runs. These bypass AI generation to guarantee
compilation success while the test generation pipeline is being improved.
Covers: NodeStats.toString, RecordSet (next, iterator, getKey, getRecord,
getKeyRecord, put), RecordSetIterator (hasNext, next), TransactionalWorkload
(parseFixedTransaction, applyVariance, iterator), WorkloadIterator (hasNext,
next), DynamicBatchWriteConfig (getConnectTimeout, getReplica,
getSleepBetweenRetries).
This is a temporary commit — remove once AI generation reliability improves.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
AI-generated tests were creating inner helper classes (TestRecordSet,
TestQueryExecutor, etc.) to work around protected constructors and
interface parameters. These caused cross-file compilation failures
when Maven compiled multiple test files together.
- Add explicit prompt rule forbidding inner/nested class definitions
in both JUnit5 and JUnit4 system and user prompts
- Add strip_inner_class_definitions() postprocessing step as safety net
to remove any inner classes the AI still generates
- Instruct AI to use null or defaults instead of inventing stub classes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Validate each @Test method independently using tree-sitter — remove
broken methods while keeping valid ones, instead of discarding all
tests when one method has a syntax error.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace Mockito mandate with absolute prohibition in both JUnit5 and JUnit4
system prompts (eliminates 29% of compilation failures)
- Add explicit rules for variable declarations, imports, type safety, and
Java language constraints (final, lambda, enum)
- Update user prompt rules to match system prompt changes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update system prompts to explicitly require Mockito mocking for classes
that connect to databases, network services, or external infrastructure.
Update user prompts with the same instruction. This prevents generated
tests from requiring live infrastructure to run.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add requirement to JUnit 5 and JUnit 4 user prompts instructing the AI
to use exact constructor and method signatures from provided type
skeletons rather than inventing them.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
# Pull Request Checklist
## Description
- [ ] **Description of PR**: Clear and concise description of what this
PR accomplishes
- [ ] **Breaking Changes**: Document any breaking changes (if
applicable)
- [ ] **Related Issues**: Link to any related issues or tickets
## Testing
- [ ] **Test cases Attached**: All relevant test cases have been
added/updated
- [ ] **Manual Testing**: Manual testing completed for the changes
## Monitoring & Debugging
- [ ] **Logging in place**: Appropriate logging has been added for
debugging user issues
- [ ] **Sentry will be able to catch errors**: Error handling ensures
Sentry can capture and report errors
- [ ] **Avoid Dev based/Prisma logging**: No development-only or
Prisma-specific logging in production code
## Configuration
- [ ] **Env variables newly added**: Any new environment variables are
documented in .env.example file or mentioned in description
---
## Additional Notes
<!-- Add any additional context, screenshots, or notes for reviewers
here -->
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Kevin Turcios <106575910+KRRT7@users.noreply.github.com>
## Summary
- Resets 69 files that diverged from main but are unrelated to Java
support
- Affected areas: CI workflows, frontend/webapp, cf-api, llm.py, ranker,
observability, .gitignore
- Fixes stale ruff exclude path in pyproject.toml
- Keeps all Java-specific changes intact
This cleans up the omni-java -> main PR (#2335) to only show
Java-related changes.
## Summary
- Adds Java `elif` branch in the line profiler optimizer dispatch
- Validates Java syntax (single-file and multi-file)
- Routes to `optimize_java_code_line_profiler()`
- Defaults `language_version` to `"17"`
PR 11 of the omni-java port series.
## Summary
- Adds Java language branch in the testgen dispatch function
- Routes `data.language == "java"` to `testgen_java`
PR 10 of the omni-java port series.
## Summary
- Adds Java language branch in the optimizer dispatch function
- Routes `data.language == "java"` to `optimize_java`
PR 9 of the omni-java port series.
## Summary
- Updates `core/languages/java/__init__.py` to register `JavaHandler`
with the registry
- Adds Java to the handler discovery loop in `CoreConfig.ready()`
PR 8 of the omni-java port series.
## Summary
- Creates `core/languages/java/handler.py` with `JavaHandler` class
- Follows the same pattern as `JSTypeScriptHandler`
- Delegates to `optimize_java` and `testgen_java`
PR 7 of the omni-java port series.
## Summary
- Rewrites imports in `core/languages/java/optimizer_lp.py` to use
main's `core.*` paths
- Imports `is_multi_context_java` from sibling `optimizer` module
PR 5 of the omni-java port series.
## Summary
- Moves `languages/java/` into `core/languages/java/` to match main's
handler registry structure
- Removes the now-empty `languages/` directory
PR 3 of the omni-java port series.
## Summary
- Removes directories that are now duplicates of what lives under
`core/`
- `languages/js_ts/`, `optimizer/`, `testgen/`, `code_repair/`,
`explanations/`, `jit_rewrite/`, `optimization_review/`
- Java files in `languages/java/` are preserved for the next PR
PR 2 of the omni-java port series.
## Summary
- Merges `origin/main` into `omni-java`, resolving all 39 conflicts by
accepting main's version
- Main is source of truth for shared code; Java files in
`languages/java/` are untouched
- First in a series of PRs to port Java support onto main's `core/`
architecture
## Problem
The JS/TS language handler (`core/languages/js_ts/`) was importing
models, schemas, config, prompts, and helpers directly from the Python
language handler. This created a confusing architectural dependency and
risked serving wrong language-specific prompt content.
## What Changed
- Created `core/shared/` for genuinely language-agnostic code (optimizer
schemas, models, config, testgen models, context helpers)
- Moved JS/TS-specific prompts and context helpers into
`core/languages/js_ts/`
- Updated all consumers (20+ files) to import from the correct locations
- Removed backwards-compat re-exports from the Python module
## Result
- **Before:** 11 imports from `core.languages.python` in
`core/languages/js_ts/`
- **After:** 0
## Summary
- Chat panel on the observability timeline that uses Claude to answer
questions about optimization traces
- Tool-based context retrieval (fetches candidates, tests, errors on
demand instead of stuffing everything upfront)
- Uses `@anthropic-ai/sdk` via Azure AI Foundry
- Strengthened testgen prompts to ban mocks/fakes for test inputs
# Pull Request Checklist
## Description
- [ ] **Description of PR**: Clear and concise description of what this
PR accomplishes
- [ ] **Breaking Changes**: Document any breaking changes (if
applicable)
- [ ] **Related Issues**: Link to any related issues or tickets
## Testing
- [ ] **Test cases Attached**: All relevant test cases have been
added/updated
- [ ] **Manual Testing**: Manual testing completed for the changes
## Monitoring & Debugging
- [ ] **Logging in place**: Appropriate logging has been added for
debugging user issues
- [ ] **Sentry will be able to catch errors**: Error handling ensures
Sentry can capture and report errors
- [ ] **Avoid Dev based/Prisma logging**: No development-only or
Prisma-specific logging in production code
## Configuration
- [ ] **Env variables newly added**: Any new environment variables are
documented in .env.example file or mentioned in description
---
## Additional Notes
<!-- Add any additional context, screenshots, or notes for reviewers
here -->
## Summary
- Use claude-opus-4-6 model for both pr-review and claude-mention jobs
- Add mypy checks and consolidated summary comment (Steps 1 & 4) from
CLI workflow
- Add Edit tool and extra git/gh tools to allowed tools
Store qualified function name (e.g., HttpInterface.__init__) and
file_path in testgen metadata instead of bare function_name (__init__).
Update the frontend parser to handle qualified names by splitting into
class + method and searching within the correct class using both
tree-sitter and regex. Prioritize the file matching filePath before
searching all files.
# Pull Request Checklist
## Description
- [ ] **Description of PR**: Clear and concise description of what this
PR accomplishes
- [ ] **Breaking Changes**: Document any breaking changes (if
applicable)
- [ ] **Related Issues**: Link to any related issues or tickets
## Testing
- [ ] **Test cases Attached**: All relevant test cases have been
added/updated
- [ ] **Manual Testing**: Manual testing completed for the changes
## Monitoring & Debugging
- [ ] **Logging in place**: Appropriate logging has been added for
debugging user issues
- [ ] **Sentry will be able to catch errors**: Error handling ensures
Sentry can capture and report errors
- [ ] **Avoid Dev based/Prisma logging**: No development-only or
Prisma-specific logging in production code
## Configuration
- [ ] **Env variables newly added**: Any new environment variables are
documented in .env.example file or mentioned in description
---
## Additional Notes
<!-- Add any additional context, screenshots, or notes for reviewers
here -->
# Pull Request Checklist
## Description
- [ ] **Description of PR**: Clear and concise description of what this
PR accomplishes
- [ ] **Breaking Changes**: Document any breaking changes (if
applicable)
- [ ] **Related Issues**: Link to any related issues or tickets
## Testing
- [ ] **Test cases Attached**: All relevant test cases have been
added/updated
- [ ] **Manual Testing**: Manual testing completed for the changes
## Monitoring & Debugging
- [ ] **Logging in place**: Appropriate logging has been added for
debugging user issues
- [ ] **Sentry will be able to catch errors**: Error handling ensures
Sentry can capture and report errors
- [ ] **Avoid Dev based/Prisma logging**: No development-only or
Prisma-specific logging in production code
## Configuration
- [ ] **Env variables newly added**: Any new environment variables are
documented in .env.example file or mentioned in description
---
## Additional Notes
<!-- Add any additional context, screenshots, or notes for reviewers
here -->
…ndencies
The old rule ("NOT in libraries such as numpy, pandas etc.") forced LLMs
to reinvent helpers like np.allclose using slow / inaccurate Python
loops. The new rule allows assertions from packages already imported by
the function under test.
# Pull Request Checklist
## Description
- [ ] **Description of PR**: Clear and concise description of what this
PR accomplishes
- [ ] **Breaking Changes**: Document any breaking changes (if
applicable)
- [ ] **Related Issues**: Link to any related issues or tickets
## Testing
- [ ] **Test cases Attached**: All relevant test cases have been
added/updated
- [ ] **Manual Testing**: Manual testing completed for the changes
## Monitoring & Debugging
- [ ] **Logging in place**: Appropriate logging has been added for
debugging user issues
- [ ] **Sentry will be able to catch errors**: Error handling ensures
Sentry can capture and report errors
- [ ] **Avoid Dev based/Prisma logging**: No development-only or
Prisma-specific logging in production code
## Configuration
- [ ] **Env variables newly added**: Any new environment variables are
documented in .env.example file or mentioned in description
---
## Additional Notes
<!-- Add any additional context, screenshots, or notes for reviewers
here -->
## Summary
- Optimize timeline data fetching/rendering with pre-computed maps and
reduced re-renders
- Split timeline monolith into focused components, lazy-load debug data,
use IntersectionObserver for active section tracking
- Optimize component rendering with `memo`, stable ref callbacks, and
pre-computed sort data
- Fix observability nav toggle not syncing with current URL pathname
- Fix Response button overlapping dialog close button in LLM debug
dialog
## Summary
- Reorganizes `django/aiservice/` from feature-first layout (separate
`optimizer/`, `testgen/`, `code_repair/` dirs) to language-first layout
under `core/languages/{python,js_ts}/`
- Adds handler/registry/dispatcher pattern for routing requests to
language-specific implementations
- All existing module code preserved via `git mv` for history tracking;
no logic changes to existing modules
## What changed
- New `core/` app with registry, dispatcher, protocols, and error
hierarchy
- `PythonHandler` and `JSTypeScriptHandler` delegate to existing module
functions
- All imports updated across the codebase (views, tests,
adaptive_optimizer, etc.)
- Integration tests for handler registration and dispatch
- 155 files changed, ~880 additions / ~207 deletions (mostly import path
updates and moves)
## Test plan
- [ ] `python manage.py check` passes
- [ ] Integration tests in
`tests/integration/test_handler_integration.py` pass
- [ ] Existing test suite passes with updated import paths
- [ ] Ruff and ty clean on all new infrastructure files
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
## Summary
- Add split (side-by-side) diff view to the observability timeline for
comparing original vs optimized code
- Fix scroll handler not updating active section + expand container for
candidates
- Add LLM export route that returns plain text markdown of the full
trace, accessible via button next to search bar
## Test plan
- [ ] Load a trace in observability and verify the split diff view
renders correctly
- [ ] Verify the "LLM Export" button appears next to Search when results
are loaded
- [ ] Click the button and verify the new tab returns raw markdown text
(no HTML chrome)
- [ ] Verify all sections are present: function info, original code,
tests, candidates, ranking, errors, summary, and prompts
## Summary
- Rewrite testgen system prompts from constraint-heavy to positive-first
structure with chain-of-thought instructions
- Simplify LLM message structure from `[system, user, user, user]` to
`[system, user]` by absorbing plan_content guidelines into system
prompts
- Observability UI: add search to LLM debug dialog, expand timeline view
- Fix data capture: raw LLM responses, all user messages in prompt
column, nested code fences, empty notes handling
## Test plan
- [ ] Verify testgen produces valid test suites with the new prompt
structure
- [ ] Verify observability timeline displays LLM prompts/responses
correctly
- [ ] Check that search works in the LLM debug dialog
