| feat(cache): add LangGraph node-level Replay Guard for framework regression testing
Replay mode previously only mocked LLM calls but let KernelVerifier run
real compilation. When the environment differed from recording time
(e.g. missing AVX512/OpenMP), the verifier would fail and route to
conductor, which had no cached LLM response — causing a silent retry
loop until max_step was exhausted.
Introduce ReplaySnapshotStore that records each node's key output fields
during cache_mode=record and verifies them during cache_mode=replay.
On mismatch (e.g. verifier_result expected=True but actual=False due to
env issues), a ReplayGuardError is raised immediately, preventing the
workflow from entering un-cached error-handling branches.
Key changes:
- New replay_guard.py: ReplaySnapshotStore with per-node field snapshots
using sha256 fingerprints for large text fields
- Extend track_node decorator to call record/verify after each node
- Add _replay_guard field to BaseState so LangGraph preserves it
- Inject ReplaySnapshotStore into state in LangGraphTask when
cache_mode is record or replay
- Add _node_snapshots to existing cache sample JSON files
- 14 new unit tests for replay guard logic
The guard is completely inactive (zero overhead) when cache_mode is off,
which is the default for all normal workflows.
Made-with: Cursor
| 1 个月前 |
| refactor: rename project from aikg to akg_agents
Complete project renaming:
- Renamed main directory: aikg/ -> akg_agents/
- Renamed Python package: ai_kernel_generator -> akg_agents
- Renamed benchmark: aikgbench -> akg_kernels_bench
- Updated client API: AIKGClient -> AKGAgentsClient
- Updated all import paths and module references
- Updated environment variables: AIKG_* -> AKG_AGENTS_*
- Updated output directories and log paths
- Updated all documentation and configuration files
- Fixed Git submodules paths
Breaking changes:
- All Python imports need to update to 'from akg_agents'
- Environment variable names changed: AIKG_* -> AKG_AGENTS_*
- Package name changed from ai_kernel_generator to akg_agents
- Client class renamed: AIKGClient -> AKGAgentsClient
Co-authored-by: Cursor <cursoragent@cursor.com>
| 3 个月前 |
| refactor tests dir
| 3 个月前 |
| Refactor: remove legacy code, standardize test structure, and enhance core module test coverage
| 2 个月前 |
| update fixcodegen
| 1 个月前 |
| LLM 输出去 JSON 化改造 + stream 模式支持
- KernelGen/Coder: 移除 JSON parser 依赖，改用代码提取 + py_compile 语法校验
- 删除 robust_parse 节点和相关 parser 配置
- 新增 stream 模式支持
- 新增 KernelGen 基准测试工具 (bench_kernel_gen.py)
- 更新依赖文件 requirements
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
| 2 个月前 |
| fix llm settings fallback
| 1 个月前 |
| Refactor Skill System: Replace level-based management with category-based management. Update documentation and examples to reflect changes in skill classification, filtering, and selection processes. Adjusted skill metadata to use categories instead of levels for better organization and retrieval.
| 2 个月前 |
| bugfix: wrong tool invoke
| 2 个月前 |
| Refactor: remove legacy code, standardize test structure, and enhance core module test coverage
| 2 个月前 |
| Refactor: remove legacy code, standardize test structure, and enhance core module test coverage
| 2 个月前 |
| Refactor: remove legacy code, standardize test structure, and enhance core module test coverage
| 2 个月前 |
