2.0 KiB
Step 7 — Implementation Detail
Decision: the original pipeline is deleted. The owner asked for its removal on 2026-10-06, after it had first been kept frozen in app/legacy/, tests/legacy/ and eval/legacy/ (step 6).
- Deleted
app/legacy/,tests/legacy/,eval/legacy/andeval/datasets/benchmark_cases.json. - Removed the legacy-only settings from
app/config.pyand.env.example:HOST,PORT, the OpenAI and Azure keys,LLM_TEMPERATURE,GOOGLE_APPLICATION_CREDENTIALS,GCP_PROJECT_ID,GCP_REGION,ADK_*,DEVELOPER_KNOWLEDGE_MCP_*,SKILLS_DIR,EVAL_DATASET_PATH. Google client libraries still readGOOGLE_APPLICATION_CREDENTIALSfrom the environment themselves. - Removed the legacy exclusions from
ruff.toml,mypy.iniand.dockerignore. - Removed four dependencies no live module imports:
langchain,langchain-openai,sqlalchemy,asyncpg. - Rewrote the top of
README.mdaround the Orchestrator, Specialists, Skills and A2A, and pointedVALIDATION.mdateval.solution_eval.
Verified: 206 passed (227 less the 21 legacy tests); ruff check . and mypy . clean; grep -rn "app\.legacy\|eval\.legacy" app eval tests scripts is empty; the image rebuilt from the trimmed requirements.txt imports every live module, including both checkpointers, and answers /health and the agent card.
Recovering the old code: the committed versions are in git history at their pre-move paths (app/adk/, app/nodes/, app/workflows/, app/skills/, app/states/, app/agent.py, app/card.py) up to commit e94b249. Uncommitted formatting changes to those files were not kept.
Left in place, because they are checked-in sample artefacts and not pipeline code: scripts/validate_artifacts.py, tests/test_artifacts.py, tests/test_package.py, the root terraform/, docs/*.md, deliverables/{as-is,target,validation,guides}/, requirements.yaml. app/database.py keeps two methods only the old pipeline called (get_session, save_evaluation).