Fix/spelling in data science/prompt.py - #6
Closed
prasannakotyal wants to merge 3 commits into
Closed
Conversation
…_instructions_root()](e.g. 'ANLAYZIE' → 'ANALYZE')
…_instructions_root()](e.g. 'ANLAYZIE' → 'ANALYZE')
Collaborator
|
Hi Prasanna, Thanks a lot for contributing to our repo. I reviewed your files and you are correct with the changes however since they are a part of the agent's prompt I would decline this PR because of the possible (untested) implications of correcting this change to the quality of the agent. |
Author
|
Hi, Thanks for the response. Yes, I agree the "changing without tests" makes sense. I would be careful though, as incorrect spellings in agents' prompts might lead to ambiguity and maybe cause problems. |
happyhuman
added a commit
that referenced
this pull request
Jul 14, 2026
…python-recipe Pipeline now ends with a lightweight `python -m py_compile` check against the runnability test file generated in Phase 6. Purpose: catch generator bugs (invalid Python emitted by the runnability-test skill) and gross syntax errors in a hand-edited test file — without executing the test or requiring `.env` / GCP credentials. Deliberately weaker than `uv run pytest`: - Does NOT execute the test function. - Does NOT resolve imports. - Does NOT need `.env` populated (which would be a scope-creep dependency and would make the pipeline fail spuriously on developer machines that haven't set up the env). Failure semantics: - Exit 0 → PASS. Progress line reports OK. - Exit non-zero → FAIL. Print stderr verbatim in the summary as a Manual TODO. Do NOT diagnose, retry, or auto-fix. Do NOT block the summary from being printed. - File missing (Phase 6 skipped generation) → SKIP. Rationale: closes the "unverified pipeline" gap I flagged in the retest retrospective (friction #6) without introducing the ambiguity of running full pytest (real recipe bug vs. env-var-not-set vs. no creds vs. network flake — the master can't reliably distinguish). py_compile catches the one class of failure it CAN reliably attribute (the generator emitted invalid Python), and delegates everything heavier to the user's manual `uv run pytest` step listed under "Next steps." Ordering: Phase 5 (recipe `uv sync`) already runs before Phase 6 (test generation), so dependencies are installed in the recipe venv before the test file exists. No reordering needed — just append Phase 7.
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.
Title: Fix typos in : adk-samples/agents/data-science/data_science/prompts.py
Description:
This PR corrects several spelling mistakes in the instruction_prompt_root_v2,v1,v0 string, such as "ANLAYZIE" → "ANALYZE", "REPOSNE" → "RESPONSE", and "PREVIOU" → "PREVIOUS", to improve clarity and reduce ambiguity for downstream tools and users.