This repository was archived by the owner on Oct 19, 2026. It is now read-only.
Repository navigation
Test pi_tools.ts through the real pi; run the tests in CI - #2
Merged
Merged
Conversation
tests/test_pi_tools.py drives the pinned pi with a scripted model on a local OpenAI-compatible server: the research floor, failed research not counting, pieces filtered to wanted keys, the one warning for unknown or missing keys, one final answer, and a no-research spec offering only submit_forecast. Skipped without node and pi, except in CI. .github/workflows/test.yml: pytest on Python 3.11 and 3.13 with node 22.19 (pi's floor) and `npm ci`. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
tests/test_pi_tools.py: the pinned pi 0.99.2 loadspi_tools.tsas in production, and a scripted model on a local OpenAI-compatible server makes the tool calls. Covers the research floor, failed research not counting toward it, pieces filtered to wanted keys, the single warning for unknown or missing keys, exactly one final answer, and a no-research spec that offers onlysubmit_forecast(and none of pi's built-ins). No network, no spend. Checked by breaking the floor and the failed-research count inpi_tools.ts: both fail the tests..github/workflows/test.yml: pytest on Python 3.11 and 3.13, node 22.19 (pi's engines floor),npm ci. In CI the pi tests fail instead of skipping when pi is missing.🤖 Generated with Claude Code