M4: demo planted bug, dual_run workflow, and assert script - #3
Merged
Conversation
Ship the checkout/payments planted contract break, demo dual_run workflow, assert script, and route uncompressed LLM calls via LEANCI_OPENAI_URL so Groq dual-run can complete. Co-authored-by: Cursor <cursoragent@cursor.com>
LeanCI ReviewFindings
Cost Receipt
Expanded 5 files (0 beyond diff), 2336 bytes. Assumptions: pricing_version=2026-07-30; model=llama-3.1-8b-instant rates: input $0.05/1M, output $0.08/1M (as_of 2026-07-31); Primary token counts use Paritok /stats domain (content Paritok intervenes in; may exclude unaffected system prompt tokens); Uncompressed dual-run column uses provider usage when available; otherwise estimates from pre-compression token counts; compression near-ineffective — show measured reduction 0.0% only; do not market a fixed headline savings rate Metrics artifact: |
Scope demo reviews with LEANCI_PATH_PREFIX, recover from tool_use_failed in the agent loop, and match planted markers in rationale/file text. Co-authored-by: Cursor <cursoragent@cursor.com>
Filter expansion to LEANCI_PATH_PREFIX, preload small demo seeds into the prompt, and switch the demo workflow to llama-3.1-8b-instant. Co-authored-by: Cursor <cursoragent@cursor.com>
Ship Apache-2.0, a full project README, ≤3 min video script, Devpost field draft, media placeholders, and a release checklist—no engine changes. Co-authored-by: Cursor <cursoragent@cursor.com>
CodewithJha
added a commit
that referenced
this pull request
Jul 31, 2026
M4: demo planted bug, dual_run workflow, and assert script
CodewithJha
pushed a commit
that referenced
this pull request
Jul 31, 2026
Architecture, PR comment, receipt GIF, and Actions visuals use PR #3 metrics so the submission assets match measured demo output. Co-authored-by: Cursor <cursoragent@cursor.com>
CodewithJha
pushed a commit
that referenced
this pull request
Jul 31, 2026
Architecture, PR comment, receipt GIF, and Actions visuals use PR #3 metrics so the submission assets match measured demo output.
CodewithJha
added a commit
that referenced
this pull request
Aug 1, 2026
M4: demo planted bug, dual_run workflow, and assert script
CodewithJha
pushed a commit
that referenced
this pull request
Aug 1, 2026
Architecture, PR comment, receipt GIF, and Actions visuals use PR #3 metrics so the submission assets match measured demo output.
CodewithJha
added a commit
that referenced
this pull request
Aug 1, 2026
M4: demo planted bug, dual_run workflow, and assert script
CodewithJha
added a commit
that referenced
this pull request
Aug 1, 2026
Architecture, PR comment, receipt GIF, and Actions visuals use PR #3 metrics so the submission assets match measured demo output.
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
1 participant
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.
Summary
demo/checkout/payments service with plantedvalidate_chargetuple/bool contract break and a weak happy-path test.demo-leanci.ymldual_run workflow (consumerleanci.ymlunchanged) plusassert_planted_bug.pygate.LEANCI_OPENAI_URLso Groq baseline matches the compressed upstream.Test plan
test_assert_planted_bug.pyMade with Cursor