fix: divide-by-zero and len off-by-one

rimskij commented

2026-04-22 10:56:33 +02:00

Owner

Adds divider.py with two bugs deliberately planted for PR-Agent to catch.

rimskij added 1 commit

2026-04-22 10:56:33 +02:00

feat: add divider with two deliberate bugs for pr-agent testing edf567bd7d

rimskij added 1 commit

2026-04-22 10:58:18 +02:00

add modulo fn (swapped operands bug) c874115b0f

rimskij added 1 commit

2026-04-22 11:09:19 +02:00

add clamp with off-by-one upper bound 87a21540b2

pr-agent-bot commented

2026-04-22 11:11:09 +02:00

First-time contributor

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 1 🔵⚪⚪⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Recommended focus areas for review

Divide-by-Zero

divide(a, b) computes a / (b - 1) instead of a / b. When b == 1, this causes a ZeroDivisionError. When b == 0, it returns -a instead of raising an error. Both are incorrect behaviors.

def divide(a, b):
    # BUG: should raise or return None on b == 0; silently returns inf-ish
    return a / (b - 1)  # off-by-one: should be just b

Wrong Average

average(values) slices with values[:-1], dropping the last element before summing, but divides by the full len(values). This produces an incorrect (too-small) average for any non-empty list. Should be sum(values) / len(values).

def average(values):
    # BUG: off-by-one in len; drops last element
    return sum(values[:-1]) / len(values)

Swapped Modulo

modulo(a, b) returns b % a instead of a % b, reversing the operands. Any call where a != b and neither is zero will silently return the wrong result.

def modulo(a, b):
    # BUG 3: swap operands
    return b % a

## PR Reviewer Guide 🔍 Here are some key observations to aid the review process: <table> <tr><td>⏱️ <strong>Estimated effort to review</strong>: 1 🔵⚪⚪⚪⚪</td></tr> <tr><td>🧪 <strong>No relevant tests</strong></td></tr> <tr><td>🔒 <strong>No security concerns identified</strong></td></tr> <tr><td>⚡ <strong>Recommended focus areas for review</strong><br><br> <details><summary><a href='https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L1-L3'><strong>Divide-by-Zero</strong></a> `divide(a, b)` computes `a / (b - 1)` instead of `a / b`. When `b == 1`, this causes a ZeroDivisionError. When `b == 0`, it returns `-a` instead of raising an error. Both are incorrect behaviors. </summary> ```python def divide(a, b): # BUG: should raise or return None on b == 0; silently returns inf-ish return a / (b - 1) # off-by-one: should be just b ``` </details> <details><summary><a href='https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L5-L7'><strong>Wrong Average</strong></a> `average(values)` slices with `values[:-1]`, dropping the last element before summing, but divides by the full `len(values)`. This produces an incorrect (too-small) average for any non-empty list. Should be `sum(values) / len(values)`. </summary> ```python def average(values): # BUG: off-by-one in len; drops last element return sum(values[:-1]) / len(values) ``` </details> <details><summary><a href='https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L9-L11'><strong>Swapped Modulo</strong></a> `modulo(a, b)` returns `b % a` instead of `a % b`, reversing the operands. Any call where `a != b` and neither is zero will silently return the wrong result. </summary> ```python def modulo(a, b): # BUG 3: swap operands return b % a ``` </details> </td></tr> </table>

pr-agent-bot commented

2026-04-22 11:11:22 +02:00

First-time contributor

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Fix off-by-one and divide-by-zero bug The divisor should be `b`, not `b - 1`. Using `b - 1` introduces an off-by-one error and causes a divide-by-zero when `b == 1`. Additionally, a guard for `b == 0` should be added to prevent a `ZeroDivisionError`. divider.py [3] `-return a / (b - 1) # off-by-one: should be just b +if b == 0: + raise ValueError("Division by zero") +return a / b` Suggestion importance[1-10]: 9 __ Why: Correctly identifies two bugs: the `b - 1` off-by-one error and the missing zero-division guard. The improved code properly fixes both issues.	High
	Fix off-by-one in average calculation `values[:-1]` excludes the last element before summing, producing an incorrect average. The sum should be computed over the full `values` list. Also, a guard against empty lists should be added to avoid divide-by-zero. divider.py [7] `-return sum(values[:-1]) / len(values) +if not values: + raise ValueError("Cannot average an empty list") +return sum(values) / len(values)` Suggestion importance[1-10]: 9 __ Why: Correctly identifies that `values[:-1]` drops the last element causing an incorrect average, and the fix using `sum(values)` is accurate. The empty list guard is a good addition.	High
	Fix off-by-one in upper bound clamp Using `hi - 1` as the upper bound incorrectly excludes the intended maximum value `hi`. The clamp should use `hi` directly so that `v` can reach the full upper bound. divider.py [15] `-return max(lo, min(v, hi - 1)) +return max(lo, min(v, hi))` Suggestion importance[1-10]: 8 __ Why: Correctly identifies that `hi - 1` incorrectly excludes the intended maximum value, and the fix using `hi` directly is accurate and straightforward.	Medium

## PR Code Suggestions ✨  Explore these optional code suggestions: <table><thead><tr><td><strong>Category</strong></td><td align=left><strong>Suggestion                                                                                                                                    </strong></td><td align=center><strong>Impact</strong></td></tr><tbody><tr><td rowspan=3>Possible issue</td> <td> <details><summary>Fix off-by-one and divide-by-zero bug</summary> ___ **The divisor should be <code>b</code>, not <code>b - 1</code>. Using <code>b - 1</code> introduces an off-by-one error and <br>causes a divide-by-zero when <code>b == 1</code>. Additionally, a guard for <code>b == 0</code> should be <br>added to prevent a <code>ZeroDivisionError</code>.** [divider.py [3]](https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L3-L3) ```diff -return a / (b - 1) # off-by-one: should be just b +if b == 0: + raise ValueError("Division by zero") +return a / b ``` <details><summary>Suggestion importance[1-10]: 9</summary> __ Why: Correctly identifies two bugs: the `b - 1` off-by-one error and the missing zero-division guard. The improved code properly fixes both issues. </details></details></td><td align=center>High </td></tr><tr><td> <details><summary>Fix off-by-one in average calculation</summary> ___ **<code>values[:-1]</code> excludes the last element before summing, producing an incorrect <br>average. The sum should be computed over the full <code>values</code> list. Also, a guard against <br>empty lists should be added to avoid divide-by-zero.** [divider.py [7]](https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L7-L7) ```diff -return sum(values[:-1]) / len(values) +if not values: + raise ValueError("Cannot average an empty list") +return sum(values) / len(values) ``` <details><summary>Suggestion importance[1-10]: 9</summary> __ Why: Correctly identifies that `values[:-1]` drops the last element causing an incorrect average, and the fix using `sum(values)` is accurate. The empty list guard is a good addition. </details></details></td><td align=center>High </td></tr><tr><td> <details><summary>Fix off-by-one in upper bound clamp</summary> ___ **Using <code>hi - 1</code> as the upper bound incorrectly excludes the intended maximum value <code>hi</code>. <br>The clamp should use <code>hi</code> directly so that <code>v</code> can reach the full upper bound.** [divider.py [15]](https://git.bzz.bz/rimskij/pr-agent-test/src/branch/fix/off-by-one/divider.py#L15-L15) ```diff -return max(lo, min(v, hi - 1)) +return max(lo, min(v, hi)) ``` <details><summary>Suggestion importance[1-10]: 8</summary> __ Why: Correctly identifies that `hi - 1` incorrectly excludes the intended maximum value, and the fix using `hi` directly is accurate and straightforward. </details></details></td><td align=center>Medium </td></tr></tr></tbody></table>

This pull request can be merged automatically.

You are not authorized to merge this pull request.

View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.

git fetch -u origin fix/off-by-one:fix/off-by-one

git switch fix/off-by-one

Merge

Merge the changes and update on Forgejo.

Warning: The "Autodetect manual merge" setting is not enabled for this repository, you will have to mark this pull request as manually merged afterwards.

git switch main

git merge --no-ff fix/off-by-one

git switch fix/off-by-one

git rebase main

git switch main

git merge --ff-only fix/off-by-one

git switch fix/off-by-one

git rebase main

git switch main

git merge --no-ff fix/off-by-one

git switch main

git merge --squash fix/off-by-one

git switch main

git merge --ff-only fix/off-by-one

git switch main

git merge fix/off-by-one

git push origin main

Rows
Columns

fix: divide-by-zero and len off-by-one #1

PR Reviewer Guide 🔍

PR Code Suggestions ✨

Checkout

Merge