Show HN: Farol – A risk map of a pull request for the person who approves it (github.com)
60 points by ericholiveira 27 days ago | 43 comments



munro 27 days ago | flag as AI [–]

IDK lot of noise in report, I need more signal to noise ratio, already reading so much AI output as it is.

But the example PR... It said code generate with Claude, is it really still this bad? Last I was using SQLAlchemy with Claude was Opus 4.5, and it took some heavy coaching and skill gen not to generate code like this--but why even use SQLAlchemy at all if you're just going to use string interpolation jeez

https://github.com/erich-oliveira-winnin/full-stack-fastapi-...

    owner = "" if current_user.is_superuser else f"WHERE owner_id = '{current_user.id}'"
    query = f"SELECT status, count(*) FROM item {owner} GROUP BY status"
    rows = session.execute(text(query)).all()
Part of me thinks maybe because it's not popular or well documented, but SQLAlchemy has an eDSL of SQL, so you can skip the whole ORM/table mapping layer, and just use it to programmatically construct SQL syntax

> SQLAlchemy has an eDSL of SQL, so you can skip the whole ORM/table mapping layer, and just use it to programmatically construct SQL syntax

Yes, this is called SQLAlchemy Core: http://docs.sqlalchemy.org/en/latest/core/

You can also just use psycopg (the Postgres driver layer) directly, it’s surprisingly ergonomic in my (limited) experience.

nico 27 days ago | flag as AI [–]

> It said code generate with Claude, is it really still this bad?

Anecdata, datapoint of 1 personal experience: I had been using Opus 4.6 with no problems until yesterday, then it seemed like it was missing things constantly, introducing random bugs, forgetting basic stuff that was in its memory and skills and should never miss

Same thing happened on 2 separate sessions I had with Opus 4.6

Ended up switching to 5.5 and Fable, things improved instantly

This left me with a weird taste

lurkshark 27 days ago | flag as AI [–]

Out of curiosity, was this on a codebase where other folks started using Opus 5.5? I’ve been curious if each generation of model has its own biases that make it generate output that’s more difficult for other models/previous models to work with. That’s been my personal suspicion when I’ve hit situations like yours

That’s my favorite part of sqlalchemy. I don’t even use the orm anymore.
nina71 27 days ago | flag as AI [–]

Nitpick: you're probably using Core, the expression language, and the ORM is just a layer on top of it. So you still lean on the same machinery. IIRC 2.0 made `select()` work the same in both, which makes dropping the ORM even easier.
messia 27 days ago | flag as AI [–]

it's hard for me to imagine something made with so little taste can be any good...

Thank you for the feedback, ive just updated the UI... would love to hear if you feel it improved it
timcobb 27 days ago | flag as AI [–]

This looks nice, but I would use it with caution.

There was a post here recently, "Using LLM for confidence scoring is a bad idea", my mind went immediately to using LLMs for scoring risk. Seems like a bad idea. If there's anything we still need a human for, it's assessing risk.


It dont uses LLM to give score.. the score is based on static analysis only, based on some criterias: - Dependency graph of the code (the more is central on the graph, the riskier is the change) - If it have any obvious flaws (security, lint, breaking API Changes) - Test coverage of diff lines
pixl97 27 days ago | flag as AI [–]

>we still need a human for

A trained human mind that is.

Your average human in any given topic will give confidently incorrect risk assessments just like an LLM.

cowlevel 27 days ago | flag as AI [–]

Good idea. Do you take bribes to exclude certain lines from the risk map? Asking for my good friend Jia Tan.
b473a 27 days ago | flag as AI [–]

What, are you doubting in the integrity of the large language binary blob?

>> Claude Code lives in its own repository, separate from the monorepo

I thought mono meant one.

Zambyte 27 days ago | flag as AI [–]

If there couldn't be multiple monorepos, there would be no such thing as a monorepo.
dboreham 27 days ago | flag as AI [–]

Well there's one at Google, one at Facebook...

Monorepo -> microservices -> monoreposervices
hbcdbff 27 days ago | flag as AI [–]

Birepo

An engineer where I work built something like this so that when QA is about to deploy, they have a better indication of who to call and what is potentially going to be impacted. Our implementation is done prior to production deploy (which requires human approval) and compares currrebt deployed build code to new build changes diff and then analyses. I think there is a lot of room for tools like this in the future. Scoping/homing/etc

I do agree those kinds of tools are needed... great to know youve been working on something similar
fcarraldo 27 days ago | flag as AI [–]

I think tools like this are needed and will become standard in the near future.

However, the backend demo report seems longer and more complex than just reading the code. I’m trying to build something similar as well, and no one has quite nailed this yet.

The risk map / assisted review needs to be succinct and information dense, to guide your attention. My current philosophy is that we need to be annotating code, not replacing the entire code review interface with a bunch of text.


Ive taken your feedback in consideration, and recreated UX/UI for the artifact, would love to hear your feedback on it

Thanks... it surely is possible to try to reduce the amount of information
alsiola 27 days ago | flag as AI [–]

Looked at the backend demo, and the first lines suggested to look at were importing things. Exactly what I really don't need to be reviewing

It suggested based on the files most used (through graph dependency), for this reason it appears as a important file (as if it breaks, it can break several places in your codebase), but that being said, you can add some files to be ignored (if you have special files, like consts or i18n)
pebble82 27 days ago | flag as AI [–]

Even if the graph reasoning is sound, first impression is what counts. We tried a similar risk-scoring thing internally, and the moment reviewers saw a trivial file ranked first, they stopped opening it. I'd filter out import-only changes entirely, or at least rank by actual logic changed.

Heard your feedback on improving UX/UI for the final artifact and just updated it... Thank you all, and would love to hear more feedbacks
hbcdbff 27 days ago | flag as AI [–]

I want off this train. Please, make it stop…

why is the only comment by the OP flagged and dead? Is it because they were supposed to include that data in the description text rather than a comment, was it flagged as AI generated, or..?

Trying to understand why the poster's own comment was flagged and killed but the original article remains up.

BalinKing 27 days ago | flag as AI [–]

AI-edited or -generated comments are disallowed by HN guidelines: https://news.ycombinator.com/newsguidelines.html#generated. I don't think any such restriction exists for submissions themselves, so that's my guess as to why the comment but not the submission has been flagged to death.
lucid76 27 days ago | flag as AI [–]

Enforcement is just users flagging, so it's whoever notices first. Nobody scrutinizes a repo link the way they read a wall of text. Not a rule applied evenly, just what got caught. Same as any queue nobody's watching.
nico 27 days ago | flag as AI [–]

No restriction for the submission itself, unless it’s something like an Ask/Tell/Show HN, in which the content goes directly on the post (and will get flagged if AI-generated/assisted)

You can vouch for it, if you view the comment by clicking the time since posted a “vouch” option appears. I did it. I’ve noticed this happening more and more on here for show HN posts especially. I’m not sure if it’s like some sort of troll gang or what…
nico 27 days ago | flag as AI [–]

In my personal experience, it’s very rare to catch a comment/story while vouchable. Not sure how many flags does it take for something to be killed, but it seems like almost as soon as something gets flagged, it becomes a signal for others to flag it too immediately without thought (similar thing kinda happens too when you post a comment and the first vote is a downvote, it almost never recovers, even if it was a good comment, as the initial drop/greying biases anyone that sees it before they even read it)
tomhow 27 days ago | flag as AI [–]

It was classified by our software as genai, which is explicitly against the guidelines: https://news.ycombinator.com/newsguidelines.html#genai
shiandow 27 days ago | flag as AI [–]

I'm not sure either. The comments don't look wrong to me.
cpan22 27 days ago | flag as AI [–]

this is very needed - I don't think we'll see a world where agents approve all our PRs but there can definitely be better tooling for focusing human attention during review

Thank you... good to know youre sensing the same problem
mark 27 days ago | flag as AI [–]

Has anyone measured whether this actually catches more bugs? My worry is reviewers treat the low-risk regions as skippable, and the nasty bug is usually in the boring-looking config change or rename that the map scored green. Focusing attention also means un-focusing it somewhere.
sikozu 27 days ago | flag as AI [–]

I like the concept, a risk map could be useful in some circumstances but I absolutely hate the UI design; it reeks of AI with no human thought or care put into it.

Thats is surely true... i did it with AI and i do lack design skills

Or you could, you know, read the changes your approving
y42 27 days ago | flag as AI [–]

Sire, wouldst thou perchance elaborate upon this ancient, forgotten technique, long buried in the mists of antiquity and shrouded in mysterious lore?
esafak 27 days ago | flag as AI [–]

Assuming it works this could focus your attention.

Hi HN, I built farol at Winnin, where we open-sourced it (MIT).

AI agents now write a lot of our code, and AI reviewers catch a lot of the line-level problems. But someone still has to press "merge", and that person has the same question every time: how risky is this, and where should I spend my attention? A 40-file PR where 38 files are isolated is very different from a 3-file PR that changes a model used by 23 endpoints.

farol is a CLI (and a GitHub Action) that answers that statically:

- classifies the PR (global / touches-existing / isolated / unknown) and gives a 0-100 merge risk score - ranks the files by risk and says why: what each one reaches (routes, endpoints, jobs), contract breaks in API responses, dependency changes, security patterns - diff coverage from your existing coverage report, so "38% of the changed lines are tested" sits next to the risky files - an HTML report where you mark files as reviewed and the score and test plan follow; incremental mode for "what changed since my last review"; suggested reviewers from git blame

How: it uses the TypeScript compiler API for TS/React (React Router, Next.js, TanStack Router) and TS backends, a small go/types helper for Go, and Python's ast for FastAPI/Flask/Django and friends. No LLM, no network during analysis, and it never executes the analyzed repo's code. It's deterministic and informs only; it never blocks a merge.

Live demo (two reports from a real PR, nothing to install): https://winnin.github.io/farol/demo/

Try it on a branch: npx @winninjs/farol --help

Limitations: only TS, Go and Python for now, and the reachability is static, so dynamic dispatch and reflection make it fail closed ("unknown") rather than guess. I'd love feedback on the risk score and on false positives in your codebase.