标签：#Debugging

By BDubs · AI Rook Trading Engine My trading engine has a feature called "FVG anchoring." When a trade moves in your favor, the engine looks for a Fair Value Gap (a structural support/resistance zone from price action theory) and anchors the stop-loss just beyond it. This widens the stop from a tight breakeven level to a structurally meaningful one — giving the trade room to breathe while still protecting capital. It worked great for long trades. For short trades, it did the exact opposite: it placed the stop-loss below the entry price. A stop below your entry on a short means the trade can lose money before the stop even triggers. Three separate bugs, all in the same code path, all caused by the same mistake: the short-trade logic was written as if it were a long trade. The Context The Rook Engine manages trade exits in phases. Phase 1 is the initial breakeven guard. Phase 2 tries to anchor the stop to a reverse FVG. Phase 3 switches to trailing. The FVG anchoring code lives across two files: fvg-detector.js (finds the FVG) and exit-manager.js (uses it to set the stop). The bugs only manifested on short trades because the engine had been primarily backtested and paper-traded on longs. The short path was never properly validated until a live S10 short entry at $75,359 got its stop anchored to $75,354 — five points below entry. The trade was stopped out immediately. Bug 1: Wrong FVG Type for Shorts The findReverseFVG() function finds the nearest structural zone to anchor the stop. For longs, you want a bearish FVG above price (resistance). For shorts, you want… also a bearish FVG above price (resistance). The code was finding a bullish FVG below price instead: // BEFORE — finds bullish FVG below price (wrong for shorts!) const candidates = active . filter ( f => f . type === ' bullish ' && f . top < currentPrice ) . sort (( a , b ) => b . top - a . top ); A bullish FVG below price is a support zone. Placing a stop just above support when you're short is like placing

Back in July my scheduled DEV.to publishing run failed at the very first step — the quota check couldn't reach dev.to:443 at all. Diagnosing it took manually running curl $HTTPS_PROXY/__agentproxy/status from inside the session and reading a proxy diagnostic by hand, because nothing in my own code had written down what actually happened. Not which host, not which of my two HTTP helper functions made the call, not a timestamp, nothing. The failure was real and the fix (get dev.to added to the environment's egress allowlist) was correct, but I found it by treating my own server as a black box and probing it from outside, which is exactly backwards for code I wrote myself. eight tools, one shared blind spot server.py is an 8-tool FastMCP server: three GitHub tools, four DEV.to tools, one that shells out to claude -p . Every HTTP-calling tool routes through one of two helpers: def _gh ( path , method = " GET " , data = None ): req = urllib . request . Request ( f " https://api.github.com { path } " , method = method ) req . add_header ( " Authorization " , f " token { os . environ [ ' GITHUB_TOKEN ' ] } " ) req . add_header ( " Accept " , " application/vnd.github.v3+json " ) if data : req . add_header ( " Content-Type " , " application/json " ) req . data = json . dumps ( data ). encode () with urllib . request . urlopen ( req ) as r : return json . loads ( r . read ()) def _dev ( path , method = " GET " , data = None ): req = urllib . request . Request ( f " https://dev.to/api { path } " , method = method ) req . add_header ( " api-key " , os . environ [ " DEV_TO_API " ]) req . add_header ( " Content-Type " , " application/json " ) req . add_header ( " User-Agent " , " developer-presence-mcp/1.0 " ) if data : req . data = json . dumps ( data ). encode () with urllib . request . urlopen ( req ) as r : return json . loads ( r . read ()) Neither one logs anything. When urlopen raises, the caller — whichever @mcp.tool() function invoked it — sees a bare urllib.error.HTTPEr

Originally published on the MyTreda engineering blog: read here A support message described what looked like one confusing mobile bug. It turned out to be two independent ones — a cross-site cookie getting blocked by Safari's ITP, and a React Hook Form autofill desync — that just happened to both only show up on mobile. Full breakdown, code, and fixes below.

버그를 발견한 순간, 텍스트로 상황을 설명하려다 시간을 낭비한 경험이 있을 것이다. PromptShot의 그리기 기능과 단축키(Alt+Shift+S)를 쓰면, 브라우저에서 발견한 버그의 상태와 재현 경로를 캡처·주석·프롬프트 복사까지 한 흐름으로 처리할 수 있다. 텍스트만으로 버그 상황을 기술할 때 생기는 문제 버그를 텍스트로 설명하는 일은 생각보다 까다롭다. "오른쪽 상단 버튼을 누르면 모달이 이상하게 뜬다"는 문장을 받은 개발자는 어떤 버튼인지, 어떻게 이상한지 확인하기 위해 다시 질문해야 한다. 그 왕복이 쌓이면 간단한 버그 하나에도 맥락 공유만 수십 분이 걸린다. 특히 Cursor나 Claude 같은 AI 코딩 도구에 버그를 설명할 때, 텍스트만 붙여 넣으면 도구가 UI 상태를 추측해야 한다. 추측이 틀리면 엉뚱한 수정 코드가 나온다. 결국 개발자가 다시 맥락을 보완하는 루프가 반복된다. 문제는 두 가지다. 위치 : 텍스트로는 "어디에 있는 요소인지"를 정확히 전달하기 어렵다. 상태 : 에러 메시지, 깨진 레이아웃, 빈 영역 등 시각적 상태는 캡처 없이 설명하면 정보가 줄어든다. 그리기 도구로 화면에 직접 표시하고, 그 이미지와 함께 프롬프트를 LLM에 붙여 넣는 방식이 이 문제를 해결하는 가장 빠른 경로다. PromptShot 그리기 도구로 버그 위치를 어떻게 표시할까? PromptShot의 그리기 도구는 캡처 직후 바로 활성화된다. 별도 이미지 편집기를 열 필요가 없다. 영역을 드래그해 캡처하면 편집 패널이 열리고, 여기서 선택할 수 있는 도구는 다음과 같다. 도구 용도 버그 리포트에서 쓰는 방식 펜(자유 드로잉) 특정 영역에 자유롭게 표시 깨진 텍스트나 이미지 경계에 동그라미 형광펜 반투명 강조 에러 메시지 텍스트 강조 화살표 방향 지시 "이 버튼을 누른 뒤 저 팝업이 열림" 순서 표시 텍스트 짧은 주석 "여기서 클릭 → 404" 같은 재현 경로 메모 예를 들어, 가상의 시나리오를 생각해 보자. 결제 플로에서 "다음" 버튼이 특정 해상도에서 잘리는 버그를 발견했다고 가정하면, 화살표로 버튼 위치를 가리키고 텍스트 도구로 "1280px에서 clip 발생"이라고 짧게 메모한다. 이 이미지 하나가 세 문단짜리 텍스트 설명보다 정확하다. 캡처 범위는 전체 화면이 아니라 문제가 발생한 컴포넌트 영역만 잘라도 된다. 오히려 범위를 좁히면 LLM이 어디에 집중해야 하는지 명확해진다. 클립보드 즉시 복사로 버그 리포트 프롬프트를 작성하는 방법 주석 작업이 끝나면 Alt+1 또는 Alt+2로 복사 대상을 선택한다. Alt+1 : PNG 이미지만 클립보드에 복사 Alt+2 : 프롬프트 텍스트 + PNG 이미지를 함께 클립보드에 복사 버그 리포트 프롬프트를 만들 때는 Alt+2를 쓴다. 복사된 내용을 Cursor, Claude, ChatGPT에 그대로 붙여 넣으면 이미지와 텍스트 맥락이 동시에 전달된다. 프롬프트 텍스트 부분에는 캡처한 URL, 브라우저 정보, 캡처 시각이 자동으로 포함된다. 여기에 직접 한 줄을 추가해 재현 조건을 붙이면 완성도 높은 버그 리포트 프롬프트가 된다. 실제로 AI 코딩 도구에 붙여 넣는 프롬프트 구조는 이런 형태다. [캡처 이미지 첨부됨] URL: /checkout 재현 환경: Chrome 124, 1280×800 재현 단계: 1. 장바구니에서 '결제하기' 클릭 2. 배송 정보 입력 후 '다음' 클릭 3. 위 이미지처럼 버튼이 뷰포트 밖으로 잘림 예상 동작: 버튼 전체가 화면 안에 표시됨 실제 동작: 버튼 오른쪽 일부가 잘려 클릭 불가 위 이미지와 재현 단계를 기반으로 원인을 분석하고 수정 방향을 제안해 주세요. 이 구조를 매번 타이핑하지 않아도 된다. PromptShot에서 프롬프트 템플릿을 저장해 두면, 다음 버그부터는 캡처 → 주석 → 붙여넣기 세 단계로 끝난다. Alt+Shift+S로 이슈 트래킹을 어떻게 빠르게 처리할까? Alt+Shift+S는 PromptShot의 전역 캡처 단축키다. 브라우저 외 어떤 창에서도 작동하며, 누르는 순간 드래그 선택 모드로 바로 진입한다. 이슈 트래킹

A few weeks back I picked up google-gemini/gemini-cli issue #28090: the shell tool was forwarding a command's entire stdout/stderr straight into the model's context, with no cap unless you opted into an LLM-based summarization step. Run one noisy build command and you'd hand the model tens of thousands of tokens of log spam it never asked for. The fix sounded trivial: cap the output before it goes into llmContent . I had a one-liner in my head before I'd even opened the file. That one-liner is exactly the kind of "obviously correct" fix that ships bugs. The one-liner The naive version looks like this: const MAX = 32 * 1024 ; // 32 KiB function truncate ( output ) { if ( output . length <= MAX ) return output ; return output . slice ( 0 , MAX ) + ' \n ...[truncated]... \n ' + output . slice ( - MAX ); } It compiles. It passes a quick manual test with a big ASCII log file. It looks done. I almost committed it as-is before writing the actual test suite. The problem is what .slice() is slicing. JavaScript strings are sequences of UTF-16 code units, not bytes and not Unicode codepoints. Most characters in typical shell output (letters, digits, punctuation) are one code unit each, so .slice() looks safe in casual testing. But the moment real-world command output contains anything outside the Basic Multilingual Plane — an emoji in a commit message, certain box-drawing/progress-bar characters some CLIs use, non-Latin filenames — that character is represented as a surrogate pair : two 16-bit code units that only mean something together. Slice between them and you don't get an error. You get one dangling unpaired surrogate on each side of the cut, silently baked into the string that gets sent to the model. No exception. No lint warning. JSON.stringify on the payload can even throw later, in a completely unrelated part of the request pipeline, for a reason that has nothing to do with where the bug actually is. Or worse: it doesn't throw, and the model just receives a slightly

I run a scheduled agent that writes and publishes DEV.to articles twice a day. Step 5 of its instructions has always said the same thing: write the log entry, commit the drafts, push. I've read that line a dozen times without questioning it. This morning I actually checked what "commit the drafts" had been doing for the last month, across more than thirty published articles. The answer: nothing. Not once. the check that should have happened on day one The task instructions reference source files like drafts/scheduled-agent-shared-quota-no-memory.md and drafts/one-env-key-two-usernames.md in every log entry — real filenames, written by the agent, presumably sitting in the repo as a record of what was drafted before it got published. I went looking for one of them: $ git log --all -- drafts/ $ # (nothing) Empty. Not "one commit, then deleted later" — completely absent from git history since the very first commit in this repo. Every single run that logged "committed drafts + the log" had, in fact, only ever committed the log. why git let this happen silently .gitignore in this repo has listed drafts/ since the initial commit: . env __ pycache__ / *. pyc codes / drafts / . omc / . claude / CLAUDE . md That line predates the scheduled publishing task entirely — it was almost certainly written back when drafts were just scratch files someone edited by hand before a publish script existed. Nobody revisited it when the publishing task's instructions later started saying "commit the drafts." The instruction and the ignore rule have been quietly contradicting each other since before either was written by the same person in the same sitting. Here's what actually happens when a script (or an agent) runs git add drafts/whatever.md in this repo: $ git add drafts/gitignore-ate-my-drafts-folder.md The following paths are ignored by one of your .gitignore files: drafts hint: Use -f if you really want to add them. hint: Turn this message off by running hint: "git config advice.addIgn

This is a submission for DEV's Summer Bug Smash: Clear the Lineup . Project Overview Typst is the Rust-based markup typesetting system that's been quietly eating LaTeX's lunch for the last couple of years — you write plain-text markup, Typst compiles it to PDF (or HTML) with a real incremental compiler underneath instead of a multi-pass macro soup. Part of what makes it pleasant is that it exposes its own evaluator to itself: a document can call #eval("some typst code") and get back whatever that code produces, at runtime, inside the document being compiled. It's a small feature, but it opens up a surprisingly deep rabbit hole, which is exactly where this bug was hiding. Bug Fix or Performance Improvement The problem: typst/typst#8632 reports that Typst crashes instead of erroring when #eval is used to recursively re-import the file it's running in. The repro is one line. Save this as overflow.typ : #eval("import \"overflow.typ\"") Then: $ ./target/debug/typst compile overflow.typ overflow.pdf thread 'main' (750833) has overflowed its stack fatal runtime error: stack overflow, aborting No PDF, no diagnostic, no exit code you can act on — just a native stack overflow and a SIGABRT. Typst has had cyclic-import detection since forever; a normal top-level import "overflow.typ" inside itself gets caught cleanly with an error: cyclic import message. Something about routing the import through #eval specifically was bypassing that check. The hunt I'll be upfront about how this investigation actually went: I worked through it with Claude (Anthropic's coding agent) rather than solo. The triage pass it did before I sat down with the code had already narrowed the search to one function — eval_string in crates/typst-eval/src/lib.rs — and named the suspect line. That's a big head start, but a named suspect isn't a confirmed root cause, so the actual work was reading that function next to its sibling, the file-level eval() a few lines above it, and checking the claim against the s

I wrote a cleanup routine that matched processes by command line with a wildcard pattern. It reported success on every run. It had never matched anything — the path separators in the pattern were escaped in a way the matcher read as literal doubles, so the filter was structurally incapable of hitting. I only caught it because I counted the survivors afterward and seven of them were still there. The fix was switching from a wildcard match to a plain substring containment check with no escape semantics at all. A filter that cannot fail loudly will lie to you politely forever. Before trusting any matcher, feed it a known-positive and watch it fire — a green result from an instrument you never saw go red is noise. What's the equivalent lesson your worst bug taught you?

Most LLM failures are easy to describe and surprisingly hard to reproduce. A user reports that the model returned an empty answer. A tool call disappeared halfway through a stream. One provider rejected a request that worked everywhere else. Then I open the logs and find something like this: LLM request failed: 400 Bad Request Technically true. Operationally useless. The missing piece is usually the exact request shape: model, parameters, message roles, tool definitions, timeout behavior, and the raw provider response. I wanted something smaller than a full observability platform, so I built a request recorder around fetch . It stores enough information to inspect or replay a failed call without logging the API key. What the recorder captures For each request, I want: a unique request ID timestamp and duration URL and model sanitized request body HTTP status raw response body network or timeout errors I deliberately do not record the Authorization header. Prompt content is also redacted by default. Full payload capture must be enabled explicitly because storing production prompts can create a much worse problem than the bug being investigated. The recorder This example runs on Node.js 18 or newer and has no external dependencies. Create recorded-fetch.mjs : import { randomUUID } from " node:crypto " ; import { mkdir , writeFile } from " node:fs/promises " ; import path from " node:path " ; function sanitize ( value , captureContent ) { if ( Array . isArray ( value )) { return value . map (( item ) => sanitize ( item , captureContent )); } if ( ! value || typeof value !== " object " ) { return value ; } const result = {}; for ( const [ key , child ] of Object . entries ( value )) { const normalizedKey = key . toLowerCase (); if ( normalizedKey . includes ( " api_key " ) || normalizedKey . includes ( " apikey " ) || normalizedKey . includes ( " authorization " ) ) { result [ key ] = " [REDACTED] " ; continue ; } if ( ! captureContent && ( normalizedKey === " content "

I have been working on building a private, secure network accessible from anywhere. The goal was to connect my mobile phone and my local development laptop using a WireGuard VPN , hosting the central gateway on a free-tier Google Cloud Platform (GCP) e2-micro instance. I wanted to access my self-hosted services, specifically my Docker-hosted Open WebUI , running on my local home Wi-Fi connected laptop, directly from my phone using mobile data. It sounded straightforward. But if you read my other from scratch journeys, you might have already guessed, it was not. The Setup My architectural plan was a simple hub-and-spoke topology: The Hub: GCP VM ( 10.66.66.1 ) with IPv4 forwarding enabled. Spoke 1 (My Phone): 10.66.66.2 Spoke 2 (My Laptop): 10.66.66.3 I wrote my server configurations, enabled IP forwarding ( net.ipv4.ip_forward=1 ), wrote the iptables rules to allow forwarding between peers, and started the interfaces. Then came the moment of truth. I tried to bring up the tunnel. Absolute silence. No packet moving from anywhere. Hurdle 1: The Classic Cloud NAT Trap (Internal vs. Public IP) Before I could even worry about routing packets between my phone and laptop, I couldn't even get them to handshake with the GCP server. Like many of us do when working inside a VM, I had run ip addr on the GCP instance to grab its IP address for my client configurations. I set up the WireGuard peers to point to this IP. Nothing connected. The Culprit: GCP (and AWS) operates on a 1:1 NAT mapping. The virtual network interface inside your VM only sees and binds to a private, internal cloud IP (e.g., 10.128.0.x ). The public IP assigned to your instance lives outside the VM at the VPC gateway level. By putting the internal IP into my client configs, my phone and laptop were trying to connect to a private address that didn't exist on their local networks. The Fix: I had to swap the internal IP in the client configurations with the GCP Ephemeral/Static External IP . Once the handshake

Submission for DEV's Summer Bug Smash — Smash Stories track. There was a file in my repo called run_benchmark_1_22.py . Not 1 to 24, which is what the harness was written to do. Not 1 to 26, which is how many Mersenne exponents the agents know. Twenty-two. A chart in the README — a2a_latency_times_1_22.png — agreed. At some point, past-me had decided the benchmark ends at 22, committed the evidence, and moved on. This summer, hunting for a Bug Smash target, I finally asked: why 22? The setup a2a-benchmark compares A2A agent performance across four languages. Python and Go sit behind Gemini tool-calling (ADK); Node and Rust are bare HTTP handlers. Each computes Mersenne primes with Lucas–Lehmer; a harness sweeps N from 1 to 24 and draws two charts. I ran the full sweep. At N=24, the Python column printed N/A . Every other language returned data. There it was — not a decision, a crash , worked around by shortening the run until it stopped hurting. The 4,300-digit wall The Python agent's response at N=24 wasn't even subtle about it: "Exceeds the limit (4300 digits) for integer string conversion; use sys.set_int_max_str_digits() to increase the limit" CPython 3.11 added a default cap on int→str conversion — 4,300 digits — as a denial-of-service mitigation. My agent stringified every prime it found. The 24th Mersenne prime, 2^19937−1, has 6,002 digits . Here's the part that made me laugh out loud: the stringified list was never returned . The tool reports only its elapsed time. The line that had silently amputated my benchmark at N=23 was decorative. The fix was git rm energy: delete the str() , keep the raw int. Go had the identical dead weight ( val.String() ) inside its timed region — it just happened not to crash. One deleted expression, and a column of data that had never existed came into being: N=24, Python, 2,425.9 ms. It gets worse before it gets better With the agents finally running, I kept pulling the thread. The harness parsed Python's elapsed time out of th

Submission for DEV's Summer Bug Smash — Clear the Lineup track. The codebase a2a-benchmark is my multi-language A2A (Agent-to-Agent) performance suite: four agents — Python and Go behind Gemini tool-calling via ADK, Node.js and Rust as direct handlers — each compute Mersenne primes with the Lucas–Lehmer test, while a harness sweeps N=1–24 and charts calculation time and round-trip time. The committed results stopped at N=22. I never questioned that. I should have. The headline bug: a whole column of data didn't exist CPython 3.11+ limits int→str conversion to 4,300 digits by default (a DoS mitigation). My Python agent stringified each prime it found: mersenne_primes . append ( str (( 1 << p ) - 1 )) The 24th Mersenne exponent is p=19937, and 2^19937−1 has 6,002 digits . So for any request of 24+ primes, the tool raised ValueError — and the A2A response dutifully delivered the stack-trace text instead of a result: "text": "Exceeds the limit (4300 digits) for integer string conversion; use sys.set_int_max_str_digits() to increase the limit" The benchmark's Python column was structurally incapable of producing data at N≥24. The kicker: the stringified list was never used . The tool returns only elapsed_time . The fix is deleting the str() — which also removes formatting work from the timed region that the Node and Rust agents never paid (Go had the same dead val.String() call). Fix: PR #1 — plus a switch from time.time() (wall clock, non-monotonic) to time.perf_counter() , and a regression test at count=24. Before/after, N=24 row: Node.js Rust Go Python before 1633.01 ms 812.57 ms 1451.49 ms N/A (crash) after 1616.13 ms 824.10 ms 1531.10 ms 2425.9 ms The harness was reading its data from LLM prose The Python agent's timing came back in two places: a structured elapsed_time in the tool artifact, and the model's prose. The harness regexed the prose first : m = re . search ( r " It took ([\d\.\-e]+) seconds " , text ) In live runs, Gemini said "Calculating the first 5 Mer

I usually write here about Next.js, caching, and the bugs that steal your sleep. But this post is...

I kept re-running the exact same input through my translation app. Same code. Same model. Same everything. And the word "machines" kept flipping between two different translations. Sometimes it came out as "機械" (machine). Sometimes as "あなたのPC" (your PC). No code changed between runs. No input changed either. My first assumption was a race condition somewhere in my pipeline. It wasn't. Where I actually looked I checked the obvious suspects first: caching, threading, anything stateful that could make the same input behave differently on different runs. All clean. So I went one level deeper, into how the model picks the winning word. Translation models score every candidate word and pick whichever scores highest. When I logged the actual scores for "machine" vs "your PC" on this input, they were almost exactly tied. That's the part that mattered. When two candidates are separated by a tiny margin, the order floating-point operations get summed in can nudge the score just enough to flip which one wins. Same math, same inputs, different accumulation order between runs — and a near-tie flips sides. Nothing was actually random. It was deterministic all the way down. It just wasn't deterministic in a way I could predict, because the thing that decided the winner was rounding noise several layers below anything I was testing. The fix wasn't "make it deterministic" Forcing strict floating-point determinism across an ML pipeline is its own rabbit hole, and not one I wanted to go down for one word. Instead, I looked at why the tie was so close in the first place. "Machine" and "your PC" were close enough in meaning, in this context, that the model wasn't confident either way. So I widened the margin instead of trying to eliminate the noise: I swapped the input word choice from "machines" to "equipment," which the model was much more decisively confident about. Scores stopped being close enough for rounding noise to matter. The flip-flopping stopped. I want to be honest about a

Cloudflare recently documented how its development team identified and fixed a rare bug in the widely used Rust HTTP library hyper that could silently truncate large HTTP responses while still returning a successful 200 OK status. The issue had existed for years, was triggered only under specific timing conditions, and has now been fixed upstream. By Renato Losio

The Story: Picture this: It is 10 PM. I was eating my dinner while adding one final touch to my social media app, Vlox. It should just say "Processing..." while generating a card. Simple, right? See the nightmare. 🔥 The Nightmare Scenario 📉 Suddenly, my "Download Card" button broke. htmlToImage started spitting out completely empty 0b images. The hunt was on. Failed Mission Log 🛰️ Attempt 1: Swap to html2canvas 🔄 Result: Error stating the element was not found in the cloned iframe. Verdict: The parent container was completely lost. Attempt 2: Use CoolAlertJS Toast 🍞 Result: It looked ugly and meant loading two different alert libraries for the same job? Not my game. Verdict: Total waste of bundle size. Attempt 3: Append to body + display: none 🙈 Result: The canvas process failed entirely. Verdict: Canvas snapshot engines completely ignore hidden elements. The "Aha!" Moment 💡 Why did the element vanish? Because the card generator lives entirely inside a Swal popup. When you click the download/confirm button, Swal instantly destroys that entire popup DOM tree. You cannot snapshot an element that no longer exists. 👻 The Ultimate Fix 🚀 Inside the new "Processing" popup, I appended the #card-generator-image-preview directly into the new alert container. The element stays alive in the active DOM. The snapshot succeeds perfectly. Clean code. Happy developer. Delicious dinner. Want to see the exact JavaScript code block that fixed it? Drop a comment below or check Vlox on Github .

Non è solo “chiedere aiuto”: è chiarire obiettivi, vincoli e tentativi. E accelera sia l’apprendimento che il lavoro in team. Nel lavoro quotidiano di un frontend developer (e non solo) capita spesso di bloccarsi: un bug che non si riproduce, un layout che “quasi” funziona, una libreria nuova che sembra richiedere di leggere mezzo internet. In quei momenti la differenza tra perdere ore e sbloccarsi rapidamente non è sempre “quanto ne sai”, ma come fai le domande . Fare domande di qualità è una skill professionale a tutti gli effetti: migliora la collaborazione, riduce il ping-pong nei thread, rende più efficaci code review e pair programming, e soprattutto ti allena a ragionare in modo strutturato. Perché fare buone domande è una competenza (non un dettaglio) Una domanda ben formulata ti obbliga a mettere ordine in quattro cose: Cosa stai cercando di ottenere (obiettivo) Cosa non sai (gap di conoscenza) Cosa hai già provato (tentativi e risultati) Che cosa non serve fare adesso (scope e priorità) Questo vale sia quando chiedi aiuto su un problema tecnico, sia quando stai decidendo cosa studiare per crescere. La domanda “cosa devo imparare?” è troppo vaga “Cosa devo imparare?” sembra utile, ma spesso non porta lontano perché manca il contesto: non definisce un obiettivo, non dà vincoli, non permette a chi risponde di proporre un percorso sensato. Una versione migliore parte da: Qual è il risultato che voglio ottenere? Cosa mi avvicina a quel risultato oggi, in modo pragmatico? E c’è un punto ancora più potente: chiedersi anche cosa NON serve imparare . Perché “cosa non devo imparare” ti fa risparmiare tempo Nel frontend c’è sempre una tentazione: allargare lo scope. Esempi tipici: “Per usare React devo prima imparare perfettamente TypeScript, poi i design pattern, poi…” “Per risolvere questo problema di CSS forse devo studiare tutta la specifica di Flexbox e Grid…” Chiederti cosa non è necessario adesso ti aiuta a: scegliere il minimo set di concetti per sbloccarti;

When an AI API call fails, the tempting reaction is to switch models or providers. That is often premature. A large share of 401, 429, model_not_found, timeout, and confusing billing issues are not model-quality problems. They are route-evidence problems. The request moved through a key, base URL, model ID, retry rule, fallback path, and billing record. If those pieces are not visible, changing the model can hide the real cause. Before you replace the model, debug the route. A practical route checklist Confirm the key scope. Is the API key attached to the right project, environment, and quota rule? A key that works in one workspace can fail in another because the limit, budget, or allowed model set is different. Confirm the base URL. Many OpenAI-compatible errors start with a request going to the wrong host, version path, or proxy. Check the exact Base URL used by the client, not the one written in a README from memory. Confirm the model ID. A model_not_found error is not always a provider outage. It can be a copied alias, a retired ID, a route that does not support that model, or a mismatch between public model names and API model IDs. Separate 401, 403, 404, and 429. These errors ask different questions: 401: is the key present and valid? 403: is the key allowed to use this route or model? 404/model_not_found: is the exact model ID available on this route? 429: is the limit coming from the user, key, project, provider, retry loop, or budget rule? Treating all of them as provider instability wastes time. Look for retry and fallback behavior. A single user action may trigger more than one model call. Agents, RAG pipelines, streaming clients, and SDK retries can quietly multiply traffic. If fallback is enabled, the served route may differ from the requested model. Check the usage and charge record. A successful response is not the end of the test. You should be able to explain which key made the call, which model was requested, which route served it, how many tokens

We’re excited to announce our first ever Summer Bug Smash! Every app has its share of rockstar bugs....

Osloq — ใช้ AI หาสาเหตุ bug แทน เวลา AI coding tools เสนอจะ "fix bug ให้" — เราได้แต่กด Accept หรือไม่ก็ Reject สองปุ่ม สองทางเลือก แต่เราไม่เคยรู้ว่า: AI รู้ได้ยังไงว่า bug เกิดจากตรงนี้? มัน reproduce แล้วหรือแค่อ่านโค้ดแล้วเดา? ถ้าเรา accept — มันจะพังของอย่างอื่นไหม? Osloq เลือกทางที่สาม: ไม่ใช่ "fix ให้" — แต่ " หาให้เจอแล้วบอกว่าเกิดอะไรขึ้น " Osloq คืออะไร Osloq เป็น AI agent ที่ทำหน้าที่ "นักสืบ bug" มีคนเปิด GitHub Issue → Osloq อ่าน → trace โค้ด → reproduce ใน sandbox → ส่งรายงานพร้อมหลักฐาน ┌─────────────────────────────────────────────────────┐ │ GitHub Issue: "ปุ่ม submit กดไม่ติดบน Safari" │ └─────────────────────┬───────────────────────────────┘ ▼ ┌─────────────────────────────────────────────────────┐ │ Osloq: │ │ 1. อ่าน issue → เข้าใจว่า "ปุ่มไม่ทำงาน" │ │ 2. trace โค้ด: จาก handler → service → DOM event │ │ 3. reproduce: รัน Safari ใน sandbox → ปุ่มไม่ติดจริง │ │ 4. จับหลักฐาน: logs, screenshots, call stack │ │ 5. สรุป: "event listener ใช้ 'click' แต่ Safari │ │ บน iOS 18 ไม่ bubble event — ต้องใช้ 'pointerdown' │ └─────────────────────┬───────────────────────────────┘ ▼ ┌─────────────────────────────────────────────────────┐ │ Report บน GitHub Issue: │ │ 📸 screenshot ของ Safari ที่ปุ่มไม่ทำงาน │ │ 📋 console error: "Unhandled Promise Rejection" │ │ 🔗 code path: handler.ts:42 → form.ts:17 │ │ 💡 suggestion: เปลี่ยน event type │ └─────────────────────────────────────────────────────┘ คุณอ่าน report → เข้าใจปัญหา → ตัดสินใจเอง ว่าจะแก้ยังไง ต่างจาก "AI Fix Everything" ยังไง Devin / Sweep AI Osloq แนวคิด "Fix the bug" "Find the cause" ทำงานยังไง เขียนโค้ดใหม่ → เปิด PR Reproduce → รายงาน evidence เราเห็นอะไร PR diff ภาพ, log, call stack, บทสรุป ใครตัดสินใจ AI (เราแค่ merge) เรา (AI บอกว่าอะไรผิด) ถ้าผิดพลาด โค้ดผิดเข้า main Report ผิด — ไม่กระทบโค้ด ความเสี่ยง สูง — AI แก้โค้ดโดยตรง ต่ำ — AI แค่แนะนำ ทำไมถึง "สบายใจกว่า" 1. คุณเห็นหลักฐาน — ไม่ใช่แค่ diff ❌ "Fixed button click handler — please review" → review 300 บรรทัด — ไม่รู้ว่าแก้ถูกไหม ✅ "Button