DEV Community

jidonglab profile picture

jidonglab

1 project a week. Building and sharing the entire process — from idea to shipped product in 7 days. Currently: AI news automation.

JSON Schema Field Order: My vLLM Classifier Answered Before Thinking

JSON Schema Field Order: My vLLM Classifier Answered Before Thinking

Comments
6 min read

Want to connect with jidonglab?

Create an account to connect with jidonglab. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Claude Prompt Caching Hit 0 of 1,412 Calls: A Timestamp Killed It

Claude Prompt Caching Hit 0 of 1,412 Calls: A Timestamp Killed It

Comments
7 min read
Codex Image Gen Saved My White Pixels as Transparent

Codex Image Gen Saved My White Pixels as Transparent

Comments
6 min read
GitHub Actions Cache Never Updates: 9 Weeks of a Frozen mypy Cache

GitHub Actions Cache Never Updates: 9 Weeks of a Frozen mypy Cache

Comments
6 min read
Claude Batch API Returned Results Out of Order: 59% of My Labels Wrong

Claude Batch API Returned Results Out of Order: 59% of My Labels Wrong

Comments
6 min read
vLLM KV Cache Math: Why My 24GB GPU Served Only 4 Requests at Once

vLLM KV Cache Math: Why My 24GB GPU Served Only 4 Requests at Once

Comments
7 min read
Docker RUN rm Didn't Delete My .env. 3 of 14 Images Still Had It

Docker RUN rm Didn't Delete My .env. 3 of 14 Images Still Had It

Comments
6 min read
I Shipped a Friends Feature, Then Dropped It the Same Day

I Shipped a Friends Feature, Then Dropped It the Same Day

Comments 1
5 min read
SQLite 'database is locked' Ignored My 30s busy_timeout: 311 Failures

SQLite 'database is locked' Ignored My 30s busy_timeout: 311 Failures

Comments 1
6 min read
Claude stop_reason max_tokens: 83 Reports Silently Cut Off Mid-JSON

Claude stop_reason max_tokens: 83 Reports Silently Cut Off Mid-JSON

Comments
6 min read
Five Parallel AI Builders, One Contract, 25 Review Fixes

Five Parallel AI Builders, One Contract, 25 Review Fixes

Comments 2
6 min read
Refmade: a free desktop app for Claude Code and Codex, without the terminal

Refmade: a free desktop app for Claude Code and Codex, without the terminal

1
Comments
3 min read
BM25 vs Embeddings: Why My Vector Search Couldn't Find Error E4012

BM25 vs Embeddings: Why My Vector Search Couldn't Find Error E4012

1
Comments 1
7 min read
Why docker stop Takes 10 Seconds: PID 1 Is Ignoring Your SIGTERM

Why docker stop Takes 10 Seconds: PID 1 Is Ignoring Your SIGTERM

Comments
6 min read
Claude Code Hooks: Exit Code 1 Doesn't Block. 9 of 9 Commands Ran

Claude Code Hooks: Exit Code 1 Doesn't Block. 9 of 9 Commands Ran

Comments 2
6 min read
Reading Claude Code and Codex Session Logs: Four Traps

Reading Claude Code and Codex Session Logs: Four Traps

Comments 1
6 min read
vLLM Temperature 0 Isn't Deterministic: 23 of 200 Answers Changed

vLLM Temperature 0 Isn't Deterministic: 23 of 200 Answers Changed

Comments
7 min read
Whisper Hallucinations: 'Thanks for Watching' in 9% of My Transcripts

Whisper Hallucinations: 'Thanks for Watching' in 9% of My Transcripts

Comments
6 min read
Stop Trusting Agent Self-Reports: Read the Logs Instead

Stop Trusting Agent Self-Reports: Read the Logs Instead

Comments
6 min read
A Local-First Plan, Then 4 Days of Scope Creep

A Local-First Plan, Then 4 Days of Scope Creep

1
Comments
6 min read
GitHub Actions fetch-depth: 1 Made My CI Skip Tests for 41 PRs

GitHub Actions fetch-depth: 1 Made My CI Skip Tests for 41 PRs

1
Comments
7 min read
I Built an Agent Team, Then Couldn't See What It Did

I Built an Agent Team, Then Couldn't See What It Did

Comments
5 min read
Sync Anthropic Client Blocked My asyncio Loop: Voice p95 Hit 11.4s

Sync Anthropic Client Blocked My asyncio Loop: Voice p95 Hit 11.4s

Comments
7 min read
Python json.dumps ensure_ascii: 24% More Claude Tokens, Wrong Kanji

Python json.dumps ensure_ascii: 24% More Claude Tokens, Wrong Kanji

1
Comments
6 min read
Cosine Similarity Threshold 0.8: Embedding Anisotropy Broke My RAG

Cosine Similarity Threshold 0.8: Embedding Anisotropy Broke My RAG

1
Comments
7 min read
Docker Compose depends_on Won't Wait for Postgres: 11/50 Runs Failed

Docker Compose depends_on Won't Wait for Postgres: 11/50 Runs Failed

Comments
6 min read
Ollama num_ctx Truncated 287 of 400 Prompts and Never Told Me

Ollama num_ctx Truncated 287 of 400 Prompts and Never Told Me

Comments
6 min read
bge-reranker Truncates at 512 Tokens: 31% of My Chunks Got Cut

bge-reranker Truncates at 512 Tokens: 31% of My Chunks Got Cut

1
Comments 4
7 min read
LLM-as-a-Judge: Claude Gave 68% of Answers a 7 or 8 Out of 10

LLM-as-a-Judge: Claude Gave 68% of Answers a 7 or 8 Out of 10

1
Comments 3
6 min read
GitHub Actions GITHUB_TOKEN Won't Trigger Workflows: 0 of 11 Releases

GitHub Actions GITHUB_TOKEN Won't Trigger Workflows: 0 of 11 Releases

Comments
6 min read
tiktoken Undercounts Claude Tokens: 37 of 418 Requests Blew the Limit

tiktoken Undercounts Claude Tokens: 37 of 418 Requests Blew the Limit

Comments
7 min read
Speculative Decoding Made My vLLM Server Slower: The Acceptance Math

Speculative Decoding Made My vLLM Server Slower: The Acceptance Math

1
Comments 1
7 min read
Anthropic SDK max_retries Stacked on My Retries: 36 Calls per Job

Anthropic SDK max_retries Stacked on My Retries: 36 Calls per Job

Comments 1
6 min read
Claude Code Deny Rules Blocked Read(.env). Bash Read It Anyway

Claude Code Deny Rules Blocked Read(.env). Bash Read It Anyway

2
Comments 1
6 min read
Claude Code in launchd: My Nightly claude -p Job Worked 6 of 14 Nights

Claude Code in launchd: My Nightly claude -p Job Worked 6 of 14 Nights

1
Comments
6 min read
pgvector HNSW Filtering: My RAG Asked for 10 Rows and Got 0

pgvector HNSW Filtering: My RAG Asked for 10 Rows and Got 0

Comments 1
6 min read
Nginx proxy_buffering Broke My LLM SSE Stream: 0.4s Became 3.4s

Nginx proxy_buffering Broke My LLM SSE Stream: 0.4s Became 3.4s

1
Comments
6 min read
GitHub Actions Cron Was Late 30 Nights Straight, Then Skipped One

GitHub Actions Cron Was Late 30 Nights Straight, Then Skipped One

1
Comments 1
7 min read
Claude Parallel Tool Use: My Agent Loop Crashed on 388 of 1,200 Runs

Claude Parallel Tool Use: My Agent Loop Crashed on 388 of 1,200 Runs

4
Comments 3
7 min read
Lost in the Middle: My RAG Found the Right Chunk and the LLM Ignored It

Lost in the Middle: My RAG Found the Right Chunk and the LLM Ignored It

Comments
7 min read
Claude Prompt Caching Hit Rate Was 0%. One Timestamp Did It

Claude Prompt Caching Hit Rate Was 0%. One Timestamp Did It

Comments
7 min read
GitHub Actions Cache Never Saves on a Key Hit: 23 Days of Stale CI

GitHub Actions Cache Never Saves on a Key Hit: 23 Days of Stale CI

2
Comments 2
6 min read
MCP stdio Server: One print() Broke 19% of My Tool Calls

MCP stdio Server: One print() Broke 19% of My Tool Calls

1
Comments 1
6 min read
KV Cache Math: Why Llama 3.1 8B at 128K Context Won't Fit in 24GB

KV Cache Math: Why Llama 3.1 8B at 128K Context Won't Fit in 24GB

Comments 1
6 min read
git push --force-with-lease Stops Protecting You After git fetch

git push --force-with-lease Stops Protecting You After git fetch

Comments
6 min read
Deepgram endpointing=300 Cut Off 22% of My Voice AI Users Mid-Answer

Deepgram endpointing=300 Cut Off 22% of My Voice AI Users Mid-Answer

1
Comments
6 min read
Claude stop_reason max_tokens: json_repair Hid 198 Truncated Replies

Claude stop_reason max_tokens: json_repair Hid 198 Truncated Replies

1
Comments
6 min read
BM25 vs Embeddings: Why Your RAG Can't Find Error Code PGX-4012

BM25 vs Embeddings: Why Your RAG Can't Find Error Code PGX-4012

Comments
7 min read
Docker Stop Takes 10 Seconds: Your App Is PID 1 and Ignores SIGTERM

Docker Stop Takes 10 Seconds: Your App Is PID 1 and Ignores SIGTERM

Comments
7 min read
Claude Code Subagents Were 48% of My Bill. Their Output Was 0.9%

Claude Code Subagents Were 48% of My Bill. Their Output Was 0.9%

1
Comments 1
6 min read
Temperature 0 Isn't Deterministic: Batch Invariance in LLM Inference

Temperature 0 Isn't Deterministic: Batch Invariance in LLM Inference

Comments
7 min read
Whisper Hallucinates on Silence: 187 Phantom Transcripts in a Week

Whisper Hallucinates on Silence: 187 Phantom Transcripts in a Week

Comments
6 min read
actions/checkout fetch-depth: Why Your CI Diff Against main Is Empty

actions/checkout fetch-depth: Why Your CI Diff Against main Is Empty

1
Comments
5 min read
Claude Code Hooks Only Block on Exit Code 2: 47 Writes Got Through

Claude Code Hooks Only Block on Exit Code 2: 47 Writes Got Through

1
Comments
6 min read
Constrained Decoding: Your JSON Schema Key Order Is a Prompt

Constrained Decoding: Your JSON Schema Key Order Is a Prompt

1
Comments
6 min read
npm publish Ignores .gitignore: The .npmignore Override Rule

npm publish Ignores .gitignore: The .npmignore Override Rule

Comments
5 min read
Playwright MCP Token Usage: 9 Tool Calls, 62% of My Context

Playwright MCP Token Usage: 9 Tool Calls, 62% of My Context

1
Comments
6 min read
Anthropic Batch API: 112 of My 1,842 Jobs Never Came Back

Anthropic Batch API: 112 of My 1,842 Jobs Never Came Back

1
Comments 1
6 min read
all-MiniLM-L6-v2 Truncates at 256 Tokens: Your RAG Chunks Are Half Blind

all-MiniLM-L6-v2 Truncates at 256 Tokens: Your RAG Chunks Are Half Blind

1
Comments
6 min read
GitHub Actions pull_request Runs on a Merge Commit You Never Pushed

GitHub Actions pull_request Runs on a Merge Commit You Never Pushed

1
Comments
6 min read
loading...