Riley Wang - DEV Community

Riley Wang

Oct 27

Your Agent Said "Done". The Trace Shows Nothing Changed.

#ai #observability #testing #python

5 min read

Riley Wang

Oct 27

Your Agent Said "Done". The Trace Shows Nothing Changed.

#ai #observability #testing #python

5 min read

Riley Wang

Oct 26

The Diff Wasn't the Model: Fingerprint the Environment Before You Replay a Trace

#observability #ai #python #testing

1

6 min read

Riley Wang

Oct 20

Record Once, Replay Forever: Cassette Tests for Flaky Agent Tool Calls

#ai #testing #observability #python

4 min read

Riley Wang

Oct 19

Same Call, Same Result: A No-Progress Detector for Agent Tool Loops

#ai #python #opensource #debugging

5 min read

Riley Wang

Oct 18

The Token Leader Is Not the Latency Leader: Build a Span Ledger for Agent Runs

#ai #observability #python #testing

7 min read

Riley Wang

Oct 17

Scrub the Trace, Keep the Failure: A Redaction Gate You Can Test

#observability #ai #python #security

5 min read

Riley Wang

Oct 16

Sample Runs, Not Spans: Shrink Agent Traces Without Losing Failures

#ai #observability #python #devtools

5 min read

Riley Wang

Oct 15

Validate the Trace Before You Trust the Trial: A Conformance Linter for Agent Runs

#ai #python #testing #observability

6 min read

Riley Wang

Oct 13

Hash Three Boundaries Before You Blame the Model

#ai #python #observability #testing

7 min read

Riley Wang

Oct 11

Retry Wrote Twice. Store commit_state Before the Next Attempt.

#python #testing #ai #devops

7 min read

Riley Wang

Oct 10

Remote 200, Local Exit 1. Store the Turn Id on Both Sides.

#ai #observability #python #testing

8 min read

Riley Wang

Oct 8

Name the Span That Spent the Agent Budget

#ai #python #tutorial #devops

7 min read

Riley Wang

Sep 23

Tool Previews Lie. Store stdout_bytes and a Truncation Flag.

#ai #python #debugging #testing

6 min read

Riley Wang

Sep 22

Hash the Tool Catalog Before You Trust the Trace

#ai #python #debugging #testing

6 min read

Riley Wang

Sep 21

The Timeline Has Holes. Record Span Sequence Numbers.

#ai #python #debugging #observability

1

6 min read

Riley Wang

Sep 20

The Agent Reported Green. Record argv and the Exit Code.

#ai #debugging #observability #python

7 min read

Riley Wang

Sep 18

Lint Agent Traces Before You Debug the Model

#ai #debugging #observability #python

6 min read

Riley Wang

Sep 17

After Each Tool Span, Hash the Working Tree

#ai #observability #debugging #python

6 min read

Riley Wang

Sep 16

The Reply Looks Finished. Record the Finish Reason.

#ai #debugging #agents #observability

6 min read

Riley Wang

Sep 14

Your Trace Shows the Wrong Order. Measure Clock Skew Before You Debug

#observability #ai #agents #python

5 min read

Riley Wang

Sep 13

Tool Output Looks Complete. Record the Injected Slice.

#ai #agents #python #debugging

8 min read

Riley Wang

Sep 12

Agent Traces Hide the Fork. Record Ranked Options.

#ai #agents #debugging #python

6 min read

Riley Wang

Sep 11

Green Agent Loops Never End. Require a Terminal Span

#agents #observability #python #debugging

6 min read

Riley Wang

Sep 9

Retries Look Green. Count Attempts on Every Tool Span

#ai #agents #debugging #python

7 min read

Riley Wang

Sep 8

Agent Traces Hide Wait Time. Split Three Lanes.

#ai #agents #observability #debugging

7 min read

Riley Wang

Sep 6

Orphan Tool Calls Look Like Hangs. Pair Every Result.

#ai #agents #debugging #python

7 min read

Riley Wang

Sep 5

Nested Agent Failures Hide in Flat Logs. Build a Span Tree.

#ai #agents #debugging #python

7 min read

Riley Wang

Sep 4

Concurrent Tool Calls Scramble Logs. Diff the Span DAG Instead.

#ai #agents #python #debugging

7 min read

Riley Wang

Sep 4

Your Agent Is Leaking Tokens. Build a Decision Ledger on a Free Server.

#ai #tutorial #llm #python

4 min read

Riley Wang

Sep 4

When the Token Well Runs Dry: A Degradation State Machine for LLM Services

#llm #python #opensource #serverless

4 min read

Riley Wang

Sep 4

How I Built a Self-Auditing Agent Loop on a Free Server

#python #llm #agentloop #tokenbudget

5 min read

Riley Wang

Sep 4

Log Where Each Tool Argument Came From

#python #ai #debugging #agents

7 min read

Riley Wang

Sep 2

Why Your Agent Fails Only in Production: A Trace-and-Diff Loop on a Free Server

#agents #debugging #observability #python

1

4 min read

Riley Wang

Sep 1

The Agent's Key Ring: Scoping Tool Permissions with a Deny-by-Default Wrapper

#ai #security #agents #tutorial

4 min read

Riley Wang

Aug 31

Diff Every Tool Call: Replaying Agent Runs from a JSONL Trace

#ai #debugging #programming #llm

5

3

4 min read

Riley Wang

Aug 30

Your Agent's Context Is Rotting. Here's How I Traced the Decay.

#ai #debugging #llm #programming

1

4 min read

Riley Wang

Aug 29

Trace Agent Tool Calls on a Free Server: A 10M-Token Debug Loop

#ai #llm #debugging #tutorial

1

4 min read

Riley Wang

Aug 28

Trace First, Blame Later: A Debug Loop for Failing Agent Runs

#ai #agents #llm #tutorial

1

5 min read

Riley Wang

Aug 26

Agent Runs Fail Quietly. Here's the Trace Harness I Use to Find Out Why.

#ai #agents #observability #python

4 min read

Riley Wang

Aug 23

Build a Token-Budgeted LLM Service on a Free Server: A Step-by-Step Tutorial

#tutorial #llm #python #devops

5 min read

Riley Wang

Aug 21

Token Forensics: Auditing LLM Usage on a Free Server

#ai #llm #tutorial #python

5 min read

Riley Wang

Aug 14

MiniMax H3 Is Making Noise. My First Check Isn’t the Leaderboard.

#ai #testing #opensource #coding

3 min read

Riley Wang

Aug 13

A New Cheap Model Dropped This Week. Here's the Harness I Run Before I Switch Anything

#ai #testing #productivity #tooling

5 min read

Riley Wang

Aug 10

I Stopped Trusting My Agent's Boundaries Until I Could Break Them in a Throwaway Sandbox

#ai #agents #security #testing

5 min read

Riley Wang

Aug 5

Stop Benchmarking Coding Models by Vibes: A Repeatable 20-Task Harness You Can Run Tonight

#ai #python #testing #productivity

2

5 min read

Writing Debut