systematic-debugging

name	systematic-debugging
description	4-phase root cause debugging: understand bugs before fixing.
version	1.1.0
author	Hermes Agent (adapted from obra/superpowers)
license	MIT
platforms	["linux","macos","windows"]
metadata	{"hermes":{"tags":["debugging","troubleshooting","problem-solving","root-cause","investigation"],"related_skills":["test-driven-development","writing-plans","subagent-driven-development"]}}

Systematic Debugging

Overview

Random fixes waste time and create new bugs. Quick patches mask underlying issues.

Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.

Violating the letter of this process is violating the spirit of debugging.

The Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

If you haven't completed Phase 1, you cannot propose fixes.

When to Use

Use for ANY technical issue:

• Test failures
• Bugs in production
• Unexpected behavior
• Performance problems
• Build failures
• Integration issues

Use this ESPECIALLY when:

• Under time pressure (emergencies make guessing tempting)
• "Just one quick fix" seems obvious
• You've already tried multiple fixes
• Previous fix didn't work
• You don't fully understand the issue

Don't skip when:

• Issue seems simple (simple bugs have root causes too)
• You're in a hurry (rushing guarantees rework)
• Someone wants it fixed NOW (systematic is faster than thrashing)

The Four Phases

You MUST complete each phase before proceeding to the next.

---

Phase 1: Root Cause Investigation

BEFORE attempting ANY fix:

1. Read Error Messages Carefully

• Don't skip past errors or warnings
• They often contain the exact solution
• Read stack traces completely
• Note line numbers, file paths, error codes

Action: Use read_file on the relevant source files. Use search_files to find the error string in the codebase.

2. Reproduce Consistently

• Can you trigger it reliably?
• What are the exact steps?
• Does it happen every time?
• If not reproducible → gather more data, don't guess

Action: Use the terminal tool to run the failing test or trigger the bug:

# Run specific failing test
pytest tests/test_module.py::test_name -v

# Run with verbose output
pytest tests/test_module.py -v --tb=long

3. Check Recent Changes

• What changed that could cause this?
• Git diff, recent commits
• New dependencies, config changes

Action:

# Recent commits
git log --oneline -10

# Uncommitted changes
git diff

# Changes in specific file
git log -p --follow src/problematic_file.py | head -100

4. Gather Evidence in Multi-Component Systems

WHEN system has multiple components (API → service → database, CI → build → deploy):

BEFORE proposing fixes, add diagnostic instrumentation:

For EACH component boundary:

• Log what data enters the component
• Log what data exits the component
• Verify environment/config propagation
• Check state at each layer

Run once to gather evidence showing WHERE it breaks. THEN analyze evidence to identify the failing component. THEN investigate that specific component.

5. Trace Data Flow

WHEN error is deep in the call stack:

• Where does the bad value originate?
• What called this function with the bad value?
• Keep tracing upstream until you find the source
• Fix at the source, not at the symptom

Action: Use search_files to trace references:

# Find where the function is called
search_files("function_name(", path="src/", file_glob="*.py")

# Find where the variable is set
search_files("variable_name\\s*=", path="src/", file_glob="*.py")

Phase 1 Completion Checklist

• Error messages fully read and understood
• Issue reproduced consistently
• Recent changes identified and reviewed
• Evidence gathered (logs, state, data flow)
• Problem isolated to specific component/code
• Root cause hypothesis formed

STOP: Do not proceed to Phase 2 until you understand WHY it's happening.

---

Phase 2: Pattern Analysis

Find the pattern before fixing:

1. Find Working Examples

• Locate similar working code in the same codebase
• What works that's similar to what's broken?

Action: Use search_files to find comparable patterns:

search_files("similar_pattern", path="src/", file_glob="*.py")

2. Compare Against References

• If implementing a pattern, read the reference implementation COMPLETELY
• Don't skim — read every line
• Understand the pattern fully before applying

3. Identify Differences

• What's different between working and broken?
• List every difference, however small
• Don't assume "that can't matter"

4. Understand Dependencies

• What other components does this need?
• What settings, config, environment?
• What assumptions does it make?

---

Phase 3: Hypothesis and Testing

Scientific method:

1. Form a Single Hypothesis

• State clearly: "I think X is the root cause because Y"
• Write it down
• Be specific, not vague

2. Test Minimally

• Make the SMALLEST possible change to test the hypothesis
• One variable at a time
• Don't fix multiple things at once

3. Verify Before Continuing

• Did it work? → Phase 4
• Didn't work? → Form NEW hypothesis
• DON'T add more fixes on top

4. When You Don't Know

• Say "I don't understand X"
• Don't pretend to know
• Ask the user for help
• Research more

---

Phase 4: Implementation

Fix the root cause, not the symptom:

1. Create Failing Test Case

• Simplest possible reproduction
• Automated test if possible
• MUST have before fixing
• Use the test-driven-development skill

2. Implement Single Fix

• Address the root cause identified
• ONE change at a time
• No "while I'm here" improvements
• No bundled refactoring

3. Verify Fix

# Run the specific regression test
pytest tests/test_module.py::test_regression -v

# Run full suite — no regressions
pytest tests/ -q

4. If Fix Doesn't Work — The Rule of Three

• STOP.
• Count: How many fixes have you tried?
• If < 3: Return to Phase 1, re-analyze with new information
• If ≥ 3: STOP and question the architecture (step 5 below)
• DON'T attempt Fix #4 without architectural discussion

5. If 3+ Fixes Failed: Question Architecture

Pattern indicating an architectural problem:

• Each fix reveals new shared state/coupling in a different place
• Fixes require "massive refactoring" to implement
• Each fix creates new symptoms elsewhere

STOP and question fundamentals:

• Is this pattern fundamentally sound?
• Are we "sticking with it through sheer inertia"?
• Should we refactor the architecture vs. continue fixing symptoms?

Discuss with the user before attempting more fixes.

This is NOT a failed hypothesis — this is a wrong architecture.

---

Red Flags — STOP and Follow Process

If you catch yourself thinking:

• "Quick fix for now, investigate later"
• "Just try changing X and see if it works"
• "Add multiple changes, run tests"
• "Skip the test, I'll manually verify"
• "It's probably X, let me fix that"
• "I don't fully understand but this might work"
• "Pattern says X but I'll adapt it differently"
• "I see the problem, let me fix it"
• "One more fix attempt" (when already tried 2+)
• Each fix reveals a new problem in a different place

ALL of these mean: STOP. Return to Phase 1.

If 3+ fixes failed: Question the architecture (Phase 4 step 5).

Signal: Enormous Issue Count

When a scanner/analyzer reports "N issues found" and N is extraordinarily large (thousands+), the algorithm is almost always wrong — not the data. For example: a script reporting 25,197 "contradictions" meant the detection algorithm (same-tag + score-diff ≥ 3) was fundamentally flawed, not that the wiki had 25K real contradictions. Run the script directly first to inspect the raw output before investigating the data.

New Pitfalls — Frontend / Multi-Language Debugging

TypeScript: build IS the test

For frontend React/TS projects, npm run build (which runs tsc && vite build) is the equivalent of pytest tests/. TypeScript compilation catches type errors before runtime. There is no separate "run tests to verify types" step — if npm run build succeeds without errors, the type layer is clean. Verbose TS test output often gets truncated; check the RC (return code) and the final build output summary.

execute_code subprocess limits for long foreground commands

execute_code subprocess caps at ~5 minutes and 50KB stdout. Commands that produce heavy output (pip install -v, npm install, verbose pytest) can silently appear to succeed (RC 0) but output empty. Use terminal() for any operation likely to exceed these limits. Workaround: pipe to a temp file and read it after.

Multi-component system: verify each layer independently

When debugging a full-stack issue (frontend → FastAPI → LangGraph → DB), don't assume the subagent's "all done" means all layers work. Verify each component:

• Backend: curl http://localhost:8000/health
• Frontend: npm run build (TypeScript clean)
• Integration: actual API call end-to-end

SSE/streaming: server may send two data shapes for the same event type

When SSE endpoint sends data with different field layouts depending on code path (e.g. historical backfill vs live events), the client receives a mix and the field access event.payload.name silently returns undefined for half the events, falling back to placeholder text. Symptom: "some events show content, others show 'unknown' or empty" with the same code rendering both.

Diagnostic (2026-06-01, PromptQueue task events):

# Stream raw SSE for ~5s, capture both shapes
curl -sN http://localhost:9090/api/v1/tasks/<id>/events 2>&1 | head -20
# Look for: data: {...} lines, compare structure
# Historical backfill might be: {"id":94,"eventType":"agent_text","payload":{"content":"..."}}
# Live events might be: {"type":"text","content":"..."}  ← different shape

Fix options (pick one, document why):

• Server-side normalize (events.ts): always send the same shape regardless of source. Wrap live events in TaskEvent envelope before JSON.stringify. Best when other clients depend on the data too.
• Client-side normalize (api-client.ts): detect shape (e.g. if 'payload' in data vs not) and extract accordingly. Best when you can't change the server.

The key insight: JSON.parse(e.data) doesn't fail on either shape, so the try/catch around it never triggers. The bug is silent — the client just renders ?? "unknown" for half the data. Add a console.log of the parsed shape during diagnosis so the asymmetry is visible.

Verify the LLM endpoint directly, not the metadata

When debugging "is provider X actually working", the user preference (2026-06-01) is to curl/urllib the endpoint with a known prompt and confirm HTTP 200 + sane response. This is the opposite of investigating jobs.json last_run_at, last_status: ok, or agent.log tool-call entries. The user considers the endpoint the ground truth — metadata is a downstream artifact that may lie.

A last_status: ok cron does NOT mean the LLM endpoint is healthy. It means "the gateway saw a 200 response or a shell-only command completed". Many 'ok' cron jobs (heartbeat-touch, file counting, email sending) don't call the LLM at all.

Concrete probe pattern lives in cron-job-provider-migration/scripts/migrate-cron-provider.py and the reference cron-job-provider-migration/references/yidong-provider-verification.md.

Git: large artifacts (>500KB) before commit

Check git diff --stat before every commit. If a single file change exceeds ~500KB (e.g. accidentally committed node_modules, dist/, .venv/), the commit will be impractical to clean up later. Create .gitignore before the first commit, not after. If 3+ fixes failed: Question the architecture (Phase 4 step 5).

Common Rationalizations

Excuse	Reality
"Issue is simple, don't need process"	Simple issues have root causes too. Process is fast for simple bugs.
"Emergency, no time for process"	Systematic debugging is FASTER than guess-and-check thrashing.
"Just try this first, then investigate"	First fix sets the pattern. Do it right from the start.
"I'll write test after confirming fix works"	Untested fixes don't stick. Test first proves it.
"Multiple fixes at once saves time"	Can't isolate what worked. Causes new bugs.
"Reference too long, I'll adapt the pattern"	Partial understanding guarantees bugs. Read it completely.
"I see the problem, let me fix it"	Seeing symptoms ≠ understanding root cause.
"One more fix attempt" (after 2+ failures)	3+ failures = architectural problem. Question the pattern, don't fix again.

Quick Reference

Phase	Key Activities	Success Criteria
1. Root Cause	Read errors, reproduce, check changes, gather evidence, trace data flow	Understand WHAT and WHY
2. Pattern	Find working examples, compare, identify differences	Know what's different
3. Hypothesis	Form theory, test minimally, one variable at a time	Confirmed or new hypothesis
4. Implementation	Create regression test, fix root cause, verify	Bug resolved, all tests pass

Hermes Agent Integration

Investigation Tools

Use these Hermes tools during Phase 1:

• search_files — Find error strings, trace function calls, locate patterns
• read_file — Read source code with line numbers for precise analysis
• terminal — Run tests, check git history, reproduce bugs
• web_search/web_extract — Research error messages, library docs

With delegate_task

For complex multi-component debugging, dispatch investigation subagents:

delegate_task(
    goal="Investigate why [specific test/behavior] fails",
    context="""
    Follow systematic-debugging skill:
    1. Read the error message carefully
    2. Reproduce the issue
    3. Trace the data flow to find root cause
    4. Report findings — do NOT fix yet

    Error: [paste full error]
    File: [path to failing code]
    Test command: [exact command]
    """,
    toolsets=['terminal', 'file']
)

With test-driven-development

When fixing bugs:

1. Write a test that reproduces the bug (RED)
2. Debug systematically to find root cause
3. Fix the root cause (GREEN)
4. The test proves the fix and prevents regression

Real-World Impact

From debugging sessions:

• Systematic approach: 15-30 minutes to fix
• Random fixes approach: 2-3 hours of thrashing
• First-time fix rate: 95% vs 40%
• New bugs introduced: Near zero vs common

No shortcuts. No guessing. Systematic always wins.