Echo
Back

We opened a real Codex session and found problems you won't believe

The waste in one session was absurd.

Research noteContext healthUpdated Jul 1, 2026

More than 600K tokens were not doing work. They were re-paying for mistakes that were already over: stale file reads, a git rebuild loop, debug output from a bug fixed forty turns earlier, and the rediscovery scramble that follows every auto-compaction.

Your agent doesn't remember any of this happening. But it pays for all of it, every single turn.

A mistake in a chat is paid once. A mistake in a context window is billed on every turn after it.

The Bill, Itemized

Agent Doctor reads a real Codex or Claude Code session and labels each class of waste. Here is one audit of a single session:

ProblemTypeWasted
Post-Compaction Rediscoverystructural accumulation83,919 tok
Long-Abort Disk Side-Effectplatform defect28,389 tok
Invalid Completion Debthuman cost17,876 tok
Git Rebuild Loopmodel behavior7,993 tok

In this audit, the top visible problems accounted for more than 600K tokens of wasted effort — before the deeper semantic failures were even counted. This is one session. Yours will look different, but it is rarely clean.

Why the Meter Keeps Running

The failure chain is mechanical, not mysterious:

a mistake happens its evidence stays in the window every later turn re-reads it the window fills faster compaction fires earlier compaction keeps the noise and drops the why the agent rediscovers state it already had more tokens, more waiting, and edits that drift off target.

Notice what this means: the model was never the problem. Your agent didn't get dumber. It was reasoning inside a window where its own history kept outvoting your task.

Almost All of It Is Avoidable

Here is the part nobody tells you: most of these problems don't need a smarter model, a bigger window, or better prompts.

They need you to leave earlier.

Every session has a precision curve. For the first twenty turns, nearly every token in the window still serves the current task. Past that, the window fills with old plans, old reads, and old debugging — and the model starts paying attention tax on all of it. When compaction finally fires, it decides what survives, and it decides badly.

Compaction is not memory. It is lossy compression with opinions. The single highest-leverage move in agentic coding is to move to a fresh session before compaction ever happens.

Shorter sessions are not a discipline hack. They are how precision works.

The Short Session Protocol

Three moves:

1

Audit

Run Agent Doctor on your sessions. See which problem classes you actually hit — not which ones you guess you hit.

2

Exit before compaction

Keep sessions under ~20 turns. Never let auto-compact decide which of your decisions survive.

3

Carry only clean state

When you start fresh, move exactly five things forward:

current goalfiles changeddecisionsconstraintsfailed attempts

You can do step 3 by hand. It works. It is exactly what Echo automates — it builds the clean handoff for you, so every new session warm-starts with effective context instead of a cold rebuild.

What Your Report Tells You

Agent Doctor generates your Context Efficiency Report from your own sessions:

  • which problems your agent actually hits, ranked by token cost
  • which of them are avoidable with shorter sessions and clean carries
  • the total you would save if you avoided them

Then it translates that number into things you feel:

Money

If a third of your window is dead weight, you are paying a plan tier for tokens that buy you nothing. Cut the waste, and the plan you "need" is often one tier lower.

Time

Every context rebuild is time you spend watching the agent re-read files it already read. Clean sessions skip the rebuild.

Output

A short, clean window is the difference between an agent that follows your constraints and one that forgets them on turn 40.

Do This Today

  • Generate your Context Efficiency Report. See what your agent has been carrying and what avoiding it is worth.
  • In your next session: exit before compaction, and carry the five things forward.

Agent Doctor is the diagnosis

Short sessions and clean handoffs are the first treatment. Real memory is the cure.

Keep Reading