[isaacdl]

Anywhere we can read more about what a "harness issue" means? What was the impact of it?

[xnorswap]

One thing that could be a strong degradation especially for benchmarks is they switched the default "Exit Plan" mode from:

    "Proceed"

to

   "Clear Context and Proceed"

It's rare you'd want to do that unless you're actually near the context window after planning.

I pressed it accidentally once, and it managed to forget one of the clarifying questions it asked me because it hadn't properly written that to the plan file.

If you're running in yolo mode ( --dangerously-skip-permissions ) then it wouldn't surprise me to see many tasks suddenly do a lot worse.

Even in the best case, you've just used a ton of tokens searching your codebase, and it then has to repeat all that to implement because it's been cleared.

I'd like to see the option of:

    "Compact and proceed"

because that would be useful, but just proceed should still be the default imo.

[samusiam]

I disagree that this was the issue, or that it's "rare that you'd want to do that unless you're near the context window". Clearing context after writing a plan, before starting implementation of said plan, is common practice (probably standard practice) with spec driven development. If the plan is adequate, then compaction would be redundant.

[plexicle]

"It's rare you'd want to do that unless you're actually near the context window after planning."

Highly disagree. It's rare you WOULDN'T want to do this. This was a good change, and a lot of us were doing this anyway, but just manually.

Getting the plan together and then starting fresh will almost always produce better results.

[rubslopes]

Not disagreeing with you, but FYI you can roll back to the conversation before the 'clear context and proceed' with 'claude --resume'.

[airstrike]

Pretty sure they mean the issue is on the agentic loop and related tool calling, not on the model itself

In other words, it was the Claude Code _app_ that was busted