Model treated "freely explore" as an unbounded licence and never proposed a budget or checkpoint

**What happened**
The task said "freely explore" six large repositories. The model treated that as licence for open-ended reading and never proposed a spend ceiling, a checkpoint, or a first-pass summary before going deeper. Roughly 400k tokens of context were consumed before the user stopped it, with no deliverable produced.

**Expected**
State an intended budget and a checkpoint at the start, and deliver a first draft before the second pass.

**What the user said**
"You don't let me do any single task."

**Repro**
Give an open-ended investigation over several large indexed repositories.

**Environment:** Claude Code CLI 2.1.270 (Claude Code), macOS, auto mode, model claude-fable-5-1, session of 2026-09-14.

Start by reproducing the reported open-ended investigation over several large indexed repositories in Claude Code CLI and observe whether the model sets a budget, checkpoint, and first-pass deliverable. Done means the behavior consistently establishes those limits and produces an initial draft before continuing into a second pass.

Written by the indexing model from the issue text.