anthropics / anthropics/claude-code

Opus 5: completes an approved subtask detour, then stops instead of returning to the primary deliverable

Aperta
#94,043 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub
area:model bug platform:macos
Lingua principale
Python
Stelle
145k
Fork
23.1k
Metriche di merge delle PR
Metriche PR in attesa

Descrizione

## What happened

A session was given a multi-part task: write a technical document (the primary deliverable) covering a merged PR, with one section requiring evidence gathered from a production database (read-only queries).

The model spent the entire session on the evidence sub-investigation. Along the way it found a small data mismatch; the user approved a detour to file an upstream issue for it ("do that first, then continue"). The model filed the issue, reported it — and ended its turn with "I haven't written the document yet. When you want it, …", treating the detour's completion as the end of the task.

The user had to intervene: "how's the write-up going? say something — why did you obsess over a small thing for ages and forget the main line?"

## Expected

- The primary deliverable stays on top of the internal task list; an open-ended evidence sub-task is bounded by it, not the other way around.
- After a user-approved detour completes, the model returns to the main deliverable on its own instead of stopping and waiting to be re-prompted. The earlier commission was never withdrawn; completing a sub-task is not a natural end-of-turn.

## Repro shape

1. Ask for a document that requires an investigation as input (write-up + evidence section).
2. Mid-way, approve a small side fix the investigation surfaced.
3. Observe: side fix completes → turn ends; the document is never started until the user asks again.

## Environment

- Claude Code CLI on macOS, model `claude-opus-5`
- Task shape: documentation/write-up with a data-investigation dependency

Guida per i contributori

Nessuna guida per i contributori indicizzata per questo repository

Direzione di ricerca

No files or tests are named. Start by reproducing the described Claude Code CLI session shape: primary write-up, evidence investigation, then an approved side detour. Done means the agent resumes the original document after completing the detour instead of ending the turn, but locating the planning/task-state code will require project familiarity.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Valutazione

Stack tecnologico
ai-infra-agents, macos
Ambito
ai-infra-agents, cli
Tipo di issue
Bug
Difficoltà
5/5
Tempo stimato
Più di una settimana
Stato di attività
Attiva
Chiarezza
Abbastanza chiara
Idoneità per principianti
25/100

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.