[MODEL] Agent briefs/replies refused by the user's own hook: NO REDIRECT (7 on one day)

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude ignored my instructions or configuration

What You Asked Claude to Do

Standing project instructions and a user-written hook set rules for how agents brief, message, stop and report. This report covers one refusal type, NO REDIRECT. Rows below are the day's count (7); actors: previous overseer 4, ops overseer 2 twice, a trailer worker once.

What Claude Actually Did

Agents sent new instructions to agents that were finished (DONE), in progress, or whose state the hook could not read (UNKNOWN). The user's rule: a working agent is never redirected; new direction goes to a new agent. Targets: a finished overseer twice (state DONE), a cross-host agent three times (state read as UNKNOWN once and in-play twice), a Nexus publish worker in progress, and a site worker in progress.

Expected Behavior

Check the target agent's state before messaging it, and create a new agent for new work instead of messaging one that is working.

Files Affected

None. Agent messages and tool calls only.

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Sometimes (intermittent)

Steps to Reproduce

Not a deterministic repro. The sequence is in the record above; the underlying logs are on the reporter's machine and can be summarised on request.

Claude Model

Opus

Relevant Conversation

See "What Claude Actually Did". Quotes are limited to the agents' own tool results and messages.

Impact

Medium - Extra work to undo changes

Claude Code Version

2.1.289 (as recorded in the agent session logs; the claude on PATH reports 2.1.220)

Platform

Other

Additional Context

This is one of 19 refusal types from the same day; the summary ticket links all of them. The hook is user-written and is not part of the product; the behaviour reported is what the agents sent into it.
Single-day record, 2026-10-06, all times US Eastern (Windows 11), a multi-agent session driven through a third-party agent harness; API platform is unverified. Reported as behaviour, not as a claim that Claude Code is defective.