Report chain: when consecutive report cards exceed the failure limit the
parent now fails through transition_work_item (settlement, dependents,
manager visibility) instead of parking forever in AWAITING_MANAGER_REVIEW
behind a metadata hold no reconcile path could clear. The hold stamp
survives only as the quarantine fallback when the FAILED write does not
land, mirroring the attempt ledger's terminalize pattern.
Cursor prompt spill: one stable file per task (retries overwrite instead
of accumulating) and a self-ignoring .gitignore so workspace git never
picks up .opc/external_prompts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
On Windows, an npm-installed `claude` resolves to a .cmd shim, so
_resolve_launch_command wraps it in `cmd.exe /d /s /c ...`. cmd.exe treats a
newline inside an argument as end-of-command, silently truncating a multiline
prompt at the first line break -- the agent received only the "## Task Brief"
heading and replied that no task was included.
Detect this case in _interactive_prompt_transport and deliver the prompt over
the existing stdin channel instead. The guard requires all three of: nt
platform, a newline in the prompt, and a command that resolves to .cmd/.bat.
It reuses _resolve_windows_command_shim so the check matches the same
resolution logic that decides whether cmd.exe wrapping happens.
Also records prompt_transport_reason in the stdin metadata to distinguish this
trigger from the pre-existing oversized-prompt path.
Verified against the real claude CLI: transport flips to stdin and the CLI
confirms all prompt lines arrive intact.
Cursor-agent puts prompts on argv, so oversized company/report handoffs hit
OS ARG_MAX, crash the card as FAILED, and reconcile kept minting new Report
attempts forever. Spill large Cursor prompts to a workspace file and hold the
report chain after consecutive failures.
LZH-YS1998