# Todos

## Support subagent launches through `multi_tool_use.parallel`

A user reported that launching the repository's subagent plugin through Pi's `multi_tool_use.parallel` wrapper does not work, although equivalent launches succeed outside the wrapper in another session. Reproduce with two minimal independent subagent launches, comparing direct tool calls with wrapped calls. Capture whether failure occurs during schema validation, dispatch, asynchronous acknowledgement, task registration, or completion delivery. The wrapper must return promptly for fire-and-forget launches, preserve each subagent's name and working directory, and allow the existing automatic completion notification to deliver each result exactly once without polling. Add focused integration coverage for successful parallel launch, one-child failure, cancellation, and duplicate-delivery prevention before changing either tool.

## Investigate transient concurrent NeMo benchmark failures

During Dictate Phase 0 on 26AUG2026, repeated overlapping throwaway benchmark processes produced two one-off failures in the external `/srv/data/tools/parakeet-v3/.venv` environment:

1. `ASRModel.restore_from()` raised `MemoryError` while OmegaConf rebuilt `joint.vocabulary`. The exact clean/noisy/silence harness passed on its immediate rerun.
2. A later production-adapter check raised `ValueError: bad marshal data (invalid reference)` while importing `torch._tensor`. An immediate standalone `import torch` succeeded, and the cached `_tensor.cpython-312.pyc` passed `marshal.loads()`.

The production service serializes model loading and inference and therefore does not intentionally launch concurrent NeMo processes. Before treating concurrent workers as supported, build a repeatable cold-load stress loop, monitor process and cgroup memory, disable bytecode writes, and determine whether the failures come from NeMo/OmegaConf resource pressure or concurrent access to the external environment's bytecode cache.

## Repair nono self-diagnosis after terminal path drift

During Dictate waveform testing on 26AUG2026, every Unix socket `bind()` in `services/dictate/tests/test_unix_server.py` failed with `EACCES` or `EPERM`, including when `TMPDIR` pointed inside the repository worktree. The required diagnostic also failed:

```text
$ nono why --self --path /tmp --op readwrite
nono: Configuration parse error: sandbox state path drifted at reload: serialized resolved=/dev/pts/15, actual resolved=/dev/null
```

Reproduce in a non-interactive or reloaded Pi session, determine whether `/dev/pts/*` should be serialized by identity rather than resolved path, and make `nono why --self` report the active policy even after the controlling terminal changes. Also verify whether the Pi profile intentionally denies `AF_UNIX` socket creation in otherwise writable paths; the Dictate service loop tests need local throwaway sockets.

## Reuse the verified Dictate model during reinstall

The protocol-v2 reinstall on 26AUG2026 attempted to download the pinned model again even though the exact model already existed under `~/.local/share/pi-dictate/models/`. The sandbox correctly blocked unapproved access to `huggingface.co`, so installation had to be repeated with the installed model passed explicitly through `--model-source`.

Teach `services/dictate/install.sh` to checksum an existing model first and keep it when it matches `MODEL_SHA256`. Download only when the model is absent or invalid, while preserving the current atomic temporary-file replacement for new model sources.