# WIP.subagent-reliability.md

## Status
Status: `open`
Owner: `zap`
Opened: `2026-03-13`

## Purpose
Investigate and improve subagent / ACP delegation reliability, including timeout behavior, runtime failures, and delayed/duplicate completion-event noise.

## Why now
This is the highest-leverage remaining open reliability item because it affects trust in delegation and the usability of fresh implementation runs.

## Related tasks
- `task-20260304-2215-subagent-reliability` — in progress
- `task-20260304-211216-acp-claude-codex` — open

## Known context
- Prior work already patched TUI formatting to suppress internal runtime completion context blocks.
- Upstream patch exists in `external/openclaw-upstream` on branch `fix/tui-hide-internal-runtime-context` commit `0f66a4547`.
- User explicitly wants subagent tooling reliability fixed and completion-event spam prevented.
- Fresh-session implementation discipline and monitoring thresholds were already documented locally.

## Goals for this pass
1. Establish the current failure modes with concrete evidence.
2. Separate ACP-specific failures from generic subagent/session issues.
3. Determine what is already fixed versus still broken.
4. Produce a concrete recommendation and, if feasible in one pass, implement the highest-confidence fix.
5. Update task/memory state with evidence before ending.

## Suggested investigation plan
1. Review current OpenClaw docs and local memory around subagent/ACP failures.
2. Reproduce or inspect recent failures using session/task evidence instead of guessing.
3. Check current runtime status / relevant logs / known local patches.
4. If the issue is in OpenClaw core, work in `external/openclaw-upstream/` on a focused branch.
5. Validate with the smallest reliable reproduction possible.

## Evidence gathered so far
- Fresh subagent run failed immediately with provider auth error for `zai` before any task execution.
- Current installed agent auth profiles include `openai-codex:default`, `litellm:default`, and `github-copilot:github`; there is no `zai` profile configured.
- Root cause for this immediate repro appears to be an incorrect explicit spawn model choice (`glm-5` alias → `zai/glm-5`) rather than missing auth propagation between agents.
- Next step after confirming the model-selection issue: prefer `gpt-5.4` for fresh subagent reliability/debug passes for now, per Will's instruction, and continue separating real runtime issues from operator/config mistakes.

## Constraints
- Prefer evidence over theory.
- Do not claim a fix without concrete validation.
- Keep the main session clean; use this file as the canonical baton.

## Success criteria
- Clear diagnosis of the current reliability problem(s).
- At least one of:
  - implemented fix with validation, or
  - sharply scoped next fix plan with exact evidence and files.
- `memory/2026-03-13.md` (or current daily note), `memory/tasks.json`, and this WIP updated.