HANDOFF.md

Purpose

Immediate baton-pass for the next fresh implementation session.

Current objective

Investigate and improve subagent / ACP delegation reliability with evidence-first debugging. The current target is to verify the newly landed upstream fix for subagent error/outcome handling and then continue on any remaining real runtime failures.

Use these state files first

WIP.subagent-reliability.md — canonical state for this pass
memory/tasks.json — task tracking for reliability items
memory/2026-03-04-subagent-delegation.md — earlier delegation context
memory/2026-03-13.md if present, otherwise append today’s evidence there
external/openclaw-upstream/ — for any core-runtime fix work

task-20260304-2215-subagent-reliability — in progress
task-20260304-211216-acp-claude-codex — open

Known truths

TUI noise suppression was already patched locally and upstreamed earlier.
User still wants actual subagent reliability improved, not just UI noise hidden.
Prior ACP failures included Claude/Codex runtime exits.
Fresh-session implementation discipline is now the expected approach for non-trivial work.
One explicit failure mode is already understood: requesting glm-5 can route into an unavailable GLM-5 provider/entitlement path in this setup.
A deeper bug was also identified: a subagent run could finish with terminal assistant errors yet still be recorded as successful with no frozen result.
An upstream patch for that error/outcome handling now exists in external/openclaw-upstream on branch fix/subagent-wait-error-outcome with targeted tests passing.

Highest-priority next actions

The success side is now verified on a real fresh gpt-5.4 subagent run.
Find and execute the smallest safe controlled-failure repro on a valid model/runtime (gpt-5.4 preferred) so we can confirm:
- a failing child run is stored as error rather than ok
- a successful child run stores a useful frozen result / announcement payload
Re-check whether ACP-specific Claude/Codex runtime failures are still reproducible after separating them from the generic subagent reporting bug.
If another core bug appears, continue in external/openclaw-upstream/ on a focused branch with targeted validation.
Update WIP + memory + tasks before ending.

Success criteria

Real-run verification of the new error/outcome fix.
Clear separation between resolved reporting bug(s) and any still-open ACP/runtime failures.
State files updated with paths, commands, and outcomes.

2.5 KiB Raw Blame History Unescape Escape