---
name: recover-subagent-yield-payload
description: "Recover or salvage subagent deliverables: missing yields, payloads misrouted to xd://report_issue, and degraded TAKEN-list echoes."
---

# Recovering subagent deliverables

Three failure modes seen with scout bulk-content tasks, in order of frequency.

## 1. Misrouted payload: scout wrote the deliverable to `xd://report_issue`
Symptom: yield summary says "delivered to `xd://report_issue`" instead of containing the content. That device is write-only (a bug-report channel); the response "Noted, thanks!" fooled the scout into thinking delivery worked.

**Salvage path (often impossible — decide fast, ≤2 probes):**
- Transcript jsonl: `~/.omp/agent/sessions/*/*/Tan-*/Tan-*.jsonl` (glob by agent id).
- Streamed `toolCall` blocks store only **partial arg fragments** of big writes (`arguments.content` is chunked/empty; `partialArgs` holds deltas). Reassembly of a 140-line write across ~100 fragment rows has never worked — if `content` on the toolCall rows is empty or truncated, **abandon salvage**.
- Only reliable in-file content: final assistant text blocks — walk rows for `message.role=="assistant"`, `content[].type=="text"`, filter lines against the delivery contract regex.

**Prevention (put in scout prompts for bulk content):** "Return the deliverable as plain lines in your FINAL OUTPUT TEXT. NEVER write it to `xd://report_issue`, files, or eval state."

## 2. Degenerate echo: scout returns the TAKEN/dedupe examples verbatim
Symptom: candidate lines repeat the "already used" examples given in the prompt, in looping blocks. Write off that batch entirely — do not re-prompt (it repeats). Cover the cluster inline yourself.

## 3. No yield at all (hung/force-stopped)
`history://<agent-id>` renders the transcript but compresses tool payloads to "1 line" — useless for payloads, fine for status. Try `write agent://<id>` with a one-line re-emit instruction ("end your turn by yielding the lines verbatim; do not re-research") exactly once; if the reply is garbage, abandon.

## Rule of thumb for bulk creative content
Scouts add value for *terminology research* (search the universe's rank/offices vocabulary, 2-5 searches), not for drafting hundreds of lines — models echo, spin variants ("dune-mentat of the X" ×14), and misroute. Pattern: scout researches → parent drafts.