[BUG] Multiple background agents completing simultaneously overflow main context — API returns empty response

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

When multiple background agents (via Agent tool with run_in_background: true) complete near-simultaneously, their combined output is injected into the main conversation context in a single turn. This causes context window overflow (100%) before auto-compaction can trigger. The API then returns an empty/malformed response (HTTP 200 with no content), rendering the entire session unusable with no recovery except /clear.

There is no flow control between background agent completion and main context injection:

1. No output size budget: Each agent's full result is injected without checking whether the main context has room
2. 2. No serialization of agent results: Multiple agent completions in the same turn are batched, not queued
3. 3. Auto-compaction can't intervene mid-turn: Compaction only runs between turns, so a single oversized turn bypasses it entirely
4. 4. No truncation/summarization of agent output: Unlike TaskOutput (which truncates to 30K chars), the Agent tool injects the full transcript

What Should Happen?

Before injecting agent results, the system should:

1. Check context capacity — estimate if injection would overflow
2. 2. Run auto-compaction first if near threshold — free up space before injection
3. 3. Serialize concurrent completions — inject one agent result at a time with compaction checks between each
4. 4. Truncate or summarize if still too large after compaction

Expected: Agent results should be injected safely without overflowing the context window, even when multiple agents complete simultaneously.

Error Messages/Logs

API Error: API returned an empty or malformed response (HTTP 200) — check for a proxy or gateway intercepting the request

Steps to Reproduce

1. Start a Claude Code session with moderate context usage (~40-60%)
2. 2. Launch 2+ background agents via Agent tool with run_in_background: true, each returning substantial output (~50-100K tokens each)
3. 3. Wait for both agents to complete within a short time window
4. 4. Both agent results are injected into the main context in the same turn
5. 5. Context jumps from ~50% to 100% in one step
6. 6. API returns empty response
7. 7. Session is stuck — no recovery possible except /clear (losing all context)

In my case: two background agents (Write 13 interview cards + Rewrite 12 interview cards) completed simultaneously, each consuming ~100K tokens. The main context was overflowed instantly.

Claude Model

Not sure / Multiple models

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

2.1.177

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

This is the convergence point of several related issues that were either closed or remain unresolved:

• #17208 — Proposed output_mode parameter for Task tool, closed as "not planned"
• - #52390 — AUTOCOMPACT_PCT_OVERRIDE not triggering, still open
• - - #53065 — advisor() inflating reported input tokens, still open
• - - - #34556 — Memory loss across compactions

The fundamental problem: background agent results have no flow control when entering the main context. Sub-agents are isolated during execution, but their outputs are injected atomically on completion. When multiple agents finish at the same time, the main thread receives all their outputs in a single turn, bypassing auto-compaction entirely.

Suggested fix priority:

1. Short-term: Serialize agent result injection — inject one result at a time, run compaction checks between each
2. 2. Medium-term: Add output size budget — estimate tokens before injection, compact first if needed
3. 3. Long-term: Add output_mode parameter to Agent tool (revisit #17208)