Summary

OpenClaw repeatedly hits hard context-overflow resets on a specific group session key:

• agent:main:voltti:group:46679641

This happens even with high compaction headroom configured (reserveTokensFloor already above the recommended value), and after aggressive pruning/compaction tuning.

The user-facing fallback message suggests increasing agents.defaults.compaction.reserveTokensFloor, but in this case it is already high and does not resolve the loop.

Environment

• OpenClaw: 2026.4.8
• Provider/model: openai-codex/gpt-5.3-codex
• Channel/plugin path: Basecamp via local Voltti extension
• Host: Linux

Relevant config at time of failures:

• agents.defaults.compaction.reserveTokensFloor: 60000
• agents.defaults.compaction.reserveTokens: 60000
• agents.defaults.compaction.keepRecentTokens: 8000
• agents.defaults.bootstrapMaxChars: 6000
• agents.defaults.bootstrapTotalMaxChars: 12000
• agents.defaults.contextPruning.mode: cache-ttl

What happens

For normal inbound Basecamp events in this thread, OpenClaw repeatedly does:

1. context overflow detected (attempt 1/3)
2. auto-compaction retry
3. context overflow detected (attempt 2/3)
4. auto-compaction retry
5. context overflow detected (attempt 3/3)
6. tool result truncation attempt (sometimes)
7. hard reset/restart of session key to a new session ID

This cycle repeats across multiple newly restarted session IDs.

Representative logs

[agent] [context-overflow-diag] sessionKey=agent:main:voltti:group:46679641 ... compactionAttempts=3 ...
[agent] [context-overflow-recovery] Attempting tool result truncation ...
[agent] [context-overflow-recovery] Tool result truncation did not help: empty session
Auto-compaction failed (...). Restarting session agent:main:voltti:group:46679641 -> <new-session-id> and retrying.

Also observed repeatedly in the same failing cycle:

[agent] workspace bootstrap file AGENTS.md is 11593 chars (limit 6000); truncating ...
[agent] workspace bootstrap file TOOLS.md is 13283 chars (limit 1579); truncating ...
[agent] remaining bootstrap budget is 53 chars (<64); skipping additional bootstrap files ...

This suggests bootstrap context is re-injected on each retry path for the same failing turn.

Why this looks like a bug

1. The fallback operator hint is misleading in this scenario:
   • reserve floor is already high (60000), yet resets continue.
2. tool result truncation did not help: empty session appears in cases where failures still persist immediately after.
3. Re-injecting bootstrap context every retry may amplify failure loops in already-tight runs.

Additional related observation

In earlier failing sessions for this same key, duplicate user payloads were observed in transcript history during retries/restarts (same inbound content repeated multiple times with different message IDs/timestamps), which may contribute to avoidable token growth.

Expected behavior

• If reserve headroom is already high, fallback guidance should avoid always suggesting reserveTokensFloor as primary fix.
• Retry path should avoid repeatedly re-inflating prompt context where possible.
• If truncation reports empty session, recovery should either branch to a minimal context execution path or provide a more actionable root-cause diagnostic.

Related issues

• [Bug]: Hard context reset destroys in-progress task state with no recovery path #55366 (hard reset UX/state loss)
• Bug: Sudden Context Overflow from Large Tool Results (no preflight guard) #10694 (large tool-result overflow)
• [Bug]: Context overflow recovery skips tool-result truncation when multiple medium-sized results collectively overflow #15409 (aggregate overflow/truncation blind spot)
• webchat: single chat.send creates 3-4 duplicate user messages in session JSONL #46005 (duplicate user messages causing context bloat)
• [Bug]: Workspace bootstrap files silently truncated at 20,000 chars — agent receives incomplete context with no warning #54623 (bootstrap truncation visibility)

Request

Please investigate retry-path prompt construction and recovery behavior for cases where:

• compaction repeatedly succeeds but overflow immediately reoccurs,
• truncation says "did not help: empty session",
• and bootstrap injection appears on every retry in the same failing cycle.