| name | add-compact |
| description | Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only. |
Add /compact Command
Adds a /compact session command that compacts conversation history to fight context rot in long-running sessions. Uses the Claude Agent SDK's built-in /compact slash command — no synthetic system prompts.
Session contract: /compact keeps the same logical session alive. The SDK returns a new session ID after compaction (via the init system message), which the agent-runner forwards to the orchestrator as newSessionId. No destructive reset occurs — the agent retains summarized context.
Phase 1: Pre-flight
Check if src/session-commands.ts exists:
test -f src/session-commands.ts && echo "Already applied" || echo "Not applied"
If already applied, skip to Phase 3 (Verify).
Phase 2: Apply Code Changes
Merge the skill branch:
git fetch upstream skill/compact
git merge upstream/skill/compact
Note: upstream is the remote pointing to sbusso/claudeclaw. If using a different remote name, substitute accordingly.
This adds:
src/session-commands.ts (extract and authorize session commands)
src/session-commands.test.ts (unit tests for command parsing and auth)
- Session command interception in
src/index.ts (both processGroupMessages and startMessageLoop)
- Slash command handling in
agent/runner/src/index.ts
Validate
npm test
npm run build
Rebuild container
./src/runtimes/docker/build.sh
Service name: Derived from the directory name: com.claudeclaw.<dirname> (macOS) / claudeclaw-<dirname> (Linux). For example, if cwd is my-assistant, the service is com.claudeclaw.my-assistant. Determine the correct service name before running service commands below.
Restart service
launchctl kickstart -k gui/$(id -u)/com.claudeclaw
Phase 3: Verify
Integration Test
- Start ClaudeClaw in dev mode:
npm run dev
- From the main group (self-chat), send exactly:
/compact
- Verify:
- The agent acknowledges compaction (e.g., "Conversation compacted.")
- The session continues — send a follow-up message and verify the agent responds coherently
- A conversation archive is written to
groups/{folder}/conversations/ (by the PreCompact hook)
- Container logs show
Compact boundary observed (confirms SDK actually compacted)
- If
compact_boundary was NOT observed, the response says "compact_boundary was not observed"
- From a non-main group as a non-admin user, send:
@<assistant> /compact
- Verify:
- The bot responds with "Session commands require admin access."
- No compaction occurs, no container is spawned for the command
- From a non-main group as the admin (device owner /
is_from_me), send: @<assistant> /compact
- Verify:
- Compaction proceeds normally (same behavior as main group)
- While an active container is running for the main group, send
/compact
- Verify:
- The active container is signaled to close (authorized senders only — untrusted senders cannot kill in-flight work)
- Compaction proceeds via a new container once the active one exits
- The command is not dropped (no cursor race)
- Send a normal message, then
/compact, then another normal message in quick succession (same polling batch):
- Verify:
- Pre-compact messages are sent to the agent first (check container logs for two
runAgent calls)
- Compaction proceeds after pre-compact messages are processed
- Messages after
/compact in the batch are preserved (cursor advances to /compact's timestamp only) and processed on the next poll cycle
- From a non-main group as a non-admin user, send
@<assistant> /compact:
- Verify:
- Denial message is sent ("Session commands require admin access.")
- The
/compact is consumed (cursor advanced) — it does NOT replay on future polls
- Other messages in the same batch are also consumed (cursor is a high-water mark — this is an accepted tradeoff for the narrow edge case of denied
/compact + other messages in the same polling interval)
- No container is killed or interrupted
- From a non-main group (with
requiresTrigger enabled) as a non-admin user, send bare /compact (no trigger prefix):
- Verify:
- No denial message is sent (trigger policy prevents untrusted bot responses)
- The
/compact is consumed silently
- Note: in groups where
requiresTrigger is false, a denial message IS sent because the sender is considered reachable
- After compaction, verify no auto-compaction behavior — only manual
/compact triggers it
Validation on Fresh Clone
git clone <your-fork> /tmp/claudeclaw-test
cd /tmp/claudeclaw-test
claude
npm run build
npm test
./src/runtimes/docker/build.sh
Security Constraints
- Main-group or trusted/admin sender only. The main group is the user's private self-chat and is trusted (see
docs/SECURITY.md). Non-main groups are untrusted — a careless or malicious user could wipe the agent's short-term memory. However, the device owner (is_from_me) is always trusted and can compact from any group.
- No auto-compaction. This skill implements manual compaction only. Automatic threshold-based compaction is a separate concern and should be a separate skill.
- No config file. ClaudeClaw's philosophy is customization through code changes, not configuration sprawl.
- Transcript archived before compaction. The existing
PreCompact hook in the agent-runner archives the full transcript to conversations/ before the SDK compacts it.
- Session continues after compaction. This is not a destructive reset. The conversation continues with summarized context.
What This Does NOT Do
- No automatic compaction threshold (add separately if desired)
- No
/clear command (separate skill, separate semantics — /clear is a destructive reset)
- No cross-group compaction (each group's session is isolated)
- No changes to the container image, Dockerfile, or build script
Troubleshooting
- "Session commands require admin access": Only the device owner (
is_from_me) or main-group senders can use /compact. Other users are denied.
- No compact_boundary in logs: The SDK may not emit this event in all versions. Check the agent-runner logs for the warning message. Compaction may still have succeeded.
- Pre-compact failure: If messages before
/compact fail to process, the error message says "Failed to process messages before /compact." The cursor advances past sent output to prevent duplicates; /compact remains pending for the next attempt.