> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# sessions

# `openclaw sessions`

List stored conversation sessions. The command reads the per-agent `sessions.json` store file
and (when session metadata includes a transcript path) may read transcript content. With a database
session backend (`session.storage.backend: "sqlite" | "postgres"`), transcript content is served from
the configured database; with `backend: "fs-jsonl"`, transcripts are read from local JSONL files.
See [Session Management / External session storage](/concepts/session#external-session-storage).

```bash theme={"dark"}
openclaw sessions
openclaw sessions --agent work
openclaw sessions --all-agents
openclaw sessions --active 120
openclaw sessions --json
```

Scope selection:

* default: configured default agent store
* `--agent <id>`: one configured agent store
* `--all-agents`: aggregate all configured agent stores
* `--store <path>`: explicit store path (cannot be combined with `--agent` or `--all-agents`)

JSON examples:

`openclaw sessions --all-agents --json`:

```json theme={"dark"}
{
  "path": null,
  "stores": [
    { "agentId": "main", "path": "/home/user/.openclaw/agents/main/sessions/sessions.json" },
    { "agentId": "work", "path": "/home/user/.openclaw/agents/work/sessions/sessions.json" }
  ],
  "allAgents": true,
  "count": 2,
  "activeMinutes": null,
  "sessions": [
    { "agentId": "main", "key": "agent:main:main", "model": "gpt-5" },
    { "agentId": "work", "key": "agent:work:main", "model": "claude-opus-4-5" }
  ]
}
```

## Cleanup maintenance

Run maintenance now (instead of waiting for the next write cycle):

```bash theme={"dark"}
openclaw sessions cleanup --dry-run
openclaw sessions cleanup --agent work --dry-run
openclaw sessions cleanup --all-agents --dry-run
openclaw sessions cleanup --enforce
openclaw sessions cleanup --enforce --active-key "agent:main:telegram:dm:123"
openclaw sessions cleanup --json
```

`openclaw sessions cleanup` uses `session.maintenance` settings from config:

* Scope note: `openclaw sessions cleanup` maintains session stores/transcripts only. It does not prune cron run logs (`cron/runs/<jobId>.jsonl`), which are managed by `cron.runLog.maxBytes` and `cron.runLog.keepLines` in [Cron configuration](/automation/cron-jobs#configuration) and explained in [Cron maintenance](/automation/cron-jobs#maintenance).

* `--dry-run`: preview how many entries would be pruned/capped without writing.
  * In text mode, dry-run prints a per-session action table (`Action`, `Key`, `Age`, `Model`, `Flags`) so you can see what would be kept vs removed.

* `--enforce`: apply maintenance even when `session.maintenance.mode` is `warn`.

* `--active-key <key>`: protect a specific active key from disk-budget eviction.

* `--agent <id>`: run cleanup for one configured agent store.

* `--all-agents`: run cleanup for all configured agent stores.

* `--store <path>`: run against a specific `sessions.json` file.

* `--json`: print a JSON summary. With `--all-agents`, output includes one summary per store.

`openclaw sessions cleanup --all-agents --dry-run --json`:

```json theme={"dark"}
{
  "allAgents": true,
  "mode": "warn",
  "dryRun": true,
  "stores": [
    {
      "agentId": "main",
      "storePath": "/home/user/.openclaw/agents/main/sessions/sessions.json",
      "beforeCount": 120,
      "afterCount": 80,
      "pruned": 40,
      "capped": 0
    },
    {
      "agentId": "work",
      "storePath": "/home/user/.openclaw/agents/work/sessions/sessions.json",
      "beforeCount": 18,
      "afterCount": 18,
      "pruned": 0,
      "capped": 0
    }
  ]
}
```

## Claims status

View session consumer claim ledger status — what work is owed, stalled, or dead-lettered:

```bash theme={"dark"}
openclaw sessions claims status
openclaw sessions claims status --agent work
openclaw sessions claims status --json
```

The command calls the gateway RPC `sessions.claims.status`. Text output shows:

* **Consumers** table: consumer ID, lane, effect kind, enabled flag, and counts
  by status (`pending`, `claimed`, `processing`, `dlq`, `processed`).
* **Stalled leases** table: expired claims still in `claimed`/`processing` state.
* **Last sweep** timestamp (when the reconciler last ran).
* **Recent events** table: last diagnostic events from the in-memory ring buffer
  (event type, consumer ID, reason, count, timestamp).

`--json` outputs the raw RPC response:

```json theme={"dark"}
{
  "consumers": [
    {
      "consumerId": "learning-core:session.end",
      "lane": "main",
      "effectKind": "session.end",
      "enabled": true,
      "agentId": "main",
      "counts": { "pending": 3, "claimed": 0, "processing": 0, "dlq": 1, "processed": 120 }
    }
  ],
  "stalledLeases": [
    {
      "sessionId": "abc123",
      "consumerId": "learning-core:session.end",
      "lane": "main",
      "consumedMs": 45000,
      "attemptCount": 2
    }
  ],
  "lastSweepTs": 1751821200000,
  "recentEvents": [
    {
      "event": "skipped_backlog",
      "consumerId": "old-plugin:session.end",
      "reason": "backstop release, consumer disabled",
      "count": 3,
      "timestamp": 1751820900000
    }
  ]
}
```

Related:

* Operator guide: [Session Consumer Claims](/gateway/session-consumer-claims)

Related:

* Session config: [Configuration reference](/gateway/configuration-reference#session)