Monitoring, logs, and alerts

Bailian CLI command reference for model call monitoring, call logs, and alert rules.

bl monitor, bl log, and bl alert query model call monitoring, call logs, traces, and alert rules, and manage monitoring delivery, log delivery, and alert templates.

Common flags

The following flags are available to all bl monitor, bl log, and bl alert commands and are not repeated in the command sections.

Parameter	Type	Description
--console-region <region>	string	Console gateway region, e.g. cn-beijing, ap-southeast-1
--console-site <site>	string	Console site: domestic, international
--console-switch-agent <uid>	number	Switch agent UID for delegated access
--workspace-id <id>	string	Workspace ID; can also be set with BAILIAN_WORKSPACE_ID
--output <format>	string	Output format: text, json

• Business results default to JSON even when the Profile specifies text. Pass --output text or set DASHSCOPE_OUTPUT=text for text output.
• Telemetry commands resolve the console identity of the selected workspace automatically, and use the same identity for preflight, business requests, asynchronous polling, and follow-up requests.
• bl monitor and bl alert history query the last 7 days by default; bl log queries the last hour.
• --start-time and --end-time override the default time range and accept ISO dates or millisecond timestamps.
• Commands with pagination use --max-results and --skip; when a pagination token is returned, pass next-token back unchanged.
• log audit count and log inference count use the totalCount from the corresponding list API without paginating or fetching full log content. Inference counts preserve multiple-model and multiple-API-key filters, deduplicate and query single-value combinations, and emit totals only after every query succeeds.

Monitoring

bl monitor overview

Show aggregated model call statistics, including call volume, success rate, failures, 4xx/5xx, average latency, first-token latency, and stream calls.

Usage

bl monitor overview [--days <days>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--channel <channel>] [--source <source>]

Parameter	Type	Required	Description
--days <days>	number	no	Days to look back (default: 7)
--start-time <time>	string	no	Range start; overrides --days
--end-time <time>	string	no	Range end; default: now
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated
--channel <channel>	string	no	Call channel(s), comma-separated
--source <source>	string	no	Call source(s), comma-separated

Example: Show the last 7 days of call statistics

bl monitor overview --days 7

bl monitor models

List per-model or per-API-key call statistics with server-side sorting and pagination.

Usage

bl monitor models [--days <days>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--channel <channel>] [--source <source>] [--sort-by <field>] [--order <ASC|DESC>] [--max-results <n>] [--skip <n>] [--next-token <token>]

Parameter	Type	Required	Description
--days <days>	number	no	Days to look back (default: 7)
--start-time <time>	string	no	Range start; overrides --days
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated
--channel <channel>	string	no	Call channel(s), comma-separated
--source <source>	string	no	Call source(s), comma-separated
--sort-by <field>	string	no	Sort field: modelAndWorkspaceId, callCount, callSuccessCount, callFailedCount, callFailedPercent, avgCallDuration, avgFirstTokenDuration (default: callCount)
--order <ASC|DESC>	string	no	Sort order (default: DESC)
--max-results <n>	number	no	Rows per page, 1-50 (default: 10)
--skip <n>	number	no	Rows to skip (default: 0)
--next-token <token>	string	no	Pagination token from a previous response

Example: Show the top 3 models by failure count

bl monitor models --days 7 --sort-by callFailedCount --order DESC --max-results 3

bl monitor metrics

Query time-series metrics such as call count, failures, latency percentiles, and token usage.

Usage

bl monitor metrics --metric <name>[,<name>...] [--agg <agg>] [--step <seconds>] [--days <days>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--channel <channel>] [--source <source>]

Parameter	Type	Required	Description
--metric <name>	string	yes	Metric name(s), comma-separated
--agg <agg>	string	no	Aggregation: sum, avg, max, min, p50, p95, p99, cumsum, cumavg, sum_pm (default: sum)
--step <seconds>	number	no	Data point interval: 60, 3600, or 86400 (default: auto by time range)
--days <days>	number	no	Days to look back (default: 7)
--start-time <time>	string	no	Range start; overrides --days
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated
--channel <channel>	string	no	Call channel(s), comma-separated
--source <source>	string	no	Call source(s), comma-separated

View supported metrics

Metric	Description
model_call_count	Call count
model_call_duration	Call duration
model_first_token_duration	First-token duration
model_generation_duration_per_token	Generation duration per token
model_call_failed_count	Failed calls
model_call_4xx_count	4xx calls
model_call_5xx_count	5xx calls
model_call_429_count	429 calls
model_call_data_inspection_failed_count	Content inspection failures
model_total_amount	Total usage
model_input_amount	Input usage
model_output_amount	Output usage
model_usage	Model usage
model_tps_per_request	TPS per request
model_cache_hit_percent	Cache hit rate
model_ptu_token_quota	PTU token quota
model_ptu_usage_quota	PTU used quota
model_ptu_total_tokens	PTU total tokens
model_ptu_quota	PTU quota
model_ptu_utilization	PTU utilization

Example: Query call count and failures for the last hour

bl monitor metrics --metric model_call_count,model_call_failed_count --days 1 --step 3600

• Monitoring statistics count real-time (online) inference calls only.
• When --start-time is set, it overrides --days.

bl monitor errors

Show the failure breakdown by HTTP status code and error code.

Usage

bl monitor errors [--days <days>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--channel <channel>] [--source <source>]

Parameter	Type	Required	Description
--days <days>	number	no	Days to look back (default: 7)
--start-time <time>	string	no	Range start; overrides --days
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated
--channel <channel>	string	no	Call channel(s), comma-separated
--source <source>	string	no	Call source(s), comma-separated

Example: Show the last 7 days of failures

bl monitor errors --days 7

• Each row includes httpStatusCode, errorCode, callCount, and callPercent.
• errorCode is null when no server error code is available.

bl monitor delivery status

Show monitoring delivery status: CMS service-linked role, CMS service, Prometheus instance, and the delivery switch.

Usage

bl monitor delivery status

Example: Show monitoring delivery status

bl monitor delivery status

• When not activated, returns Telemetry.SlrNotExist or cmsSlrAuthorized: false.
• Text output includes the next action to take.

bl monitor delivery enable

Activate monitoring delivery: authorize the CMS service-linked role, activate the CMS service, create a dedicated Prometheus instance, and turn on monitoring delivery for all models.

Usage

bl monitor delivery enable [--no-wait]

Parameter	Type	Required	Description
--no-wait	switch	no	Submit the activation requests and return without waiting for the instance to become ready

Example: Activate monitoring delivery

bl monitor delivery enable

• Steps: authorize SLR → activate CMS service (async polling) → create Prometheus instance (async polling) → turn on the delivery switch.
• The server throttles duplicate submissions within 30 seconds.

bl monitor delivery disable

Turn off monitoring delivery for all models.

Usage

bl monitor delivery disable

Example: Preview disabling monitoring delivery

bl monitor delivery disable --dry-run

• Only the delivery switch is turned off; the CMS service and Prometheus instance (with stored data) are kept.
• Run bl monitor delivery enable to resume delivery.

Logs

bl log status

Show log delivery status, including SLS authorization, audit and inference log services, and switches.

Usage

bl log status

Example: Show log delivery status

bl log status

• Audit and inference logs have independent switches; inference logs require the audit log to stay on.
• When not activated, returns Telemetry.SlrNotExist; run bl log audit enable first.

bl log audit list

Query model audit logs. Audit logs record call metadata, not request or response content.

Usage

bl log audit list [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--channel <channel>] [--source <source>] [--call-source <Online|Offline>] [--request-id <id>] [--status-code <type>] [--max-results <n>] [--skip <n>] [--next-token <token>]

Parameter	Type	Required	Description
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated
--channel <channel>	string	no	Call channel(s), comma-separated
--source <source>	string	no	Call source(s), comma-separated
--call-source <Online|Offline>	string	no	Inference type: Online, Offline
--request-id <id>	string	no	Exact model request ID
--status-code <type>	string	no	Status filter: SUCCESS, CLIENT_ERROR, SERVER_ERROR, CANCEL, comma-separated
--max-results <n>	number	no	Rows per page (default: 20)
--skip <n>	number	no	Rows to skip (default: 0)
--next-token <token>	string	no	Pagination token from a previous response

Example: Query audit logs for the last hour

bl log audit list --hours 1 --max-results 20

• Audit logs include call time, model, status code, latency, token usage, and request ID.
• Use inference logs for request and response content.

bl log audit get

Show a single audit log entry with its raw record.

Usage

bl log audit get --request-id <id> [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>]

Parameter	Type	Required	Description
--request-id <id>	string	yes	Model request ID (from log audit list)
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name to narrow the search

Example: Show the audit log for a specific request ID

bl log audit get --request-id 12345678-abcd-1234-abcd-123456789012 --hours 2

bl log audit count

Count audit logs in a time range, useful for estimating exports.

Usage

bl log audit count [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>]

Parameter	Type	Required	Description
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated

Example: Count audit logs for the last 24 hours

bl log audit count --hours 24

bl log audit enable

Activate audit log delivery: authorize the SLS service-linked role, initialize the SLS instance, and turn on the audit log switch for all models.

Usage

bl log audit enable [--no-wait]

Parameter	Type	Required	Description
--no-wait	switch	no	Return right after submitting, without waiting for the SLS instance

Example: Activate audit log delivery

bl log audit enable

• Audit log delivery is required before enabling inference log delivery.
• Audit logs record call metadata only.

bl log audit disable

Disable audit log delivery for all models.

Usage

bl log audit disable

Example: Preview disabling audit log delivery

bl log audit disable --dry-run

• Rejected while the inference log is still enabled; run bl log inference disable first.

bl log inference list

Query model inference logs, including request and response content.

Usage

bl log inference list [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>] [--request-id <id>] [--status-code <type>] [--call-source <Online|Offline>] [--max-results <n>] [--skip <n>]

Parameter	Type	Required	Description
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name; the inference log API accepts a single model
--api-key-id <id>	string	no	API key ID; the inference log API accepts a single ID
--request-id <id>	string	no	Exact model request ID
--status-code <type>	string	no	Status filter: SUCCESS, CLIENT_ERROR, SERVER_ERROR, CANCEL, comma-separated
--call-source <Online|Offline>	string	no	Inference type: Online, Offline
--max-results <n>	number	no	Rows per page (default: 20)
--skip <n>	number	no	Rows to skip (default: 0)

Example: Query inference logs for the last hour

bl log inference list --hours 1 --max-results 20

• Inference log delivery must be enabled first.
• The list contains summaries; use log inference get for full request and response content.

bl log inference get

Show the full request and response content of a single inference log entry.

Usage

bl log inference get --request-id <id> [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>]

Parameter	Type	Required	Description
--request-id <id>	string	yes	Model request ID (from log inference list)
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name to narrow the search

Example: Show the full inference log for a request

bl log inference get --request-id 12345678-abcd-1234-abcd-123456789012 --hours 2

bl log inference count

Count inference logs in a time range.

Usage

bl log inference count [--hours <n>] [--start-time <time>] [--end-time <time>] [--model <model>] [--api-key-id <id>]

Parameter	Type	Required	Description
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--model <model>	string	no	Model name(s), comma-separated
--api-key-id <id>	string	no	API key ID(s), comma-separated

Example: Count inference logs for the last 24 hours

bl log inference count --hours 24

• Only calls made while inference log delivery was enabled are counted.

bl log inference enable

Activate inference log delivery: authorize the SLS service-linked role, initialize the SLS instance, and turn on the inference log switch for all models.

Usage

bl log inference enable [--no-wait]

Parameter	Type	Required	Description
--no-wait	switch	no	Return right after submitting, without waiting for the SLS instance

Example: Activate inference log delivery

bl log inference enable

• Audit log delivery must be enabled first (bl log audit enable).

bl log inference disable

Disable inference log delivery for all models.

Usage

bl log inference disable

Example: Preview disabling inference log delivery

bl log inference disable --dry-run

• Only the inference log is disabled; the audit log switch is unchanged.

bl log trace list

List call traces for a model or app.

Usage

bl log trace list --resource-id <id> [--resource-type <model|app>] [--hours <n>] [--start-time <time>] [--end-time <time>] [--max-results <n>] [--skip <n>]

Parameter	Type	Required	Description
--resource-id <id>	string	yes	Model name or app ID to query
--resource-type <model|app>	string	no	Resource type: model, app (default: model)
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end
--max-results <n>	number	no	Rows per page (default: 20)
--skip <n>	number	no	Rows to skip (default: 0)

Example: List traces for a specific model

bl log trace list --resource-id qwen3.6-plus --hours 1

bl log trace get

Show the span tree of a single call trace.

Usage

bl log trace get --trace-id <id> [--resource-id <id>] [--hours <n>] [--start-time <time>] [--end-time <time>]

Parameter	Type	Required	Description
--trace-id <id>	string	yes	Trace ID (from log trace list)
--resource-id <id>	string	no	Model name or app ID to narrow the search
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end

Example: Show the span tree for a trace

bl log trace get --trace-id trace_xxx --resource-id qwen3.6-plus

bl log trace stats

Show per-resource trace statistics, including calls, token usage, and latency.

Usage

bl log trace stats [--resource-id <id>] [--resource-type <model|app>] [--hours <n>] [--start-time <time>] [--end-time <time>]

Parameter	Type	Required	Description
--resource-id <id>	string	no	Model name(s) or app ID(s), comma-separated; omit for all
--resource-type <model|app>	string	no	Resource type: model, app (default: model)
--hours <hours>	number	no	Hours to look back (default: 1)
--start-time <time>	string	no	Range start; overrides --hours
--end-time <time>	string	no	Range end

Example: Show app trace statistics for the last hour

bl log trace stats --resource-type app --hours 1

• In testing, --resource-type model returned Not support resourceType model; use --resource-type app for app traces.

Alerts

bl alert metrics

List metrics that alert rules can use and their supported aggregations.

Usage

bl alert metrics

Example: List available alert metrics

bl alert metrics

• Requires monitoring delivery to be activated (bl monitor delivery enable).
• When not activated, returns The monitoring service is not activated yet.

bl alert template list

List official and custom alert templates; pass --template-id to view one template.

Usage

bl alert template list [--template-id <id>] [--name <name>] [--source <Official|Customize>] [--max-results <n>] [--skip <n>]

Parameter	Type	Required	Description
--template-id <id>	string	no	Exact template ID
--name <name>	string	no	Fuzzy filter by template name
--source <Official|Customize>	string	no	Template source: Official, Customize; omit for all
--max-results <n>	number	no	Rows per page (default: 50)
--skip <n>	number	no	Rows to skip (default: 0)

Example: List official alert templates

bl alert template list --source Official

bl alert template create

Create a custom alert template, or copy an existing template with --from.

Usage

bl alert template create --name <name> [--condition <metric:agg:cmp:value:period>...] [--from <template-id>] [--logical-operator <or|and>]

Parameter	Type	Required	Description
--name <name>	string	yes	Template name (max 64 characters)
--condition <metric:agg:cmp:value:period>	array	no	Alert condition, repeatable 1-10 times
--from <template-id>	string	no	Copy conditions from an existing template
--logical-operator <or|and>	string	no	How multiple conditions combine (default: or)

Example: Create a failure-count alert template

bl alert template create --name failure-count --condition 'model_call_failed_count:sum:>:10:60'

• The condition format is metric:aggregation:comparison:threshold:period, e.g. model_call_failed_count:sum:>:10:60.
• When a condition contains > or <, quote the entire condition so the shell does not treat it as redirection.
• Use bl alert metrics to list metric names.

bl alert template update

Update a custom alert template, replacing the complete condition list.

Usage

bl alert template update --template-id <id> --name <name> --condition <metric:agg:cmp:value:period>... [--logical-operator <or|and>]

Parameter	Type	Required	Description
--template-id <id>	string	yes	Template ID
--name <name>	string	yes	Template name (max 64 characters)
--condition <metric:agg:cmp:value:period>	array	yes	Alert condition, repeatable 1-10 times
--logical-operator <or|and>	string	no	How multiple conditions combine (default: or)

Example: Raise the failure threshold

bl alert template update --template-id 123 --name failure-count --condition 'model_call_failed_count:sum:>:20:60'

bl alert template delete

Delete custom alert templates. Official templates cannot be deleted.

Usage

bl alert template delete --template-id <id>[,<id>...]

Parameter	Type	Required	Description
--template-id <id>	string	yes	Template ID(s), comma-separated
--yes	switch	no	Confirm this high-risk operation

Example: Preview deleting an alert template

bl alert template delete --template-id 123 --dry-run

bl alert list

List model alert rules.

Usage

bl alert list [--rule-id <id>] [--name <name>] [--enabled <true|false>] [--level <INFO|WARNING|ERROR>] [--max-results <n>] [--skip <n>] [--next-token <token>]

Parameter	Type	Required	Description
--rule-id <id>	string	no	Exact rule ID
--name <name>	string	no	Fuzzy filter by rule name
--enabled <true|false>	string	no	Filter by enabled state
--level <INFO|WARNING|ERROR>	string	no	Filter by alert level
--max-results <n>	number	no	Rows per page (default: 20)
--skip <n>	number	no	Rows to skip (default: 0)
--next-token <token>	string	no	Pagination token from a previous response

Example: List enabled alert rules

bl alert list --enabled true

bl alert create

Create a model alert rule from an alert template.

Usage

bl alert create --name <name> --template-id <id> --model <model> [--message <text>] [--level <INFO|WARNING|ERROR>] [--interval <seconds>] [--duration <seconds>] [--contact <id>] [--contact-group <id>] [--notify-window <HH:mm-HH:mm>] [--notify-days <days>] [--silence <seconds>] [--gmt-offset <offset>]

Parameter	Type	Required	Description
--name <name>	string	yes	Alert rule name (max 64 characters)
--template-id <id>	string	yes	Alert template ID (from alert template list)
--model <model>	string	yes	Model name(s) to alert on, comma-separated
--message <text>	string	no	Alert notification content (Go template); defaults to the console template
--level <INFO|WARNING|ERROR>	string	no	Alert level (default: INFO)
--interval <seconds>	number	no	Check interval (default: 60)
--duration <seconds>	number	no	How long the condition must hold; 0 = immediately (default: 60)
--contact <id>	string	no	CloudMonitor contact ID(s), comma-separated
--contact-group <id>	string	no	CloudMonitor contact group ID(s), comma-separated
--notify-window <HH:mm-HH:mm>	string	no	Daily notification window (default: 00:00-23:59)
--notify-days <days>	string	no	Days of week, 1-7, comma-separated (default: every day)
--silence <seconds>	number	no	Silence period between repeat notifications (default: never repeat)
--gmt-offset <offset>	string	no	Timezone offset for the notify window (default: +0800)

Example: Create a failure-count alert for a model

bl alert create --name high-failure-rate --template-id 123 --model qwen3.6-plus

• Alert conditions come from the template; choose one with alert template list.
• Create contacts and contact groups in the CloudMonitor console, then pass their IDs.
• Use --dry-run to inspect the request body before creating.

bl alert update

Update a model alert rule, replacing all fields.

Usage

bl alert update --rule-id <id> --name <name> --template-id <id> --model <model> [--message <text>] [--level <INFO|WARNING|ERROR>] [--interval <seconds>] [--duration <seconds>] [--contact <id>] [--contact-group <id>] [--notify-window <HH:mm-HH:mm>] [--notify-days <days>] [--silence <seconds>] [--gmt-offset <offset>]

Parameter	Type	Required	Description
--rule-id <id>	string	yes	Alert rule ID (from alert list)
--name <name>	string	yes	Alert rule name
--template-id <id>	string	yes	Alert template ID
--model <model>	string	yes	Model name(s) to alert on, comma-separated
--message <text>	string	no	Alert notification content (Go template)
--level <INFO|WARNING|ERROR>	string	no	Alert level (default: INFO)
--interval <seconds>	number	no	Check interval (default: 60)
--duration <seconds>	number	no	How long the condition must hold (default: 60)
--contact <id>	string	no	Contact ID(s), comma-separated
--contact-group <id>	string	no	Contact group ID(s), comma-separated
--notify-window <HH:mm-HH:mm>	string	no	Daily notification window
--notify-days <days>	string	no	Days of week, 1-7
--silence <seconds>	number	no	Silence period between repeat notifications
--gmt-offset <offset>	string	no	Timezone offset for the notify window

Example: Change the alert level

bl alert update --rule-id 789 --name high-failure-rate --template-id 123 --model qwen3.6-plus --level WARNING

bl alert delete

Delete model alert rules.

Usage

bl alert delete --rule-id <id>[,<id>...]

Parameter	Type	Required	Description
--rule-id <id>	string	yes	Rule ID(s), comma-separated
--yes	switch	no	Confirm this high-risk operation

Example: Preview deleting an alert rule

bl alert delete --rule-id 789 --dry-run

bl alert enable

Enable a model alert rule.

Usage

bl alert enable --rule-id <id>

Parameter	Type	Required	Description
--rule-id <id>	string	yes	Alert rule ID

Example: Enable an alert rule

bl alert enable --rule-id 789

bl alert disable

Disable a model alert rule. The rule is kept but notifications stop.

Usage

bl alert disable --rule-id <id>

Parameter	Type	Required	Description
--rule-id <id>	string	yes	Alert rule ID

Example: Disable an alert rule

bl alert disable --rule-id 789

bl alert history

List model alert history, including firing and recovered events.

Usage

bl alert history [--days <days>] [--start-time <time>] [--end-time <time>] [--rule-id <id>] [--status <ALARM|OK>] [--level <INFO|WARNING|ERROR>] [--max-results <n>] [--skip <n>] [--next-token <token>]

Parameter	Type	Required	Description
--days <days>	number	no	Days to look back (default: 7)
--start-time <time>	string	no	Range start; overrides --days
--end-time <time>	string	no	Range end
--rule-id <id>	string	no	Filter by alert rule ID
--status <ALARM|OK>	string	no	Alert state: ALARM (firing), OK (recovered)
--level <INFO|WARNING|ERROR>	string	no	Filter by highest alert level
--max-results <n>	number	no	Rows per page, 1-50 (default: 10)
--skip <n>	number	no	Rows to skip (default: 0)
--next-token <token>	string	no	Pagination token from a previous response

Example: Show alerts that fired in the last 7 days

bl alert history --days 7 --status ALARM