@thinkingai/ae-cli 6.1.9 → 6.1.11

package/skills/ae-analysis/references/system_role_upsert.md

@@ -0,0 +1,27 @@
+# system role upsert
+
+Use when the user needs to create or update a company role and its function set.
+
+Do not use it outside the system role operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system role upsert --dry-run --company-id <company-id> --role-desc <role-desc> --function-names <function-names_json>
+ae-cli system role upsert --company-id <company-id> --role-desc <role-desc> --function-names <function-names_json> --yes
+```
+
+Capability id: `system.role.upsert`.
+
+Run `--dry-run` first, summarize the affected target and impact, then wait for explicit user confirmation before rerunning the unchanged command with global `--yes`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--role-name` | No | Existing role name for update; omit when creating. |
+| `--role-desc` | Yes | Role description. |
+| `--function-names` | Yes | Complete function-name JSON array. |

package/skills/ae-analysis/references/system_role_user_list.md

@@ -0,0 +1,22 @@
+# system role-user list
+
+Use when the user needs to list users assigned to a company role.
+
+Do not use it outside the system role-user operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system role-user list --company-id <company-id> --role-name <role-name>
+```
+
+Capability id: `system.role_user.list`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--role-name` | Yes | Role name. |

package/skills/ae-analysis/references/system_seat_list.md

@@ -0,0 +1,25 @@
+# system seat list
+
+Use when the user needs to list company seat assignments.
+
+Do not use it outside the system seat operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system seat list --company-id <company-id>
+```
+
+Capability id: `system.seat.list`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--query` | No | Optional keyword filter. |
+| `--limit` | No | Page size. Default and maximum depend on the capability schema. |
+| `--offset` | No | Zero-based result offset. |
+| `--seat-type` | No | Optional seat type. |

package/skills/ae-analysis/references/system_seat_update.md

@@ -0,0 +1,26 @@
+# system seat update
+
+Use when the user needs to assign management/view BI seats or remove seats from an explicit member set.
+
+Do not use it without first reading current seat assignments and company quota with `ae-cli system seat list`.
+
+Command:
+
+```bash
+ae-cli system seat update --dry-run --company-id <company_id> --seat-type <manage_or_view_or_empty> --open-ids '["ou_xxx"]'
+ae-cli system seat update --company-id <company_id> --seat-type <manage_or_view_or_empty> --open-ids '["ou_xxx"]' --yes
+```
+
+Capability id: `system.seat.update`.
+
+`seat-type=empty` removes seats. Run `--dry-run` first and verify additions, removals, unchanged members, and license quota impact. Wait for explicit user confirmation before rerunning the unchanged command with global `--yes`.
+
+The response uses `ok`, `data`, and `meta`. A quota conflict is not proof of a partial update; inspect the returned transactional result.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--seat-type` | Yes | `manage`, `view`, or `empty`; `empty` removes seats. |
+| `--open-ids` | Yes | Non-empty company member open-ID JSON array. |

package/skills/ae-analysis/references/system_smtp_delete.md

@@ -0,0 +1,24 @@
+# system smtp delete
+
+Use when the user needs to delete company SMTP configuration.
+
+Do not use it outside the system smtp operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system smtp delete --dry-run --company-id <company-id>
+ae-cli system smtp delete --company-id <company-id> --yes
+```
+
+Capability id: `system.smtp.delete`.
+
+Run `--dry-run` first, summarize the affected target and impact, then wait for explicit user confirmation before rerunning the unchanged command with global `--yes`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |

package/skills/ae-analysis/references/system_smtp_get.md

@@ -0,0 +1,21 @@
+# system smtp get
+
+Use when the user needs to get sanitized company SMTP configuration.
+
+Do not use it outside the system smtp operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system smtp get --company-id <company-id>
+```
+
+Capability id: `system.smtp.get`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |

package/skills/ae-analysis/references/system_smtp_test.md

@@ -0,0 +1,22 @@
+# system smtp test
+
+Use when the user needs to send one SMTP test using the saved configuration.
+
+Do not use it outside the system smtp operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system smtp test --company-id <company-id> --receiver <receiver>
+```
+
+Capability id: `system.smtp.test`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--receiver` | Yes | Test email receiver. |

package/skills/ae-analysis/references/system_smtp_upsert.md

@@ -0,0 +1,31 @@
+# system smtp upsert
+
+Use when the user needs to create or update company SMTP configuration using a protected password source.
+
+Do not use it outside the system smtp operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system smtp upsert --company-id <company-id> --server-host <server-host> --server-port <server-port> --sender-address <sender-address> --sender-name <sender-name> --password-file <chmod_600_file>
+```
+
+Capability id: `system.smtp.upsert`.
+
+Sensitive values are accepted only through a permission-protected file or stdin. Never put a secret value in argv, examples, logs, validation output, dry-run output, or the response.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--server-host` | Yes | SMTP server host. |
+| `--server-port` | Yes | SMTP server port. |
+| `--has-encrypt` | No | Encryption mode: 0, 1, or 2. |
+| `--sender-address` | Yes | Sender email address. |
+| `--sender-name` | Yes | Sender display name. |
+| `--subject-prefix` | No | Optional subject prefix. |
+| `--password-file` | No | SMTP password. Read from a local permission-protected file; one of file/stdin is required. |
+| `--password-stdin` | No | SMTP password. Read from stdin; one of file/stdin is required. |

package/skills/ae-analysis/references/system_third_party_login_disable.md

@@ -0,0 +1,25 @@
+# system third-party-login disable
+
+Use when the user needs to disable a third-party login provider.
+
+Do not use it outside the system third-party-login operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system third-party-login disable --dry-run --company-id <company-id> --login-type <login-type>
+ae-cli system third-party-login disable --company-id <company-id> --login-type <login-type> --yes
+```
+
+Capability id: `system.third_party_login.disable`.
+
+Run `--dry-run` first, summarize the affected target and impact, then wait for explicit user confirmation before rerunning the unchanged command with global `--yes`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--login-type` | Yes | Third-party login type. |

package/skills/ae-analysis/references/system_third_party_login_list.md

@@ -0,0 +1,21 @@
+# system third-party-login list
+
+Use when the user needs to list sanitized third-party login configurations.
+
+Do not use it outside the system third-party-login operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system third-party-login list --company-id <company-id>
+```
+
+Capability id: `system.third_party_login.list`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |

package/skills/ae-analysis/references/system_third_party_login_upsert.md

@@ -0,0 +1,33 @@
+# system third-party-login upsert
+
+Use when the user needs to create or update a third-party login configuration using protected secret sources.
+
+Do not use it outside the system third-party-login operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system third-party-login upsert --company-id <company_id> --login-type feishu --app-id <app_id> --app-secret-file <chmod_600_file>
+ae-cli system third-party-login upsert --company-id <company_id> --login-type dingtalk --app-id <app_id> --corp-id <corp_id> --agent-id <agent_id> --dd-scan-app-id <scan_app_id> --app-secret-file <chmod_600_file> --dd-scan-app-secret-file <chmod_600_file>
+```
+
+Capability id: `system.third_party_login.upsert`.
+
+Sensitive values are accepted only through a permission-protected file or stdin. Never put a secret value in argv, examples, logs, validation output, dry-run output, or the response.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--login-type` | Yes | Third-party login type. |
+| `--app-id` | Yes | Provider application ID. |
+| `--corp-id` | No | Provider corporation ID. |
+| `--agent-id` | No | Provider agent ID. |
+| `--dd-scan-app-id` | No | DingTalk scan-login application ID. |
+| `--app-secret-file` | No | Provider application secret. Read from a local permission-protected file; one of file/stdin is required. |
+| `--app-secret-stdin` | No | Provider application secret. Read from stdin; one of file/stdin is required. |
+| `--dd-scan-app-secret-file` | No | DingTalk scan-login application secret. Read from a local permission-protected file; the value is never accepted directly on argv. |
+| `--dd-scan-app-secret-stdin` | No | DingTalk scan-login application secret. Read from stdin; do not combine with --dd-scan-app-secret-file. |

package/skills/ae-analysis/references/system_usage_overview.md

@@ -0,0 +1,21 @@
+# system usage overview
+
+Use when the user needs to get the current company system-usage summary.
+
+Do not use it outside the system usage operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system usage overview --company-id <company-id>
+```
+
+Capability id: `system.usage.overview`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |

package/skills/ae-analysis/references/system_usage_trend_export.md

@@ -0,0 +1,44 @@
+# system usage-trend export
+
+Use when the user needs the complete usage-trend result as a cancellable gzip JSONL artifact.
+
+Do not use it for a small inline result; use `ae-cli system usage-trend query` instead.
+
+Command:
+
+```bash
+ae-cli system usage-trend export --company-id <company_id> --metric <metric> --start-time <yyyy-MM-dd> --end-time <yyyy-MM-dd> --time-granularity <day_or_week_or_month>
+```
+
+Capability id: `system.usage_trend.export`.
+
+The submit response returns the `run_id` for this exact export. Preserve it and poll:
+
+```bash
+ae-cli analysis run inspect --run-id <run_id>
+```
+
+When the run succeeds, preserve its `artifact_id` and download the same run-scoped artifact:
+
+```bash
+ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <output_path>
+```
+
+The artifact format is fixed gzip-compressed JSONL (`.jsonl.gz`); this command intentionally has no `--artifact-format`. Cancel an unfinished export with `ae-cli analysis query cancel --run-id <run_id>`.
+
+The response uses `ok`, `data`, and `meta`. Empty exported data is success when `ok=true`; preserve `request_id` and `invocation_id`.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--metric` | Yes | One supported usage metric; `apollo_token` is not implemented. |
+| `--start-time` | Yes | Inclusive start date in `yyyy-MM-dd`. |
+| `--end-time` | Yes | Inclusive end date in `yyyy-MM-dd`. |
+| `--time-granularity` | Yes | `day`, `week`, or `month`. |
+| `--scope` | No | `company` or `project`; project scope requires `--project-ids`. |
+| `--project-ids` | No | Project ID JSON array. |
+| `--data-type` | No | `all`, `event`, or `user` for project-scoped total event volume. |
+| `--request-id` | No | Caller-supplied `cli_<32 lowercase hex>` lifecycle ID; generated when omitted. |
+| `--timeout-seconds` | No | Maximum runtime, `1..21600`; default `21600`. |

package/skills/ae-analysis/references/system_usage_trend_query.md

@@ -0,0 +1,28 @@
+# system usage-trend query
+
+Use when the user needs to query a bounded company or project usage trend.
+
+Do not use it outside the system usage-trend operation or with fields absent from the inspected capability schema.
+
+Command:
+
+```bash
+ae-cli system usage-trend query --company-id <company-id> --start-time <start-time> --end-time <end-time> --metric <metric> --time-granularity <time-granularity>
+```
+
+Capability id: `system.usage_trend.query`.
+
+The response uses `ok`, `data`, and `meta`. Treat empty `data` as success when `ok=true`; preserve `request_id` and `invocation_id` when present.
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--company-id` | Yes | Company ID. |
+| `--start-time` | Yes | Inclusive ISO date/time lower bound. |
+| `--end-time` | Yes | Inclusive ISO date/time upper bound. |
+| `--metric` | Yes | Supported usage metric; apollo_token is not available. |
+| `--time-granularity` | Yes | Aggregation granularity. |
+| `--scope` | No | Aggregation scope. |
+| `--project-ids` | No | Project ID JSON array; required for project scope. |
+| `--data-type` | No | Optional event-volume data type. |

package/skills/ae-dataops/SKILL.md

@@ -89,7 +89,7 @@ You must understand the following key concepts before use, otherwise errors are
 ### Flow Lifecycle
 
 ```
-Create DEV Flow → Create/Update DEV SQL Tasks → Configure Dependencies/Schedule → Preview Release → Release to PROD → PROD Manual Execution / Operations Troubleshooting
+Create DEV Flow → Create/Update DEV SQL, Integration, or Workflow Instance Check Tasks → Configure Dependencies/Schedule → Preview Release → Release to PROD → PROD Manual Execution / Operations Troubleshooting
 ```
 
 ### CRON Format (6 fields)

package/skills/ae-dataops/references/dataops-flow-create.md

@@ -41,7 +41,7 @@ ae-cli dataops_flow +create_sql_task --spaceCode "${spaceCode}" \
 # Create task with upstream dependency
 ae-cli dataops_flow +create_sql_task --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --taskName "Export Results" \
-  --preTaskCode ${upstreamTaskCode} \
+  --preTasks "[${upstreamTaskCode},${anotherUpstreamTaskCode}]" \
   --sql "INSERT INTO ads_user SELECT * FROM dwd_user"
 ```
 
@@ -63,23 +63,40 @@ ae-cli dataops_flow +update_integration_task --spaceCode "${spaceCode}" \
 
 Use `dataops_integration +list_sync_solutions` or `+get_sync_detail` to find the `syncId` first. These commands expose workflow `OFFLINE_SYNC` tasks only; app sync tasks are not part of this flow.
 
-### Step 4: Modify SQL Task Content
+### Step 4: Create or Modify Workflow Instance Check Task
+
+`checkItems` is a flat JSON array. Every item contains only `flowCode`, `left`, `right`, and `checkTimeUnit` (`DAY`, `HOUR`, or `MINUTE`). One `AND` or `OR` relation applies to the entire array; nested groups are not supported. For the current workflow, `left` and `right` are at least `1`; for another workflow they may be `0`; `right` must not exceed `left`.
+
+```bash
+ae-cli dataops_flow +create_workflow_instance_check_task --spaceCode "${spaceCode}" \
+  --flowCode ${flowCode} --taskName "Wait for upstream workflows" \
+  --checkItems '[{"flowCode":10037355068544,"left":1,"right":1,"checkTimeUnit":"DAY"},{"flowCode":10037355068545,"left":2,"right":0,"checkTimeUnit":"HOUR"}]' \
+  --relation OR
+
+ae-cli dataops_flow +update_workflow_instance_check_task --spaceCode "${spaceCode}" \
+  --flowCode ${flowCode} --taskCode ${taskCode} \
+  --checkItems '[{"flowCode":10037355068544,"left":1,"right":1,"checkTimeUnit":"DAY"}]'
+```
+
+Create defaults are `relation=AND`, `checkInterval=5`, `checkTime=3`, `failRetryTimes=3`, `failRetryInterval=5`, and `failRetryUnit=MINUTE`. On update, omitted check scalars, dependencies, and retry fields keep their current values.
+
+### Step 5: Modify SQL Task Content
 
 ```bash
-# Update SQL task content without changing owner, remark, dependencies, retry, or timeout
+# Update SQL task content and keep dependencies and retry policy
 ae-cli dataops_flow +update_sql_task --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --taskCode ${taskCode} \
   --sql "SELECT * FROM dwd_user"
 ```
 
-### Step 5: Add Task Dependencies (DAG connections)
+### Step 6: Add Task Dependencies (DAG connections)
 
 ```bash
 ae-cli dataops_flow +add_task_relation --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --preTaskCode ${upstreamTaskCode} --taskCode ${downstreamTaskCode}
 ```
 
-### Step 6: Configure Schedule
+### Step 7: Configure Schedule
 
 ```bash
 # CRON expression for scheduled execution
@@ -93,7 +110,7 @@ ae-cli dataops_flow +save_schedule_config --spaceCode "${spaceCode}" \
 - `0 0 */4 * * ?` — Every 4 hours
 - `0 30 8 * * 1-5` — Weekdays at 8:30
 
-### Step 7: Preview Release
+### Step 8: Preview Release
 
 ```bash
 # Preview pending DEV-to-PROD release changes before publishing
@@ -101,7 +118,7 @@ ae-cli dataops_flow +preview_release_flow --spaceCode "${spaceCode}" \
   --flowCode ${flowCode}
 ```
 
-### Step 8: Release to Production and Verify
+### Step 9: Release to Production and Verify
 
 ```bash
 ae-cli dataops_flow +release_flow --spaceCode "${spaceCode}" \
@@ -130,10 +147,12 @@ ae-cli dataops_operations +get_task_instance_detail --spaceCode "${spaceCode}" \
 | Command | Purpose | Key Flags |
 |---------|---------|-----------|
 | `+create_flow` | Create DEV flow | `--spaceCode` `--flowName` `[--remark]` |
-| `+create_sql_task` | Create DEV Trino SQL task and save SQL | `--spaceCode` `--flowCode` `--taskName` `--sql` `[--preSql]` `[--postSql]` `[--preTaskCode]` `[--remark]` |
-| `+update_sql_task` | Update DEV Trino SQL task content | `--spaceCode` `--flowCode` `--taskCode` `--sql` `[--preSql]` `[--postSql]` |
-| `+create_integration_task` | Create DEV integration sync task from an existing sync solution | `--spaceCode` `--flowCode` `--taskName` `--syncId` `[--preTaskCode]` `[--remark]` |
-| `+update_integration_task` | Rebind DEV integration sync task to a sync solution | `--spaceCode` `--flowCode` `--taskCode` `--syncId` |
+| `+create_sql_task` | Create DEV Trino SQL task and save SQL | `--spaceCode` `--flowCode` `--taskName` `--sql` `[--preSql]` `[--postSql]` `[--preTasks]` `[--failRetryTimes]` `[--failRetryInterval]` `[--failRetryUnit]` `[--remark]` |
+| `+update_sql_task` | Update DEV Trino SQL task content | `--spaceCode` `--flowCode` `--taskCode` `--sql` `[--preSql]` `[--postSql]` `[--preTasks]` `[--failRetryTimes]` `[--failRetryInterval]` `[--failRetryUnit]` |
+| `+create_integration_task` | Create DEV integration sync task from an existing sync solution | `--spaceCode` `--flowCode` `--taskName` `--syncId` `[--preTasks]` `[--failRetryTimes]` `[--failRetryInterval]` `[--failRetryUnit]` `[--remark]` |
+| `+update_integration_task` | Rebind DEV integration sync task to a sync solution | `--spaceCode` `--flowCode` `--taskCode` `--syncId` `[--preTasks]` `[--failRetryTimes]` `[--failRetryInterval]` `[--failRetryUnit]` |
+| `+create_workflow_instance_check_task` | Create DEV workflow instance check task | `--spaceCode` `--flowCode` `--taskName` `--checkItems` `[--relation]` `[--checkInterval]` `[--checkTime]` `[--preTasks]` `[retry flags]` `[--remark]` |
+| `+update_workflow_instance_check_task` | Update DEV workflow instance check task | `--spaceCode` `--flowCode` `--taskCode` `--checkItems` `[--relation]` `[--checkInterval]` `[--checkTime]` `[--preTasks]` `[retry flags]` |
 | `+add_task_relation` | Add DEV dependency | `--spaceCode` `--flowCode` `--preTaskCode` `--taskCode` |
 | `+save_schedule_config` | Save DEV schedule config | `--spaceCode` `--flowCode` `--enabled` `[--cron]` |
 | `+get_task_params` | View DEV task parameter list | `--spaceCode` `--flowCode` `--taskCode` |
@@ -150,17 +169,33 @@ ae-cli dataops_operations +get_task_instance_detail --spaceCode "${spaceCode}" \
 - **Schedule config**: `+save_schedule_config` requires `--spaceCode`, `--flowCode`, and `--enabled`. `--cron` is required only when `--enabled true`; omit it when disabling scheduling. It returns `action/result/status`; `result` includes `enabled`, `flow`, `message`, and `cron` only when enabled.
 - **Release preview**: `+preview_release_flow` requires `--spaceCode` and `--flowCode`; it has no optional flags. It returns `flowCode`, `releaseStatus`, `message`, and `changes`. Each change may include `scheduleConfigChange` and `tasks`; task entries may include `changed`, `contentCompare`, and `targetTable`.
 - **Release**: `+release_flow` requires `--spaceCode` and `--flowCode`; it has no optional flags. It returns `action/result/status`; `result` includes `flowCode`, `releaseStatus`, `message`, optional `packageCode`, and optional `changes`. Each change may include `scheduleConfigChange` and `tasks`; task entries include `changed`.
-- **SQL task creation**: `+create_sql_task` requires `--spaceCode`, `--flowCode`, `--taskName`, and `--sql`; `--preSql`, `--postSql`, `--preTaskCode`, and `--remark` are optional. It returns `action/result/status`; `result` includes `flowCode`, `taskCode`, `taskName`, `taskType=TRINO_SQL`, and `sqlSaved=true`.
-- **SQL task update**: `+update_sql_task` requires `--spaceCode`, `--flowCode`, `--taskCode`, and `--sql`; `--preSql` and `--postSql` are optional and keep existing values when omitted. It returns `action/result/status`; `result` includes `sqlSaved`, `flowCode`, `taskCode`, `taskType=TRINO_SQL`, and `task`.
+- **Task dependencies**: `--preTasks` is a JSON array of upstream task codes on SQL, integration, and workflow instance check create/update commands. Omit `--preTasks` on update to preserve existing dependencies; pass `--preTasks '[]'` to clear them; pass a non-empty array to replace them.
+- **Retry policy**: The three task types accept `--failRetryTimes`, `--failRetryInterval`, and `--failRetryUnit`. Create defaults to `3`, `5`, and `MINUTE`. Update preserves every omitted retry field. `MINUTE` is the only supported unit.
+- **SQL task creation**: `+create_sql_task` requires `--spaceCode`, `--flowCode`, `--taskName`, and `--sql`; SQL hooks, dependencies, retry policy, and remark are optional. It returns `action/result/status`; `result` includes `flowCode`, `taskCode`, `taskName`, `taskType=TRINO_SQL`, and `sqlSaved=true`.
+- **SQL task update**: `+update_sql_task` requires `--spaceCode`, `--flowCode`, `--taskCode`, and `--sql`; omitted SQL hooks, dependencies, and retry fields keep existing values. It returns `action/result/status`; `result` includes `sqlSaved`, `flowCode`, `taskCode`, `taskType=TRINO_SQL`, and `task`.
 - **Task dependency**: `+add_task_relation` requires `--spaceCode`, `--flowCode`, `--preTaskCode`, and `--taskCode`. `preTaskCode` is upstream and `taskCode` is downstream. It returns `action/result/status`; `result` includes `status`, `flowCode`, `preTaskCode`, `taskCode`, and `message`.
 - **Task parameters**: `+get_task_params` requires `--spaceCode`, `--flowCode`, and `--taskCode`; it has no optional flags. It queries DEV and returns `data` as an array. Items include fields such as `paramKey`, `paramType`, `paramDataType`, `paramFrom`, and built-in flags like `isBd`.
-- **Integration task creation**: `+create_integration_task` requires `--spaceCode`, `--flowCode`, `--taskName`, and `--syncId`; `--preTaskCode` and `--remark` are optional. It returns `action/result/status`; `result` includes `syncTaskSaved`, `flowCode`, `taskCode`, `taskName`, `taskType=OFFLINE_SYNC`, `syncId`, and `nextAction`.
-- **SQL task dependencies**: Use optional `--preTaskCode` to create one upstream dependency with the task. Use `+add_task_relation` for additional DAG dependencies.
+- **Integration task creation**: `+create_integration_task` requires `--spaceCode`, `--flowCode`, `--taskName`, and `--syncId`; dependencies, retry policy, and remark are optional. It returns `action/result/status`; `result` includes `syncTaskSaved`, `flowCode`, `taskCode`, `taskName`, `taskType=OFFLINE_SYNC`, `syncId`, and `nextAction`.
+- **Workflow instance check tasks**: `checkItems` is required and replaces the complete check item list. Create defaults `relation/checkInterval/checkTime` to `AND/5/3`; update preserves omitted scalar values. This command creates `FLOW_CHECK`, not task-instance `TASK_CHECK`.
+
+## Transport Status
+
+Transition status: transitional
+
+Owning module: gaia-mcp workflow
+
+Current transport: DataOps CLI REST
+
+Gateway target: TBD after DataOps workflow Gateway schema review
+
+Review after: 2026-10-27
+
+Exit condition: Migrate or remove these one-to-one commands after equivalent Capability Gateway actions are available.
 
 ## Important Notes
 
 1. **Getting flowCode**: Use `+list_flows` (see `dataops-flow-monitor` Skill)
-2. **Getting taskCode**: Returned by `+create_sql_task` / `+create_integration_task` or query via `+get_flow_overview`
+2. **Getting taskCode**: Returned by a task create command or query via `+get_flow_overview`
 3. **Release Impact**: Submits current DEV changes to PROD; released schedule/config applies to future PROD runs
 4. **SQL Validation**: Recommended to validate before saving TRINO_SQL tasks
 5. **Cannot create circular dependencies**