@thinkingai/ae-cli 1.0.1 → 1.0.15

package/skills/ae-dataops/references/dataops-table.md

@@ -0,0 +1,122 @@
+---
+name: dataops-table
+version: 1.0.0
+description: "Data table and view management: search tables, view table details, create physical tables/views, batch create linked views. Trigger keywords: create table, table creation, view, data dictionary, table details, linked view, linkview, datatable, DDL."
+metadata:
+  requires:
+    bins: ["ae-cli"]
+---
+
+# DataOps Data Table and View Management
+
+> **Prerequisites:** Read [`ae-dataops/SKILL.md`](../SKILL.md) for general rules.
+
+Use the `dataops_datatable` subcommand to manage data tables.
+
+**Core Rules:**
+- Creating/modifying/deleting workspace task tables **must use dataops_datatable**, prohibited to use dataops_ide
+- Confirm no table with the same name exists before creation
+- When creating views or data tables, generate DDL according to **Trino DDL specifications**
+- Create task tables in DEV environment first, then PROD environment (can create simultaneously)
+
+---
+
+## Workflow A: Search and View Table Information
+
+```bash
+# Search tables in data dictionary (fuzzy match by table name/description)
+ae-cli dataops_datatable +dict_search_tables --spaceCode "${spaceCode}" --search "user" --maxResults 20
+
+# Get detailed table information (fields, DDL, data lineage)
+ae-cli dataops_datatable +get_table_detail --spaceCode "${spaceCode}" --tableName "dwd_user_info"
+
+# Paginated query of registered tables in workspace
+ae-cli dataops_datatable +list_tables_by_page --spaceCode "${spaceCode}" --search "user" --pageNum 1 --pageSize 20
+
+# Get table hierarchy by repository dimension (repo→catalog→schema→tables)
+ae-cli dataops_datatable +struct_by_repo --spaceCode "${spaceCode}"
+
+# Search system tables (event tables, user tables, dimension tables)
+ae-cli dataops_datatable +list_system_tables --spaceCode "${spaceCode}" --projectName "my_project"
+```
+
+---
+
+## Workflow B: Create Physical Table
+
+```bash
+# Step 1: Confirm no table with same name exists
+ae-cli dataops_datatable +dict_search_tables --spaceCode "${spaceCode}" --search "dwd_user_info"
+
+# Step 2: Create physical table in DEV environment (DDL must follow Trino specifications)
+ae-cli dataops_datatable +create_table --spaceCode "${spaceCode}" \
+  --ddl "CREATE TABLE dwd_user_info (user_id VARCHAR, user_name VARCHAR, age INTEGER) WITH (format = 'ORC')" \
+  --repoCode "te_etl" --catalog "hive" --schema "ws_default_dev" --confirmed true
+
+# Step 3: Create physical table in PROD environment (same DDL, change schema to product database)
+ae-cli dataops_datatable +create_table --spaceCode "${spaceCode}" \
+  --ddl "CREATE TABLE dwd_user_info (user_id VARCHAR, user_name VARCHAR, age INTEGER) WITH (format = 'ORC')" \
+  --repoCode "te_etl" --catalog "hive" --schema "ws_default_product" --confirmed true
+```
+
+---
+
+## Workflow C: Create View
+
+```bash
+# Step 1: Confirm no view with same name exists
+ae-cli dataops_datatable +dict_search_tables --spaceCode "${spaceCode}" --search "v_user_info"
+
+# Step 2: Create view (defaults to v_${source_table_name} if view name not specified)
+ae-cli dataops_datatable +create_view --spaceCode "${spaceCode}" \
+  --ddl "CREATE VIEW v_user_info AS SELECT user_id, user_name FROM hive.ws_default_dev.dwd_user_info" \
+  --repoCode "te_etl" --catalog "hive" --schema "ws_default_dev" --confirmed true
+```
+
+---
+
+## Workflow D: Batch Create Linked Views
+
+```bash
+# Step 1: List source tables available for creating linked views
+ae-cli dataops_datatable +linkview_list_source_tables --spaceCode "${spaceCode}" \
+  --srcRepoCode "te_etl" --srcCatalog "hive" --srcSchema "ws_default_hidden"
+
+# Step 2: Batch create linked views (async execution)
+ae-cli dataops_datatable +batch_create --spaceCode "${spaceCode}" \
+  --srcRepoCode "te_etl" --srcCatalog "hive" --srcSchema "ws_default_hidden" \
+  --processType 2 --batchCreationMode 1 --owner "${ownerOpenId}" \
+  --viewInfos '[{"viewName":"v_orders","srcTableName":"ta_event_123","srcTableType":"TABLE"}]' \
+  --confirmed true
+
+# Step 3: Poll batch creation status (recommend 3-5 second interval)
+# status: WAIT / RUNNING / SUCCESS / STOP
+ae-cli dataops_datatable +linkview_get_batch_status --spaceCode "${spaceCode}" --batchId "${batchId}"
+
+# View historical batch creation records
+ae-cli dataops_datatable +list_batches --spaceCode "${spaceCode}"
+```
+
+---
+
+## Command Quick Reference
+
+| Command | Purpose | Key Flags |
+|---------|---------|-----------|
+| `+dict_search_tables` | Data dictionary search | `--spaceCode` `--search` `--maxResults` |
+| `+get_table_detail` | Table details | `--spaceCode` `--tableName` |
+| `+list_tables_by_page` | Paginated list | `--spaceCode` `--search` `--pageNum` `--pageSize` |
+| `+struct_by_repo` | By repository hierarchy | `--spaceCode` `--search` |
+| `+list_system_tables` | System table list | `--spaceCode` `--projectId`/`--projectName` `--pageNum` `--pageSize` |
+| `+create_table` | Create physical table | `--spaceCode` `--ddl` `--repoCode` `--catalog` `--schema` `--confirmed` |
+| `+create_view` | Create view | `--spaceCode` `--ddl` `--repoCode` `--catalog` `--schema` `--confirmed` |
+| `+batch_create` | Batch create views | `--spaceCode` `--srcRepoCode` `--srcCatalog` `--srcSchema` `--processType` `--batchCreationMode` `--owner` `--viewInfos` `--confirmed` |
+| `+linkview_get_batch_status` | Batch creation status | `--spaceCode` `--batchId` |
+| `+list_batches` | Historical batch records | `--spaceCode` `--status` |
+
+## Parameter Notes
+
+- **schema naming**: DEV environment uses `ws_${spaceCode}_dev`, PROD environment uses `ws_${spaceCode}_product`
+- **processType**: `1`=DEV only | `2`=DEV+PROD
+- **batchCreationMode**: `1`=full sync | `2`=retry failures
+- **Table name rule**: `^[a-z][0-9a-z_]{0,127}$`

package/skills/ae-engage/SKILL.md

@@ -0,0 +1,311 @@
+---
+name: ae-engage
+version: 1.0.0
+description: "AE Engage MCP: config items, flows, channel settings, task data query, and management"
+metadata:
+  requires:
+    bins: ["ae-cli"]
+  cliHelp: "ae-cli engage --help"
+---
+
+# ae-engage
+
+AE CLI (`ae-cli`) is the command-line tool for the ThinkingEngine data analysis platform, used by AI Agents and human users.
+
+## Authentication
+
+You must authenticate before use. Authentication priority:
+
+1. Environment variable `TE_TOKEN` (highest priority, suitable for CI/scripts)
+2. Cached token (`~/.ae-cli/tokens.json`, valid for 20 hours)
+3. macOS automatically extracts it from Chrome (macOS only)
+
+### Authentication Commands
+
+```bash
+# Automatic macOS authentication (extract token from Chrome)
+ae-cli auth login
+
+# Manually set token
+ae-cli auth set-token <token>
+
+# View authentication status
+ae-cli auth status
+
+# Log out
+ae-cli auth logout
+```
+
+### Multi-environment Support
+
+```bash
+# Specify host
+ae-cli auth login --host ta-staging.example.com
+ae-cli auth set-token <token> --host ta-staging.example.com
+
+# Configure default host
+ae-cli config set defaultHost ta-staging.example.com
+```
+
+## Global Parameters
+
+All commands support the following global parameters:
+
+| Parameter | Description | Default |
+|------|------|--------|
+| `--host <host>` | AE instance address | defaultHost from config or ta.thinkingdata.cn |
+| `--format <json\|table>` | Output format | json |
+| `--jq <expr>` | jq filter expression | - |
+| `--dry-run` | Show the request only, do not execute it | false |
+| `--yes` | Skip confirmation for write operations | false |
+
+## Output Format
+
+### JSON (default)
+
+```json
+{
+  "ok": true,
+  "data": { ... }
+}
+```
+
+### Table
+
+```bash
+ae-cli engage +channel_list --project_id <YOUR_PROJECT_ID> --format table
+```
+
+### jq Filtering
+
+```bash
+ae-cli engage +channel_list --project_id <YOUR_PROJECT_ID> --jq '.'
+```
+
+## Error Handling
+
+Error output goes to stderr, in the following format:
+
+```json
+{
+  "ok": false,
+  "error": {
+    "type": "auth | api | validation | config",
+    "message": "...",
+    "hint": "..."
+  }
+}
+```
+
+Exit code: success `0`, error `1`.
+
+## Security Constraints
+
+- Commands with `risk: read` execute directly
+- Commands with `risk: write` require confirmation unless `--yes` is passed
+- Use `--dry-run` to preview the request that will be sent
+
+## Command Structure
+
+```bash
+ae-cli <domain> +<command> [flags]
+ae-cli api <METHOD> <PATH> [--params] [--data]
+```
+
+## Overview
+
+The `ae-engage` package provides Hermes Engage MCP capabilities across config items, flows, channel settings, and task data. Commands are invoked through `ae-cli engage <command>`.
+
+Typical use cases include:
+
+- Querying and managing channels, config channels, approvers, and whitelists
+- Querying task lists, task details, experiment reports, and metric reports
+- Querying config items and strategies, copying templates, and managing strategy status
+- Querying flow lists, node schemas, and flow reports, and saving or managing flows
+
+## Parameter Conventions
+
+- Use regular flags for simple parameters, for example `--project_id`, `--task_id`, and `--flow_uuid`
+- Use JSON flags for array parameters, for example `--strategy_id_list '["id1","id2"]'`
+- Use named JSON flags for object parameters, for example `--req '{...}'` and `--flow_list '[...]'`
+- Optional global parameters work the same way as in other domains, for example `--host`, `--mcp-url`, and `--dry-run`
+
+## JSON Parameter Format
+
+Common JSON flag examples:
+
+```bash
+--provider_list '["webhook","fcm"]'
+--strategy_id_list '["strategy_a","strategy_b"]'
+--flow_id_list '["flow_1","flow_2"]'
+--req '{"pageNum":1,"pageSize":20}'
+```
+
+## Common Scenarios
+
+### 1. setting
+
+```bash
+# Query the channel list
+ae-cli engage +channel_list --project_id 1
+
+# Filter by provider
+ae-cli engage +channel_list --project_id 1 --provider_list '["webhook","fcm"]'
+
+# Query config channels
+ae-cli engage +config_channel_list --project_id 1
+```
+
+### 2. task
+
+```bash
+# Query the task list
+ae-cli engage +task_list --project_id 1 --req '{"pageNum":1,"pageSize":20}'
+
+# Query task details
+ae-cli engage +task_detail --project_id 1 --task_id task_123
+
+# Query the task overview
+ae-cli engage +task_data_overview --project_id 1 --task_id task_123
+```
+
+### 3. config
+
+```bash
+# Query the config item list
+ae-cli engage +config_item_list --project_id 1
+
+# Query the strategy list
+ae-cli engage +strategy_list --project_id 1 --config_id cfg_123
+
+# Query a config item report
+ae-cli engage +config_item_trigger_report \
+  --project_id 1 --config_id cfg_123 \
+  --start_time 2026-04-01 --end_time 2026-04-07
+```
+
+### 4. flow
+
+```bash
+# Query the flow list
+ae-cli engage +flow_list --project_id 1
+
+# Query flow details
+ae-cli engage +flow_detail --project_id 1 --flow_uuid flow_uuid_123
+
+# Query the node schema
+ae-cli engage +flow_node_config_schema --node_type message_push
+```
+
+## `+save_flow` Critical Constraints
+
+When the user wants to "create a flow / generate a flow canvas / save a flow", do not treat `+save_flow` as a normal single command. You must follow the workflow below.
+
+### Required Workflow
+
+1. First confirm that the user intent is specific enough. At minimum you need:
+   - The business scenario
+   - The target users
+   - The touchpoint or delivery method
+   - Whether branching is needed, and the branching conditions
+2. Do not jump directly from natural language to `--req`. You must first organize a stable intermediate intent structure, then map it to the final `req`.
+3. Before building any condition-related nodes, you must call:
+
+```bash
+ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+```
+
+4. Before building touchpoint nodes such as `message_push`, `wechat_push`, or `webhook_push`, you must call:
+
+```bash
+ae-cli engage +channel_list --project_id <projectId>
+```
+
+5. The final `--req` for `+save_flow` must be the complete canvas request payload, not an intent description. It must contain at least:
+   - `flowName`
+   - `flowDesc`
+   - `nodeList`
+   - `edgeList`
+6. `nodeList[].config` and `edgeList[].config` must be JSON strings, not JSON objects.
+7. If `targetClusterQp` appears inside a node `config`, its value should usually also be a string produced by `JSON.stringify`, not a raw object.
+8. You must self-check before submitting:
+   - There is exactly one entry node
+   - There is at least one `exit_flow`
+   - `edge.source` and `edge.target` both reference valid nodes
+   - Any branch node `sourceBranchId` has already been declared in the upstream node `config`
+   - The whole graph is a DAG and contains no cycles
+
+### Explicitly Forbidden
+
+- Do not invent a `channelId`
+- Do not fill in branching logic when the user has not provided enough information
+- Do not submit business-semantic nodes directly as final `nodeList` nodes
+- Do not put `config` into `--req` as an object
+
+### Recommended Order
+
+```text
+User request
+-> Organize intent
+-> analysis_audience +get_cluster_definition_schema --cluster_type condition
+-> +channel_list --project_id <projectId>
+-> Build nodeList / edgeList
+-> Self-check
+-> +save_flow
+```
+
+For more detailed generation rules, consult these references first:
+
+- `references/save-flow.md`
+- `references/flow-node-config-schema.md`
+- `references/validate-flow-node-config.md`
+
+## Dry-Run Debugging
+
+```bash
+ae-cli --dry-run engage +channel_list --project_id 1
+ae-cli --dry-run engage +task_list --project_id 1 --req '{"pageNum":1,"pageSize":20}'
+ae-cli --dry-run engage +flow_list --project_id 1
+```
+
+## References
+
+More detailed single-command guidance is available in the business-oriented `references/` directory:
+
+- `references/channel-list.md`
+- `references/task-list.md`
+- `references/config-item-list.md`
+- `references/flow-list.md`
+
+This split documentation structure is easier to extend later, because commands with more complex object inputs can stay centralized in the `references/` root directory.
+
+## Command Groups
+
+### setting
+
+`+channel_list`, `+channel_detail`, `+update_channel_status`, `+delete_channel`, `+add_channel`, `+whitelist_list`, `+add_approver`, `+approver_list`, `+cancel_query_by_request_id`, `+config_channel_detail`, `+config_channel_list`, `+delete_config_channel`, `+update_config_channel_status`
+
+### task
+
+`+task_data_overview`, `+task_data_detail`, `+task_metric_detail`, `+task_experiment_report`, `+task_detail`, `+task_list`, `+task_stats`, `+manage_task`
+
+### config
+
+`+config_item_trigger_report`, `+config_item_analysis_report`, `+config_item_strategy_comparison`, `+config_item_list`, `+config_item_detail`, `+delete_config_item`, `+copy_config_template`, `+strategy_list`, `+strategy_detail`, `+manage_strategy`
+
+### flow
+
+`+save_flow`, `+flow_node_config_schema`, `+flow_detail`, `+flow_list`, `+flow_node_overview_report`, `+manage_flow`, `+flow_ab_split_node_report`, `+flow_process_report`, `+validate_flow_node_config`, `+flow_node_detail_report`, `+delete_flow`, `+modify_flow_base_info`
+
+## Date Format
+
+Commands that accept date parameters usually use `yyyy-MM-dd`, for example `--start_time 2026-04-01`.
+
+## Write Operation Reminder
+
+The following commands are write operations. Confirm that the user intent is explicit before executing them:
+
+- Channels and config channels: `+add_channel`, `+delete_channel`, `+update_channel_status`, `+delete_config_channel`, `+update_config_channel_status`
+- Strategies and config items: `+delete_config_item`, `+copy_config_template`, `+manage_strategy`
+- Flows: `+save_flow`, `+modify_flow_base_info`, `+manage_flow`, `+delete_flow`
+- Tasks: `+manage_task`

package/skills/ae-engage/references/add-approver.md

@@ -0,0 +1,24 @@
+# ae-engage +add_approver
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Batch add approvers.
+
+Mapped command: `ae-cli engage +add_approver`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--project_id` / `-p` | number | Yes | Project ID |
+| `--approvers` | json | Yes | approver open ID JSON array |
+
+## Safety Constraints
+
+This command is a **write operation** and and modifies the project approver configuration.
+
+## Examples
+
+```bash
+ae-cli engage +add_approver --project_id 1 --approvers '["ou_xxx","ou_yyy"]'
+```

package/skills/ae-engage/references/add-channel.md

@@ -0,0 +1,74 @@
+# ae-engage +add_channel
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Create a new Engage channel.
+
+Mapped command: `ae-cli engage +add_channel`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--project_id` / `-p` | number | Yes | Project ID |
+| `--req` | json | Yes | Channel creation request JSON object |
+
+## `--req` Object Fields
+
+| Field | Type | Required | Description |
+|------|------|------|------|
+| `channelType` | number | Yes | channel type |
+| `channelSubBizType` | string | Yes | channel subtype, for example `webhook`、`fcm`、`aurora` |
+| `channelName` | string | Yes | channel name |
+| `pushIdType` | string | Yes | push target ID field name |
+| `config` | string | Yes | channel config JSON string |
+| `enableTouchEvent` | number | Yes | touch event switch |
+| `eventClickName` | string | Yes | click event name |
+| `eventDeliveryName` | string | Yes | delivery event name |
+| `touchEventSource` | string | Yes | touch event source |
+
+`projectId` is automatically written into the `--req` object by the CLI, so you do not need to fill it manually. If you provide a field with the same name, the top-level `--project_id` takes precedence.
+
+## Enum Notes
+
+### `req.channelType`
+
+- `1`: `WEBHOOK`
+- `2`: `APP_PUSH`
+- `3`: `CLIENT_PUSH`
+- `4`: `WECHAT`
+- `5`: `DOU_YIN`
+
+### `req.channelSubBizType`
+
+Common values are listed below and should usually match `channelType`:
+
+- `webhook`: Webhook channel
+- `fcm`: App Push, Firebase Cloud Messaging
+- `aurora`: App Push, Aurora
+- `apns`: App Push, Apple Push Notification Service
+- `client`: Client Push
+- `wechat_mini_game`: WeChat mini game
+- `dou_yin_recommended_game_card`: Douyin recommended game card
+
+### `req.enableTouchEvent`
+
+- `0`: disable touch events
+- `1`: enable touch events
+
+## Additional Constraints
+
+- `req.config` must be a JSON string, not a JSON object.
+- `req.channelSubBizType` should match the actual channel capability; for example, when `channelType=1`, `webhook` is usually used.
+- If delivery or click callbacks are required, also check that `eventDeliveryName`, `eventClickName`, and `touchEventSource` are complete.
+
+## Safety Constraints
+
+This command is a **write operation** and creates a new channel. Check that the `--req` fields are complete before executing.
+
+## Examples
+
+```bash
+ae-cli engage +add_channel --project_id 1 \
+  --req '{"channelType":1,"channelSubBizType":"webhook","channelName":"demo","pushIdType":"user_id","config":"{}","enableTouchEvent":0,"eventClickName":"","eventDeliveryName":"","touchEventSource":""}'
+```

package/skills/ae-engage/references/approver-list.md

@@ -0,0 +1,19 @@
+# ae-engage +approver_list
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Query the project approver list.
+
+Mapped command: `ae-cli engage +approver_list`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--project_id` / `-p` | number | Yes | Project ID |
+
+## Examples
+
+```bash
+ae-cli engage +approver_list --project_id 1
+```

package/skills/ae-engage/references/cancel-query-by-request-id.md

@@ -0,0 +1,23 @@
+# ae-engage +cancel_query_by_request_id
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Cancel a running data query by requestId.
+
+Mapped command: `ae-cli engage +cancel_query_by_request_id`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--request_id` | string | Yes | Query requestId |
+
+## Safety Constraints
+
+This command is a **write operation** and cancels an existing query.
+
+## Examples
+
+```bash
+ae-cli engage +cancel_query_by_request_id --request_id 00000000-0000-0000-0000-000000000000
+```

package/skills/ae-engage/references/channel-detail.md

@@ -0,0 +1,52 @@
+# ae-engage +channel_detail
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Query the details of a single Engage channel.
+
+Mapped command: `ae-cli engage +channel_detail`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--project_id` / `-p` | number | Yes | Project ID |
+| `--channel_id` | string | Yes | channel ID |
+
+## Common enums in the response
+
+### `channelStatus`
+
+- `0`: disabled
+- `1`: enabled
+
+### `channelType`
+
+- `1`: `WEBHOOK`
+- `2`: `APP_PUSH`
+- `3`: `CLIENT_PUSH`
+- `4`: `WECHAT`
+- `5`: `DOU_YIN`
+
+### `channelSubBizType`
+
+Common values include:
+
+- `webhook`
+- `fcm`
+- `aurora`
+- `apns`
+- `client`
+- `wechat_mini_game`
+- `dou_yin_recommended_game_card`
+
+### `enableTouchEvent`
+
+- `0`: disable the touch funnel
+- `1`: enable the touch funnel
+
+## Examples
+
+```bash
+ae-cli engage +channel_detail --project_id 1 --channel_id <channel_id>
+```

package/skills/ae-engage/references/channel-list.md

@@ -0,0 +1,41 @@
+# ae-engage +channel_list
+
+> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
+
+Query the list of Engage channels in a project.
+
+Mapped command: `ae-cli engage +channel_list`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--project_id` / `-p` | number | Yes | Project ID |
+| `--provider_list` | json | No | Provider list JSON array |
+| `--channel_status` | number | No | Channel status filter |
+
+## Enum Notes
+
+### `--channel_status`
+
+- `0`: disabled
+- `1`: enabled
+
+### `--provider_list`
+
+Common provider / channelSubBizType values:
+
+- `webhook`
+- `fcm`
+- `aurora`
+- `apns`
+- `client`
+- `wechat_mini_game`
+- `dou_yin_recommended_game_card`
+
+## Examples
+
+```bash
+ae-cli engage +channel_list --project_id 1
+ae-cli engage +channel_list --project_id 1 --provider_list '["webhook","fcm"]'
+```