@thinkingai/ae-cli 1.0.28 → 6.0.16-1

package/skills/ae-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: ae-agent
 version: 1.0.0
-description: "AE Agent platform resource management CLI for adding/removing/listing/toggling custom models, MCP servers, Skills, and uploading sandbox files to the attachment library. Use when the user asks to manage Agent platform resources: add a custom model, configure an MCP server, create or toggle a Skill, or upload generated files to the attachment library for download. Must use ae-cli agent commands."
+description: "AE Agent platform resource management CLI for listing Agents, creating and updating automations, adding/removing/listing/toggling custom models, MCP servers, Skills, and uploading sandbox files to the attachment library. Use when the user asks to manage Agent platform resources or create scheduled Agent automations. Must use ae-cli agent commands."
 ---
 
 # ae-agent
@@ -14,7 +14,7 @@ ae-cli agent +<command> [options]
 
 ## Global Rules
 
-- Use this skill for Agent platform resource management: models, MCP servers, Skills, and attachments.
+- Use this skill for Agent platform resource management: Agents, automations, models, MCP servers, Skills, and attachments.
 - Read operations can run directly. Write operations require explicit user intent and normally keep the confirmation prompt unless `--yes` is passed.
 - Prefer `--dry-run` before destructive writes.
 - Only personal scope resources can be created or deleted; company/system resources are read-only in the CLI.
@@ -25,40 +25,52 @@ ae-cli agent +<command> [options]
 
 ## Commands
 
+### Agents
+
+| Command        | Risk | Purpose                                                        |
+| -------------- | ---: | -------------------------------------------------------------- |
+| `+list-agents` | read | List Agents visible to current user (personal/company/system). |
+
+### Automations
+
+| Command              |  Risk | Purpose                                |
+| -------------------- | ----: | -------------------------------------- |
+| `+create-automation` | write | Create an Agent automation task. |
+
 ### Models
 
-| Command | Risk | Purpose |
-|---|---:|---|
-| `+list-models` | read | List models visible to current user (personal/company/system). |
-| `+add-model` | write | Add a custom model (personal scope). |
-| `+del-model` | write | Delete a personal model. |
-| `+toggle-model` | write | Enable or disable a model. |
+| Command         |  Risk | Purpose                                                        |
+| --------------- | ----: | -------------------------------------------------------------- |
+| `+list-models`  |  read | List models visible to current user (personal/company/system). |
+| `+add-model`    | write | Add a custom model (personal scope).                           |
+| `+del-model`    | write | Delete a personal model.                                       |
+| `+toggle-model` | write | Enable or disable a model.                                     |
 
 ### MCP Servers
 
-| Command | Risk | Purpose |
-|---|---:|---|
-| `+list-mcps` | read | List MCP servers visible to current user. |
-| `+add-mcp` | write | Add an MCP server (personal scope). |
-| `+del-mcp` | write | Delete a personal MCP server. |
-| `+toggle-mcp` | write | Enable or disable an MCP server. |
+| Command       |  Risk | Purpose                                   |
+| ------------- | ----: | ----------------------------------------- |
+| `+list-mcps`  |  read | List MCP servers visible to current user. |
+| `+add-mcp`    | write | Add an MCP server (personal scope).       |
+| `+del-mcp`    | write | Delete a personal MCP server.             |
+| `+toggle-mcp` | write | Enable or disable an MCP server.          |
 
 ### Skills
 
-| Command | Risk | Purpose |
-|---|---:|---|
-| `+list-skills` | read | List Skills visible to current user. |
-| `+add-skill` | write | Create a custom Skill (personal scope). |
-| `+del-skill` | write | Delete a personal Skill (physical delete). |
-| `+toggle-skill` | write | Enable or disable a Skill. |
+| Command         |  Risk | Purpose                                    |
+| --------------- | ----: | ------------------------------------------ |
+| `+list-skills`  |  read | List Skills visible to current user.       |
+| `+add-skill`    | write | Create a custom Skill (personal scope).    |
+| `+del-skill`    | write | Delete a personal Skill (physical delete). |
+| `+toggle-skill` | write | Enable or disable a Skill.                 |
 
 ### Attachments
 
-| Command | Risk | Purpose |
-|---|---:|---|
-| `+list-attachments` | read | List user attachments (paginated). |
-| `+add-attachment` | write | Upload sandbox file(s) to attachment library. |
-| `+del-attachment` | write | Soft-delete an attachment. |
+| Command             |  Risk | Purpose                                       |
+| ------------------- | ----: | --------------------------------------------- |
+| `+list-attachments` |  read | List user attachments (paginated).            |
+| `+add-attachment`   | write | Upload sandbox file(s) to attachment library. |
+| `+del-attachment`   | write | Soft-delete an attachment.                    |
 
 ## Usage Examples
 
@@ -69,6 +81,33 @@ ae-cli agent +list-models
 ae-cli agent +list-models --scope personal --format table
 ```
 
+### List all visible Agents
+
+```bash
+ae-cli agent +list-agents
+ae-cli agent +list-agents --scope personal --q "daily"
+```
+
+### Create an enabled daily automation
+
+```bash
+ae-cli agent +create-automation \
+  --name "Daily AI Brief" \
+  --schedule-kind daily \
+  --time 09:00 \
+  --message "Summarize yesterday's AI news" \
+  --yes
+
+# Create but keep paused when the user explicitly asks not to enable it.
+ae-cli agent +create-automation \
+  --name "Daily AI Brief" \
+  --schedule-kind daily \
+  --time 09:00 \
+  --message "Summarize yesterday's AI news" \
+  --enabled false \
+  --yes
+```
+
 ### Add a custom model
 
 ```bash
@@ -128,7 +167,8 @@ ae-cli agent +toggle-model --id <model-cuid> --enabled false
 ## Notes
 
 - Only `personal` scope resources can be created or deleted via CLI.
-- MCP creation automatically validates server connectivity.
+- Automations are enabled by default; pass `--enabled false` only when the user explicitly asks to create or update the task without enabling it. Use `+list-automations` to find the target ID internally, but do not show automation IDs, raw JSON, or concrete detail paths in user-facing replies.
+- MCP creation does NOT validate server connectivity — an unreachable URL is accepted at create time and only fails when the agent actually calls the MCP at runtime. Double-check the URL.
 - Attachment upload supports files up to 50MB each, with a 1GB user quota.
 - Batch attachment uploads support partial success — individual file failures don't affect others.
 - Skill `--instructions @-` reads from stdin, useful for piping long instruction text.

package/skills/ae-analysis/SKILL.md

@@ -1,11 +1,12 @@
 ---
 name: ae-analysis
-version: 3.0.0
+version: 3.1.0
 description: "AE/TE/ThinkingEngine/ThinkingAI ae-cli manual for analysis-side tasks in the AE system or analysis platform: reports, dashboards, alerts, ad hoc analysis, drilldown, audience clusters, tags, tag members, metrics and metric definitions, events, properties, virtual events, virtual properties, metadata, project configuration, tracking plans, event tracking, mark times, project lists, and resource links. Use when the user asks to query, create, update, refresh, inspect, troubleshoot, govern, or manage these AE analysis assets. Must use ae-cli, read the matching references/<tool_name>.md command manual before composing commands, and never guess command names, flags, JSON payloads, project_id, resource IDs, or parameter formats."
 ---
 
 # ae-analysis
 
+> **CRITICAL - This skill is self-contained.** Use the Global AE CLI Rules below; do not require a separate shared skill for analysis-side tasks.
 > **CRITICAL - For all commands that require `project_id`, you MUST satisfy `PROJECT_ID_GATE` first (no guessing): verify the project by ID/name with `analysis_common +list_projects` only when there is no valid project context yet, when the user switches project/host/environment, or when the supplied project is ambiguous. Reuse a project already verified in the same continuous conversation and same host/environment.**
 > **CRITICAL - For write operations in this skill, you MUST complete the post-write link loop when applicable:** after success and extractable `resource_id`, call `analysis_common +get_resource_url` and return the main result + resource link (or explicit link-failure reason).
 > **CRITICAL - Before running any `+<tool_name>` command, you MUST first read the corresponding `references/<tool_name>.md`.** The reference filename always equals the command name without the leading `+`, for example `+query_adhoc` -> `references/query_adhoc.md`.
@@ -195,9 +196,102 @@ Legacy query_adhoc chain:
 3. Build QP manually from the documented schema and verified project metadata.
 4. Call `+query_adhoc`.
 
-## Tool Groups (73)
+### F. ABSOLUTE_CONTRIBUTION_ATTRIBUTION
 
-### analysis (35)
+**When attributing a metric change to dimensions, you MUST use Absolute Contribution Decomposition. Never judge the primary driver based solely on relative change percentage.**
+
+#### Problem Definition
+
+Base rate fallacy causes inaccurate attribution:
+
+| Dimension | Baseline | Comparison | Absolute Δ | Relative Δ | Contribution |
+|-----------|----------|------------|-----------|-----------|-------------|
+| A         | 1        | 5          | +4        | +400%     | **40%**     |
+| B         | 50       | 55         | +5        | +10%      | **50%**     |
+| C         | 49       | 50         | +1        | +2%       | **10%**     |
+
+Wrong: "Dimension A grew 400%, it is the main driver."
+Correct: "Dimension B contributed 50% of the absolute increase (+5), making it the primary driver."
+
+#### Algorithm
+
+##### Scenario 1: Additive Metrics
+
+Use this for count-based metrics such as DAU, event counts, and payment amounts.
+
+```
+delta_total = V_total(comparison) - V_total(baseline)
+delta_dim_i = V_dim_i(comparison) - V_dim_i(baseline)
+contribution_pct_i = delta_dim_i / delta_total * 100%
+```
+
+- Sort by `|delta_dim_i|` in descending order.
+- Do not sort by `delta_dim_i / V_dim_i(baseline)`.
+
+##### Scenario 2: Ratio / Conversion Metrics
+
+Ratio changes come from two components:
+- **Composition effect**: changes in subgroup weight.
+- **Rate effect**: changes in each subgroup's own rate.
+
+Simplified mode is the default:
+
+```
+rate_change = R_total(comparison) - R_total(baseline)
+```
+
+Report subgroup rates hierarchically and call out structural impact in the conclusion.
+
+Precise decomposition is only required when the user explicitly requests structural breakdown:
+
+```
+contribution_rate_i   = w_i(baseline) * [R_i(comparison) - R_i(baseline)]
+contribution_weight_i = [w_i(comparison) - w_i(baseline)] * R_i(baseline)
+```
+
+Where `w_i` is the subgroup's share of total users.
+
+#### Execution Workflow
+
+1. Identify metric type: additive uses Scenario 1, ratio uses Scenario 2.
+2. Fetch baseline total and dimension values with `query_adhoc` and grouped dimensions.
+3. Fetch comparison total and dimension values with the same scope.
+4. Compute `delta_dim_i` for each dimension.
+5. Compute `contribution_pct_i = delta_dim_i / delta_total * 100%`.
+6. Sort by absolute contribution magnitude and preserve sign.
+7. Present the conclusion.
+
+If the builder supports comparison mode for both periods in one query, prefer it to avoid two `query_adhoc` calls.
+
+#### Output Format
+
+```
+Core conclusion: [Metric] from [baseline] to [comparison], changed by [±][absolute] ([±][percent])
+
+Dimension contribution ranking (by absolute contribution, descending):
+1. [dimension value] -> [±][absolute delta] (contributed [xx]%), relative change [±][percent]
+2. [dimension value] -> [±][absolute delta] (contributed [xx]%), relative change [±][percent]
+...
+
+Conclusion: "[Metric] [increase/decrease] was primarily driven by [top dimension] (contributed [xx]% of the change), followed by [second dimension] ([xx]%)"
+```
+
+If any dimension shows a cross-effect, such as positive contribution but negative relative change, call it out explicitly.
+
+#### Exceptions
+
+Skip absolute contribution decomposition when:
+- The user explicitly asks for growth-rate or percentage-change ranking only.
+- The user asks for a single dimension's trend without cross-dimension comparison.
+- A dimension baseline is zero; mark it as a new dimension separately.
+
+#### Self-Check
+
+After outputting attribution results, verify that dimension contributions sum to approximately 100%. If the sum deviates from 100% by more than 5 percentage points, flag that some dimensions may be missing or data scoping may be inconsistent.
+
+## Tool Groups (79)
+
+### analysis (40)
 
 Alerts (5):
 - `+get_alert_definition_schema` ([doc](references/get_alert_definition_schema.md))
@@ -206,11 +300,12 @@ Alerts (5):
 - `+create_alert` ([doc](references/create_alert.md))
 - `+update_alert` ([doc](references/update_alert.md))
 
-Reports and Dashboards (13):
+Reports and Dashboards (17):
 - `+create_report` ([doc](references/create_report.md))
 - `+get_report_definition` ([doc](references/get_report_definition.md))
 - `+list_reports` ([doc](references/list_reports.md))
 - `+query_report_data` ([doc](references/query_report_data.md))
+- `+create_space` ([doc](references/create_space.md))
 - `+create_dashboard` ([doc](references/create_dashboard.md))
 - `+list_dashboards` ([doc](references/list_dashboards.md))
 - `+query_dashboard_detail` ([doc](references/query_dashboard_detail.md))
@@ -220,13 +315,17 @@ Reports and Dashboards (13):
 - `+list_public_access_links` ([doc](references/list_public_access_links.md))
 - `+create_public_access_link` ([doc](references/create_public_access_link.md))
 - `+update_public_access_link` ([doc](references/update_public_access_link.md))
+- `+list_bi_panels` ([doc](references/list_bi_panels.md))
+- `+get_bi_panel_detail` ([doc](references/get_bi_panel_detail.md))
+- `+query_bi_panel_data` ([doc](references/query_bi_panel_data.md))
 
-Model Analysis (10):
+Model Analysis (11):
 - `+build_event_analysis_qp` ([doc](references/build_event_analysis_qp.md))
 - `+build_retention_analysis_qp` ([doc](references/build_retention_analysis_qp.md))
 - `+build_funnel_analysis_qp` ([doc](references/build_funnel_analysis_qp.md))
 - `+build_prop_analysis_qp` ([doc](references/build_prop_analysis_qp.md))
 - `+query_adhoc` ([doc](references/query_adhoc.md))
+- `+cancel_query` ([doc](references/cancel_query.md))
 - `+drilldown_users` ([doc](references/drilldown_users.md))
 - `+drilldown_user_events` ([doc](references/drilldown_user_events.md))
 - `+create_result_cluster` ([doc](references/create_result_cluster.md))
@@ -266,7 +365,7 @@ Schema Definitions (2):
 - `+get_cluster_definition_schema` ([doc](references/get_cluster_definition_schema.md))
 - `+get_tag_definition_schema` ([doc](references/get_tag_definition_schema.md))
 
-### analysis_meta (20)
+### analysis_meta (23)
 
 Metadata and Governance (10):
 - `+list_events` ([doc](references/list_events.md))
@@ -293,7 +392,8 @@ Project and Tracking (11):
 - `+list_project_mark_times` ([doc](references/list_project_mark_times.md))
 - `+delete_project_mark_times` ([doc](references/delete_project_mark_times.md))
 
-Entity Catalog (1):
+Entity Catalog (2):
+- `+create_entity` ([doc](references/create_entity.md))
 - `+list_entities` ([doc](references/list_entities.md))
 
 ### analysis_common (2)
@@ -316,4 +416,4 @@ npm run verify:analysis-common-tools
 
 ## Reference Docs
 
-See the unified `references/` directory (73 command docs total).
+See the unified `references/` directory (79 command docs total).

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

@@ -0,0 +1,39 @@
+# analysis +cancel_query (cancel MCP query)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Query lifecycle**
+
+## Use Cases
+- Cancel a running MCP query when the user asks to stop waiting.
+- Cancel a query when the caller or agent timed out before the query returned but it may still be running on the server.
+- Cancel a query by the same `requestId` that was supplied to or returned by a previous query command.
+- For proactive cancellation, pass `requestId` to the query tool before starting it, then call `cancel_query` with the same value if you stop waiting.
+- If a query returns `fetch failed`, hits an HTTP timeout, or the caller stops waiting, the backend query may still be running; call `+cancel_query --request_id <same value>` with the preset `requestId`.
+- auto-generated requestId is not available when the HTTP request fails before a response, so preset `requestId` before any query that may exceed the CLI/MCP HTTP timeout.
+
+## Command
+```bash
+ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef --yes
+ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef --reason "agent timeout" --yes
+ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--request_id` | Yes | Request ID returned by a query tool in `metadata.requestId`, or the requestId supplied before starting the query. It must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. |
+| `--reason` | No | Optional cancellation reason. Default: `MCP_CANCEL_QUERY_TOOL`. |
+
+## Decision Rules
+- This is a write operation. Use `--yes` only when the user clearly asked to cancel or stop a running query.
+- The request must belong to the current MCP user. Otherwise the service returns `REQUEST_NOT_FOUND_OR_NOT_OWNED`.
+- Do not invent a request ID. Use the ID from the query response or the ID explicitly supplied to the original query.
+- This command cancels by request ID only. It does not cancel by SQL text, report ID, dashboard ID, BI panel ID, run ID, or tool call ID.
+- For query commands that expose `--request_id`, prefer supplying a stable ID before execution using `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`, so proactive cancellation does not depend on waiting for the response metadata.
+- For query commands that may exceed the CLI/MCP HTTP timeout, preset `--request_id`; if `fetch failed`, HTTP timeout, or caller timeout happens, immediately call `+cancel_query --request_id <same value> --yes`.
+- For commands that do not expose caller-supplied `request_id`, cancel only if the response includes a request ID.
+
+## Next Steps on Failure
+- If `REQUEST_NOT_FOUND_OR_NOT_OWNED` appears, verify the request ID, user identity, host, and whether the original query already finished.
+- If cancellation succeeds but the UI still shows stale data, refresh the query status/result surface rather than sending another cancel blindly.

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

@@ -31,7 +31,7 @@ Domain: **Model analysis**
 ## Command
 ```bash
 ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]'
-ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --page_num 1 --page_size 20
+ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --page_num 1 --page_size 20 --request_id mcp_bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
 ae-cli analysis +drilldown_user_events --dry-run
 ```
 
@@ -55,13 +55,15 @@ ae-cli analysis +drilldown_user_events --dry-run
 | `--entity_value` | No | Optional entity value for multi-entity scenarios |
 | `--use_cache` | No | Whether to use cache. Default: true |
 | `--page_num` | No | Start page number, default 1 |
-| `--page_size` | No | Page size. Default: 1000, maximum: 100000 |
+| `--page_size` | No | Page size. Default: 1000, maximum: 10000 |
+| `--request_id` | No | Optional unique request ID used for tracking and cancellation. If provided, it must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. For long-running or cancelable queries, provide this before starting the query so it can be cancelled later with `+cancel_query --request_id <same value>`, even if the caller stops waiting before the tool returns. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running. The auto-generated requestId is not available when the HTTP request fails before a response, so preset `requestId` is required for proactive cleanup. Generated automatically if omitted. The response `metadata.requestId` can also be passed to `cancel_query` when the query is no longer needed. |
 | `--timeout_minutes` | No | Query timeout in minutes |
 
 ## Decision Rules
 - `user_id` / `event_names` / `target_dates` must come from the previous step result and must not be constructed out of thin air.
 - On the first run, start with only the required parameters (`--project_id`,`--user_id`,`--event_names`,`--target_dates`), and add optional parameters after confirming the path works.
 - Wrap JSON parameters in single quotes (for example `--event_names '[]'`, `--target_dates '[]'`) to avoid shell escaping issues.
+- For long-running or cancelable drilldowns, supply your own `--request_id` before starting so `+cancel_query` can cancel by the same ID if the caller or user stops waiting. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running; call `+cancel_query --request_id <same value>` with the preset ID. The auto-generated requestId is not available when the HTTP request fails before a response. The value must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`.
 - For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
 
 ## Next Steps on Failure

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

@@ -30,7 +30,7 @@ Domain: **Model Analysis**
 ## Commands
 ```bash
 ae-cli analysis +drilldown_users --project_id <project_id> --model_type event --qp '{}'
-ae-cli analysis +drilldown_users --project_id <project_id> --model_type retention --qp '{}' --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo --limit 10 --offset 0
+ae-cli analysis +drilldown_users --project_id <project_id> --model_type retention --qp '{}' --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo --limit 10 --offset 0 --request_id mcp_cccccccccccccccccccccccccccccccc
 ae-cli analysis +drilldown_users --dry-run
 ```
 
@@ -55,14 +55,16 @@ ae-cli analysis +drilldown_users --dry-run
 | `--include_total` | No | Whether to query users from the total row. Default: false |
 | `--relation_val` | No | Relation value used in relation analysis scenarios |
 | `--use_cache` | No | Whether to use cache. Default: true |
-| `--limit` | No | Optional limit. Default: 1000, maximum: 100000. |
+| `--limit` | No | Optional limit. Default: 1000, maximum: 10000. |
 | `--offset` | No | Optional offset. Default: 0. |
+| `--request_id` | No | Optional unique request ID used for tracking and cancellation. If provided, it must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. For long-running or cancelable queries, provide this before starting the query so it can be cancelled later with `+cancel_query --request_id <same value>`, even if the caller stops waiting before the tool returns. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running. The auto-generated requestId is not available when the HTTP request fails before a response, so preset `requestId` is required for proactive cleanup. Generated automatically if omitted. The response `metadata.requestId` can also be passed to `cancel_query` when the query is no longer needed. |
 | `--timeout_minutes` | No | Query timeout in minutes. If the query exceeds this time, it will be cancelled automatically. |
 
 ## Decision Rules
 - Drilldown positioning parameters must come from upstream analysis results and must not be fabricated.
 - `qp` must not be rewritten or "simplified"; it should remain consistent with the source analysis.
 - For pagination, use `--limit` and `--offset` together. Default limit is 1000, maximum 100000.
+- For long-running or cancelable drilldowns, supply your own `--request_id` before starting so `+cancel_query` can cancel by the same ID if the caller or user stops waiting. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running; call `+cancel_query --request_id <same value>` with the preset ID. The auto-generated requestId is not available when the HTTP request fails before a response. The value must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`.
 - For the first run, it is recommended to pass only the required parameters (`--project_id`, `--model_type`, `--qp`) and add optional parameters after confirming the chain works.
 - Wrap JSON parameters in single quotes (for example `--qp '{}'`, `--drilldown_groups '{}'`) to avoid shell escaping issues.
 - When dates/time ranges are involved, validate with a short range first and then expand gradually.

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

@@ -0,0 +1,35 @@
+# analysis +get_bi_panel_detail (read BI panel structure)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **BI panel management**
+
+## Use Cases
+- Read a BI panel's released structure without querying data.
+- Inspect pages, queryable charts, summary page metadata, dashboard-level parameter controls, dashboard-level permission controls, and page chart filter controls.
+- Get `pageKey`, `chartId`, `defaultColumns`, and control schemas needed by `+query_bi_panel_data`.
+
+## Command
+```bash
+ae-cli analysis +get_bi_panel_detail --project_id <project_id> --panel_id <panel_id>
+ae-cli analysis +get_bi_panel_detail --project_id <project_id> --panel_id <panel_id> --fields '["basic","pages","charts","parameterControls","permissionControls","chartFilterControls","summary"]'
+ae-cli analysis +get_bi_panel_detail --project_id <project_id> --panel_id <panel_id> --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--panel_id` | Yes | BI panel ID returned by `+list_bi_panels` |
+| `--fields` / `-f` | No | Optional detail sections. Supported values: `basic`, `pages`, `charts`, `parameterControls`, `permissionControls`, `chartFilterControls`, `summary`. |
+
+## Decision Rules
+- This command reads the released BI panel version only. It does not expose version selection.
+- Use `charts` and the three control sections when preparing `+query_bi_panel_data`.
+- `parameterControls` are dashboard-level parameter controls and keep single-value semantics.
+- `permissionControls` are dashboard-level permission control values. Their `allowedValues` are hints, not an MCP-side whitelist.
+- `chartFilterControls` are page-level filter controls and apply only to their `boundChartIds`. Some filters are stored as `pageCharts` components and are returned as non-queryable filter controls.
+- Do not infer internal fields such as `paramList`, `permissionFilters`, `visualCfg`, `whereList`, `field`, `columnName`, `userId`, or `openId`.
+
+## Recommended Chaining
+- `+list_bi_panels` -> `+get_bi_panel_detail` -> `+query_bi_panel_data`

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

@@ -25,7 +25,7 @@ ae-cli analysis +list_alerts --dry-run
 |---|---|---|
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against alert names; if omitted, all alerts are returned. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 ## Decision Rules

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

@@ -0,0 +1,35 @@
+# analysis +list_bi_panels (list BI panels)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **BI panel management**
+
+## Use Cases
+- Discover BI panels accessible to the current MCP user in a project.
+- Search BI panels by name before asking for structure or data.
+- Get lightweight panel metadata such as `panelId`, `name`, `pageCount`, and `hasSummary`.
+
+## Command
+```bash
+ae-cli analysis +list_bi_panels --project_id <project_id>
+ae-cli analysis +list_bi_panels --project_id <project_id> --query "history" --fields '["panelId","name","pageCount","hasSummary"]' --limit 20 --offset 0
+ae-cli analysis +list_bi_panels --project_id <project_id> --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--query` / `-q` | No | Optional keyword filter. Fuzzy matches BI panel names. |
+| `--fields` / `-f` | No | Optional returned fields. Supported values: `panelId`, `name`, `spaceId`, `spaceName`, `ownerName`, `updatedAt`, `pageCount`, `hasSummary`. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
+| `--offset` / `-o` | No | Optional page offset. Default: 0. |
+
+## Decision Rules
+- Use this before `+get_bi_panel_detail` unless the target `panel_id` is already verified in the same project and host.
+- Do not use this command to inspect pages, charts, controls, raw config, SQL, or permission rules.
+- Do not pass `userId` or `openId`; the service uses the current MCP user.
+- If no panel is found by keyword, broaden the keyword or list accessible panels and ask the user to choose.
+
+## Recommended Chaining
+- `+list_bi_panels` -> `+get_bi_panel_detail` -> `+query_bi_panel_data`

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

@@ -13,7 +13,7 @@ Domain: **Cluster Management**
 ```bash
 ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo
 ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo --property_names '["#user_id","name"]' --use_cache false
-ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo --query user_001 --fields '["#user_id","name"]' --limit 20 --offset 0
+ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo --query user_001 --fields '["#user_id","name"]' --limit 20 --offset 0 --request_id mcp_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa --timeout_minutes 8
 ae-cli analysis_audience +list_cluster_members --dry-run
 ```
 
@@ -28,10 +28,13 @@ ae-cli analysis_audience +list_cluster_members --dry-run
 | `--fields` | No | Optional return field list (JSON array). Invalid fields will fail with `INVALID_FIELDS`. |
 | `--limit` | No | Optional page size. Default: 20, max: 50. |
 | `--offset` | No | Optional page offset. Default: 0. |
+| `--request_id` | No | Optional unique request ID used for tracking and cancellation. If provided, it must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. For long-running or cancelable queries, provide this before starting the query so it can be cancelled later with `+cancel_query --request_id <same value>`, even if the caller stops waiting before the tool returns. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running. The auto-generated requestId is not available when the HTTP request fails before a response, so preset `requestId` is required for proactive cleanup. Generated automatically if omitted. The response `metadata.requestId` can also be passed to `cancel_query` when the query is no longer needed. |
+| `--timeout_minutes` | No | Query timeout in minutes. If omitted, 30 minutes is used. |
 
 ## Decision Rules
 - For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--cluster_name`) and add optional parameters after confirming the path works.
 - `--property_names` must be passed as a JSON array (e.g. `--property_names '["#user_id"]'`).
+- For long-running or cancelable member queries, supply your own `--request_id` before starting so `analysis +cancel_query` can cancel by the same ID if the caller or user stops waiting. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running; call `+cancel_query --request_id <same value>` with the preset ID. The auto-generated requestId is not available when the HTTP request fails before a response. The value must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`.
 - When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
 
 ## Next Step on Failure

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

@@ -28,7 +28,7 @@ ae-cli analysis +list_dashboards --dry-run
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against dashboard names and AI remarks; if omitted, all accessible dashboards are returned. |
 | `--fields` / `-f` | No | Optional fields to return (JSON array). Supported fields: `dashboardId`, `dashboardName`, `aiRemark`. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 ## Decision Rules

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

@@ -24,7 +24,7 @@ ae-cli analysis_meta +list_entities --dry-run
 | `--event_name` | No | Optional event name filter |
 | `--query` / `-q` | No | Optional keyword filter. Fuzzy match is applied to entityName, columnName, and columnDesc; if omitted, all accessible dashboards are returned. |
 | `--fields` / `-f` | No | Optional fields to return (JSON array). Supported fields: `entityId`, `entityName`, `columnName`, `columnDesc`, `selectType`. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 

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

@@ -28,7 +28,7 @@ ae-cli analysis_meta +list_events --dry-run
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against eventName, eventDesc, and aiRemark; if omitted, all events are returned. |
 | `--fields` / `-f` | No | Optional fields to return (JSON array). Supported fields: `eventName`, `eventDesc`, `aiRemark`, `eventTag`, `remark`. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 ## Decision Rules
 - For the first run, pass only the required parameter (`--project_id`) to confirm the path works, then add optional parameters.

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

@@ -30,7 +30,7 @@ ae-cli analysis_meta +list_metrics --dry-run
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Fuzzy match on metricName, metricDesc, metricRemark. |
 | `--fields` | No | Optional fields to return. Supported: metricId, metricName, metricDesc, metricRemark, metricMode, openId, creator, creatorLoginName, updateOpenId, updateCreator, updateLoginName, createTime, updateTime. Invalid fields cause INVALID_FIELDS error. |
-| `--limit` | No | Optional limit. Default: 20, maximum: 50. |
+| `--limit` | No | Optional limit. Default: 20, maximum: 10000. |
 | `--offset` | No | Optional offset. Default: 0. |
 
 ## Decision Rules

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

@@ -24,7 +24,7 @@ ae-cli analysis_meta +list_project_mark_times --dry-run
 | `--zone_offset` | No | Marker time zone offset |
 | `--query` / `-q` | No | Optional keyword filter. Fuzzy match on markContent. |
 | `--fields` | No | Optional fields to return. Supported: id, projectId, markTime, userZoneTime, zoneOffset, markContent, isShow, creatorName, creatorId, lastModifierName, lastModifierId, createTime, updateTime. Invalid fields cause INVALID_FIELDS error. |
-| `--limit` | No | Optional limit. Default: 20, maximum: 50. |
+| `--limit` | No | Optional limit. Default: 20, maximum: 10000. |
 | `--offset` | No | Optional offset. Default: 0. |
 
 ## Decision Rules

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

@@ -28,7 +28,7 @@ ae-cli analysis_meta +list_properties --dry-run
 | `--event_name` | No | Optional event name. If provided, only event properties available for that event are returned. |
 | `--query` / `-q` | No | Optional keyword filter. Fuzzy match is applied to propName, propDesc, and aiRemark; if omitted, all matched properties are returned. |
 | `--fields` / `-f` | No | Optional fields to return (JSON array). Supported fields: `propName`, `propDesc`, `aiRemark`, `selectType`, `tableType`, `subTableType`. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 

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

@@ -23,7 +23,7 @@ ae-cli analysis +list_public_access_links --dry-run
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Fuzzy match on shorter and remarks. |
 | `--fields` | No | Optional fields to return. Supported: id, shorter, creator, projectIdAndName, source, accessId, target, options, remarks, accessStatus, effectTime, expireTime, createTime, updateTime. Invalid fields cause INVALID_FIELDS error. |
-| `--limit` | No | Optional limit. Default: 20, maximum: 50. |
+| `--limit` | No | Optional limit. Default: 20, maximum: 10000. |
 | `--offset` | No | Optional offset. Default: 0. |
 
 ## Decision Rules

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

@@ -28,7 +28,7 @@ ae-cli analysis +list_reports --dry-run
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against report names, descriptions, and AI remarks; if omitted, all accessible reports are returned. |
 | `--fields` / `-f` | No | Optional fields to return (JSON array). Supported fields: `reportId`, `reportName`, `reportDesc`, `reportModel`, `aiRemark`. |
-| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 10000. |
 | `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 ## Decision Rules

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

@@ -13,7 +13,7 @@ Domain: **Tag Management**
 ```bash
 ae-cli analysis_audience +list_tag_members --project_id <project_id> --tag_name demo
 ae-cli analysis_audience +list_tag_members --project_id <project_id> --tag_name demo --snapshot_date 2026-04-01 --property_names '["#user_id","name"]' --use_cache false
-ae-cli analysis_audience +list_tag_members --project_id <project_id> --tag_name demo --query user_001 --fields '["#user_id","name"]' --limit 20 --offset 0
+ae-cli analysis_audience +list_tag_members --project_id <project_id> --tag_name demo --query user_001 --fields '["#user_id","name"]' --limit 20 --offset 0 --request_id mcp_bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb --timeout_minutes 8
 ae-cli analysis_audience +list_tag_members --dry-run
 ```
 
@@ -29,10 +29,13 @@ ae-cli analysis_audience +list_tag_members --dry-run
 | `--fields` | No | Optional return field list (JSON array). Invalid fields will fail with `INVALID_FIELDS`. |
 | `--limit` | No | Optional page size. Default: 20, max: 50. |
 | `--offset` | No | Optional page offset. Default: 0. |
+| `--request_id` | No | Optional unique request ID used for tracking and cancellation. If provided, it must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. For long-running or cancelable queries, provide this before starting the query so it can be cancelled later with `+cancel_query --request_id <same value>`, even if the caller stops waiting before the tool returns. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running. The auto-generated requestId is not available when the HTTP request fails before a response, so preset `requestId` is required for proactive cleanup. Generated automatically if omitted. The response `metadata.requestId` can also be passed to `cancel_query` when the query is no longer needed. |
+| `--timeout_minutes` | No | Query timeout in minutes. If omitted, 30 minutes is used. |
 
 ## Decision Rules
 - For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--tag_name`) and add optional parameters after confirming the path works.
 - `--property_names` must be passed as a JSON array (e.g. `--property_names '["#user_id"]'`).
+- For long-running or cancelable member queries, supply your own `--request_id` before starting so `analysis +cancel_query` can cancel by the same ID if the caller or user stops waiting. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running; call `+cancel_query --request_id <same value>` with the preset ID. The auto-generated requestId is not available when the HTTP request fails before a response. The value must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`.
 - When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
 
 ## Next Step on Failure