@thinkingai/ae-cli 6.0.30 → 6.0.31

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

@@ -0,0 +1,25 @@
+# analysis-governance asset batch-sql-export
+
+Use when the user needs to batch export asset SQL definitions through the capability gateway.
+
+Do not use it for general asset information or query execution; it exports SQL definitions for verified asset `node_ids` as XLSX.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset batch-sql-export --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset batch-sql-export --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_batch.sql_export.
+
+Input sends project_id, payload, node_ids, reports_version, zone_offset, schedule_ui_config, dashboard_status, refresh_type, cache_config, clear_history_tag. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` is an async XLSX descriptor with `run_id`, `artifact_id`, status, and expiry fields. Reuse those IDs for lifecycle inspection and download.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-ids | No | Asset node ID JSON array; required unless provided inside payload. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,30 @@
+# analysis-governance asset-dependency list
+
+Use when the user needs to list upstream dependencies for one asset through the capability gateway.
+
+Do not use it for downstream impact or a full lineage tree; this command pages direct upstream dependencies for one resolved asset node.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset-dependency list --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset-dependency list --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_dependency.list.
+
+Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` contains dependency `items`, `total`, `operation_types`, `limit`, and `offset`; continue paging only while the observed total exceeds the current page.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
+| --query | No | Keyword filter. |
+| --searchs | No | Quick filter JSON array. |
+| --rule | No | Advanced governance Filter JSON. |
+| --limit | No | Inline page size. |
+| --offset | No | Zero-based page offset. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,30 @@
+# analysis-governance asset export
+
+Use when the user needs the complete asset usage governance result as an asynchronous JSONL artifact.
+
+Do not use it for a small interactive preview; use `asset list` when bounded inline rows are sufficient.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset export --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset export --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_usage.export.
+
+Input sends project_id, payload, query, searchs, rule, operation_type, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` is an async export descriptor with `run_id`, `artifact_id`, status, and expiry fields. Inspect and download that exact artifact rather than resubmitting the export.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --query | No | Keyword filter. |
+| --searchs | No | Quick filter JSON array. |
+| --rule | No | Advanced governance Filter JSON. |
+| --operation-type | No | Batch operation type filter. |
+| --limit | No | Inline page size. |
+| --offset | No | Zero-based page offset. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,30 @@
+# analysis-governance asset-impact list
+
+Use when the user needs to list downstream impacts for one asset through the capability gateway.
+
+Do not use it for upstream dependencies or a full lineage tree; this command pages downstream consumers affected by one asset node.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset-impact list --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset-impact list --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_impact.list.
+
+Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` contains impacted-asset `items`, `total`, `operation_types`, `limit`, and `offset`; an empty page means no downstream impact matched the filters.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
+| --query | No | Keyword filter. |
+| --searchs | No | Quick filter JSON array. |
+| --rule | No | Advanced governance Filter JSON. |
+| --limit | No | Inline page size. |
+| --offset | No | Zero-based page offset. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,25 @@
+# analysis-governance asset-lineage get
+
+Use when the user needs to get an asset lineage tree through the capability gateway.
+
+Do not use it for a flat upstream or downstream page; use `dependency-list` or `impact-list` when pagination and filtering are required.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset-lineage get --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset-lineage get --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_lineage.get.
+
+Input sends project_id, payload, node_id. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` is the lineage tree rooted at the requested `node_id`; an absent node is an asset-resolution failure, not an empty lineage result.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,30 @@
+# analysis-governance asset list
+
+Use when the user needs to list assets for usage governance through the capability gateway.
+
+Do not use it for report/dashboard result data or lineage; it lists governance rows that can be filtered or selected for later asset operations.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset list --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset list --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_usage.list.
+
+Input sends project_id, payload, query, searchs, rule, operation_type, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` contains `items`, `total`, `operation_types`, `limit`, and `offset`. An empty `items` array is a successful page with no matching governed assets.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --query | No | Keyword filter. |
+| --searchs | No | Quick filter JSON array. |
+| --rule | No | Advanced governance Filter JSON. |
+| --operation-type | No | Batch operation type filter. |
+| --limit | No | Inline page size. |
+| --offset | No | Zero-based page offset. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,30 @@
+# analysis-governance asset-query-history list
+
+Use when the user needs to list query history for one asset through the capability gateway.
+
+Do not use it to execute or inspect an analysis query; it only pages historical query usage associated with one governed asset.
+
+Command:
+
+```bash
+ae-cli analysis-governance asset-query-history list --project-id <project_id> --payload '{}'
+ae-cli analysis-governance asset-query-history list --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_query_history.list.
+
+Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` contains query-history `items`, `total`, `operation_types`, `limit`, and `offset`; treat an empty history as a successful no-usage result.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
+| --query | No | Keyword filter. |
+| --searchs | No | Quick filter JSON array. |
+| --rule | No | Advanced governance Filter JSON. |
+| --limit | No | Inline page size. |
+| --offset | No | Zero-based page offset. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -2,12 +2,12 @@
 
 Use when the user needs to list recently visited assets for the current user.
 
-Do not use this command for unrelated analysis queries, ad-hoc query construction, or MCP metadata discovery when an existing specialized command already fits the user's request.
+Do not use it as a general asset search or as a source of all accessible assets; use `asset search` for keyword discovery.
 
 Command:
 
 ```bash
-ae-cli analysis-meta asset recent-list --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset recent-list --project-id <project_id> --payload '[{"res_id":<resource_id>,"res_cat":"<resource_category>"}]'
 ae-cli analysis-meta asset recent-list --dry-run
 ```
 
@@ -15,10 +15,10 @@ Capability id: `metadata.asset.recent_list`.
 
 Input sends `project_id`, `payload`.
 
-Output is the gateway envelope. `data` contains the common-service capability result.
+Output `data.resources[]` contains the recent-view records resolved for the supplied resource identities.
 
 ## Parameters
 | Parameter | Required | Description |
 |---|---|---|
 | `--project-id` | Yes | Numeric project ID. |
-| `--payload` | Yes | Capability payload JSON. |
+| `--payload` | Yes | Non-empty JSON array of `{res_id,res_cat}` resource identities. This payload is an array, not an object. |

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

@@ -2,12 +2,12 @@
 
 Use when the user needs to search project assets by keyword.
 
-Do not use this command for unrelated analysis queries, ad-hoc query construction, or MCP metadata discovery when an existing specialized command already fits the user's request.
+Do not use it to query report/dashboard result data; it discovers asset records only.
 
 Command:
 
 ```bash
-ae-cli analysis-meta asset search --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset search --project-id <project_id> --payload '{"keyword":"revenue"}'
 ae-cli analysis-meta asset search --dry-run
 ```
 
@@ -15,10 +15,10 @@ Capability id: `metadata.asset.search`.
 
 Input sends `project_id`, `payload`.
 
-Output is the gateway envelope. `data` contains the common-service capability result.
+Output `data.resources[]` contains matching assets. A blank keyword returns an empty array rather than a full asset list.
 
 ## Parameters
 | Parameter | Required | Description |
 |---|---|---|
 | `--project-id` | Yes | Numeric project ID. |
-| `--payload` | Yes | Capability payload JSON. |
+| `--payload` | Yes | Search object. Required semantic field: non-blank `keyword`. Optional filters are `own_types` and `res_cats`; do not pass server-owned identity or pagination-test fields. |

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

@@ -0,0 +1,28 @@
+# analysis-meta asset url-get
+
+Use when the user needs to get or normalize an asset governance resource link payload through the capability gateway.
+
+Do not use it to discover assets or query asset data; resolve a real asset first, then use this command only to turn its governance identity into a link.
+
+Command:
+
+```bash
+ae-cli analysis-meta asset url-get --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset url-get --dry-run --project-id <project_id>
+```
+
+Capability id: analysis_meta.asset_url.get.
+
+Input sends project_id, payload, node_id, resource_id, resource_type, link_info. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+
+Output `data` identifies the normalized asset and returns `raw_url` plus `markdown_link` when the resource type supports a link; `status=ok` without a URL means no URL mapping was available.
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| --project-id | Yes | Numeric project ID. |
+| --node-id | No | Poseidon asset node ID. |
+| --resource-id | No | Asset business resource ID. |
+| --resource-type | No | Asset resource type. |
+| --link-info | No | link_info JSON from asset governance results. |
+| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |

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

@@ -0,0 +1,42 @@
+# Shared audience definition primitives
+
+This file contains only the primitives shared by user-cluster and user-tag semantic definitions. Read the domain-specific contract before constructing JSON:
+
+- [`user_cluster_models.md`](user_cluster_models.md) for cluster condition/SQL definitions.
+- [`user_tag_models.md`](user_tag_models.md) for tag condition/metric/first-last/SQL definitions.
+
+Use semantic snake_case only. Never send compiler or UI fields such as `filts`, `conditionType`, `eventName`, `uceCalcuSymbol`, `C030`, `columnName`, `ftv`, `tagValue`, or `taSqlVo`.
+
+## Operators
+
+`eq`, `neq`, `lt`, `lte`, `gt`, `gte`, `exists`, `not_exists`, `between`, `contains`, `not_contains`, `is_true`, `is_false`, `regex`, `not_regex`, `in_cluster`, `not_in_cluster`.
+
+## Property reference
+
+A property is either a name or a typed object:
+
+```json
+"country"
+```
+
+```json
+{"name":"country","type":"user_property"}
+```
+
+## Time range
+
+```json
+{"mode":"recent","unit":"day","value":7}
+{"mode":"previous","unit":"day","value":30}
+{"mode":"custom","start_time":"2026-07-01","end_time":"2026-07-07"}
+```
+
+## Filter group
+
+Groups use `{relation,items}`. Each item has `field`, `operator`, and optional `values`:
+
+```json
+{"relation":"and","items":[{"field":"country","operator":"eq","values":["US"]}]}
+```
+
+Pass a semantic object directly to `--definition-request`. Create/update validate and compile it in the same operation. Use `--validate` for schema validation or `--dry-run` for a no-write execution preview; there is no separate public definition build command.

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

@@ -6,6 +6,10 @@ Domain: **Metadata Query**
 
 ## Use Cases
 - Batch create SYSTEM METADATA in one atomic request (events/eventProperties/userProperties) and apply name-based associations. This tool is only for effective production metadata, not tracking-plan metadata. For bury plan draft/review/publish data, use BuryProgramTool only.
+- Do not use it to edit existing metadata; use `+batch_edit_metadata` after resolving the existing names.
+
+## Output
+The response reports the batch creation outcome. Treat any item-level validation error as a failed item; do not assume the whole requested batch was created from transport success alone.
 
 ## Commands
 ```bash
@@ -27,7 +31,7 @@ ae-cli analysis_meta +batch_create_metadata --dry-run
 - Wrap JSON parameters in single quotes (for example `--events '{}'` and `--event_properties '{}'`) to avoid shell escaping issues.
 - At least one non-empty list among `--events`, `--event_properties`, and `--user_properties` must be provided.
 - For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
-- Write operations keep confirmation prompts by default; evaluate whether to use `--yes` only for automation scenarios.
+- This is an ordinary `write` operation and does not require CLI confirmation.
 
 ## Next Steps After Failure
 - If required parameters are missing, fall back to the smallest runnable command and fill them in first (focus on `--project_id`).

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

@@ -8,6 +8,9 @@ Domain: **Metadata Query**
 - Batch edit SYSTEM METADATA already effective in project (super events / event properties / user properties). Do NOT use for tracking-plan metadata (bury/track program); tracking plan operations must use BuryProgramTool. Routing rule: if target is planned/unpublished bury metadata, never call this tool.
 - Batch edit SYSTEM METADATA already effective in project (super events / event properties / user properties).
 
+## Output
+The response reports the batch update outcome. Review item-level failures before claiming that every requested metadata item changed.
+
 ## Command
 ```bash
 ae-cli analysis_meta +batch_edit_metadata --project_id <project_id> --type event --items '[{"eventName":"purchase","eventDesc":"Purchase"}]'
@@ -26,7 +29,7 @@ ae-cli analysis_meta +batch_edit_metadata --dry-run
 - Wrap JSON arguments in single quotes (for example `--items '{}'`) to avoid shell escaping issues.
 - `--type` only accepts `event`, `event_property`, and `user_property`.
 - For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
-- Write operations keep the confirmation prompt by default; re-evaluate whether to use `--yes` in automation scenarios.
+- This is an ordinary `write` operation and does not require CLI confirmation.
 
 ## Next Steps After Failure
 - If required parameters are missing, fall back to the smallest runnable command and fill them in (focus on `--project_id`, `--type`, and `--items`).

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

@@ -7,7 +7,7 @@ Do not use to create a blank BI panel. Use `bi-panel create`.
 Command:
 
 ```bash
-ae-cli analysis bi-panel copy --project-id <project_id> [--panel-name <name>] [--panel-uuid <source_uuid>] [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}'] --yes
+ae-cli analysis bi-panel copy --project-id <project_id> [--panel-name <name>] [--panel-uuid <source_uuid>] [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}']
 ```
 
 Input sends `project_id`, optional source/target fields, and `payload`.

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

@@ -7,7 +7,7 @@ Do not use to copy an existing BI panel. Use `bi-panel copy`.
 Command:
 
 ```bash
-ae-cli analysis bi-panel create --project-id <project_id> [--panel-name <name>] [--panel-uuid <uuid>] [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}'] --yes
+ae-cli analysis bi-panel create --project-id <project_id> [--panel-name <name>] [--panel-uuid <uuid>] [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}']
 ```
 
 Input sends `project_id` plus optional BI panel identifiers, target IDs, and `payload`.

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

@@ -7,6 +7,8 @@ Do not use for dashboards. Use `dashboard delete`.
 Command:
 
 ```bash
+ae-cli analysis bi-panel delete --project-id <project_id> --panel-ids '[2001,2002]' --dry-run
+# Summarize the target and impact, then wait for explicit user confirmation.
 ae-cli analysis bi-panel delete --project-id <project_id> --panel-ids '[2001,2002]' --yes
 ```
 

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

@@ -7,9 +7,11 @@ Do not use for dashboard assets. Use `dashboard list`.
 Command:
 
 ```bash
-ae-cli analysis bi-panel list --project-id <project_id> [--query <keyword>] [--fields '["id","name"]'] [--limit 20] [--offset 0]
+ae-cli analysis bi-panel list --project-id <project_id> [--query <keyword>] [--limit 50] [--offset 0]
 ```
 
-Input sends `project_id` and optional `query`, `fields`, `limit`, `offset`.
+Input sends `project_id` and optional `query`, `fields`, `limit`, `offset`. Prefer the default projection for discovery. Do not request generic `id`; BI panel summaries use fields such as `panel_id` and `name` when projected.
+
+When `has_more=true`, continue only with the returned `next_offset`; do not calculate the next page locally.
 
 Output is the gateway envelope. `data` contains BI panel summaries and paging metadata when returned.

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

@@ -2,7 +2,9 @@
 
 Use for BI panel page data that may be large or long-running.
 
-Do not use for tiny previews. Use `bi-panel-page-data run` with a small limit.
+Routing: read [`analysis_data_retrieval.md`](analysis_data_retrieval.md) before choosing this `export` command instead of `bi-panel-page-data run`.
+
+Do not use this command for bounded inline previews; use `bi-panel-page-data run` when the requested result fits the sync data retrieval rule.
 
 Command:
 
@@ -10,9 +12,11 @@ Command:
 ae-cli analysis bi-panel-page-data export --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts [--chart-ids '["chart1"]'] [--artifact-format jsonl]
 ```
 
-Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional control, paging, cache, request, timeout, and format fields. Use CLI flag `--artifact-format` for the gateway `format` input; `--format` is the CLI output formatter.
+Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional control, paging, cache, request, timeout, and format fields. Use CLI flag `--artifact-format` for the gateway `format` input; `--format` is the CLI output formatter. Async export has no inline row limit. Runtime defaults to and is capped at 21600 seconds (6 hours); cancel earlier with `analysis query cancel --run-id <run_id>`. `--row-limit` and related BI page controls are chart/summary window controls, not the generic async artifact row policy; see [`analysis_data_retrieval.md`](analysis_data_retrieval.md).
+
+Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, expiration fields, and possibly `query_context_id`. It does not expose inspect/download API paths; use the CLI commands below.
 
-Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, and expiration fields. It does not expose inspect/download API paths; use the CLI commands below.
+When `result_type=charts` and the backend can resolve chart SQL sources, the export descriptor and first artifact metadata line may include `query_context_id` plus `sources`. BI chart sources are SQL contexts, so `drilldown_available` and `result_cluster_available` are false unless the response explicitly says otherwise. Do not call model drilldown commands from a BI SQL context with `drilldown_available=false`.
 
 Follow-up workflow:
 
@@ -20,6 +24,6 @@ Follow-up workflow:
 2. Poll status with `ae-cli analysis run inspect --run-id <run_id>`.
 3. Continue polling while status is running or pending. Treat `COMPLETED` or `SUCCEEDED` as success, and `FAILED`, `CANCELED`, or `CANCELLED` as terminal failure.
 4. On success, download with `ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>`.
-5. If the export is no longer needed, cancel with `ae-cli analysis query cancel --run-id <run_id> --yes`.
+5. If the export is no longer needed, cancel with `ae-cli analysis query cancel --run-id <run_id>`.
 
 Do not write custom Python/curl for polling or download unless the CLI command itself is unavailable.

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

@@ -2,14 +2,18 @@
 
 Use for bounded inline BI panel page chart or summary data.
 
-Do not use for large or long-running page data. Use `bi-panel-page-data export`.
+Routing: read [`analysis_data_retrieval.md`](analysis_data_retrieval.md) before choosing this `run` command instead of `bi-panel-page-data export`.
+
+Do not use this command for full, unknown-size, larger than 1000-row, or long-running page data; use `bi-panel-page-data export`.
 
 Command:
 
 ```bash
-ae-cli analysis bi-panel-page-data run --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts [--chart-ids '["chart1"]'] [--limit 100] [--timeout-seconds 60]
+ae-cli analysis bi-panel-page-data run --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts [--chart-ids '["chart1"]'] [--row-limit 100] [--limit 100] [--timeout-seconds 120]
 ```
 
-Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional control, paging, cache, request, timeout, and limit fields.
+Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional control, paging, cache, request, timeout, and limit fields. Control defaults: inline `--limit` default 100 / max 1000, `--timeout-seconds` default 120 / max 180. Chart `--row-limit` default 100 / max 1000. The routing rule lives in [`analysis_data_retrieval.md`](analysis_data_retrieval.md).
 
 Output is the gateway envelope. `data` contains bounded inline page data.
+
+When `result_type=charts` and the backend can resolve chart SQL sources, the response may include `query_context_id` plus `sources`. BI chart sources are SQL contexts, so `drilldown_available` and `result_cluster_available` are false unless the response explicitly says otherwise. Do not call model drilldown commands from a BI SQL context with `drilldown_available=false`.

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

@@ -7,7 +7,7 @@ Do not use to share dashboards or folders. Use the matching resource share comma
 Command:
 
 ```bash
-ae-cli analysis bi-panel share --project-id <project_id> --panel-id <panel_id> [--payload '{...}'] --yes
+ae-cli analysis bi-panel share --project-id <project_id> --panel-id <panel_id> [--payload '{...}']
 ```
 
 Input sends `project_id`, `panel_id`, and backend-compatible snake_case `payload`.

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

@@ -10,7 +10,7 @@ reads only the released/queryable version. Use `bi-panel-version get` to inspect
 Command:
 
 ```bash
-ae-cli analysis bi-panel update --project-id <project_id> [--panel-name <name>] [--panel-uuid <uuid>] [--payload '{...}'] --yes
+ae-cli analysis bi-panel update --project-id <project_id> [--panel-name <name>] [--panel-uuid <uuid>] [--payload '{...}']
 ```
 
 Input sends `project_id`, optional `panel_name`, `panel_uuid`, and `payload`.

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

@@ -10,7 +10,7 @@ as `--source-version`. The gateway rejects stale `source_version` values.
 Command:
 
 ```bash
-ae-cli analysis bi-panel-version publish --project-id <project_id> --panel-id <panel_id> --source-version <draft_version> --yes
+ae-cli analysis bi-panel-version publish --project-id <project_id> --panel-id <panel_id> --source-version <draft_version>
 ```
 
 Input sends `project_id`, one of `panel_id` or `panel_uuid`, and required

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

@@ -14,8 +14,8 @@ Domain: **Query lifecycle**
 
 ## 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
+ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef --reason "agent timeout"
 ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef --dry-run
 ```
 
@@ -26,12 +26,12 @@ ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef
 | `--reason` | No | Optional cancellation reason. Default: `MCP_CANCEL_QUERY_TOOL`. |
 
 ## Decision Rules
-- This is a write operation (`risk: write`). Use `--yes` only when the user clearly asked to cancel or stop a running query.
+- This is an ordinary `write` operation and does not require CLI confirmation.
 - 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`, supplying a stable ID before execution is required. Use `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 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>`.
 
 ## 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.