@thinkingai/ae-cli 6.0.34 → 6.0.36

package/skills/ae-engage/references/save-task.md

@@ -10,13 +10,9 @@ Recommended workflow:
 
 1. `ae-cli engage-setting channel list --project-id <projectId>`
 2. `ae-cli engage-task task build-save-guide --project-id <projectId> --req '{...}'`
-3. If the guide indicates an audience or QP-derived fields are needed, create the audience directly and read it back:
-
-```bash
-ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
-ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
-```
-
+3. If the guide indicates QP-derived fields, call `ae-cli engage-setting query cluster-qp-skill --project-id <projectId>` and build
+   `targetConfig.qp`, `triggerConfig.triggerRule`, `clientConfig.clientQp`, or `completionIndicatorDef.event`
+   from the returned skill text. For existing-cluster audiences, use `analysis user-cluster get`.
 4. Build the final grouped `req`
 5. `ae-cli engage-task task save --project-id <projectId> --req '{...}'`
 
@@ -40,7 +36,7 @@ For the full guide contract, request format, return sections, and handoff usage,
 The command supports two modes:
 
 - create mode: omit `req.taskId`
-- update mode: include `req.taskId` for an existing draft task
+- update mode: include `req.taskId` for an existing draft or paused task
 
 Regardless of mode, this tool only saves a draft:
 
@@ -59,8 +55,8 @@ Notes:
 - the outer Capability input uses `project_id` and `req`; fields inside `req` keep the native camelCase DTO shape shown below
 - Hermes assigns the outer `--project-id` to `req.projectId`; if `req.projectId` is also present, the outer value wins
 - the whole `req` must be a JSON object, not a stringified JSON string
-- for update mode, Hermes only allows modifying draft tasks
-- in update mode, omitted fields are backfilled from the existing draft before validation, so partial draft updates are allowed
+- for update mode, Hermes allows modifying **draft** or **paused** tasks (`status` 0 or 2); running/ended tasks are rejected with `invalid_status`
+- in update mode, omitted fields are backfilled from the existing task before validation, so partial updates (e.g. rename only) are allowed
 
 ### Response shape
 
@@ -160,12 +156,13 @@ Top-level notes:
 
 ### 4.1 `taskId`
 
-Use `taskId` only when you are updating an existing draft task.
+Use `taskId` only when you are updating an existing draft or paused task.
 
 - create mode: omit `taskId`
 - update mode: include `taskId`
-- update mode can send only the fields that need changing
-- update mode still fails if the referenced task is not in draft status
+- update mode can send only the fields that need changing (e.g. `baseInfo.taskName` for rename)
+- update mode fails with `invalid_status` if the task is running or ended
+- for paused tasks that already started pushing, Hermes rejects changes to key attributes (channel, trigger time/type, audience cluster, timezone, completion indicators); renames and other non-key fields remain allowed
 
 ### 4.2 `channelConfig`
 
@@ -273,7 +270,7 @@ Before submission, verify:
 5. `targetClusterType` matches the presence or absence of `clusterKey` / `qp`.
 6. `triggerType` matches the provided scheduling or event fields.
 7. `completionIndicatorDef` is present and structurally valid for the current scenario.
-8. `taskId` is omitted for create mode and present only for updating a draft.
+8. `taskId` is omitted for create mode and present only for updating a draft or paused task.
 9. No unsupported `triggerType=6` is used.
 10. No placeholder IDs or fabricated resource names remain in the request.
 
@@ -309,6 +306,6 @@ This command is a write operation.
 - Do not pass the whole `req` as a JSON string
 - Do not use `triggerType=6`
 - Do not invent `channelId`, `clusterKey`, audience definitions, or content keys
-- Do not use `taskId` for a non-draft task
+- Do not use `taskId` for a running or ended task
 - Do not pass `occasionKeys`; Hermes derives them from content
 - Do not call the semantic cluster definition builder as a reflex; call it only when guide output says QP-derived fields are needed

package/skills/ae-engage/references/scene-config-channel.md

@@ -1,6 +1,6 @@
 # engage-scene config-channel
 
-> Capability ids: `engage-scene.config-channel.{list,get,create,update,update-status,delete,query-log}` · Domain: `engage`.
+> Trigger keywords: config center, scene config, config channel · Capability ids: `engage-scene.config-channel.{list,get,create,update,update-status,delete,query-log}` · Domain: `engage`.
 
 Scene / config center — **config channel management** (Webhook / client config channels).
 
@@ -102,7 +102,7 @@ ae-cli engage-scene config-channel query-log --project-id <project_id> --channel
   "customsParamList": [
     {
       "key": "user_id",
-      "columnName": "#account_id",
+      "columnName": "user:#account_id",
       "defaultValue": "",
       "systemIdParam": true
     }
@@ -114,10 +114,33 @@ ae-cli engage-scene config-channel query-log --project-id <project_id> --channel
 - `url` — production environment URL (required for webhook)
 - `testUrl` — optional test environment URL
 - `authConfig.enable` — channel auth switch; when true, `secretKey` is required; `secretType` **1 = basic**, **2 = advanced**
-- `customsParamList` — user params (field key / linked user property / default value / system-integration identity)
-- `envParamList` — environment params (from config tables)
+- `customsParamList` — **user params** (field key / linked user property / default value / system-integration identity). Each entry's `columnName` must use the `user:` prefix and reference a real user property code, e.g. `user:#account_id`, `user:#distinct_id`. Do **not** pass bare property names such as `#account_id`.
+- `envParamList` — **environment params** (from config tables). `columnName` here is the env-param field name and does **not** take the `user:` prefix.
 - At most one `systemIdParam=true` across user + env params
 
+When creating or updating a config channel (`create` / `update` with `--config`), normalize every `customsParamList[].columnName` to `user:<prop_code>` before submit. If `get` returns bare names, add the prefix when building the next update payload.
+
+## Preflight: verify user properties (ae-analysis)
+
+Before setting `customsParamList[].columnName`, use the **ae-analysis** skill to confirm each linked user property exists in the project. Do not invent property names.
+
+```bash
+# 1) Browse / search user properties
+ae-cli analysis-meta property list --project-id <project_id> --scope user \
+  --query <keyword> \
+  --fields '["prop_name","prop_desc","select_type","table_type"]' --limit 50
+
+# 2) Verify one exact property before submit (optional but recommended)
+ae-cli analysis-meta property get --project-id <project_id> --table-type user --prop-name <prop_name>
+```
+
+Decision rules:
+
+- Read `skills/ae-analysis/references/property_list.md` and `property_get.md` when unsure about flags or output shape.
+- Match a real `data.properties[].prop_name` (or confirmed `data.property.prop_name`) from metadata, then set `columnName` to `user:` + that name — e.g. `prop_name` `#account_id` → `columnName` `user:#account_id`.
+- If the property is not found after list + optional get, stop and tell the user; do not submit the channel config with a fabricated `columnName`.
+- `envParamList` names come from config-table / env-param setup, not from user-property metadata.
+
 ## Output
 
 - `list`: `data.items` + `data.total` (snake_case fields: `channel_id` / `channel_name` / `channel_type` / `channel_status` / `creator` / `updater` / `create_time` / `update_time`)
@@ -130,6 +153,7 @@ ae-cli engage-scene config-channel query-log --project-id <project_id> --channel
 
 - Risk: `list` / `get` / `query-log` = read; `create` / `update` / `update-status` = write; `delete` = high-risk-write (user confirmation + `--yes`)
 - Discover `channel_id` with `list` first; never invent IDs
+- **User params (`customsParamList`)**: `columnName` must be `user:<user_prop_code>` (e.g. `user:#account_id`). Applies to both webhook and client channels on create/update. Preflight each name with `ae-cli analysis-meta property list/get` (ae-analysis skill) before submit.
 - Enabled channel (`channel_status=1`): only limited fields such as name can change; disable first (`update-status --channel-status 2`) before changing URL, auth, or parameter definitions
 - Delete: disable first, then `delete --yes`
 - Copy: `get` → rename (often append `_copy`) → `create`

package/skills/ae-engage/references/scene-config-group.md

@@ -1,6 +1,6 @@
 # engage-scene config-group
 
-> Capability ids: `engage-scene.config-group.{list,batch-add,update,batch-delete}` · Domain: `engage`.
+> Trigger keywords: config center, scene config · Capability ids: `engage-scene.config-group.{list,batch-add,update,batch-delete}` · Domain: `engage`.
 
 Scene management / config center — config item group management.
 

package/skills/ae-engage/references/scene-config-item.md

@@ -1,6 +1,6 @@
 # engage-scene config-item
 
-> Capability ids: `engage-scene.config-item.{list,get,create,update,delete}` · Domain: `engage`.
+> Trigger keywords: config center, scene config, config item · Capability ids: `engage-scene.config-item.{list,get,create,update,delete}` · Domain: `engage`.
 
 Scene management / config center — config item management.
 

package/skills/ae-engage/references/scene-config-metric.md

@@ -1,6 +1,6 @@
 # engage-scene config-metric
 
-> Capability ids: `engage-scene.config-metric.{list,get,batch-add,update-rule,batch-delete}` · Domain: `engage`.
+> Trigger keywords: config center, config item · Capability ids: `engage-scene.config-metric.{list,get,batch-add,update-rule,batch-delete}` · Domain: `engage`.
 
 Scene management / config center — config item related-metric management.
 

package/skills/ae-engage/references/scene-config-param.md

@@ -1,6 +1,6 @@
 # engage-scene config-param
 
-> Capability ids: `engage-scene.config-param.{list,batch-add,update,batch-delete}` · Domain: `engage`.
+> Trigger keywords: config center, scene config, config item · Capability ids: `engage-scene.config-param.{list,batch-add,update,batch-delete}` · Domain: `engage`.
 
 Scene management / config center — config item parameter management.
 

package/skills/ae-engage/references/scene-preset-metric.md

@@ -1,6 +1,6 @@
 # engage-scene preset-metric
 
-> Capability ids: `engage-scene.preset-metric.{get,set}` · Domain: `engage`.
+> Trigger keywords: config center, config item · Capability ids: `engage-scene.preset-metric.{get,set}` · Domain: `engage`.
 
 Scene management / config center — config item preset metrics (impression / click / engagement) QP configuration.