@acedatacloud/skills 2026.1005.261001 → 2026.1005.262001
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/skills/ai-chat/SKILL.md +0 -2
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.1005.
|
|
3
|
+
"version": "2026.1005.262001",
|
|
4
4
|
"description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"agent-skills",
|
package/skills/ai-chat/SKILL.md
CHANGED
|
@@ -136,7 +136,6 @@ curl -X POST https://api.acedata.cloud/v1/messages \
|
|
|
136
136
|
-H "Content-Type: application/json" \
|
|
137
137
|
-d '{
|
|
138
138
|
"model":"claude-sonnet-5-5",
|
|
139
|
-
"metadata":{"user_id":"example-user-001"},
|
|
140
139
|
"messages":[{"role":"user","content":"Review this implementation plan."}],
|
|
141
140
|
"max_tokens":8192,
|
|
142
141
|
"thinking":{"type":"adaptive"},
|
|
@@ -144,7 +143,6 @@ curl -X POST https://api.acedata.cloud/v1/messages \
|
|
|
144
143
|
}'
|
|
145
144
|
```
|
|
146
145
|
|
|
147
|
-
- Use the optional top-level `metadata` object for caller-supplied request metadata. `metadata.user_id` must be a string; choose a stable identifier without personal information. Keep it outside `messages`; it does not replace Bearer authentication.
|
|
148
146
|
- Send `thinking`, `output_config`, effort, sampling parameters, and extension fields unchanged. The platform does not enforce a frozen per-model enum or rewrite thinking modes; the selected model decides which values and combinations it accepts and its parameter errors are returned to the caller. Pass-through is not a promise of feature support across models or protocols.
|
|
149
147
|
- Common `thinking.type` values are `adaptive`, `enabled`, and `disabled`; newer modes such as `between_tools`, fixed `budget_tokens`, and whether thinking can be disabled depend on the model. Common effort values include `low`, `medium`, `high`, `xhigh`, and `max`, but are not a closed enum.
|
|
150
148
|
- `thinking.display="summarized"` returns a readable summary, not raw reasoning. `omitted` hides the thinking text while retaining its opaque `signature`. Beta `updates` requests short progress updates between tool calls with hidden reasoning; send `anthropic-beta: thinking-display-updates-2026-08-18` and `thinking.display="updates"`. The value and beta header are forwarded, not rewritten to `summarized`; actual support and output depend on the selected model.
|