You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Video generation now defaults to the upgraded HappyHorse 1.1 model for better quality. The 1.0 models are still available via `--model`.
14
+
-`bl update` now keeps the agent skill in sync across all your agent apps (Claude Code, Cursor, etc.), and refreshes it even when the CLI is already up to date.
15
+
16
+
## [1.4.0] - 2026-06-17
17
+
18
+
### Added
19
+
20
+
- Console gateway now supports multiple regions and sites: `cn-beijing` and `ap-southeast-1`, each with domestic and international variants, plus `switchAgent` for delegated access.
21
+
- New global flags `--console-region`, `--console-site`, and `--console-switch-agent`; `bl console call` also gains `--site` and `--switch-agent`.
22
+
-`bl auth login --base-url <url>` to specify the base URL when logging in with an API key.
- All user-facing CLI text is now standardized to English.
28
+
-`bl advisor recommend` internal intent/ranking model upgraded from `qwen-turbo` to `qwen-flash`.
29
+
- Cleaner JSON output for `usage`, `quota`, and `workspace` commands.
30
+
-`base_url` from the config file now takes priority over the `DASHSCOPE_BASE_URL` environment variable.
31
+
-`bl config show` now displays all fields from `config.json`, with sensitive values masked.
32
+
33
+
### Removed
34
+
35
+
- The legacy `region` config field and its related options.
36
+
- Invalid leftover code for the removed `model list` command.
37
+
38
+
### Fixed
39
+
40
+
- When the console session is not logged in or has expired, the CLI now shows a clear sign-in prompt instead of a generic gateway error.
41
+
- Corrected `--resolution` / `--ratio` / `--duration` flag descriptions for `bl video` commands.
42
+
43
+
## [1.3.3] - 2026-06-16
44
+
45
+
### Changed
46
+
47
+
-`bl knowledge retrieve --help` now clearly indicates that `--api-key` is the recommended authentication method; AK/SK flags are explicitly marked as deprecated with guidance to use `--api-key` instead.
48
+
49
+
### Added
50
+
51
+
-`notes` field for command definitions — commands can now include contextual notes (auth requirements, deprecation notices, etc.) that are displayed in both `--help` output and the generated reference docs.
Copy file name to clipboardExpand all lines: README.md
+7-4Lines changed: 7 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,9 +27,12 @@ Equip your AI Agent out-of-the-box with these capabilities, composable across co
27
27
-**Text chat** — Qwen3.7-max: major gains in agentic coding, frontend coding, and vibe coding
28
28
-**Multimodal (Omni)** — Full omni-modal support across text + image + audio + video
29
29
-**Image generation & editing** — Qwen-Image 2.0: pro text rendering, photorealism, strong semantic adherence, multi-image composition
30
-
-**Video generation & editing** — HappyHorse-1.0 series: text-/image-/reference-to-video and natural-language video editing (up to 9-image reference)
30
+
-**Video generation & editing** — happyhorse-1.1 series: text-/image-/reference-to-video and natural-language video editing (up to 9-image reference)
31
31
-**Speech synthesis & recognition** — CosyVoice streaming TTS, voice cloning from 5–20s samples; FunAudio-ASR covers 30 languages including 7 Chinese dialects and 20+ Mandarin accents
32
32
-**Image & video understanding** — Qwen-VL: long-form video analysis, chart/document parsing, visual reasoning, multilingual OCR
33
+
34
+
> **Note:** The features below are currently available only to China site (aliyun.com) account holders and are not yet supported for international / global site accounts.
35
+
33
36
-**Knowledge base & memory** — Multimodal RAG retrieval and cross-session memory for personalized, coherent dialogue
34
37
-**App calls** — Invoke agents and workflows already published on Aliyun Model Studio
35
38
-**MCP integration** — Orchestrate Bailian MCP servers: list services, inspect tools, and invoke any tool directly from the terminal
@@ -51,7 +54,7 @@ Equip your AI Agent out-of-the-box with these capabilities, composable across co
51
54
A complete **2-minute, 16:9 cinematic short film** — produced end-to-end from a single natural-language sentence, with **zero manual editing**. This showcase demonstrates how an AI Agent can compose a multi-step creative pipeline by orchestrating three primitives:
52
55
53
56
-**[Qwen Code](https://github.com/QwenLM/qwen-code)** — the agentic coding model that interprets the user's intent and drives the workflow
54
-
-**[Aliyun Model Studio CLI](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)** — invokes **HappyHorse 1.0**, Aliyun Model Studio's text-/image-/reference-to-video generation model
57
+
-**[Aliyun Model Studio CLI](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)** — invokes **HappyHorse 1.1**, Aliyun Model Studio's text-/image-/reference-to-video generation model
55
58
-**[spark-video Skill](https://github.com/JohnKeating1997/spark-video)** — handles scene decomposition, storyboarding, shot continuity, and final stitching
56
59
57
60
### The single prompt
@@ -64,7 +67,7 @@ A complete **2-minute, 16:9 cinematic short film** — produced end-to-end from
64
67
65
68
1.**Qwen Code** parses the request, plans the narrative beats, and decides which tools to call.
66
69
2. The **spark-video Skill** breaks the story into shots, writes per-shot prompts, and enforces visual continuity (characters, lighting, palette, lens language).
67
-
3.**`bl video generate`** dispatches each shot to **HappyHorse 1.0** in parallel.
70
+
3.**`bl video generate`** dispatches each shot to **HappyHorse 1.1** in parallel.
68
71
4. The skill stitches all clips back together into a single 16:9 / ~2-min deliverable.
69
72
70
73
No timeline scrubbing. No frame-by-frame editing. Just one sentence → one video.
0 commit comments