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
- Token Plan defaults now use the current text, image, and dedicated text-to-video, image-to-video, and reference-to-video models.
14
+
- The Bailian CLI Skill now distinguishes Bailian-specific tasks from ordinary host-agent work more accurately and avoids repeated consent prompts within an approved workflow.
15
+
- Published CLI packages now support Node.js 18.17 and later, lowering the previous minimum requirement from Node.js 22.12.
16
+
17
+
### Fixed
18
+
19
+
- Token Plan now handles local images correctly for image editing, image-to-video, reference-to-video, and vision understanding without requiring a separately hosted URL.
20
+
21
+
## [1.10.0] - 2026-07-19
22
+
23
+
### Added
24
+
25
+
-**`bl config agent`** — configure Claude Code, Qwen Code, OpenCode, OpenClaw, Hermes Agent, or Codex to use DashScope in one command.
26
+
27
+
### Changed
28
+
29
+
- The Bailian CLI Skill now routes only matching Bailian and multimodal tasks to `bl`, and asks for consent before provider-neutral remote or billable calls.
30
+
31
+
### Fixed
32
+
33
+
- Full `bl auth logout` now clears the model Base URL so later logins cannot inherit a stale custom or Token Plan endpoint.
34
+
35
+
## [1.9.0] - 2026-07-17
36
+
37
+
### Added
38
+
39
+
-**Token Plan support** — log in and call supported models directly without manually configuring the endpoint.
40
+
-**Named Config Profiles** — create, switch, and manage isolated configurations; logging in to a named Profile activates it automatically.
-**`bl workspace init`** — initialize a Bailian workspace and activate the required services in one workflow.
43
+
44
+
### Fixed
45
+
46
+
- Improved configuration safety and consistency, including secret masking and preservation of custom configuration fields.
47
+
48
+
## [1.8.3] - 2026-07-16
49
+
50
+
### Fixed
51
+
52
+
- Fixed `bl text chat --messages-file -` failing on Windows by treating standard input as a `/dev/stdin` file path; piped JSON messages are now read from standard input correctly. (#103)
53
+
54
+
## [1.8.2] - 2026-07-15
55
+
56
+
### Changed
57
+
58
+
-`bl model list` now defaults to JSON output; pass `--output text` for the table view.
59
+
60
+
### Fixed
61
+
62
+
-`bl model list --enrich` now returns each model's input parameter schema (predictConfig); it was previously always empty because the console gateway response envelope was not unwrapped.
63
+
64
+
## [1.8.1] - 2026-07-14
65
+
66
+
### Changed
67
+
68
+
- Expanded the Command Pack allowlist to accept an additional internal command extension.
69
+
70
+
## [1.8.0] - 2026-07-13
71
+
72
+
### Added
73
+
74
+
-**`bl model list`** — browse the Bailian model marketplace: list model families or show full details for a single family (`--model`), with filters for provider, capability, feature, and context-window, pagination (`--page` / `--page-size`), pricing, and `--enrich` for richer metadata.
75
+
-**`bl usage summary`** — a unified usage view combining free-tier quota and a recent usage overview; `--days` sets the overview window (default 7).
76
+
-**Command Pack host support** — added support for allowlisted internal command extensions.
77
+
-**Audio & image fine-tuning** — `bl finetune audio create` (CosyVoice TTS) and `bl finetune image create` (Wan image generation) join the existing text flow. `bl finetune image create` supports `--generation-type t2i|i2i` to select text-to-image or image-to-image training.
78
+
-**Audio & image deployment** — `bl deploy audio create` and `bl deploy image create` deploy fine-tuned TTS and image models as endpoints.
79
+
-**Multimodal dataset validation** — `bl dataset upload` and `bl dataset validate` now accept `.zip` archives with `tts` and `image` schemas, validate referenced media files, and allow image archives up to 1 GB.
80
+
81
+
### Changed
82
+
83
+
-**Fine-tune and deploy commands are now split by modality (BREAKING)**: `bl finetune create` → `bl finetune text create`, and `bl deploy create` → `bl deploy text create`. Update any scripts that use the old paths.
-**Fine-tune status exit behavior changed (BREAKING)**: `bl finetune watch` no longer reserves exit code 3 for running jobs. Running and succeeded jobs return 0; failed and canceled jobs use normal CLI errors.
86
+
-`bl deploy audio create` now defaults to `--plan mu` (model-unit billing, per the CosyVoice deployment contract); text and image continue to default to `lora`.
87
+
-`bl finetune audio create` now validates CosyVoice training data: audio files must be `.wav`, each `wav_fn` must start with `train/`, and exactly one training file is accepted.
88
+
-`bl quota list` and `bl quota check` now report real RPM/TPM usage against limits, adding `RPM Left` / `TPM Left` columns with remaining-quota progress bars sourced from monitoring data.
89
+
-`bl usage free` output now shares its rendering with `bl usage summary` for consistent free-tier tables.
90
+
-`bl advisor recommend` no longer depends on a dedicated intent-detection model to analyze your request.
91
+
92
+
### Removed
93
+
94
+
-**Removed the `tongyi-intent-detect-v3` integration (BREAKING)** used by `bl advisor recommend`, along with the `intent_detect_base_url` config field and the `DASHSCOPE_INTENT_DETECT_BASE_URL` environment variable.
95
+
96
+
### Fixed
97
+
98
+
- Skill command-reference generation now reads product command maps directly from source and produces stable formatting during release checks.
0 commit comments