Add SSE disable header, data-URI format inference, broader response text
parsing, HTTP contract e2e, pipeline routing tests, and ASR model selection
guidance in bailian-gen.
- Support content array format [{text/image/video}] alongside legacy string
- Add tool role support with tool_calls structure and tool_call_id validation
- Add thinking tag placement check (only in last assistant message)
- Add OpenAI migration guards: warn on unsupported name/weight fields
- Add loss_weight range validation (0.0–1.0)
- Fix size limits: SFT/DPO 200MB, CPT 300MB, media ZIP 2GB
- Enforce data.jsonl at ZIP root (reject nested wrapping folders)
- Add ZIP filename constraints: charset [a-zA-Z0-9_-], length ≤120, uniqueness
- Add .tif to accepted image extensions
- Add DPO_LAST_MSG_NOT_USER warning when messages don't end with user role
- CPT profile now uses dedicated 300MB cap instead of shared default
- Expand unit tests from 19 to 45 covering all new validation paths
finetune video create passed a fixed modality "video" to the profile
validator without probing the data for last_frame_path. This caused a
false KF2V_DATA_MISMATCH error when training kf2v models (wan2.2-kf2v-*)
with datasets that correctly contain last_frame_path.
Add sub-variant detection symmetric to the existing image-i2i upgrade:
when a local file is provided, detectModality() inspects the first record
and upgrades "video" → "video-kf2v" if last_frame_path is present.
- Replace all instances of `npx skills add modelstudioai/cli --all -g` with `bl skill add --name all`
- Update installation documentation in INSTALL.md, README.md, and related files
- Modify code references in config/inventory.ts, generate-reference.ts, and other files
- Update HTML UI messages to reflect new installation command
- Correct setup.md to include binary installation option and update subset install instructions
- Adjust versioning documentation to use new skill installation command
- Update all SKILL.md files with consistent installation instructions
- Add finetune video create subcommand (wan2.7/2.5/2.2 i2v + kf2v)
- Align video hyperparams with official docs (n_epochs=50, per-model batch_size/max_pixels)
- Add --last-frame flag to video generate for kf2v (image2video endpoint)
- Fix wan2.1-2.6 i2v input format (img_url instead of media[])
- Add training_cost field to finetune get/watch (catalog ft price, API-key domain only)
- Add --aigc-* flags to deploy create (optional, for video LoRA prompt config)
- Add `bl deploy pause` and `bl deploy resume` (console domain, first
console-auth commands in deploy group) via modelInstance start/stop APIs
- Add core deploy/lifecycle.ts with input-wrapped console gateway calls
- Switch all dataset/finetune/deploy commands to JSON-only output, removing
text formatting logic
- Expose usage/charge_type in finetune get, model_name/expire_time in
finetune checkpoints with near-expiry warning
- Update deploy delete hint to suggest `bl deploy pause`
故璃