90 Commits

Author SHA1 Message Date
chenanran555 02d859ee18 Merge origin/main into feat/sandbox 2026-09-11 11:14:11 +08:00
若麒 0c7ba721a7 Merge remote-tracking branch 'origin/main' into feat/global-watermark-config 2026-09-10 15:39:12 +08:00
clh02467605 7803d91e3f chore: fixed Formatting issues 2026-09-10 14:07:37 +08:00
clh02467605 c2d17707c0 feat(speech): add instant hotwords, context, and vocabulary CRUD 2026-09-10 14:02:05 +08:00
若麒 3477a08dad feat(config): add profile-level watermark setting 2026-09-08 16:33:40 +08:00
chenanran555 c0fca869c2 fix(sandbox): support shared --base-url configuration with workspace fallback 2026-09-07 16:37:56 +08:00
chenanran555 332efb05b8 feat(sandbox): add Bailian Sandbox lifecycle commands 2026-09-07 15:11:51 +08:00
若麒 a402026cce Merge remote-tracking branch 'origin/main' into feat/runtime-risk-confirmation 2026-09-01 19:49:04 +08:00
故璃 9e6f5ca9cb fix(skill): retry registry fetches and tolerate blocked backup cleanup
- bl skill init: raise index timeout 10s→30s and retry transient network
  failures (3 attempts); advisor sync silent channel stays fail-fast
- make post-swap backup deletion best-effort so host safe-delete guards
  cannot fail a completed install (postinstall.js mirror included)
- add unit coverage for guard-blocked cleanup and registry retry policy
2026-09-01 16:37:12 +08:00
若麒 4f59ca5118 Merge branch 'main' into feat/runtime-risk-confirmation 2026-08-28 17:42:57 +08:00
若麒 00bcee36a6 feat(runtime): add unified confirmation gate for high-risk commands 2026-08-27 15:54:23 +08:00
若麒 d343dc3265 fix(auth): only apply profile presets on login 2026-08-26 17:10:00 +08:00
若麒 670c15532b feat(auth): expand Token Plan capabilities and speech defaults 2026-08-26 13:42:27 +08:00
若麒 e31addf0d6 Merge branch 'main' into feat/bilingual-quick-start-examples 2026-08-18 14:33:34 +08:00
clark-fc ad5c44d746 Merge pull request #166 from modelstudioai/feat/iteration1-w1-foundation
Feat/iteration1 w1 foundation
2026-08-17 14:08:56 +08:00
zeyu.fz 70b50060cf Merge remote-tracking branch 'origin/main' into feat/iteration1-w1-foundation 2026-08-17 12:55:57 +08:00
故璃 7461189007 Merge branch 'main' into feat/cli-skill-sync 2026-08-15 10:22:09 +08:00
若麒 94ccab0898 feat(text): support Responses API 2026-08-14 17:02:29 +08:00
clh02467605 3b7c4cfabc Merge remote-tracking branch 'refs/remotes/origin/main' into feat/mcp-support-sse 2026-08-14 14:42:21 +08:00
clh02467605 d5d9fcb50f fix: fixed sse error 2026-08-14 14:41:37 +08:00
clh02467605 3ea2931152 fix(mcp): harden SSE parsing, abort, and fallback matching 2026-08-14 11:11:47 +08:00
zeyu.fz b7a4efe619 feat(speech): 支持同步Flash ASR模型和异步文件转录模型
- 新增同步Flash ASR模型请求流程,支持单音频文件识别
- 实现了对同步Flash模型不支持异步标志及参数的限制校验
- 异步文件转录模型支持单文件URL上传和语言参数细化
- 优化异步和同步鉴权域显示,丰富根帮助和分组帮助提示
- speech recognize增加dry-run测试覆盖多种识别场景
- free-tier自动停用功能优化,改用统一轮询函数处理批量请求
- 统一轮询逻辑,支持console和telemetry接口的异步任务完成判定
- 规范输出格式和错误提示,增强用户调试体验
- 版本升级到1.14.3,更新示例参数和模型ID引用
2026-08-14 11:07:21 +08:00
clh02467605 4dcec7d075 fix(mcp): fix SSE header timeout, 405 fallback matching, and parseSSE chunking 2026-08-13 18:32:54 +08:00
若麒 6b685964f3 feat(runtime): support colocated localized CLI help text 2026-08-13 16:12:09 +08:00
clh02467605 ae0c2c1213 fix(speech): handle qwen3-filetrans singular result.transcription_url
Normalize async ASR transcription items so waiting mode downloads text and --out works without changing shared media task types.
2026-08-13 15:52:34 +08:00
clh02467605 798ce596f6 fix(mcp): harden SSE fallback for Bailian and --url overrides 2026-08-13 15:37:32 +08:00
clh02467605 e244771ee9 test(speech): harden flash ASR contract coverage and docs
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.
2026-08-13 14:25:47 +08:00
clh02467605 9379da7a4c fix(speech): align flash vocabulary_id and qwen3-filetrans language params 2026-08-13 09:47:09 +08:00
clh02467605 241de61866 fix: support sync-flash and qwen3-filetrans ASR models in speech recognize
- Add asr-routes.ts with resolveAsrApi() to route models to the correct
  DashScope endpoint instead of always hitting asr/transcription
- Async filetrans: fun-asr / paraformer / *-filetrans → file_urls (plural)
- Async filetrans (qwen3): qwen3-asr-flash-filetrans* → file_url (singular)
- Sync flash (input-audio): fun-asr-flash* / qwen-audio-*-asr-flash → multimodal-generation
- Sync flash (qwen3): qwen3-asr-flash* → multimodal-generation + asr_options
- Realtime/streaming models now give a clear USAGE error instead of a
  confusing server-side "url error"
- Propagate same routing logic to pipeline speechRecognize step
- Add table-driven unit tests and dry-run e2e assertions
Fixes #146
2026-08-12 17:12:23 +08:00
clh02467605 313966d7a9 feat(mcp): add SSE support with fallback mechanism for MCP connections
- Add McpSseClient implementation for classic HTTP+SSE MCP protocol
- Implement connectBailianMcpWithFallback with Streamable HTTP to SSE fallback
- Add isStreamableHttpUnsupported helper to detect 405 streamableHttp errors
- Update activate-hint logic to handle WebSearch 405 streamableHttp cases
- Replace direct MCP client usage with connection manager in call/tools commands
- Add proper client cleanup with close() calls in finally blocks
- Export new MCP connection utilities and types from core client module
- Add comprehensive tests for SSE client and fallback behavior
2026-08-12 15:44:51 +08:00
故璃 d74d4efcd0 fix(dataset): align validation with the platform data-format rules doc
Reviewed against the official text-tuning data rules; fixes two confirmed
mismatches and fills enforcement gaps:

- thinking: exempt assistant messages carrying tool_calls from the
  THINK_TAG_NOT_LAST check — the spec's tool+thinking combo example puts
  <think> on a non-last assistant and was previously false-flagged
- DPO support matrix: reject image/video content items, tools, tool_calls
  and role:tool (DPO_UNSUPPORTED_ELEMENT); also scan chosen/rejected
- DPO: messages not ending with user upgraded warning -> error
- OpenAI migration: name/weight upgraded warning -> error (spec: must not
  carry); drop dead record-level name branch
- tool_call_id: unmatched tool response upgraded warning -> error
  (one-to-one per spec); new TOOL_CALL_NO_RESPONSE warning for orphan calls
- loss_weight: validate range at message level too; warn when placed on
  anything but the last assistant message (LOSS_WEIGHT_PLACEMENT)
- video params: fps/sample_fps must be within [0.1, 10]
  (INVALID_VIDEO_FPS); mode-mismatched params warned
  (VIDEO_PARAM_MODE_MISMATCH); video_start/video_end type-checked
- zip: skip macOS packaging metadata (__MACOSX/, .DS_Store, ._*) in
  filename constraints and image counting to stop false failures on
  Finder-created archives

Tests 45 -> 59 covering every new/changed rule, including a replica of the
spec's official tool+thinking example.
2026-08-12 10:09:10 +08:00
故璃 e7422bd2e5 fix(dataset): align validation rules with platform data format spec
- 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
2026-08-12 07:48:11 +08:00
故璃 2965080cb7 feat(skills): replace foreign skill dirs containing SKILL.md during fan-out
Previously, fan-out skipped any existing real directory not recorded in
the lock file, treating it as user content. This left stale skill copies
installed by other tools (e.g. npx skills add) permanently out of date.

Now: if the directory contains a SKILL.md, it is recognized as a skill
artifact and replaced with a symlink to the canonical dir. Directories
without SKILL.md are still preserved (user content safety boundary).
2026-08-11 14:29:10 +08:00
zeyu.fz 4343fc87af feat(core): 添加并统一管理 x-dashscope-openapisource 请求头
- 在 headers.ts 中新增 OPEN_API_SOURCE 常量,作为静态的 OpenAPI 源标识
- 在 trackingHeaders 函数中添加 x-dashscope-openapisource 请求头
- 更新 client/index.ts 以导出 OPEN_API_SOURCE
- 在 instrumented-fetch.test.ts 中添加对应请求头的测试,确保其正确添加或省略
- 修改文档注释,明确 x-dashscope-openapisource 与 x-dashscope-source-config 的用途和区别
2026-08-11 14:20:44 +08:00
zeyu.fz 99a3dbae2d Merge remote-tracking branch 'origin/main' into feat/iteration1-w1-foundation 2026-08-10 15:26:18 +08:00
Gong Shiqi 6338df36be Merge pull request #138 from modelstudioai/feat/update-defmodel
Update default image model to qwen-image-3.0
2026-08-05 19:43:48 +08:00
zeyu.fz 9fc6434a26 Merge remote-tracking branch 'origin/main' into feat/iteration1-w1-foundation 2026-08-05 17:46:12 +08:00
若麒 01ec13aad8 feat: add CLI source config tags 2026-08-05 17:37:14 +08:00
clh02467605 b68ff45fb9 Merge remote-tracking branch 'refs/remotes/origin/main' into feat/update-defmodel 2026-08-05 17:08:44 +08:00
clh02467605 4990b27436 feat: update image default model 2026-08-05 16:58:29 +08:00
故璃 8488b251f7 Merge branch 'main' into feat/deploy-update 2026-08-05 16:11:38 +08:00
zeyu.fz 43abf0aca5 feat(knowledge): 新增知识库管理及用户旅程端到端测试支持
- 增加test:journey脚本,覆盖知识库跨命令全链路用户旅程测试
- 在文档中新增Journey E2E章节,详细说明用户旅程测试定位及断言机制
- 完善commands模块,新增知识库相关命令包括知识库列表、信息、创建、更新、删除
- 新增知识库文档相关命令,如文档列表、状态、上传、删除、打标签及OSS导入
- 添加知识服务管理命令,支持列表、创建、更新、部署、删除及复制
- 支持知识块增删查改命令,完善知识点的灵活操作能力
- 实现数据中心分类管理命令,支持分类增删查操作
- 优化knowledge chat命令,增加workspace-id统一解析及agent-version版本控制
- 重构与知识库相关命令的导出与注册,完善CLI整体能力覆盖
- 新增命令详尽的帮助文档,包含参数说明、使用示例及错误边界
- 实现批量删除知识块的自动分批处理逻辑,易于操作大规模数据
- 添加必要的输入校验与安全提示,确保操作安全且符合规范
2026-08-05 12:02:32 +08:00
故璃 121fa1317f feat(skills): align agent registry with upstream and harden cross-platform install 2026-08-05 10:17:06 +08:00
若麒 081d09863b Merge branch 'main' into feat/multi-channel-install 2026-08-04 20:22:26 +08:00
故璃 3766b6d7ca Merge branch 'main' into feat/bailian-wiki-doc-sync 2026-08-03 19:33:16 +08:00
若麒 026e250cd3 Merge branch 'main' into feat/multi-channel-install 2026-08-03 17:16:56 +08:00
clh02467605 1c38c381e5 feat: switch default text model to qwen3.8-max
Align text chat, pipeline, config UI, login validation, and Token Plan
text presets, and update README, skill reference, and related tests.
2026-08-03 15:34:18 +08:00
rendianmeng 45d468838f feat: win bl update exe file test 2026-07-31 17:44:59 +08:00
rendianmeng 5e2833569a Merge branch main of github.com:modelstudioai/cli into feat/multi-channel-install 2026-07-30 10:12:42 +08:00
故璃 30fe8182f4 Merge branch 'main' into feat/bailian-wiki-doc-sync
# Conflicts:
#	packages/cli/src/commands.ts
#	packages/commands/tests/e2e/topic-routes.ts
#	pnpm-lock.yaml
#	pnpm-workspace.yaml
#	skills/bailian-cli/reference/index.md
2026-07-29 17:34:28 +08:00