737f8db359
chore(release): prepare 1.19.0
2026-09-01 20:21:21 +08:00
a402026cce
Merge remote-tracking branch 'origin/main' into feat/runtime-risk-confirmation
2026-09-01 19:49:04 +08:00
da6e1313e5
feat(commands): migrate delete commands to runtime risk confirmation
2026-09-01 19:25:50 +08:00
2d2ec1c628
Merge remote-tracking branch 'origin/feat/quota-delete-split' into feat/runtime-risk-confirmation
2026-09-01 19:16:40 +08:00
a78ed7ffe8
Merge pull request #187 from modelstudioai/release/1.18.2
...
chore(release): prepare 1.18.2
2026-09-01 19:02:29 +08:00
5a1dfa5227
chore(release): prepare 1.18.2
2026-09-01 18:56:28 +08:00
b5dec926b7
Merge pull request #185 from modelstudioai/fix/skill-init-issue
...
fix(skill): retry registry fetches and tolerate blocked backup cleanup
2026-09-01 17:37:22 +08:00
fd96fd664c
feat(quota): split --delete into a dedicated quota delete command
...
The destructive --delete flag sat on "quota update", but the --yes
high-risk confirmation guards command paths rather than individual flags.
Promote it to its own "quota delete" command with a --yes guardrail, and
reduce "quota update" to QPM/TPM updates only.
2026-09-01 17:35:46 +08:00
719c0b68bb
Merge remote-tracking branch 'origin/main' into feat/runtime-risk-confirmation
2026-09-01 17:06:41 +08:00
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
3f78de2dc1
Merge pull request #183 from modelstudioai/feat/confirm-destructive-ops
...
feat: require --yes confirmation for destructive operations
2026-08-31 19:47:17 +08:00
38926aeb22
feat: require --yes confirmation for destructive operations
...
- finetune/deploy/dataset delete: add --yes flag + confirmDangerousAction
- quota update --delete: confirm before clearing rate limits
- non-TTY runs without --yes fail with a USAGE error
- add e2e coverage and regenerate skill references
2026-08-31 19:26:31 +08:00
e53daf05eb
feat(managed-agent): add directory project workflow
2026-08-31 15:55:10 +08:00
67ae182ec3
feat(managed-agent): require confirmation for removals
2026-08-31 11:06:43 +08:00
e3f2996291
Merge pull request #181 from modelstudioai/perf/registry-smoke-inprocess
...
perf(test): reduce CLI E2E startup overhead
2026-08-31 10:59:51 +08:00
59250c4f44
perf(test): streamline command e2e execution
2026-08-28 19:14:06 +08:00
676b6c2ece
test(runtime): update auth fallback fixture for confirmation context
2026-08-28 17:48:07 +08:00
4f59ca5118
Merge branch 'main' into feat/runtime-risk-confirmation
2026-08-28 17:42:57 +08:00
0872ff6a20
feat(cli): expose high-risk confirmation guidance in help and skills
2026-08-28 17:19:24 +08:00
98ebeb398c
perf(test): run registry smoke help checks in process
2026-08-28 16:54:55 +08:00
5c96077d9f
Merge pull request #179 from modelstudioai/feat/cancel-key-auth
...
chore(release): prepare 1.18.1
2026-08-28 15:50:42 +08:00
8a7674e7c3
chore(release): prepare 1.18.1
2026-08-28 15:37:15 +08:00
afb547e0c8
refactor(commands): migrate remaining confirmations to runtime gate
2026-08-28 14:35:17 +08:00
4fdd8389f8
Merge pull request #178 from modelstudioai/feat/cancel-key-auth
...
feat: cancel validate API key
2026-08-28 14:29:45 +08:00
bd8b08b617
feat: cancel validate API key
2026-08-28 13:10:56 +08:00
449eede237
fix(managed-agent): upgrade OpenAgentPack SDK to 0.4.0 beta
2026-08-27 20:47:51 +08:00
8906108744
refactor(knowledge): migrate high-risk commands to runtime confirmation
2026-08-27 19:42:51 +08:00
2fbb6efe67
Merge remote-tracking branch 'origin/main' into feat/cma-command
2026-08-27 17:27:55 +08:00
47e9bcc634
feat(managed-agent): add scoped resource create commands
2026-08-27 17:01:27 +08:00
00bcee36a6
feat(runtime): add unified confirmation gate for high-risk commands
2026-08-27 15:54:23 +08:00
e9479e4084
Merge pull request #176 from modelstudioai/feat/profile-capability-fallback
...
feat(auth): add Profile API key capability fallback
2026-08-27 11:45:03 +08:00
4c7ef0c7a5
feat(managed-agent): add scoped agent create command
...
Add `bl managed-agent agent create` with automatic YAML key generation,
atomic config updates, preview-by-default behavior, and create-only scoped
apply that ignores unrelated resource drift.
2026-08-27 11:44:00 +08:00
17ffde4ac2
chore(release): prepare 1.18.0
2026-08-27 11:33:50 +08:00
9600f06205
Merge remote-tracking branch 'origin/main' into feat/profile-capability-fallback
...
# Conflicts:
# skills/bailian-gen/reference/index.md
2026-08-26 19:27:01 +08:00
fc3ac36d00
Merge branch 'main' into feat/profile-capability-fallback
2026-08-26 18:54:01 +08:00
fe11227789
Merge pull request #174 from modelstudioai/feat/update-def-video-model
...
Switch default video model to wan3.0-video
2026-08-26 18:00:38 +08:00
9469556671
refactor(managed-agent)!: replace Git versioning with local snapshots
...
Replace @openagentpack/local-git with @openagentpack/project-versions so
the CLI and Workbench share a Git-independent, lock-protected YAML
snapshot store.
- create versions only after a successful Apply
- migrate version commands to local version IDs
- remove Git project scaffolding and CI-specific Apply policy
- update tests and managed-agent skill references
BREAKING CHANGE: remove `managed-agent init --git` and
`managed-agent apply --ci`; version preview and restore now use
`--version-id` instead of `--commit`.
2026-08-26 18:00:05 +08:00
804a43f8ed
docs(skill): use profile default model when unspecified
2026-08-26 17:55:44 +08:00
d343dc3265
fix(auth): only apply profile presets on login
2026-08-26 17:10:00 +08:00
0d24f46f73
fix(e2e): unbind wan3.0/--file dry-run tests from token-plan
2026-08-26 17:09:27 +08:00
cc209ce0b1
Merge pull request #173 from modelstudioai/feat/update-install.md
...
Clarify install guide skill fallback and post-install tips
2026-08-26 16:43:53 +08:00
8360a9f584
feat(e2e): add tests for video generation with --file option and mutual exclusivity checks
2026-08-26 15:48:08 +08:00
90d1ef9dc5
fix: format fix
2026-08-26 15:30:05 +08:00
124c425133
chore: 优化一键安装引导脚本中node版本兼容问题
2026-08-26 15:25:51 +08:00
670c15532b
feat(auth): expand Token Plan capabilities and speech defaults
2026-08-26 13:42:27 +08:00
b93e0d586d
feat(managed-agent): add Workbench and Git-backed CI versioning
...
Add Workbench launch and local Git version commands, enable automatic
agents.yaml versioning after successful applies, introduce CI-safe apply
policies, and reuse the shared @openagentpack/local-git package.
2026-08-25 20:41:47 +08:00
4067b2c2aa
Merge pull request #175 from modelstudioai/feat/migrate-kb-dsh-plugin
...
Feat/migrate kb dsh plugin
2026-08-25 09:56:07 +08:00
adb1ced45c
chore(bailian-kb-dsh): 更新版本号至0.1.19
...
- 将package.json中的版本号从0.1.18更新为0.1.19
- 保持项目描述和关键词不变
- 为发布新版本做准备
2026-08-24 21:19:29 +08:00
69c1fb9f08
feat(managed-agent): 增加托管 Agent 全面管理命令集及功能实现
...
- 扩展 CLI 命令，新增托管 Agent 相关全部操作命令包括能力、Agent、环境、技能、保管库、部署、会话及文件管理
- 实现 Agent 列表、详情、版本、搜索等功能
- 实现环境列表、详情及搜索功能
- 实现部署列表、详情、搜索、运行、暂停与恢复功能
- 实现会话的搜索、更新、归档及事件操作功能
- 实现文件上传、列表、下载、删除及搜索功能
- 添加托管 Agent API 操作能力展示命令
- 统一异常处理及输出格式支持，支持 JSON 与表格展示
- 完善分页、查询参数及权限验证逻辑，支持按需筛选与翻页
- 新增输入输出文件支持与控制台保护机制，提升命令行体验和稳定性
2026-08-24 20:15:09 +08:00
e023af5be3
docs(kb-dsh): 优化知识服务清单注入与错误处理提示
...
- 补查型工具(service_find)确认不暴露服务清单，避免与catalog冲突
- 清单内容策略扩展，0服务时注入明确禁止猜测id的提示
- 工具描述保持静态，上下文消息注入带source的UserMessage实现动态清单
- bl命令及安装提示仅在动态文本中出现，避免静态描述频繁消耗token
- 错误处理中4xx刷新并追加服务清单，0服务状态下明确提示不重试须创建部署
- service-catalog新增无服务提示及刷新服务列表构建函数
- service-context调整使用新清单构建逻辑，缓存空时注入无服务通知
- tools调整描述文案，提示来自上下文消息且拒绝猜测
- README补充bl CLI安装使用说明
- 测试补充无服务情况注入提示及刷新列表文本内容校验
2026-08-24 19:34:15 +08:00
若麒