75699966d4
Merge remote-tracking branch 'origin/main' into feat/memory
2026-09-10 20:43:23 +08:00
2220f932b5
Merge pull request #198 from modelstudioai/codex/release-1.23.0
...
chore(release): prepare 1.23.0
2026-09-10 17:37:40 +08:00
d9134d6f0a
feat(memory): 增加长度校验及限流提示并强化安全确认
...
- 在多条命令中统一添加对 userId 和 memoryLibraryId 长度的校验
- 新增 profile schema 名称、描述及属性字段长度断言
- 为 delete 内存节点命令添加高风险删除确认机制及 --yes 标志
- 增加账号级别限流说明，提示遇 HTTP 429 需降低请求频率
- 统一移除分散的长度常量，集中定义并使用共享常量
- 相关 E2E 测试覆盖长度限制和高风险操作确认情况
- 支持内存消息内容多样化，新增 MemoryContentPart 类型定义
- 内存文档中新增限流描述及删除命令风险提示，强调确认操作要求
2026-09-10 17:31:42 +08:00
5c390fad74
chore(release): prepare 1.23.0
2026-09-10 16:57:58 +08:00
6218637f7c
Merge pull request #194 from modelstudioai/feat/global-watermark-config
...
Feat/global watermark config
2026-09-10 16:49:33 +08:00
0c7ba721a7
Merge remote-tracking branch 'origin/main' into feat/global-watermark-config
2026-09-10 15:39:12 +08:00
0dbf071368
Merge pull request #197 from modelstudioai/feat/speech-vocabulary
...
Add ASR instant hotwords, context, and vocabulary CRUD
2026-09-10 15:11:35 +08:00
75a7100702
feat(memory): 完善记忆及画像相关命令支持并统一参数
...
- 在 CLI 文档中新增记忆 live 场景说明与变量需求
- 扩展 CLI 命令集，添加记忆画像 Profile 的增删改查功能
- 统一所有记忆相关命令加入 workspace 和 library 参数支持
- 记忆添加命令支持自定义 meta_data，完善输入校验和互斥说明
- 记忆删除、列表、获取用户画像等命令增加工作空间参数支持
- 画像模板相关命令新增分页参数及属性操作接口
- 重构知识命令共享模块，移除重复的 workspace 解析实现，统一导出
- 优化命令输出格式，文本模式下显示更多详细信息和异常提示
- 提供完整的示例参数，增强命令使用说明和提示文档
2026-09-10 14:40:39 +08:00
16e30686f0
fix(speech): validate --words JSON before auth
...
Invalid vocabulary JSON was parsed in run(), so CI without an API key failed with AUTH(3) instead of USAGE(2).
2026-09-10 14:28:16 +08:00
7803d91e3f
chore: fixed Formatting issues
2026-09-10 14:07:37 +08:00
c2d17707c0
feat(speech): add instant hotwords, context, and vocabulary CRUD
2026-09-10 14:02:05 +08:00
1dfb4400cc
Merge branch 'main' of github.com:modelstudioai/cli into feat/global-watermark-config
2026-09-10 10:33:23 +08:00
fd2077b373
feat: pipeline watermark 处理完善
2026-09-09 17:40:49 +08:00
2090293f85
Merge pull request #192 from modelstudioai/feat/managed-agent-ci
...
fix(managed-agent): improve project initialization and build validation
2026-09-08 19:39:03 +08:00
a245359792
chore(release): prepare 1.22.0
2026-09-08 19:26:17 +08:00
19bd5a5ea8
test(managed-agent): remove obsolete build confirmation flag
2026-09-08 19:01:47 +08:00
e262f2e574
chore(deps): bump OpenAgentPack SDK to 0.7.1
2026-09-08 18:01:41 +08:00
180aac9f28
fix(managed-agent): show absolute YAML paths during init
2026-09-08 16:57:15 +08:00
3477a08dad
feat(config): add profile-level watermark setting
2026-09-08 16:33:40 +08:00
aa1484264e
fix(managed-agent): improve project initialization and build validation
2026-09-08 14:46:56 +08:00
2767491ce6
Merge pull request #182 from modelstudioai/feat/managed-agent-ci
...
Feat/managed agent ci 添加managed agents模块的ci能力
2026-09-07 21:42:35 +08:00
efb832815a
chore(release): prepare 1.21.0
2026-09-07 21:11:51 +08:00
902516bbad
fix(managed-agent): check latest Playground version before launch
...
Resolve the requested npm version before reusing local builds or running processes, fetch mismatched versions on demand, and preserve explicit binary overrides. Add launcher regression tests and sync the SDK 0.7.0 lockfile.
2026-09-07 20:46:07 +08:00
f44fb2e95f
refactor(managed-agent): use SDK project service subpaths
...
Replace standalone project packages with @openagentpack/sdk 0.7.0 and update project/version imports.
The pnpm lockfile remains pending until SDK 0.7.0 is published to npm; this integration has been validated against the local SDK build.
2026-09-07 19:58:47 +08:00
c6b9931d6f
feat(managed-agent): integrate directory resource scaffolds and safe builds
2026-09-04 17:20:50 +08:00
a92c58420b
fix(managed-agent): use CLI credentials for directory projects
...
Make project init fully offline, stop generating project-local credential files, bind Publish to the reviewed plan fingerprint, remove the unsafe Apply refresh-only mode, and document Agent-owned File mounts.
2026-09-04 11:22:11 +08:00
bcf68a31f3
Merge remote-tracking branch 'origin/main' into feat/managed-agent-ci
...
# Conflicts:
# packages/commands/package.json
# packages/commands/src/commands/managed-agent/apply.ts
# packages/commands/src/commands/managed-agent/init.ts
# packages/commands/tests/e2e/managed-agent.e2e.test.ts
# skills/bailian-managed-agent/SKILL.md
# skills/bailian-managed-agent/reference/index.md
# skills/bailian-managed-agent/reference/managed-agent.md
2026-09-03 11:38:44 +08:00
8e5dd127a9
Merge pull request #177 from modelstudioai/feat/cma-command
...
Feat/cma command 补齐managed agent cli能力
2026-09-03 11:00:47 +08:00
4f41eaabc2
chore(release): prepare 1.20.0
2026-09-03 10:47:23 +08:00
e1634c40ed
chore(deps): upgrade @openagentpack/sdk to 0.5.0
2026-09-02 22:26:33 +08:00
4c5688ad4a
feat(managed-agent)!: restrict CLI to Bailian provider
...
Remove multi-provider CLI flags and reject non-Bailian provider configs while preserving SDK support.
2026-09-02 19:23:40 +08:00
176961dc56
feat(managed-agent): hide capabilities command from public CLI
2026-09-02 15:33:50 +08:00
888031562f
Merge pull request #189 from modelstudioai/docs/console-gateway-backend-attribution
...
docs(telemetry): update Console Gateway backend attribution
2026-09-02 15:18:51 +08:00
d017954ae8
docs(telemetry): update Console Gateway backend attribution
2026-09-02 15:11:24 +08:00
9d19558645
feat(managed-agent): enforce high-risk confirmation for runtime operations
2026-09-02 15:07:22 +08:00
a9200a3f85
Merge remote-tracking branch 'origin/main' into feat/cma-command
...
# Conflicts:
# packages/commands/src/commands/managed-agent/session-delete.ts
# packages/commands/tests/e2e/managed-agent.e2e.test.ts
# skills/bailian-managed-agent/SKILL.md
# skills/bailian-managed-agent/reference/managed-agent.md
2026-09-02 14:51:49 +08:00
83d7982ecb
feat(managed-agent): support creating agents with remote and local skills
2026-09-02 14:36:22 +08:00
d33cb71cc7
Merge pull request #180 from modelstudioai/feat/runtime-risk-confirmation
...
feat(cli): add unified confirmation for high-risk operations
2026-09-02 14:31:18 +08:00
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
zeyu.fz