260 Commits

Author SHA1 Message Date
故璃 65c0fe9604 feat: add skill commend & skill install 2026-07-29 17:04:17 +08:00
lisheng.lisheng adc89f635d Merge branch 'main' of github.com:modelstudioai/cli into feat/config-ui-enhancements
# Conflicts:
#	packages/commands/tests/config-ui.test.ts
2026-07-28 20:43:42 +08:00
lisheng.lisheng bbf45a5961 Merge branch 'main' of github.com:modelstudioai/cli into feat/config-agent-fix
# Conflicts:
#	CHANGELOG.md
#	CHANGELOG.zh.md
#	packages/cli/package.json
#	packages/commands/package.json
#	packages/core/package.json
#	packages/kscli/package.json
#	packages/runtime/package.json
#	skills/bailian-cli/SKILL.md
2026-07-28 20:33:16 +08:00
lisheng.lisheng 3988e701e1 chore(cli): 发布 1.11.0 版本,更新 agent 配置功能
- 新增 `bl config agent --key` / `--region`,支持控制台编码 API Key 本地解码和区域派生 Token Plan 地址
- 新增 `bl config agent --context-window`,设置 OpenClaw 配置的上下文窗口大小,默认 256000
- 新增 `bl config agent --wire-api`,支持选择 Codex 配置的通信协议,兼容旧版 chat 协议并提示警告
- 变更 Codex 默认写入通信协议为 `responses`,适配新版 Codex 不再支持旧 chat 模式
- 变更 Qwen Code 代理配置改用 `DASHSCOPE_API_KEY` 环境变量替代 `BAILIAN_CLI_API_KEY`
- 修复各 agent 配置格式不匹配问题,支持 JSONC 格式和官方结构,完善模型白名单与计费元数据
- 修复配置写入逻辑,合并保持用户自定义配置,避免覆盖及重复条目,优化显示名保留
- 更新所有相关包版本号至 1.11.0,包含 bailian-cli、commands、core、kscli、runtime
- 更新 bailian-cli 技能元数据版本号至 1.11.0
2026-07-28 20:27:28 +08:00
若麒 be6ddb6126 chore(release): prepare 1.11.2 2026-07-28 19:24:40 +08:00
clh02467605 25ac5c9c84 fix: revert change about defaultTextModel 2026-07-28 18:05:18 +08:00
clh02467605 8ef91fe395 test(core): align token-plan preset expectation with qwen3.7-plus 2026-07-28 17:29:41 +08:00
clh02467605 5d9e22de8f Merge remote-tracking branch 'refs/remotes/origin/main' into fix/web-search-and-thinking 2026-07-28 17:20:46 +08:00
clh02467605 20e3555b84 fix(text,auth): drop enable_thinking retry and omit the field by default
Pass through model constraint errors instead of auto-retrying, switch token-plan default text model to qwen3.7-plus, and align related e2e expectations.
2026-07-28 17:19:05 +08:00
若麒 4c4e7afb83 chore(release): prepare 1.11.1 2026-07-28 16:07:29 +08:00
若麒 17c52fb86f Merge branch 'main' into fix/default-model 2026-07-28 15:46:46 +08:00
rendianmeng 871c667e97 docs: install shell md 2026-07-28 13:49:51 +08:00
若麒 eadd92327f chore(release): prepare 1.11.0 2026-07-28 13:28:11 +08:00
故璃 467756b319 feat: update manifest.json 2026-07-28 10:17:16 +08:00
clh02467605 7ad14a79b9 Merge branch 'main' of github.com:modelstudioai/cli into fix/web-search-and-thinking 2026-07-28 09:25:34 +08:00
clh02467605 8211268bd8 fix(text,mcp): keep thinking_budget on enable_thinking retry and hint MCP activation on 404 2026-07-28 09:25:02 +08:00
chenanran555 9819eb6ddc feat(agent): 非bailian provider也走鉴权逻辑 2026-07-27 21:33:36 +08:00
qcq01083097 58252911a8 fix(image): correct wan2.5/2.6 size presets and wanx-v1 dated aliases 2026-07-27 21:09:32 +08:00
chenanran555 93c9149e45 feat(agent): 鉴权分离线命令和在线命令,仅对bailian provider鉴权 2026-07-27 19:51:56 +08:00
clh02467605 36ebd63716 fix(text): omit enable_thinking by default and retry when API requires false
Non-streaming chat no longer forces enable_thinking=false, which breaks
thinking-only models. Retry once with false only when the server demands it.
2026-07-27 16:51:11 +08:00
故璃 bd17c27023 feat: index.json protocol adapter 2026-07-27 15:41:04 +08:00
故璃 87c37994f2 feat: update skill commend group 2026-07-27 12:30:20 +08:00
qcq01083097 c4f5bb09c6 fix(image): resolve size and prompt_extend by model profile
Stop inferring size/prompt_extend from sync vs async; use per-family sizeProfile. wanx*-imageedit uses function+base_image_url; bare qwen-image uses the fixed resolution table.
2026-07-27 10:17:09 +08:00
qcq01083097 9a13700390 fix(image): route text-to-image and image-edit by model family
Fix wanx/wan2.x-t2i, wan2.5-i2i, z-image, and qwen-image-plus hitting the wrong endpoint, and add routing unit tests plus dry-run coverage.
2026-07-27 10:16:25 +08:00
故璃 ebbd173b79 feat: update manifest.json path 2026-07-25 08:43:38 +08:00
故璃 8dd786287f feat: add skill commend 2026-07-24 19:56:53 +08:00
rendianmeng d30fb2ae68 feat(release): distribute binaries as per-platform zips 2026-07-24 15:33:15 +08:00
chenanran555 1d589c5178 Merge remote-tracking branch 'origin/main' into feat/cma 2026-07-24 14:52:21 +08:00
chenanran555 9cad1994e7 feat(agent): validate by client apiKey auth type 2026-07-24 14:50:30 +08:00
若麒 92ee845bdd fix(core): normalize model base URL to origin 2026-07-23 19:31:02 +08:00
rendianmeng 66a797203c multi channel install test 2026-07-23 17:34:30 +08:00
chenanran555 64335a6201 feat(agent): rename cli command to managed-agent 2026-07-23 16:46:06 +08:00
故璃 90a44d7140 feat: llm wiki sync 2026-07-23 15:31:57 +08:00
inhai e1caee99f2 feat(config-ui): MCP management, skill zip install, and UI polish
- MCP: editable JSON config in the detail drawer with secret masking and
  mask-preserving writes; create/update/delete across claude-code, qwen-code,
  opencode, cursor, windsurf, gemini, qoderwork, openclaw and Claude Desktop
- Skills: upload a .zip and install into any agent's skills root (self-contained
  ZIP reader, zip-slip safe); scan more roots (openclaw workspace, qoderwork,
  windsurf/codeium, gemini antigravity, workbuddy)
- Markdown: GFM table rendering in the skill detail drawer
- Layout: collapsible grouped sidebar with icons + persistent state, responsive
  breakpoint, wider main, single-line tile titles, 2-line description clamp,
  round icon run buttons, custom file picker, modal spacing
- Server: /api/mcp POST/DELETE, /api/skill/install, binary upload reader,
  constant-time token compare, CSP/no-store headers, error logging
2026-07-23 10:52:26 +08:00
chenanran555 7cbd61dd5c Merge remote-tracking branch 'origin/main' into feat/cma
# Conflicts:
#	packages/commands/src/commands/auth/login.ts
#	packages/commands/src/commands/config/set.ts
#	packages/commands/src/index.ts
#	packages/core/src/client/index.ts
#	packages/core/src/config/schema.ts
#	skills/bailian-cli/reference/auth.md
#	skills/bailian-cli/reference/config.md
#	skills/bailian-cli/reference/index.md
2026-07-22 16:38:46 +08:00
chenanran555 1c9dac24e9 feat(cma): login时初始化agent相关的baseUrl 2026-07-22 14:20:24 +08:00
chenanran555 d6bd38a46a feat(agent): agent相关cli命令的client层功能,对齐cli client的基础能力 2026-07-22 13:40:28 +08:00
若麒 d11b55b956 chore(release): prepare 1.10.1 2026-07-22 11:30:43 +08:00
Gong Shiqi 440cbfe6ae Merge pull request #114 from modelstudioai/feat/token-plan-default-models
feat: update Token Plan defaults and support local image inputs
2026-07-22 10:52:35 +08:00
若麒 81539005cc Merge branch 'main' into feat/token-plan-default-models 2026-07-22 09:55:39 +08:00
若麒 4c566fd60e feat(token-plan): support local images with base64 data URIs
- convert local images to Base64 for Token Plan image and video commands
- preserve the existing OSS upload flow for standard API Key profiles
- use wan2.7-image as the default image model with the sync endpoint
- hide full Base64 image content in dry-run output
- add Token Plan compatibility tests and update related docs
2026-07-22 09:54:54 +08:00
rendianmeng 3b779a708d feat: node engines limit change 2026-07-21 13:55:38 +08:00
若麒 4ca3e2de80 feat(config): update token-plan default models
- switch the default text model to qwen3.8-max-preview
- add dedicated T2V, I2V, and R2V model defaults
- persist and consume per-mode video model settings
- enable thinking when validating the qwen3.8 preview model
2026-07-20 16:44:53 +08:00
若麒 39f12e1a78 chore(release): prepare 1.10.0 2026-07-19 16:47:29 +08:00
故璃 d08edf0cd8 feat: sync wiki data from oss by fc 2026-07-17 16:43:06 +08:00
若麒 a03ba673be fix(auth): clear model base URL on full logout 2026-07-17 15:57:23 +08:00
若麒 92719a1a21 Merge branch 'main' into feat/cli-access-token 2026-07-17 10:36:26 +08:00
若麒 310e6ead33 chore(release): prepare 1.9.0 2026-07-17 10:15:47 +08:00
若麒 ece0c8dd1c feat(config): activate explicit profile after successful login 2026-07-17 09:59:14 +08:00
若麒 8b91b9f35f feat: release 1.8.3 2026-07-16 16:43:22 +08:00