leokun
65edad6a21
chore: release v0.1.0-beta.9
2026-08-24 19:13:50 +08:00
leokun
58daa91c90
chore: release v0.1.0-beta.8
2026-08-24 18:43:44 +08:00
leokun
eb26b17ba0
fix: stabilize todo state and responses streams
2026-08-24 18:43:44 +08:00
leokun
95fb9be967
chore: release v0.1.0-beta.7
2026-08-24 18:21:49 +08:00
leokun
89631bdab0
fix: adjust secondary button height and enhance MultiCombobox input behavior
2026-08-24 18:06:49 +08:00
leokun
fe17e15e75
chore: release v0.1.0-beta.6
2026-08-24 15:46:25 +08:00
leokun
24177fcb6e
fix: restore service entrypoint and clean checks
2026-08-24 15:46:14 +08:00
leokun
7fa4953883
fix: harden provider, tool, and desktop behavior
2026-08-24 15:37:42 +08:00
leokun
4bb4ca5c8d
chore: release v0.1.0-beta.5
2026-08-24 12:33:17 +08:00
leokun
4ddd3adb3f
feat: normalize MCP tool names and enhance OpenAI response handling
2026-08-24 12:22:11 +08:00
leookun
1a0cf89fe1
fix: set OpenAI Responses image detail to auto
2026-08-24 12:00:49 +08:00
leookun
81a1afdae9
feat: add model connectivity tests and harden cursor heartbeats
2026-08-24 09:57:28 +08:00
leookun
6170778de9
feat: add update indicators and stabilize Cursor streams
2026-08-24 05:24:07 +08:00
leookun
0f23a9a9c3
feat: add configurable Cursor TAB routing
2026-08-24 04:35:28 +08:00
leookun
8a4fc5076a
fix token usage average
2026-08-24 03:49:57 +08:00
leookun
b5199de6f1
Merge branch 'refactor/0.1.0-beta'
2026-08-24 03:46:56 +08:00
leookun
b74291af79
stabilize cursor request context and release workflow
2026-08-24 03:44:56 +08:00
leookun
2075b61763
release desktop beta 0.1.0-beta.1
2026-08-24 03:22:18 +08:00
leookun
03075952a6
feat(i18n): add i18n support
2026-08-24 03:08:29 +08:00
leokun
4c2efb05c2
Merge pull request #304 from leookun/refactor/0.1.0-beta
...
Refactor/0.1.0-beta
2026-08-24 02:54:36 +08:00
leookun
2abffcc835
merge main into refactor after Tauri rewrite
2026-08-24 02:53:35 +08:00
leookun
4053a7fb20
refactor: rebuild desktop app with Tauri
2026-08-24 02:49:00 +08:00
leokun
564f2bdcae
Merge pull request #313 from leookun/codex/main-worktree
...
Codex/main worktree
2026-08-20 14:00:13 +08:00
leookun
77c8e31a09
update prompt
2026-08-20 13:59:31 +08:00
leookun
eb68375306
update prompt
2026-08-20 12:56:49 +08:00
leokun
e9d3845de0
Merge pull request #295 from Sxuan-Coder/feat/config-import-export
...
feat(config): 支持完整配置导入导出
2026-08-19 11:36:43 +08:00
leokun
d4bfa8b938
Merge pull request #308 from Sxuan-Coder/fix/replay-dangling-tool-call-output
...
fix: 修复工具调用与结果之间穿插文本时，调用被误删导致 Responses API 400（#307）
2026-08-19 11:36:29 +08:00
leokun
dead4477be
Merge pull request #306 from ProtectCookies/main
...
fix(network): 修复长耗时请求被误报「Network disconnected」中断的问题
2026-08-19 11:36:02 +08:00
上玄
b7f8237f3b
fix: keep tool call in provider sanitize when text interleaves call and result
...
trimDanglingAssistantToolCalls in the provider router held the same
consecutive-tool-message assumption as the replay projector: when a
model emits function_call items before explanation text within one
response (e.g. gpt-5.3-codex-spark), the sanitized sequence becomes
assistant[tool_call] -> assistant[text] -> tool[result] and responded
calls were stripped at the provider boundary even though the projector
already replayed them correctly. The orphan tool result then forced the
Responses adapter to synthesize a placeholder function_call with empty
arguments, degrading the arguments the model sees on in-loop requests.
Widen the response collection window to skip interleaved plain
assistant text messages and drop orphan tool results, mirroring the
projector fix.
2026-08-14 19:59:47 +08:00
上玄
5d04b5b08b
fix: keep tool call replay when assistant text interleaves call and result
...
trimReplayDanglingAssistantToolCalls only collected tool results that
immediately followed the assistant tool-call message. Models such as
gpt-5.3-codex-spark may emit the function_call item before the
explanation text within one response, so history replay order becomes
assistant[tool_call] -> assistant[text] -> tool[result]. The call was
misjudged as dangling and stripped while the tool result survived,
producing a function_call_output without a matching function_call that
the Responses API rejects with 400.
- widen the response collection window to skip interleaved plain
assistant text messages, and drop orphan tool results in the same pass
- synthesize a placeholder function_call (or drop the output when the
tool name is unknown) in normalizeOpenAIResponsesInput so conversations
already persisted with corrupted history can resume
2026-08-14 16:51:45 +08:00
杨超
a90c8d9560
fix(network): 修复proto打包报错问题
2026-08-14 14:13:43 +08:00
杨超
e9dc2e098d
fix(network): 修复长耗时请求被误报「Network disconnected」中断的问题
...
客户端扩展在慢请求（如提交信息生成）开始约 10 秒后会探测
NetworkService/IsConnected，非 200 应答即判定断网并中止进行中的请求。
此前该探测落入通配路由返回 404，导致模型仍在正常返回时界面先报断连。
- host.go: 注册 IsConnected 精确路由，恒定以 200 + 空 IsConnectedResponse 应答
- client.go: newProtoMessage 补齐 aiserver.v1.IsConnectedResponse 类型，
避免 mock 编码失败导致探测返回 502
- state_db.go: 新增强开 statsig gate 机制（cursorStateEnabledStatsigGates），
强制启用 disable_network_change_monitor_local 从源头关闭该探测；
disableCursorStatsigGates 泛化为 syncCursorStatsigGateOverrides
2026-08-14 12:19:47 +08:00
leokun
a3ec2a0dfc
release: 0.0.48
2026-08-12 20:32:19 +08:00
leokun
38472a3c63
Merge pull request #299 from leookun/fix/issue-298-per-user-ca
...
Fix shared root CA by generating one per installation
2026-08-12 20:11:43 +08:00
leokun
2b8d1c9e3d
fix: generate a per-installation root CA
2026-08-12 20:04:29 +08:00
上玄
3fc04eeb4f
feat(config): 支持完整配置导入导出
2026-08-12 09:34:02 +08:00
leokun
7a67e76617
Merge pull request #270 from zfscgy/feat/image-read
...
Feat/image read: 本地文件读取工具支持读取图片
2026-08-12 01:22:35 +08:00
leookun
08ce12aa55
Merge branch 'main' into codex/pr270-content-addressed-read-images
...
# Conflicts:
# frontend/src/i18n/generated/catalog.json
2026-08-12 01:14:24 +08:00
leookun
8f8d28880d
feat(forwarder): persist read images by content hash
2026-08-12 01:10:14 +08:00
leokun
988ba63d40
Merge pull request #291 from Sxuan-Coder/feat/optional-reasoning-effort
...
fix(model): 支持不设置 reasoning effort
2026-08-11 23:44:52 +08:00
上玄
edd59dc684
fix(model): 支持不设置推理强度
2026-08-11 21:18:10 +08:00
leokun
da5fa34a4d
更新 README-CN.md
2026-08-10 23:19:34 +08:00
leokun
4bd2359282
Update README-CN.md
2026-08-10 23:14:14 +08:00
leokun
7838ffc6a2
Update README.md
2026-08-10 23:13:48 +08:00
leokun
ee30775be1
Update Chinese translation link in README
2026-08-10 23:10:17 +08:00
leokun
80a5093aa9
Update README.md
2026-08-10 23:09:41 +08:00
leokun
b9742b1667
Update README-CN.md
2026-08-10 23:09:04 +08:00
leokun
7d3e74be59
Update README.md
2026-08-10 23:08:36 +08:00
leokun
1285bf9d62
Update README-CN.md
2026-08-10 23:05:44 +08:00
leokun
7a724595eb
Update README.md
2026-08-10 23:05:31 +08:00
leokun