From 901bd575e1786d1a8f7d12e54fdbf435c5ebf21a Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 30 Jul 2026 14:44:30 +0800 Subject: [PATCH] test(web): refresh web aria goldens stale on master These 15 goldens already failed replay at origin/master d17fcd3a6 before this branch touched anything: master's committed expectations lag master's own code (localized sidebar labels, the access-mode control becoming a button, message IconActions and clock placement, context-injection affordances). Recorded by running DSH_SNAPSHOT=refresh over the web suite in a pristine worktree at that commit, then importing the result here, so the stats-line change in the following commit shows up as its own reviewable delta rather than mixed into pre-existing drift. Two web e2e specs still fail at that same pristine commit for non-golden reasons and are untouched here: queue-actions (counts 2 user/message events where it expects 1) and details-session-lifecycle (times out waiting for a New session button). --- .../snapshots/code-mode-round/ui.expected.md | 16 +++--------- .../cordis-tool-round/ui.expected.md | 26 +++---------------- .../snapshots/fresh-round-trip/ui.expected.md | 20 +++++--------- .../lifecycle-chrome/hero.expected.md | 14 ++++------ .../lifecycle-chrome/reloaded.expected.md | 11 +++----- .../live-interactions/cancel.expected.md | 11 +++----- .../live-interactions/error-auth.expected.md | 8 ++---- .../live-interactions/retry.expected.md | 11 +++----- .../snapshots/message-actions/ui.expected.md | 16 +++--------- .../question-composer/answered.expected.md | 16 +++--------- .../queue-actions/editing.expected.md | 1 + .../snapshots/queue-actions/ui.expected.md | 1 + .../snapshots/seeded-history/ui.expected.md | 16 +++--------- .../snapshots/steering/mid-steer.expected.md | 7 +---- .../snapshots/steering/settled.expected.md | 16 +++--------- docs/architecture.md | 4 +-- docs/architecture.zh.md | 4 +-- 17 files changed, 57 insertions(+), 141 deletions(-) diff --git a/apps/web/tests/snapshots/code-mode-round/ui.expected.md b/apps/web/tests/snapshots/code-mode-round/ui.expected.md index f20e3528c4..436ee2c8f8 100644 --- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md +++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md @@ -16,11 +16,6 @@ - img - img - text: "Think The user wants me to write a single `run_code` program that:" -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img @@ -37,16 +32,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 8.3k uncached input · 252 output · 9k cache read · cache hit 52% · context 7% of 128k · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 52% Input 17.2K tok · Output 252 tok diff --git a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md index 4c38143e51..d18e1c631c 100644 --- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md +++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md @@ -16,11 +16,6 @@ - img - img - text: "Think The user wants me to:" -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img @@ -29,11 +24,6 @@ - img - img - text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code." -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button [expanded]: - img - text: Mount temporary Plugin typescript @@ -43,11 +33,6 @@ - img - img - text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id." -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img @@ -61,16 +46,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 15.3k uncached input · 312 output · 51.2k cache read · cache hit 77% · context 13% of 128k · 1 turns · 4 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 4 steps Tool call {{duration}} Cache hit 77% Input 66.5K tok · Output 312 tok diff --git a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md index fba4176c10..6bd81e2252 100644 --- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md +++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md @@ -16,13 +16,10 @@ - img - img - text: Think The user wants me to run a simple bash command and reply with "DONE". -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - img -- text: Bash Echo the test string +- text: Bash Echo the test string 已完成 workspace echo WEB_E2E_OK +- button "复制" +- text: WEB_E2E_OK - button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".": - img - img @@ -32,16 +29,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 219 uncached input · 111 output · 15.5k cache read · cache hit 99% · context 6% of 128k · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 99% Input 15.7K tok · Output 111 tok diff --git a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md index ee6c1a7475..fb14ed8fa2 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md @@ -1,9 +1,9 @@ -- button "New session" -- button "Collapse sidebar": +- button "新建会话" +- button "收起侧边栏": - img -- button "New session": +- button "新建会话": - img - - text: New Session + - text: 新会话 - text: Workspaces - button "Group by": - img @@ -28,11 +28,7 @@ - textbox "Describe what you want to build" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md index 81a2bb680f..ba14e4ffda 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md @@ -21,16 +21,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 109 uncached input · 21 output · 7.7k cache read · cache hit 99% · context unknown · 1 turns · 1 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 21 tok diff --git a/apps/web/tests/snapshots/live-interactions/cancel.expected.md b/apps/web/tests/snapshots/live-interactions/cancel.expected.md index 71a67a93ef..76de5f81df 100644 --- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md +++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md @@ -18,16 +18,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 0 uncached input · 0 output · 0 cache read · context 4% of 128k · 1 turns · 1 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 1 steps Input 0 tok · Output 0 tok diff --git a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md index 7fd444dc9d..551e9370ff 100644 --- a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md +++ b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md @@ -12,14 +12,10 @@ - button "编辑": - img - button "▸ 上下文注入" -- textbox "Message the agent" +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/live-interactions/retry.expected.md b/apps/web/tests/snapshots/live-interactions/retry.expected.md index 5521ccc8bc..62ab5eeb65 100644 --- a/apps/web/tests/snapshots/live-interactions/retry.expected.md +++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md @@ -21,16 +21,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 110 uncached input · 79 output · 7.7k cache read · cache hit 99% · context 4% of 128k · 1 turns · 1 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 79 tok diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index e25ac348c5..f9f771d46d 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -16,11 +16,6 @@ - img - img - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel. -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - img - text: Read - button "a.txt" @@ -36,16 +31,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 339 uncached input · 135 output · 15.5k cache read · cache hit 98% · context unknown · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 deepseek-v4-flash": - text: deepseek-v4-flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/apps/web/tests/snapshots/question-composer/answered.expected.md b/apps/web/tests/snapshots/question-composer/answered.expected.md index bd03429898..55670871b4 100644 --- a/apps/web/tests/snapshots/question-composer/answered.expected.md +++ b/apps/web/tests/snapshots/question-composer/answered.expected.md @@ -16,11 +16,6 @@ - img - img - text: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that. -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img @@ -34,16 +29,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} cache hit 95% · 8,769 tokens · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 95% Input 8.6K tok · Output 180 tok diff --git a/apps/web/tests/snapshots/queue-actions/editing.expected.md b/apps/web/tests/snapshots/queue-actions/editing.expected.md index 6a17d57df5..f2c56646b2 100644 --- a/apps/web/tests/snapshots/queue-actions/editing.expected.md +++ b/apps/web/tests/snapshots/queue-actions/editing.expected.md @@ -11,6 +11,7 @@ - img - button "编辑": - img +- button "▸ 上下文注入" - paragraph: partial - list: - listitem: diff --git a/apps/web/tests/snapshots/queue-actions/ui.expected.md b/apps/web/tests/snapshots/queue-actions/ui.expected.md index 05d3e3b347..bab7ab62f8 100644 --- a/apps/web/tests/snapshots/queue-actions/ui.expected.md +++ b/apps/web/tests/snapshots/queue-actions/ui.expected.md @@ -11,6 +11,7 @@ - img - button "编辑": - img +- button "▸ 上下文注入" - paragraph: partial - list: - listitem: diff --git a/apps/web/tests/snapshots/seeded-history/ui.expected.md b/apps/web/tests/snapshots/seeded-history/ui.expected.md index 84e91053d1..c5b9d706af 100644 --- a/apps/web/tests/snapshots/seeded-history/ui.expected.md +++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md @@ -15,11 +15,6 @@ - img - img - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel. -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - img - text: Read - button "a.txt" @@ -35,16 +30,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 339 uncached input · 135 output · 15.5k cache read · cache hit 98% · context unknown · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 deepseek-v4-flash": - text: deepseek-v4-flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/apps/web/tests/snapshots/steering/mid-steer.expected.md b/apps/web/tests/snapshots/steering/mid-steer.expected.md index 665394647b..19fc143373 100644 --- a/apps/web/tests/snapshots/steering/mid-steer.expected.md +++ b/apps/web/tests/snapshots/steering/mid-steer.expected.md @@ -16,15 +16,10 @@ - img - img - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that. -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img -- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]} 151 uncached input · 115 output · 7.7k cache read · cache hit 98% · context 4% of 128k · 1 turns · 1 steps" +- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}" - region "Ready to continue?": - text: Checkpoint - heading "Ready to continue?" [level=2] diff --git a/apps/web/tests/snapshots/steering/settled.expected.md b/apps/web/tests/snapshots/steering/settled.expected.md index 9a57ea85f8..ae88935e00 100644 --- a/apps/web/tests/snapshots/steering/settled.expected.md +++ b/apps/web/tests/snapshots/steering/settled.expected.md @@ -16,11 +16,6 @@ - img - img - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that. -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} - button: - img - img @@ -34,16 +29,13 @@ - img - button "在新对话中分支": - img -- text: {{clock}} 323 uncached input · 156 output · 15.5k cache read · cache hit 98% · context 6% of 128k · 1 turns · 2 steps -- textbox "Message the agent" +- text: {{clock}} +- textbox "给智能体发消息" - button "Add attachment": - img -- text: Danger Full Access -- combobox "Access mode": - - option "Read Only" - - option "Workspace Write" - - option "Danger Full Access" [selected] +- 'button "Access mode, current: Danger Full Access"': Danger Full Access - button "选择模型，当前 DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 156 tok diff --git a/docs/architecture.md b/docs/architecture.md index 7cf1805db5..1fd9bd128d 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -94,7 +94,7 @@ forever: assemble system prompt and tool schemas snapshot the derived messages (the reconstruction boundary) 'step/start' - agent/request (config only) -> prepare reasoning/default + context under turn signal -> log request/header -> obtain outer llm/stream handle (frozen request; prepared calls registration-bound) -> agent/model-request (live, contained attempt) -> iterate + agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound) 'assistant/chunk' 'assistant/message' schedule tool calls by ctx.tools.executionMode: @@ -153,7 +153,7 @@ Log-only events may sit between turns. Owners append through `Session`, flushing Messages use typed blocks from merge-extensible `ContentBlockMap`; the pattern also types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New blocks coordinate adapters, UI, compaction, token metering, and persistence; replay measurements live in [token-meter.md](core-data-structures/token-meter.md). -Streaming uses chunks and `BlockAssembler`. When the outer `llm/stream` returns a handle, AgentLoop emits contained, non-durable, non-replayed `agent/model-request` attempt metadata—not proof of provider I/O. `agent/request-error` may retry. Replay crosses routes only through a shared adapter ([contract](core-data-structures/llm-streaming.md)). +Streaming uses raw chunks and `BlockAssembler`. Each `LlmAdapter.stream()` is one provider attempt; adapters report normalized failure facts, and a handling `agent/request-error` plugin returns a retry action. The loop logs chunks, successful provenance, and replay state. Remote adapters use per-read idle watchdogs. Replay crosses routes only through a shared adapter instance ([contract](core-data-structures/llm-streaming.md)). ## Extension And Composition diff --git a/docs/architecture.zh.md b/docs/architecture.zh.md index 0c9a136ac4..8521f09c6e 100644 --- a/docs/architecture.zh.md +++ b/docs/architecture.zh.md @@ -94,7 +94,7 @@ forever: assemble system prompt and tool schemas snapshot the derived messages (the reconstruction boundary) 'step/start' - agent/request (config only) -> prepare reasoning/default + context under turn signal -> log request/header -> obtain outer llm/stream handle (frozen request; prepared calls registration-bound) -> agent/model-request (live, contained attempt) -> iterate + agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound) 'assistant/chunk' 'assistant/message' schedule tool calls by ctx.tools.executionMode: @@ -153,7 +153,7 @@ idle inject: 消息使用从可合并扩展的 `ContentBlockMap` 派生的类型化块；同一模式也为 `MessageSource`、`FinishReason`、`TurnTrigger` 和 `TurnEndReason` 定义类型。新增块会协调适配器、UI、压缩、token 计量和持久化；回放计量见 [token-meter.md](core-data-structures/token-meter.md)。 -流式输出使用分片和 `BlockAssembler`。外层 `llm/stream` 返回句柄时，AgentLoop 会发出 `agent/model-request` 尝试元数据；该通知的失败会被收容，元数据不会持久化或回放，但这并不能证明提供方 I/O 已开始。`agent/request-error` 可以重试。回放仅通过共用适配器跨路由传递（[契约](core-data-structures/llm-streaming.md)）。 +流式输出使用原始分片和 `BlockAssembler`。每次 `LlmAdapter.stream()` 调用代表一次提供方尝试；适配器报告标准化的故障事实，负责处理的 `agent/request-error` 插件会返回重试动作。循环会记录分片、成功结果的来源信息和回放状态。远程适配器使用逐次读取空闲看门狗。回放仅通过共用的适配器实例跨路由传递（[契约](core-data-structures/llm-streaming.md)）。 ## 扩展与组合