From 96c44c83d44ec0bf665f6660c9b58f970d0b157a Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 5 Aug 2026 17:55:49 +0800 Subject: [PATCH] test(web): stabilize and refresh the aria goldens for the speed readings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The TTFT and tok/s readings divide by measured wall time, so they are not reproducible: the same replayed scenario yielded 69 and 70 tok/s on consecutive local runs, and a 3 ms replayed stream reads 26333 tok/s. Baking those into committed goldens made the Web lane flaky by construction, and the goldens for the readings themselves were never refreshed. Three fixes, then a refresh: The footer's decorative dots are `aria-hidden`, so the readings concatenated into one accessible string — `Ran for 13sTTFT 0.2s12 tok/s`. That is a real defect on its own (a reader hears one run-on instead of three facts) and it also denied `{{duration}}` the word boundary it matches on, so even the previously-stable `Ran for` duration started leaking raw. The separators now carry flanking spaces. `normalizeAria` gains `{{throughput}}` beside `{{duration}}`, and its duration alternation accepts the stats line's compact `2m42s` as well as the message-chrome template's `2m 42s` — the compact form had no pattern at all, which is why `LLM 382m39s` survived the first refresh. Refreshed 17 goldens. They also record that the stats line's `LLM` group now renders at all: it folds assistant `timing`, which the live transcript adapter only began attaching in this branch, so the group was previously dead in Chat. Verified by running the lane in replay three times after the refresh: 41/41 files green each time, goldens untouched. Before this change two consecutive runs disagreed on both the values and the failure count. --- ...08-04-web-latency-throughput-metrics.i18n.yaml | 4 ++-- .../2026-08-04-web-latency-throughput-metrics.md | 2 ++ ...026-08-04-web-latency-throughput-metrics.zh.md | 2 ++ apps/web/tests/scaffold.ts | 15 ++++++++++++--- .../tests/snapshots/bash-abort-row/ui.expected.md | 2 +- .../snapshots/code-mode-round/ui.expected.md | 5 +++-- .../snapshots/cordis-tool-round/ui.expected.md | 5 +++-- .../snapshots/fresh-round-trip/ui.expected.md | 5 +++-- .../lifecycle-chrome/reloaded.expected.md | 5 +++-- .../live-interactions/cancel.expected.md | 2 +- .../snapshots/live-interactions/retry.expected.md | 5 +++-- .../snapshots/markdown-images/ui.expected.md | 2 +- .../snapshots/message-actions/ui.expected.md | 6 +++--- .../snapshots/plan-review/approved.expected.md | 5 +++-- .../question-composer/answered.expected.md | 5 +++-- .../snapshots/queue-actions/preserved.expected.md | 2 +- .../seeded-history/command-row.expected.md | 4 ++-- .../tests/snapshots/seeded-history/ui.expected.md | 4 ++-- .../tests/snapshots/steering/settled.expected.md | 5 +++-- .../subagent-conversation/ui.expected.md | 7 ++++--- .../snapshots/web-search-round/ui.expected.md | 5 +++-- .../src/client/chat/MessageIconActions.tsx | 9 +++++++++ 22 files changed, 69 insertions(+), 37 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml index 1cf49844ab..f8b22ddc13 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md -2026-08-04-web-latency-throughput-metrics.md: f891ce8d2f772c66d5affba2d89694d0eeb681b6 -2026-08-04-web-latency-throughput-metrics.zh.md: e62f5ad6341cffe052118871b57e27f5380c2fd1 +2026-08-04-web-latency-throughput-metrics.md: d7c816ba1d6380bd257fe358d26e3c2e72c3fbe1 +2026-08-04-web-latency-throughput-metrics.zh.md: c9e5f63da576b6b850a55dc2a741b59fd729705c diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md index f891ce8d2f..d7c816ba1d 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md @@ -27,3 +27,5 @@ The stats line reuses the same step reading in its window fold: `deriveStats` ac ## Consequences A settled in-window turn's footer reveals `TTFT`/`tok/s` on hover after the wall time, and the stats line shows window-average latency and throughput beside its wall times, all without new session events or host changes. Metrics degrade by omission: providers or steps without timing or usage samples drop individual figures rather than rendering zeros. Older history outside the loaded window stays uncounted, recorded in the package README's stats-line limitation. + +Both readings divide by measured wall time, so neither is reproducible: the same replayed scenario yielded 69 and 70 tok/s on consecutive local runs, and a 3 ms replayed stream reads 26333 tok/s. The Web aria goldens therefore normalize throughput to `{{throughput}}` beside the existing `{{duration}}`, and the footer's decorative separators gained flanking spaces — without them the readings concatenate into one accessible string (`Ran for 13sTTFT 0.2s12 tok/s`), which both loses the reading boundaries a screen reader needs and denies `{{duration}}` the word boundary it matches on. diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md index e62f5ad634..c9e5f63da5 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md @@ -27,3 +27,5 @@ assistant 页脚把读数追加到既有 hover 显示的时间附属元素中、 ## 后果 窗口内已结算轮次的页脚在 hover 时于实际耗时之后显示 `首 token`／`tok/s`，统计行在墙钟时间旁显示窗口平均延迟与吞吐，全程不新增会话事件、不改 host。指标以省略的方式退化：没有计时或 usage 采样的提供方或步骤只是丢掉对应数字，而不会渲染成零。已加载窗口之外的更早历史仍不计入，已记录在包 README 的统计行限制中。 + +两个读数都以实测墙钟时间作分母，因此都不可复现：同一个回放场景在本机连续两次跑出 69 与 70 tok/s，而一段 3 毫秒的回放流会读成 26333 tok/s。因此 Web aria golden 在既有的 `{{duration}}` 之外，把吞吐归一化为 `{{throughput}}`；页脚的装饰性分隔符也补上了两侧空格——没有它们，这些读数会连成一整串无障碍文本（`Ran for 13sTTFT 0.2s12 tok/s`），既让屏幕阅读器失去读数之间的边界，也让 `{{duration}}` 失去它赖以匹配的词边界。 diff --git a/apps/web/tests/scaffold.ts b/apps/web/tests/scaffold.ts index a4498e0cf2..cf3a6384e0 100644 --- a/apps/web/tests/scaffold.ts +++ b/apps/web/tests/scaffold.ts @@ -523,8 +523,14 @@ export async function seedSession(scaffold: WebScaffold, fixtureText: string, id } /** - * Normalize an aria snapshot: uuid, cwd, workspace-basename, and duration - * volatility collapse to stable tokens. + * Normalize an aria snapshot: uuid, cwd, workspace-basename, duration, and + * decode-throughput volatility collapse to stable tokens. + * + * Throughput needs a token for the same reason durations do, and no fixture + * can supply one: the figure divides a replayed step's output tokens by the + * wall time the local run took to stream them, so it moves between two runs + * on one machine (measured 69 → 70 tok/s) and swings wildly on a fast replay + * (26333 tok/s for a 3 ms stream). */ function normalizeAria(snapshot: string, workspaceCwd: string): string { // The session heading renders the workspace's basename, not the full @@ -534,14 +540,17 @@ function normalizeAria(snapshot: string, workspaceCwd: string): string { .split(workspaceCwd).join('{{cwd}}') .split(base).join('{{workspace}}') .replace(/[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi, '{{uuid}}') + // The optional space in `\d+m ?\d+s` covers both minute spellings: the + // stats line's compact `2m42s` and the message-chrome template's `2m 42s`. .replace( - /~\d+(?:y(?: \d+mo)?|mo(?: \d+d)?)|\b(?:\d+d(?: \d+h(?: \d+m \d+s)?)?|\d+h \d+m \d+s|\d+m \d+s|\d+(?:\.\d+)?s|\d+(?:\.\d+)?ms)\b/g, + /~\d+(?:y(?: \d+mo)?|mo(?: \d+d)?)|\b(?:\d+d(?: \d+h(?: \d+m \d+s)?)?|\d+h \d+m \d+s|\d+m ?\d+s|\d+(?:\.\d+)?s|\d+(?:\.\d+)?ms)\b/g, duration => duration.startsWith('~') ? duration : '{{duration}}', ) .replace( /约\d+(?:年(?:\d+个月)?|个月(?:\d+天)?)|\d+(?:天(?:\d+小时(?:\d+分\d+秒)?)?|小时\d+分\d+秒|分\d+秒|(?:\.\d+)?秒)/g, duration => duration.startsWith('约') ? duration : '{{duration}}', ) + .replace(/\d+(?:\.\d+)?(?= tok\/s(?!\w))/g, '{{throughput}}') // Message IconActions clocks widen by calendar day/year; collapse every // shape so goldens stay stable across midnight and year boundaries. .replace(/\d{4}年\d{1,2}月\d{1,2}日 \d{2}:\d{2}/g, '{{clock}}') diff --git a/apps/web/tests/snapshots/bash-abort-row/ui.expected.md b/apps/web/tests/snapshots/bash-abort-row/ui.expected.md index 8d544cefc1..7c975351d3 100644 --- a/apps/web/tests/snapshots/bash-abort-row/ui.expected.md +++ b/apps/web/tests/snapshots/bash-abort-row/ui.expected.md @@ -30,4 +30,4 @@ - text: Select model - img - button "Send message" [disabled] -- text: 1 turns · 1 steps Tool call {{duration}} Cache hit 0% Input 10 tok · Output 10 tok +- text: 1 turns · 1 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 0% Input 10 tok · Output 10 tok 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 42758237bb..6270a5429f 100644 --- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md +++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md @@ -36,7 +36,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -44,5 +44,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "7% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 7% of 128K Cache hit 52% Input 17.2K tok · Output 252 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s 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 85ef8932b2..2442e9d927 100644 --- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md +++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md @@ -51,7 +51,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -59,5 +59,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "13% of context used" - button "Send message" [disabled] -- text: 1 turns · 4 steps Tool call {{duration}} Context 13% of 128K Cache hit 77% Input 66.5K tok · Output 312 tok +- text: 1 turns · 4 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s 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 159e77d5bc..37ae3ba520 100644 --- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md +++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md @@ -31,7 +31,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -39,5 +39,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "6% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 99% Input 15.7K tok · Output 111 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 99% Input 15.7K tok · Output 111 tok diff --git a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md index f6f965337e..5e554f289d 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md @@ -23,7 +23,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -31,5 +31,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "6% of context used" - button "Send message" [disabled] -- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 21 tok +- text: 1 turns · 1 steps LLM {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s 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 cd06310db0..156b30f82a 100644 --- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md +++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md @@ -20,7 +20,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img diff --git a/apps/web/tests/snapshots/live-interactions/retry.expected.md b/apps/web/tests/snapshots/live-interactions/retry.expected.md index 5f834e15f0..91ddca897a 100644 --- a/apps/web/tests/snapshots/live-interactions/retry.expected.md +++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md @@ -25,7 +25,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -33,5 +33,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "6% of context used" - button "Send message" [disabled] -- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 79 tok +- text: 1 turns · 1 steps LLM {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 99% Input 7.8K tok · Output 79 tok diff --git a/apps/web/tests/snapshots/markdown-images/ui.expected.md b/apps/web/tests/snapshots/markdown-images/ui.expected.md index ed42dfec84..fbdbff395a 100644 --- a/apps/web/tests/snapshots/markdown-images/ui.expected.md +++ b/apps/web/tests/snapshots/markdown-images/ui.expected.md @@ -19,7 +19,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index 815acaef1d..81c2796e5a 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -20,7 +20,7 @@ - img - button "Branch into a new conversation" [disabled]: - img -- text: Available only on the last message of a completed turn 7/25 {{clock}}Ran for {{duration}} +- text: Available only on the last message of a completed turn 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - button "Read a.txt": - img - img @@ -46,7 +46,7 @@ - img - button "Branch into a new conversation": - img -- text: 7/25 {{clock}}Ran for {{duration}} +- text: 7/25 {{clock}} Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img @@ -55,4 +55,4 @@ - text: Select model - img - button "Send message" [disabled] -- text: 2 turns · 3 steps Tool call {{duration}} Cache hit 98% Input 7.8K tok · Output 103 tok +- text: 2 turns · 3 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 98% Input 7.8K tok · Output 103 tok diff --git a/apps/web/tests/snapshots/plan-review/approved.expected.md b/apps/web/tests/snapshots/plan-review/approved.expected.md index 2120c32408..0bcf2c5dca 100644 --- a/apps/web/tests/snapshots/plan-review/approved.expected.md +++ b/apps/web/tests/snapshots/plan-review/approved.expected.md @@ -36,7 +36,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -44,5 +44,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "4% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 4% of 128K Cache hit 51% Input 10.2K tok · Output 346 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 51% Input 10.2K tok · Output 346 tok diff --git a/apps/web/tests/snapshots/question-composer/answered.expected.md b/apps/web/tests/snapshots/question-composer/answered.expected.md index a54b7dcd75..8176008f25 100644 --- a/apps/web/tests/snapshots/question-composer/answered.expected.md +++ b/apps/web/tests/snapshots/question-composer/answered.expected.md @@ -31,7 +31,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -39,5 +39,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "3% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 3% of 128K Cache hit 95% Input 8.6K tok · Output 180 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 95% Input 8.6K tok · Output 180 tok diff --git a/apps/web/tests/snapshots/queue-actions/preserved.expected.md b/apps/web/tests/snapshots/queue-actions/preserved.expected.md index 2ce0077a2e..3c76d0d623 100644 --- a/apps/web/tests/snapshots/queue-actions/preserved.expected.md +++ b/apps/web/tests/snapshots/queue-actions/preserved.expected.md @@ -20,7 +20,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} Edited queue item {{clock}} +- text: {{clock}} Ran for {{duration}} Edited queue item {{clock}} - button "Copy": - img - button "Branch into a new conversation" [disabled]: diff --git a/apps/web/tests/snapshots/seeded-history/command-row.expected.md b/apps/web/tests/snapshots/seeded-history/command-row.expected.md index 9338167f2c..fb2f5e4cba 100644 --- a/apps/web/tests/snapshots/seeded-history/command-row.expected.md +++ b/apps/web/tests/snapshots/seeded-history/command-row.expected.md @@ -33,7 +33,7 @@ - img - button "Branch into a new conversation": - img -- text: 7/25 {{clock}}Ran for {{duration}} +- text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - button "Context compacted View compaction summary": - img - text: Context compacted View compaction summary @@ -51,4 +51,4 @@ - text: Select model - img - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/apps/web/tests/snapshots/seeded-history/ui.expected.md b/apps/web/tests/snapshots/seeded-history/ui.expected.md index f24aaac77c..f804046ad2 100644 --- a/apps/web/tests/snapshots/seeded-history/ui.expected.md +++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md @@ -33,7 +33,7 @@ - img - button "Branch into a new conversation": - img -- text: 7/25 {{clock}}Ran for {{duration}} +- text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - button "Context compacted View compaction summary": - img - text: Context compacted View compaction summary @@ -49,4 +49,4 @@ - text: Select model - img - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/apps/web/tests/snapshots/steering/settled.expected.md b/apps/web/tests/snapshots/steering/settled.expected.md index 00f1b33206..c68451bc19 100644 --- a/apps/web/tests/snapshots/steering/settled.expected.md +++ b/apps/web/tests/snapshots/steering/settled.expected.md @@ -37,7 +37,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -45,5 +45,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "6% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 98% Input 15.8K tok · Output 156 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 98% Input 15.8K tok · Output 156 tok diff --git a/apps/web/tests/snapshots/subagent-conversation/ui.expected.md b/apps/web/tests/snapshots/subagent-conversation/ui.expected.md index 561277b8ee..c3f1038650 100644 --- a/apps/web/tests/snapshots/subagent-conversation/ui.expected.md +++ b/apps/web/tests/snapshots/subagent-conversation/ui.expected.md @@ -28,7 +28,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} Now give the same explanation to a human reader. {{clock}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s Now give the same explanation to a human reader. {{clock}} - button "Copy": - img - button "Branch into a new conversation" [disabled]: @@ -43,10 +43,11 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img - 'button "Access mode, current: Workspace Write"': Workspace Write +- button "6% of context used" - button "Send message" [disabled] -- text: 2 turns · 2 steps Context 6% of 128K Cache hit 99% Input 15.6K tok · Output 158 tok +- text: 2 turns · 2 steps LLM {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 99% Input 15.6K tok · Output 158 tok diff --git a/apps/web/tests/snapshots/web-search-round/ui.expected.md b/apps/web/tests/snapshots/web-search-round/ui.expected.md index 45098769f7..8fdd4d8585 100644 --- a/apps/web/tests/snapshots/web-search-round/ui.expected.md +++ b/apps/web/tests/snapshots/web-search-round/ui.expected.md @@ -23,7 +23,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s - textbox "Message the agent" - button "Commands": - img @@ -31,5 +31,6 @@ - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img +- button "0% of context used" - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Context 0% of 128K Cache hit 0% Input 22 tok · Output 7 tok +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 0% Input 22 tok · Output 7 tok diff --git a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx index 640189bf63..e1481c437f 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx @@ -71,24 +71,33 @@ export function MessageIconActions({ }, 1000) }) }, [copied, text]) + // The dot is decorative and stays hidden, but its margins separate the + // readings only on screen: without the flanking spaces a reader hears one + // run-on string ("Ran for 13sTTFT 0.2s12 tok/s") instead of three facts. const clockEl = time === undefined ? null : ( {formatMessageClock(time, t, day)} {runMs !== undefined && ( <> + {' '} · + {' '} {t('message.ranFor', { duration: formatRunDuration(runMs, t) })} )} {ttftMs !== undefined && ( <> + {' '} · + {' '} {t('message.ttft', { seconds: formatLatencySeconds(ttftMs) })} )} {tokensPerSecond !== undefined && ( <> + {' '} · + {' '} {t('message.tokensPerSecond', { tps: formatTokensPerSecond(tokensPerSecond) })} )}