Yichen Jiang
96c44c83d4
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.
2.4 KiB
2.4 KiB
- banner:
- navigation "Session hierarchy":
- 'button "Plan a small change: add" [disabled]'
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"
- navigation "Session hierarchy":
- img
- text: "plan Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}"
- button "Copy":
- img
- button "Branch into a new conversation" [disabled]:
- img
- text: Available only on the last message of a completed turn
- button "Context injection":
- img
- img
- text: Context injection
- 'button "Think The user wants me to plan a small change to add a
--greetingflag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."':- img
- img
- text: "Think The user wants me to plan a small change to add a
--greetingflag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."
- paragraph:
- text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with
- code: exit_plan_mode
- text: .
- 'button "Tool call exit_plan_mode · # Add
--greetingflag to CLI"':- img
- img
- text: "Tool call exit_plan_mode · # Add
--greetingflag to CLI"
- 'button "Think The plan was approved. The user''s last instruction says: "Once the plan is approved, reply with the single word DONE and stop." So I should just reply with DONE and stop."':
- img
- img
- text: "Think The plan was approved. The user's last instruction says: "Once the plan is approved, reply with the single word DONE and stop." So I should just reply with DONE and stop."
- paragraph: DONE
- button "Copy":
- img
- button "Branch into a new conversation":
- img
- 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 "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 LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 51% Input 10.2K tok · Output 346 tok