deepseek-harness/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md at c84ad45f26ad4105a27ce6c2e335a8ca5f386190

Files

Hypatia May c84ad45f26 test(web): re-record composer stats goldens over merged master

Reapplies this branch's one added occupancy segment on top of master's own
golden refresh from the preceding merge. Recorded with DSH_SNAPSHOT=refresh,
not hand-edited: an attempt to strip the co-recorded context-injection
affordance out of these files broke replay, which is the suite working as
intended — a golden must match the real render byte-for-byte.

Web replay is now 76/77. The one failure, queue-actions ("edits and removes
exact pending occurrences", counts 2 user/message events where it expects 1),
reproduces at pristine origin/master and is untouched here.

2026-07-30 14:55:01 +08:00

2.1 KiB

Raw Blame History

banner:
- navigation "Session hierarchy":
  - button "Use only Cordis tools. First" [disabled]
- tablist:
  - tab "Chat" [selected]
  - tab "Trajectory"
text: "Use only Cordis tools. First call cordis_inspect with what "temporary". Then call cordis_mount with this exact code: "return { name: \"snapshot-noop\", apply(ctx) {} }". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop. {{clock}}"
button "复制":
- img
button "在新对话中分支":
- img
button "编辑":
- img
button "▸ 上下文注入"
button "Think The user wants me to:":
- img
- img
- text: "Think The user wants me to:"
button:
- img
- img
text: Inspect temporary
'button "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."':
- img
- img
- text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
button [expanded]:
- img
text: Mount temporary Plugin typescript
button "复制"
code: "return { name: "snapshot-noop", apply(ctx) {} }"
'button "Think The id is "dyn-1". Now step 3: call cordis_unmount with that id."':
- img
- img
- text: "Think The id is "dyn-1". Now step 3: call cordis_unmount with that id."
button:
- img
- img
text: Unmount temporary Plugin dyn-1
button "Think All three calls succeeded. I should now reply exactly "CORDIS_UI_DONE" and stop.":
- img
- img
- text: Think All three calls succeeded. I should now reply exactly "CORDIS_UI_DONE" and stop.
paragraph: CORDIS_UI_DONE
button "复制":
- img
button "在新对话中分支":
- img
text: {{clock}}
textbox "Message the agent"
button "Add attachment":
- img
'button "Access mode, current: Danger Full Access"': Danger Full Access
button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img
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

2.1 KiB Raw Blame History

2.1 KiB

Raw Blame History