Merge remote-tracking branch 'origin/master' into worktree/web-theme-settings-integration-fde706

apps/web/tests/seeded-history.e2e.ts

@@ -3,12 +3,11 @@
 // else covers: sidebar cold listing, the implicit resume/attach inside the
 // history RPC, history-page tool views, and the client's log-ordered transcript
 // events — with ZERO model calls in replay (no replay fixture; a stray stream
-// fails loud on the open llm seam). The cold session also carries the one
-// keyless command-row surfaces: the seeded manual `/compact` lifecycle folds
-// into its checkpoint, while an Access-chip pick later runs `/permission` on
-// the host. The seed is a recorded
-// fixture under the
-// same record discipline as every other: DSH_SNAPSHOT=record drives the turn
+// fails loud on the open llm seam). The cold session also carries keyless
+// command-row surfaces: the seeded manual `/compact` lifecycle folds into its
+// checkpoint, an Access-chip pick later runs `/permission` on the host, and
+// `/feedback` pins its expandable correlation ids. The seed is a recorded
+// fixture under the same record discipline as every other: DSH_SNAPSHOT=record drives the turn
 // live through the composer (real read tool against seeded workspace files)
 // and harvests seed.jsonl; replay/refresh seed it cold and only render.
 import { readFile, writeFile, mkdir } from 'node:fs/promises'
@@ -32,9 +31,9 @@ import { newEnglishPage, saveFailureShot } from './support.ts'
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/seeded-history', import.meta.url))
 const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
 const UI_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/ui.expected.md', import.meta.url))
-// The command-row golden: the same conversation after one /permission switch,
-// which is the only surface that shows a settled command row's copy.
+// Command-row goldens over the same conversation after direct host commands.
 const COMMAND_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/command-row.expected.md', import.meta.url))
+const FEEDBACK_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/feedback-row.expected.md', import.meta.url))
 const MODE = webSnapshotMode()
 const SEED_ID = 'seeded-history-web-e2e'
 
@@ -446,6 +445,44 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await compareOrRefreshGolden(COMMAND_ROW_EXPECTED, snapshot, MODE)
   }, 60_000)
 
+  it.skipIf(MODE === 'record')('reports full feedback correlation ids in an expandable two-line row', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-feedback-row'))
+    const previousDshHome = process.env.DSH_HOME
+    process.env.DSH_HOME = scaffold.harnessHome
+    try {
+      const input = page.locator('textarea').first()
+      await input.fill('/feedback the diff view is unreadable')
+      await input.press('Enter')
+      const row = page.locator('[data-variant="others"]').filter({
+        hasText: `Feedback recorded for session ${SEED_ID}`,
+      })
+      await row.waitFor({ timeout: 10_000 })
+      const disclosure = row.locator('[data-expandable]')
+      expect(await disclosure.getAttribute('aria-expanded')).toBe('false')
+      await disclosure.click()
+      await expect.poll(() => disclosure.getAttribute('aria-expanded')).toBe('true')
+
+      const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
+      if (agent === undefined) throw new Error('seeded session did not attach an agent')
+      const done = agent.session.events.filter(event => event.type === 'command/done').at(-1)
+      if (done?.type !== 'command/done') throw new Error('feedback command did not settle')
+      const [sessionLine, userLine, extraLine] = done.data.text?.split('\n') ?? []
+      expect(sessionLine).toBe(`Feedback recorded for session ${SEED_ID}`)
+      expect(userLine).toMatch(/^User: [0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i)
+      expect(extraLine).toBeUndefined()
+      const userId = userLine?.slice('User: '.length)
+      if (userId === undefined) throw new Error('feedback command omitted the user id')
+
+      const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
+        .split(SEED_ID).join('{{seededId}}')
+        .split(userId).join('{{userId}}')
+      await compareOrRefreshGolden(FEEDBACK_ROW_EXPECTED, snapshot, MODE)
+    } finally {
+      if (previousDshHome === undefined) delete process.env.DSH_HOME
+      else process.env.DSH_HOME = previousDshHome
+    }
+  }, 60_000)
+
   it.skipIf(MODE === 'record')('fits short logged context without a scrollport', async () => {
     const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
     if (agent === undefined) throw new Error('seeded session did not attach an agent')
@@ -473,6 +510,6 @@ describe('web e2e: seeded history renders through cold resume', () => {
     // stream would have failed the turn loudly. Cleanliness pins the wire.
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'seed.jsonl', 'ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'feedback-row.expected.md', 'seed.jsonl', 'ui.expected.md'])
   })
 })

apps/web/tests/snapshots/seeded-history/feedback-row.expected.md

@@ -0,0 +1,53 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Use the read tool twice" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}"
+- button "Copy":
+  - img
+- button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.":
+  - 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 "Read a.txt":
+  - img
+  - img
+  - text: Read
+  - button "a.txt"
+- button "Read b.txt":
+  - img
+  - img
+  - text: Read
+  - button "b.txt"
+- button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.":
+  - img
+  - img
+  - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed.
+- paragraph: DONE
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s
+- button "compact Compacted 5 history items (~{{tokens}} tokens)"
+- button "Context injection AGENTS.md":
+  - img
+  - img
+  - text: Context injection AGENTS.md
+- img
+- text: permission preset read-only
+- 'button "feedback Feedback recorded for session {{seededId}} User: {{uuid}}" [expanded]':
+  - img
+  - text: "feedback Feedback recorded for session {{seededId}} User: {{uuid}}"
+- text: "Feedback recorded for session {{seededId}} User: {{uuid}}"
+- textbox "Message the agent"
+- button "Commands":
+  - img
+- 'button "Access mode, current: Read Only"': Read Only
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Send message" [disabled]
+- 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