Merge remote-tracking branch 'origin/master' into worktree/custom-deepseek-models

# Conflicts:
#	packages/host/apiproxy/README.i18n.yaml

apps/web/tests/live-interactions.e2e.ts

@@ -27,11 +27,12 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/live-interactions', import.meta.url))
 const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
-// One golden per interactive end-state: what the user is left looking at
-// after cancel, after a non-retryable failure (pins the FIXME(web-error-surface)
-// gap as a reviewable artifact: NO error copy in the tree), and after retry
-// recovery — three genuinely different terminal surfaces of one fixture.
+// One golden pins the stable mid-turn loading state; the other three capture
+// what the user is left looking at after cancel, after a non-retryable failure
+// (pins the FIXME(web-error-surface) gap as a reviewable artifact: NO error
+// copy in the tree), and after retry recovery.
 const CANCEL_EXPECTED = join(SNAPSHOT_DIR, 'cancel.expected.md')
+const LOADING_EXPECTED = join(SNAPSHOT_DIR, 'loading.expected.md')
 const ERROR_EXPECTED = join(SNAPSHOT_DIR, 'error-auth.expected.md')
 const RETRY_EXPECTED = join(SNAPSHOT_DIR, 'retry.expected.md')
 const MODE = webSnapshotMode()
@@ -133,6 +134,12 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
     // The marker IS the synchronization: the stream is provably parked in the
     // hang (prefix chunks delivered to the loop) before the stop click.
     await expect.poll(() => existsSync(marker), { timeout: 15_000 }).toBe(true)
+    await expect.poll(
+      () => page.getByRole('status').filter({ hasText: 'Deep diving...' }).isVisible(),
+      { timeout: 10_000 },
+    ).toBe(true)
+    const loadingSnapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)
+    await compareOrRefreshGolden(LOADING_EXPECTED, loadingSnapshot, MODE)
     await page.getByRole('button', { name: 'Stop generating' }).click()
     await settled
     expect(turnEndReasons(sessionEvents).at(-1)).toBe('aborted')
@@ -231,7 +238,7 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
 
   it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
     await assertFixtureInventory(SNAPSHOT_DIR, [
-      'session.jsonl', 'cancel.expected.md', 'error-auth.expected.md', 'retry.expected.md',
+      'session.jsonl', 'cancel.expected.md', 'loading.expected.md', 'error-auth.expected.md', 'retry.expected.md',
     ])
   })
 })

apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md

@@ -16,7 +16,7 @@
   - treeitem "workspace 1 session" [expanded]:
     - img
     - text: workspace 1 session
-  - treeitem "New Session now" [selected]
+  - treeitem "New Session" [selected]
 - button "Settings":
   - img
   - text: Settings

apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md

@@ -16,7 +16,7 @@
   - treeitem "workspace 1 session" [expanded]:
     - img
     - text: workspace 1 session
-  - treeitem "New Session now" [selected]
+  - treeitem "New Session" [selected]
 - button "Settings":
   - img
   - text: Settings

apps/web/tests/snapshots/live-interactions/loading.expected.md

@@ -0,0 +1,23 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Edit":
+  - img
+- paragraph: partial
+- status: Deep diving...
+- textbox "Message the agent"
+- button "Commands":
+  - img
+- 'button "Access mode, current: Full access"': Full access
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Stop generating"

apps/web/tests/snapshots/queue-actions/collapsed.expected.md

@@ -12,6 +12,7 @@
 - button "Edit":
   - img
 - paragraph: partial
+- status: Deep diving...
 - button "2 queued messages"
 - textbox "Message the agent"
 - button "Commands":

apps/web/tests/snapshots/queue-actions/editing.expected.md

@@ -12,6 +12,7 @@
 - button "Edit":
   - img
 - paragraph: partial
+- status: Deep diving...
 - button "2 queued messages" [disabled] [expanded]
 - list:
   - listitem:

apps/web/tests/snapshots/queue-actions/ui.expected.md

@@ -12,6 +12,7 @@
 - button "Edit":
   - img
 - paragraph: partial
+- status: Deep diving...
 - list:
   - listitem:
     - text: Edited queue item

apps/web/tests/snapshots/steering/mid-steer.expected.md

@@ -19,6 +19,7 @@
   - img
   - img
   - text: Ask question waiting
+- status: Deep diving...
 - region "Ready to continue?":
   - text: Checkpoint
   - heading "Ready to continue?" [level=2]

apps/web/tests/workspace-management.e2e.ts

@@ -1,10 +1,13 @@
 // Web e2e scenarios: workspace management — the create-by-name dialog, the
 // rename round trip over the real wire (workspace.rename RPC + durable
 // registry), duplicate-name pre-check, the flat "In one list" view with its
-// persisted group-by preference, and the session hover card. Zero model
-// calls: workspace.create/rename are host RPCs with no model involvement,
-// and the one session row the flat/hover scenarios need comes from a seeded
-// fixture (the seeded-history seed reused verbatim — no new recording).
+// persisted group-by preference, the session hover card, and the session
+// archive round trip (row menu → workspace.archiveSession RPC → durable
+// global set → row hidden across reload). Zero model calls:
+// workspace.create/rename/archiveSession are host RPCs with no model
+// involvement, and the one session row the flat/hover/archive scenarios need
+// comes from a seeded fixture (the seeded-history seed reused verbatim — no
+// new recording).
 import { mkdir, readFile, stat, writeFile } from 'node:fs/promises'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
@@ -413,6 +416,55 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
+  it('archives the seeded session from its row menu, hiding it durably across reload', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-archive'))
+    // The seeded session lives under Ungrouped (expanded by the hover-card
+    // test's gesture; converge again for order independence).
+    const ungroupedRow = page.getByText('Ungrouped', { exact: true }).locator('..').locator('..')
+    const ungroupedSection = ungroupedRow.locator('..')
+    await expect.poll(async () => {
+      if (await ungroupedRow.getAttribute('aria-expanded') !== 'true') {
+        await page.getByText('Ungrouped', { exact: true }).click()
+        await page.waitForTimeout(50)
+      }
+      return await ungroupedRow.getAttribute('aria-expanded')
+    }, { timeout: 5_000 }).toBe('true')
+    // Anchor on session rows (the rows carrying a session actions button),
+    // not a positional index, and assert the single-stray assumption loudly
+    // so a fixture gaining a second stray fails here instead of archiving
+    // the wrong row. CSS attribute match, not getByRole: the button is
+    // display:none until its row hovers, and role queries skip hidden nodes.
+    const sessionRows = ungroupedSection.locator('[role="treeitem"]')
+      .filter({ has: page.locator('button[aria-label^="Session actions for "]') })
+    await expect.poll(() => sessionRows.count(), { timeout: 10_000 }).toBe(1)
+    const sessionRow = sessionRows.first()
+    const rowTitle = await sessionRow.locator('[class*="title"]').innerText()
+    // Row menu: hover reveals the actions button; Archive session commits
+    // without a confirmation dialog (non-destructive: log + accounting stay).
+    await sessionRow.hover()
+    await sessionRow.getByRole('button', { name: `Session actions for ${rowTitle}` }).click()
+    await page.getByRole('menuitem', { name: 'Archive session' }).click()
+    // The row disappears on the archive-set echo; with no other visible
+    // stray, the whole Ungrouped bucket withdraws.
+    await expect.poll(() => page.getByText(rowTitle, { exact: true }).count(), { timeout: 10_000 }).toBe(0)
+    await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }).toBe(0)
+    // Durable on the host: the registry-global set carries the id while the
+    // session log itself stays in persistence untouched.
+    expect([...scaffold.ctx.workspace.archivedSessionIds]).toEqual([SessionId(SEED_ID)])
+    expect((await scaffold.ctx.sessionPersistence.list()).map(header => header.id)).toContain(SessionId(SEED_ID))
+    // Reload: the hidden state is rebuilt from the workspace.list baseline.
+    const warningStart = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+    await expect.poll(() => page.getByText('Workspaces', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
+    // The archived row must not resurface (the Ungrouped bucket itself may
+    // reappear if selection restore lands on another stray — not this test's
+    // concern).
+    expect(await page.getByText(rowTitle, { exact: true }).count()).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 90_000)
+
   it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
     expect(tripwire.warnings).toEqual([])
     // The directory-browser aria golden is this spec's one owned artifact;