feat(task-chat): show web searches, model switches, waits and verification checks as dedicated rows (#19262)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Agents run through the native runner. The runner turns harness
activity into typed canonical events such as `research.*`,
`model.route.changed`, `wait.*` and the run's own verification checks.
> - The task chat flattened these events into generic tool rows. A web
search showed as "Ran Research eventType: research.started, summary: …".
The run's verification checks were dropped completely.
> - Live tests found a second break: the Rust runner core forwarded
Codex `webSearch` items without their query, action or results. The
canonical `research.*` events therefore had `query: null`.
> - This pull request keeps the full payload for these families (as
#19252 did for plans), adds small dedicated rows, and keeps the
web-search fields through the durable runner.
> - The benefit is that users see what the agent searched for, which
model actually ran, how long a wait lasts, and whether each check
passed, without opening the run log.

## Linked Issues or Issue Description

Refs #19252 (same pattern for the plan card)

**Subsystem affected**
Task chat activity rows (UI), the native run-event transcript mapping,
and the Rust runner core Codex normalizer.

**Problem or motivation**
Provider activity that the runner already maps to canonical events
reaches the task chat as unreadable generic rows. Verification checks
never appear. For Codex, the web-search query and action are lost before
they reach the canonical event.

**Proposed solution**
Keep `research`, `model_identity`, `artifact`, `review` and `wait`
events as `provider_activity` entries with their full payload. Project
the runner's `verification` items as a new `verification` family. Render
dedicated rows: a web search with its quoted query and source-domain
chips, a model switch as `from → to · reason`, a wait with a live
countdown, and green/red check lines. Keep bounded web-search and sleep
fields in the Rust normalizer.

**Alternatives considered**
A separate "Checks" block beside the final answer. We kept the checks in
the activity group, because the group summary already leads with "Check
failed" when a check fails.

## What Changed

- `ui/src/components/transcript/native-run-events.ts`: keep research,
model, artifact, review and wait events as `provider_activity` with the
full payload. Map `item.completed` items of kind `verification` to the
new `verification` family. Context, hook, safety and delegation stay on
the generic path, because other work items own them.
- `packages/adapter-utils/src/types.ts`,
`ui/src/components/task-chat/task-chat-model.ts`,
`ui/src/lib/issue-chat-messages.ts`: add the `verification`
provider-activity family.
- `ui/src/components/task-chat/task-chat-activity-presentation.ts`: add
labels: "Searched the web “query”", "Opened a web page host/path",
"Switched models a → b · reason", "Waiting 30s" / "Waited 30s", and
"Check passed" / "Check failed" / "Check not run".
- `ui/src/components/task-chat/TaskChatRunnerActivityGroup.tsx` and
`TaskChatProtocolActivityRow.tsx`: show up to three source-domain chips
under a finished search, a live countdown for a running wait, and a
check line with a tinted icon and its detail.
- `ui/src/components/task-chat/completed-activity-summary.ts`: the group
summary leads with "Check failed" when a check fails, and says "Switched
models" for a reroute.
- `ui/src/components/task-chat/transcript-adapter.ts`: verification
detail keys, and a `startedAt` timestamp that stays across lifecycle
merges (used by the countdown).
-
`packages/paperclip-runner/runner/crates/runner-core/src/provider_events.rs`:
keep bounded `query`, `action` and http(s) `results` for Codex
`webSearch` items, and `durationMs` for `sleep` items. Other item types
do not change.
- `ui/storybook/stories/tasks/task-chat-provider-activity.stories.tsx`:
new story. Its fixtures are persisted run events that go through the
production transcript path.

## Verification

- `pnpm --filter @paperclipai/ui exec vitest run
src/components/transcript src/components/task-chat
src/components/TaskChatThread.test.tsx src/adapters/paperclip-runner
src/lib`: 275 files and 3669 tests pass.
- `cargo test -p paperclip-runner-core`: all tests pass, including the
new `keeps_bounded_web_search_and_sleep_identity`.
- UI typecheck is clean. `pnpm check:token-gates` is clean. `cargo fmt
--check` is clean.
- Storybook: open "Tasks and conversations / … / Task chat / Provider
activity". It shows a settled run, a live search, a live wait countdown
and a narrow layout.
- Live test on a local worktree instance with a real Codex agent
(gpt-5.6-sol, Codex app-server 0.160). The task asked for a web search,
a parser with tests, a pause, and two checks. The task chat showed
"Searched the web “ISO 8601 week date first week Thursday conversion
calendar date”" and two green check rows ("node --test week-date.test.js
· 8 tests passed; 0 failed.", "node --check week-date.js"). The group
summary read "Ran checks". Before the runner fix, the same search had
`query: null`.

Not verified live:
- The source-domain chips. Codex 0.160 sends `results: null`, because it
keeps search results on the server. The chips appear only when a
provider reports sources. Unit tests and the story cover them.
- The wait countdown and the model-switch row. In the live run Codex
paused with a shell `sleep`, not a native `sleep` item, and no reroute
occurred. Unit tests and the story cover both.
- Claude. Its WebSearch and WebFetch calls arrive as generic tool
executions, because ACPX drops the tool metadata. They show as tool
rows, as before. The ACPX `_meta` work is separate.

## Risks

- Low risk. The change only affects how canonical events display. The
generic path stays for the families that this PR does not change.
- The Rust normalizer now persists the web-search query and the source
URLs/titles in the run events. This data was already intended for the
canonical `research.v1` event, and it is bounded (4,000 characters per
text field, 64 results, http(s) URLs only).
- A search that Codex reports with `action: other` and no query shows as
"Searched the web" with no subject.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use
(shell, file edit, browser automation) and extended reasoning.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

ui/src/components/task-chat/TaskChatProtocolActivityRow.tsx

@@ -9,6 +9,7 @@ import {
 } from "lucide-react";
 import { MarkdownBody } from "@/components/MarkdownBody";
 import { WorkspaceFileLink } from "@/components/WorkspaceFileLink";
+import { useSecondTick } from "@/hooks/useSecondTick";
 import { cn } from "@/lib/utils";
 import { useTaskChatShimmer } from "./TaskChatShimmer";
 import type {
@@ -20,6 +21,7 @@ import type {
   TaskChatWorkspaceFileItem,
 } from "./task-chat-model";
 import {
+  durationLabel,
   protocolActivityIsRunning,
   protocolActivityLabel,
   protocolActivityPresentation,
@@ -28,6 +30,7 @@ import {
 
 const COMPACT_RESEARCH_RESULT_LIMIT = 5;
 const COMPACT_WORKSPACE_FILE_LIMIT = 8;
+const RESEARCH_SOURCE_PREVIEW_LIMIT = 3;
 
 function StatusIcon({ status }: { status: "running" | "completed" | "failed" | "interrupted" | "informational" }) {
   if (status === "running") return <Loader2 className="h-3.5 w-3.5 animate-spin text-(--status-agent-running)" aria-hidden />;
@@ -228,9 +231,29 @@ function WorkspaceFileDetails({ item }: { item: TaskChatWorkspaceFileItem }) {
   );
 }
 
+/** One-line outcome for a check: its detail, or why it did not run. */
+export function verificationOutcome(item: TaskChatProviderActivityItem): string | undefined {
+  const detail = item.details.find((entry) => entry.label === "Detail")?.value;
+  if (detail) return detail;
+  const reason = item.details.find((entry) => entry.label === "Reason Code")?.value;
+  return reason ? reason.replaceAll("_", " ").replace(/^\w/, (letter) => letter.toUpperCase()) : undefined;
+}
+
+/** The full check: command and untruncated outcome, wrapped. */
+function VerificationDetails({ item }: { item: TaskChatProviderActivityItem }) {
+  const outcome = verificationOutcome(item);
+  return (
+    <div className="flex min-w-0 flex-col gap-1.5" data-testid="task-chat-verification-details">
+      {item.summary ? <p className="min-w-0 break-all font-mono text-foreground">{item.summary}</p> : null}
+      {outcome ? <p className="min-w-0 whitespace-pre-wrap break-words">{outcome}</p> : null}
+    </div>
+  );
+}
+
 function detailContent(item: TaskChatProtocolItem, neutral = false): ReactNode | null {
   switch (item.surface) {
     case "provider_activity": {
+      if (item.family === "verification") return verificationOutcome(item) ? <VerificationDetails item={item} /> : null;
       const expandable = item.details.length > 0 || item.steps.length > 0 || item.links.length > 0 || item.children.length > 0 || Boolean(item.output) || Boolean(item.outputTruncated);
       return expandable ? <ProviderDetails item={item} neutral={neutral} /> : null;
     }
@@ -257,6 +280,8 @@ function safeActivityHref(value: string | null | undefined): string | undefined
 }
 
 export function hasTaskChatProtocolActivityDetails(item: TaskChatProtocolItem): boolean {
+  // A check expands only when it has an outcome that may not fit on one line.
+  if (item.surface === "provider_activity" && item.family === "verification") return detailContent(item) !== null;
   if (item.surface === "resource") return Boolean(safeActivityHref(item.href));
   return detailContent(item) !== null || (item.surface === "provider_activity" && Boolean(item.summary?.trim()));
 }
@@ -267,7 +292,55 @@ export function TaskChatProtocolActivityDetails({ item, neutral = false }: { ite
     const href = safeActivityHref(item.href);
     return href ? <a href={href} className="text-foreground underline">{item.title}</a> : <p>{item.title}</p>;
   }
-  return <>{item.surface === "provider_activity" && item.summary ? <p className="whitespace-pre-wrap break-words">{item.summary}</p> : null}{detail}</>;
+  return <>{item.surface === "provider_activity" && item.family !== "verification" && item.summary ? <p className="whitespace-pre-wrap break-words">{item.summary}</p> : null}{detail}</>;
+}
+
+/** Source domains under a finished web search, so results are visible without expanding. */
+export function ResearchSourceStrip({ item }: { item: TaskChatProviderActivityItem }) {
+  const seen = new Set<string>();
+  const sources = item.links.flatMap((link) => {
+    const host = sourceHostname(link.href);
+    if (seen.has(host)) return [];
+    seen.add(host);
+    return [{ ...link, host }];
+  });
+  if (sources.length === 0) return null;
+  const visible = sources.slice(0, RESEARCH_SOURCE_PREVIEW_LIMIT);
+  const hidden = item.links.length - visible.length;
+  return (
+    <div className="ml-7 flex min-w-0 flex-wrap items-center gap-1 pb-0.5" data-testid="task-chat-research-sources">
+      {visible.map((source) => (
+        <a
+          key={source.href}
+          className="inline-flex min-w-0 max-w-full items-center gap-1 rounded-full border border-border px-2 py-0.5 text-(length:--text-nano) text-muted-foreground transition-colors hover:bg-muted/60 hover:text-foreground"
+          href={source.href}
+          target="_blank"
+          rel="noreferrer"
+          title={source.label}
+        >
+          <span className="truncate">{source.host}</span>
+        </a>
+      ))}
+      {hidden > 0 ? <span className="text-(length:--text-nano) text-muted-foreground">+{hidden} more</span> : null}
+    </div>
+  );
+}
+
+/** Live "12s left" for an intentional wait with a planned duration. */
+export function WaitCountdown({ item }: { item: TaskChatProviderActivityItem }) {
+  useSecondTick(true);
+  const planned = Number(item.details.find((detail) => detail.label === "Planned Duration Ms")?.value);
+  const startedAtMs = item.startedAt ? Date.parse(item.startedAt) : Number.NaN;
+  if (!Number.isFinite(planned) || !Number.isFinite(startedAtMs)) return null;
+  const remaining = Math.max(0, planned - (Date.now() - startedAtMs));
+  return <span className="shrink-0 tabular-nums" data-testid="task-chat-wait-countdown">{durationLabel(String(remaining))} left</span>;
+}
+
+export function verificationTone(item: TaskChatProviderActivityItem): string | undefined {
+  const status = item.details.find((detail) => detail.label === "Status")?.value;
+  if (status === "passed") return "text-(--status-task-icon-done)";
+  if (status === "failed") return "text-destructive";
+  return undefined;
 }
 
 function itemStatus(item: TaskChatProtocolItem): "running" | "completed" | "failed" | "interrupted" | "informational" {
@@ -304,6 +377,9 @@ export function TaskChatProtocolActivityRow({ item }: { item: TaskChatProtocolIt
       </div>
     );
   }
+  const verification = item.surface === "provider_activity" && item.family === "verification" ? item : null;
+  const runningWait = item.surface === "provider_activity" && item.family === "wait" && item.status === "running" ? item : null;
+  const research = item.surface === "provider_activity" && item.family === "research" && item.status !== "running" ? item : null;
   const detail = detailContent(item);
   const expandable = detail !== null;
   const Icon = presentation.icon;
@@ -313,11 +389,17 @@ export function TaskChatProtocolActivityRow({ item }: { item: TaskChatProtocolIt
   const row = (
     <>
       <span className="flex w-5 shrink-0 items-center justify-center">
-        <Icon className="h-3.5 w-3.5 shrink-0" aria-hidden data-testid="task-chat-protocol-activity-icon" />
+        <Icon className={cn("h-3.5 w-3.5 shrink-0", verification && verificationTone(verification))} aria-hidden data-testid="task-chat-protocol-activity-icon" />
       </span>
       <span data-conversation-tool-running={active && shimmer && item.surface === "provider_activity" && item.family === "tool_execution" ? "true" : undefined} className="flex min-w-0 flex-1 items-center gap-2 overflow-hidden">
         <span className={cn("shrink-0 font-medium", active && shimmer && "shimmer-text shimmer-text-muted")}>{label}{active ? "…" : ""}</span>
         {presentation.detail ? <span className="task-chat-collapsed-line-fade min-w-0 flex-1 font-mono text-(length:--text-micro)">{presentation.detail}</span> : null}
+        {verification && verificationOutcome(verification) ? (
+          <span className="min-w-0 shrink truncate" data-testid="task-chat-verification-detail">
+            {verificationOutcome(verification)}
+          </span>
+        ) : null}
+        {runningWait ? <WaitCountdown item={runningWait} /> : null}
       </span>
       <span className="ml-auto flex shrink-0 items-center gap-2">
         {expandable ? (
@@ -326,7 +408,7 @@ export function TaskChatProtocolActivityRow({ item }: { item: TaskChatProtocolIt
             aria-hidden
           />
         ) : null}
-        <StatusIcon status={status} />
+        {verification ? null : <StatusIcon status={status} />}
       </span>
     </>
   );
@@ -359,6 +441,7 @@ export function TaskChatProtocolActivityRow({ item }: { item: TaskChatProtocolIt
   return (
     <div className="flex min-w-0 flex-col text-xs" data-testid="task-chat-protocol-activity-row" data-activity-family={item.surface === "provider_activity" ? item.family : item.surface}>
       {activityRow}
+      {research && !open ? <ResearchSourceStrip item={research} /> : null}
       {open && detail ? (
         <div id={detailId} className="ml-2.5 mt-0.5 border-l-2 border-border py-1 pl-2.5" data-testid="task-chat-protocol-activity-detail">
           {detail}