test(runner): harden native OpenCode paid fixtures (#12833)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paid runner E2E tests verify the full control-plane path for
supported providers.
> - Native OpenCode could write the reserved terminal marker through
progress and final output.
> - The restart fixture also waited for all development assets after the
recovered UI was already usable.
> - These behaviors made two valid local runner paths fail
qualification.
> - This pull request makes the OpenCode write contract explicit and
uses the visible UI as the restart readiness gate.
> - The benefit is reliable local OpenCode qualification without weaker
duplicate detection.

## Linked Issues or Issue Description

Refs #12769
Refs #12829
Refs #12828

**What happened?**

The native OpenCode ask fixture allowed a progress tool call before the
final response. OpenCode could write the reserved terminal marker in
both places. The structured restart fixture could also time out while it
waited for `DOMContentLoaded` after the recovered UI was visible and
usable.

**Expected behavior**

The ask fixture must write the reserved marker once. The restart fixture
must continue when the recovered UI and interaction API prove that the
application is ready.

**Steps to reproduce**

1. Run the local native OpenCode ask-question paid cell.
2. Observe a run that calls `report_progress`, calls `paperclip_finish`,
and then emits the exact marker.
3. Run the local native OpenCode structured-question restart-resume cell
with a fresh Vite graph.
4. Observe that the page is usable before the navigation lifecycle event
completes.

**Paperclip version or commit**

The failures reproduced at `06cdf88bd9ac0fad82588025d23a68e810b20fd0`.
The fixes are at `f7e044e71df11a0582eafe28d2fd52ea7cd07948`.

**Deployment mode**

Local dev.

**Installation method**

Built from source.

**Agent adapter(s) involved**

OpenCode through the native runner.

## What Changed

- Require `paperclip_finish` to be the only tool call in the native ask
fixture.
- Forbid `report_progress` and other tool calls in that fixture.
- Wait for navigation commit after a server restart.
- Keep the explicit recovered UI and interaction API readiness checks.
- Add prompt contract assertions.

## Verification

- The exact two-cell paid run passed both affected cells on the AWS
runner fleet:
https://github.com/paperclipai/paperclip/actions/runs/33883334853
- Native OpenCode ask-question passed in job
https://github.com/paperclipai/paperclip/actions/runs/33883334853/job/101058952662
- Native OpenCode structured restart-resume passed in job
https://github.com/paperclipai/paperclip/actions/runs/33883334853/job/101058952823
- Prettier passed for all three changed files.
- `git diff --check` passed.
- The run-level aggregate failed only because the workflow source still
used the pre-repair lockfile on `master`. PR #12828 repairs that
lockfile.

## Risks

Low risk. The prompt change affects native ask fixtures across provider
profiles. The navigation change remains guarded by explicit UI and API
assertions.

## Model Used

OpenAI Codex, `gpt-5.6-sol`, extended reasoning, tool use, and code
execution.

## 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
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

tests/runner-e2e/catalog.test.ts

@@ -206,6 +206,12 @@ describe("runner E2E catalog", () => {
     expect(breadthHello).toContain(
       "Do not emit any assistant text, acknowledgement, or preamble before calling it",
     );
+
+    const nativeAsk = ask?.buildPrompt("nonce");
+    expect(nativeAsk).toContain("paperclip_finish must be your only tool call");
+    expect(nativeAsk).toContain(
+      "never call report_progress or any other tool before or after it",
+    );
   });
 
   it("uses only declared secret references in generated payloads", () => {

tests/runner-e2e/catalog.ts

@@ -512,7 +512,7 @@ export const runnerTasks: readonly RunnerTaskFixture[] = [
         `Your final visible task-thread answer must be exactly this complete marker, including its final suffix: E2E_ASK_12_${nonce}.`,
         "Do not create or modify files, do not create a plan or additional work, and do not expose credentials.",
         "After posting the direct answer, mark this task Done.",
-        `In a native runner, call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"E2E_ASK_12_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly E2E_ASK_12_${nonce} as the complete final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
+        `In a native runner, call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"E2E_ASK_12_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. For the entire run, paperclip_finish must be your only tool call: never call report_progress or any other tool before or after it. Wait for that tool call to succeed, then emit exactly E2E_ASK_12_${nonce} as the complete final response. Do not write a user-facing final response before paperclip_finish succeeds.`,
         `In a legacy runner, post exactly E2E_ASK_12_${nonce} as the task comment body and mark the task Done through the public API.`,
       ].join("\n"),
     buildMatchers(nonce, execution) {

tests/runner-e2e/runner.spec.ts

@@ -1026,7 +1026,11 @@ for (const execution of executions) {
           });
           await page.goto(
             `/${encodeURIComponent(issuePrefix)}/issues/${encodeURIComponent(issue.identifier ?? issue.id)}`,
-            { waitUntil: "domcontentloaded" },
+            // A restarted Vite dev server may keep loading its fresh module
+            // graph after the task UI is already usable. Bind navigation only
+            // to the committed canonical route, then let the explicit UI and
+            // API assertions below prove readiness and preserved state.
+            { waitUntil: "commit" },
           );
           await expect(
             page