test: require saved onboarding approval cards (#18292)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Product E2E tests exercise real user workflows through the browser.
> - The onboarding journey requires a human to accept one proposed child
task.
> - A live agent tried to create the child before it saved a proposal
card. The product correctly rejected that action.
> - The scripted request named the required result but did not name the
proposal tool or require its saved receipt.
> - This pull request makes that handoff explicit. It keeps the existing
human approval and independent result checks.
> - The benefit is a clearer scripted workflow without a change to
product authority.

## Linked Issues or Issue Description

Refs #18288 and #18266.

**What happened?**

The agent treated the opening task request as a step toward acceptance
without first saving a proposal. It then stopped after child creation
was denied. Its visible response referred to a pending proposal, but no
proposal card existed.

**Expected behavior**

The agent saves a native confirmation card, checks its receipt, and
waits for the human to accept it through the browser. It must not record
its own approval. Only an accepted card authorizes the child task.

**Steps to reproduce**

Run the scripted Cloud onboarding journey. Give the canonical onboarding
task its first task request. The observed agent skipped the saved
proposal and tried to create the child. Model behavior varies, so this
is a fixture guidance change rather than a deterministic product defect
claim.

**Paperclip version or commit**

Fixture base: `7a7ade4b9360aaf8e1a2808bb2b1a752c080f564`. The serving
product was Core `965184d2968f40b1183803529b88f288264c832f`.

**Deployment mode**

Testing Cloud workspace with native Codex. This pull request selects no
product release or deployment.

## What Changed

- Name the existing `request_human_input` confirmation or revision-bound
checkbox contract and `wake_assignee` policy in the parent request.
- Require a saved pending-card receipt. Require corrections when tool
arguments are rejected.
- Forbid self-approval. Require the actual accepted human card decision
before child creation.
- Document this scripted handoff. Keep the child brief, final download
links, browser actions, and all grading assertions.

## Verification

- Focused onboarding and Cloud journey tests: 79 passed.
- Shared evidence, campaign, and contract tests: 66 passed.
- `pnpm test:e2e:runner:typecheck`: passed after building the existing
workspace type dependencies.
- Credential-free preview under a network-deny guard: passed with zero
external calls. Its preparation plan matches the base fixture.
- `git diff --check`: passed.
- No prompt-string test was added. Existing tests continue to enforce
approval order, child scope, independent file checks, and real result
links.
- Full local repository build and database suites were not repeated for
this fixture text change. Required PR CI must pass before merge.
- The original live result remains unchanged. This local work does not
prove that a later model run will comply.

## Risks

- The model can still ignore the instructions. A new real campaign must
prove the workflow.
- More explicit guidance makes this a scripted product journey. It is
not a model discovery benchmark.
- There are no product runtime, schema, credential, model, budget, or
approval-policy changes.

## Model Used

OpenAI Codex, exact model `gpt-6.1-sol`, ultra reasoning effort. Parent
runtime metadata confirmed this model. Context window size was not
reported. Used source inspection, local code execution, and an
independent agent review.

## 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
- [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

Co-authored-by: Paperclip <noreply@paperclip.ing>

tests/runner-e2e/PRODUCT-JOURNEYS.md

@@ -41,7 +41,10 @@ reusing successful onboarding reports `onboarding`. Preconfigured state is never
 counted as onboarding coverage.
 
 The scripted onboarding request supplies a self-contained child brief. The
-parent must copy the full marked brief verbatim into `create_task.description`,
+parent must first save its proposal through the existing native confirmation
+tool and check the saved card receipt. The browser records the human decision;
+the parent must not record its own approval or treat the opening scope as acceptance.
+It must copy the full marked brief verbatim into `create_task.description`,
 including tool names, parameters, and the encoded input. It orders the child's
 work: create the files, publish `connection-proof.json` with that exact filename
 and workspace-relative content reference, save its Paperclip task document with

tests/runner-e2e/product-journeys/onboarding-first-task.ts

@@ -188,6 +188,8 @@ export async function onboardingFirstTask(input: OnboardingFirstTaskInput): Prom
   ].join("\n");
   await page.getByTestId("question-other-answer-composer").last().locator('[contenteditable="true"],textarea').first().fill([
     `I have one task in mind. Propose exactly one child task named "${title}" and wait for my approval before creating it or doing its work.`,
+    'Save that proposal with request_human_input using interactionKind "confirmation" (or "checkbox" bound to the saved plan revision when plan mode applies) and continuationPolicy "wake_assignee". Check that the tool returned a saved pending card. Correct rejected arguments from its feedback; a failed call is not a pending proposal.',
+    "Do not resolve, accept, or record approval yourself. This opening answer supplies scope, not approval. Wait for my actual accepted card decision before calling create_task; a rejection does not authorize the work.",
     "After approval, assign it to yourself and let its own Paperclip execution produce the result. After it finishes, verify its saved document and published attachment.",
     "In your final reply in this onboarding conversation, include actual Markdown links to the child task, its saved document, and connection-proof.json. Copy the published attachment's returned contentPath or downloadPath into the file link URL, including its actual attachment ID. A backticked filename, document key, or path is not a clickable link. Obtain the real references from the child's saved results; do not invent IDs or URLs. Then complete both tasks.",
     "When you create the child, copy the entire brief between BEGIN CHILD BRIEF and END CHILD BRIEF VERBATIM into create_task.description. Preserve every step, tool name, parameter instruction, and exact encoded input. Do not summarize or paraphrase it.",