fix: send review to terminal respects repo default agent setting

[Ziinc]

handleCreateAgentWithReview in ShowWorkspace was calling onSessionCreated
without an agent field, so the session always launched with the claude
agent regardless of the repo or app default_agent setting.
Now it reads the repo-level default_agent first (falling back to the
app-level default), and passes the resolved agent to onSessionCreated,
matching the same resolution logic used when creating sessions from the
task input.
Also adds getRepoSetting to the api mock in ShowWorkspace test files to
avoid falling through to the real implementation when the review handler
is invoked in tests.

[github-actions]

📸 App QA screenshots

Re-ran the flow whose spec this PR adds or modifies — 2 captures. Other specs in the library were not run.

⬇️ Download the screenshots

send-review-to-terminal-default-agent

• send-review-codex-01-popover.png
  • The "Finish review" popover is open showing the "Finish your review" heading.
  • Three action buttons are visible: "Copy" on the left, "Plan" and "Edit" on the right.
  • The diff pane for example.ts is visible in the background.
• send-review-codex-02-terminal.png
  • The terminal pane at the bottom is open.
  • A session tab labelled "Code Review" is visible in the terminal pane.
  • The "Code Review" tab has a Sparkles (✨) icon — the codex agent icon — not a Bot icon (which would indicate the claude agent was launched instead).

Each bullet under a capture is what the spec claims that image should show — open the PNG and check it.

---

_{commit 6b40227 · workflow run — this comment is updated in place on each run.}