Fix agent deep dive run pagination

> [!CAUTION]
> Protected files were modified in this change.
> This pull request is in `request_review` mode and requires explicit human scrutiny before merge.
>
> Protected files: `.github/workflows/agent-deep-dive.lock.yml`, `.github/workflows/agent-deep-dive.md`

Closes \#1685

The agent deep-dive workflow now uses `gh run list --limit` instead of a single-page REST API response, so the configured run count is honored across API pages. The generated lock file is refreshed accordingly.

Validation: `make test` and `make lint` pass.

> [!WARNING]
>
> Firewall blocked 2 domains
>
> The following domains were blocked by the firewall during workflow execution:
>
> - `awmgmcpg`
> - `models.dev`
>> To allow these domains, add them to the `network.allowed` list in your workflow frontmatter:
>
> ```yaml
> network:
> allowed:
> - defaults
> - "awmgmcpg"
> - "models.dev"
> ```
>
> See [Network Configuration](https://github.github.com/gh-aw/reference/network/) for more information.
>
>

---
[What is this?](https://ela.st/github-ai-tools) | [From workflow: Trigger Framework Best Practices](https://github.com/elastic/ai-github-actions/actions/runs/30272098469)

Give us feedback! React with 🚀 if perfect, 👍 if helpful, 👎 if not.

---

> [!NOTE]
> This was originally intended as a pull request, but the git push operation failed.
>
> **Original error:** pushSignedCommits: refusing unsigned push for branch 'fix/agent-deep-dive-run-pagination-ae8cbbb3a3abe11b': Signed-commit payload violates file-protection policy (request_review): .github/workflows/agent-deep-dive.lock.yml, .github/workflows/agent-deep-dive.md
>
> **Workflow Run:** [View run details and download bundle artifact](https://github.com/elastic/ai-github-actions/actions/runs/30272098469)
>
> The bundle file is available in the `agent` artifact in the workflow run linked above.

To create a pull request with the changes:

```sh
# Download the artifact from the workflow run
gh run download 30272098469 -n agent -D /tmp/agent-30272098469

# Fetch the bundle into a temporary ref, then update the local branch
git fetch /tmp/agent-30272098469/aw-elastic-ai-github-actions-fix-agent-deep-dive-run-pagination.bundle refs/heads/fix/agent-deep-dive-run-pagination:refs/bundles/create-pr-fix-agent-deep-dive-run-pagination-ae8cbbb3a3abe11b-099a1c5c
git update-ref refs/heads/fix/agent-deep-dive-run-pagination-ae8cbbb3a3abe11b refs/bundles/create-pr-fix-agent-deep-dive-run-pagination-ae8cbbb3a3abe11b-099a1c5c
git checkout fix/agent-deep-dive-run-pagination-ae8cbbb3a3abe11b
# Ensure the working tree matches the updated branch
git reset --hard
# Remove the temporary bundle ref
git update-ref -d refs/bundles/create-pr-fix-agent-deep-dive-run-pagination-ae8cbbb3a3abe11b-099a1c5c

# Push the branch to origin
git push origin fix/agent-deep-dive-run-pagination-ae8cbbb3a3abe11b

# Create the pull request
gh pr create --title 'Fix agent deep dive run pagination' --base main --head fix/agent-deep-dive-run-pagination-ae8cbbb3a3abe11b --repo elastic/ai-github-actions
```

Inspect .github/workflows/agent-deep-dive.md and the generated .github/workflows/agent-deep-dive.lock.yml, focusing on the switch to `gh run list --limit` and the configured run count. Refresh the lock file as needed, then run `make test` and `make lint`; done means pagination honors the configured count and both checks pass.

Written by the indexing model from the issue text.