Skip to content

feat: add a Parallel search option to the deep research example - #863

Open
georgeatparallel wants to merge 1 commit into
Agent-Field:mainfrom
georgeatparallel:parallel/search-mcp-2t145730659078z-9e649fc5
Open

feat: add a Parallel search option to the deep research example#863
georgeatparallel wants to merge 1 commit into
Agent-Field:mainfrom
georgeatparallel:parallel/search-mcp-2t145730659078z-9e649fc5

Conversation

@georgeatparallel

Copy link
Copy Markdown

Summary

The Deep Research example currently requires a Tavily API key for web search. This adds an explicit SEARCH_PROVIDER=parallel option that uses Parallel's hosted Search MCP endpoint without changing the default Tavily path.

Type of change

  • Bug fix
  • New feature
  • Refactor / cleanup
  • Docs only
  • Tests only
  • CI / tooling
  • Breaking change

Test plan

  • PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s examples/python_agent_nodes/deep_research/tests -p 'test_*.py' -v
  • git diff --check and python3 -m compileall -q examples/python_agent_nodes/deep_research
  • Ruff lint and format checks for the changed Python files
  • Bounded anonymous request to https://search.parallel.ai/mcp, parsed through the new adapter

Test coverage

This repo enforces a coverage gate on every PR (see
.github/workflows/coverage.yml and
docs/COVERAGE.md).

  • The gate runs ./scripts/coverage-summary.sh and compares per-surface
    numbers against coverage-baseline.json.
  • It fails if any surface drops more than 1.0 pp below its baseline,
    if any surface is below 80%, or if the weighted aggregate falls below
    85%.

Before asking for review, please confirm:

  • I ran tests for the surface(s) I changed locally.
  • New code paths are covered by tests in this PR (no bare additions).
  • I did not lower or otherwise change coverage-baseline.json.
  • The coverage gate check is green in CI before requesting review.

For AI coding agents: if the Coverage Summary GitHub Actions job
fails, read the sticky PR comment titled "📊 Coverage report" — it lists
the specific surface that regressed, the delta, and the exact command to
reproduce locally. Add tests for the uncovered lines in this same PR
before requesting review again. Do not lower baselines to silence the
gate unless the regression is intentional and explicitly called out in
the PR summary.

Checklist

  • I have read CONTRIBUTING.md (if present) and
    docs/DEVELOPMENT.md.
  • Commits are signed off and follow conventional-commits style.
  • I have linked any related issues (none for this focused example change).

Related issues / PRs

None.

The repository-wide CI and coverage checks will run after this draft is opened. The hosted CLA will also require completion through the repository's CLA Assistant check.

Disclosure: I work at Parallel.ai, which operates this MCP endpoint.

Signed-off-by: georgeatparallel <george@parallel.ai>
@CLAassistant

CLAassistant commented Aug 2, 2026

Copy link
Copy Markdown

CLA assistant check
All committers have signed the CLA.

@georgeatparallel
georgeatparallel marked this pull request as ready for review August 4, 2026 22:48
@georgeatparallel
georgeatparallel requested review from a team and AbirAbbas as code owners August 4, 2026 22:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants