Skip to content

docs: add web dashboard section to README with screenshot#48

Merged
jrob5756 merged 2 commits intomainfrom
docs/web-dashboard-and-example-fixes
Mar 17, 2026
Merged

docs: add web dashboard section to README with screenshot#48
jrob5756 merged 2 commits intomainfrom
docs/web-dashboard-and-example-fixes

Conversation

@jrob5756
Copy link
Collaborator

Summary

  • Adds a dedicated Web Dashboard section to the README with a screenshot, highlighting the real-time DAG visualization, live agent streaming, in-browser human gates, per-node detail, and background mode
  • Updates the Features list with a richer description and anchor link to the new section
  • Fixes two bugs in example workflows:
    • parallel-research.yaml: flattens the planner's nested object output schema (plan.questions/areas/sources) to top-level fields for more reliable LLM output generation, and updates all downstream template references
    • parallel-research.yaml and research-assistant.yaml: wraps context.iteration route conditions in Jinja2 delimiters ({{ }}) so the router uses the Jinja2 engine instead of simpleeval, which can't handle dotted attribute access

Test plan

  • make validate-examples passes
  • Run conductor run examples/parallel-research.yaml --web --input topic="AI in healthcare" and verify it completes without errors
  • Verify the screenshot renders correctly in the README on GitHub

🤖 Generated with Claude Code

Jason Robert and others added 2 commits March 17, 2026 16:11
- Add a dedicated "Web Dashboard" section to README highlighting the
  real-time DAG visualization, live streaming, in-browser human gates,
  and background mode
- Add screenshot of the dashboard running the parallel-research workflow
- Update Features bullet with a richer description and anchor link

Also fix two bugs in example workflows:

- Fix parallel-research.yaml: flatten planner output schema from nested
  object properties to top-level fields (questions, areas, sources) for
  more reliable LLM output, and update all downstream references
- Fix context.iteration route conditions in parallel-research.yaml and
  research-assistant.yaml: wrap in Jinja2 delimiters so the router uses
  the Jinja2 engine instead of simpleeval, which can't handle dotted
  attribute access

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The test mock for parallel-research.yaml still used the old nested
plan object structure. Update it to match the flattened top-level
fields (questions, areas, sources).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@jrob5756 jrob5756 merged commit 0f5387e into main Mar 17, 2026
7 checks passed
@jrob5756 jrob5756 deleted the docs/web-dashboard-and-example-fixes branch March 18, 2026 18:07
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.

1 participant