Skip to content

Stream model responses and reasoning summaries - #32

Open
ch55secake wants to merge 1 commit into
mainfrom
feat/markdown-transcript-rendering
Open

Stream model responses and reasoning summaries#32
ch55secake wants to merge 1 commit into
mainfrom
feat/markdown-transcript-rendering

Conversation

@ch55secake

Copy link
Copy Markdown
Owner

Summary

  • stream OpenAI, Anthropic, and OpenCode model output through the agent loop, CLI, and OpenTUI
  • show provider-supplied reasoning summaries through an explicit opt-in without persisting live deltas
  • add OpenCode Chat Completions reasoning support and correct OpenCode Go Messages authentication
  • render assistant transcript content as Markdown

Verification

  • go test ./...
  • go vet ./...
  • bun test
  • bun run typecheck
  • bun run build
  • docker compose config --quiet

Reasoning summaries are opt-in via --reasoning-summaries or /reasoning on.

@github-actions github-actions Bot added documentation Improvements or additions to documentation test Test coverage or test infrastructure feat Product behavior or capability labels Aug 10, 2026
@coderabbitai

coderabbitai Bot commented Aug 10, 2026

Copy link
Copy Markdown

Warning

Review limit reached

@ch55secake, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 6 minutes

You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
鈿欙笍 Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: de087c5d-40b7-4284-9e8a-6be0a69cad82

馃摜 Commits

Reviewing files that changed from the base of the PR and between fdb8c91 and 05c7d30.

馃搾 Files selected for processing (19)
  • README.md
  • cmd/symphony/main.go
  • cmd/symphony/main_test.go
  • internal/agent/loop.go
  • internal/agent/turn.go
  • internal/config/config.go
  • internal/providers/anthropic/provider.go
  • internal/providers/anthropic/provider_test.go
  • internal/providers/openai/provider.go
  • internal/providers/openai/provider_test.go
  • internal/providers/opencode/provider.go
  • internal/providers/opencode/provider_test.go
  • internal/providers/sse.go
  • internal/ui/assets/symphony-ui
  • internal/ui/protocol.go
  • ui/src/app/App.tsx
  • ui/src/components/Conversation.tsx
  • ui/src/protocol/types.ts
  • ui/src/screens/UtilityScreens.tsx

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

鉂わ笍 Share

Comment @coderabbitai help to get the list of available commands.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation feat Product behavior or capability test Test coverage or test infrastructure

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant