Skip to content

Update docs to include uninterruptable flag for direct speech - #29

Open
serhatzx wants to merge 2 commits into
mainfrom
serhat/sdk-38-include-uninterruptable-flag-for-direct-speech-in-docs
Open

Update docs to include uninterruptable flag for direct speech#29
serhatzx wants to merge 2 commits into
mainfrom
serhat/sdk-38-include-uninterruptable-flag-for-direct-speech-in-docs

Conversation

@serhatzx

@serhatzx serhatzx commented Jul 13, 2026

Copy link
Copy Markdown
Member

Summary by CodeRabbit

  • Documentation
    • Added a “Sending a Welcome Message” guide for when an agent session starts.
    • Updated Deepslate-specific capability listings and removed the older welcome trigger pattern.
    • Revised “Direct Speech” examples and reference tables to support uninterruptable, and clarified includeInHistory: false behavior.
    • Updated supported integration snippets (including Pipecat and WebSocket helpers) to reflect the new options.
  • New Features (Realtime API)
    • Added uninterruptable to direct-speech directives and introduced protocol support for session experiments, plus new Ping/Pong messages.

@serhatzx
serhatzx requested a review from Jannek312 July 13, 2026 09:45
@coderabbitai

coderabbitai Bot commented Jul 13, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 74ff316d-72ba-45a4-a0b2-98dc7bbe9203

📥 Commits

Reviewing files that changed from the base of the PR and between 4a34151 and c70b1af.

📒 Files selected for processing (1)
  • api-reference/realtime.proto

📝 Walkthrough

Walkthrough

Documentation replaces session-initialization welcome examples with agent entry-hook flows, documents uninterruptable direct speech behavior across integrations, and extends the realtime protocol with experiment, speech, and ping/pong fields.

Changes

Realtime speech documentation and protocol

Layer / File(s) Summary
Welcome message flow
livekit-node.mdx, livekit.mdx
Welcome messages now use agent entry hooks and realtime session speech methods instead of the session_initialized event.
Direct speech options
livekit-node.mdx, livekit.mdx, pipecat.mdx, websocket.mdx
Examples and reference text document uninterruptable playback, barge-in behavior, and conversation-history inclusion settings.
Realtime protocol extensions
api-reference/realtime.proto
Session initialization accepts experiment values, direct speech supports uninterruptable playback, and service/client messages support ping/pong packets.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Suggested reviewers: jannek312

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly matches the main theme of the changes: documenting the new uninterruptable direct speech behavior.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch serhat/sdk-38-include-uninterruptable-flag-for-direct-speech-in-docs

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

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🧹 Nitpick comments (2)
livekit-node.mdx (1)

289-291: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Add prerequisites and use second-person instructions.

State the required LiveKit worker/session setup before this procedure, and rewrite the new explanatory prose to address the reader as “you.” As per coding guidelines, “Include prerequisites at the start of procedural content” and “Use second-person voice ('you') when writing documentation content.”

Also applies to: 330-332

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@livekit-node.mdx` around lines 289 - 291, Update the “Sending a Welcome
Message” procedure to begin with the required LiveKit worker and session setup
prerequisites. Rewrite the surrounding explanatory prose in second-person voice,
including the instructions around subclassing voice.Agent, overriding onEnter(),
and calling speakDirect() via getActivityOrThrow().realtimeLLMSession; preserve
the existing API details and behavior.

Source: Coding guidelines

livekit.mdx (1)

230-232: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Add prerequisites and address the reader directly.

Document the required worker/session setup before this procedure and rewrite the new prose in second person. As per coding guidelines, “Include prerequisites at the start of procedural content” and “Use second-person voice ('you') when writing documentation content.”

Also applies to: 300-302

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@livekit.mdx` around lines 230 - 232, Update the “Sending a Welcome Message”
procedure by adding the required worker and session setup prerequisites before
the instructions. Rewrite the surrounding guidance in direct second-person
voice, using “you” to explain how to override Agent.on_enter() and call
speak_direct() through self.realtime_llm_session; apply the same voice change to
the referenced later prose.

Source: Coding guidelines

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@websocket.mdx`:
- Around line 272-292: Update the speak example to remove the unsupported
uninterruptable parameter and its usage, and delete the accompanying
playback-guarantee documentation. Keep only the supported text and
includeInHistory fields and their documented behavior.

---

Nitpick comments:
In `@livekit-node.mdx`:
- Around line 289-291: Update the “Sending a Welcome Message” procedure to begin
with the required LiveKit worker and session setup prerequisites. Rewrite the
surrounding explanatory prose in second-person voice, including the instructions
around subclassing voice.Agent, overriding onEnter(), and calling speakDirect()
via getActivityOrThrow().realtimeLLMSession; preserve the existing API details
and behavior.

In `@livekit.mdx`:
- Around line 230-232: Update the “Sending a Welcome Message” procedure by
adding the required worker and session setup prerequisites before the
instructions. Rewrite the surrounding guidance in direct second-person voice,
using “you” to explain how to override Agent.on_enter() and call speak_direct()
through self.realtime_llm_session; apply the same voice change to the referenced
later prose.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 0858f8f6-2f48-478c-9d2a-b8728c21ef1a

📥 Commits

Reviewing files that changed from the base of the PR and between 3ddd526 and 4a34151.

📒 Files selected for processing (4)
  • livekit-node.mdx
  • livekit.mdx
  • pipecat.mdx
  • websocket.mdx

Comment thread websocket.mdx
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