Transcripts #492
Transcripts #492
Conversation
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the
✨ Finishing touches🧪 Generate unit tests (beta)
Comment |
| :learning-objective-2: Navigate between detail views to inspect span information at different levels | ||
| :learning-objective-3: Use the timeline interactively to navigate to specific time periods | ||
|
|
||
| The Transcripts view provides filtering, searching, and navigation capabilities for investigating agent and MCP server execution transcripts. Use these features to efficiently locate specific operations, analyze performance patterns, and debug issues across tool invocations, LLM calls, and agent reasoning steps. |
There was a problem hiding this comment.
Also anything that goes through the ai gateway should become visible through transcripts. Eventually also knowledgebase query operations - generally everything in the ADP that is being requested/queried should emit those traces/transcripts.
|
|
||
| === Use the interactive timeline | ||
|
|
||
| Use the timeline visualization to quickly identify when errors began or patterns changed, and navigate directly to transcripts from particular timestamps. |
There was a problem hiding this comment.
Also: If we have many traces (e.g. hundreds or thousands) we can only show a subset of the traces. We have the timeline bar indicate what data is being shown currently. It may be just 5 minutes worth of data evne though you selected "Last 24h". Not sure if worth clarifying, should be intuitive hopefully
|
|
||
| === Search and filter for transcripts | ||
|
|
||
| Use search and filters together to narrow down transcripts and quickly locate specific executions. |
There was a problem hiding this comment.
I need to clarify and follow-up what the search field and the filter targets. It's not clear at the moment. I'll try to have the search field compare against all span attributes in the selected time range (possibly exact matches only). Let's talk again by mid of next week, then I should have an answer for package 1
There was a problem hiding this comment.
@weeco got it, I'll check in shortly! Also, does it make sense to filter (instead of search) based on scope/layer? Would there be actual use cases for that
|
|
||
| == Inspect span details | ||
|
|
||
| Each row in the transcript table represents a high-level agent or MCP server request flow. Expand each parent span to see the xref:ai-agents:observability/concepts.adoc#agent-transcript-hierarchy[hierarchical structure] of nested operations, including tool calls, LLM interactions, and internal processing steps. Parent-child spans show how operations relate: for example, an agent invocation (parent) triggers LLM calls and tool executions (children). |
There was a problem hiding this comment.
Technically they will fold under the same trace. So for example if the declarative agent uses our remote mcp platform we will create a trace id on the very first touchpoint of the request and this trace id is passed around across services (such as the MCP server) and they will emit traces that belong to this trace id. That's why we can build this tree view for a single agent invocation.
If someone uses their own agents and just invokes the MCP servers directly on our platform then they may see a parent trace just for the MCP server invocation (unless they also pass around the trace id and emit traces from their agents to our platform)
There was a problem hiding this comment.
Updated for detail
|
Worth having some content around using the new connectors to add your own traces or export them? 15292de |
❌ Deploy Preview for rp-cloud failed. Why did it fail? →
|
kbatuigas
force-pushed
the
DOC-1901-document-feature-adp-execution-logs-ui-package-1
branch
from
b80bd5b to
9592dcb
Compare
Description
Resolves https://github.com/redpanda-data/documentation-private/issues/
Review deadline:
Page previews
Checks