Add OrcaReplay to Observability - #70
Open
xizhuomengcontin wants to merge 1 commit into
Open
xizhuomengcontin wants to merge 1 commit into
xizhuomengcontin wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this adds
One new entry under
servers/observability/orcareplay/server.json:OrcaReplay — a local-first recorder/replayer for AI agent runs. It sits between a coding agent and its model provider, writes the real traffic (prompts, tool calls, responses, raw bytes) into an on-disk trace library, and serves that library over a read-only stdio MCP server (
npx -y orcareplay mcp) with six tools:list,show,checkpoints,graph,replay,compare. No account, no auth — it only reads local traces.Why it belongs in Observability
The category currently covers what you can query while a run is happening. OrcaReplay covers the half that is missing here: keeping the run itself. A failed run can be replayed offline without contacting any provider, and two recorded runs can be diffed — which is what you want when the failure is not reproducible live.
Checks
node scripts/validate-catalog.mjs→Validated 29 MCP server entries.node scripts/generate-readme.mjs→README.mdregenerated and committed (one row added under Observability)homepage_url/repository_url/package_urlall httpsDisclosure: I maintain OrcaReplay.