feat(examples): add Microsoft 365 Agents SDK example with Splunk AO OTel instrumentation - #223
Draft
etserend wants to merge 3 commits into
Draft
feat(examples): add Microsoft 365 Agents SDK example with Splunk AO OTel instrumentation#223etserend wants to merge 3 commits into
etserend wants to merge 3 commits into
Conversation
…Tel instrumentation Adds a working Q&A agent example using the Microsoft 365 Agents SDK (microsoft-agents-hosting-aiohttp) wired to Splunk AO via stock SplunkAOSpanProcessor. opentelemetry-instrumentation-openai-v2 auto-instruments the Azure OpenAI call, emitting gen_ai.* spans. Supports both O11Y (SPLUNK_AO_REALM + token) and standalone (SPLUNK_AO_API_KEY) deployment modes. AnonymousTokenProvider for local testing with npx @microsoft/m365agentsplayground; MsalConnectionManager for authenticated Teams/Copilot channels. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
etserend
marked this pull request as draft
August 12, 2026 01:33
…65 Agents SDK app_auto_lab0.py: SplunkAOSpanProcessor + OpenAIAgentsTraceInstrumentor → Splunk AO lab0 app_manual_lab0.py: SplunkAOLogger with full 5-level span hierarchy matching auto trace Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
… and MS A365 observability - start_server.py: APP_MODE dispatch (auto/manual/auto_lab0/manual_lab0/default) - app.py: rewrite to use MS A365 OpenAIAgentsTraceInstrumentor + InvokeAgentScope - pyproject.toml: replace opentelemetry-instrumentation-openai-v2 with ms-a365-observability deps Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
microsoft-agents-hosting-aiohttp) wired to Splunk AO via stockSplunkAOSpanProcessoropentelemetry-instrumentation-openai-v2auto-instruments the Azure OpenAI call, emittinggen_ai.*spans with full i/o contentSPLUNK_AO_REALM+ token) and standalone mode (SPLUNK_AO_API_KEY) via.env.exampleAnonymousTokenProviderfor local testing withnpx @microsoft/m365agentsplayground;MsalConnectionManagerfor authenticated Teams/Copilot channelsWhat works today
The AO UI correctly renders the
chat gpt-4o-miniLLM child span in Messages mode with full i/o and token counts. The root span (agents.adapter.process) renders as typetracewith empty Input/Output columns — this is a known backend limitation (the backend classifies spans by span name prefix;agents.adapter.processmatches none). Tracked in spike doc: https://splunk.atlassian.net/wiki/x/F4AjjPsTest plan
cd examples/agent/microsoft-365-agents-sdk && cp .env.example .env— fill in credentialsuv run python start_server.pynpx @microsoft/m365agentsplayground— send a message, verify responsechat gpt-4o-minispan rendered in Messages mode🤖 Generated with Claude Code