mosaic/stack
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Add OpenTelemetry Tracing Infrastructure #131

New Issue
Closed
opened 2026-01-30 21:29:13 +00:00 by jason.woltje · 0 comments
jason.woltje commented 2026-01-30 21:29:13 +00:00
Owner
Copy Link

Implement OpenTelemetry distributed tracing and observability.

Objective: Add comprehensive tracing for all HTTP requests and LLM calls with GenAI semantic conventions.

Tasks:

  • Add OpenTelemetry dependencies to package.json
  • Create telemetry.service.ts for OTEL SDK initialization
  • Create telemetry.interceptor.ts for HTTP request tracing
  • Create llm-telemetry.decorator.ts for LLM-specific spans
  • Create span-context.service.ts for context propagation
  • Configure Jaeger exporter
  • Instrument all LLM provider calls
  • Add trace context to existing logging
  • Write documentation in docs/3-architecture/telemetry.md
  • Benchmark performance impact

Features:

  • Automatic HTTP request spans
  • LLM call instrumentation with token counts
  • Error tracking with stack traces
  • GenAI semantic conventions support
  • Jaeger/Zipkin export

Acceptance Criteria:

  • All HTTP requests create spans
  • LLM calls show token counts and latency
  • Traces viewable in Jaeger
  • No more than 5% performance overhead
  • Documentation complete

Related: Epic #121, Phase 3 OpenTelemetry
Depends on: #127 (refactored LlmService)

Implement OpenTelemetry distributed tracing and observability. Objective: Add comprehensive tracing for all HTTP requests and LLM calls with GenAI semantic conventions. Tasks: - Add OpenTelemetry dependencies to package.json - Create telemetry.service.ts for OTEL SDK initialization - Create telemetry.interceptor.ts for HTTP request tracing - Create llm-telemetry.decorator.ts for LLM-specific spans - Create span-context.service.ts for context propagation - Configure Jaeger exporter - Instrument all LLM provider calls - Add trace context to existing logging - Write documentation in docs/3-architecture/telemetry.md - Benchmark performance impact Features: - Automatic HTTP request spans - LLM call instrumentation with token counts - Error tracking with stack traces - GenAI semantic conventions support - Jaeger/Zipkin export Acceptance Criteria: - All HTTP requests create spans - LLM calls show token counts and latency - Traces viewable in Jaeger - No more than 5% performance overhead - Documentation complete Related: Epic #121, Phase 3 OpenTelemetry Depends on: #127 (refactored LlmService)
jason.woltje added the phase-3p0apiapi labels 2026-01-30 21:29:13 +00:00
jason.woltje added this to the M4-LLM (0.0.4) milestone 2026-01-30 23:40:48 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
ai
AI/LLM integration
 api
Backend/API work
 api
auth
Authentication
 database
database
Database/schema work
 devops
Docker/deployment
 docs
Documentation
 frontend
graph
knowledge-module
migration
Data migration
 orchestrator
Orchestrator service (apps/orchestrator/)
 p0
Critical priority
 p1
High priority
 p2
Medium priority
 p3
Low priority
 performance
Performance work
 phase-1
phase-2
phase-3
phase-4
phase-5
plugin
MoltBot plugin work
 search
security
Security-related
 setup
Initial setup
 testing
Testing/QA
 web
Frontend work
No Label api api p0 phase-3
Milestone
No items
No Milestone M4-LLM (0.0.4)
Projects
Clear projects
No project
Assignees
Clear assignees
jason.woltje
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mosaic/stack#131
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?