|
About the Observability & Evals category
|
|
0
|
456
|
April 22, 2025
|
|
Benchmarking a multi-step agent guardrail (local-first): catch vs false-alarm rate, and the eval cases I can’t invent
|
|
0
|
5
|
October 29, 2026
|
|
What should become an evaluation case after an agent failure?
|
|
0
|
7
|
October 28, 2026
|
|
Feature Request: Add a pluggable binary classification evaluator for System 1 models
|
|
0
|
7
|
October 28, 2026
|
|
Bug with high precision results from code evaluators
|
|
3
|
321
|
October 2, 2026
|
|
Introducing Langshark a local-first companion observability tool for self-hosted Langgraph deployments
|
|
1
|
109
|
August 17, 2026
|
|
LangSmith continues making OpenAI API calls after OpenAI billing threshold is reached
|
|
3
|
119
|
August 7, 2026
|
|
Traces on Claude
|
|
2
|
122
|
August 3, 2026
|
|
Getting 403 Forbidden on /runs/multipart despite valid key, correct workspace, and active billing
|
|
2
|
285
|
July 20, 2026
|
|
Experiment table not showing cost breakdown & own metadata
|
|
1
|
114
|
June 18, 2026
|
|
Trace-to-Fix: how are you actually improving RAG/agents after observability flags issues?
|
|
3
|
275
|
June 15, 2026
|
|
LangSmith cost/token attribution differs between LangGraph v2 streaming and v3 `astream_events` with Anthropic prompt caching
|
|
1
|
133
|
June 10, 2026
|
|
How can I verify my runs have been queued for deletion via the API?
|
|
3
|
151
|
June 2, 2026
|
|
[Feature]: MetacognitiveGate node — source-aware instruction checking before tool execution
|
|
2
|
100
|
June 2, 2026
|
|
Is there a limit on runs deleted by /api/v1/runs/delete when using filtered metadata
|
|
2
|
135
|
June 1, 2026
|
|
Access to Langsmith Engine
|
|
1
|
106
|
May 29, 2026
|
|
How to delete traces or runs?
|
|
10
|
1945
|
May 28, 2026
|
|
Getting 404 when clicking "Connect Github" on the Issues/Langsmith Engine tab
|
|
1
|
110
|
May 14, 2026
|
|
Trouble understanding and editing experiment summary evaluators feedbacks
|
|
3
|
175
|
May 13, 2026
|
|
Run link 404s — v2 endpoint can't find run that v1 just returned
|
|
3
|
167
|
May 12, 2026
|
|
Question about LangSmith Trace Search
|
|
4
|
198
|
May 8, 2026
|
|
Runs visiblty problem
|
|
1
|
155
|
May 5, 2026
|
|
Alert triggering and ignoring filters
|
|
9
|
448
|
April 29, 2026
|
|
Enable OpenTelemetry traces without sending data to LangSmith
|
|
2
|
334
|
April 18, 2026
|
|
[Proposal] Solving "Silent Failures" with a Causal Precedence Evaluator for Agent Trajectories
|
|
0
|
129
|
April 9, 2026
|
|
[FEATURE-REQUEST] Ability to add builtin tools in Prompt Playground/Evaluations
|
|
0
|
94
|
April 1, 2026
|
|
How are teams handling evals when agent pipelines span multiple LangSmith projects?
|
|
1
|
136
|
April 1, 2026
|
|
Passing variable to multi-turn conversation eval prompt, coming as empty during execution
|
|
3
|
212
|
March 9, 2026
|
|
Reasoning_effort parameter not working with GPT-5.2 in playground
|
|
2
|
737
|
March 9, 2026
|
|
How to enable LangSmith tracing in my project?
|
|
5
|
590
|
March 6, 2026
|