Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langchain-debug-bundle
Produce a reproducible, sanitized diagnostic bundle for a LangChain / LangGraph incident — environment snapshot, version manifest, filtered astream_events(v2) transcript, propagating callback stack, LangSmith trace URL — so a debug colleague can reproduce the failure without a live terminal.
Passed 20 of 22 test cases with the skill, and 12 of 22 without it.
and 11 more in the full report
8 fixed12 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
An engineer receiving an incident bundle needs to investigate a bug report stating 'agent returned an empty tool response'. Which file inside the bundle should they inspect first, and what specific event type should they search for?
| Checked | Without skill | With skill |
|---|---|---|
| Directs inspection of events.jsonl first when triaging empty tool responses. | Passed | Passed |
| Recommends searching events.jsonl for on_tool_error events. | Missed | Passed |
The instructions your model reads when the skill loads.
An on-call engineer pages you at 2am: the production agent loops, ToolMessage
outputs are empty strings, the user sees "I could not find the answer." Someone
asks the right question — what state was the graph in when it gave up? — and
there is no answer, because the terminal that caught the failure is already
gone, the Kubernetes pod has restarted, and the LangSmith URL was never
recorded.
This skill produces one artifact: a single bundle-<incident_id>.tar.gz (typically
1-10 MB) containing everything a second engineer needs to reproduce the failure
without a live terminal — environment and version manifest, filtered
astream_events(version="v2") JSONL, a propagating callback stack, the
LangSmith trace URL, and a post-write sanitization pass.
Four pitfalls make naive bundles useless:
ChatAnthropic.stream() reports token_usage only on stream close; token math read from on_llm_end lags by stream duration, so cost context in the bundle is wrong.BaseCallbackHandler.with_config(callbacks=[...]) does NOT propagate into subgraphs or inner create_react_agent loops. A debug callback bound that way silently captures zero events from the place the incident actually happened.astream_events(version="v2") emits 2,000+ events per invocation. A raw dump is 50 MB and unreadable; an SSE viewer crashes on it.astream_log() is soft-deprecated in 1.0. Diagnostic tooling built on it breaks on the next minor version.The skill's answer: assemble the manifest, capture v2 events with a whitelist
(drop lifecycle noise, keep on_chat_model_stream / on_tool_* / any *_error
event), attach DebugCallbackHandler via config["callbacks"] at invoke time,
pull the LangSmith URL from the active RunTree, run the sanitization pass,
tar it up. Pinned: langchain-core 1.0.x, langgraph 1.0.x, langsmith 0.1.x.
Pain-catalog anchors: P01, P28, P47, P67.
langchain-core >= 1.0, < 2.0, langgraph >= 1.0, < 2.0langsmith >= 0.1.40 for RunTree accessLANGSMITH_TRACING=true, LANGSMITH_API_KEY=...,
LANGSMITH_PROJECT=...) — canonical 1.0 env-var names, not the legacy
LANGCHAIN_TRACING_V2 (see P26).test cases passed, vs 12 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.