Fix resource leak in langchain-openrouter where each model instantiation creates unclosed httpx connections, especially problematic with FastAPI dependency injection and LangGraph factory graphs Includes evidence for LangChain troubleshooting demand.
Source-backedLast updated May 24, 20262 sourcesNeeds local verification
ChatOpenRouter.__init__ creates brand-new httpx.Client/AsyncClient per instance with no caching; under per-request instantiation patterns this leaks TLS keep-alive sockets and pool state to openrouter.ai
Quick fix
Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated
Verification status
Source-backed
Evidence
2 public source URLs
Before you change production
This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.
Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for LangChain, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.
What this error means
ChatOpenRouter.__init__ creates brand-new httpx.Client/AsyncClient per instance with no caching; under per-request instantiation patterns this leaks TLS keep-alive sockets and pool state to openrouter.ai is a LangChain failure pattern reported for developers trying to fix resource leak in langchain-openrouter where each model instantiation creates unclosed httpx connections, especially problematic with fastapi dependency injection and langgraph factory graphs. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
GitHub issues #37497/#37498 on langchain-ai/langchain report LangChain OpenRouter wrapper creating new httpx clients per instantiation without pooling, same class of bug fixed previously for AzureChatOpenAI (#32489). Impacts developers building LLM applications that create model instances per request. Category maps to AI Coding Tools since LangChain is listed in approved category mapping table.
Common causes
GitHub issues #37497/#37498 on langchain-ai/langchain report LangChain OpenRouter wrapper creating new httpx clients per instantiation without pooling, same class of bug fixed previously for AzureChatOpenAI (#32489). Impacts developers building LLM applications that create model instances per request. Category maps to AI Coding Tools since LangChain is listed in approved category mapping table.
Quick fixes
Confirm the exact error signature matches ChatOpenRouter.__init__ creates brand-new httpx.Client/AsyncClient per instance with no caching; under per-request instantiation patterns this leaks TLS keep-alive sockets and pool state to openrouter.ai.
Check the LangChain account, local tool state, and provider configuration involved in the failing workflow.
Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.
How to prevent it
Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.
Diagnostic flow for this page
Match ChatOpenRouter.__init__ creates brand-new httpx.Client/AsyncClient per instance with no caching; under per-request instantiation patterns this leaks TLS keep-alive sockets and pool state to openrouter.ai exactly before applying the quick fix.
Compare the failing environment with LangChain versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.