AI & LLM Engineering · LangGraph · By jeremylongshore

Wire LangChain 1.0 / LangGraph 1.0 tests into a GitHub Actions pipeline — unit tests with FakeListChatModel, VCR-gated integration tests, warning-filter policy, and eval-regression merge gates.

jeremylongshore/tons-of-skills-marketplace

Paste-match catalog of 14 real LangChain 1.0 / LangGraph 1.0 exceptions with named causes and named fixes, plus a triage decision tree.

jeremylongshore/tons-of-skills-marketplace

Produce a reproducible, sanitized diagnostic bundle for a LangChain / LangGraph incident — environment snapshot, version manifest, filtered astreamevents(v2) transcript, propagating callback stack…

jeremylongshore/tons-of-skills-marketplace

Build a LangGraph 1.0 Deep Agent — planner + subagents + virtual filesystem + reflection loop — without the state-growth and prompt-inheritance traps.

jeremylongshore/tons-of-skills-marketplace

Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager…

jeremylongshore/tons-of-skills-marketplace

Enforce tenant isolation and role-based access across LangChain 1.0 chains and LangGraph 1.0 agents — per-request retriever construction, tenant-scoped rate limits, role-scoped tool allowlists, and…

jeremylongshore/tons-of-skills-marketplace

Build reproducible evaluation pipelines for LangChain 1.0 chains and LangGraph 1.0 agents — golden datasets, LangSmith evaluate(), ragas RAG metrics, deepeval LLM-as-judge, agent trajectory…

jeremylongshore/tons-of-skills-marketplace

Triage LangChain 1.0 / LangGraph 1.0 production incidents — LLM-specific SLOs, provider outage runbook, latency spike decision tree, cost-overrun response, agent loop containment.

jeremylongshore/tons-of-skills-marketplace

Build a correct LangGraph 1.0 ReAct agent with createreactagent — typed tools, error propagation, recursion caps, and stop conditions that actually stop.

jeremylongshore/tons-of-skills-marketplace

Build a correct LangGraph 1.0 StateGraph — typed TypedDict state with reducers, nodes, edges, compile, and recursion budgets — without hitting the silent-termination and state-replacement traps.

jeremylongshore/tons-of-skills-marketplace

Persist LangGraph agent state correctly with MemorySaver and PostgresSaver — threadid discipline, JSON-serializable state rules, time-travel, schema migration.

jeremylongshore/tons-of-skills-marketplace

Build LangGraph 1.0 human-in-the-loop approval flows with interruptbefore / interruptafter and Command(resume=...) — JSON-serializable state, clean resume semantics, and UI wiring for approval…

jeremylongshore/tons-of-skills-marketplace

Pick the correct LangGraph 1.0 streammode ("messages" vs "updates" vs "values"), wire it into SSE or WebSocket without proxy-buffering gotchas, and filter astreamevents(v2) server-side before…

jeremylongshore/tons-of-skills-marketplace

Compose LangGraph 1.0 subgraphs correctly — shared state key propagation, Send / Command(graph=...) dispatch, callback scoping, per-subgraph recursion budgets, and testing each subgraph in isolation.

jeremylongshore/tons-of-skills-marketplace

Build a fast, deterministic local test loop for LangChain 1.0 / LangGraph 1.0 — FakeListChatModel fixtures, pytest config, VCR cassettes with key redaction, warning-filter policy.

jeremylongshore/tons-of-skills-marketplace

Wire LangSmith tracing and custom metric callbacks into a LangChain 1.0 chain or LangGraph 1.0 agent correctly — env-var spelling, subgraph propagation, per-tenant dimensions, cost and latency…

jeremylongshore/tons-of-skills-marketplace

Wire LangChain 1.0 / LangGraph 1.0 traces into an OpenTelemetry-native backend (Jaeger, Honeycomb, Grafana Tempo, Datadog) with LLM-specific SLOs, safe prompt-content policy, and subgraph-aware span…

jeremylongshore/tons-of-skills-marketplace

Tune LangChain 1.0 / LangGraph 1.0 Python chains and agents for throughput, latency, and cost — streaming modes, explicit batch concurrency, semantic plus exact caches, persistent message history…

jeremylongshore/tons-of-skills-marketplace

A reference layered architecture for production LangChain 1.0 / LangGraph 1.0 services — LLM factory with version-safe defaults, chain/graph registry, retriever and tool DI, Pydantic-validated…

jeremylongshore/tons-of-skills-marketplace

Migrate a LangChain 0.3.x Python codebase to LangChain 1.0 / LangGraph 1.0 without breaking production — named breaking changes, codemod patterns, and a phased rollout.

jeremylongshore/tons-of-skills-marketplace

Dispatch LangChain 1.0 chain/agent events to external systems — webhooks, Kafka, Redis Streams, SNS — via async fire-and-forget callbacks, subgraph-aware wiring, and HMAC-signed delivery with…

jeremylongshore/tons-of-skills-marketplace