Start Debugging

Tag: llm

11 posts · Page 1 of 2

2026-05-18 errors ai-agents llm

Fix: rate_limit_error on Claude Sonnet 4.6 in a Long Agent Loop

A 429 rate_limit_error on claude-sonnet-4-6 in a long agent loop is almost always ITPM, not RPM. Read retry-after, cache the system prompt, and gate on anthropic-ratelimit-input-tokens-remaining. Step-by-step fix with code.

2026-05-17 errors ai-agents llm

Fix: Context Window Exceeded During an Aider Refactor

Aider 0.86 hit the token limit mid-refactor. The fix is /clear, /drop, --map-tokens, and switching to architect mode with Claude Sonnet 4.6's 1M window. Step-by-step repro, error breakdown, and config.

2026-05-16 errors claude-code anthropic-sdk

Fix: Tool Call Arguments Did Not Match Schema in Anthropic Tool Use

Why your Claude tool call fails schema validation, in both flavours: the API rejecting your tool definition at request time, and Claude returning a tool_use block your runner cannot accept. Concrete fixes for each, with strict mode, oneOf/anyOf, additionalProperties, and the retry loop pattern.

2026-05-12 llm ai-agents claude-code

How to Cache Multi-Turn Claude Conversations Across API Calls

Place rolling cache_control breakpoints across messages, respect the 20-block lookback, and refresh the 5-minute TTL automatically so a 50-turn agent loop pays the prefix once, not fifty times. Verified against anthropic 0.42 (Python) and @anthropic-ai/sdk 0.30 (Node) in May 2026.

2026-05-11 ai-agents llm claude-code

How to Set Up an LLM-as-Judge Eval Harness for a Coding Agent

Build a working LLM-as-judge eval harness for a coding agent in Python: golden tasks, deterministic checks, a rubric judge on Claude Sonnet 4.6, calibration against human labels, and a CI gate that fails the build when scores regress.

2026-05-10 cursor ai-agents llm

How to Pipe Cursor's Context to an Aider Session for Multi-Agent Refactors

Cursor is the best place to plan a refactor. Aider is the best place to execute it from a terminal with cheap models and atomic git commits. This guide shows the exact pipe: dump the Cursor chat to markdown, hand it to Aider as a read-only context file, and run an architect/editor split that finishes the work.

2026-05-06 ai-agents semantic-kernel llm

How to Run a Semantic Kernel Plugin From a BackgroundService

Wire a Microsoft.SemanticKernel 1.75.0 plugin into a hosted BackgroundService on .NET 11 and invoke its KernelFunctions on a PeriodicTimer schedule. Covers DI scopes, [KernelFunction] resolution, prompt-cache-friendly invocation, cancellation, and the lifetime gotchas that bite when you move a plugin off the request path.

2026-05-03 llm ai-agents dotnet

How to Add Tool Calling to a Microsoft.Extensions.AI Chat Client

Wire AIFunctionFactory.Create, ChatOptions.Tools, and ChatClientBuilder.UseFunctionInvocation in Microsoft.Extensions.AI 10.5 so an IChatClient can call your .NET methods automatically. Covers OpenAI and Azure OpenAI providers, the FunctionInvokingChatClient knobs that actually matter (iteration limits, concurrent calls, approval prompts, error handling), and streaming responses with tools.

2026-04-30 llm ai-agents anthropic-sdk

How to Call the Claude API from a .NET 11 Minimal API with Streaming

Stream Claude responses from an ASP.NET Core 11 minimal API end-to-end: the official Anthropic .NET SDK, TypedResults.ServerSentEvents, SseItem, IAsyncEnumerable, cancellation flow, and the gotchas that buffer your tokens silently. With Claude Sonnet 4.6 and Opus 4.7 examples.

2026-04-29 llm ai-agents anthropic-sdk

How to Add Prompt Caching to an Anthropic SDK App and Measure the Hit Rate

Add prompt caching to a Python or TypeScript Anthropic SDK app, place cache_control breakpoints correctly, and read cache_read_input_tokens and cache_creation_input_tokens to compute a real hit rate. With pricing math for Claude Sonnet 4.6 and Opus 4.7.