Dotnet

Reject stale chat-history writes when another turn changes the conversation during generation.

Compare cache, retry, and telemetry order around IChatClient with a fake provider, exact event traces, cancellation, and a streaming failure.

Evaluate real Qdrant results in .NET with a custom IEvaluator, labeled chunks, Precision@K, Recall@K, MRR, nDCG, and persisted HTML reports.

Assemble model context from Qdrant results in .NET: deduplicate exact text, check a local token allowance, and trace citations to admitted evidence.

Extend the .NET Qdrant chunking sample with payload metadata, keyword indexes, and filters that restrict retrieval to published runbooks.

Use admission control, bounded waiting, and shared provider limits to keep slow AI work from turning overload into an outage, with C# examples.

Extend .NET and Qdrant indexing with section boundaries, paragraph overlap, deterministic chunk IDs, and queries that expose incomplete evidence.

Limit buffered work with a bounded channel, then decide whether producers should wait, reject, or drop work when it fills.

Qualify fallback models against the feature contract, define eligible failures, bound attempts, and make reduced behavior visible to callers.

Compose shared chat-client behavior in .NET without moving feature policy into middleware or hiding streaming, caching, and retry costs.