Tag: llm

BYOK lets you point GitHub Copilot at a local Ollama model in VS Code, the Copilot CLI, and the Copilot app. You keep chat and agent mode. You lose inline completions, semantic search, embeddings, /delegate, and roughly 20 points of SWE-bench. Here is the exact trade.

Since August 21, 2026 mentioning @GitHub in Slack starts a Copilot cloud agent session the whole channel can steer. Here is the setup, the Slack Code channel model, why the pull request comes from an app identity instead of you, what the thread context capture actually exposes, and how the two separate billing meters add up.

The agent-framework-hosting packages are conversion helpers, not a runtime. One Agent instance, one AgentState, and three thin adapters give you a Telegram bot, an A2A peer, and an MCP tool from the same process. Here is the wiring, the per-channel session-ID policy, and the four things each channel refuses to do.

Agent Framework ships an in-memory chat history provider and nothing else for .NET. Here is a Cosmos DB backed ChatHistoryProvider that survives process restarts, the container design that keeps a 200-turn session cheap, and the second provider you need if you want semantic recall across sessions.

The cold start of a subagent is not what costs you money. Measured across 117 real Claude Code subagent transcripts, startup context was 0.6% to 18% of each agent's total spend. Depth is expensive because every layer runs its own agentic loop and hands the layer above a summary instead of evidence. Here is the compression test that tells you which layer to delete.

Conversation history can live in your process, in your database, in the provider, or on the machine that ran the agent. Where you put it does not change your token bill, it decides your retention exposure, and it decides whether you can ever change providers. The numbers, the retention windows, and a storage shape that survives all three.

Defensive system prompts are heuristic. Information-flow control is not: label every piece of content with integrity and confidentiality, propagate most-restrictive-wins through every tool call, and check the label at the sink before it runs. An 80-line runnable harness, the Agent Framework FIDES implementation, and the false positives the pattern buys you.

ModelContextProtocol 2.0.0 flipped HTTP transport to stateless by default, which is the one change that can drop every client still speaking 2025-11-25. HttpServerSessionMode.StatefulForInitializeClients in 2.2.0 serves both revisions on one endpoint. Here is the ordered upgrade, the ten breaking changes that matter, and the discover-probe bug that only a 2.1.0 client fixes.

Instructions files are deterministic and always sent. AGENTS.md sits at the bottom of the documented repository precedence list. Copilot Memory is a separate store Copilot writes for itself, read by only three surfaces, and it is not in the precedence list at all. Here is the support matrix and the rule for deciding where each convention belongs.

The experimental /rubber-duck command in VS Code 1.135 hands the agent's plan, code, and tests to a model from another family for review. GPT-5.4 critiques Claude, and the cross-family choice is the whole point.