#context-window
Every post tagged "context-window".
36 posts · showing 1–10
-
Your Support Agent Still Remembers the Customer Who Was Furious in March. Decide What Memory Expires Before You Decide What It Stores.
Cross-session memory fails less often from forgetting than from remembering too long. A four-class expiry scheme for support agents, and the one field every stored memory needs.
-
The On-Call Agent Restarted the Primary Anyway. The Instruction Not To Had Been Summarised Away.
Context compaction keeps the story of a long session and quietly drops the rules. The fix is a pinned constraint block that the summariser is never allowed to touch, plus a check that proves it survived.
-
Summarising the Conversation Threw Away the One ID the Next Tool Call Needed. Summarise Prose, Never Identifiers.
Context compaction reads fine to a human and breaks the agent anyway: the summary kept the story and lost the order number. The fix is to stop asking a summariser to carry identifiers at all.
-
When the Context Window Fills, Cut in This Order — and Leave a Stub Behind
Most agents evict context by dropping the oldest tokens, which reliably deletes the nine words that mattered while keeping a 4,000-token HTML dump nobody needs. Here is the order to cut in, and why every eviction should leave a stub behind.
-
Your Tool Returned 4,000 Rows and the Agent Needed Three: Truncate, Paginate, or Summarize?
Most tool endpoints were written for a caller that can loop and discard. An agent reads the whole response in one gulp and keeps it forever — and the three ways of shrinking that response fail in completely different ways.
-
Your Retriever Returned 12 Chunks. The Agent Only Really Read 3 of Them.
The correct passage was in the prompt and the agent wrote around it anyway. That's not a retrieval bug — it's a placement bug, and there's a one-minute test that tells the two apart before you touch your embeddings.
-
Map-Reduce or Sequential Refine? How an Agent Should Read 400 Pages
Chunking 400 pages of contracts forces a choice most teams make by accident. One shape quietly drops evidence as it goes; the other can never spot a conflict between two documents — and the fix is not the pattern, it's what the map step returns.
-
What Should Your Agent Forget? Give Every Memory an Expiry Rule
Agent memory systems have a write verb and a recall verb, but no verb for "stop believing this." Here's how to decide at write time what makes each memory stop being true — and why expiry should downgrade a fact rather than delete it.
-
When Memory Contradicts the Tool Call, Which One Does the Agent Believe?
An agent had the live billing data and a three-week-old memory in the same context window, and answered from the memory. The reason isn't retrieval — it's how prompts are assembled, and there are three specific fixes.
-
What Crosses the Handoff: Transcript, Summary, or Contract?
A triage agent spends eleven tool calls finding the bug, then hands off. Passing the transcript ships its dead ends; passing a summary strips the uncertainty. What a typed handoff contract gets right — and the one field teams always forget.