Context & Memory

17 篇文章

Agent-Powered Codebase Q&A / Onboarding

Understanding a large or unfamiliar codebase can be a significant challenge for developers, especially when onboarding to a new project or trying to debug a complex system. Manually searching and trac

validated-in-production

Context-Minimization Pattern

User-supplied or tainted text lingers in the conversation, enabling it to influence later generations.

emerging

Context Window Anxiety Management

Models like Claude Sonnet 4.5 exhibit "context anxiety"—they become aware of approaching context window limits and proactively summarize progress or make decisive moves to close tasks, even when suffi

emerging

Context Window Auto-Compaction

Context overflow is a silent killer of agent reliability. When accumulated conversation history exceeds the model's context window: - **API errors**: Requests fail with `context_length_exceeded` or s

validated-in-production

Curated Code Context Window

Loading **all source files** or dumping entire repositories into the agent's context overwhelms the model, introduces noise, and slows inference. Coding agents need to focus on **only the most relevan

validated-in-production

Curated File Context Window

A coding agent often needs to reason about multiple source files, but dumping **all** files into its prompt: - Quickly exceeds token limits or inference budget. - Introduces noise: unrelated files (e

best-practice

Dynamic Context Injection

While layered configuration files provide good baseline context, agents often need specific pieces of information (e.g., contents of a particular file, output of a script, predefined complex prompt) o

established

Episodic Memory Retrieval & Injection

Stateless calls make agents forget prior decisions, causing repetition and shallow reasoning.

validated-in-production

Filesystem-Based Agent State

Many agent workflows are long-running or may be interrupted (by errors, timeouts, or user intervention). Keeping all intermediate state in the model's context window is fragile and doesn't persist acr

established

Layered Configuration Context

AI agents require relevant context to perform effectively. Providing this context manually in every prompt is cumbersome, and a one-size-fits-all global context is often too broad or too narrow. Diffe

established

Memory Synthesis from Execution Logs

Individual task execution transcripts contain valuable learnings, but: - **Too specific**: "Make this button pink" isn't useful as general guidance - **Unknown relevance**: Hard to predict which lear

emerging

Proactive Agent State Externalization

Modern models like Claude Sonnet 4.5 proactively attempt to externalize their state by writing summaries and notes (e.g., `CHANGELOG.md`, `SUMMARY.md`) to the file system without explicit prompting. H

emerging

Progressive Disclosure for Large Files

Large files (PDFs, DOCXs, images) overwhelm the context window when loaded naively. A 5-10MB PDF may contain only 10-20KB of relevant text/tables, but the entire file is often shoved into context, was

emerging

Prompt Caching via Exact Prefix Preservation

Long-running agent conversations with many tool calls can suffer from **quadratic performance degradation**: - **Growing JSON payloads**: Each iteration sends the entire conversation history to the A

emerging

Self-Identity Accumulation

AI agents lack continuous memory across sessions. Each conversation starts from zero, causing: - **Lost familiarity**: The agent doesn't remember user preferences, goals, or working patterns - **Repe

emerging

Semantic Context Filtering Pattern

Raw data sources are too verbose and noisy for effective LLM consumption. Full representations include invisible elements, implementation details, and irrelevant information that bloat context and con

emerging

Working Memory via TodoWrite

During complex multi-step tasks, AI agents lose track of: - What tasks are pending, in progress, or completed - Which tasks are blocked by dependencies - Verification steps that need to run - Next act

emerging