{
  "schema_version": "1.1",
  "id": "atlas-context-caching",
  "slug": "context-caching",
  "title": "Context Caching",
  "url": "https://feed7.dev/atlas/context-caching",
  "current_answer": null,
  "implementation_consequence": null,
  "agent_context": null,
  "confidence": "auto_collected",
  "last_verified": null,
  "last_updated": null,
  "evidence": [
    {
      "schema_version": "1.1",
      "id": "p9",
      "slug": "gemini-context-caching",
      "url": "https://feed7.dev/p/gemini-context-caching",
      "title": "Gemini agent SDK adds shared context caching across sessions",
      "why_included": "Cached context is billed once and reused across agent sessions — changes the economics of long system prompts.",
      "summary": "The agent SDK now exposes cross-session context caching with explicit TTL control. Cached tokens are ~10x cheaper on reuse.",
      "practical_implication": "Big static context (style guides, schemas, docs) belongs in the cache, not the prompt. Restructure bundles so stable material leads.",
      "agent_context": "Gemini SDK caches context across sessions with TTL control; cached tokens ~10x cheaper. Put stable material (guides, schemas) first so it caches; keep volatile material last.",
      "source": {
        "name": "Google",
        "url": "https://developers.googleblog.com/gemini-agent-sdk-context-cache",
        "published_at": "2026-06-29T00:00:00.000Z"
      },
      "source_class": "blog_post",
      "content_type": "Docs Update",
      "layer": "context",
      "domains": [
        "coding"
      ],
      "topics": [
        "context-caching"
      ],
      "verification": {
        "status": "official_source",
        "label": "Official Source",
        "method": "source_feed",
        "verified_at": null
      },
      "uncertainty": [],
      "connected_context": null,
      "lifecycle": "New",
      "published_at": "2026-06-29T00:00:00.000Z",
      "modified_at": "2026-06-29T00:00:00.000Z",
      "supersedes": [],
      "expires_at": null,
      "formats": {
        "html": "https://feed7.dev/p/gemini-context-caching",
        "json": "https://feed7.dev/p/gemini-context-caching.json",
        "markdown": "https://feed7.dev/p/gemini-context-caching.md"
      }
    },
    {
      "schema_version": "1.1",
      "id": "auto-cc8e132c61",
      "slug": "how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
      "url": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
      "title": "How enabling two settings tripled our scores on the ARC-AGI-3 benchmark",
      "why_included": "Record reasoning retention and compaction with the model name because runtime settings can materially alter agent eval results.",
      "summary": "Two API settings—reasoning retention and compaction—reportedly tripled GPT-5.6’s ARC-AGI-3 score. Agent evals should treat runtime configuration as part of the tested system.",
      "practical_implication": "Record these settings alongside the model name in agent evaluations. Configuration can materially affect results, so defaults and explicit settings should not be compared as equivalent systems.",
      "agent_context": "OpenAI says enabling **reasoning retention** and **compaction** produced **3× ARC-AGI-3 scores** for GPT-5.6 while also improving efficiency.\n\nRecord these settings alongside the model name in agent evaluations. Configuration can materially affect results, so defaults and explicit settings should not be compared as equivalent systems.\n\nThe supplied material provides no absolute scores, token usage, latency, or experimental detail, leaving the size and generality of the efficiency gain unclear.",
      "source": {
        "name": "OpenAI",
        "url": "https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores",
        "published_at": "2026-07-29T00:00:00.000Z"
      },
      "source_class": "blog_post",
      "content_type": "Official Release",
      "layer": "benchmark",
      "domains": [],
      "topics": [
        "agent-evals",
        "benchmark-integrity",
        "context-caching"
      ],
      "verification": {
        "status": "official_source",
        "label": "Official Source",
        "method": "source_feed",
        "verified_at": null
      },
      "uncertainty": [],
      "connected_context": null,
      "lifecycle": "New",
      "published_at": "2026-07-29T00:00:00.000Z",
      "modified_at": "2026-07-29T00:00:00.000Z",
      "supersedes": [],
      "expires_at": null,
      "formats": {
        "html": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
        "json": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61.json",
        "markdown": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61.md"
      }
    }
  ],
  "conflicting_sources": [],
  "superseded_claims": [],
  "corpus_evidence": [
    {
      "title": "TokTier: Exact Stateful Tokenization for Agentic LLM Serving",
      "url": "https://arxiv.org/abs/2607.29678v1",
      "source_name": "arXiv",
      "published_at": "2026-07-31T17:56:30+00:00",
      "summary": "TokTier targets a hidden agent-serving bottleneck: repeatedly tokenizing long transcripts after small tool results. Its stateful repair cut median vLLM time to first token by 16–34% in reported tests."
    },
    {
      "title": "ReToken: One Token to Improve Vision-Language Models for Visual Retrieval",
      "url": "https://arxiv.org/abs/2607.28627v1",
      "source_name": "arXiv",
      "published_at": "2026-07-30T17:59:56+00:00",
      "summary": "ReToken adds one learned retrieval embedding to select relevant visual tokens from a cached context, improving long-image and video benchmarks while fitting training and inference on one H100."
    },
    {
      "title": "Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating",
      "url": "https://arxiv.org/abs/2607.24667v1",
      "source_name": "arXiv",
      "published_at": "2026-07-27T17:08:27+00:00",
      "summary": "A delayed KV-eviction policy helps when memory reuse is sharp and observable, but loses its edge on natural-text benchmarks—a useful warning for agent-memory claims."
    },
    {
      "title": "diegosouzapw/OmniRoute",
      "url": "https://github.com/diegosouzapw/OmniRoute",
      "source_name": "GitHub",
      "published_at": null,
      "summary": "OmniRoute puts many model providers behind one OpenAI-compatible endpoint, with routing, quota failover, cost telemetry, compression, and coding-agent setup. Its breadth raises operational and trust questions."
    },
    {
      "title": "esengine/DeepSeek-Reasonix",
      "url": "https://github.com/esengine/DeepSeek-Reasonix",
      "source_name": "GitHub",
      "published_at": null,
      "summary": "Reasonix is a configurable terminal coding agent built to preserve DeepSeek prefix-cache reuse across long sessions, with optional planner/executor models and subprocess-based plugins."
    }
  ]
}