{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "@id": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026",
  "id": "coding-agent-streaming-apr26",
  "slug": "coding-agent-streaming-adoption-apr-2026",
  "title": "Streaming adoption by coding agent, April 2026",
  "shortTitle": "Agent streaming adoption",
  "topic": "agentic",
  "abstract": "Do coding agents stream their API responses? In April 2026, most agents stream nearly 100% of calls. Aider is the major outlier at 22% streaming, preferring batch completions. Claude Code streams 93% of calls. Aider also has the highest reasoning token intensity at 82%, suggesting it relies on reasoning models in non-streaming mode.",
  "whyItMatters": "Streaming affects both user experience and infrastructure cost. Streaming responses allow coding agents to show partial output in real time, improving perceived latency. Aider takes a different approach: it sends batch requests to reasoning models, waits for the full response, then applies code changes. This architectural choice explains its lower streaming rate and higher reasoning intensity.",
  "questions": [
    "Which coding agents use streaming responses?",
    "Why does Aider not use streaming for most calls?",
    "How does streaming adoption correlate with reasoning model usage?",
    "What percentage of Claude Code calls use streaming?"
  ],
  "period": "Apr 2026",
  "updated": "2026-05-16",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "caveats": [
    "Streaming percentage reflects request count, not token volume. A single non-streaming request may generate more tokens than multiple streaming ones.",
    "Reasoning intensity is computed as reasoning_tokens / output_tokens. Claude models report 0 reasoning_tokens in our pipeline even when extended thinking is active.",
    "GitHub Copilot and Codex CLI are excluded due to minimal traffic volume."
  ],
  "keyFindings": [
    "Cline, Forge, Zed, and OpenCode: 100% streaming. No batch completions at all.",
    "Claude Code: 93% streaming. The 7% non-streaming calls may be health checks or metadata requests.",
    "Aider: 22% streaming, 82% reasoning intensity. The only agent that primarily uses batch mode with reasoning models.",
    "Zed: 100% streaming with 40% reasoning intensity. Highest reasoning use among fully-streaming agents.",
    "Forge: 100% streaming but only 0.6% reasoning intensity. Minimal use of reasoning models."
  ],
  "columns": [
    {
      "key": "label",
      "label": "Agent",
      "unit": "count"
    },
    {
      "key": "streamingPct",
      "label": "Streaming",
      "unit": "percent"
    },
    {
      "key": "reasoningIntensity",
      "label": "Reasoning intensity",
      "unit": "percent"
    },
    {
      "key": "cacheHitPct",
      "label": "Cache hit rate",
      "unit": "percent"
    }
  ],
  "rows": [
    {
      "label": "Cline",
      "streamingPct": 1,
      "reasoningIntensity": 0.1207,
      "cacheHitPct": 0.6136
    },
    {
      "label": "Forge",
      "streamingPct": 1,
      "reasoningIntensity": 0.0062,
      "cacheHitPct": 0.6393
    },
    {
      "label": "Zed",
      "streamingPct": 1,
      "reasoningIntensity": 0.3983,
      "cacheHitPct": 0.8005
    },
    {
      "label": "OpenCode",
      "streamingPct": 1,
      "reasoningIntensity": 0.21,
      "cacheHitPct": 0.8898
    },
    {
      "label": "Kilo Code",
      "streamingPct": 0.9992,
      "reasoningIntensity": 0.1387,
      "cacheHitPct": 0.4549
    },
    {
      "label": "Roo Code",
      "streamingPct": 0.9987,
      "reasoningIntensity": 0.0807,
      "cacheHitPct": 0.7363
    },
    {
      "label": "Claude Code",
      "streamingPct": 0.9347,
      "reasoningIntensity": 0.0217,
      "cacheHitPct": 0.9191
    },
    {
      "label": "Aider",
      "streamingPct": 0.2223,
      "reasoningIntensity": 0.8155,
      "cacheHitPct": 0.8402
    }
  ],
  "rowKey": "label",
  "citation": {
    "apa": "Requesty (2026). Streaming adoption by coding agent, April 2026. Requesty Data. https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026",
    "bibtex": "@misc{requesty_coding_agent_streaming_adoption_apr_2026,\n  author       = {{Requesty}},\n  title        = {Streaming adoption by coding agent, April 2026},\n  year         = {2026},\n  howpublished = {\\url{https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026}},\n  note         = {Requesty Data}\n}"
  },
  "permalink": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026",
  "downloads": {
    "json": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026/data.json",
    "csv": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026/data.csv",
    "markdown": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026.md"
  },
  "citedIn": [],
  "image": "https://requesty.ai/data/coding-agent-streaming-adoption-apr-2026/opengraph-image",
  "source": {
    "organization": "Requesty",
    "url": "https://requesty.ai"
  }
}