--- title: "Claude Code Subagent Cost Controls: autoCompactWindow, Workflow Model Pinning, and Cache-Write Telemetry" date: 2026-10-15 tags: ["claude-code","subagents","cost","observability","changelog"] categories: ["Guides"] summary: "Claude Code v2.1.296 lets a subagent auto-compact earlier than the main session and pins every workflow agent to one model; v2.1.300 splits OpenTelemetry cache writes into 5-minute and 1-hour buckets. Together they are the first real cost-control surface for multi-agent runs. Based on the changelog only; I have not tested these." --- ![Claude Code Subagent Cost Controls: autoCompactWindow, Workflow Model Pinning, and Cache-Write Telemetry](/images/claude-code-subagent-cost-controls-v2-1-296-v2-1-300.png) Multi-agent setups get expensive in a boring way. No single call is outrageous. Ten subagents each drag a bloated context through a dozen turns, and the bill arrives as a surprise. The last two Claude Code releases add three small controls aimed at exactly that. Everything below comes from the [official changelog](https://code.claude.com/docs/en/changelog). I have not run these features hands-on, so treat the behavior descriptions as the changelog's claims, not my measurements. ## autoCompactWindow: compaction per subagent v2.1.296 (October 9) added `autoCompactWindow` to subagent frontmatter and to `--agents` definitions. The changelog's wording: a subagent can now auto-compact earlier than the main conversation's window. Why it matters: a research subagent that greps a monorepo accumulates tool output fast. Previously it inherited the same compaction threshold as everything else. A short-lived worker rarely needs a huge window. It needs to finish and hand back a summary. Setting a smaller window per agent keeps each turn's input smaller, which is where most of the spend sits. A sketch of what the frontmatter might look like (field name from the changelog; the value and its unit are my assumption, so check the docs before copying): ```markdown --- name: repo-scout description: Finds call sites and summarizes them model: haiku autoCompactWindow: 60000 --- Search the codebase for the requested symbol. Return a summary of at most 20 lines. ``` ## CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL: one model for the whole workflow Also in v2.1.296: the `CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL` environment variable runs every workflow agent on one model, while other subagents keep theirs. This pairs naturally with [Haiku 5.5's pricing](/posts/claude-haiku-5-5-subagent-model-pricing-effort-levels/) as a cheap worker tier. Fan out a workflow of twenty agents and you can force the entire fan-out onto a small model with one variable, rather than editing each definition. The trade-off is obvious and worth saying out loud: a pinned cheap model on a hard step will fail more, and you will pay for the retries. Use it for mechanical fan-out such as per-file review or migration passes, not for the planner. The same release also priced Sonnet 5.5 cache reads at $0.10 per million tokens in `/cost`, the status line, `--max-budget-usd`, and the SDK (it was $0.20). That is a display-side correction to match the halved price, but it means budget caps now count differently, so a limit you tuned last month will stretch further. ## Cache-write telemetry in v2.1.300 v2.1.300 (October 14) added `cache_creation_5m_tokens` and `cache_creation_1h_tokens` to the OpenTelemetry `api_request` event, splitting cache writes by lifetime. This is the piece I'd adopt first. Last week's idle-compaction change in v2.1.299 exists because a one-hour prompt cache expiring mid-session forces a full reprocess. Until now you could see that cost only in aggregate. With the split, you can answer concrete questions: - Are my subagents writing 1-hour cache entries for work that lasts three minutes? - Which workflows churn 5-minute entries because they idle between turns? - Did a config change move writes between buckets? If you already export OTel to a dashboard, adding two fields to a panel is cheap. If you don't, this is a decent reason to start. ## Smaller changes worth a line - Large requests to api.anthropic.com now use gzip compression even with telemetry disabled; `CLAUDE_CODE_GZIP_REQUEST_BODIES=0` turns it off. If you run behind a proxy that inspects bodies, test this before rollout. - Exit now force-kills background commands still running 1.5 seconds after being asked to stop. Good for leaked processes, bad if you relied on a background job surviving a quit. - `CLAUDE_CODE_OVERLOADED_RETRY_MAX_DELAY_MS` sets a longer maximum backoff for 529 overloaded retries, useful for unattended runs. - The MCP tool-description cap sent up front moved from 2,048 to 4,096 characters. - `virtualText` for mod prompt decorations draws text in the prompt box that never enters the submitted prompt. ## What to do this week 1. Add `autoCompactWindow` to your two or three most-spawned subagents and compare token usage before and after. 2. Pin mechanical workflow fan-out with `CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL`, keep planning on your strongest model. 3. Add the two cache-creation fields to your telemetry so you can see what you are paying for. ## The bigger point This is the unglamorous side of spec-driven development. When the spec is good and the agents run unattended, cost per run becomes a property you tune, like latency. Editor-bound tools that keep a human approving each step never face this problem, because the human is the throttle. A terminal-native agent that fans out to dozens of workers needs budgets, per-agent limits, and telemetry, and Claude Code is now shipping them release by release. That is what autonomy at scale requires. The caveat stands: until someone publishes measurements, how much these save is unknown. Measure your own runs. ## Sources - [Claude Code changelog (v2.1.296, v2.1.299, v2.1.300)](https://code.claude.com/docs/en/changelog)