Claude 4 API: Tool Use Streaming & Prompt Caching vs Cursor 2.0

“The primitive here is clean: incremental tool-call deltas over SSE, and a cache-control header you attach to prompt segments to pin them server-side. The DX bet is that complexity lives in the HTTP layer, not in a new SDK abstraction — you opt in per-request, no new mental model required. The moment of truth is calling `stream=true` on a tool-use request and watching partial JSON arguments arrive before the model finishes thinking, which actually matters for agent loops where you want to dispatch work early. This is not a weekend-script replacement — implementing correct incremental JSON parsing for partial tool arguments plus a reliable distributed cache with 2M token capacity is a real engineering problem Anthropic has solved for you. The specific decision that earns the ship: cache invalidation is explicit and cache hits are reflected in the usage object, so you can actually measure what you're saving instead of guessing.”

“The primitive here is genuinely new: a persistent agent that holds task state across your editor session and works asynchronously, not just a fancy autocomplete loop. The DX bet is right — background agent offloads the mental overhead of babysitting a generation without yanking you out of flow state. The moment of truth is kicking off a refactor and watching it run in the background while you write new code; I've done this with raw Claude API calls and shell scripts and it's a bad time. The specific technical decision that earns the ship is the multi-repo context indexing — that's the hard infra problem nobody else has solved cleanly, and doing it at the editor layer rather than a separate indexing service is the right call.”

“Direct competitors are OpenAI's cached completions and Google's context caching in Gemini 1.5 — both shipping for months — so Anthropic is catching up, not leading. The specific scenario where this breaks: cache hit rates depend entirely on prompt structure, and developers who dynamically compose system prompts (inserting user-specific context at the top) will see near-zero cache utilization and pay full price while assuming they're saving money. The prediction: this feature doesn't get killed — it becomes table stakes infrastructure and Anthropic wins by having the largest cache window (2M vs. competitors' current limits). What would have to be true for me to be wrong: OpenAI ships a 10M token cache window before Anthropic's ecosystem matures, commoditizing the advantage. Still a ship because the streaming tool-use delta is genuinely differentiated — no competitor has clean partial-argument streaming for tool calls yet, and that changes agent loop architecture in ways that matter.”

“Direct competitor is GitHub Copilot Workspace, and Cursor 2.0 beats it on editor integration and context depth — Copilot Workspace still feels like a separate webapp bolted onto VS Code. The scenario where this breaks is any long-horizon task that touches infrastructure, auth, or secrets: the background agent runs in a sandboxed context and the moment it needs a credential or an environment variable it doesn't have, the whole async promise collapses into a blocked queue. What kills this in 12 months isn't a competitor — it's Microsoft shipping a credible background agent natively in VS Code with GitHub model access; the moat is editor UX and context indexing speed, and Microsoft can buy both. That said, Cursor's execution lead is real enough to ship today.”

“The thesis this bets on: by 2027, the dominant AI application architecture is a persistent agent with a large, stable context (tools, memory, instructions) that gets reused across thousands of user interactions — making context I/O cost the primary unit economics lever, not generation cost. The dependency that has to hold: agents don't collapse back to stateless chatbots, and context windows keep growing faster than per-token prices fall. The second-order effect nobody's talking about: prompt caching at 2M tokens makes it economically viable to give every enterprise user a fully-loaded, role-specific agent context at request time — which shifts competitive differentiation from 'who has the best model' to 'who has the best cached context corpus,' effectively making knowledge curation the new moat. This tool is riding the trend of context-window expansion-as-infrastructure, and it's on-time, not early — but the streaming tool-use primitive is ahead of the curve on agent loop efficiency. The future state where this is infrastructure: every production agentic system has a cache manifest the same way it has a CDN config.”

“The thesis Cursor 2.0 is betting on: within 2 years, the primary unit of developer work shifts from writing code to reviewing and directing code — the editor becomes a task queue, not a text buffer. The dependency is that long-horizon agents stop failing on multi-file refactors at the rate they currently do, which requires model reliability improvements that are trending in the right direction but not guaranteed. The second-order effect nobody is talking about is what happens to code review culture when PRs are generated asynchronously while the developer is in a meeting — the reviewing-to-writing ratio inverts, and that changes team structure, not just tooling. Cursor is riding the trend of agent-native development workflows and they are early, not on-time, which is the right place to be building infra.”

“The buyer is the engineering team at any company running Claude in production with long system prompts or multi-step agents — this comes out of the AI infrastructure budget, not a new budget line, which means no procurement friction. The pricing architecture is sound: cache reads at ~90% discount means the savings are real and measurable in the first billing cycle, which creates immediate retention — developers who restructure prompts to maximize cache hits are now architecturally coupled to Anthropic's caching implementation. The moat question is the honest one: this is infrastructure that OpenAI and Google will match, so the defensible position isn't the feature itself but the ecosystem of developers who've restructured their codebases around it. What survives a 10x model price drop: the streaming tool-use architecture, because that's about latency, not cost. The specific business decision that makes this viable is pricing cache reads as a separate SKU — it lets Anthropic capture value from high-volume production workloads without losing price-sensitive experimenters.”

“The buyer is the individual developer on a team budget, and the pricing architecture is smart — the $20 Pro tier gets you in the door but background agent compute burns through usage caps fast enough that teams will rationalize the $40 Business seat, which is where Anysphere's unit economics actually work. The moat question is the one that matters: it's not the model (they use Claude and OpenAI), it's the context indexing pipeline and the editor muscle memory they've built with hundreds of thousands of developers. The stress test is what happens when VS Code ships background agents natively — and it will — but Cursor's bet is that editor-level product velocity and distribution among early adopters creates enough switching friction to survive. That's a defensible bet for 18 months, not forever.”