feat(llm): cache hint TTL, breakpoint cap, and tool placement (#26779)

packages/llm/src/protocols/utils/bedrock-cache.ts

@@ -1,20 +1,37 @@
 import { Schema } from "effect"
 import type { CacheHint } from "../../schema"
+import { newBreakpoints, ttlBucket, type Breakpoints } from "./cache"
 
 // Bedrock cache markers are positional: emit a `cachePoint` block immediately
-// after the content the caller wants treated as a cacheable prefix.
+// after the content the caller wants treated as a cacheable prefix. Bedrock
+// accepts optional `ttl: "5m" | "1h"` on cachePoint, mirroring Anthropic.
 export const CachePointBlock = Schema.Struct({
-  cachePoint: Schema.Struct({ type: Schema.tag("default") }),
+  cachePoint: Schema.Struct({
+    type: Schema.tag("default"),
+    ttl: Schema.optional(Schema.Literals(["5m", "1h"])),
+  }),
 })
 export type CachePointBlock = Schema.Schema.Type<typeof CachePointBlock>
 
-// Bedrock recently added optional `ttl: "5m" | "1h"` on cachePoint. Map
-// `CacheHint.ttlSeconds` here once a recorded cassette validates the wire shape.
-const DEFAULT: CachePointBlock = { cachePoint: { type: "default" } }
+// Bedrock-Claude enforces the same 4-breakpoint cap as the Anthropic Messages
+// API. Callers pass a shared counter through every `block()` call site so the
+// budget is respected across `system`, `messages`, and `tools`.
+export const BEDROCK_BREAKPOINT_CAP = 4
 
-export const block = (cache: CacheHint | undefined): CachePointBlock | undefined => {
+export type { Breakpoints } from "./cache"
+export const breakpoints = () => newBreakpoints(BEDROCK_BREAKPOINT_CAP)
+
+const DEFAULT_5M: CachePointBlock = { cachePoint: { type: "default" } }
+const DEFAULT_1H: CachePointBlock = { cachePoint: { type: "default", ttl: "1h" } }
+
+export const block = (breakpoints: Breakpoints, cache: CacheHint | undefined): CachePointBlock | undefined => {
   if (cache?.type !== "ephemeral" && cache?.type !== "persistent") return undefined
-  return DEFAULT
+  if (breakpoints.remaining <= 0) {
+    breakpoints.dropped += 1
+    return undefined
+  }
+  breakpoints.remaining -= 1
+  return ttlBucket(cache.ttlSeconds) === "1h" ? DEFAULT_1H : DEFAULT_5M
 }
 
 export * as BedrockCache from "./bedrock-cache"

packages/llm/src/protocols/utils/cache.ts

@@ -0,0 +1,16 @@
+// Shared helpers for provider cache-marker lowering. Anthropic and Bedrock
+// both enforce a 4-breakpoint cap per request and accept the same `5m`/`1h`
+// TTL buckets, so the counter and TTL mapping live here.
+
+export interface Breakpoints {
+  remaining: number
+  dropped: number
+}
+
+export const newBreakpoints = (cap: number): Breakpoints => ({ remaining: cap, dropped: 0 })
+
+// Returns `"1h"` for any `ttlSeconds >= 3600`, otherwise `undefined` (the
+// provider default 5m). Anthropic & Bedrock both treat anything shorter than
+// an hour as 5m.
+export const ttlBucket = (ttlSeconds: number | undefined): "1h" | undefined =>
+  ttlSeconds !== undefined && ttlSeconds >= 3600 ? "1h" : undefined