@loopingai/core 0.7.1 → 0.8.0

package/README.md

@@ -229,7 +229,6 @@ not drag in the A2A adapter, and the test harness cannot reach a production bund
 | `@loopingai/core/agent`        | session, history, models + Workers AI, inference, budget, control tools     |
 | `@loopingai/core/host`         | `LoopingAgent` — the Durable Object body — and `PluginHost`                 |
 | `@loopingai/core/round`        | the delegating round loop: `RoundAgentBase`, `runHandleTask`, `runTurn`     |
-| `@loopingai/core/anthropic`    | Claude as a second provider — _optional peer on `@anthropic-ai/sdk`_        |
 | `@loopingai/core/subtasks`     | delegation types, decomposition, the `delegate` tool                        |
 | `@loopingai/core/subagent`     | `RecipeSubagentBase`, resumable runs, fingerprinting, workspace             |
 | `@loopingai/core/db`           | `AgentDB`, `notify_tasks` + `subtasks` schema, migrations, `PluginStore`    |
@@ -271,8 +270,9 @@ performs. A gateway pins the card's `kid` + `jku` on first registration
 
 ### Calling out, and knowing your own origin
 
-The same key proves this agent to services that are not the gateway — an inference
-proxy, another agent. `signCallerToken` mints the short-lived token for that: `iss` is
+The same key proves this agent to services that are not the gateway — another agent,
+or any service that verifies against the published JWKS. `signCallerToken` mints the
+short-lived token for that: `iss` is
 this deployment's origin, `jku` is derived from it, and the audience is normalized to a
 bare origin because the far side compares it byte-for-byte.
 
@@ -499,7 +499,6 @@ await withDb("accepts a turn once", async (db) => {
 - **Bindings:** `AI`, one Durable Object, one Workflow
 - **Secrets:** `A2A_SIGNING_KEY`, `GATEWAY_ORIGINS`
 - **Peers, never bundled:** `agents`, `ai`, `workers-ai-provider`
-- **Optional peer:** `@anthropic-ai/sdk`, needed only by `@loopingai/core/anthropic`
 
 That last point is not stylistic: two copies of `agents` in one Worker breaks the
 `Session` / `SessionMessage` types and every `instanceof`. For local development

package/dist/a2a/self-origin.d.ts

@@ -15,10 +15,10 @@
  * The obvious answer is a `SELF_ORIGIN` secret, and it is the wrong one. It
  * restates a value the request already carries, and it has to be kept
  * byte-identical by hand with the origin allowlist on the far side, in every
- * environment, forever. Both siblings that tried it took it back out:
- * `looping-anthropic-proxy` deleted `PROXY_AUDIENCE` in favour of `url.origin`,
- * and `looping-gateway` discovers its own origin from the first
- * signature-verified request rather than being told.
+ * environment, forever. Every sibling that tried it took it back out —
+ * `looping-gateway` discovers its own origin from the first signature-verified
+ * request rather than being told, and a verifying Worker that once carried a
+ * configured audience replaced it with `url.origin`.
  *
  * ## Where the value comes from
  *
@@ -51,9 +51,9 @@
  * The cost of pinning is what an agent does not have: several identities. An
  * agent has one endpoint — the one its card advertises, the one a gateway calls
  * and a verifier allowlists — so there is nothing to follow. Note the asymmetry
- * with `looping-anthropic-proxy`, which derives its audience per request and
- * refuses to cache: a *verifier* must accept every hostname it answers on, while
- * a *signer* needs one stable identity.
+ * with a *verifier*, which derives the audience it expects per request and must
+ * not cache it: a verifier has to accept every hostname it answers on, while a
+ * signer needs one stable identity.
  *
  * Nothing is persisted, which is what keeps a pin from outliving its truth. An
  * isolate is fresh on every `wrangler deploy` and recycles on its own, so a moved

package/dist/a2a/self-origin.js

@@ -15,10 +15,10 @@
  * The obvious answer is a `SELF_ORIGIN` secret, and it is the wrong one. It
  * restates a value the request already carries, and it has to be kept
  * byte-identical by hand with the origin allowlist on the far side, in every
- * environment, forever. Both siblings that tried it took it back out:
- * `looping-anthropic-proxy` deleted `PROXY_AUDIENCE` in favour of `url.origin`,
- * and `looping-gateway` discovers its own origin from the first
- * signature-verified request rather than being told.
+ * environment, forever. Every sibling that tried it took it back out —
+ * `looping-gateway` discovers its own origin from the first signature-verified
+ * request rather than being told, and a verifying Worker that once carried a
+ * configured audience replaced it with `url.origin`.
  *
  * ## Where the value comes from
  *
@@ -51,9 +51,9 @@
  * The cost of pinning is what an agent does not have: several identities. An
  * agent has one endpoint — the one its card advertises, the one a gateway calls
  * and a verifier allowlists — so there is nothing to follow. Note the asymmetry
- * with `looping-anthropic-proxy`, which derives its audience per request and
- * refuses to cache: a *verifier* must accept every hostname it answers on, while
- * a *signer* needs one stable identity.
+ * with a *verifier*, which derives the audience it expects per request and must
+ * not cache it: a verifier has to accept every hostname it answers on, while a
+ * signer needs one stable identity.
  *
  * Nothing is persisted, which is what keeps a pin from outliving its truth. An
  * isolate is fresh on every `wrangler deploy` and recycles on its own, so a moved

package/dist/agent/errors.d.ts

@@ -6,7 +6,7 @@
  * any particular one exists. `nonRecoverableKind` in
  * {@link file://./inference.ts inference.ts} keys on this file, so a provider
  * written outside core — the thing `ModelRuntimeFactory` exists to make cheap —
- * gets the same handling as `agent/anthropic` with no change to core.
+ * gets the same handling as core's own, with no change to core.
  *
  * ## Why a third classification was needed at all
  *
@@ -24,26 +24,26 @@
 /**
  * Who refused the request, when a `401` came back.
  *
- * There can be up to three authorities on the path, each with its own
- * credential: the AI Gateway (`cf-aig-authorization`), an optional intermediary
- * a deployment puts between the gateway and the provider (`"proxy"`), and the
- * model provider itself (`Authorization`). They fail with the same status code
- * and completely different remedies, so a rejection that does not say which one
- * it was sends an operator to rotate the wrong secret — which is exactly what
- * happened before this existed.
- *
- * `"proxy"` is the odd one out: it is generally *not* a secret to rotate. An
- * intermediary that mints its caller credential per request fails for reasons
- * upstream of any stored secret — configuration drift, a rotated signing key,
- * clock skew — so the remedy is to look, not to rotate. Core recognises no
- * particular intermediary; a deployment that has one supplies its own classifier
- * (see `AnthropicModelDeps.classifyAuthFailure`).
+ * Two authorities sit on the path, each with its own credential: the AI Gateway
+ * (`cf-aig-authorization`) and the model provider itself (`Authorization`). They
+ * fail with the same status code and have completely different remedies, so a
+ * rejection that does not say which one it was sends an operator to rotate the
+ * wrong secret — which is exactly what happened before this existed.
  *
  * `"unknown"` is a real answer and the default. Guessing `"provider"` for an
  * unrecognised body is how the misdiagnosis happens; saying "one of these, here
  * is how to check each" is worse copy and better information.
+ *
+ * A third arm, `"proxy"`, named an optional intermediary between the two — the
+ * shape where a deployment terminates the gateway's request at its own Worker to
+ * attach a credential. It was removed in 0.8.0 with the deployment that had one.
+ * If you build that topology again, the honest classification for its refusals
+ * is `"unknown"` until you widen this union, because the remedy genuinely
+ * differs: an intermediary minting its caller credential per request fails for
+ * reasons upstream of any stored secret, so the fix is to look rather than to
+ * rotate.
  */
-export type CredentialRejectedBy = "provider" | "gateway" | "proxy" | "unknown";
+export type CredentialRejectedBy = "provider" | "gateway" | "unknown";
 /**
  * A credential on the path to the model was rejected (HTTP 401 / 403).
  *

package/dist/agent/errors.js

@@ -6,7 +6,7 @@
  * any particular one exists. `nonRecoverableKind` in
  * {@link file://./inference.ts inference.ts} keys on this file, so a provider
  * written outside core — the thing `ModelRuntimeFactory` exists to make cheap —
- * gets the same handling as `agent/anthropic` with no change to core.
+ * gets the same handling as core's own, with no change to core.
  *
  * ## Why a third classification was needed at all
  *

package/dist/agent/inference.d.ts

@@ -49,14 +49,16 @@ export declare function isTransientAiError(err: unknown): boolean;
  * - `gateway-credential` — the gateway *in front of* the provider rejected the
  *   request, which the provider therefore never saw. Rotate the gateway's token
  *   instead; the model credential is very likely fine.
- * - `proxy-credential` — an intermediary between the gateway and the provider
- *   rejected the caller. Notably **not** a token to rotate: the credential it
- *   refused is minted per request, so the fault is upstream of the secret —
- *   configuration drift, a rotated signing key, or clock skew.
  * - `unknown-credential` — a `401`/`403` matching none of the shapes. Says so,
  *   rather than picking one and sending an operator to rotate a working secret.
+ *
+ * A fourth, `proxy-credential`, was removed in 0.8.0 along with
+ * {@link file://./errors.ts CredentialRejectedBy}'s `"proxy"` arm. Adding a kind
+ * back is a breaking change for every consumer, because the `Record` they map it
+ * with is total — which is the property that makes a new kind impossible to
+ * ignore, and the reason to remove one rather than leave it unreachable.
  */
-export type NonRecoverableKind = "credential" | "gateway-credential" | "proxy-credential" | "unknown-credential";
+export type NonRecoverableKind = "credential" | "gateway-credential" | "unknown-credential";
 /**
  * Why a round ended with no answer — one terminal status, two situations.
  *

package/dist/agent/inference.js

@@ -80,8 +80,6 @@ export function nonRecoverableKind(err) {
             return "credential";
         case "gateway":
             return "gateway-credential";
-        case "proxy":
-            return "proxy-credential";
         // Includes an error that crossed a realm boundary carrying no `source` at
         // all: `isInstance` is structural, so that is reachable, and "unknown" is
         // the honest reading of it.

package/dist/agent/model.d.ts

@@ -10,11 +10,17 @@ import type { ModelConfig } from "../config.js";
  * more than a `LanguageModel` from `ai`. It never learns which provider produced
  * it.
  *
- * The implementations are siblings under `agent/`, one directory each:
- * {@link file://./workers-ai/index.ts `./workers-ai`} is core's default, and
- * {@link file://./anthropic/index.ts `./anthropic`} is Claude behind an optional
- * peer dependency. A third provider is a third directory exporting one
- * {@link ModelRuntimeFactory}; nothing here has to change to admit it.
+ * Core ships exactly one implementation —
+ * {@link file://./workers-ai/index.ts `./workers-ai`} — as a sibling directory
+ * under `agent/`. A second provider is a second directory exporting one
+ * {@link ModelRuntimeFactory}, and nothing here has to change to admit it;
+ * a consumer can equally supply one from outside the package, which is the
+ * point of the seam.
+ *
+ * There was a `./anthropic` sibling until 0.8.0 — a hand-written Messages API
+ * adapter behind an optional peer dependency. It was removed with the only
+ * deployment that used it. Nothing about this contract changed when it went,
+ * which is the strongest thing that can be said for the contract.
  *
  * Which is why this file has no runtime imports at all. The Workers AI factory
  * used to live in it, and a contract that ships one implementation inline reads

package/dist/agent/workers-ai/index.d.ts

@@ -1,23 +1,23 @@
 /**
  * Workers AI — core's default model provider.
  *
- * A sibling of {@link file://../anthropic/index.ts `./anthropic`}, and like it a
- * provider rather than a capability: it ships no tools, no prompt copy and no
+ * A provider rather than a capability: it ships no tools, no prompt copy and no
  * policy; it satisfies {@link file://../model.ts ModelRuntime} and stops.
  *
- * It differs from that sibling in two ways, both deliberate:
+ * Two things about its shape are worth stating, because both look like
+ * omissions:
  *
  * **No `LanguageModel` adapter.** `workers-ai-provider` ships one, so this
- * directory is a factory and nothing else. The Anthropic side hand-builds the
- * adapter — the prompt mapping, the cache control, the error taxonomy — which is
- * why it is five files and this is one.
+ * directory is a factory and nothing else — one file rather than the five a
+ * hand-written adapter costs (a prompt mapping, a cache-control policy, an
+ * error taxonomy). That is what makes it the cheap default.
  *
- * **No package subpath.** `/anthropic` has one because `@anthropic-ai/sdk` is an
- * *optional* peer and an agent on Workers AI must not pay for a provider it
- * never calls. That argument does not apply here: `workers-ai-provider` is a
- * required peer, and this is the default every un-overridden seam reaches
- * through `LoopingAgent` itself, so it is in every consumer's module graph
- * already. It is exported from `@loopingai/core/agent` — one symbol, one import
- * path.
+ * **No package subpath.** `workers-ai-provider` is a *required* peer and this is
+ * the default every un-overridden seam reaches through `LoopingAgent` itself, so
+ * it is in every consumer's module graph already and a subpath would buy
+ * nothing. It is exported from `@loopingai/core/agent` — one symbol, one import
+ * path. A provider behind an *optional* peer would want its own subpath instead,
+ * so that an agent never calling it does not pay for it; `./anthropic` was one
+ * until 0.8.0.
  */
 export { createWorkersAIModelRuntime, workersAIModels, type WorkersAIRuntimeDeps } from "./runtime.js";

package/dist/agent/workers-ai/index.js

@@ -1,23 +1,23 @@
 /**
  * Workers AI — core's default model provider.
  *
- * A sibling of {@link file://../anthropic/index.ts `./anthropic`}, and like it a
- * provider rather than a capability: it ships no tools, no prompt copy and no
+ * A provider rather than a capability: it ships no tools, no prompt copy and no
  * policy; it satisfies {@link file://../model.ts ModelRuntime} and stops.
  *
- * It differs from that sibling in two ways, both deliberate:
+ * Two things about its shape are worth stating, because both look like
+ * omissions:
  *
  * **No `LanguageModel` adapter.** `workers-ai-provider` ships one, so this
- * directory is a factory and nothing else. The Anthropic side hand-builds the
- * adapter — the prompt mapping, the cache control, the error taxonomy — which is
- * why it is five files and this is one.
+ * directory is a factory and nothing else — one file rather than the five a
+ * hand-written adapter costs (a prompt mapping, a cache-control policy, an
+ * error taxonomy). That is what makes it the cheap default.
  *
- * **No package subpath.** `/anthropic` has one because `@anthropic-ai/sdk` is an
- * *optional* peer and an agent on Workers AI must not pay for a provider it
- * never calls. That argument does not apply here: `workers-ai-provider` is a
- * required peer, and this is the default every un-overridden seam reaches
- * through `LoopingAgent` itself, so it is in every consumer's module graph
- * already. It is exported from `@loopingai/core/agent` — one symbol, one import
- * path.
+ * **No package subpath.** `workers-ai-provider` is a *required* peer and this is
+ * the default every un-overridden seam reaches through `LoopingAgent` itself, so
+ * it is in every consumer's module graph already and a subpath would buy
+ * nothing. It is exported from `@loopingai/core/agent` — one symbol, one import
+ * path. A provider behind an *optional* peer would want its own subpath instead,
+ * so that an agent never calling it does not pay for it; `./anthropic` was one
+ * until 0.8.0.
  */
 export { createWorkersAIModelRuntime, workersAIModels } from "./runtime.js";

package/dist/config.d.ts

@@ -27,21 +27,6 @@ export interface ModelConfig {
     fallbackChatModelId: string;
     /** AI Gateway slug; `"default"` auto-provisions on first request. */
     aiGatewayId: string;
-    /**
-     * The segment after the gateway slug in `.../{gateway}/{provider}` — either a
-     * provider-native path like `"anthropic"` or a
-     * [custom provider](https://developers.cloudflare.com/ai-gateway/configuration/custom-providers/)
-     * slug. Core never reads it; a `ModelRuntime` that builds its own base URL
-     * does.
-     *
-     * Config rather than a literal at that call site because the parent agent and
-     * its subagent facet resolve their config independently, and a value that
-     * drifts between them routes delegated subtasks through a different provider
-     * than the round that delegated them — silently, since both satisfy
-     * `ModelRuntime`. Which path to pick, and why, belongs with the agent that
-     * picks it.
-     */
-    aiGatewayProvider: string;
     /**
      * Output-token ceiling for every chat call. Left unset, the binding applies a
      * per-model default which a reasoning model spends on `reasoning_content`
@@ -71,9 +56,9 @@ export interface ModelConfig {
      * The AI SDK does the waiting, and it does it properly:
      * `retryWithExponentialBackoffRespectingRetryHeaders` honours `retry-after-ms`
      * and `retry-after` and falls back to exponential backoff. It only fires for
-     * an `APICallError` carrying `isRetryable`, which is why
-     * {@link file://./agent/anthropic/language-model.ts} maps provider errors into
-     * that shape rather than rethrowing them raw.
+     * an `APICallError` carrying `isRetryable`, so a provider written outside core
+     * has to map its errors into that shape rather than rethrowing them raw, or
+     * none of this fires for it.
      *
      * Bounded at 4 by `resolveConfig`. The retries happen *inside*
      * `step.do("turn:<round>")`, and the SDK caps a single honoured `retry-after`

package/dist/config.js

@@ -32,10 +32,6 @@ export const DEFAULT_CORE_CONFIG = {
         // Not a model: an AI Gateway slug, and `"default"` is Cloudflare's own
         // auto-provision behaviour rather than a choice core is making for anyone.
         aiGatewayId: "default",
-        // The provider-native Anthropic endpoint, which is what a deployment with
-        // no custom provider registered has. Agents that must own the credential
-        // themselves override this with their `custom-*` slug.
-        aiGatewayProvider: "anthropic",
         maxOutputTokens: 16_384,
         reasoningEffort: "medium",
         // Two, which is the AI SDK's own default and enough to ride out the kind of

package/dist/host/agent.d.ts

@@ -118,12 +118,11 @@ export declare abstract class LoopingAgent<TEnv extends Cloudflare.Env & AiEnv &
      * a trap that only shows up as a performance bug. This is called once.
      *
      * `ModelRuntime` is the whole contract: return anything satisfying it and
-     * every loop in core keeps working unchanged. Core ships two implementations,
-     * one directory each — {@link file://../agent/workers-ai/index.ts
-     * `agent/workers-ai`} (the default below) and `@loopingai/core/anthropic` —
-     * and a third provider is a third directory exporting one
-     * {@link file://../agent/model.ts ModelRuntimeFactory}, not a change to
-     * anything on this path.
+     * every loop in core keeps working unchanged. Core ships one implementation,
+     * {@link file://../agent/workers-ai/index.ts `agent/workers-ai`} (the default
+     * below); a second provider is one more
+     * {@link file://../agent/model.ts ModelRuntimeFactory}, defined here or in the
+     * consumer, not a change to anything on this path.
      *
      * Takes the resolved {@link ModelConfig} rather than reading `this.config`, so
      * that this signature matches

package/dist/host/agent.js

@@ -125,12 +125,11 @@ export class LoopingAgent extends Agent {
      * a trap that only shows up as a performance bug. This is called once.
      *
      * `ModelRuntime` is the whole contract: return anything satisfying it and
-     * every loop in core keeps working unchanged. Core ships two implementations,
-     * one directory each — {@link file://../agent/workers-ai/index.ts
-     * `agent/workers-ai`} (the default below) and `@loopingai/core/anthropic` —
-     * and a third provider is a third directory exporting one
-     * {@link file://../agent/model.ts ModelRuntimeFactory}, not a change to
-     * anything on this path.
+     * every loop in core keeps working unchanged. Core ships one implementation,
+     * {@link file://../agent/workers-ai/index.ts `agent/workers-ai`} (the default
+     * below); a second provider is one more
+     * {@link file://../agent/model.ts ModelRuntimeFactory}, defined here or in the
+     * consumer, not a change to anything on this path.
      *
      * Takes the resolved {@link ModelConfig} rather than reading `this.config`, so
      * that this signature matches

package/dist/round/subagent.d.ts

@@ -59,14 +59,17 @@ export declare abstract class RecipeSubagentHost<TEnv extends Cloudflare.Env & A
      * Which provider this facet's chunks run on. Mirrors
      * {@link file://../host/agent.ts LoopingAgent.modelRuntime}, and **must be
      * overridden to match it** — a facet that keeps the Workers AI default while
-     * its parent runs on Claude would silently execute every subtask on a
-     * different model than the round that delegated it.
+     * its parent runs on another provider would silently execute every subtask on
+     * a different model than the round that delegated it.
      *
      * The two seams take the same arguments precisely so that keeping them in step
      * needs no discipline: write the provider once as a
      * {@link file://../agent/model.ts ModelRuntimeFactory} and have both return
-     * it. Two hand-copied `createAnthropicModelRuntime({...})` bodies is what this
-     * shape exists to stop, because nothing type-checks their agreement.
+     * it. Two hand-copied runtime-construction bodies is what this shape exists to
+     * stop, because nothing type-checks their agreement.
+     *
+     * Note the cheapest way to satisfy this is to override *neither* seam, which
+     * is what an agent on core's default does.
      *
      * Takes the model config rather than reading `this.config`, because the facet
      * resolves its config inside `buildRuntime` and this is called from there.

package/dist/round/subagent.js

@@ -54,14 +54,17 @@ export class RecipeSubagentHost extends RecipeSubagentBase {
      * Which provider this facet's chunks run on. Mirrors
      * {@link file://../host/agent.ts LoopingAgent.modelRuntime}, and **must be
      * overridden to match it** — a facet that keeps the Workers AI default while
-     * its parent runs on Claude would silently execute every subtask on a
-     * different model than the round that delegated it.
+     * its parent runs on another provider would silently execute every subtask on
+     * a different model than the round that delegated it.
      *
      * The two seams take the same arguments precisely so that keeping them in step
      * needs no discipline: write the provider once as a
      * {@link file://../agent/model.ts ModelRuntimeFactory} and have both return
-     * it. Two hand-copied `createAnthropicModelRuntime({...})` bodies is what this
-     * shape exists to stop, because nothing type-checks their agreement.
+     * it. Two hand-copied runtime-construction bodies is what this shape exists to
+     * stop, because nothing type-checks their agreement.
+     *
+     * Note the cheapest way to satisfy this is to override *neither* seam, which
+     * is what an agent on core's default does.
      *
      * Takes the model config rather than reading `this.config`, because the facet
      * resolves its config inside `buildRuntime` and this is called from there.

package/dist/subtasks/delegate.d.ts

@@ -54,9 +54,10 @@ export declare function makeDelegateTool(types: SubtaskTypeRegistry, maxSubtasks
  * why it took a Claude-backed agent to surface it.
  *
  * Nothing persists this: both halves of the pair are rebuilt together on every
- * request, so changing the shape needs no migration. See
- * {@link file://../agent/anthropic/prompt.ts providerSafeToolCallId} for the
- * backstop that catches the next one of these.
+ * request, so changing the shape needs no migration. There is no longer a
+ * provider-side backstop in core — the adapter that carried one went with
+ * `./anthropic` in 0.8.0 — so a provider added here that validates tool-call ids
+ * needs to sanitize them on its own way out.
  */
 export declare function delegateToolCallId(taskId: string, round: number): string;
 /**

package/dist/subtasks/delegate.js

@@ -60,9 +60,10 @@ export function makeDelegateTool(types, maxSubtasks) {
  * why it took a Claude-backed agent to surface it.
  *
  * Nothing persists this: both halves of the pair are rebuilt together on every
- * request, so changing the shape needs no migration. See
- * {@link file://../agent/anthropic/prompt.ts providerSafeToolCallId} for the
- * backstop that catches the next one of these.
+ * request, so changing the shape needs no migration. There is no longer a
+ * provider-side backstop in core — the adapter that carried one went with
+ * `./anthropic` in 0.8.0 — so a provider added here that validates tool-call ids
+ * needs to sanitize them on its own way out.
  */
 export function delegateToolCallId(taskId, round) {
     return `task_${taskId}_round_${round}_delegate`;

package/dist/testing/mock-model.js

@@ -122,7 +122,7 @@ export function rateLimitedModel(failures, ...steps) {
                 if (calls <= failures) {
                     throw new APICallError({
                         message: "429 Wholesale Rate limited",
-                        url: "anthropic:messages:test",
+                        url: "mock:chat:test",
                         requestBodyValues: {},
                         statusCode: 429,
                         responseHeaders: { "retry-after": "0" }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@loopingai/core",
-  "version": "0.7.1",
+  "version": "0.8.0",
   "description": "Shared, mandatory foundation for Looping agents on Cloudflare Workers: zero-trust A2A, durable task lifecycle, delegation and subagent runtime, test harness.",
   "keywords": [
     "a2a",
@@ -94,10 +94,6 @@
       "import": "./dist/testing/vcr-global-setup.js"
     },
     "./eslint": "./eslint-rules/index.js",
-    "./anthropic": {
-      "types": "./dist/agent/anthropic/index.d.ts",
-      "import": "./dist/agent/anthropic/index.js"
-    },
     "./package.json": "./package.json"
   },
   "scripts": {
@@ -123,8 +119,6 @@
     "zod": "^4.4.3"
   },
   "peerDependencies": {
-    "@ai-sdk/provider": "^4.0.0",
-    "@anthropic-ai/sdk": "^0.116.0",
     "@cloudflare/vitest-pool-workers": ">=0.18",
     "@typescript-eslint/utils": ">=8",
     "agents": "^0.20.0",
@@ -133,12 +127,6 @@
     "workers-ai-provider": "^4.0.0"
   },
   "peerDependenciesMeta": {
-    "@ai-sdk/provider": {
-      "optional": true
-    },
-    "@anthropic-ai/sdk": {
-      "optional": true
-    },
     "@cloudflare/vitest-pool-workers": {
       "optional": true
     },
@@ -150,8 +138,6 @@
     }
   },
   "devDependencies": {
-    "@ai-sdk/provider": "^4.0.0",
-    "@anthropic-ai/sdk": "^0.116.0",
     "@cloudflare/vitest-pool-workers": "^0.20.1",
     "@types/node": "^26.1.1",
     "agents": "^0.20.0",

package/dist/agent/anthropic/index.d.ts

@@ -1,15 +0,0 @@
-/**
- * `@loopingai/core/anthropic` — Claude as a second model provider.
- *
- * Its own subpath, and an **optional** peer dependency on `@anthropic-ai/sdk`,
- * for the same reason `/round` is not re-exported from the root barrel: an agent
- * that runs on Workers AI should not pay — in install size, in bundle bytes, or
- * in a dependency it must keep current — for a provider it never calls.
- *
- * What lives here is a provider, not a capability. It ships no tools, no prompt
- * copy and no policy; it satisfies {@link ModelRuntime} and stops.
- */
-export { CredentialRejectedError, type CredentialRejectedBy } from "../errors.js";
-export { createAnthropicLanguageModel, type AnthropicModelDeps } from "./language-model.js";
-export { createAnthropicModelRuntime, type AnthropicRuntimeDeps } from "./runtime.js";
-export { ANTHROPIC_PROVIDER, type CacheTtl } from "./prompt.js";

package/dist/agent/anthropic/index.js

@@ -1,19 +0,0 @@
-/**
- * `@loopingai/core/anthropic` — Claude as a second model provider.
- *
- * Its own subpath, and an **optional** peer dependency on `@anthropic-ai/sdk`,
- * for the same reason `/round` is not re-exported from the root barrel: an agent
- * that runs on Workers AI should not pay — in install size, in bundle bytes, or
- * in a dependency it must keep current — for a provider it never calls.
- *
- * What lives here is a provider, not a capability. It ships no tools, no prompt
- * copy and no policy; it satisfies {@link ModelRuntime} and stops.
- */
-// Re-exported, not owned: a rejected credential is a fact about the path to a
-// model, not about Anthropic, so the error lives with the rest of the provider
-// contract in {@link file://../errors.ts}. An agent that only imports this
-// subpath still gets it from one place.
-export { CredentialRejectedError } from "../errors.js";
-export { createAnthropicLanguageModel } from "./language-model.js";
-export { createAnthropicModelRuntime } from "./runtime.js";
-export { ANTHROPIC_PROVIDER } from "./prompt.js";

package/dist/agent/anthropic/language-model.d.ts

@@ -1,59 +0,0 @@
-import type Anthropic from "@anthropic-ai/sdk";
-import type { LanguageModelV4 } from "@ai-sdk/provider";
-import { type CredentialRejectedBy } from "../errors.js";
-import { type CacheTtl } from "./prompt.js";
-/**
- * A `LanguageModelV4` over `@anthropic-ai/sdk`, so core's loops can call Claude
- * without knowing they are.
- *
- * Every loop in core is written against `generateText` from `ai` and a
- * `LanguageModel` — {@link file://../../round/turn.ts turn.ts},
- * {@link file://../../subagent/run.ts run.ts} and
- * {@link file://../session.ts session.ts}. Satisfying that interface is what
- * keeps the round loop, the control-tool repair ladder, subtask execution and
- * the Workflow untouched by a second provider. The alternative — a bespoke
- * Messages-API loop for one agent — would have given all of that up.
- *
- * `ai@7` accepts `LanguageModelV2 | V3 | V4`; this targets **v4**, the newest
- * the installed `@ai-sdk/provider` defines.
- */
-/** How the adapter reaches the API. Everything is injected so nothing reads env. */
-export interface AnthropicModelDeps {
-    /**
-     * Constructed lazily by the runtime — see the note in
-     * {@link file://./runtime.ts}. Awaited, because building it has to resolve
-     * `env.AI.gateway(id).getUrl()`, which is async.
-     */
-    client: () => Anthropic | Promise<Anthropic>;
-    /** Anthropic model id, e.g. `claude-opus-5`. */
-    modelId: string;
-    /** `max_tokens` when a caller supplies none. Anthropic requires the field. */
-    defaultMaxTokens: number;
-    /** Prompt-cache TTL, or `false` to place no breakpoints. Defaults to `"5m"`. */
-    cache?: CacheTtl | false;
-    /**
-     * Reasoning effort, when the caller does not set one per-call.
-     *
-     * Maps to `output_config.effort`. Coding and agentic work wants `"xhigh"`;
-     * `"high"` is the API default. Core never picks this — an agent does.
-     */
-    effort?: "low" | "medium" | "high" | "xhigh" | "max";
-    /** Extra headers merged into every request (AI Gateway metadata lives here). */
-    headers?: Record<string, string>;
-    /**
-     * Recognise a deployment-specific authority in a `401`/`403` body.
-     *
-     * Consulted before the built-in shapes; return `undefined` to fall through to
-     * them. It exists because a deployment may put an authenticated intermediary
-     * between the gateway and Anthropic, and only that deployment knows what its
-     * refusal looks like — core recognising one particular proxy's error body
-     * would be exactly the deployment policy this package does not ship.
-     *
-     * The remedy is what makes it worth distinguishing at all: a proxy that mints
-     * its caller credential per request has no secret to rotate, so reporting its
-     * `401` as `credential` sends an operator to replace a working token. See
-     * {@link file://../errors.ts CredentialRejectedBy}.
-     */
-    classifyAuthFailure?: (body: unknown) => CredentialRejectedBy | undefined;
-}
-export declare function createAnthropicLanguageModel(deps: AnthropicModelDeps): LanguageModelV4;