@xtruder/opencode-claude-max-plugin 0.3.1 → 0.4.1

package/build/model.d.ts

@@ -2,6 +2,31 @@ import type { LanguageModelV3, LanguageModelV3CallOptions, LanguageModelV3Genera
 import type Anthropic from "@anthropic-ai/sdk";
 type DoGenerateResult = LanguageModelV3GenerateResult;
 type DoStreamResult = LanguageModelV3StreamResult;
+/**
+ * Build a clear error for a Fable 5 / Mythos-class safety refusal.
+ *
+ * Fable 5's safety classifiers can decline a request — the Messages API
+ * returns this as a *successful* HTTP 200 with `stop_reason: "refusal"`,
+ * empty `content`, and a `stop_details` object naming the policy area.
+ * Categories: cyber, bio, frontier_llm, reasoning_extraction (may be null).
+ *
+ * For now we surface this as an error so the user gets a clear message
+ * instead of an empty/confusing response. A future enhancement is to
+ * automatically retry on a fallback model (Claude Opus 4.8), per Anthropic's
+ * recommended pattern. See RESEARCH.md.
+ */
+export declare function isRefusal(stopReason: string | null | undefined): boolean;
+export declare function refusalError(stopDetails: any, fallbackModel?: string): Error;
+/**
+ * Internal marker header: set on requests that need the server-side-fallback
+ * betas (request carries a `fallbacks` chain, or the conversation history
+ * echoes a `fallback` block from a previous fallback response). The fetch
+ * wrapper in index.ts translates it into the real `anthropic-beta` flags and
+ * strips it before the request leaves the process. This keeps the decision
+ * here — where the request is built — instead of sniffing the serialized
+ * body in the fetch wrapper (cf. RESEARCH.md Discovery #24/#25).
+ */
+export declare const FALLBACK_BETAS_HEADER = "x-anthropic-sdk-fallback-betas";
 export declare class AnthropicSDKModel implements LanguageModelV3 {
     private client;
     private providerName;

package/build/model.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"model.d.ts","sourceRoot":"","sources":["../src/model.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,eAAe,EACf,0BAA0B,EAG1B,6BAA6B,EAE7B,2BAA2B,EAE5B,MAAM,kBAAkB,CAAA;AACzB,OAAO,KAAK,SAAS,MAAM,mBAAmB,CAAA;AAQ9C,KAAK,gBAAgB,GAAG,6BAA6B,CAAA;AACrD,KAAK,cAAc,GAAG,2BAA2B,CAAA;AA8HjD,qBAAa,iBAAkB,YAAW,eAAe;IAarD,OAAO,CAAC,MAAM;IACd,OAAO,CAAC,YAAY;IACpB,OAAO,CAAC,OAAO;IAdjB,QAAQ,CAAC,oBAAoB,EAAG,IAAI,CAAS;IAC7C,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAA;IACzB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAA;IACxB,QAAQ,CAAC,aAAa,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CAAK;IAErD,mEAAmE;IACnE,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAQ;IACnC,+FAA+F;IAC/F,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAS;gBAGnC,OAAO,EAAE,MAAM,EACP,MAAM,EAAE,SAAS,EACjB,YAAY,EAAE,MAAM,EACpB,OAAO,GAAE,OAAe;IASlC,OAAO,CAAC,WAAW;IA6KnB;;;;OAIG;IACH,OAAO,CAAC,mBAAmB;IAMrB,UAAU,CAAC,OAAO,EAAE,0BAA0B,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAsF1E,QAAQ,CAAC,OAAO,EAAE,0BAA0B,GAAG,OAAO,CAAC,cAAc,CAAC;CA4E7E"}
+{"version":3,"file":"model.d.ts","sourceRoot":"","sources":["../src/model.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,eAAe,EACf,0BAA0B,EAG1B,6BAA6B,EAE7B,2BAA2B,EAE5B,MAAM,kBAAkB,CAAA;AACzB,OAAO,KAAK,SAAS,MAAM,mBAAmB,CAAA;AAc9C,KAAK,gBAAgB,GAAG,6BAA6B,CAAA;AACrD,KAAK,cAAc,GAAG,2BAA2B,CAAA;AAkDjD;;;;;;;;;;;;GAYG;AACH,wBAAgB,SAAS,CAAC,UAAU,EAAE,MAAM,GAAG,IAAI,GAAG,SAAS,GAAG,OAAO,CAExE;AAED,wBAAgB,YAAY,CAAC,WAAW,EAAE,GAAG,EAAE,aAAa,CAAC,EAAE,MAAM,GAAG,KAAK,CAW5E;AAmBD;;;;;;;;GAQG;AACH,eAAO,MAAM,qBAAqB,mCAAmC,CAAA;AA6DrE,qBAAa,iBAAkB,YAAW,eAAe;IAarD,OAAO,CAAC,MAAM;IACd,OAAO,CAAC,YAAY;IACpB,OAAO,CAAC,OAAO;IAdjB,QAAQ,CAAC,oBAAoB,EAAG,IAAI,CAAS;IAC7C,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAA;IACzB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAA;IACxB,QAAQ,CAAC,aAAa,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CAAK;IAErD,mEAAmE;IACnE,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAQ;IACnC,+FAA+F;IAC/F,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAS;gBAGnC,OAAO,EAAE,MAAM,EACP,MAAM,EAAE,SAAS,EACjB,YAAY,EAAE,MAAM,EACpB,OAAO,GAAE,OAAe;IASlC,OAAO,CAAC,WAAW;IAuMnB;;;;OAIG;IACH,OAAO,CAAC,mBAAmB;IAUrB,UAAU,CAAC,OAAO,EAAE,0BAA0B,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAqL1E,QAAQ,CAAC,OAAO,EAAE,0BAA0B,GAAG,OAAO,CAAC,cAAc,CAAC;CA2F7E"}

package/build/pause-turn.d.ts

@@ -0,0 +1,36 @@
+/**
+ * Auto-continuation for `stop_reason: "pause_turn"`.
+ *
+ * The Messages API pauses long-running turns and expects the client to
+ * resend the conversation — with the paused turn's partial assistant
+ * content appended — to let the model continue the same turn. Observed in
+ * the wild with Claude Fable 5 when the safety-refusal fallback hop runs
+ * long: the server returns `pause_turn` after ~1 output token and no
+ * content. Without auto-continuation that surfaces as a silent empty
+ * response (finish reason "unknown").
+ *
+ * The wrapper is transport-agnostic: it consumes streaming events,
+ * reconstructs the raw wire content blocks, and re-issues the request via
+ * the provided `request` callback whenever a segment ends with
+ * `pause_turn`. The paused segment's `message_delta` and `message_stop`
+ * events are suppressed so downstream conversion sees one continuous turn.
+ */
+import type { MessageStreamEvent } from "@anthropic-ai/sdk/resources/messages";
+export declare const MAX_PAUSE_TURN_CONTINUATIONS = 5;
+type RawBlock = Record<string, any>;
+export declare function isPauseTurn(stopReason: string | null | undefined): boolean;
+/**
+ * Continuation request params: the original conversation with the paused
+ * turn's partial content appended as an assistant message. With no partial
+ * content (the observed Fable 5 case) the request is resent unchanged —
+ * an empty assistant content array would be rejected by the API.
+ */
+export declare function continuationParams(params: Record<string, any>, blocks: RawBlock[]): Record<string, any>;
+/**
+ * Wrap a stream of Anthropic events with pause_turn auto-continuation.
+ * After `maxContinuations` pauses the pause_turn `message_delta` is passed
+ * through so stream conversion can surface a clear error.
+ */
+export declare function withPauseTurnContinuation(initial: AsyncIterable<MessageStreamEvent>, params: Record<string, any>, request: (params: Record<string, any>) => Promise<AsyncIterable<MessageStreamEvent>>, maxContinuations?: number): AsyncGenerator<MessageStreamEvent>;
+export {};
+//# sourceMappingURL=pause-turn.d.ts.map

package/build/pause-turn.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"pause-turn.d.ts","sourceRoot":"","sources":["../src/pause-turn.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AACH,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,sCAAsC,CAAA;AAE9E,eAAO,MAAM,4BAA4B,IAAI,CAAA;AAE7C,KAAK,QAAQ,GAAG,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAA;AAEnC,wBAAgB,WAAW,CAAC,UAAU,EAAE,MAAM,GAAG,IAAI,GAAG,SAAS,GAAG,OAAO,CAE1E;AAoDD;;;;;GAKG;AACH,wBAAgB,kBAAkB,CAChC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAC3B,MAAM,EAAE,QAAQ,EAAE,GACjB,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAMrB;AAED;;;;GAIG;AACH,wBAAuB,yBAAyB,CAC9C,OAAO,EAAE,aAAa,CAAC,kBAAkB,CAAC,EAC1C,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAC3B,OAAO,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,KAAK,OAAO,CAAC,aAAa,CAAC,kBAAkB,CAAC,CAAC,EACpF,gBAAgB,SAA+B,GAC9C,cAAc,CAAC,kBAAkB,CAAC,CAuBpC"}

package/build/server.js

@@ -48,8 +48,8 @@ function hasCchPlaceholder(body) {
   return block?.text?.includes("cch=00000") ?? false;
 }
 
-// src/claudecode-system-opus48.txt
-var claudecode_system_opus48_default = `
+// src/claudecode-system-new.txt
+var claudecode_system_new_default = `
 You are an interactive agent that helps users with software engineering tasks.
 
 # Harness
@@ -222,6 +222,84 @@ function getCachedCredentials(path) {
 import { APIError, RateLimitError } from "@anthropic-ai/sdk";
 import { createHash, randomBytes } from "node:crypto";
 
+// src/pause-turn.ts
+var MAX_PAUSE_TURN_CONTINUATIONS = 5;
+function isPauseTurn(stopReason) {
+  return stopReason === "pause_turn";
+}
+
+class BlockAccumulator {
+  blocks = [];
+  open = new Map;
+  push(event) {
+    switch (event.type) {
+      case "content_block_start": {
+        this.open.set(event.index, {
+          block: JSON.parse(JSON.stringify(event.content_block))
+        });
+        break;
+      }
+      case "content_block_delta": {
+        const entry = this.open.get(event.index);
+        if (!entry)
+          break;
+        const delta = event.delta;
+        if (delta.type === "text_delta") {
+          entry.block.text = (entry.block.text ?? "") + delta.text;
+        } else if (delta.type === "thinking_delta") {
+          entry.block.thinking = (entry.block.thinking ?? "") + delta.thinking;
+        } else if (delta.type === "signature_delta") {
+          entry.block.signature = (entry.block.signature ?? "") + delta.signature;
+        } else if (delta.type === "input_json_delta") {
+          entry.argsText = (entry.argsText ?? "") + delta.partial_json;
+        }
+        break;
+      }
+      case "content_block_stop": {
+        const entry = this.open.get(event.index);
+        if (!entry)
+          break;
+        this.open.delete(event.index);
+        if (entry.argsText !== undefined) {
+          try {
+            entry.block.input = JSON.parse(entry.argsText || "{}");
+          } catch {
+            entry.block.input = {};
+          }
+        }
+        this.blocks.push(entry.block);
+        break;
+      }
+    }
+  }
+}
+function continuationParams(params, blocks) {
+  if (blocks.length === 0)
+    return params;
+  return {
+    ...params,
+    messages: [...params.messages ?? [], { role: "assistant", content: blocks }]
+  };
+}
+async function* withPauseTurnContinuation(initial, params, request, maxContinuations = MAX_PAUSE_TURN_CONTINUATIONS) {
+  const acc = new BlockAccumulator;
+  let stream = initial;
+  let continuations = 0;
+  outer:
+    while (true) {
+      for await (const event of stream) {
+        if (event.type === "message_delta" && isPauseTurn(event.delta?.stop_reason) && continuations < maxContinuations) {
+          continuations++;
+          stream = await request(continuationParams(params, acc.blocks));
+          continue outer;
+        }
+        acc.push(event);
+        yield event;
+      }
+      return;
+    }
+}
+
 // src/tool-names.ts
 import { existsSync as existsSync2, readFileSync as readFileSync2 } from "node:fs";
 import { homedir as homedir2 } from "node:os";
@@ -382,6 +460,14 @@ function convertUserMessage(message) {
 function convertAssistantMessage(message) {
   const content = [];
   for (const part of message.content) {
+    const fallback = part.providerMetadata?.anthropic?.fallback ?? part.providerOptions?.anthropic?.fallback;
+    if (fallback?.from?.model && fallback?.to?.model) {
+      content.push({
+        type: "fallback",
+        from: { model: fallback.from.model },
+        to: { model: fallback.to.model }
+      });
+    }
     switch (part.type) {
       case "text":
         if (part.text.length > 0) {
@@ -460,6 +546,14 @@ var idCounter = 0;
 function generateId() {
   return `block-${Date.now()}-${idCounter++}`;
 }
+function buildRefusalError(stopDetails, fallbackModel) {
+  const category = stopDetails?.category ?? null;
+  const explanation = stopDetails?.explanation ?? null;
+  const categoryNote = category ? ` (category: ${category})` : "";
+  const detail = explanation ? explanation : "Claude Fable 5's safety classifiers declined this request.";
+  const hint = fallbackModel ? `The configured fallback model (${fallbackModel}) also refused.` : `Retry with a fallback model such as anthropic-sdk/claude-opus-4-8.`;
+  return new Error(`Claude Fable 5 refused this request${categoryNote}. ${detail} ${hint}`);
+}
 function mapFinishReason(stopReason) {
   const unified = (() => {
     switch (stopReason) {
@@ -476,8 +570,13 @@ function mapFinishReason(stopReason) {
   })();
   return { unified, raw: stopReason ?? undefined };
 }
-function convertStream(anthropicStream, modelId) {
+function convertStream(anthropicStream, modelId, context) {
   const blockStates = new Map;
+  const ctx = {
+    apiModelId: context?.apiModelId ?? modelId,
+    fallbacksEnabled: context?.fallbacksEnabled ?? false,
+    fallbackModel: context?.fallbackModel
+  };
   let inputTokens;
   let outputTokens;
   let cachedInputTokens;
@@ -486,7 +585,7 @@ function convertStream(anthropicStream, modelId) {
     async start(controller) {
       try {
         for await (const event of anthropicStream) {
-          const parts = processEvent(event, blockStates, modelId);
+          const parts = processEvent(event, blockStates, modelId, ctx);
           if (event.type === "message_start" && event.message.usage) {
             const u = event.message.usage;
             inputTokens = u.input_tokens;
@@ -496,6 +595,18 @@ function convertStream(anthropicStream, modelId) {
           if (event.type === "message_delta") {
             const delta = event;
             outputTokens = delta.usage?.output_tokens;
+            if (delta.delta?.stop_reason === "refusal") {
+              controller.enqueue({
+                type: "error",
+                error: buildRefusalError(delta.delta?.stop_details, ctx.fallbacksEnabled ? ctx.fallbackModel : undefined)
+              });
+            }
+            if (delta.delta?.stop_reason === "pause_turn") {
+              controller.enqueue({
+                type: "error",
+                error: new Error(`Anthropic kept pausing this turn (stop_reason "pause_turn") ` + `after the provider's auto-continuation attempts. Retry the request.`)
+              });
+            }
             const finishReason = mapFinishReason(delta.delta?.stop_reason);
             controller.enqueue({
               type: "finish",
@@ -532,10 +643,16 @@ function convertStream(anthropicStream, modelId) {
     }
   });
 }
-function processEvent(event, blockStates, modelId) {
+function processEvent(event, blockStates, modelId, ctx) {
   const parts = [];
   switch (event.type) {
     case "message_start": {
+      const servedModel = event.message.model;
+      if (ctx.fallbacksEnabled && servedModel && servedModel !== ctx.apiModelId) {
+        ctx.pendingMeta = {
+          servedBy: { from: ctx.apiModelId, to: servedModel, kind: "sticky" }
+        };
+      }
       parts.push({
         type: "response-metadata",
         id: event.message.id,
@@ -547,14 +664,38 @@ function processEvent(event, blockStates, modelId) {
     case "content_block_start": {
       const index = event.index;
       const block = event.content_block;
-      if (block.type === "text") {
+      const takeMeta = () => {
+        const meta = ctx.pendingMeta;
+        ctx.pendingMeta = undefined;
+        return meta;
+      };
+      if (block.type === "fallback") {
+        ctx.pendingMeta = {
+          fallback: { from: block.from, to: block.to },
+          servedBy: {
+            from: block.from?.model ?? ctx.apiModelId,
+            to: block.to?.model ?? "unknown",
+            kind: "fallback"
+          }
+        };
+      } else if (block.type === "text") {
         const id = generateId();
-        blockStates.set(index, { type: "text", id });
-        parts.push({ type: "text-start", id });
+        const meta = takeMeta();
+        blockStates.set(index, { type: "text", id, fallbackMeta: meta });
+        parts.push({
+          type: "text-start",
+          id,
+          ...meta ? { providerMetadata: { anthropic: meta } } : {}
+        });
       } else if (block.type === "thinking") {
         const id = generateId();
-        blockStates.set(index, { type: "thinking", id });
-        parts.push({ type: "reasoning-start", id });
+        const meta = takeMeta();
+        blockStates.set(index, { type: "thinking", id, fallbackMeta: meta });
+        parts.push({
+          type: "reasoning-start",
+          id,
+          ...meta ? { providerMetadata: { anthropic: meta } } : {}
+        });
       } else if (block.type === "tool_use") {
         const toolId = block.id;
         const toolName = toOpencodeToolName(block.name);
@@ -563,7 +704,8 @@ function processEvent(event, blockStates, modelId) {
           id: toolId,
           toolUseId: toolId,
           toolName,
-          argsText: ""
+          argsText: "",
+          fallbackMeta: takeMeta()
         });
         parts.push({
           type: "tool-input-start",
@@ -611,12 +753,14 @@ function processEvent(event, blockStates, modelId) {
       if (state.type === "text") {
         parts.push({ type: "text-end", id: state.id });
       } else if (state.type === "thinking") {
+        const meta = {
+          ...state.signature ? { signature: state.signature } : {},
+          ...state.fallbackMeta
+        };
         parts.push({
           type: "reasoning-end",
           id: state.id,
-          ...state.signature ? {
-            providerMetadata: { anthropic: { signature: state.signature } }
-          } : {}
+          ...Object.keys(meta).length > 0 ? { providerMetadata: { anthropic: meta } } : {}
         });
       } else if (state.type === "tool_use") {
         parts.push({ type: "tool-input-end", id: state.id });
@@ -624,7 +768,8 @@ function processEvent(event, blockStates, modelId) {
           type: "tool-call",
           toolCallId: state.toolUseId,
           toolName: state.toolName,
-          input: state.argsText || "{}"
+          input: state.argsText || "{}",
+          ...state.fallbackMeta ? { providerMetadata: { anthropic: state.fallbackMeta } } : {}
         });
       }
       blockStates.delete(index);
@@ -695,6 +840,17 @@ function handleApiError(error) {
   }
   throw error;
 }
+function isRefusal(stopReason) {
+  return stopReason === "refusal";
+}
+function refusalError(stopDetails, fallbackModel) {
+  const category = stopDetails?.category ?? null;
+  const explanation = stopDetails?.explanation ?? null;
+  const categoryNote = category ? ` (category: ${category})` : "";
+  const detail = explanation ? explanation : "Claude Fable 5's safety classifiers declined this request.";
+  const hint = fallbackModel ? `The configured fallback model (${fallbackModel}) also refused.` : `Retry with a fallback model such as anthropic-sdk/claude-opus-4-8.`;
+  return new Error(`Claude Fable 5 refused this request${categoryNote}. ${detail} ${hint}`);
+}
 function mapFinishReason2(stopReason) {
   const unified = (() => {
     switch (stopReason) {
@@ -711,9 +867,10 @@ function mapFinishReason2(stopReason) {
   })();
   return { unified, raw: stopReason ?? undefined };
 }
+var FALLBACK_BETAS_HEADER = "x-anthropic-sdk-fallback-betas";
 var BILLING_SYSTEM_BLOCK = {
   type: "text",
-  text: "x-anthropic-billing-header: cc_version=2.1.154.cea; cc_entrypoint=sdk-cli; cch=00000;"
+  text: "x-anthropic-billing-header: cc_version=2.1.173.d11; cc_entrypoint=sdk-cli; cch=00000;"
 };
 var IDENTITY_SYSTEM_BLOCK = {
   type: "text",
@@ -847,6 +1004,9 @@ class AnthropicSDKModel {
       }
       if (anthropicOptions.metadata)
         params.metadata = anthropicOptions.metadata;
+      if (typeof anthropicOptions.refusalFallback === "string" && anthropicOptions.refusalFallback.length > 0) {
+        params.fallbacks = [{ model: anthropicOptions.refusalFallback }];
+      }
     }
     if (this.isOAuth && supportsContextManagement(this.apiModelId)) {
       const edits = [];
@@ -861,16 +1021,19 @@ class AnthropicSDKModel {
         params.context_management = { edits };
       }
     }
-    return { params, warnings };
+    const needsFallbackBetas = params.fallbacks != null || messages.some((msg) => Array.isArray(msg.content) && msg.content.some((block) => block?.type === "fallback"));
+    return { params, warnings, needsFallbackBetas };
   }
-  buildRequestOptions(signal) {
+  buildRequestOptions(signal, needsFallbackBetas) {
     const opts = {};
     if (signal)
       opts.signal = signal;
+    if (needsFallbackBetas)
+      opts.headers = { [FALLBACK_BETAS_HEADER]: "1" };
     return opts;
   }
   async doGenerate(options) {
-    const { params, warnings } = this.buildParams(options);
+    const { params, warnings, needsFallbackBetas } = this.buildParams(options);
     if (!options.maxOutputTokens && params.max_tokens > 4096) {
       params.max_tokens = 4096;
     }
@@ -879,31 +1042,92 @@ class AnthropicSDKModel {
       response = await this.client.messages.create({
         ...params,
         stream: false
-      }, this.buildRequestOptions(options.abortSignal));
+      }, this.buildRequestOptions(options.abortSignal, needsFallbackBetas));
     } catch (error) {
       handleApiError(error);
     }
+    const pausedBlocks = [];
+    let continuations = 0;
+    while (isPauseTurn(response.stop_reason) && continuations < MAX_PAUSE_TURN_CONTINUATIONS) {
+      continuations++;
+      pausedBlocks.push(...response.content);
+      try {
+        response = await this.client.messages.create({
+          ...continuationParams(params, pausedBlocks),
+          stream: false
+        }, this.buildRequestOptions(options.abortSignal, needsFallbackBetas));
+      } catch (error) {
+        handleApiError(error);
+      }
+    }
+    if (isPauseTurn(response.stop_reason)) {
+      throw new Error(`Anthropic paused this turn (stop_reason "pause_turn") more than ` + `${MAX_PAUSE_TURN_CONTINUATIONS} times. Retry the request.`);
+    }
+    const responseContent = [...pausedBlocks, ...response.content];
+    const fallbacksSent = Array.isArray(params.fallbacks) && params.fallbacks.length > 0;
+    if (isRefusal(response.stop_reason)) {
+      throw refusalError(response.stop_details, fallbacksSent ? params.fallbacks[0].model : undefined);
+    }
+    const fallbackBlock = responseContent.find((b) => b.type === "fallback");
+    const sticky = !fallbackBlock && fallbacksSent && response.model && response.model !== this.apiModelId;
+    let pendingMeta;
+    if (fallbackBlock) {
+      pendingMeta = {
+        fallback: { from: fallbackBlock.from, to: fallbackBlock.to },
+        servedBy: {
+          from: fallbackBlock.from?.model ?? this.apiModelId,
+          to: fallbackBlock.to?.model ?? "unknown",
+          kind: "fallback"
+        }
+      };
+    } else if (sticky) {
+      pendingMeta = {
+        servedBy: { from: this.apiModelId, to: response.model, kind: "sticky" }
+      };
+    }
     const content = [];
-    for (const block of response.content) {
+    const takeMeta = () => {
+      const meta = pendingMeta;
+      pendingMeta = undefined;
+      return meta;
+    };
+    let seenFallbackBlock = false;
+    for (const block of responseContent) {
       switch (block.type) {
-        case "text":
-          content.push({ type: "text", text: block.text });
+        case "text": {
+          const meta = seenFallbackBlock || sticky ? takeMeta() : undefined;
+          content.push({
+            type: "text",
+            text: block.text,
+            ...meta ? { providerMetadata: { anthropic: meta } } : {}
+          });
           break;
-        case "tool_use":
+        }
+        case "tool_use": {
+          const meta = seenFallbackBlock || sticky ? takeMeta() : undefined;
           content.push({
             type: "tool-call",
             toolCallId: block.id,
             toolName: toOpencodeToolName(block.name),
-            input: JSON.stringify(block.input)
+            input: JSON.stringify(block.input),
+            ...meta ? { providerMetadata: { anthropic: meta } } : {}
           });
           break;
+        }
         default: {
           const anyBlock = block;
-          if (anyBlock.type === "thinking" && anyBlock.thinking) {
+          if (anyBlock.type === "fallback") {
+            seenFallbackBlock = true;
+          } else if (anyBlock.type === "thinking" && anyBlock.thinking) {
+            const extra = seenFallbackBlock || sticky ? takeMeta() : undefined;
+            const meta = {
+              ...anyBlock.signature ? { signature: anyBlock.signature } : {},
+              ...extra
+            };
             content.push({
               type: "reasoning",
               text: anyBlock.thinking,
-              providerMetadata: anyBlock.signature ? { anthropic: { signature: anyBlock.signature } } : undefined
+              providerMetadata: Object.keys(meta).length > 0 ? { anthropic: meta } : undefined
             });
           }
           break;
@@ -942,13 +1166,13 @@ class AnthropicSDKModel {
     };
   }
   async doStream(options) {
-    const { params, warnings } = this.buildParams(options);
+    const { params, warnings, needsFallbackBetas } = this.buildParams(options);
     let anthropicStream;
     try {
       anthropicStream = await this.client.messages.create({
         ...params,
         stream: true
-      }, this.buildRequestOptions(options.abortSignal));
+      }, this.buildRequestOptions(options.abortSignal, needsFallbackBetas));
     } catch (error) {
       if (error instanceof APIError && error.status === 400 && error.message?.includes("must end with a user message")) {
         return {
@@ -976,7 +1200,14 @@ class AnthropicSDKModel {
       }
       handleApiError(error);
     }
-    const stream = convertStream(anthropicStream, this.modelId);
+    const makeRequest = (p) => this.client.messages.create({ ...p, stream: true }, this.buildRequestOptions(options.abortSignal, needsFallbackBetas));
+    const continued = withPauseTurnContinuation(anthropicStream, params, makeRequest);
+    const fallbacksSent = Array.isArray(params.fallbacks) && params.fallbacks.length > 0;
+    const stream = convertStream(continued, this.modelId, {
+      apiModelId: this.apiModelId,
+      fallbacksEnabled: fallbacksSent,
+      fallbackModel: fallbacksSent ? params.fallbacks[0].model : undefined
+    });
     const wrappedStream = new ReadableStream({
       async start(controller) {
         controller.enqueue({
@@ -1099,13 +1330,14 @@ var API_TTL_MS = 5 * 60000;
 
 // src/index.ts
 var CLAUDE_CODE_SYSTEM_PROMPT = claudecode_system_default;
-var CLAUDE_CODE_OPUS48_SYSTEM_PROMPT = claudecode_system_opus48_default;
+var CLAUDE_CODE_NEW_SYSTEM_PROMPT = claudecode_system_new_default;
 function selectClaudePromptForModel(modelId) {
-  if (modelId.includes("opus-4-8"))
-    return claudecode_system_opus48_default;
+  if (modelId.includes("opus-4-8") || modelId.includes("fable-5")) {
+    return claudecode_system_new_default;
+  }
   return claudecode_system_default;
 }
-var CLAUDE_CODE_VERSION = "2.1.154";
+var CLAUDE_CODE_VERSION = "2.1.173";
 var OAUTH_BETAS = [
   "claude-code-20250219",
   "oauth-2025-04-20",
@@ -1122,7 +1354,8 @@ var PROVIDER_ID = "anthropic-sdk";
 var API_KEY_COSTS = {
   haiku: { input: 1, output: 5, cache_read: 0.1, cache_write: 1.25 },
   sonnet: { input: 3, output: 15, cache_read: 0.3, cache_write: 3.75 },
-  opus: { input: 5, output: 25, cache_read: 0.5, cache_write: 6.25 }
+  opus: { input: 5, output: 25, cache_read: 0.5, cache_write: 6.25 },
+  fable: { input: 10, output: 50, cache_read: 1, cache_write: 12.5 }
 };
 var ZERO_COST = { input: 0, output: 0, cache_read: 0, cache_write: 0 };
 function buildPluginModels(isOAuth) {
@@ -1236,6 +1469,21 @@ function buildPluginModels(isOAuth) {
       },
       options: { effort: "medium" },
       ...opus47Variants
+    },
+    "claude-fable-5": {
+      name: "Claude Fable 5",
+      reasoning: true,
+      tool_call: true,
+      attachment: true,
+      temperature: true,
+      limit: { context: 1e6, output: 128000 },
+      cost: cost("fable"),
+      modalities: {
+        input: ["text", "image", "pdf"],
+        output: ["text"]
+      },
+      options: { effort: "medium", refusalFallback: "claude-opus-4-8" },
+      ...opus47Variants
     }
   };
 }
@@ -1300,7 +1548,7 @@ function createAnthropicSDK(options = {}) {
         if (!betas.includes("effort-2025-11-24"))
           betas.push("effort-2025-11-24");
       }
-      if (model.includes("opus-4-8")) {
+      if (model.includes("opus-4-8") || model.includes("fable-5")) {
         if (!betas.includes("mid-conversation-system-2026-04-07")) {
           betas.push("mid-conversation-system-2026-04-07");
         }
@@ -1308,6 +1556,19 @@ function createAnthropicSDK(options = {}) {
       reqHeaders.set("anthropic-beta", betas.join(","));
       init = { ...init, headers: reqHeaders };
     }
+    {
+      const reqHeaders = new Headers(init?.headers);
+      if (reqHeaders.has(FALLBACK_BETAS_HEADER)) {
+        reqHeaders.delete(FALLBACK_BETAS_HEADER);
+        const betas = (reqHeaders.get("anthropic-beta") ?? "").split(",").map((beta) => beta.trim()).filter(Boolean);
+        for (const beta of ["server-side-fallback-2026-06-01", "fallback-credit-2026-06-01"]) {
+          if (!betas.includes(beta))
+            betas.push(beta);
+        }
+        reqHeaders.set("anthropic-beta", betas.join(","));
+        init = { ...init, headers: reqHeaders };
+      }
+    }
     const resp = await baseFetch(url, init);
     const h5 = resp.headers.get("anthropic-ratelimit-unified-5h-utilization");
     if (h5 != null) {
@@ -1356,10 +1617,22 @@ var anthropicSDKPlugin = async () => {
       if (!cfg.provider) {
         cfg.provider = {};
       }
+      const userProvider = cfg.provider[PROVIDER_ID] ?? {};
+      const defaultModels = buildPluginModels(isOAuth);
+      const models = { ...defaultModels };
+      for (const [modelID, userModel] of Object.entries(userProvider.models ?? {})) {
+        const base = defaultModels[modelID];
+        models[modelID] = base ? {
+          ...base,
+          ...userModel,
+          options: { ...base.options, ...userModel?.options },
+          variants: { ...base.variants, ...userModel?.variants }
+        } : userModel;
+      }
       cfg.provider[PROVIDER_ID] = {
         npm: PACKAGE_NAME,
-        models: buildPluginModels(isOAuth),
-        ...cfg.provider[PROVIDER_ID]
+        ...userProvider,
+        models
       };
     },
     "experimental.chat.system.transform": async (input, output) => {