@earendil-works/pi-ai 1.4.0 → 1.5.1

package/dist/api/anthropic-messages.js

@@ -1,19 +1,25 @@
 import Anthropic, {} from "@anthropic-ai/sdk";
 import { ANTHROPIC_FEDERATION_RULE_ID_ENV, ANTHROPIC_IDENTITY_TOKEN_FILE_ENV, ANTHROPIC_ORGANIZATION_ID_ENV, ANTHROPIC_SERVICE_ACCOUNT_ID_ENV, ANTHROPIC_WORKSPACE_ID_ENV, } from "../env-api-keys.js";
 import { calculateCost } from "../models.js";
+import { registerSessionResourceCleanup } from "../session-resources.js";
 import { appendAssistantMessageDiagnostic } from "../utils/diagnostics.js";
+import { withCauseDetail } from "../utils/error-body.js";
 import { AssistantMessageEventStream } from "../utils/event-stream.js";
+import { shortHash } from "../utils/hash.js";
 import { headersToRecord } from "../utils/headers.js";
 import { getIdentityHeaders } from "../utils/identity.js";
-import { parseJsonWithRepair, parseStreamingJson, parseToolCallArguments } from "../utils/json-parse.js";
+import { parseJsonWithRepair } from "../utils/json-parse.js";
+import { applyOpenRouterReportedCost, isOpenRouterModel, } from "../utils/openrouter-cost.js";
 import { getProviderEnvValue } from "../utils/provider-env.js";
 import { retryProviderRequest } from "../utils/provider-retry.js";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
+import { ToolCallArgumentsStream } from "../utils/streaming-json.js";
 import { getSystemMessageText, renderSystemMessageUpdate } from "../utils/text.js";
 import { getCurrentTools, getInitialSystemMessage, resolveTranscript, } from "../utils/transcript.js";
-import { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling, } from "./constrained-sampling.js";
+import { getJsonSchemaToolParameters, prefersJsonSchemaStrictSampling, resolveJsonSchemaStrictSampling, } from "./constrained-sampling.js";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
 import { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext } from "./simple-options.js";
+import { hasExceededStrictToolLimits, isStrictToolLimitErrorMessage, markStrictToolLimitsExceeded, } from "./strict-tool-limits.js";
 import { splitErrorToolResultImages, transformMessages } from "./transform-messages.js";
 /**
  * Resolve cache retention preference.
@@ -120,6 +126,7 @@ const SERVER_SIDE_FALLBACK_BETA = "server-side-fallback-2026-07-01";
 const MID_CONVERSATION_OUTPUT_CONFIG_BETA = "mid-conversation-output-config-2026-07-01";
 const THINKING_BINDING_CONTROLS_BETA = "thinking-binding-controls-2026-08-01";
 const INLINE_TOOLS_BETA = "inline-tools-2026-09-15";
+const MESSAGE_THREADS_BETA = "message-threads-2026-08-12";
 /**
  * Stable deferred tool declared whenever native tool changes are in use. Anthropic adds
  * hidden prompt scaffolding for mid-conversation tool changes; declaring this placeholder
@@ -149,8 +156,178 @@ function getAnthropicCompat(model) {
         supportsStrictTools: model.compat?.supportsStrictTools ?? false,
         supportsMidConvoSystemMessages: model.compat?.supportsMidConvoSystemMessages ?? false,
         supportsMidConvoToolChanges: model.compat?.supportsMidConvoToolChanges ?? false,
+        // Gateways that drop unknown request fields would silently turn a `continue` into a request
+        // without the earlier conversation, so the default is limited to Anthropic's own endpoint.
+        // Widen or remove this restriction once proxies generally forward the `thread` field.
+        supportsMessageThreads: model.compat?.supportsMessageThreads ??
+            (model.provider === "anthropic" && model.baseUrl.includes("api.anthropic.com")),
     };
 }
+/** Per session: where the next request can continue, or "off" after the endpoint rejected threads. */
+const threadState = new Map();
+const MAX_THREAD_STATE_ENTRIES = 10_000;
+/** Rejections of a `continue` that a new thread fixes: expired, raced, or a fixed setting changed. */
+const NEW_THREAD_ERRORS = new Set([
+    "thread_not_found",
+    "thread_already_continued",
+    "thread_continue_in_flight",
+    "thread_fingerprint_mismatch",
+]);
+/**
+ * Sets a session's thread state, keeping at most `MAX_THREAD_STATE_ENTRIES` sessions.
+ *
+ * State is normally freed by `cleanupSessionResources(sessionId)` when a session ends, as pi's
+ * coding agent does. The cap bounds memory for library users that never call it, for example a
+ * server passing a new `sessionId` per conversation. Dropping the least recently updated session
+ * is cheap: its thread has most likely expired on the server already (after a few minutes idle),
+ * and otherwise its next request just starts a new thread.
+ */
+function setThreadState(sessionId, value) {
+    // Re-insert so Map order stays oldest-first for the cap.
+    threadState.delete(sessionId);
+    threadState.set(sessionId, value);
+    if (threadState.size > MAX_THREAD_STATE_ENTRIES) {
+        const oldest = threadState.keys().next().value;
+        if (oldest !== undefined)
+            threadState.delete(oldest);
+    }
+}
+registerSessionResourceCleanup((sessionId) => {
+    if (sessionId)
+        threadState.delete(sessionId);
+    else
+        threadState.clear();
+});
+/**
+ * Hash of everything a `continue` builds on: the settings that must stay the same within a thread
+ * and the messages the server already holds.
+ *
+ * - Settings, as sent: the endpoint (a thread exists on one endpoint only), and the fixed request
+ *   fields. A `continue` omits `system` and `tools` and the server keeps the thread's own, so only
+ *   this check can notice a change to them, including their cache markers. The server rejects
+ *   changes to the other fields with `thread_fingerprint_mismatch`; checking them here saves that
+ *   rejected request. A fixed field missing here costs only that rejection, which also starts a
+ *   new thread.
+ * - Messages, normalized so messages that mean the same to the API hash the same.
+ */
+function hashThreadPrefix(model, params, messages) {
+    const { system, tools, thinking, output_config, tool_choice, betas, fallbacks } = params;
+    const settings = JSON.stringify([
+        model.provider,
+        model.baseUrl,
+        params.model,
+        system,
+        tools,
+        thinking,
+        output_config,
+        tool_choice,
+        betas,
+        fallbacks,
+    ]);
+    const conversation = JSON.stringify(messages, (key, value) => {
+        // Cache markers don't change what a message means, but they move: pi puts one on the newest
+        // message, so the message that had it in the last request has none in this one. Extensions
+        // may add markers anywhere too.
+        if (key === "cache_control")
+            return undefined;
+        // To attach that marker, the newest user message's string content is sent as one text block;
+        // the next request sends the same message as a string: "hi" vs [{ type: "text", text: "hi" }].
+        if (key === "content" && typeof value === "string")
+            return [{ type: "text", text: value }];
+        return value;
+    });
+    return shortHash(settings + conversation);
+}
+function createThreadRequest(sessionId, params) {
+    return { sessionId, body: { ...params, thread: { type: "create" } } };
+}
+function prepareThreadRequest(model, sessionId, params) {
+    const state = threadState.get(sessionId);
+    if (state === "off")
+        return undefined;
+    if (state !== undefined &&
+        params.messages.length > state.prefixCount &&
+        hashThreadPrefix(model, params, params.messages.slice(0, state.prefixCount)) === state.prefixHash) {
+        // Each reply can be continued once; deleting also keeps a concurrent request from trying.
+        threadState.delete(sessionId);
+        const { system: _system, tools: _tools, ...rest } = params;
+        return {
+            body: {
+                ...rest,
+                messages: params.messages.slice(state.prefixCount),
+                thread: { type: "continue", previous_message_id: state.replyId },
+            },
+            sessionId,
+        };
+    }
+    return createThreadRequest(sessionId, params);
+}
+/** The `error_code` Anthropic puts in `error.details` of thread rejections. */
+function getThreadErrorCode(error) {
+    const body = error.error;
+    const code = body?.error?.details?.error_code;
+    return typeof code === "string" ? code : undefined;
+}
+/**
+ * Sends a thread request. A rejection about the thread (never a started stream) is resent once in
+ * full: as a new thread when the old one can't be continued, or without `thread` when the endpoint
+ * can't use threads, which also turns threads off for the session. Other errors are passed on.
+ * Returns the response and the thread request that produced it, if any.
+ */
+async function sendThreadRequest(thread, params, send, output, signal) {
+    try {
+        return { response: await send(thread.body), thread };
+    }
+    catch (error) {
+        if (signal?.aborted || !(error instanceof Anthropic.APIError))
+            throw error;
+        const errorCode = getThreadErrorCode(error);
+        const startNewThread = errorCode !== undefined && NEW_THREAD_ERRORS.has(errorCode);
+        // The endpoint can't use threads: it can't thread this request, or it doesn't know the
+        // `thread` field and rejects it without a code ("thread: Extra inputs are not permitted"),
+        // e.g. with an `anthropic-beta` header that lacks the threads beta.
+        const threadsUnsupported = errorCode === "thread_unsupported_request" ||
+            (errorCode === undefined && error.status === 400 && error.message.includes("thread"));
+        // Any other error (prompt too long, unknown model, strict tool limits, ...) is not about the
+        // thread, and resending would only fail again.
+        if (!startNewThread && !threadsUnsupported)
+            throw error;
+        // Recorded before the resend, so a failed resend keeps it.
+        appendAssistantMessageDiagnostic(output, {
+            type: "anthropic_thread_fallback",
+            timestamp: Date.now(),
+            error: { message: error.message },
+            details: { reason: errorCode ?? String(error.status) },
+        });
+        if (startNewThread) {
+            const created = createThreadRequest(thread.sessionId, params);
+            return { response: await send(created.body), thread: created };
+        }
+        // With the threads beta, a request without `thread` is a normal request.
+        const response = await send(params);
+        setThreadState(thread.sessionId, "off");
+        return { response, thread: undefined };
+    }
+}
+/**
+ * Records where the session's next request can continue: after `output`, the clean reply to the
+ * thread request `thread`, whose full request was `params`.
+ */
+function recordThreadReply(model, thread, params, output, isOAuth, allowEmptySignature) {
+    // `responseModel` is set only when a fallback model answered; the server does not store those
+    // replies, so they cannot be continued.
+    if (output.responseId === undefined || output.responseModel !== undefined)
+        return;
+    // Convert the reply like the next request will, keeping only the assistant message
+    // (transformMessages adds placeholder results for trailing tool calls).
+    const reply = convertMessages(transformMessages([output], model, normalizeToolCallId), isOAuth, undefined, allowEmptySignature).messages.filter((message) => message.role === "assistant");
+    const prefix = [...params.messages, ...reply];
+    setThreadState(thread.sessionId, {
+        prefixCount: prefix.length,
+        prefixHash: hashThreadPrefix(model, params, prefix),
+        replyId: output.responseId,
+    });
+}
 function mergeHeaders(...headerSources) {
     const merged = {};
     for (const headers of headerSources) {
@@ -375,7 +552,8 @@ async function* iterateAnthropicEvents(response, signal) {
 }
 export const stream = (model, context, options) => {
     const stream = new AssistantMessageEventStream();
-    const normalizedContext = resolveTranscript(context, getAnthropicCompat(model).supportsMidConvoSystemMessages);
+    const compat = getAnthropicCompat(model);
+    const normalizedContext = resolveTranscript(context, compat.supportsMidConvoSystemMessages);
     const currentTools = getCurrentTools(normalizedContext.messages);
     (async () => {
         const output = {
@@ -400,6 +578,12 @@ export const stream = (model, context, options) => {
             let isOAuth;
             let usageModel = model;
             let inputTransformations;
+            const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
+            const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
+            // Session whose requests may use threads; undefined when threads don't apply. Sessions where
+            // the endpoint rejected threads ("off") still send the threads beta, which the resend that
+            // turned them off was accepted with; `prepareThreadRequest()` just sends no `thread`.
+            const threadSessionId = compat.supportsMessageThreads ? cacheSessionId : undefined;
             if (options?.client) {
                 client = options.client;
                 isOAuth = false;
@@ -417,8 +601,6 @@ export const stream = (model, context, options) => {
                         hasImages,
                     });
                 }
-                const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
-                const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
                 const created = createClient(model, apiKey, options?.headers, options?.fetch, copilotDynamicHeaders, cacheSessionId, federation, options?.identity);
                 client = created.client;
                 isOAuth = created.isOAuthToken;
@@ -428,24 +610,38 @@ export const stream = (model, context, options) => {
                 ...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),
                 maxRetries: 0,
             };
-            let disablePreferredStrictTools = false;
+            const send = (body) => retryProviderRequest(() => client.beta.messages.create(body, requestOptions).asResponse(), {
+                maxRetries: options?.maxRetries,
+                maxRetryDelayMs: options?.maxRetryDelayMs,
+                signal: options?.signal,
+            });
+            let disablePreferredStrictTools = hasExceededStrictToolLimits(options?.sessionId);
             let response;
+            let params;
+            // The thread request that produced the response; undefined when no `thread` was sent.
+            let thread;
             for (;;) {
                 options?.signal?.throwIfAborted();
-                const built = buildParams(model, normalizedContext, isOAuth, options, disablePreferredStrictTools);
+                const built = buildParams(model, normalizedContext, isOAuth, options, {
+                    disablePreferredStrictTools,
+                    messageThreads: threadSessionId !== undefined,
+                });
                 if (built.providerThinkingLevel)
                     output.providerThinkingLevel = built.providerThinkingLevel;
-                let params = built.params;
+                params = built.params;
                 const nextParams = await options?.onPayload?.(params, model);
                 if (nextParams !== undefined) {
                     params = { ...nextParams, stream: true };
                 }
+                const prepared = threadSessionId !== undefined && options?.disableContinuation !== true
+                    ? prepareThreadRequest(model, threadSessionId, params)
+                    : undefined;
                 try {
-                    response = await retryProviderRequest(() => client.beta.messages.create(params, requestOptions).asResponse(), {
-                        maxRetries: options?.maxRetries,
-                        maxRetryDelayMs: options?.maxRetryDelayMs,
-                        signal: options?.signal,
-                    });
+                    const sent = prepared
+                        ? await sendThreadRequest(prepared, params, send, output, options?.signal)
+                        : { response: await send(params), thread: undefined };
+                    response = sent.response;
+                    thread = sent.thread;
                     break;
                 }
                 catch (error) {
@@ -456,14 +652,11 @@ export const stream = (model, context, options) => {
                         !(error instanceof Anthropic.APIError) ||
                         error.status !== 400 ||
                         error.type !== "invalid_request_error" ||
-                        ![
-                            "The compiled grammar is too large",
-                            "Too many strict tools (",
-                            "Schemas contains too many parameters with union types (",
-                        ].some((message) => error.message.includes(message))) {
+                        !isStrictToolLimitErrorMessage(error.message)) {
                         throw error;
                     }
                     disablePreferredStrictTools = true;
+                    markStrictToolLimitsExceeded(options?.sessionId);
                     appendAssistantMessageDiagnostic(output, {
                         type: "anthropic_strict_tools_fallback",
                         timestamp: Date.now(),
@@ -474,7 +667,12 @@ export const stream = (model, context, options) => {
             }
             await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
             stream.push({ type: "start", partial: output });
-            const blocks = output.content;
+            // Stream state per Anthropic block index, kept off the content blocks so it never reaches partials.
+            const openBlocks = new Map();
+            const openBlock = (anthropicIndex) => {
+                const open = openBlocks.get(anthropicIndex);
+                return open === undefined ? undefined : { ...open, block: output.content[open.contentIndex] };
+            };
             for await (const event of iterateAnthropicEvents(response, options?.signal)) {
                 await options?.onProviderStreamEvent?.(event, model);
                 if (event.type === "message_start") {
@@ -509,105 +707,92 @@ export const stream = (model, context, options) => {
                         continue;
                     }
                     if (event.content_block.type === "text") {
-                        const block = {
-                            type: "text",
-                            text: event.content_block.text ?? "",
-                            index: event.index,
-                        };
-                        output.content.push(block);
+                        output.content.push({ type: "text", text: event.content_block.text ?? "" });
+                        openBlocks.set(event.index, { contentIndex: output.content.length - 1 });
                         stream.push({ type: "text_start", contentIndex: output.content.length - 1, partial: output });
                     }
                     else if (event.content_block.type === "thinking") {
-                        const block = {
+                        output.content.push({
                             type: "thinking",
                             thinking: event.content_block.thinking ?? "",
                             thinkingSignature: event.content_block.signature ?? "",
-                            index: event.index,
-                        };
-                        output.content.push(block);
+                        });
+                        openBlocks.set(event.index, { contentIndex: output.content.length - 1 });
                         stream.push({ type: "thinking_start", contentIndex: output.content.length - 1, partial: output });
                     }
                     else if (event.content_block.type === "redacted_thinking") {
-                        const block = {
+                        output.content.push({
                             type: "thinking",
                             thinking: "[Reasoning redacted]",
                             thinkingSignature: event.content_block.data,
                             redacted: true,
-                            index: event.index,
-                        };
-                        output.content.push(block);
+                        });
+                        openBlocks.set(event.index, { contentIndex: output.content.length - 1 });
                         stream.push({ type: "thinking_start", contentIndex: output.content.length - 1, partial: output });
                     }
                     else if (event.content_block.type === "tool_use") {
-                        const block = {
+                        output.content.push({
                             type: "toolCall",
                             id: event.content_block.id,
                             name: isOAuth
                                 ? fromClaudeCodeName(event.content_block.name, currentTools)
                                 : event.content_block.name,
                             arguments: event.content_block.input ?? {},
-                            partialJson: "",
-                            index: event.index,
-                        };
-                        output.content.push(block);
+                        });
+                        openBlocks.set(event.index, {
+                            contentIndex: output.content.length - 1,
+                            arguments: new ToolCallArgumentsStream(),
+                        });
                         stream.push({ type: "toolcall_start", contentIndex: output.content.length - 1, partial: output });
                     }
                 }
                 else if (event.type === "content_block_delta") {
+                    const open = openBlock(event.index);
                     if (event.delta.type === "text_delta") {
-                        const index = blocks.findIndex((b) => b.index === event.index);
-                        const block = blocks[index];
-                        if (block && block.type === "text") {
-                            block.text += event.delta.text;
+                        if (open?.block.type === "text") {
+                            open.block.text += event.delta.text;
                             stream.push({
                                 type: "text_delta",
-                                contentIndex: index,
+                                contentIndex: open.contentIndex,
                                 delta: event.delta.text,
                                 partial: output,
                             });
                         }
                     }
                     else if (event.delta.type === "thinking_delta") {
-                        const index = blocks.findIndex((b) => b.index === event.index);
-                        const block = blocks[index];
-                        if (block && block.type === "thinking") {
-                            block.thinking += event.delta.thinking;
+                        if (open?.block.type === "thinking") {
+                            open.block.thinking += event.delta.thinking;
                             stream.push({
                                 type: "thinking_delta",
-                                contentIndex: index,
+                                contentIndex: open.contentIndex,
                                 delta: event.delta.thinking,
                                 partial: output,
                             });
                         }
                     }
                     else if (event.delta.type === "input_json_delta") {
-                        const index = blocks.findIndex((b) => b.index === event.index);
-                        const block = blocks[index];
-                        if (block && block.type === "toolCall") {
-                            block.partialJson += event.delta.partial_json;
-                            block.arguments = parseStreamingJson(block.partialJson);
+                        if (open?.block.type === "toolCall" && open.arguments !== undefined) {
+                            open.block.arguments = open.arguments.append(event.delta.partial_json);
                             stream.push({
                                 type: "toolcall_delta",
-                                contentIndex: index,
+                                contentIndex: open.contentIndex,
                                 delta: event.delta.partial_json,
                                 partial: output,
                             });
                         }
                     }
                     else if (event.delta.type === "signature_delta") {
-                        const index = blocks.findIndex((b) => b.index === event.index);
-                        const block = blocks[index];
-                        if (block && block.type === "thinking") {
-                            block.thinkingSignature = block.thinkingSignature || "";
-                            block.thinkingSignature += event.delta.signature;
+                        if (open?.block.type === "thinking") {
+                            open.block.thinkingSignature = open.block.thinkingSignature || "";
+                            open.block.thinkingSignature += event.delta.signature;
                         }
                     }
                 }
                 else if (event.type === "content_block_stop") {
-                    const index = blocks.findIndex((b) => b.index === event.index);
-                    const block = blocks[index];
-                    if (block) {
-                        delete block.index;
+                    const open = openBlock(event.index);
+                    openBlocks.delete(event.index);
+                    if (open) {
+                        const { block, contentIndex: index } = open;
                         if (block.type === "text") {
                             stream.push({
                                 type: "text_end",
@@ -624,11 +809,8 @@ export const stream = (model, context, options) => {
                                 partial: output,
                             });
                         }
-                        else if (block.type === "toolCall") {
-                            Object.assign(block, parseToolCallArguments(block.partialJson));
-                            // Finalize in-place and strip the scratch buffer so replay only
-                            // carries parsed arguments.
-                            delete block.partialJson;
+                        else if (block.type === "toolCall" && open.arguments !== undefined) {
+                            Object.assign(block, open.arguments.finish());
                             stream.push({
                                 type: "toolcall_end",
                                 contentIndex: index,
@@ -680,6 +862,11 @@ export const stream = (model, context, options) => {
                     output.usage.totalTokens =
                         output.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;
                     calculateCost(usageModel, output.usage);
+                    if (isOpenRouterModel(model) && event.usage) {
+                        // OpenRouter adds billing fields to streamed message_delta usage at runtime,
+                        // although its OpenAPI schema and the Anthropic SDK do not type those fields.
+                        applyOpenRouterReportedCost(output.usage, event.usage);
+                    }
                 }
             }
             if (options?.signal?.aborted) {
@@ -691,6 +878,8 @@ export const stream = (model, context, options) => {
             if (output.stopReason === "aborted" || output.stopReason === "error") {
                 throw new Error(output.errorMessage || "An unknown error occurred");
             }
+            if (thread)
+                recordThreadReply(model, thread, params, output, isOAuth, compat.allowEmptySignature);
             if (inputTransformations && inputTransformations.length > 0) {
                 appendAssistantMessageDiagnostic(output, {
                     type: "anthropic_input_transformations",
@@ -708,13 +897,8 @@ export const stream = (model, context, options) => {
             stream.end();
         }
         catch (error) {
-            for (const block of output.content) {
-                delete block.index;
-                // partialJson is only a streaming scratch buffer; never persist it.
-                delete block.partialJson;
-            }
             output.stopReason = options?.signal?.aborted ? "aborted" : "error";
-            output.errorMessage = error instanceof Error ? error.message : JSON.stringify(error);
+            output.errorMessage = error instanceof Error ? withCauseDetail(error) : JSON.stringify(error);
             stream.push({ type: "error", reason: output.stopReason, error: output });
             stream.end();
         }
@@ -849,7 +1033,7 @@ function createClient(model, apiKey, optionsHeaders, fetch, dynamicHeaders, sess
     });
     return { client, isOAuthToken: false };
 }
-function getBetaFeatures(model, context, isOAuthToken, nativeToolChanges, options) {
+function getBetaFeatures(model, context, options, { isOAuthToken, nativeToolChanges, messageThreads }) {
     let configuredFeatures;
     for (const headers of [model.headers, options?.headers]) {
         for (const [name, value] of Object.entries(headers ?? {})) {
@@ -885,9 +1069,11 @@ function getBetaFeatures(model, context, isOAuthToken, nativeToolChanges, option
     }
     if (nativeToolChanges)
         features.push(INLINE_TOOLS_BETA);
+    if (messageThreads)
+        features.push(MESSAGE_THREADS_BETA);
     return [...new Set(features)];
 }
-function buildParams(model, context, isOAuthToken, options, disablePreferredStrictTools = false) {
+function buildParams(model, context, isOAuthToken, options, flags) {
     const { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);
     const compat = getAnthropicCompat(model);
     const initialSystemMessage = getInitialSystemMessage(context.messages);
@@ -900,11 +1086,8 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
     // active tool to anchor the placeholder. Otherwise the current tool list is sent.
     let hasPreferredStrictTools = false;
     const convertToolDefinitions = (tools, toolCacheControl) => {
-        const definitions = convertTools(tools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsStrictTools, toolCacheControl, disablePreferredStrictTools);
-        if (definitions.some((definition, index) => {
-            const config = tools[index].constrainedSampling;
-            return definition.strict === true && config && config.type === "json_schema" && config.strict === "prefer";
-        })) {
+        const definitions = convertTools(tools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsStrictTools, toolCacheControl, flags.disablePreferredStrictTools);
+        if (definitions.some((definition, index) => definition.strict === true && prefersJsonSchemaStrictSampling(tools[index]))) {
             hasPreferredStrictTools = true;
         }
         return definitions;
@@ -916,7 +1099,11 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
     const effortMessages = model.compat?.supportsMidConvoEffort === true && !thinkingDisabled;
     const converted = convertMessages(conversationMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, effortMessages ? model.provider : undefined, nativeToolChanges ? convertToolDefinitions : undefined);
     const activeEffort = options?.effort ?? "high";
-    const betaFeatures = getBetaFeatures(model, context, isOAuthToken, nativeToolChanges, options);
+    const betaFeatures = getBetaFeatures(model, context, options, {
+        isOAuthToken,
+        nativeToolChanges,
+        messageThreads: flags.messageThreads,
+    });
     const params = {
         model: model.id,
         messages: effortMessages ? insertThinkingLevelMessages(converted, activeEffort) : converted.messages,
@@ -985,7 +1172,10 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
             display: options?.thinkingDisplay ?? "summarized",
             block_binding: { prefix_mismatch_behavior: "drop_block" },
         };
-        params.output_config = { effort: "high" };
+        // Effort markers set the level for every reply. The top-level effort is part of the cached
+        // prompt, so it stays fixed. It is "low" because organizations can cap effort and reject
+        // requests containing any level above the cap.
+        params.output_config = { effort: "low" };
     }
     else if (model.reasoning && options?.thinkingEnabled) {
         // Default to "summarized" so Opus 4.7 and Mythos Preview behave like
@@ -1045,7 +1235,9 @@ convertToolDefinitions) {
     const params = [];
     const assistantLevels = new Map();
     // Later system messages are held back and emitted directly before the next assistant
-    // message (or at the end of the transcript). Anthropic requires `tool_result` blocks to
+    // message that is sent (or at the end of the transcript). Assistant messages that convert to
+    // no blocks are dropped, so holding past them keeps an update from landing before a user
+    // message (#11091). Anthropic requires `tool_result` blocks to
     // immediately follow their `tool_use`, so a system message between them is rejected; this
     // also mirrors where the managed-effort system messages are inserted. As a result an
     // update placed before a user message in the transcript lands after it on the wire.
@@ -1118,7 +1310,6 @@ convertToolDefinitions) {
             }
         }
         else if (msg.role === "assistant") {
-            flushPendingSystemMessages();
             const blocks = [];
             for (const block of msg.content) {
                 if (block.type === "text") {
@@ -1176,6 +1367,7 @@ convertToolDefinitions) {
             }
             if (blocks.length === 0)
                 continue;
+            flushPendingSystemMessages();
             const messageIndex = params.length;
             params.push({
                 role: "assistant",
@@ -1299,16 +1491,19 @@ function convertTools(tools, isOAuthToken, supportsEagerToolInputStreaming, supp
     if (!tools)
         return [];
     return tools.map((tool, index) => {
-        const config = tool.constrainedSampling;
-        const strict = disablePreferredStrictTools && config && config.type === "json_schema" && config.strict === "prefer"
+        const strict = disablePreferredStrictTools && prefersJsonSchemaStrictSampling(tool)
             ? undefined
             : resolveJsonSchemaStrictSampling(tool, supportsStrictTools, isAnthropicStrictUnsupportedKeyword);
         const parameters = getJsonSchemaToolParameters(tool, strict);
         const schema = parameters;
+        // Keep shared definitions so property $refs still resolve. Other root keywords stay out:
+        // Anthropic rejects root anyOf/oneOf/allOf with a 400.
         const legacyInputSchema = {
             type: "object",
             properties: schema.properties ?? {},
             required: schema.required ?? [],
+            ...(schema.$defs === undefined ? {} : { $defs: schema.$defs }),
+            ...(schema.definitions === undefined ? {} : { definitions: schema.definitions }),
         };
         const inputSchema = strict === true
             ? {