@averyyy/pi-ai 1.0.0-piclient.2 → 1.0.2-piclient.1

package/README.md

@@ -896,7 +896,7 @@ Classifier models consume structured JSON state and answer one or more typed que
 | --- | --- | --- |
 | `typesafe` | `jev-latest` | `TYPESAFE_API_KEY` |
 | `openrouter` | `typesafe/jev-1.13`, `~typesafe/jev-latest` | `OPENROUTER_API_KEY` or OpenRouter OAuth |
-| `cloudflare-workers-ai` | `typesafe/jev` | `CLOUDFLARE_API_KEY` and `CLOUDFLARE_ACCOUNT_ID` |
+| `cloudflare-workers-ai` | `typesafe/jev`, `@cf/cloudflare/clef`, `@cf/cloudflare/clef-flash` | `CLOUDFLARE_API_KEY` and `CLOUDFLARE_ACCOUNT_ID` |
 | `vercel-ai-gateway` | `typesafe-ai/jev` | `AI_GATEWAY_API_KEY` |
 | `opencode` | `jev-1.13`, `jev-1.13-free` | `OPENCODE_API_KEY` |
 
@@ -1587,7 +1587,7 @@ getCurrentTools(messages);        // []
 
 A custom `Provider` or `ProviderStreams` implementation reads the prompt and tools the same way from `context.messages`; `context.systemPrompt` and `context.tools` do not exist at that layer.
 
-Models that accept system messages mid-conversation (`supportsMidConvoSystemMessages` in the model's compat settings, set by the generated catalog for verified models) receive each later system message in place, so the cached prefix stays intact; section changes are framed by name for the model. Every other model receives `collapseSystemMessages(transcript)`: the replayed prompt and current tools as the leading system message, with later system messages dropped. Anthropic models that also set `supportsMidConvoToolChanges` send tool changes as native `tool_addition`/`tool_removal` blocks: the initial tools stay active at the top level, every later declaration is sent with `defer_loading` (plus a stable deferred placeholder from the first request, which keeps Anthropic's deferred-tool scaffolding in the cached prefix), and removed tools stay declared, so tool changes do not invalidate the prompt cache. That needs at least one initial tool and no same-name redefinition; otherwise the current tool list is sent at the top level with the system text only. OpenAI Responses models with `supportsAdditionalTools` or `supportsToolSearch` anchor additive tool changes at their message; everything else sends the current tool list at the top level.
+Models that accept system messages mid-conversation (`supportsMidConvoSystemMessages` in the model's compat settings, set by the generated catalog for verified models) receive each later system message in place, so the cached prefix stays intact; section changes are framed by name for the model. Every other model receives `collapseSystemMessages(transcript)`: the replayed prompt and current tools as the leading system message, with later system messages dropped. Anthropic models that also set `supportsMidConvoToolChanges` send tool changes as native blocks (`inline-tools-2026-09-15` beta): the top-level tool list holds the initial tools plus a stable deferred placeholder and never changes, later tools are defined by value in `tool_addition` blocks (a new definition under an existing name replaces the old one), and removals are `tool_removal` references, so tool changes do not invalidate the prompt cache. That needs at least one initial tool; otherwise the current tool list is sent at the top level with the system text only. OpenAI Responses models with `supportsAdditionalTools` or `supportsToolSearch` anchor additive tool changes at their message; everything else sends the current tool list at the top level.
 
 ## Context Serialization
 

package/dist/api/anthropic-messages.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"anthropic-messages.d.ts","sourceRoot":"","sources":["../../src/api/anthropic-messages.ts"],"names":[],"mappings":"AAAA,OAAO,SAAiC,MAAM,mBAAmB,CAAC;AAoBlE,OAAO,KAAK,EASX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAqJrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AA2ChE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;;OAIG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;;;OAWG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;;OAWG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C;;;;;OAKG;IACH,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACtE;;;;OAIG;IACH,MAAM,CAAC,EAAE,SAAS,CAAC;CACnB;AAwRD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CA0UzE,CAAC;AA2BF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAgDlF,CAAC"}
+{"version":3,"file":"anthropic-messages.d.ts","sourceRoot":"","sources":["../../src/api/anthropic-messages.ts"],"names":[],"mappings":"AAAA,OAAO,SAAiC,MAAM,mBAAmB,CAAC;AAoBlE,OAAO,KAAK,EASX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAmJrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AA2ChE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;;OAIG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;;;OAWG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;;OAWG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C;;;;;OAKG;IACH,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACtE;;;;OAIG;IACH,MAAM,CAAC,EAAE,SAAS,CAAC;CACnB;AAwRD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CA0UzE,CAAC;AA2BF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAgDlF,CAAC"}

package/dist/api/anthropic-messages.js

@@ -10,7 +10,7 @@ import { getProviderEnvValue } from "../utils/provider-env.js";
 import { retryProviderRequest } from "../utils/provider-retry.js";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
 import { getSystemMessageText, renderSystemMessageUpdate } from "../utils/text.js";
-import { getCurrentTools, getDeclaredTools, getInitialSystemMessage, hasToolRedefinitions, resolveTranscript, } from "../utils/transcript.js";
+import { getCurrentTools, getInitialSystemMessage, resolveTranscript, } from "../utils/transcript.js";
 import { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling, } from "./constrained-sampling.js";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
 import { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext } from "./simple-options.js";
@@ -116,13 +116,13 @@ const INTERLEAVED_THINKING_BETA = "interleaved-thinking-2025-05-14";
 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 MID_CONVERSATION_TOOL_CHANGES_BETA = "mid-conversation-tool-changes-2026-07-01";
+const INLINE_TOOLS_BETA = "inline-tools-2026-09-15";
 /**
  * Stable deferred tool declared whenever native tool changes are in use. Anthropic adds
- * hidden prompt scaffolding as soon as any tool has `defer_loading`; declaring this
- * placeholder from the first request keeps that scaffolding in the cached prefix, so the
- * first real late tool does not invalidate the cache (measured: full miss without it).
- * It is never activated and the model cannot see it.
+ * hidden prompt scaffolding for mid-conversation tool changes; declaring this placeholder
+ * from the first request keeps that scaffolding in the cached prefix, so the first tool
+ * change does not invalidate the cache (measured: full miss without it). It is never
+ * activated and the model cannot see it.
  */
 const DEFERRED_TOOL_PLACEHOLDER = {
     name: "__pi_deferred_placeholder__",
@@ -852,7 +852,7 @@ function getBetaFeatures(model, context, isOAuthToken, nativeToolChanges, option
         features.push(MID_CONVERSATION_OUTPUT_CONFIG_BETA, THINKING_BINDING_CONTROLS_BETA);
     }
     if (nativeToolChanges)
-        features.push(MID_CONVERSATION_TOOL_CHANGES_BETA);
+        features.push(INLINE_TOOLS_BETA);
     return [...new Set(features)];
 }
 function buildParams(model, context, isOAuthToken, options) {
@@ -862,15 +862,15 @@ function buildParams(model, context, isOAuthToken, options) {
     const initialSystemText = initialSystemMessage ? getSystemMessageText(initialSystemMessage) : "";
     const transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);
     const conversationMessages = initialSystemMessage ? transformedMessages.slice(1) : transformedMessages;
-    // Native tool changes reference tools by name, so a redefined name cannot be expressed,
-    // and Anthropic rejects a tool list where every tool is deferred, so there must be an
-    // initial active tool to anchor the deferred ones. Otherwise the current tool list is sent.
+    // Native tool changes keep the request-level tool list fixed and define every later tool
+    // by value in a `tool_addition` block, which also expresses same-name redefinitions.
+    // Anthropic rejects a tool list where every tool is deferred, so there must be an initial
+    // active tool to anchor the placeholder. Otherwise the current tool list is sent.
     const initialTools = initialSystemMessage?.toolsAdded ?? [];
-    const nativeToolChanges = compat.supportsMidConvoSystemMessages &&
-        compat.supportsMidConvoToolChanges &&
-        initialTools.length > 0 &&
-        !hasToolRedefinitions(context.messages);
-    const converted = convertMessages(conversationMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, model.compat?.supportsMidConvoEffort === true ? model.provider : undefined, nativeToolChanges);
+    const nativeToolChanges = compat.supportsMidConvoSystemMessages && compat.supportsMidConvoToolChanges && initialTools.length > 0;
+    const converted = convertMessages(conversationMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, model.compat?.supportsMidConvoEffort === true ? model.provider : undefined, nativeToolChanges
+        ? (tools) => convertTools(tools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsStrictTools)
+        : undefined);
     const activeEffort = options?.effort ?? "high";
     const betaFeatures = getBetaFeatures(model, context, isOAuthToken, nativeToolChanges, options);
     const params = {
@@ -918,16 +918,13 @@ function buildParams(model, context, isOAuthToken, options) {
     }
     const toolCacheControl = compat.supportsCacheControlOnTools ? cacheControl : undefined;
     if (nativeToolChanges) {
-        // Initial tools stay active with the cache breakpoint on the last one. Every later
-        // declaration is deferred and only surfaced by its `tool_addition` block; removed
-        // tools stay declared and are withdrawn by `tool_removal`. The request-level list
-        // therefore only grows, keeping the cached prefix intact across tool changes.
-        const initialNames = new Set(initialTools.map((tool) => tool.name));
-        const laterTools = getDeclaredTools(context.messages).filter((tool) => !initialNames.has(tool.name));
+        // Initial tools stay active with the cache breakpoint on the last one, followed by the
+        // placeholder. The list never changes afterwards: later tools are defined by value in
+        // `tool_addition` blocks and withdrawn by `tool_removal`, so the cached prefix survives
+        // every tool change.
         params.tools = [
             ...convertTools(initialTools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsStrictTools, toolCacheControl),
             DEFERRED_TOOL_PLACEHOLDER,
-            ...convertTools(laterTools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsStrictTools).map((tool) => ({ ...tool, defer_loading: true })),
         ];
     }
     else {
@@ -1003,7 +1000,9 @@ function convertToolResult(msg) {
         is_error: msg.isError,
     };
 }
-function convertMessages(transformedMessages, isOAuthToken, cacheControl, allowEmptySignature = false, managedProvider, nativeToolChanges = false) {
+function convertMessages(transformedMessages, isOAuthToken, cacheControl, allowEmptySignature = false, managedProvider, 
+/** Converts tool definitions for native `tool_addition` blocks; undefined when tool changes are not native. */
+convertToolDefinitions) {
     const params = [];
     const assistantLevels = new Map();
     // Later system messages are held back and emitted directly before the next assistant
@@ -1025,18 +1024,20 @@ function convertMessages(transformedMessages, isOAuthToken, cacheControl, allowE
             const blocks = [];
             if (text.length > 0)
                 blocks.push({ type: "text", text: sanitizeSurrogates(text) });
-            if (nativeToolChanges) {
+            if (convertToolDefinitions) {
+                const added = msg.toolsAdded ?? [];
+                const redefined = new Set(added.map((tool) => tool.name));
                 for (const tool of msg.toolsRemoved ?? []) {
+                    // A new definition under the same name replaces the old one, so no removal is needed.
+                    if (redefined.has(tool.name))
+                        continue;
                     blocks.push({
                         type: "tool_removal",
                         tool: { type: "tool_reference", name: isOAuthToken ? toClaudeCodeName(tool.name) : tool.name },
                     });
                 }
-                for (const tool of msg.toolsAdded ?? []) {
-                    blocks.push({
-                        type: "tool_addition",
-                        tool: { type: "tool_reference", name: isOAuthToken ? toClaudeCodeName(tool.name) : tool.name },
-                    });
+                for (const definition of convertToolDefinitions(added)) {
+                    blocks.push({ type: "tool_addition", tool: { type: "tool_definition", definition } });
                 }
             }
             if (blocks.length > 0)