@bastani/pi-ai 0.9.38-alpha.6 → 0.9.38-alpha.8

package/CHANGELOG.md

@@ -4,6 +4,20 @@ This package is a Bastani fork of `@earendil-works/pi-ai`. Upstream history at t
 
 ## [Unreleased]
 
+## [0.9.38-alpha.7] - 2026-10-17
+
+### Fixed
+
+- Fixed `closeOpenAICodexWebSocketSessions("")` closing other sessions' cached sockets. Empty keys now do nothing; omitting the key still closes all cached sockets.
+- Fixed the root `AssistantMessageEventStream` export being visible only as a type to TypeScript consumers. It can now be imported and constructed as a value, matching the runtime API.
+- Fixed automatic retry not triggering for `The service is temporarily unavailable` errors, which also made compaction fail on the first attempt ([#10965](https://github.com/earendil-works/pi/issues/10965)).
+- Fixed Claude Haiku 5.5 and Claude Opus 5 not offering the `off` thinking level on Anthropic. `off` now sends `thinking: {type: "disabled"}` without effort settings ([#10753](https://github.com/earendil-works/pi/issues/10753)).
+- Fixed images in error tool results being replaced with a note on Anthropic, and Claude on Amazon Bedrock rejecting error tool results that contain images. The images are now sent after the tool results of the turn, so the model still sees them ([#10794](https://github.com/earendil-works/pi/issues/10794)).
+- Fixed model switching exposing another model's thinking as visible reply text. Foreign thinking blocks are now dropped; Anthropic models that adjudicate thinking-block model binding still receive compatible blocks from the same provider ([#10995](https://github.com/earendil-works/pi/issues/10995)).
+- Fixed automatic retry not triggering for node-fetch request failures during Google Vertex authentication token refresh ([#10996](https://github.com/earendil-works/pi/issues/10996)).
+- Fixed whitespace-only tool output (for example a bare `\r\n` from bash) causing OpenAI Completions, OpenAI Responses, and Google providers to reject requests. It now uses the same placeholder as empty output ([#8720](https://github.com/earendil-works/pi/issues/8720)).
+- Fixed automatic retry not triggering for gateway upstream failures such as `upstream_error: Upstream request failed`, `upstream_stream_read_error`, and `Upstream HTTP/2 stream failed` ([#10920](https://github.com/earendil-works/pi/issues/10920)).
+
 ## [0.9.38-alpha.6] - 2026-10-16
 
 ### Fixed

package/README.md

@@ -1531,13 +1531,13 @@ Notes:
 
 ## Cross-Provider Handoffs
 
-The library supports seamless handoffs between different LLM providers within the same conversation. This allows you to switch models mid-conversation while preserving context, including thinking blocks, tool calls, and tool results.
+The library supports seamless handoffs between different LLM providers within the same conversation. This allows you to switch models mid-conversation while preserving context, including text, tool calls, and tool results.
 
 When messages from one provider are sent to a different provider, the library automatically transforms them for compatibility:
 
 - **User and tool result messages** are passed through unchanged
-- **Assistant messages from the same provider/API** are preserved as-is
-- **Assistant messages from different providers** have their thinking blocks converted to text with `<thinking>` tags
+- **Assistant messages from the same provider, API, and model** are preserved as-is, including thinking blocks
+- **Assistant messages from a different model** have their thinking blocks dropped. Signatures and encrypted reasoning only work with the model that produced them, and readable thinking sent as plain text makes the new model treat it as part of the reply. Anthropic models whose API decides which thinking blocks a model may read receive signed blocks from other models on the same provider unchanged
 - **Tool calls and regular text** are preserved unchanged
 
 ```typescript
@@ -1558,7 +1558,7 @@ const claude = models.getModel('anthropic', 'claude-sonnet-4-5')!;
 context.messages.push({ role: 'user', content: 'What is 25 * 18?', timestamp: Date.now() });
 context.messages.push(await models.completeSimple(claude, context, { reasoning: 'medium' }));
 
-// Switch to GPT-5 - it will see Claude's thinking as <thinking> tagged text
+// Switch to GPT-5 - it sees Claude's answer, but not Claude's thinking
 const gpt5 = models.getModel('openai', 'gpt-5-mini')!;
 context.messages.push({ role: 'user', content: 'Is that calculation correct?', timestamp: Date.now() });
 context.messages.push(await models.complete(gpt5, context));
@@ -1569,7 +1569,7 @@ context.messages.push({ role: 'user', content: 'What was the original question?'
 const geminiResponse = await models.complete(gemini, context);
 ```
 
-All providers can handle messages from other providers — text, tool calls and results (including images), thinking blocks (transformed to tagged text), and aborted messages with partial content. This enables flexible workflows: start with a fast model, switch to a more capable one for complex reasoning, or maintain continuity across provider outages.
+All providers can handle messages from other providers — text, tool calls and results (including images), thinking blocks (dropped when the model changes), and aborted messages with partial content. This enables flexible workflows: start with a fast model, switch to a more capable one for complex reasoning, or maintain continuity across provider outages.
 
 ## System Messages
 

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;AAiBlE,OAAO,KAAK,EASX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAOb,MAAM,aAAa,CAAC;AAoKrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAmPhE,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;AAgSD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CAyZzE,CAAC;AA4BF,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;AAiBlE,OAAO,KAAK,EASX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAOb,MAAM,aAAa,CAAC;AAwKrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAmPhE,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;AAgSD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CAwZzE,CAAC;AA4BF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAgDlF,CAAC"}

package/dist/api/anthropic-messages.js

@@ -16,7 +16,7 @@ import { getCurrentTools, getInitialSystemMessage, resolveTranscript, } from "..
 import { ANTHROPIC_STRICT_JSON_SCHEMA_PROFILE, getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling, } from "./constrained-sampling.js";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput, preserveCopilotIntegrationHeader, } from "./github-copilot-headers.js";
 import { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext } from "./simple-options.js";
-import { transformMessages } from "./transform-messages.js";
+import { splitErrorToolResultImages, transformMessages } from "./transform-messages.js";
 /**
  * Resolve cache retention preference.
  * Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
@@ -85,6 +85,16 @@ const fromClaudeCodeName = (name, tools) => {
     }
     return name;
 };
+function convertImageBlock(image) {
+    return {
+        type: "image",
+        source: {
+            type: "base64",
+            media_type: image.mimeType,
+            data: image.data,
+        },
+    };
+}
 /**
  * Convert tool-result content blocks to Anthropic API format.
  *
@@ -105,14 +115,7 @@ function convertContentBlocks(content) {
                 text: sanitizeSurrogates(block.text),
             };
         }
-        return {
-            type: "image",
-            source: {
-                type: "base64",
-                media_type: block.mimeType,
-                data: block.data,
-            },
-        };
+        return convertImageBlock(block);
     });
     // If only images (no text), add placeholder text block
     const hasText = blocks.some((b) => b.type === "text");
@@ -557,14 +560,12 @@ export const stream = (model, context, options) => {
     const normalizedContext = resolveTranscript(context, getAnthropicCompat(model).supportsMidConvoSystemMessages);
     const currentTools = getCurrentTools(normalizedContext.messages);
     (async () => {
-        const providerThinkingLevel = supportsMidConvoEffort(model) ? (options?.effort ?? "high") : undefined;
         const output = {
             role: "assistant",
             content: [],
             api: model.api,
             provider: model.provider,
             model: model.id,
-            ...(providerThinkingLevel === undefined ? {} : { providerThinkingLevel }),
             usage: {
                 input: 0,
                 output: 0,
@@ -619,6 +620,8 @@ export const stream = (model, context, options) => {
             for (;;) {
                 streamDeadline.signal?.throwIfAborted();
                 const built = buildParams(model, normalizedContext, isOAuth, options, disablePreferredStrictTools);
+                if (built.providerThinkingLevel)
+                    output.providerThinkingLevel = built.providerThinkingLevel;
                 let params = built.params;
                 const nextParams = await options?.onPayload?.(params, model);
                 if (nextParams !== undefined)
@@ -1144,11 +1147,14 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
     };
     const initialTools = initialSystemMessage?.toolsAdded ?? [];
     const nativeToolChanges = compat.supportsMidConvoSystemMessages && compat.supportsMidConvoToolChanges && initialTools.length > 0;
-    const converted = convertMessages(conversationMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, supportsMidConvoEffort(model) ? model.provider : undefined, nativeToolChanges ? convertToolDefinitions : undefined);
+    const thinkingDisabled = model.reasoning && options?.thinkingEnabled === false && model.thinkingLevelMap?.off !== null;
+    // Effort cannot change between messages while thinking is disabled, so "off" sends no effort markers.
+    const effortMessages = supportsMidConvoEffort(model) && !thinkingDisabled;
+    const converted = convertMessages(conversationMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, effortMessages ? model.provider : undefined, nativeToolChanges ? convertToolDefinitions : undefined);
     const activeEffort = options?.effort ?? "high";
     const params = {
         model: upstreamModelId(model),
-        messages: (supportsMidConvoEffort(model)
+        messages: (effortMessages
             ? insertThinkingLevelMessages(converted, activeEffort)
             : converted.messages),
         max_tokens: options?.maxTokens ?? model.maxTokens,
@@ -1205,7 +1211,7 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
     }
     // Managed effort models always use adaptive thinking. Their per-turn markers
     // carry the actual effort; the top-level high value deliberately stays stable.
-    if (supportsMidConvoEffort(model)) {
+    if (effortMessages) {
         params.thinking = {
             type: "adaptive",
             display: options?.thinkingDisplay ?? "summarized",
@@ -1301,18 +1307,13 @@ function buildParams(model, context, isOAuthToken, options, disablePreferredStri
     if (allowedFallbackModels && allowedFallbackModels.length > 0) {
         params.fallbacks = allowedFallbackModels.map((fallback) => ({ model: fallback.model }));
     }
-    return { params, hasPreferredStrictTools };
+    return { params, hasPreferredStrictTools, providerThinkingLevel: effortMessages ? activeEffort : undefined };
 }
 // Normalize tool call IDs to match Anthropic's required pattern and length
 function normalizeToolCallId(id) {
     return id.replace(/[^a-zA-Z0-9_-]/g, "_").slice(0, 64);
 }
-function convertToolResult(msg) {
-    const content = msg.isError
-        ? msg.content.map((block) => block.type === "image"
-            ? { type: "text", text: "[image omitted: error tool results cannot contain images]" }
-            : block)
-        : msg.content;
+function convertToolResult(msg, content = msg.content) {
     return {
         type: "tool_result",
         tool_use_id: msg.toolCallId,
@@ -1506,16 +1507,24 @@ function convertMessages(transformedMessages, isOAuthToken, cacheControl, allowE
         else if (msg.role === "toolResult") {
             // Collect all consecutive toolResult messages, needed for z.ai Anthropic endpoint.
             const toolResults = [];
+            // Anthropic rejects error tool results that contain anything but text, so their images follow
+            // all tool results of the turn, which must come first in the user message (#10794).
+            const errorImages = [];
             let j = i;
             while (j < transformedMessages.length && transformedMessages[j].role === "toolResult") {
-                toolResults.push(convertToolResult(transformedMessages[j]));
+                const toolMsg = transformedMessages[j];
+                const split = splitErrorToolResultImages(toolMsg);
+                toolResults.push(convertToolResult(toolMsg, split?.content));
+                if (split) {
+                    errorImages.push({ type: "text", text: split.caption }, ...split.images.map(convertImageBlock));
+                }
                 j++;
             }
             // Skip the messages we've already processed.
             i = j - 1;
             params.push({
                 role: "user",
-                content: toolResults,
+                content: [...toolResults, ...errorImages],
             });
         }
     }