@shawnstack/quickforge 1.3.18 → 1.3.19

package/node_modules/@aws-sdk/xml-builder/package.json

@@ -1,9 +1,8 @@
 {
   "name": "@aws-sdk/xml-builder",
-  "version": "3.972.25",
+  "version": "3.972.26",
   "description": "XML utilities for the AWS SDK",
   "dependencies": {
-    "@nodable/entities": "2.1.0",
     "@smithy/types": "^4.14.2",
     "fast-xml-parser": "5.7.3",
     "tslib": "^2.6.2"
@@ -55,6 +54,7 @@
     "directory": "packages-internal/xml-builder"
   },
   "devDependencies": {
+    "@nodable/entities": "2.1.0",
     "@tsconfig/recommended": "1.0.1",
     "concurrently": "7.0.0",
     "downlevel-dts": "0.10.1",

package/node_modules/@mariozechner/pi-agent-core/README.md

@@ -112,6 +112,20 @@ The `beforeToolCall` hook runs after `tool_execution_start` and validated argume
 
 Tools can also return `terminate: true` to hint that the automatic follow-up LLM call should be skipped. The loop only stops early when every finalized tool result in that batch sets `terminate: true`. Mixed batches continue normally.
 
+Low-level loop callers can set `shouldStopAfterTurn` to stop gracefully after the current turn completes:
+
+```typescript
+const stream = agentLoop(prompts, context, {
+  model,
+  convertToLlm,
+  shouldStopAfterTurn: async ({ message, toolResults, context, newMessages }) => {
+    return shouldCompactBeforeNextTurn(context.messages);
+  },
+});
+```
+
+`shouldStopAfterTurn` runs after `turn_end` is emitted and after the assistant response and any tool executions have completed normally. If it returns `true`, the loop emits `agent_end` and exits before polling steering or follow-up queues, and before starting another LLM call. It does not abort the provider stream, does not cancel running tools, and does not alter the assistant message stop reason.
+
 When you use the `Agent` class, assistant `message_end` processing is treated as a barrier before tool preflight begins. That means `beforeToolCall` sees agent state that already includes the assistant message that requested the tool call.
 
 ### continue() Event Sequence

package/node_modules/@mariozechner/pi-agent-core/dist/agent-loop.js

@@ -121,6 +121,15 @@ async function runLoop(currentContext, newMessages, config, signal, emit, stream
                 }
             }
             await emit({ type: "turn_end", message, toolResults });
+            if (await config.shouldStopAfterTurn?.({
+                message,
+                toolResults,
+                context: currentContext,
+                newMessages,
+            })) {
+                await emit({ type: "agent_end", messages: newMessages });
+                return;
+            }
             pendingMessages = (await config.getSteeringMessages?.()) || [];
         }
         // Agent would stop here. Check for follow-up messages.

package/node_modules/@mariozechner/pi-agent-core/dist/agent.js

@@ -121,7 +121,7 @@ export class Agent {
         this.followUpQueue = new PendingMessageQueue(options.followUpMode ?? "one-at-a-time");
         this.sessionId = options.sessionId;
         this.thinkingBudgets = options.thinkingBudgets;
-        this.transport = options.transport ?? "sse";
+        this.transport = options.transport ?? "auto";
         this.maxRetryDelayMs = options.maxRetryDelayMs;
         this.toolExecution = options.toolExecution ?? "parallel";
     }

package/node_modules/@mariozechner/pi-agent-core/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@mariozechner/pi-agent-core",
-	"version": "0.70.6",
+	"version": "0.73.1",
 	"description": "General-purpose agent with transport abstraction, state management, and attachment support",
 	"type": "module",
 	"main": "./dist/index.js",
@@ -17,7 +17,7 @@
 		"prepublishOnly": "npm run clean && npm run build"
 	},
 	"dependencies": {
-		"@mariozechner/pi-ai": "^0.70.6",
+		"@mariozechner/pi-ai": "^0.73.1",
 		"typebox": "^1.1.24"
 	},
 	"keywords": [

package/node_modules/@mariozechner/pi-ai/README.md

@@ -57,19 +57,19 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **Mistral**
 - **Groq**
 - **Cerebras**
+- **Cloudflare AI Gateway**
 - **Cloudflare Workers AI**
 - **xAI**
 - **OpenRouter**
 - **Vercel AI Gateway**
 - **MiniMax**
 - **GitHub Copilot** (requires OAuth, see below)
-- **Google Gemini CLI** (requires OAuth, see below)
-- **Antigravity** (requires OAuth, see below)
 - **Amazon Bedrock**
 - **OpenCode Zen**
 - **OpenCode Go**
 - **Fireworks** (uses Anthropic-compatible API)
 - **Kimi For Coding** (Moonshot AI, uses Anthropic-compatible API)
+- **Xiaomi MiMo** (uses Anthropic-compatible API; defaults to API billing endpoint, with separate Token Plan providers for `cn`/`ams`/`sgp` regions)
 - **Any OpenAI-compatible API**: Ollama, vLLM, LM Studio, etc.
 
 ## Installation
@@ -383,6 +383,8 @@ All streaming events emitted during assistant message generation:
 | `done` | Stream complete | `reason`: Stop reason ("stop", "length", "toolUse"), `message`: Final assistant message |
 | `error` | Error occurred | `reason`: Error type ("error" or "aborted"), `error`: AssistantMessage with partial content |
 
+Streaming events for different content blocks are not guaranteed to be contiguous. Providers may emit deltas for text, thinking, and tool calls in the same upstream chunk, and pi may surface corresponding events interleaved, for example `text_start`, `text_delta`, `toolcall_start`, `text_delta`, `toolcall_delta`. Consumers must use `contentIndex` to associate each delta/end event with its block and must not assume that a block's `*_start`/`*_delta`/`*_end` sequence is uninterrupted by events for other blocks.
+
 ## Image Input
 
 Models with vision capabilities can process images. You can check if a model supports images via the `input` property. If you pass images to a non-vision model, they are silently ignored.
@@ -446,7 +448,7 @@ if (model.reasoning) {
 const response = await completeSimple(model, {
   messages: [{ role: 'user', content: 'Solve: 2x + 5 = 13' }]
 }, {
-  reasoning: 'medium'  // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' (xhigh maps to high on non-OpenAI providers)
+  reasoning: 'medium'  // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'
 });
 
 // Access thinking and text blocks
@@ -630,7 +632,6 @@ The library uses a registry of API implementations. Built-in APIs include:
 
 - **`anthropic-messages`**: Anthropic Messages API (`streamAnthropic`, `AnthropicOptions`)
 - **`google-generative-ai`**: Google Generative AI API (`streamGoogle`, `GoogleOptions`)
-- **`google-gemini-cli`**: Google Cloud Code Assist API (`streamGoogleGeminiCli`, `GoogleGeminiCliOptions`)
 - **`google-vertex`**: Google Vertex AI API (`streamGoogleVertex`, `GoogleVertexOptions`)
 - **`mistral-conversations`**: Mistral Conversations API (`streamMistral`, `MistralOptions`)
 - **`openai-completions`**: OpenAI Chat Completions API (`streamOpenAICompletions`, `OpenAICompletionsOptions`)
@@ -822,6 +823,8 @@ const response = await stream(ollamaModel, context, {
 
 Some OpenAI-compatible servers do not understand the `developer` role used for reasoning-capable models. For those providers, set `compat.supportsDeveloperRole` to `false` so the system prompt is sent as a `system` message instead. If the server also does not support `reasoning_effort`, set `compat.supportsReasoningEffort` to `false` too.
 
+Use model-level `thinkingLevelMap` to describe model-specific thinking controls. Keys are pi thinking levels (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`). Missing keys use provider defaults, string values are sent to the provider, and `null` marks a level unsupported.
+
 This commonly applies to Ollama, vLLM, SGLang, and similar OpenAI-compatible servers. You can set `compat` at the provider level or per model.
 
 ```typescript
@@ -836,6 +839,13 @@ const ollamaReasoningModel: Model<'openai-completions'> = {
   cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
   contextWindow: 131072,
   maxTokens: 32000,
+  thinkingLevelMap: {
+    minimal: null,
+    low: null,
+    medium: null,
+    high: 'high',
+    xhigh: null,
+  },
   compat: {
     supportsDeveloperRole: false,
     supportsReasoningEffort: false,
@@ -1029,6 +1039,7 @@ In Node.js environments, you can set environment variables to avoid passing API
 | Mistral | `MISTRAL_API_KEY` |
 | Groq | `GROQ_API_KEY` |
 | Cerebras | `CEREBRAS_API_KEY` |
+| Cloudflare AI Gateway | `CLOUDFLARE_API_KEY` + `CLOUDFLARE_ACCOUNT_ID` + `CLOUDFLARE_GATEWAY_ID` |
 | Cloudflare Workers AI | `CLOUDFLARE_API_KEY` + `CLOUDFLARE_ACCOUNT_ID` |
 | xAI | `XAI_API_KEY` |
 | Fireworks | `FIREWORKS_API_KEY` |
@@ -1038,6 +1049,10 @@ In Node.js environments, you can set environment variables to avoid passing API
 | MiniMax | `MINIMAX_API_KEY` |
 | OpenCode Zen / OpenCode Go | `OPENCODE_API_KEY` |
 | Kimi For Coding | `KIMI_API_KEY` |
+| Xiaomi MiMo (API billing) | `XIAOMI_API_KEY` |
+| Xiaomi MiMo Token Plan (China) | `XIAOMI_TOKEN_PLAN_CN_API_KEY` |
+| Xiaomi MiMo Token Plan (Amsterdam) | `XIAOMI_TOKEN_PLAN_AMS_API_KEY` |
+| Xiaomi MiMo Token Plan (Singapore) | `XIAOMI_TOKEN_PLAN_SGP_API_KEY` |
 | GitHub Copilot | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN` |
 
 When set, the library automatically uses these keys:
@@ -1053,27 +1068,6 @@ const response = await complete(model, context, {
 });
 ```
 
-#### Antigravity Version Override
-
-Set `PI_AI_ANTIGRAVITY_VERSION` to override the Antigravity User-Agent version when Google updates their requirements:
-
-```bash
-export PI_AI_ANTIGRAVITY_VERSION="1.23.0"
-```
-
-#### Cache Retention
-
-Set `PI_CACHE_RETENTION=long` to extend prompt cache retention:
-
-| Provider | Default | With `PI_CACHE_RETENTION=long` |
-|----------|---------|-------------------------------|
-| Anthropic | 5 minutes | 1 hour |
-| OpenAI | in-memory | 24 hours |
-
-This only affects direct API calls to `api.anthropic.com` and `api.openai.com`. Proxies and other providers are unaffected.
-
-> **Note**: Extended cache retention may increase costs for Anthropic (cache writes are charged at a higher rate). OpenAI's 24h retention has no additional cost.
-
 ### Checking Environment Variables
 
 ```typescript
@@ -1090,8 +1084,6 @@ Several providers require OAuth authentication instead of static API keys:
 - **Anthropic** (Claude Pro/Max subscription)
 - **OpenAI Codex** (ChatGPT Plus/Pro subscription, access to GPT-5.x Codex models)
 - **GitHub Copilot** (Copilot subscription)
-- **Google Gemini CLI** (Gemini 2.0/2.5 via Google Cloud Code Assist; free tier or paid subscription)
-- **Antigravity** (Free Gemini 3, Claude, GPT-OSS via Google Cloud)
 
 For paid Cloud Code Assist subscriptions, set `GOOGLE_CLOUD_PROJECT` or `GOOGLE_CLOUD_PROJECT_ID` to your project ID.
 
@@ -1159,14 +1151,13 @@ import {
   loginOpenAICodex,
   loginGitHubCopilot,
   loginGeminiCli,
-  loginAntigravity,
 
   // Token management
   refreshOAuthToken,   // (provider, credentials) => new credentials
   getOAuthApiKey,      // (provider, credentialsMap) => { newCredentials, apiKey } | null
 
   // Types
-  type OAuthProvider,  // 'anthropic' | 'openai-codex' | 'github-copilot' | 'google-gemini-cli' | 'google-antigravity'
+  type OAuthProvider,
   type OAuthCredentials,
 } from '@mariozechner/pi-ai/oauth';
 ```
@@ -1228,8 +1219,6 @@ const response = await complete(model, {
 
 **GitHub Copilot**: If you get "The requested model is not supported" error, enable the model manually in VS Code: open Copilot Chat, click the model selector, select the model (warning icon), and click "Enable".
 
-**Google Gemini CLI / Antigravity**: These use Google Cloud OAuth. The `apiKey` returned by `getOAuthApiKey()` is a JSON string containing both the token and project ID, which the library handles automatically.
-
 ## Development
 
 ### Adding a New Provider

package/node_modules/@mariozechner/pi-ai/dist/env-api-keys.js

@@ -99,12 +99,19 @@ function getApiKeyEnvVars(provider) {
         mistral: "MISTRAL_API_KEY",
         minimax: "MINIMAX_API_KEY",
         "minimax-cn": "MINIMAX_CN_API_KEY",
+        moonshotai: "MOONSHOT_API_KEY",
+        "moonshotai-cn": "MOONSHOT_API_KEY",
         huggingface: "HF_TOKEN",
         fireworks: "FIREWORKS_API_KEY",
         opencode: "OPENCODE_API_KEY",
         "opencode-go": "OPENCODE_API_KEY",
         "kimi-coding": "KIMI_API_KEY",
         "cloudflare-workers-ai": "CLOUDFLARE_API_KEY",
+        "cloudflare-ai-gateway": "CLOUDFLARE_API_KEY",
+        xiaomi: "XIAOMI_API_KEY",
+        "xiaomi-token-plan-cn": "XIAOMI_TOKEN_PLAN_CN_API_KEY",
+        "xiaomi-token-plan-ams": "XIAOMI_TOKEN_PLAN_AMS_API_KEY",
+        "xiaomi-token-plan-sgp": "XIAOMI_TOKEN_PLAN_SGP_API_KEY",
     };
     const envVar = envMap[provider];
     return envVar ? [envVar] : undefined;

package/node_modules/@mariozechner/pi-ai/dist/index.js

@@ -4,8 +4,10 @@ export * from "./env-api-keys.js";
 export * from "./models.js";
 export * from "./providers/faux.js";
 export * from "./providers/register-builtins.js";
+export * from "./session-resources.js";
 export * from "./stream.js";
 export * from "./types.js";
+export * from "./utils/diagnostics.js";
 export * from "./utils/event-stream.js";
 export * from "./utils/json-parse.js";
 export * from "./utils/overflow.js";