phi-code-agent 0.56.3

package/README.md

@@ -0,0 +1,412 @@
+# @mariozechner/pi-agent-core
+
+Stateful agent with tool execution and event streaming. Built on `@mariozechner/pi-ai`.
+
+## Installation
+
+```bash
+npm install @mariozechner/pi-agent-core
+```
+
+## Quick Start
+
+```typescript
+import { Agent } from "@mariozechner/pi-agent-core";
+import { getModel } from "@mariozechner/pi-ai";
+
+const agent = new Agent({
+  initialState: {
+    systemPrompt: "You are a helpful assistant.",
+    model: getModel("anthropic", "claude-sonnet-4-20250514"),
+  },
+});
+
+agent.subscribe((event) => {
+  if (event.type === "message_update" && event.assistantMessageEvent.type === "text_delta") {
+    // Stream just the new text chunk
+    process.stdout.write(event.assistantMessageEvent.delta);
+  }
+});
+
+await agent.prompt("Hello!");
+```
+
+## Core Concepts
+
+### AgentMessage vs LLM Message
+
+The agent works with `AgentMessage`, a flexible type that can include:
+- Standard LLM messages (`user`, `assistant`, `toolResult`)
+- Custom app-specific message types via declaration merging
+
+LLMs only understand `user`, `assistant`, and `toolResult`. The `convertToLlm` function bridges this gap by filtering and transforming messages before each LLM call.
+
+### Message Flow
+
+```
+AgentMessage[] → transformContext() → AgentMessage[] → convertToLlm() → Message[] → LLM
+                    (optional)                           (required)
+```
+
+1. **transformContext**: Prune old messages, inject external context
+2. **convertToLlm**: Filter out UI-only messages, convert custom types to LLM format
+
+## Event Flow
+
+The agent emits events for UI updates. Understanding the event sequence helps build responsive interfaces.
+
+### prompt() Event Sequence
+
+When you call `prompt("Hello")`:
+
+```
+prompt("Hello")
+├─ agent_start
+├─ turn_start
+├─ message_start   { message: userMessage }      // Your prompt
+├─ message_end     { message: userMessage }
+├─ message_start   { message: assistantMessage } // LLM starts responding
+├─ message_update  { message: partial... }       // Streaming chunks
+├─ message_update  { message: partial... }
+├─ message_end     { message: assistantMessage } // Complete response
+├─ turn_end        { message, toolResults: [] }
+└─ agent_end       { messages: [...] }
+```
+
+### With Tool Calls
+
+If the assistant calls tools, the loop continues:
+
+```
+prompt("Read config.json")
+├─ agent_start
+├─ turn_start
+├─ message_start/end  { userMessage }
+├─ message_start      { assistantMessage with toolCall }
+├─ message_update...
+├─ message_end        { assistantMessage }
+├─ tool_execution_start  { toolCallId, toolName, args }
+├─ tool_execution_update { partialResult }           // If tool streams
+├─ tool_execution_end    { toolCallId, result }
+├─ message_start/end  { toolResultMessage }
+├─ turn_end           { message, toolResults: [toolResult] }
+│
+├─ turn_start                                        // Next turn
+├─ message_start      { assistantMessage }           // LLM responds to tool result
+├─ message_update...
+├─ message_end
+├─ turn_end
+└─ agent_end
+```
+
+### continue() Event Sequence
+
+`continue()` resumes from existing context without adding a new message. Use it for retries after errors.
+
+```typescript
+// After an error, retry from current state
+await agent.continue();
+```
+
+The last message in context must be `user` or `toolResult` (not `assistant`).
+
+### Event Types
+
+| Event | Description |
+|-------|-------------|
+| `agent_start` | Agent begins processing |
+| `agent_end` | Agent completes with all new messages |
+| `turn_start` | New turn begins (one LLM call + tool executions) |
+| `turn_end` | Turn completes with assistant message and tool results |
+| `message_start` | Any message begins (user, assistant, toolResult) |
+| `message_update` | **Assistant only.** Includes `assistantMessageEvent` with delta |
+| `message_end` | Message completes |
+| `tool_execution_start` | Tool begins |
+| `tool_execution_update` | Tool streams progress |
+| `tool_execution_end` | Tool completes |
+
+## Agent Options
+
+```typescript
+const agent = new Agent({
+  // Initial state
+  initialState: {
+    systemPrompt: string,
+    model: Model<any>,
+    thinkingLevel: "off" | "minimal" | "low" | "medium" | "high" | "xhigh",
+    tools: AgentTool<any>[],
+    messages: AgentMessage[],
+  },
+
+  // Convert AgentMessage[] to LLM Message[] (required for custom message types)
+  convertToLlm: (messages) => messages.filter(...),
+
+  // Transform context before convertToLlm (for pruning, compaction)
+  transformContext: async (messages, signal) => pruneOldMessages(messages),
+
+  // Steering mode: "one-at-a-time" (default) or "all"
+  steeringMode: "one-at-a-time",
+
+  // Follow-up mode: "one-at-a-time" (default) or "all"
+  followUpMode: "one-at-a-time",
+
+  // Custom stream function (for proxy backends)
+  streamFn: streamProxy,
+
+  // Session ID for provider caching
+  sessionId: "session-123",
+
+  // Dynamic API key resolution (for expiring OAuth tokens)
+  getApiKey: async (provider) => refreshToken(),
+
+  // Custom thinking budgets for token-based providers
+  thinkingBudgets: {
+    minimal: 128,
+    low: 512,
+    medium: 1024,
+    high: 2048,
+  },
+});
+```
+
+## Agent State
+
+```typescript
+interface AgentState {
+  systemPrompt: string;
+  model: Model<any>;
+  thinkingLevel: ThinkingLevel;
+  tools: AgentTool<any>[];
+  messages: AgentMessage[];
+  isStreaming: boolean;
+  streamMessage: AgentMessage | null;  // Current partial during streaming
+  pendingToolCalls: Set<string>;
+  error?: string;
+}
+```
+
+Access via `agent.state`. During streaming, `streamMessage` contains the partial assistant message.
+
+## Methods
+
+### Prompting
+
+```typescript
+// Text prompt
+await agent.prompt("Hello");
+
+// With images
+await agent.prompt("What's in this image?", [
+  { type: "image", data: base64Data, mimeType: "image/jpeg" }
+]);
+
+// AgentMessage directly
+await agent.prompt({ role: "user", content: "Hello", timestamp: Date.now() });
+
+// Continue from current context (last message must be user or toolResult)
+await agent.continue();
+```
+
+### State Management
+
+```typescript
+agent.setSystemPrompt("New prompt");
+agent.setModel(getModel("openai", "gpt-4o"));
+agent.setThinkingLevel("medium");
+agent.setTools([myTool]);
+agent.replaceMessages(newMessages);
+agent.appendMessage(message);
+agent.clearMessages();
+agent.reset();  // Clear everything
+```
+
+### Session and Thinking Budgets
+
+```typescript
+agent.sessionId = "session-123";
+
+agent.thinkingBudgets = {
+  minimal: 128,
+  low: 512,
+  medium: 1024,
+  high: 2048,
+};
+```
+
+### Control
+
+```typescript
+agent.abort();           // Cancel current operation
+await agent.waitForIdle(); // Wait for completion
+```
+
+### Events
+
+```typescript
+const unsubscribe = agent.subscribe((event) => {
+  console.log(event.type);
+});
+unsubscribe();
+```
+
+## Steering and Follow-up
+
+Steering messages let you interrupt the agent while tools are running. Follow-up messages let you queue work after the agent would otherwise stop.
+
+```typescript
+agent.setSteeringMode("one-at-a-time");
+agent.setFollowUpMode("one-at-a-time");
+
+// While agent is running tools
+agent.steer({
+  role: "user",
+  content: "Stop! Do this instead.",
+  timestamp: Date.now(),
+});
+
+// After the agent finishes its current work
+agent.followUp({
+  role: "user",
+  content: "Also summarize the result.",
+  timestamp: Date.now(),
+});
+
+const steeringMode = agent.getSteeringMode();
+const followUpMode = agent.getFollowUpMode();
+
+agent.clearSteeringQueue();
+agent.clearFollowUpQueue();
+agent.clearAllQueues();
+```
+
+Use clearSteeringQueue, clearFollowUpQueue, or clearAllQueues to drop queued messages.
+
+When steering messages are detected after a tool completes:
+1. Remaining tools are skipped with error results
+2. Steering messages are injected
+3. LLM responds to the interruption
+
+Follow-up messages are checked only when there are no more tool calls and no steering messages. If any are queued, they are injected and another turn runs.
+
+## Custom Message Types
+
+Extend `AgentMessage` via declaration merging:
+
+```typescript
+declare module "@mariozechner/pi-agent-core" {
+  interface CustomAgentMessages {
+    notification: { role: "notification"; text: string; timestamp: number };
+  }
+}
+
+// Now valid
+const msg: AgentMessage = { role: "notification", text: "Info", timestamp: Date.now() };
+```
+
+Handle custom types in `convertToLlm`:
+
+```typescript
+const agent = new Agent({
+  convertToLlm: (messages) => messages.flatMap(m => {
+    if (m.role === "notification") return []; // Filter out
+    return [m];
+  }),
+});
+```
+
+## Tools
+
+Define tools using `AgentTool`:
+
+```typescript
+import { Type } from "@sinclair/typebox";
+
+const readFileTool: AgentTool = {
+  name: "read_file",
+  label: "Read File",  // For UI display
+  description: "Read a file's contents",
+  parameters: Type.Object({
+    path: Type.String({ description: "File path" }),
+  }),
+  execute: async (toolCallId, params, signal, onUpdate) => {
+    const content = await fs.readFile(params.path, "utf-8");
+
+    // Optional: stream progress
+    onUpdate?.({ content: [{ type: "text", text: "Reading..." }], details: {} });
+
+    return {
+      content: [{ type: "text", text: content }],
+      details: { path: params.path, size: content.length },
+    };
+  },
+};
+
+agent.setTools([readFileTool]);
+```
+
+### Error Handling
+
+**Throw an error** when a tool fails. Do not return error messages as content.
+
+```typescript
+execute: async (toolCallId, params, signal, onUpdate) => {
+  if (!fs.existsSync(params.path)) {
+    throw new Error(`File not found: ${params.path}`);
+  }
+  // Return content only on success
+  return { content: [{ type: "text", text: "..." }] };
+}
+```
+
+Thrown errors are caught by the agent and reported to the LLM as tool errors with `isError: true`.
+
+## Proxy Usage
+
+For browser apps that proxy through a backend:
+
+```typescript
+import { Agent, streamProxy } from "@mariozechner/pi-agent-core";
+
+const agent = new Agent({
+  streamFn: (model, context, options) =>
+    streamProxy(model, context, {
+      ...options,
+      authToken: "...",
+      proxyUrl: "https://your-server.com",
+    }),
+});
+```
+
+## Low-Level API
+
+For direct control without the Agent class:
+
+```typescript
+import { agentLoop, agentLoopContinue } from "@mariozechner/pi-agent-core";
+
+const context: AgentContext = {
+  systemPrompt: "You are helpful.",
+  messages: [],
+  tools: [],
+};
+
+const config: AgentLoopConfig = {
+  model: getModel("openai", "gpt-4o"),
+  convertToLlm: (msgs) => msgs.filter(m => ["user", "assistant", "toolResult"].includes(m.role)),
+};
+
+const userMessage = { role: "user", content: "Hello", timestamp: Date.now() };
+
+for await (const event of agentLoop([userMessage], context, config)) {
+  console.log(event.type);
+}
+
+// Continue from existing context
+for await (const event of agentLoopContinue(context, config)) {
+  console.log(event.type);
+}
+```
+
+## License
+
+MIT

package/dist/agent-loop.d.ts

@@ -0,0 +1,21 @@
+/**
+ * Agent loop that works with AgentMessage throughout.
+ * Transforms to Message[] only at the LLM call boundary.
+ */
+import { EventStream } from "phi-code-ai";
+import type { AgentContext, AgentEvent, AgentLoopConfig, AgentMessage, StreamFn } from "./types.js";
+/**
+ * Start an agent loop with a new prompt message.
+ * The prompt is added to the context and events are emitted for it.
+ */
+export declare function agentLoop(prompts: AgentMessage[], context: AgentContext, config: AgentLoopConfig, signal?: AbortSignal, streamFn?: StreamFn): EventStream<AgentEvent, AgentMessage[]>;
+/**
+ * Continue an agent loop from the current context without adding a new message.
+ * Used for retries - context already has user message or tool results.
+ *
+ * **Important:** The last message in context must convert to a `user` or `toolResult` message
+ * via `convertToLlm`. If it doesn't, the LLM provider will reject the request.
+ * This cannot be validated here since `convertToLlm` is only called once per turn.
+ */
+export declare function agentLoopContinue(context: AgentContext, config: AgentLoopConfig, signal?: AbortSignal, streamFn?: StreamFn): EventStream<AgentEvent, AgentMessage[]>;
+//# sourceMappingURL=agent-loop.d.ts.map

package/dist/agent-loop.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"agent-loop.d.ts","sourceRoot":"","sources":["../src/agent-loop.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAGN,WAAW,EAIX,MAAM,aAAa,CAAC;AACrB,OAAO,KAAK,EACX,YAAY,EACZ,UAAU,EACV,eAAe,EACf,YAAY,EAGZ,QAAQ,EACR,MAAM,YAAY,CAAC;AAEpB;;;GAGG;AACH,wBAAgB,SAAS,CACxB,OAAO,EAAE,YAAY,EAAE,EACvB,OAAO,EAAE,YAAY,EACrB,MAAM,EAAE,eAAe,EACvB,MAAM,CAAC,EAAE,WAAW,EACpB,QAAQ,CAAC,EAAE,QAAQ,GACjB,WAAW,CAAC,UAAU,EAAE,YAAY,EAAE,CAAC,CAqBzC;AAED;;;;;;;GAOG;AACH,wBAAgB,iBAAiB,CAChC,OAAO,EAAE,YAAY,EACrB,MAAM,EAAE,eAAe,EACvB,MAAM,CAAC,EAAE,WAAW,EACpB,QAAQ,CAAC,EAAE,QAAQ,GACjB,WAAW,CAAC,UAAU,EAAE,YAAY,EAAE,CAAC,CAsBzC"}