pi-usereq 0.7.0 → 0.10.0

package/.gitignore

@@ -47,6 +47,8 @@
 !pi-usereq/
 !pi-usereq/docs/
 !pi-usereq/docs/**/*.md
+!pi.dev-src/
+!pi.dev-src/**/*
 !images/
 !images/**/*
 

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [0.10.0](https://github.com/Ogekuri/PI-useReq/compare/v0.7.0..v0.10.0) - 2026-04-24
+### ⛰️  Features
+- Add source code from a extranal branch.
+
 ## [0.7.0](https://github.com/Ogekuri/PI-useReq/compare/v0.6.0..v0.7.0) - 2026-04-20
 ### ⛰️  Features
 - Add src/resources/images/ files.
@@ -290,6 +294,7 @@
 - \[0.5.0\]: https://github.com/Ogekuri/PI-useReq/releases/tag/v0.5.0
 - \[0.6.0\]: https://github.com/Ogekuri/PI-useReq/releases/tag/v0.6.0
 - \[0.7.0\]: https://github.com/Ogekuri/PI-useReq/releases/tag/v0.7.0
+- \[0.10.0\]: https://github.com/Ogekuri/PI-useReq/releases/tag/v0.10.0
 
 [0.1.0]: https://github.com/Ogekuri/PI-useReq/releases/tag/v0.1.0
 [0.2.0]: https://github.com/Ogekuri/PI-useReq/compare/v0.1.0..v0.2.0
@@ -298,3 +303,4 @@
 [0.5.0]: https://github.com/Ogekuri/PI-useReq/compare/v0.4.0..v0.5.0
 [0.6.0]: https://github.com/Ogekuri/PI-useReq/compare/v0.5.0..v0.6.0
 [0.7.0]: https://github.com/Ogekuri/PI-useReq/compare/v0.6.0..v0.7.0
+[0.10.0]: https://github.com/Ogekuri/PI-useReq/compare/v0.7.0..v0.10.0

package/README.md

@@ -1,4 +1,4 @@
-# PI-useReq/pi-usereq (0.7.0)
+# PI-useReq/pi-usereq (0.10.0)
 
 <p align="center">
   <img src="https://img.shields.io/badge/python-3.11%2B-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python 3.11+">

package/docs/pi.dev/coding-agent-docs/custom-provider.md

@@ -59,6 +59,8 @@ export default function (pi: ExtensionAPI) {
 }
 ```
 
+The extension factory can also be `async`. For dynamic model discovery, fetch and register models in the factory instead of `session_start`. pi waits for the factory before startup continues, so the provider is available during interactive startup and to `pi --list-models`.
+
 ## Override Existing Provider
 
 The simplest use case: redirect an existing provider through a proxy.
@@ -91,6 +93,41 @@ When only `baseUrl` and/or `headers` are provided (no `models`), all existing mo
 
 To add a completely new provider, specify `models` along with the required configuration.
 
+If the model list comes from a remote endpoint, use an async extension factory:
+
+```typescript
+import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
+
+export default async function (pi: ExtensionAPI) {
+  const response = await fetch("http://localhost:1234/v1/models");
+  const payload = (await response.json()) as {
+    data: Array<{
+      id: string;
+      name?: string;
+      context_window?: number;
+      max_tokens?: number;
+    }>;
+  };
+
+  pi.registerProvider("local-openai", {
+    baseUrl: "http://localhost:1234/v1",
+    apiKey: "LOCAL_OPENAI_API_KEY",
+    api: "openai-completions",
+    models: payload.data.map((model) => ({
+      id: model.id,
+      name: model.name ?? model.id,
+      reasoning: false,
+      input: ["text"],
+      cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+      contextWindow: model.context_window ?? 128000,
+      maxTokens: model.max_tokens ?? 4096,
+    })),
+  });
+}
+```
+
+This registers the fetched models before startup finishes.
+
 ```typescript
 pi.registerProvider("my-llm", {
   baseUrl: "https://api.my-llm.com/v1",
@@ -183,12 +220,14 @@ models: [{
     },
       maxTokensField: "max_tokens",      // instead of "max_completion_tokens"
       requiresToolResultName: true,      // tool results need name field
-      thinkingFormat: "qwen"            // top-level enable_thinking: true
+      thinkingFormat: "qwen",           // top-level enable_thinking: true
+      cacheControlFormat: "anthropic"   // Anthropic-style cache_control markers
     }
   }]
 ```
 
 Use `qwen-chat-template` instead for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
+Use `cacheControlFormat: "anthropic"` for OpenAI-compatible providers that expose Anthropic-style prompt caching via `cache_control` on the system prompt, last tool definition, and last user/assistant text content.
 
 > Migration note: Mistral moved from `openai-completions` to `mistral-conversations`.
 > Use `mistral-conversations` for native Mistral models.
@@ -589,8 +628,10 @@ interface ProviderModelConfig {
     requiresAssistantAfterToolResult?: boolean;
     requiresThinkingAsText?: boolean;
     thinkingFormat?: "openai" | "zai" | "qwen" | "qwen-chat-template";
+    cacheControlFormat?: "anthropic";
   };
 }
 ```
 
 `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
+`cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user/assistant text content.