v0.2.11

- The **PageIndex SDK**, **local** or **cloud** — vectorless, reasoning-based RAG, end to end.
- **Much faster indexing** — the **PageIndex Flash** engine gets the tree from layout stats: no LLM involved for the structure generation itself, LLMs only write the node summaries — and tree expansion now proposes a wave of nodes concurrently.

```python
client = PageIndexClient()
client.submit_document("report.pdf")
client.chat("What does the report conclude?")
```

Index, to chat, to agent integration, one client.
Local mode needs no server, no vector DB, no PageIndex API key.

## Highlights

- **Flash engine**: the local default (`mode="standard"` keeps the classic LLM pipeline). Embedded bookmarks are consumed when trustworthy, and tree optimization is on by default — `optimize="merge"` for the deterministic LLM-free pass, `"full"` (default) adds LLM expand, which now runs a wave of nodes concurrently instead of one round-trip at a time.
- **One complete surface, local and cloud**: `PageIndexLocalClient(storage_path=...)` is the same client as cloud — submit, tree, page content, chat, and agent tools all present in both modes, so code moves between them unchanged.
- **Agent integration**: the cloud MCP tool contract, in-process — `client.agent_tools()` (plain functions), `as_openai_tools()`, `as_anthropic_tools()`, `as_claude_mcp()`, plus one-call `openai_agent_config()` / `anthropic_runner_config()` / `claude_agent_config()` bundles and `agent_instructions()` for the system prompt. Cloud clients get the live server tool set over the MCP bridge (read-only endpoint by default); local clients get the in-process subset with the same schemas and envelopes — agent prompts port unchanged.
- **Chat surfaces**: `chat()` — question in, answer out, on any backend; `chat_completions()` / `responses()` / `messages()` protocol doors with `doc_id` targeting, streaming, honest usage accounting, and prompt-cache continuity across turns.
- **Model & connection knobs**: `index_model` / `chat_model`, `index_backend` / `chat_backend` (and per-call `backend`) passed verbatim to each lane — LiteLLM-routed providers, keyless OpenAI-compatible servers, Azure/Bedrock/Vertex included.
- **Dependencies**: Python >= 3.10; `openai-agents` in the base install (the chat engine); `[anthropic]` and `[claude]` extras for those SDKs.

## Also in 0.2.11

- **Cloud documents, your own model**: `api_key` decides where your documents live; a configured chat model decides who answers — and the two combine. `PageIndexClient(api_key="pi-...", chat_model="openai/gpt-5.2")` runs the same in-process document-QA engine over the live cloud tool set; `chat()`, `chat_completions()`, `responses()` and `messages()` all work. Page content flows through your process to your provider on your credentials; `doc_id` targets at the prompt level; `enable_citations` stays with the managed chat.
- **`index=` / `chat=` slots**: the grouped spelling of the flat arguments — a string shorthand or a dict (`index={"model": ..., "storage_path": ...}`, `chat={"model": ..., "backend": ...}`). `"cloud"` / `"local"` name a side, an optional `mode=` cross-checks it, and `PageIndexLocalClient` / `PageIndexCloudClient` take the same slots. `PageIndexCloudClient()` reads `PAGEINDEX_API_KEY`; a bare `PageIndexClient()` stays local no matter what the environment holds.
- **Typed config shapes**: `IndexConfig` / `CloudIndexConfig` / `LocalIndexConfig` / `ChatConfig`, with `py.typed` shipped so your type checker sees them.
- **Strict validation**: unknown keys, mixed sides, empty values and mode/content conflicts refuse at construction with the legal vocabulary in the message — nothing is silently guessed.
- **Indexing fails loud**: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a context overflow stays a per-prompt failure the run absorbs; all-empty model replies never store a retrieval-ready document.
- **Chat envelopes append verbatim**: `messages()` output goes back into the next request unchanged; Claude cache marks follow the wire routing; `openai_agent_config()` takes `model_settings` and `name`.
- Every cloud error carries its HTTP status; NaN/Infinity metadata is rejected at the gate; the CLI's flash lane resolves `--summary-model` like the other lanes.

Compatibility: values that configure nothing (`""`, whitespace-only strings, `{}`) now refuse at construction; on a cloud client, `api_key` + `chat_model` (or `chat_backend`) selects own-model chat instead of erroring, and `client.retrieve_model = m` does the same.

**Full Changelog**: https://github.com/VectifyAI/PageIndex/compare/v0.2.10...v0.2.11