docs: replace stale launchdarkly-ai package name with launchdarkly-ai-python

AGENTS.md

@@ -85,7 +85,7 @@ graph TD
   newHandler["launchdarkly-ai-new-provider\n(future)"]
  end
  subgraph tier0 ["Tier 0 — Core"]
-  ai["launchdarkly-ai\n(convenience barrel)"]
+  ai["launchdarkly-ai-python\n(convenience barrel)"]
   client["launchdarkly-ai-server"]
  end
 
@@ -104,9 +104,9 @@ graph TD
 ### Tiers
 
 - **Tier 0 — Core** (`launchdarkly-ai-server`): The foundation. Owns all LaunchDarkly integration, telemetry orchestration, shared data types, and the primary entry points (`config()`, `graph()`, `resolve_graph()`). Has no dependency on any other `launchdarkly-ai-*` package.
-- **Tier 0 — Convenience barrel** (`launchdarkly-ai`): A pure re-export package that makes all of `launchdarkly-ai-server` available under a shorter install name. No new logic — intended as the default install for most Python applications.
+- **Tier 0 — Convenience barrel** (`launchdarkly-ai-python`): A pure re-export package that makes all of `launchdarkly-ai-server` available under a shorter install name. No new logic — intended as the default install for most Python applications.
 - **Tier 1 — Handler packages** (`launchdarkly-ai-claude-agents`, `launchdarkly-ai-claude-messages`, `launchdarkly-ai-openai-agents`, `launchdarkly-ai-openai-messages`, `launchdarkly-ai-langchain-agents`, `launchdarkly-ai-langchain-messages`, …): Each wraps a specific AI provider SDK. Depends on `launchdarkly-ai-server` for shared types and utilities. Must not depend on other Tier 1 packages.
-- **Tier 2 — Consumer applications** (e.g. `main.py`, downstream projects): Imports from one or more handler packages and either `launchdarkly-ai` or `launchdarkly-ai-server`. Owns tool implementations and orchestration logic. No `launchdarkly-ai-*` package should ever depend on Tier 2 code.
+- **Tier 2 — Consumer applications** (e.g. `main.py`, downstream projects): Imports from one or more handler packages and either `launchdarkly-ai-python` or `launchdarkly-ai-server`. Owns tool implementations and orchestration logic. No `launchdarkly-ai-*` package should ever depend on Tier 2 code.
 
 ### Rules
 

README.md

@@ -77,7 +77,7 @@ Tier 0 — Core Client           (launchdarkly-ai-server)
 | Package | Description |
 | --- | --- |
 | [`launchdarkly-ai-server`](packages/client/README.md) | Core client — LaunchDarkly lifecycle, telemetry, shared types, `config()`, `graph()` |
-| [`launchdarkly-ai`](packages/ai/README.md) | Convenience barrel — re-exports all of `launchdarkly-ai-server`. Install this for the simplest setup. |
+| [`launchdarkly-ai-python`](packages/ai/README.md) | Convenience barrel — re-exports all of `launchdarkly-ai-server`. Install this for the simplest setup. |
 
 ### Handler Packages
 
@@ -98,12 +98,12 @@ Tier 0 — Core Client           (launchdarkly-ai-server)
 pip install launchdarkly-ai-python launchdarkly-ai-openai-messages
 ```
 
-`launchdarkly-ai` is a thin barrel that re-exports all of `launchdarkly-ai-server`. `init_client()` auto-discovers `launchdarkly-server-sdk` at runtime — no extra setup required.
+`launchdarkly-ai-python` is a thin barrel that re-exports all of `launchdarkly-ai-server`. `init_client()` auto-discovers `launchdarkly-server-sdk` at runtime — no extra setup required.
 
 **With telemetry** (recommended for production) — traces export to the LaunchDarkly Observability dashboard:
 
 ```bash
-pip install "launchdarkly-ai[otel]" launchdarkly-ai-openai-messages
+pip install "launchdarkly-ai-python[otel]" launchdarkly-ai-openai-messages
 ```
 
 No code changes are needed — `init_client()` detects whether the OTel packages are present at runtime and configures the tracer provider automatically. If they are absent, the SDK logs a one-time warning and continues normally.
@@ -492,7 +492,7 @@ When running inside `graph()`, every node's events carry the graph key, tool inv
 
 The OpenTelemetry SDK packages are **optional** — detected at runtime via `importlib`. The LaunchDarkly server SDK (`launchdarkly-server-sdk`) is also an optional dependency; pass a pre-initialized client to `init_client(client=...)` if you bring your own.
 
-**OTel packages** (installed via `pip install "launchdarkly-ai[otel]"` or `pip install "launchdarkly-ai-server[otel]"`):
+**OTel packages** (installed via `pip install "launchdarkly-ai-python[otel]"` or `pip install "launchdarkly-ai-server[otel]"`):
 - **If installed:** `init_client()` sets up a `TracerProvider` with a GZIP-compressed OTLP HTTP exporter and W3C trace-context/baggage propagators — no code changes needed.
 - **If not installed:** `init_client()` logs a warning and continues. Feature flags and AI calls work normally; spans become no-ops.
 

packages/ai/agents.md

@@ -1,6 +1,6 @@
-# Agent Guide — `launchdarkly-ai` (Convenience Wrapper)
+# Agent Guide — `launchdarkly-ai-python` (Convenience Wrapper)
 
-This document describes the role, structure, and constraints of the `launchdarkly-ai` package for AI agents and contributors.
+This document describes the role, structure, and constraints of the `launchdarkly-ai-python` package for AI agents and contributors.
 
 ---
 
@@ -18,7 +18,7 @@ Its purpose: Python application developers install this single package and get b
 
 | File | Responsibility |
 |---|---|
-| `src/launchdarkly_ai/__init__.py` | Single `from launchdarkly_ai_server import *` — the entire public barrel |
+| `src/launchdarkly_ai_python/__init__.py` | Single `from launchdarkly_ai_server import *` — the entire public barrel |
 
 ---
 
@@ -30,7 +30,7 @@ This package re-exports everything from `launchdarkly-ai-server` and nothing els
 from launchdarkly_ai_server import *
 ```
 
-Every symbol available from `launchdarkly-ai-server` is available from `launchdarkly-ai` under the same name. No additional symbols are added. When `launchdarkly-ai-server` gains a new export, this package automatically picks it up.
+Every symbol available from `launchdarkly-ai-server` is available from `launchdarkly-ai-python` under the same name. No additional symbols are added. When `launchdarkly-ai-server` gains a new export, this package automatically picks it up.
 
 ---
 
@@ -49,7 +49,7 @@ This package itself emits no spans. OTel is initialized and configured by `launc
 
 Install the OTel packages alongside this package:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install launchdarkly-ai-python opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```
@@ -84,4 +84,4 @@ This package must remain a pure re-export barrel. Any new utility, type, or help
 
 ### 2. Do not import from both packages in the same application
 
-Importing from both `launchdarkly-ai` and `launchdarkly-ai-server` in the same app can produce subtle issues if the dependency graph deduplication fails. Pick one: use `launchdarkly-ai` for standard Python apps, `launchdarkly-ai-server` for custom runtimes where you manage the SDK client yourself. The `get_client()` singleton is process-wide and shared regardless of which package path you import through.
+Importing from both `launchdarkly-ai-python` and `launchdarkly-ai-server` in the same app can produce subtle issues if the dependency graph deduplication fails. Pick one: use `launchdarkly-ai-python` for standard Python apps, `launchdarkly-ai-server` for custom runtimes where you manage the SDK client yourself. The `get_client()` singleton is process-wide and shared regardless of which package path you import through.

packages/claude-agents/agents.md

@@ -134,11 +134,11 @@ On error: `span.record_exception(exc)`, status set to ERROR, span ended, error r
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```

packages/claude-messages/agents.md

@@ -116,11 +116,11 @@ On error: `span.record_exception(exc)`, status ERROR, span ended, error re-raise
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```

packages/client/README.md

@@ -4,7 +4,7 @@ The core package for the LaunchDarkly AI Python SDK. It owns the LaunchDarkly cl
 
 All handler packages (`launchdarkly-ai-*`) depend on this package.
 
-> **Tip:** for the simplest install, use [`launchdarkly-ai`](../ai/README.md) instead. It re-exports this package's full API and is the recommended default for most applications.
+> **Tip:** for the simplest install, use [`launchdarkly-ai-python`](../ai/README.md) instead. It re-exports this package's full API and is the recommended default for most applications.
 
 ## Installation
 

packages/client/agents.md

@@ -133,7 +133,7 @@ The core client owns all OTel initialization. `init_client()` configures a `Trac
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http \
   opentelemetry-propagator-b3
 # or via the extras:
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 ```
 
 **OTLP endpoint configuration** — the exporter uses the standard `OTEL_EXPORTER_OTLP_ENDPOINT` env var. The default (when not set) points to LaunchDarkly's hosted OTel collector.

packages/langchain-agents/agents.md

@@ -139,11 +139,11 @@ Key implementation detail: `WorkflowState` is a `TypedDict` with an `Annotated[l
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```

packages/langchain-messages/agents.md

@@ -126,11 +126,11 @@ On error: `span.record_exception(exc)`, status ERROR, span ended, error re-raise
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```

packages/openai-agents/agents.md

@@ -126,11 +126,11 @@ On error: `span.record_exception(exc)`, status ERROR, span ended, error re-raise
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```

packages/openai-messages/agents.md

@@ -114,11 +114,11 @@ On error: `span.record_exception(exc)`, status ERROR, span ended, error re-raise
 
 ## OTel Setup
 
-This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai`).
+This package emits one span per invocation using `opentelemetry-api`. **No OTel configuration is needed in this package** — the tracer provider is registered by `init_client()` in `launchdarkly-ai-server` (or `launchdarkly-ai-python`).
 
 To receive spans, install the OTel SDK in your application:
 ```sh
-pip install "launchdarkly-ai[otel]"
+pip install "launchdarkly-ai-python[otel]"
 # or:
 pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
 ```