Merge unified-llm-cli crate into unified-llm

Move the ullm binary from a separate crate into unified-llm as
src/bin/ullm.rs, consolidating CLI dependencies into the library crate.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

crates/unified-llm-cli/Cargo.toml

@@ -1,26 +0,0 @@
-[package]
-name = "unified-llm-cli"
-description = "CLI for the unified-llm library"
-edition.workspace = true
-version.workspace = true
-license.workspace = true
-
-[lints]
-workspace = true
-
-[[bin]]
-name = "ullm"
-path = "src/main.rs"
-
-[dependencies]
-unified-llm = { path = "../unified-llm" }
-clap = { workspace = true }
-tokio = { workspace = true }
-anyhow = { workspace = true }
-dotenvy = { workspace = true }
-futures = { workspace = true }
-serde_json = { workspace = true }
-
-[dev-dependencies]
-assert_cmd = "2"
-predicates = "3"

crates/unified-llm-cli/README.md

@@ -1,95 +0,0 @@
-# unified-llm-cli
-
-A command-line interface for interacting with LLM providers through the [unified-llm](../unified-llm/) library. Supports Anthropic, OpenAI, Google Gemini, and other providers with a single tool.
-
-## Installation
-
-```sh
-cargo install --path crates/unified-llm-cli
-```
-
-This installs the `ullm` binary.
-
-## Configuration
-
-API keys are read from environment variables. You can set them directly or place them in a `.env` file:
-
-```sh
-export ANTHROPIC_API_KEY="sk-..."
-export OPENAI_API_KEY="sk-..."
-export GEMINI_API_KEY="..."
-```
-
-## Commands
-
-### `ullm prompt`
-
-Send a prompt to an LLM and print the response.
-
-```sh
-ullm prompt "What is the capital of France?"
-```
-
-**Flags:**
-
-| Flag | Description |
-|------|-------------|
-| `-m, --model <MODEL>` | Model to use (defaults to first catalog model) |
-| `-s, --system <TEXT>` | System prompt |
-| `-o, --option <KEY=VALUE>` | Generation options: `temperature`, `max_tokens`, `top_p`, or provider-specific keys |
-| `-u, --usage` | Show token usage on stderr |
-| `--no-stream` | Disable streaming (wait for full response) |
-
-**Stdin support:** Pipe text into `ullm prompt` to use it as input. If both stdin and an argument are provided, they are concatenated.
-
-```sh
-echo "Summarize this" | ullm prompt
-cat article.txt | ullm prompt "Give me the key points"
-```
-
-**Examples:**
-
-```sh
-# Use a specific model
-ullm prompt -m claude-opus-4-6 "Explain quicksort"
-
-# Set a system prompt
-ullm prompt -s "You are a helpful translator" "Translate to French: hello"
-
-# Adjust generation parameters
-ullm prompt -o temperature=0.2 -o max_tokens=500 "Write a haiku"
-
-# Show token usage
-ullm prompt -u --no-stream "Hello"
-```
-
-### `ullm models`
-
-List available models from all providers. Running `ullm models` with no subcommand defaults to `ullm models list`.
-
-```sh
-ullm models
-```
-
-#### `ullm models list`
-
-```sh
-ullm models list
-```
-
-**Flags:**
-
-| Flag | Description |
-|------|-------------|
-| `-p, --provider <NAME>` | Filter models by provider (e.g., `anthropic`, `openai`, `gemini`) |
-| `-q, --query <TEXT>` | Search models by ID, display name, or alias (case-insensitive) |
-
-**Examples:**
-
-```sh
-# List only Anthropic models
-ullm models list --provider anthropic
-
-# Search for models matching "opus"
-ullm models list --query opus
-```

crates/unified-llm/Cargo.toml

@@ -9,6 +9,10 @@ readme = "README.md"
 keywords = ["llm", "ai", "openai", "anthropic"]
 categories = ["api-bindings"]
 
+[[bin]]
+name = "ullm"
+path = "src/bin/ullm.rs"
+
 [dependencies]
 anyhow.workspace = true
 thiserror.workspace = true
@@ -24,11 +28,14 @@ reqwest.workspace = true
 base64.workspace = true
 bytes.workspace = true
 tokio-util.workspace = true
+clap.workspace = true
+dotenvy.workspace = true
 
 [dev-dependencies]
-dotenvy.workspace = true
 http = "1"
 tokio = { workspace = true, features = ["test-util", "macros"] }
+assert_cmd = "2"
+predicates = "3"
 
 [lints]
 workspace = true