anveesa 0.6.0 → 0.7.1

package/Cargo.lock

@@ -60,9 +60,10 @@ dependencies = [
 
 [[package]]
 name = "anveesa"
-version = "0.6.0"
+version = "0.7.1"
 dependencies = [
  "anyhow",
+ "axum",
  "base64",
  "clap",
  "crossterm",
@@ -73,6 +74,7 @@ dependencies = [
  "serde",
  "serde_json",
  "tokio",
+ "tokio-stream",
  "toml",
 ]
 
@@ -82,12 +84,78 @@ version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
+[[package]]
+name = "async-trait"
+version = "0.1.89"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9035ad2d096bed7955a320ee7e2230574d28fd3c3a0f186cbea1ff3c7eed5dbb"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "atomic-waker"
 version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
 
+[[package]]
+name = "axum"
+version = "0.7.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "edca88bc138befd0323b20752846e6587272d3b03b0343c8ea28a6f819e6e71f"
+dependencies = [
+ "async-trait",
+ "axum-core",
+ "bytes",
+ "futures-util",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "itoa",
+ "matchit",
+ "memchr",
+ "mime",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustversion",
+ "serde",
+ "serde_json",
+ "serde_path_to_error",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tower",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "axum-core"
+version = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09f2bd6146b97ae3359fa0cc6d6b376d9539582c7b4220f041a33ec24c226199"
+dependencies = [
+ "async-trait",
+ "bytes",
+ "futures-util",
+ "http",
+ "http-body",
+ "http-body-util",
+ "mime",
+ "pin-project-lite",
+ "rustversion",
+ "sync_wrapper",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
 [[package]]
 name = "base64"
 version = "0.22.1"
@@ -518,6 +586,12 @@ version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
 
+[[package]]
+name = "httpdate"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
+
 [[package]]
 name = "hyper"
 version = "1.9.0"
@@ -531,6 +605,7 @@ dependencies = [
  "http",
  "http-body",
  "httparse",
+ "httpdate",
  "itoa",
  "pin-project-lite",
  "smallvec",
@@ -811,12 +886,24 @@ version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154"
 
+[[package]]
+name = "matchit"
+version = "0.7.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e7465ac9959cc2b1404e8e2367b43684a6d13790fe23056cc8c6c5a6b7bcb94"
+
 [[package]]
 name = "memchr"
 version = "2.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
 
+[[package]]
+name = "mime"
+version = "0.3.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
+
 [[package]]
 name = "mio"
 version = "1.2.0"
@@ -1274,6 +1361,17 @@ dependencies = [
  "zmij",
 ]
 
+[[package]]
+name = "serde_path_to_error"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10a9ff822e371bb5403e391ecd83e182e0e77ba7f6fe0160b795797109d1b457"
+dependencies = [
+ "itoa",
+ "serde",
+ "serde_core",
+]
+
 [[package]]
 name = "serde_spanned"
 version = "0.6.9"
@@ -1513,6 +1611,18 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "tokio-stream"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32da49809aab5c3bc678af03902d4ccddea2a87d028d86392a4b1560c6906c70"
+dependencies = [
+ "futures-core",
+ "pin-project-lite",
+ "tokio",
+ "tokio-util",
+]
+
 [[package]]
 name = "tokio-util"
 version = "0.7.18"
@@ -1580,6 +1690,7 @@ dependencies = [
  "tokio",
  "tower-layer",
  "tower-service",
+ "tracing",
 ]
 
 [[package]]
@@ -1618,6 +1729,7 @@ version = "0.1.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "63e71662fa4b2a2c3a26f570f037eb95bb1f85397f3cd8076caed2f026a6d100"
 dependencies = [
+ "log",
  "pin-project-lite",
  "tracing-core",
 ]

package/Cargo.toml

@@ -1,8 +1,17 @@
 [package]
 name = "anveesa"
-version = "0.6.0"
+version = "0.7.1"
 edition = "2024"
 default-run = "anveesa"
+description = "Multi-provider terminal AI assistant — TUI, web UI, and one-shot mode backed by any OpenAI-compatible API"
+license = "MIT"
+repository = "https://github.com/PandhuWibowo/anveesa-cli"
+homepage = "https://github.com/PandhuWibowo/anveesa-cli"
+documentation = "https://github.com/PandhuWibowo/anveesa-cli#readme"
+keywords = ["ai", "cli", "llm", "assistant", "tui"]
+categories = ["command-line-utilities", "development-tools"]
+readme = "README.md"
+exclude = ["npm/", ".github/", "src/web_ui.html"]
 
 [dependencies]
 base64 = "0.22"
@@ -15,5 +24,7 @@ reqwest = { version = "0.12", default-features = false, features = ["json", "rus
 rustyline = "14"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
-tokio = { version = "1.0", features = ["macros", "rt-multi-thread", "process", "time", "sync", "io-util", "signal"] }
+tokio = { version = "1.0", features = ["macros", "rt-multi-thread", "process", "time", "sync", "io-util", "signal", "net"] }
+tokio-stream = { version = "0.1", features = ["sync"] }
 toml = "0.8"
+axum = { version = "0.7", features = ["json"] }

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Pandhu Wibowo
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -1,207 +1,232 @@
 # anveesa
 
-A fast, terminal-native AI coding assistant. One command — interactive TUI or one-shot prompts — backed by any OpenAI-compatible provider.
+A fast, multi-provider terminal AI coding assistant — interactive TUI, one-shot prompts, or web UI — backed by any OpenAI-compatible API.
 
-```
-npm install -g anveesa
-anveesa
-```
+[![CI](https://github.com/PandhuWibowo/anveesa-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/PandhuWibowo/anveesa-cli/actions/workflows/ci.yml)
+[![Crates.io](https://img.shields.io/crates/v/anveesa.svg)](https://crates.io/crates/anveesa)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
 ---
 
-## Features
+## What it is
 
-- **Full TUI** — streaming output, diff previews on file edits, cost tracking, plan display
-- **28 built-in tools** — file ops, git, web search, deep-fetch, screenshot, notes, run commands
-- **Multi-provider** — Claude, GPT-4o, Gemini, DeepSeek, local Ollama, any OpenAI-compatible API
-- **Model routing** — `fast_model` for read-only tool rounds, main model for synthesis
-- **Parallel tools** — read-only tool calls run concurrently; write tools stay sequential for approval
-- **Approval flow** — every write/run tool shows a full diff preview; approve once, for the turn, or deny
-- **Multi-image paste** — ⌘V (macOS) / Ctrl+V to queue multiple clipboard images per turn
-- **Project memory** — `.anveesa.md` in your repo root is auto-injected into every session
-- **Path sandboxing** — write tools blocked outside the git root by default
-- **Conversation search** — Ctrl+R to search through all messages
+Anveesa is a multi-provider terminal AI assistant that works with any OpenAI-compatible API — including OpenAI, Anthropic (via proxy), DeepSeek, Groq, Gemini, OpenRouter, local Ollama, and more. It ships a full TUI with streaming output, diff previews, cost tracking, and plan display, plus a lightweight web UI for browser-based access. You get 28 built-in tools covering file ops, git, web search, screenshot capture, and command execution — all with an approval flow that shows a full diff before any write.
 
 ---
 
 ## Install
 
+**Cargo (recommended):**
+
+```bash
+cargo install anveesa
+```
+
+**Pre-built binaries:**
+
+Download from [GitHub Releases](https://github.com/PandhuWibowo/anveesa-cli/releases) for your platform (macOS, Linux x86_64/arm64).
+
+**npm wrapper:**
+
 ```bash
-# npm (recommended — downloads prebuilt binary)
 npm install -g anveesa
+```
+
+**Build from source:**
 
-# Cargo (builds from source)
-cargo install --path .
+```bash
+git clone https://github.com/PandhuWibowo/anveesa-cli
+cd anveesa-cli
+cargo build --release
+./target/release/anveesa
 ```
 
+Requires Rust 1.85+ (2024 edition).
+
 ---
 
 ## Quick start
 
 ```bash
-# 1. Initialize config
+# 1. Initialize config at ~/.config/anveesa/config.toml
 anveesa config init
 
-# 2. Set your API key
-export ANTHROPIC_API_KEY="sk-ant-..."
+# 2. Edit config to set your provider and API key
+#    (see sample below)
+
+# 3. Set your API key in the environment
 export OPENAI_API_KEY="sk-..."
 
-# 3. Launch the TUI
+# 4. Launch the TUI
 anveesa
 
-# 4. One-shot prompt
+# 5. One-shot prompt
 anveesa "explain the auth middleware in this repo"
 
-# 5. Specific provider/model
-anveesa --provider anthropic --model claude-sonnet-4-6 "refactor src/auth.ts"
+# 6. Specific provider/model
+anveesa --provider deepseek --model deepseek-chat "refactor src/auth.rs"
 ```
 
----
-
-## Configuration
-
-Config lives at `~/.config/anveesa/config.toml`.
+**Sample config snippet** (`~/.config/anveesa/config.toml`):
 
 ```toml
-default_provider = "anthropic"
-
-[providers.anthropic]
-api_base      = "https://api.anthropic.com/v1"
-api_key_env   = "ANTHROPIC_API_KEY"
-default_model = "claude-sonnet-4-6"
-fast_model    = "claude-haiku-4-5-20251001"  # cheap model for read-only tool rounds
-prompt_cache  = true
+default_provider = "openai"
 
 [providers.openai]
-api_base      = "https://api.openai.com/v1"
-api_key_env   = "OPENAI_API_KEY"
+kind = "openai-compatible"
+base_url = "https://api.openai.com/v1"
+api_key_env = "OPENAI_API_KEY"
 default_model = "gpt-4o"
-fast_model    = "gpt-4o-mini"
+fast_model = "gpt-4o-mini"
+
+[providers.deepseek]
+kind = "openai-compatible"
+base_url = "https://api.deepseek.com"
+api_key_env = "DEEPSEEK_API_KEY"
+default_model = "deepseek-chat"
 
-[providers.local]
-api_base      = "http://localhost:11434/v1"
+[providers.ollama]
+kind = "openai-compatible"
+base_url = "http://localhost:11434/v1"
 default_model = "qwen2.5-coder:7b"
 ```
 
-### Project instructions
+---
 
-Drop `.anveesa.md` in your repo root — auto-injected every session:
+## Providers
+
+| Provider | kind | Notes |
+|---|---|---|
+| OpenAI | `openai-compatible` | GPT-4o, o1, o3 |
+| Anthropic (via proxy) | `openai-compatible` | Claude 3.5/3.7 via OpenRouter or direct |
+| DeepSeek | `openai-compatible` | deepseek-chat, deepseek-reasoner |
+| Groq | `openai-compatible` | Ultra-fast inference |
+| Google Gemini | `openai-compatible` | gemini-1.5-pro/flash |
+| OpenRouter | `openai-compatible` | 200+ models via one API |
+| Mistral | `openai-compatible` | mistral-large, codestral |
+| xAI (Grok) | `openai-compatible` | grok-2 |
+| Together AI | `openai-compatible` | Open-source models |
+| Fireworks AI | `openai-compatible` | Fast open-source |
+| Cerebras | `openai-compatible` | High-throughput |
+| SambaNova | `openai-compatible` | Enterprise inference |
+| NVIDIA NIM | `openai-compatible` | GPU-backed cloud |
+| GitHub Models | `openai-compatible` | Free tier models |
+| Perplexity | `openai-compatible` | Web-grounded answers |
+| Ollama | `openai-compatible` | Local models |
+| LM Studio | `openai-compatible` | Local GUI + API |
+| vLLM | `openai-compatible` | Self-hosted inference |
+| LiteLLM | `openai-compatible` | Universal proxy |
+| LocalAI | `openai-compatible` | Self-hosted |
+| Claude Code | `command` | Runs `claude` CLI |
+| Codex CLI | `command` | Runs `codex` CLI |
+| GitHub Copilot | `command` | Runs `copilot` CLI |
 
-```markdown
-# My Project
+---
 
-Stack: React 18, TypeScript, Tailwind, Prisma, PostgreSQL
+## TUI commands
 
-Rules:
-- Use named exports only
-- Tests go in __tests__/ next to the source file
-- Run `pnpm test` before committing
-- DB migrations live in db/migrations/
-```
-
----
+| Command | Description |
+|---|---|
+| `/add <file>` | Inject a file into context (Aider-style) |
+| `/diff` | Show `git diff HEAD` |
+| `/commit [msg]` | Stage all + commit; omit msg to have AI generate one |
+| `/memory <note>` | Append a note to `.anveesa.md` |
+| `/clear` | Reset conversation and session |
+| `/undo` | Restore last file changed by AI |
+| `/compact` | Drop old turns to free context window |
+| `/copy` | Copy last response to clipboard |
+| `/export [path]` | Save conversation as Markdown |
+| `/model [name]` | Show or switch model |
+| `/provider [name]` | Show or switch provider |
+| `/status` | Token usage and cost summary |
+| `/search` | Search conversation (or Ctrl+R) |
+| `/help` | Show all shortcuts |
+| `/exit` | Quit |
 
-## TUI shortcuts
+**TUI keyboard shortcuts:**
 
 | Key | Action |
 |---|---|
 | Enter | Submit prompt |
 | Shift+Enter | Newline in input |
-| ↑ / ↓ | Navigate input history |
-| Tab | Complete `/command` or file path |
+| Tab | Complete `/command`, provider name, or file path |
 | Ctrl+R | Search conversation |
-| `[` / `]` | Navigate file diffs |
-| Enter (on diff) | Expand / collapse diff |
-| ⌘V / Ctrl+V | Paste image or text (repeat to queue multiple) |
-| j / k | Scroll (empty input) |
+| `[` / `]` | Navigate between file diffs and thinking blocks |
+| Enter (on diff) | Expand / collapse |
+| Ctrl+V / Cmd+V | Paste image or text |
+| j / k | Scroll (when input is empty) |
 | PageUp / PageDn | Scroll |
 | Ctrl+W | Delete word |
 | Ctrl+U | Clear line |
+| Ctrl+M | Toggle mouse capture (scroll vs. select mode) |
 | Ctrl+C | Cancel / quit |
 
 ---
 
-## Slash commands
-
-| Command | Description |
-|---|---|
-| `/help` | Show all shortcuts |
-| `/clear` | Reset conversation |
-| `/compact` | Drop old turns to free context |
-| `/search` | Search conversation (or Ctrl+R) |
-| `/undo` | Restore last AI-modified file |
-| `/copy` | Copy last response to clipboard |
-| `/export [path]` | Save as Markdown |
-| `/model [name]` | Switch model |
-| `/provider [name]` | Switch provider |
-| `/status` | Token and cost info |
-| `/exit` | Quit |
-
----
-
-## Tools
-
-**File ops:** `read_file` `write_file` `edit_file` `patch_file` `delete_file` `move_file` `copy_file` `create_dir` `list_dir` `find_files` `search_text`
-
-**Git:** `git_status` `git_diff` `git_log` `git_blame` `git_show` `git_commit` `git_stash` `git_branch`
-
-**Web:** `web_search` `fetch_url` `screenshot_url`
-
-**Notes:** `save_note` `read_notes` `search_notes` `delete_note`
-
-**Execution:** `run_command`
-
-### fetch_url modes
+## Web UI
 
+```bash
+anveesa web           # starts on http://localhost:8374
+anveesa web --port 8080
 ```
-fetch_url(url="...", mode="text")   # default — plain text, HTML stripped
-fetch_url(url="...", mode="raw")    # full HTML source
-fetch_url(url="...", mode="deep")   # HTML + all linked CSS (+ JS if include_js=true)
-```
-
-### screenshot_url
 
-```
-screenshot_url(url="https://localhost:3000", full_page=true)
-```
+The web UI provides a browser-based chat interface with the same provider/model selection as the TUI. Features:
 
-Requires Playwright: `npm install -g playwright && npx playwright install chromium`
+- Streaming responses with Markdown rendering
+- Multi-provider switching
+- Session history
+- Cost and token tracking
+- Mobile-friendly layout
 
 ---
 
-## Security
-
-- **Approval flow** — file writes and commands show a diff preview before running; `--yes` to auto-approve
-- **Path sandboxing** — writes outside the git root are refused
-- **Dangerous commands** — `rm -rf /`, pipe-to-shell, and similar patterns are hard-blocked
-- **Secret guard** — model is instructed never to expose API keys, `.env` files, or SSH keys
+## Key features
+
+- **Multi-provider** — 28 built-in providers; add any OpenAI-compatible endpoint in one config line
+- **Cost tracking** — per-turn and session cost displayed in the header; custom `pricing` override per provider
+- **Session persistence** — conversations auto-saved per working directory; resume where you left off
+- **Extended thinking** — enable Anthropic extended thinking with `extended_thinking = 10000` budget tokens
+- **Image attachments** — paste screenshots with Cmd+V / Ctrl+V; queue multiple images per turn
+- **MCP support** — connect Model Context Protocol servers for additional tools
+- **Aider-style /add** — inject files into context without leaving the TUI
+- **Auto-compact** — smart context compaction kicks in when the window fills up; AI summarises dropped turns
+- **Auto-commit helper** — `/commit` stages all changes and pre-fills the input with an AI-generated commit message
+- **Model routing** — `fast_model` for cheap read-only tool rounds; main model for final synthesis
+- **28 built-in tools** — file ops, git, web search, deep-fetch, screenshot, notes, run commands
+- **Approval flow** — every write/run tool shows a diff preview before executing
 
 ---
 
-## Environment variables
+## Config reference
 
-| Variable | Purpose |
-|---|---|
-| `ANTHROPIC_API_KEY` | Anthropic |
-| `OPENAI_API_KEY` | OpenAI |
-| `GEMINI_API_KEY` | Google Gemini |
-| `BRAVE_SEARCH_API_KEY` | Better web search |
-| `SERPER_API_KEY` | Alternative web search |
-| `ANVEESA_MAX_TOOL_ROUNDS` | Override tool round limit (default 32) |
+All fields of `OpenAiCompatibleProviderConfig`:
 
----
+| Field | Type | Default | Description |
+|---|---|---|---|
+| `base_url` | string | required | API base URL (e.g. `https://api.openai.com/v1`) |
+| `api_key` | string | — | Inline API key (prefer `api_key_env`) |
+| `api_key_env` | string | — | Environment variable holding the API key |
+| `default_model` | string | — | Model to use when none is specified |
+| `fast_model` | string | — | Lightweight model for read-only tool rounds |
+| `headers` | table | `{}` | Extra HTTP headers (e.g. for GitHub Models) |
+| `prompt_cache` | bool | — | Enable prompt caching (Anthropic cache_control markers) |
+| `max_tokens` | int | — | Upper bound on tokens generated per response |
+| `extended_thinking` | int | — | Enable Anthropic extended thinking; value = budget_tokens |
+| `pricing` | [f64; 4] | — | Custom pricing `[input, output, cache_read, cache_write]` per million tokens |
 
-## Build from source
+**Example with custom pricing:**
 
-```bash
-git clone https://github.com/PandhuWibowo/anveesa-cli
-cd anveesa-cli
-cargo build --release
-./target/release/anveesa
+```toml
+[providers.my-provider]
+kind = "openai-compatible"
+base_url = "https://my-llm-api.com/v1"
+api_key_env = "MY_API_KEY"
+default_model = "my-model-v1"
+pricing = [3.0, 15.0, 0.3, 3.75]
 ```
 
-Requires Rust 1.85+ (2024 edition).
-
 ---
 
-MIT License
+## License
+
+MIT — see [LICENSE](LICENSE).

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "anveesa",
-  "version": "0.6.0",
-  "description": "A terminal CLI that wraps AI providers (OpenAI-compatible APIs and local CLIs) into a single unified command",
+  "version": "0.7.1",
+  "description": "Multi-provider terminal AI assistant — TUI, web UI, and one-shot mode backed by any OpenAI-compatible API",
   "main": "bin/anveesa.js",
   "bin": {
     "anveesa": "bin/anveesa.js"
@@ -26,7 +26,12 @@
     "rust",
     "openai",
     "agent",
-    "copilot"
+    "copilot",
+    "tui",
+    "llm",
+    "deepseek",
+    "groq",
+    "anthropic"
   ],
   "license": "MIT",
   "engines": {

package/src/cli.rs

@@ -27,6 +27,18 @@ pub enum Command {
     Config(ConfigArgs),
     /// Manage saved interactive sessions.
     Sessions(SessionsArgs),
+    /// Launch a browser-based chat UI on localhost.
+    Web(WebArgs),
+}
+
+#[derive(Debug, Args)]
+pub struct WebArgs {
+    #[command(flatten)]
+    pub options: AskOptions,
+
+    /// Port to listen on (default 8374).
+    #[arg(long, default_value = "8374")]
+    pub port: u16,
 }
 
 #[derive(Debug, Args)]

package/src/config.rs

@@ -473,6 +473,16 @@ pub struct OpenAiCompatibleProviderConfig {
     /// truncated by the output limit (Anveesa continues truncated answers either way).
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub max_tokens: Option<u32>,
+
+    /// Enable Anthropic extended thinking. Value = budget_tokens (e.g. 10000).
+    /// Requires a Claude 3.7+ model and the anthropic-beta header.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub extended_thinking: Option<u32>,
+
+    /// Custom per-million-token pricing: [input, output, cache_read, cache_write].
+    /// Overrides the built-in model price table. Example: [3.0, 15.0, 0.3, 3.75]
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub pricing: Option<[f64; 4]>,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -512,6 +522,8 @@ fn insert_openai_provider(
             headers: BTreeMap::new(),
             prompt_cache: None,
             max_tokens: None,
+            extended_thinking: None,
+            pricing: None,
         }),
     );
 }