Files
optimclaw/src/cli/mod.rs
T
3da9810e87 feat(llm): Add OpenAI Codex (ChatGPT subscription) as LLM provider (#1461)
* feat(llm): add OpenAI Codex backend config and OAuth session manager

Add OpenAiCodex as a new LLM backend variant with config for auth
endpoint, API base URL, client ID, and session persistence path.

The session manager implements OpenAI's device code auth flow
(headless-friendly, no browser required on the server) with automatic
token refresh, following the same persistence pattern as the existing
NEAR AI session manager.

Closes #742

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(llm): add Responses API client and token-refreshing decorator

Native Responses API client for chatgpt.com/backend-api/codex/responses,
the endpoint that works with ChatGPT subscription tokens. Handles SSE
streaming, text completions, and tool call round-trips.

Token-refreshing decorator wraps the provider to pre-emptively refresh
OAuth tokens before API calls and retry once on auth failures. Reports
zero cost since billing is through subscription.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(llm): wire OpenAI Codex into provider factory, CLI, and setup wizard

Connect the new provider to the LLM factory, add openai_codex to the
CLI --backend flag, and add it as an option in the onboarding wizard.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(llm): address PR #744 review feedback (20 items)

Review fixes for the OpenAI Codex provider PR:

- Remove dead `generate_pkce()` code (device flow gets PKCE from server)
- Fix `refresh_tokens()` to use `.form()` instead of `.json()` per OAuth spec
- Inline codex dispatch into `build_provider_chain()` (single async function,
  no separate `assemble_provider_chain()` helper — matches main's pattern)
- Remove Clone from `OpenAiCodexSession`, restrict fields to `pub(crate)`
- Propagate HTTP client builder error instead of silent fallback
- Redact device code response body from debug log
- Change `set_model()` in TokenRefreshingProvider to delegate to inner
- Replace hardcoded `/tmp/` test path with `tempfile::tempdir()`
- Accept `request_timeout_secs` from config instead of hardcoded 300s
- Parse `Retry-After` header on 429 responses (matches nearai_chat.rs pattern)
- Reuse `normalize_schema_strict()` for Codex tool definitions
- Add warning log for dropped image attachments
- Add doc comments on `list_models()` and `include` field
- Add `OPENAI_CODEX_API_URL` to `.env.example`
- Fix codex error message in `create_llm_provider()` for clarity
- Revert unrelated `.worktrees` addition to `.gitignore`
- Update `src/llm/CLAUDE.md` with Codex provider docs

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address review feedback and harden OpenAI Codex provider (takeover #744)

Security:
- Add SSRF validation (validate_base_url) on OPENAI_CODEX_AUTH_URL and
  OPENAI_CODEX_API_URL, matching the pattern used by all other base URL
  configs (regression test for #1103 included)

Correctness:
- Add missing cache_write_multiplier() and cache_read_discount() trait
  delegation in TokenRefreshingProvider
- Cap device-code polling backoff at 60s to prevent unbounded interval
  growth on repeated 429 responses
- Default expires_in to 3600s when server returns 0, preventing
  immediately-expired sessions
- Fix pre-existing SseEvent::JobResult missing fallback_deliverable field
  in job_monitor.rs tests

Cleanup:
- Extract duplicated make_test_jwt() and test_codex_config() into shared
  codex_test_helpers module

Co-Authored-By: Sanjeev-S <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: address PR review feedback on OpenAI Codex provider (#1461)

- Login command now resolves OPENAI_CODEX_* env overrides even when
  LLM_BACKEND isn't set to openai_codex (Copilot review)
- Setup wizard "Keep current provider?" for codex no longer re-triggers
  device code login — mirrors Bedrock's keep-and-return pattern (Copilot)
- Revert provider init log from info back to debug (Copilot)
- Add warning log when token expires_in=0, before defaulting to 3600s
  (Gemini review)

Co-Authored-By: Sanjeev-S <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

---------

Co-authored-by: Sanjeev Suresh <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-03-20 08:14:20 -07:00

403 lines
14 KiB
Rust

//! CLI command handling.
//!
//! Provides subcommands for:
//! - Running the agent (`run`)
//! - Interactive onboarding wizard (`onboard`)
//! - Managing configuration (`config list`, `config get`, `config set`)
//! - Managing WASM tools (`tool install`, `tool list`, `tool remove`)
//! - Managing MCP servers (`mcp add`, `mcp auth`, `mcp list`, `mcp test`)
//! - Querying workspace memory (`memory search`, `memory read`, `memory write`)
//! - Managing routines (`routines list`, `routines create`, `routines edit`, ...)
//! - Managing OS service (`service install`, `service start`, `service stop`)
//! - Listing configured channels (`channels list`)
//! - Active health diagnostics (`doctor`)
//! - Viewing gateway logs (`logs`)
//! - Checking system health (`status`)
mod channels;
mod completion;
mod config;
mod doctor;
#[cfg(feature = "import")]
pub mod import;
mod logs;
mod mcp;
pub mod memory;
pub mod oauth_defaults;
mod pairing;
mod registry;
mod routines;
mod service;
mod skills;
pub mod status;
mod tool;
pub use channels::{ChannelsCommand, run_channels_command};
pub use completion::Completion;
pub use config::{ConfigCommand, run_config_command};
pub use doctor::run_doctor_command;
#[cfg(feature = "import")]
pub use import::{ImportCommand, run_import_command};
pub use logs::{LogsCommand, run_logs_command};
pub use mcp::{McpCommand, run_mcp_command};
pub use memory::MemoryCommand;
pub use memory::run_memory_command_with_db;
pub use pairing::{PairingCommand, run_pairing_command, run_pairing_command_with_store};
pub use registry::{RegistryCommand, run_registry_command};
pub use routines::{RoutinesCommand, run_routines_command};
pub use service::{ServiceCommand, run_service_command};
pub use skills::{SkillsCommand, run_skills_command};
pub use status::run_status_command;
pub use tool::{ToolCommand, run_tool_command};
use std::sync::Arc;
use clap::{ColorChoice, Parser, Subcommand};
#[derive(Parser, Debug)]
#[command(name = "ironclaw")]
#[command(
about = "Secure personal AI assistant that protects your data and expands its capabilities"
)]
#[command(
long_about = "IronClaw is a secure AI assistant. Use 'ironclaw <subcommand> --help' for details.\nExamples:\n ironclaw run # Start the agent\n ironclaw config list # List configs"
)]
#[command(version)]
#[command(color = ColorChoice::Auto)] // Enable auto-color for help (if the terminal supports it)
pub struct Cli {
#[command(subcommand)]
pub command: Option<Command>,
/// Run in interactive CLI mode only (disable other channels)
#[arg(long, global = true)]
pub cli_only: bool,
/// Skip database connection (for testing)
#[arg(long, global = true)]
pub no_db: bool,
/// Single message mode - send one message and exit
#[arg(short, long, global = true)]
pub message: Option<String>,
/// Configuration file path (optional, uses env vars by default)
#[arg(short, long, global = true)]
pub config: Option<std::path::PathBuf>,
/// Skip first-run onboarding check
#[arg(long, global = true)]
pub no_onboard: bool,
}
#[derive(Subcommand, Debug)]
pub enum Command {
/// Run the agent (default if no subcommand given)
#[command(
about = "Run the AI agent",
long_about = "Starts the IronClaw agent in default mode.\nExample: ironclaw run"
)]
Run,
/// Interactive onboarding wizard
#[command(
about = "Run interactive setup wizard",
long_about = "Guides through initial configuration.\nExamples:\n ironclaw onboard --skip-auth # Skip auth step\n ironclaw onboard --channels-only # Reconfigure channels\n ironclaw onboard --provider-only # Change LLM provider and model"
)]
Onboard {
/// Skip authentication (use existing session)
#[arg(long)]
skip_auth: bool,
/// Reconfigure channels only
#[arg(long, conflicts_with_all = ["provider_only", "quick"])]
channels_only: bool,
/// Reconfigure LLM provider and model only
#[arg(long, conflicts_with_all = ["channels_only", "quick"])]
provider_only: bool,
/// Quick setup: auto-defaults everything except LLM provider and model
#[arg(long, conflicts_with_all = ["channels_only", "provider_only"])]
quick: bool,
},
/// Manage configuration settings
#[command(
subcommand,
about = "Manage app configs",
long_about = "Commands for listing, getting, and setting configurations.\nExample: ironclaw config list"
)]
Config(ConfigCommand),
/// Manage WASM tools
#[command(
subcommand,
about = "Manage WASM tools",
long_about = "Install, list, or remove WASM-based tools.\nExample: ironclaw tool install mytool.wasm"
)]
Tool(ToolCommand),
/// Browse and install extensions from the registry
#[command(
subcommand,
about = "Browse/install extensions",
long_about = "Interact with extension registry.\nExample: ironclaw registry list"
)]
Registry(RegistryCommand),
/// List and inspect messaging channels
#[command(
subcommand,
about = "Manage channels",
long_about = "List configured messaging channels.\nExamples:\n ironclaw channels list\n ironclaw channels list --verbose\n ironclaw channels list --json"
)]
Channels(ChannelsCommand),
/// Manage routines (scheduled, event-driven, webhook, manual)
#[command(
subcommand,
alias = "cron",
about = "Manage routines",
long_about = "List, create, edit, enable/disable, delete, and view history of routines.\nExamples:\n ironclaw routines list\n ironclaw routines create --name daily-digest --schedule '0 0 9 * * *' --prompt 'Summarize today'"
)]
Routines(RoutinesCommand),
/// Manage MCP servers (hosted tool providers)
#[command(
subcommand,
about = "Manage MCP servers",
long_about = "Add, auth, list, or test MCP servers.\nExample: ironclaw mcp add notion https://mcp.notion.com"
)]
Mcp(Box<McpCommand>),
/// Query and manage workspace memory
#[command(
subcommand,
about = "Manage workspace memory",
long_about = "Search, read, or write to memory.\nExample: ironclaw memory search 'query'"
)]
Memory(MemoryCommand),
/// DM pairing (approve inbound requests from unknown senders)
#[command(
subcommand,
about = "Manage DM pairing",
long_about = "Approve or manage pairing requests.\nExamples:\n ironclaw pairing list telegram\n ironclaw pairing approve telegram ABC12345"
)]
Pairing(PairingCommand),
/// Manage OS service (launchd / systemd)
#[command(
subcommand,
about = "Manage OS service",
long_about = "Install, start, or stop service.\nExample: ironclaw service install"
)]
Service(ServiceCommand),
/// Manage SKILL.md-based skills
#[command(
subcommand,
about = "Manage skills",
long_about = "List, search, and inspect SKILL.md-based skills.\nExamples:\n ironclaw skills list\n ironclaw skills search 'writing'\n ironclaw skills info my-skill"
)]
Skills(SkillsCommand),
/// Probe external dependencies and validate configuration
#[command(
about = "Run diagnostics",
long_about = "Checks dependencies and config validity.\nExample: ironclaw doctor"
)]
Doctor,
/// View and manage gateway logs
#[command(
about = "View and manage gateway logs",
long_about = "Tail gateway logs, stream live output, or adjust log level.\nExamples:\n ironclaw logs # Show last 200 lines from gateway.log\n ironclaw logs --follow # Stream live logs via SSE\n ironclaw logs --level # Show current log level\n ironclaw logs --level debug # Set log level to debug"
)]
Logs(LogsCommand),
/// Show system health and diagnostics
#[command(
about = "Show system status",
long_about = "Displays health and diagnostics info.\nExample: ironclaw status"
)]
Status,
/// Generate shell completion scripts
#[command(
about = "Generate completions",
long_about = "Generates shell completion scripts.\nExample: ironclaw completion --shell bash > ironclaw.bash"
)]
Completion(Completion),
/// Import data from other AI systems
#[cfg(feature = "import")]
#[command(
subcommand,
about = "Import from other AI systems",
long_about = "Migrate data from other AI assistants like OpenClaw.\nExample: ironclaw import openclaw"
)]
Import(ImportCommand),
/// Authenticate with a provider (re-login)
#[command(
about = "Authenticate with a provider",
long_about = "Re-authenticate with an LLM provider.\nExample: ironclaw login --openai-codex"
)]
Login {
/// Authenticate with OpenAI Codex (ChatGPT subscription)
#[arg(long)]
openai_codex: bool,
},
/// Run as a sandboxed worker inside a Docker container (internal use).
/// This is invoked automatically by the orchestrator, not by users directly.
#[command(hide = true)]
Worker {
/// Job ID to execute.
#[arg(long)]
job_id: uuid::Uuid,
/// URL of the orchestrator's internal API.
#[arg(long, default_value = "http://host.docker.internal:50051")]
orchestrator_url: String,
/// Maximum iterations before stopping.
#[arg(long, default_value = "50")]
max_iterations: u32,
},
/// Run as a Claude Code bridge inside a Docker container (internal use).
/// Spawns the `claude` CLI and streams output back to the orchestrator.
#[command(hide = true)]
ClaudeBridge {
/// Job ID to execute.
#[arg(long)]
job_id: uuid::Uuid,
/// URL of the orchestrator's internal API.
#[arg(long, default_value = "http://host.docker.internal:50051")]
orchestrator_url: String,
/// Maximum agentic turns for Claude Code.
#[arg(long, default_value = "50")]
max_turns: u32,
/// Claude model to use (e.g. "sonnet", "opus").
#[arg(long, default_value = "sonnet")]
model: String,
},
}
impl Cli {
/// Check if we should run the agent (default behavior or explicit `run` command).
pub fn should_run_agent(&self) -> bool {
matches!(self.command, None | Some(Command::Run))
}
}
/// Initialize a secrets store from environment config.
///
/// Shared helper for CLI subcommands (`mcp auth`, `tool auth`, etc.) that need
/// access to encrypted secrets without spinning up the full AppBuilder.
pub async fn init_secrets_store()
-> anyhow::Result<Arc<dyn crate::secrets::SecretsStore + Send + Sync>> {
let config = crate::config::Config::from_env().await?;
let master_key = config.secrets.master_key().ok_or_else(|| {
anyhow::anyhow!(
"SECRETS_MASTER_KEY not set. Run 'ironclaw onboard' first or set it in .env"
)
})?;
let crypto = Arc::new(crate::secrets::SecretsCrypto::new(master_key.clone())?);
Ok(crate::db::create_secrets_store(&config.database, crypto).await?)
}
/// Run the Routines CLI subcommand.
pub async fn run_routines_cli(
routines_cmd: &RoutinesCommand,
config_path: Option<&std::path::Path>,
) -> anyhow::Result<()> {
let config = crate::config::Config::from_env_with_toml(config_path)
.await
.map_err(|e| anyhow::anyhow!("{e:#}"))?;
let db: Arc<dyn crate::db::Database> = crate::db::connect_from_config(&config.database)
.await
.map_err(|e| anyhow::anyhow!("{e:#}"))?;
let user_id = std::env::var("GATEWAY_USER_ID").unwrap_or_else(|_| "default".to_string());
run_routines_command(routines_cmd.clone(), db, &user_id).await
}
/// Run the Memory CLI subcommand.
pub async fn run_memory_command(mem_cmd: &MemoryCommand) -> anyhow::Result<()> {
let config = crate::config::Config::from_env()
.await
.map_err(|e| anyhow::anyhow!("{}", e))?;
let session = crate::llm::create_session_manager(config.llm.session.clone()).await;
let embeddings = config
.embeddings
.create_provider(&config.llm.nearai.base_url, session);
let db: Arc<dyn crate::db::Database> = crate::db::connect_from_config(&config.database)
.await
.map_err(|e| anyhow::anyhow!("{}", e))?;
let cache_config = crate::workspace::EmbeddingCacheConfig {
max_entries: config.embeddings.cache_size,
};
run_memory_command_with_db(mem_cmd.clone(), db, embeddings, cache_config).await
}
#[cfg(test)]
mod tests {
use super::*;
use clap::CommandFactory;
use insta::assert_snapshot;
#[test]
fn test_version() {
let cmd = Cli::command();
assert_eq!(
cmd.get_version().unwrap_or("unknown"),
env!("CARGO_PKG_VERSION")
);
}
#[test]
#[cfg(feature = "import")]
fn test_help_output() {
let mut cmd = Cli::command();
let help = cmd.render_help().to_string();
assert_snapshot!(help);
}
#[test]
#[cfg(not(feature = "import"))]
fn test_help_output_without_import() {
let mut cmd = Cli::command();
let help = cmd.render_help().to_string();
assert_snapshot!(help);
}
#[test]
#[cfg(feature = "import")]
fn test_long_help_output() {
let mut cmd = Cli::command();
let help = cmd.render_long_help().to_string();
assert_snapshot!(help);
}
#[test]
#[cfg(not(feature = "import"))]
fn test_long_help_output_without_import() {
let mut cmd = Cli::command();
let help = cmd.render_long_help().to_string();
assert_snapshot!(help);
}
}