gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-08-25 14:53:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
8bcdf1608f12a9be9e46023c241a17fb92a835c4
optimclaw/.env.example
T
ZeroTrustandGitHub 1b59eb6b39 feat: Reuse Codex CLI OAuth tokens for ChatGPT backend LLM calls (#693) 
* feat: add Codex auth.json token reuse for LLM authentication

When LLM_USE_CODEX_AUTH=true, IronClaw reads the Codex CLI's auth.json
(default ~/.codex/auth.json) and extracts the API key or OAuth access
token. This lets IronClaw piggyback on a Codex login without
implementing its own OAuth flow.

New env vars:
  - LLM_USE_CODEX_AUTH: enable Codex auth fallback (default: false)
  - CODEX_AUTH_PATH: override path to auth.json

* fix: handle ChatGPT auth mode correctly

Switch base_url to chatgpt.com/backend-api/codex when auth.json
contains ChatGPT OAuth tokens. The access_token is a JWT that only
works against the private ChatGPT backend, not the public OpenAI API.

Refactored codex_auth.rs to return CodexCredentials (token +
is_chatgpt_mode) instead of just a string key.

* fix: Codex auth takes highest priority over secrets store

When LLM_USE_CODEX_AUTH=true, Codex credentials are now loaded before
checking env vars or the secrets store overlay. Previously the secrets
store key (injected during onboarding) would shadow the Codex token.

* feat: Responses API provider for ChatGPT backend

- New CodexChatGptProvider speaks the Responses API protocol
- Auto-detects model from /models endpoint (gpt-4o -> gpt-5.2-codex)
- Adds store=false (required by ChatGPT backend)
- Error handling with timeout for HTTP 400 responses
- Message format translation: Chat Completions -> Responses API
- SSE response parsing for text, tool calls, and usage stats
- 7 unit tests for message conversion and SSE parsing

* fix: SSE parser uses item_id instead of call_id for tool call deltas

The Responses API sends function_call_arguments.delta events with
item_id (e.g. fc_...) not call_id (e.g. call_...). The parser now
keys pending tool calls by item_id from output_item.added and
tracks call_id separately for result matching.

* fix: strip empty string values from tool call arguments

gpt-5.2-codex fills optional tool parameters with empty strings
(e.g. timestamp: ""), which IronClaw's tool validation rejects.
Strip them before passing to tool execution.

* fix: prevent apiKey mode fallback to ChatGPT token

When auth_mode is explicitly 'apiKey' but the key is missing/empty,
do not fall through to check for a ChatGPT access_token. This prevents
returning credentials with is_chatgpt_mode: true and routing to the
wrong LLM provider.

* refactor: reuse single reqwest::Client across model discovery and LLM calls

Create Client once in with_auto_model, pass &Client to
fetch_default_model, and move it into the provider struct.
Eliminates the redundant Client::new() that wasted a connection pool.

* fix: bump client_version to 1.0.0 to unlock gpt-5.3-codex and gpt-5.4

The /models endpoint gates newer models behind client_version.
Version 0.1.0 only returns up to gpt-5.2-codex, while 1.0.0+
also returns gpt-5.3-codex and gpt-5.4.

* feat: user-configured LLM_MODEL takes priority over auto-detection

Fetch the full model list from /models endpoint. If LLM_MODEL is set,
validate it against the supported list and warn with available models
if not found. If LLM_MODEL is not set, auto-detect the highest-priority
model. Also bumps client_version to 1.0.0 to unlock gpt-5.3/5.4.

* fix: add 10s timeout to model discovery HTTP request

Prevents startup from blocking indefinitely if chatgpt.com
is slow or unreachable. Uses reqwest per-request timeout.

* docs: add private API warning for ChatGPT backend endpoint

The chatgpt.com/backend-api/codex endpoint is private and
undocumented. Add warning in module docs and a runtime log
on first use to inform users of potential ToS implications.

* feat: implement OAuth 401 token refresh for Codex ChatGPT provider

On HTTP 401, if a refresh_token is available, the provider now
automatically refreshes the access token via auth.openai.com/oauth/token
(same protocol as Codex CLI) and retries the request once. Refreshed
tokens are persisted back to auth.json.

Changes:
- codex_auth: read refresh_token, add refresh_access_token() and
  persist_refreshed_tokens()
- codex_chatgpt: RwLock for api_key, 401 detection + retry in
  send_request, send_http_request helper
- config/llm: thread refresh_token/auth_path through RegistryProviderConfig
- llm/mod: pass refresh params to with_auto_model

* refactor: lazy model detection via OnceCell, remove block_in_place

Model is no longer resolved during provider construction. Instead,
resolve_model() uses tokio::sync::OnceCell to lazily fetch from
/models on the first LLM call. This eliminates the block_in_place
+ block_on workaround in create_codex_chatgpt_from_registry.

- with_auto_model (async) -> with_lazy_model (sync constructor)
- resolve_model() added with OnceCell-based lazy init
- build_request_body takes model as parameter
- model_name() returns resolved or configured_model as fallback

* feat: support multimodal content (images) in Codex ChatGPT provider

message_to_input_items now checks content_parts for user messages.
ContentPart::Text maps to input_text and ContentPart::ImageUrl maps
to input_image, matching the Responses API format used by Codex CLI.
Falls back to plain text when content_parts is empty.

Also updates client_version to 0.111.0 for /models endpoint.

Adds test: test_message_conversion_user_with_image

* refactor: move codex_auth module from src/ to src/llm/

codex_auth is only used by the LLM layer (codex_chatgpt provider
and config/llm). Moving it under src/llm/ reflects its actual scope.

- Remove pub mod codex_auth from lib.rs
- Add pub mod codex_auth to llm/mod.rs
- Update imports: super::codex_auth, crate::llm::codex_auth

* Fix codex provider style issues

* Use SecretString throughout codex auth refresh flow

* Use SecretString for codex access tokens

* Reuse provider client for codex token refresh

* Stream Codex SSE responses incrementally

* Fix Windows clippy and SQLite test linkage

* Trigger checks after regression skip label

* Tighten codex auth module handling
2026-03-16 07:43:45 +00:00

190 lines
7.6 KiB
Bash
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Database Configuration
DATABASE_URL=postgres://localhost/ironclaw
DATABASE_POOL_SIZE=10
# LLM Provider
# LLM_BACKEND=nearai # default
# Possible values: nearai, ollama, openai_compatible, openai, anthropic, tinfoil
# LLM_REQUEST_TIMEOUT_SECS=120 # Increase for local LLMs (Ollama, vLLM, LM Studio)
# === Anthropic Direct ===
# Two auth modes:
# 1. API key: Set ANTHROPIC_API_KEY (from console.anthropic.com/settings/keys)
# 2. OAuth token: Set ANTHROPIC_OAUTH_TOKEN (from `claude login`)
# OAuth tokens use Authorization: Bearer instead of x-api-key header.
# ANTHROPIC_API_KEY=sk-ant-...
# ANTHROPIC_OAUTH_TOKEN=sk-ant-oat01-... # from `claude login` credentials
# ANTHROPIC_MODEL=claude-sonnet-4-20250514
# === OpenAI Direct ===
# OPENAI_API_KEY=sk-...
# Reuse Codex CLI auth.json instead of setting OPENAI_API_KEY manually.
# Works with both OpenAI API-key mode and Codex ChatGPT OAuth mode.
# In ChatGPT mode this uses the private `chatgpt.com/backend-api/codex` endpoint.
# LLM_USE_CODEX_AUTH=true
# CODEX_AUTH_PATH=~/.codex/auth.json
# === NEAR AI (Chat Completions API) ===
# Two auth modes:
# 1. Session token (default): Uses browser OAuth (GitHub/Google) on first run.
# Session token stored in ~/.ironclaw/session.json automatically.
# Base URL defaults to https://private.near.ai
# 2. API key: Set NEARAI_API_KEY to use API key auth from cloud.near.ai.
# Base URL defaults to https://cloud-api.near.ai
NEARAI_MODEL=zai-org/GLM-5-FP8
NEARAI_BASE_URL=https://private.near.ai
NEARAI_AUTH_URL=https://private.near.ai
# NEARAI_SESSION_TOKEN=sess_... # hosting providers: set this
# NEARAI_SESSION_PATH=~/.ironclaw/session.json # optional, default shown
# NEARAI_API_KEY=... # API key from cloud.near.ai
# Local LLM Providers (Ollama, LM Studio, vLLM, LiteLLM)
# === Ollama ===
# OLLAMA_MODEL=llama3.2
# LLM_BACKEND=ollama
# OLLAMA_BASE_URL=http://localhost:11434 # default
# === OpenAI-compatible (LM Studio, vLLM, Anything-LLM) ===
# LLM_MODEL=llama-3.2-3b-instruct-q4_K_M
# LLM_BACKEND=openai_compatible
# LLM_BASE_URL=http://localhost:1234/v1
# LLM_API_KEY=sk-... # optional for local servers
# Custom HTTP headers for OpenAI-compatible providers
# Format: comma-separated key:value pairs
# LLM_EXTRA_HEADERS=HTTP-Referer:https://github.com/nearai/ironclaw,X-Title:ironclaw
# === OpenRouter (300+ models via OpenAI-compatible) ===
# LLM_MODEL=anthropic/claude-sonnet-4 # see openrouter.ai/models for IDs
# LLM_BACKEND=openai_compatible
# LLM_BASE_URL=https://openrouter.ai/api/v1
# LLM_API_KEY=sk-or-...
# LLM_EXTRA_HEADERS=HTTP-Referer:https://myapp.com,X-Title:MyApp
# === Together AI (via OpenAI-compatible) ===
# LLM_MODEL=meta-llama/Llama-3.3-70B-Instruct-Turbo
# LLM_BACKEND=openai_compatible
# LLM_BASE_URL=https://api.together.xyz/v1
# LLM_API_KEY=...
# === Fireworks AI (via OpenAI-compatible) ===
# LLM_MODEL=accounts/fireworks/models/llama4-maverick-instruct-basic
# LLM_BACKEND=openai_compatible
# LLM_BASE_URL=https://api.fireworks.ai/inference/v1
# LLM_API_KEY=fw_...
# === MiniMax ===
# LLM_BACKEND=minimax
# MINIMAX_API_KEY=...
# MINIMAX_MODEL=MiniMax-M2.5
# MINIMAX_BASE_URL=https://api.minimax.io/v1 # default (global); use https://api.minimaxi.com/v1 for China
# === Anthropic Direct ===
# LLM_BACKEND=anthropic
# ANTHROPIC_MODEL=claude-sonnet-4-6
# ANTHROPIC_API_KEY=sk-ant-...
# ANTHROPIC_BASE_URL=https://api.anthropic.com # default
# Prompt cache retention — controls Anthropic server-side prompt caching:
# none = disabled (no cache_control injected)
# short = 5-minute TTL, 1.25× (125%) write surcharge (default)
# long = 1-hour TTL, 2.0× (200%) write surcharge
# ANTHROPIC_CACHE_RETENTION=short
# For full provider setup guide see docs/LLM_PROVIDERS.md
# Channel Configuration
# CLI is always enabled
# Slack Bot (optional)
SLACK_BOT_TOKEN=xoxb-...
SLACK_APP_TOKEN=xapp-...
SLACK_SIGNING_SECRET=...
# Telegram Bot (optional)
TELEGRAM_BOT_TOKEN=...
# HTTP Webhook Server (optional)
HTTP_HOST=0.0.0.0
HTTP_PORT=8080
HTTP_WEBHOOK_SECRET=your-webhook-secret
# Webhook authentication uses HMAC-SHA256 signature verification.
# Callers must send an X-IronClaw-Signature header with format: sha256=<hex_digest>
# where the digest is HMAC-SHA256(HTTP_WEBHOOK_SECRET, raw_request_body) in lowercase hex.
#
# Example (bash):
# BODY='{"content":"hello"}'
# SIG=$(echo -n "$BODY" | openssl dgst -sha256 -hmac "$HTTP_WEBHOOK_SECRET" | cut -d' ' -f2)
# curl -X POST http://localhost:8080/webhook \
# -H "Content-Type: application/json" \
# -H "X-IronClaw-Signature: sha256=$SIG" \
# -d "$BODY"
#
# DEPRECATED: Passing "secret" in the JSON body still works but will be removed in a future release.
# Signal Channel (optional, requires signal-cli daemon --http)
# SIGNAL_HTTP_URL=http://127.0.0.1:8080
# SIGNAL_ACCOUNT=+1234567890
# SIGNAL_ALLOW_FROM=+1234567890,uuid:xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx # comma-separated, * for all, empty = deny/require pairing
# SIGNAL_ALLOW_FROM_GROUPS= # comma-separated group IDs, * for all, empty = deny all groups
# SIGNAL_DM_POLICY=pairing # open | allowlist | pairing
# SIGNAL_GROUP_POLICY=allowlist # allowlist | open | disabled
# SIGNAL_GROUP_ALLOW_FROM= # comma-separated, empty = inherit from ALLOW_FROM
# SIGNAL_IGNORE_ATTACHMENTS=false
# SIGNAL_IGNORE_STORIES=true
# Agent Settings
AGENT_NAME=ironclaw
AGENT_MAX_PARALLEL_JOBS=5
AGENT_JOB_TIMEOUT_SECS=3600
AGENT_STUCK_THRESHOLD_SECS=300
# Maximum tokens per job (0 = unlimited, also settable via settings.json agent.max_tokens_per_job)
# AGENT_MAX_TOKENS_PER_JOB=0
# Enable planning phase before tool execution (default: true)
AGENT_USE_PLANNING=true
# Self-repair settings
SELF_REPAIR_CHECK_INTERVAL_SECS=60
SELF_REPAIR_MAX_ATTEMPTS=3
# Heartbeat settings (proactive periodic execution)
# When enabled, reads HEARTBEAT.md checklist and reports findings
HEARTBEAT_ENABLED=false
HEARTBEAT_INTERVAL_SECS=1800
HEARTBEAT_NOTIFY_CHANNEL=cli
HEARTBEAT_NOTIFY_USER=default
# Memory hygiene settings (automatic cleanup of stale workspace documents)
# Runs on each heartbeat tick; identity files (IDENTITY.md, SOUL.md) are never deleted
# MEMORY_HYGIENE_ENABLED=true
# MEMORY_HYGIENE_DAILY_RETENTION_DAYS=30 # delete daily/ docs older than this many days
# MEMORY_HYGIENE_CONVERSATION_RETENTION_DAYS=7 # delete conversations/ docs older than this many days
# MEMORY_HYGIENE_CADENCE_HOURS=12 # minimum hours between cleanup passes
# Docker Sandbox
# SANDBOX_ENABLED=true
# SANDBOX_POLICY=readonly # readonly, workspace_write, or full_access
# SANDBOX_ALLOW_FULL_ACCESS=false # REQUIRED second opt-in for full_access policy.
# # FullAccess bypasses Docker entirely and runs
# # commands directly on the host. Without this
# # set to "true", full_access is downgraded to
# # workspace_write.
# SANDBOX_IMAGE=ironclaw-worker:latest
# SANDBOX_TIMEOUT_SECS=120
# SANDBOX_MEMORY_LIMIT_MB=2048
# Safety settings
SAFETY_MAX_OUTPUT_LENGTH=100000
SAFETY_INJECTION_CHECK_ENABLED=true
# Restart Feature (Docker containers only)
# Set IRONCLAW_IN_DOCKER=true in the container entrypoint to enable the restart feature.
# Without this, the restart tool and /restart command will be disabled.
# IRONCLAW_IN_DOCKER=false
# IRONCLAW_RESTART_DELAY=5 # default wait before exit (seconds, range: 1-30)
# IRONCLAW_MAX_FAILURES=10 # max consecutive failures before container exits
# Logging
RUST_LOG=ironclaw=debug,tower_http=debug
Reference in New Issue View Git Blame Copy Permalink