# helexa-acp.example.toml — example configuration
#
# Copy to $XDG_CONFIG_HOME/helexa-acp/config.toml (typically
# ~/.config/helexa-acp/config.toml) and adjust for your environment.
#
# helexa-acp is the ACP (Agent Client Protocol) bridge that connects
# editors like Zed to multiple LLM endpoints. Each endpoint speaks a
# specific wire format (openai-chat, openai-responses, or
# anthropic-messages); helexa-acp picks the right provider at runtime
# based on the `wire_api` field.
#
# Selecting a model from the editor follows the `endpoint:model`
# syntax — e.g. `openrouter:anthropic/claude-opus-4` routes the
# request to the `openrouter` endpoint with model
# `anthropic/claude-opus-4`. A bare `<model>` (no colon) falls
# through to whichever endpoint is named in `default_endpoint`.

default_endpoint = "helexa"

# Optional: override the built-in system prompt with a file of your own.
# When unset, helexa-acp uses a concise coder prompt from src/prompt.rs.
# `{cwd}` in the file gets substituted with the session's working
# directory at request time.
# system_prompt_path = "/home/me/.config/helexa-acp/system-prompt.md"

# ── helexa (cortex/neuron, self-hosted) ────────────────────────────
#
# The canonical default. Drives cortex's reverse-proxy / fleet
# gateway, which routes to whichever neuron has the model loaded.
# `openai-chat` works against any cortex deployment; for vision
# models or reasoning surface, switch to `openai-responses` (cortex
# 0.1.16+).

[[endpoints]]
name = "helexa"
base_url = "http://hanzalova.internal:31313/v1"
wire_api = "openai-chat"
default_model = "Qwen/Qwen3.6-27B"
max_tokens = 8192
# Compaction kicks in when the rolling history grows past this token
# budget. Set to your model's context window. Disable by removing
# the field entirely.
context_window = 32768

# ── OpenRouter (proxy for OpenAI/Anthropic/Google/etc.) ────────────

[[endpoints]]
name = "openrouter"
base_url = "https://openrouter.ai/api/v1"
wire_api = "openai-chat"
api_key_env = "OPENROUTER_API_KEY"
default_model = "anthropic/claude-opus-4"

# ── OpenAI directly (Responses API) ────────────────────────────────
#
# Use `openai-responses` for the o-series and any model that
# benefits from the newer Responses API surface (web search,
# computer use, reasoning effort, etc.).

[[endpoints]]
name = "openai"
base_url = "https://api.openai.com/v1"
wire_api = "openai-responses"
api_key_env = "OPENAI_API_KEY"
default_model = "gpt-5"

# ── Anthropic directly ─────────────────────────────────────────────

[[endpoints]]
name = "anthropic"
base_url = "https://api.anthropic.com/v1"
wire_api = "anthropic-messages"
api_key_env = "ANTHROPIC_API_KEY"
default_model = "claude-opus-4"

# ── Local LM Studio / Ollama (compat mode) ─────────────────────────
#
# Most local-LLM servers expose OpenAI-compatible chat completions.
# Use `wire_api = "openai-chat"` and point at the local port.

# [[endpoints]]
# name = "lmstudio"
# base_url = "http://localhost:1234/v1"
# wire_api = "openai-chat"
# default_model = "auto"