# Phase 39: Provider Registry
#
# Per-provider base_url, auth scheme, and default model. The gateway's
# /v1/chat dispatcher reads this file at boot to populate its provider
# table. Secrets (API keys) come from /etc/lakehouse/secrets.toml or
# environment variables — NEVER inline a key here.
#
# Adding a new provider:
#   1. New [[provider]] block with name, base_url, auth, default_model
#   2. Matching adapter at crates/aibridge/src/providers/<name>.rs
#      implementing the ProviderAdapter trait (chat + embed + unload)
#   3. Route arm in crates/gateway/src/v1/mod.rs matching on `name`
#   4. Model-prefix routing hint in resolve_provider() if the provider
#      uses an "<name>/..." model prefix (e.g. "openrouter/...")

[[provider]]
name = "ollama"
base_url = "http://localhost:11434"
auth = "none"
default_model = "qwen3.5:latest"
# Hot-path local inference. No bearer needed — direct to Ollama as of
# 2026-05-02 (Python sidecar's pass-through wrapper retired). Model
# names are bare (e.g. "qwen3.5:latest", not "ollama/qwen3.5:latest").

[[provider]]
name = "ollama_cloud"
base_url = "https://ollama.com"
auth = "bearer"
auth_env = "OLLAMA_CLOUD_KEY"
default_model = "deepseek-v3.2"
# Cloud-tier Ollama (Pro plan as of 2026-04-28). Key resolved from
# OLLAMA_CLOUD_KEY at gateway boot; Pro tier upgraded the account so
# rate limits + model access widen without a key change. Model-prefix
# routing: "cloud/<model>" auto-routes here. 39-model fleet now
# includes deepseek-v3.2, deepseek-v4-{flash,pro}, gemini-3-flash-
# preview, glm-{5,5.1}, kimi-k2.6, qwen3-coder-next.
# 2026-04-28: default upgraded gpt-oss:120b → deepseek-v3.2 (newest
# DeepSeek revision; kimi-k2:1t still upstream-broken with HTTP 500).

[[provider]]
name = "openrouter"
base_url = "https://openrouter.ai/api/v1"
auth = "bearer"
auth_env = "OPENROUTER_API_KEY"
auth_fallback_files = ["/home/profit/.env", "/root/llm_team_config.json"]
default_model = "x-ai/grok-4.1-fast"
# Multi-provider gateway. Covers Anthropic, Google, OpenAI, MiniMax,
# Qwen, Gemma, etc. Key resolved via crates/gateway/src/v1/openrouter.rs
# resolve_openrouter_key() — env first, then fallback files.
# Model-prefix routing: "openrouter/<vendor>/<model>" auto-routes here,
# prefix stripped before upstream call.

[[provider]]
name = "opencode"
base_url = "https://opencode.ai/zen/v1"
# Unified endpoint — covers BOTH Zen (pay-per-token Anthropic/OpenAI/
# Gemini frontier) AND Go (flat-sub Kimi/GLM/DeepSeek/Qwen/Minimax).
# Upstream bills per-model: Zen models hit Zen balance, Go models hit
# Go subscription cap. /zen/go/v1 is the Go-only sub-path (rejects
# Zen models), kept for reference but not used by this provider.
auth = "bearer"
auth_env = "OPENCODE_API_KEY"
default_model = "claude-opus-4-7"
# OpenCode (Zen + GO unified endpoint). One sk-* key reaches Claude
# Opus 4.7, GPT-5.5-pro, Gemini 3.1-pro, Kimi K2.6, DeepSeek, GLM,
# Qwen, plus 4 free-tier models. OpenAI-compatible Chat Completions
# at /v1/chat/completions. Model-prefix routing: "opencode/<name>"
# auto-routes here, prefix stripped before upstream call.
# Key file: /etc/lakehouse/opencode.env (loaded via systemd EnvironmentFile).
# Model catalog: curl -H "Authorization: Bearer ..." https://opencode.ai/zen/v1/models
# Note: /zen/go/v1 is the GO-only sub-path (Kimi/GLM/DeepSeek tier);
# /zen/v1 covers everything including Anthropic (which /zen/go/v1 rejects).

[[provider]]
name = "kimi"
base_url = "https://api.kimi.com/coding/v1"
auth = "bearer"
auth_env = "KIMI_API_KEY"
default_model = "kimi-for-coding"
# Direct Kimi For Coding provider. `api.kimi.com` is a SEPARATE account
# system from `api.moonshot.ai` and `api.moonshot.cn` — keys are NOT
# interchangeable. Used when Ollama Cloud's `kimi-k2:1t` is upstream-
# broken and OpenRouter's `moonshotai/kimi-k2.6` is rate-limited.
# Model id: `kimi-for-coding` (kimi-k2.6 underneath).
# Key file: /etc/lakehouse/kimi.env (loaded via systemd EnvironmentFile).
# Model-prefix routing: "kimi/<model>" auto-routes here, prefix stripped.

# Planned (Phase 40 long-horizon — adapters not yet shipped):
#
# [[provider]]
# name = "gemini"
# base_url = "https://generativelanguage.googleapis.com/v1beta"
# auth = "api_key_query"
# auth_env = "GEMINI_API_KEY"
# default_model = "gemini-2.0-flash"
#
# [[provider]]
# name = "claude"
# base_url = "https://api.anthropic.com/v1"
# auth = "x_api_key"
# auth_env = "ANTHROPIC_API_KEY"
# default_model = "claude-3-5-sonnet-latest"