mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-06-22 00:52:51 +08:00
0ed85bb88b
- Removed `examples/plugin/main.go` and `internal/pluginhost/loader_plugin.go` after migrating to a more modular system. - Introduced `streamBridge` in `internal/pluginhost/stream_bridge.go` for efficient stream handling and communication. - Added examples of `thinking` plugins written in both Rust and Go under `examples/plugin/thinking`. - Enhanced test coverage for plugin host system changes, including stream chunk translation and thinking logic. - Improved API compatibility and ensured backward-compatible upgrades for plugin execution.
465 lines
24 KiB
YAML
465 lines
24 KiB
YAML
# Server host/interface to bind to. Default is empty ("") to bind all interfaces (IPv4 + IPv6).
|
||
# Use "127.0.0.1" or "localhost" to restrict access to local machine only.
|
||
host: ""
|
||
|
||
# Server port
|
||
port: 8317
|
||
|
||
# TLS settings for HTTPS. When enabled, the server listens with the provided certificate and key.
|
||
tls:
|
||
enable: false
|
||
cert: ""
|
||
key: ""
|
||
|
||
# Management API settings
|
||
remote-management:
|
||
# Whether to allow remote (non-localhost) management access.
|
||
# When false, only localhost can access management endpoints (a key is still required).
|
||
allow-remote: false
|
||
|
||
# Management key. If a plaintext value is provided here, it will be hashed on startup.
|
||
# All management requests (even from localhost) require this key.
|
||
# Leave empty to disable the Management API entirely (404 for all /v0/management routes).
|
||
secret-key: ""
|
||
|
||
# Disable the bundled management control panel asset download and HTTP route when true.
|
||
disable-control-panel: false
|
||
|
||
# Disable automatic periodic background updates of the management panel from GitHub (default: false).
|
||
# When enabled, the panel is only downloaded on first access if missing, and never auto-updated afterward.
|
||
# disable-auto-update-panel: false
|
||
|
||
# GitHub repository for the management control panel. Accepts a repository URL or releases API URL.
|
||
panel-github-repository: "https://github.com/router-for-me/Cli-Proxy-API-Management-Center"
|
||
|
||
# Authentication directory (supports ~ for home directory)
|
||
auth-dir: "~/.cli-proxy-api"
|
||
|
||
# API keys for authentication
|
||
api-keys:
|
||
- "your-api-key-1"
|
||
- "your-api-key-2"
|
||
- "your-api-key-3"
|
||
|
||
# Enable debug logging
|
||
debug: false
|
||
|
||
# Enable pprof HTTP debug server (host:port). Keep it bound to localhost for safety.
|
||
pprof:
|
||
enable: false
|
||
addr: "127.0.0.1:8316"
|
||
|
||
# Standard dynamic library plugins are trusted in-process code. They are disabled by default.
|
||
# Build Go examples with go build -buildmode=c-shared for the target GOOS/GOARCH.
|
||
# Other languages can implement the same C ABI and JSON method protocol.
|
||
# Plugin executors require a matching auth record with the same provider key.
|
||
# If the same provider is configured as OpenAI-compatible, the native executor wins.
|
||
# Plugin command-line flags and Management API routes are optional capabilities.
|
||
# Existing native flags/routes and higher-priority plugin flags/routes cannot be replaced.
|
||
# 插件列表 Management API 会读取插件 Metadata 中的 Logo 和 ConfigFields，用于管理端展示。
|
||
# 单插件 enabled 只控制 plugins.configs.<pluginID>.enabled，不会隐式修改全局 plugins.enabled。
|
||
plugins:
|
||
enabled: false
|
||
dir: "plugins"
|
||
configs:
|
||
example:
|
||
enabled: true
|
||
priority: 1
|
||
config1: true
|
||
config2: "string"
|
||
config3: 3
|
||
mode: "safe" # enum example: safe, fast
|
||
|
||
# When true, disable high-overhead request logging and HTTP middleware features to reduce per-request memory usage under high concurrency.
|
||
commercial-mode: false
|
||
|
||
# When true, write application logs to rotating files instead of stdout
|
||
logging-to-file: false
|
||
|
||
# Maximum total size (MB) of log files under the logs directory. When exceeded, the oldest log
|
||
# files are deleted until within the limit. Set to 0 to disable.
|
||
logs-max-total-size-mb: 0
|
||
|
||
# Maximum number of error log files retained when request logging is disabled.
|
||
# When exceeded, the oldest error log files are deleted. Default is 10. Set to 0 to disable cleanup.
|
||
error-logs-max-files: 10
|
||
|
||
# When false, disable in-memory usage statistics aggregation
|
||
usage-statistics-enabled: false
|
||
|
||
# How long (in seconds) usage queue items are retained in memory for the Management API.
|
||
# The local Redis RESP usage output is disabled.
|
||
# Default: 60. Max: 3600.
|
||
redis-usage-queue-retention-seconds: 60
|
||
|
||
# Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/
|
||
# Per-entry proxy-url also supports "direct" or "none" to bypass both the global proxy-url and environment proxies explicitly.
|
||
proxy-url: ""
|
||
|
||
# When true, unprefixed model requests only use credentials without a prefix (except when prefix == model name).
|
||
force-model-prefix: false
|
||
|
||
# When true, forward filtered upstream response headers to downstream clients.
|
||
# Default is false (disabled).
|
||
passthrough-headers: false
|
||
|
||
# Number of times to retry a request. Retries will occur if the HTTP response code is 403, 408, 500, 502, 503, or 504.
|
||
request-retry: 3
|
||
|
||
# Maximum number of different credentials to try for one failed request.
|
||
# Set to 0 to keep legacy behavior (try all available credentials).
|
||
max-retry-credentials: 0
|
||
|
||
# Maximum wait time in seconds for a cooled-down credential before triggering a retry.
|
||
max-retry-interval: 30
|
||
|
||
# When true, disable auth/model cooldown scheduling globally (prevents blackout windows after failure states).
|
||
disable-cooling: false
|
||
|
||
# disable-image-generation supports: false (default), true, or "chat".
|
||
# - true: disable image_generation everywhere (also returns 404 for /v1/images/generations and /v1/images/edits).
|
||
# - "chat": disable image_generation injection on non-images endpoints, but keep /v1/images/generations and /v1/images/edits enabled.
|
||
disable-image-generation: false
|
||
|
||
# Base model used when proxying gpt-image-2 via the hosted image_generation tool (Responses API).
|
||
# Must start with "gpt-" (case-insensitive). If unset or invalid, defaults to "gpt-5.4-mini".
|
||
# gpt-image-2-base-model: "gpt-5.4-mini"
|
||
|
||
# Core auth auto-refresh worker pool size (OAuth/file-based auth token refresh).
|
||
# When > 0, overrides the default worker count (16).
|
||
# auth-auto-refresh-workers: 16
|
||
|
||
# Quota exceeded behavior
|
||
quota-exceeded:
|
||
switch-project: true # Whether to automatically switch to another project when a quota is exceeded
|
||
switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
|
||
antigravity-credits: true # Whether to use credits as last-resort fallback when all free-tier auths are exhausted for Claude models
|
||
|
||
# Routing strategy for selecting credentials when multiple match.
|
||
routing:
|
||
strategy: "round-robin" # round-robin (default), fill-first
|
||
# Enable universal session-sticky routing for all clients.
|
||
# Session IDs are extracted from: metadata.user_id (Claude Code session format),
|
||
# X-Session-ID, Session_id (Codex), X-Amp-Thread-Id (Amp CLI),
|
||
# X-Client-Request-Id (PI), conversation_id, or first few messages hash.
|
||
# Automatic failover is always enabled when bound auth becomes unavailable.
|
||
session-affinity: false # default: false
|
||
# How long session-to-auth bindings are retained. Default: 1h
|
||
session-affinity-ttl: "1h"
|
||
|
||
# Codex provider behavior.
|
||
codex:
|
||
# When true, and routing.strategy is fill-first or routing.session-affinity is true,
|
||
# remap Codex prompt_cache_key and installation identity per selected auth.
|
||
# Some superstitious users believe request tracking identifiers can be used
|
||
# as evidence for TOS enforcement bans; this option only satisfies those odd concerns.
|
||
identity-confuse: false
|
||
|
||
# When true, enable authentication for the WebSocket API (/v1/ws).
|
||
ws-auth: true
|
||
|
||
# When true, enable Gemini CLI internal endpoints (/v1internal:*).
|
||
# Default is false for safety.
|
||
enable-gemini-cli-endpoint: false
|
||
|
||
# When > 0, emit blank lines every N seconds for non-streaming responses to prevent idle timeouts.
|
||
nonstream-keepalive-interval: 0
|
||
# Streaming behavior (SSE keep-alives + safe bootstrap retries).
|
||
# streaming:
|
||
# keepalive-seconds: 15 # Default: 0 (disabled). <= 0 disables keep-alives.
|
||
# bootstrap-retries: 1 # Default: 0 (disabled). Retries before first byte is sent.
|
||
|
||
# Signature cache validation for thinking blocks (Antigravity/Claude).
|
||
# When true (default), cached signatures are preferred and validated.
|
||
# When false, client signatures are used directly after normalization (bypass mode for testing).
|
||
# antigravity-signature-cache-enabled: true
|
||
|
||
# Bypass mode signature validation strictness (only applies when signature cache is disabled).
|
||
# When true, validates full Claude protobuf tree (Field 2 -> Field 1 structure).
|
||
# When false (default), only checks R/E prefix + base64 + first byte 0x12.
|
||
# antigravity-signature-bypass-strict: false
|
||
|
||
# Gemini API keys
|
||
# gemini-api-key:
|
||
# - api-key: "AIzaSy...01"
|
||
# prefix: "test" # optional: require calls like "test/gemini-3-pro-preview" to target this credential
|
||
# disable-cooling: false # optional: per-auth override for auth/model cooldown scheduling
|
||
# base-url: "https://generativelanguage.googleapis.com"
|
||
# headers:
|
||
# X-Custom-Header: "custom-value"
|
||
# proxy-url: "socks5://proxy.example.com:1080"
|
||
# # proxy-url: "direct" # optional: explicit direct connect for this credential
|
||
# models:
|
||
# - name: "gemini-2.5-flash" # upstream model name
|
||
# alias: "gemini-flash" # client alias mapped to the upstream model
|
||
# excluded-models:
|
||
# - "gemini-2.5-pro" # exclude specific models from this provider (exact match)
|
||
# - "gemini-2.5-*" # wildcard matching prefix (e.g. gemini-2.5-flash, gemini-2.5-pro)
|
||
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview)
|
||
# - "*flash*" # wildcard matching substring (e.g. gemini-2.5-flash-lite)
|
||
# - api-key: "AIzaSy...02"
|
||
|
||
# Codex API keys
|
||
# codex-api-key:
|
||
# - api-key: "sk-atSM..."
|
||
# prefix: "test" # optional: require calls like "test/gpt-5-codex" to target this credential
|
||
# disable-cooling: false # optional: per-auth override for auth/model cooldown scheduling
|
||
# base-url: "https://www.example.com" # use the custom codex API endpoint
|
||
# headers:
|
||
# X-Custom-Header: "custom-value"
|
||
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
|
||
# # proxy-url: "direct" # optional: explicit direct connect for this credential
|
||
# models:
|
||
# - name: "gpt-5-codex" # upstream model name
|
||
# alias: "codex-latest" # client alias mapped to the upstream model
|
||
# excluded-models:
|
||
# - "gpt-5.1" # exclude specific models (exact match)
|
||
# - "gpt-5-*" # wildcard matching prefix (e.g. gpt-5-medium, gpt-5-codex)
|
||
# - "*-mini" # wildcard matching suffix (e.g. gpt-5-codex-mini)
|
||
# - "*codex*" # wildcard matching substring (e.g. gpt-5-codex-low)
|
||
|
||
# Claude API keys
|
||
# claude-api-key:
|
||
# - api-key: "sk-atSM..." # use the official claude API key, no need to set the base url
|
||
# - api-key: "sk-atSM..."
|
||
# prefix: "test" # optional: require calls like "test/claude-sonnet-latest" to target this credential
|
||
# disable-cooling: false # optional: per-auth override for auth/model cooldown scheduling
|
||
# base-url: "https://www.example.com" # use the custom claude API endpoint
|
||
# headers:
|
||
# X-Custom-Header: "custom-value"
|
||
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
|
||
# # proxy-url: "direct" # optional: explicit direct connect for this credential
|
||
# models:
|
||
# - name: "claude-3-5-sonnet-20241022" # upstream model name
|
||
# alias: "claude-sonnet-latest" # client alias mapped to the upstream model
|
||
# excluded-models:
|
||
# - "claude-opus-4-5-20251101" # exclude specific models (exact match)
|
||
# - "claude-3-*" # wildcard matching prefix (e.g. claude-3-7-sonnet-20250219)
|
||
# - "*-thinking" # wildcard matching suffix (e.g. claude-opus-4-5-thinking)
|
||
# - "*haiku*" # wildcard matching substring (e.g. claude-3-5-haiku-20241022)
|
||
# cloak: # optional: request cloaking for non-Claude-Code clients
|
||
# mode: "auto" # "auto" (default): cloak only when client is not Claude Code
|
||
# # "always": always apply cloaking
|
||
# # "never": never apply cloaking
|
||
# strict-mode: false # false (default): prepend Claude Code prompt to user system messages
|
||
# # true: strip all user system messages, keep only Claude Code prompt
|
||
# sensitive-words: # optional: words to obfuscate with zero-width characters
|
||
# - "API"
|
||
# - "proxy"
|
||
# cache-user-id: true # optional: default is false; set true to reuse cached user_id per API key instead of generating a random one each request
|
||
# experimental-cch-signing: false # optional: default is false; when true, sign the final /v1/messages body using the current Claude Code cch algorithm
|
||
# # keep this disabled unless you explicitly need the behavior, so upstream seed changes fall back to legacy proxy behavior
|
||
|
||
# Default headers for Claude API requests. Update when Claude Code releases new versions.
|
||
# In legacy mode, user-agent/package-version/runtime-version/timeout are used as fallbacks
|
||
# when the client omits them, while OS/arch remain runtime-derived. When
|
||
# stabilize-device-profile is enabled, OS/arch stay pinned to the baseline values below,
|
||
# while user-agent/package-version/runtime-version seed a software fingerprint that can
|
||
# still upgrade to newer official Claude client versions.
|
||
# claude-header-defaults:
|
||
# user-agent: "claude-cli/2.1.44 (external, sdk-cli)"
|
||
# package-version: "0.74.0"
|
||
# runtime-version: "v24.3.0"
|
||
# os: "MacOS"
|
||
# arch: "arm64"
|
||
# timeout: "600"
|
||
# stabilize-device-profile: false # optional, default false; set true to enable per-auth/API-key fingerprint pinning
|
||
|
||
# Default headers for Codex OAuth model requests.
|
||
# These are used only for file-backed/OAuth Codex requests when the client
|
||
# does not send the header. `user-agent` applies to HTTP and websocket requests;
|
||
# `beta-features` only applies to websocket requests. They do not apply to codex-api-key entries.
|
||
# codex-header-defaults:
|
||
# user-agent: "codex_cli_rs/0.114.0 (Mac OS 14.2.0; x86_64) vscode/1.111.0"
|
||
# beta-features: "multi_agent"
|
||
|
||
# OpenAI compatibility providers
|
||
# openai-compatibility:
|
||
# - name: "openrouter" # The name of the provider; it will be used in the user agent and other places.
|
||
# disabled: false # optional: set to true to disable this provider without removing it
|
||
# prefix: "test" # optional: require calls like "test/kimi-k2" to target this provider's credentials
|
||
# base-url: "https://openrouter.ai/api/v1" # The base URL of the provider.
|
||
# disable-cooling: false # optional: per-provider override for auth/model cooldown scheduling
|
||
# headers:
|
||
# X-Custom-Header: "custom-value"
|
||
# api-key-entries:
|
||
# - api-key: "sk-or-v1-...b780"
|
||
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
|
||
# # proxy-url: "direct" # optional: explicit direct connect for this credential
|
||
# - api-key: "sk-or-v1-...b781" # without proxy-url
|
||
# models: # The models supported by the provider.
|
||
# - name: "moonshotai/kimi-k2:free" # The actual model name.
|
||
# alias: "kimi-k2" # The alias used in the API.
|
||
# image: false # optional: set true to allow this model on /v1/images/generations and /v1/images/edits
|
||
# thinking: # optional: omit to default to levels ["low","medium","high"]
|
||
# levels: ["low", "medium", "high"]
|
||
# # You may repeat the same alias to build an internal model pool.
|
||
# # The client still sees only one alias in the model list.
|
||
# # Requests to that alias will round-robin across the upstream names below,
|
||
# # and if the chosen upstream fails before producing output, the request will
|
||
# # continue with the next upstream model in the same alias pool.
|
||
# - name: "deepseek-v3.1"
|
||
# alias: "claude-opus-4.66"
|
||
# - name: "glm-5"
|
||
# alias: "claude-opus-4.66"
|
||
# - name: "kimi-k2.5"
|
||
# alias: "claude-opus-4.66"
|
||
|
||
# Vertex API keys (Vertex-compatible endpoints, base-url is optional)
|
||
# vertex-api-key:
|
||
# - api-key: "vk-123..." # x-goog-api-key header
|
||
# prefix: "test" # optional: require calls like "test/vertex-pro" to target this credential
|
||
# base-url: "https://example.com/api" # optional, e.g. https://zenmux.ai/api; falls back to Google Vertex when omitted
|
||
# proxy-url: "socks5://proxy.example.com:1080" # optional per-key proxy override
|
||
# # proxy-url: "direct" # optional: explicit direct connect for this credential
|
||
# headers:
|
||
# X-Custom-Header: "custom-value"
|
||
# models: # optional: map aliases to upstream model names
|
||
# - name: "gemini-2.5-flash" # upstream model name
|
||
# alias: "vertex-flash" # client-visible alias
|
||
# - name: "gemini-2.5-pro"
|
||
# alias: "vertex-pro"
|
||
# excluded-models: # optional: models to exclude from listing
|
||
# - "imagen-3.0-generate-002"
|
||
# - "imagen-*"
|
||
|
||
# Amp Integration
|
||
# ampcode:
|
||
# # Configure upstream URL for Amp CLI OAuth and management features
|
||
# upstream-url: "https://ampcode.com"
|
||
# # Optional: Override API key for Amp upstream (otherwise uses env or file)
|
||
# upstream-api-key: ""
|
||
# # Per-client upstream API key mapping
|
||
# # Maps client API keys (from top-level api-keys) to different Amp upstream API keys.
|
||
# # Useful when different clients need to use different Amp accounts/quotas.
|
||
# # If a client key isn't mapped, falls back to upstream-api-key (default behavior).
|
||
# upstream-api-keys:
|
||
# - upstream-api-key: "amp_key_for_team_a" # Upstream key to use for these clients
|
||
# api-keys: # Client keys that use this upstream key
|
||
# - "your-api-key-1"
|
||
# - "your-api-key-2"
|
||
# - upstream-api-key: "amp_key_for_team_b"
|
||
# api-keys:
|
||
# - "your-api-key-3"
|
||
# # Restrict Amp management routes (/api/auth, /api/user, etc.) to localhost only (default: false)
|
||
# restrict-management-to-localhost: false
|
||
# # Force model mappings to run before checking local API keys (default: false)
|
||
# force-model-mappings: false
|
||
# # Amp Model Mappings
|
||
# # Route unavailable Amp models to alternative models available in your local proxy.
|
||
# # Useful when Amp CLI requests models you don't have access to (e.g., Claude Opus 4.5)
|
||
# # but you have a similar model available (e.g., Claude Sonnet 4).
|
||
# model-mappings:
|
||
# - from: "claude-opus-4-5-20251101" # Model requested by Amp CLI
|
||
# to: "gemini-claude-opus-4-5-thinking" # Route to this available model instead
|
||
# - from: "claude-sonnet-4-5-20250929"
|
||
# to: "gemini-claude-sonnet-4-5-thinking"
|
||
# - from: "claude-haiku-4-5-20251001"
|
||
# to: "gemini-2.5-flash"
|
||
|
||
# Global OAuth model name aliases (per channel)
|
||
# These aliases rename model IDs for both model listing and request routing.
|
||
# Supported channels: gemini-cli, vertex, aistudio, antigravity, claude, codex, kimi, xai.
|
||
# NOTE: Aliases do not apply to gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, or ampcode.
|
||
# NOTE: Because aliases affect the merged /v1 model list and merged request routing, overlapping
|
||
# client-visible names can become ambiguous across providers. /api/provider/{provider}/... helps
|
||
# you select the protocol surface, but inference backend selection can still follow the resolved
|
||
# model/alias. For strict backend pinning, use unique aliases/prefixes or avoid overlapping names.
|
||
# You can repeat the same name with different aliases to expose multiple client model names.
|
||
# oauth-model-alias:
|
||
# gemini-cli:
|
||
# - name: "gemini-2.5-pro" # original model name under this channel
|
||
# alias: "g2.5p" # client-visible alias
|
||
# fork: true # when true, keep original and also add the alias as an extra model (default: false)
|
||
# vertex:
|
||
# - name: "gemini-2.5-pro"
|
||
# alias: "g2.5p"
|
||
# aistudio:
|
||
# - name: "gemini-2.5-pro"
|
||
# alias: "g2.5p"
|
||
# antigravity:
|
||
# - name: "gemini-3-pro-high"
|
||
# alias: "gemini-3-pro-preview"
|
||
# claude:
|
||
# - name: "claude-sonnet-4-5-20250929"
|
||
# alias: "cs4.5"
|
||
# codex:
|
||
# - name: "gpt-5"
|
||
# alias: "g5"
|
||
# kimi:
|
||
# - name: "kimi-k2.5"
|
||
# alias: "k2.5"
|
||
# xai:
|
||
# - name: "grok-4.3"
|
||
# alias: "grok-latest"
|
||
# qoder: # plugin provider keys are supported for OAuth plugins
|
||
# - name: "qmodel_latest"
|
||
# alias: "qlatest"
|
||
|
||
# OAuth provider excluded models
|
||
# oauth-excluded-models:
|
||
# gemini-cli:
|
||
# - "gemini-2.5-pro" # exclude specific models (exact match)
|
||
# - "gemini-2.5-*" # wildcard matching prefix (e.g. gemini-2.5-flash, gemini-2.5-pro)
|
||
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview)
|
||
# - "*flash*" # wildcard matching substring (e.g. gemini-2.5-flash-lite)
|
||
# vertex:
|
||
# - "gemini-3-pro-preview"
|
||
# aistudio:
|
||
# - "gemini-3-pro-preview"
|
||
# antigravity:
|
||
# - "gemini-3-pro-preview"
|
||
# claude:
|
||
# - "claude-3-5-haiku-20241022"
|
||
# codex:
|
||
# - "gpt-5-codex-mini"
|
||
# kimi:
|
||
# - "kimi-k2-thinking"
|
||
# xai:
|
||
# - "grok-3-mini"
|
||
|
||
# Optional payload configuration
|
||
# payload:
|
||
# default: # Default rules only set parameters when they are missing in the payload.
|
||
# - models:
|
||
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
|
||
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
|
||
# from-protocol: "responses" # restricts the rule to the source protocol, options: openai, responses, gemini, claude
|
||
# headers: # all configured request headers must match; values support "*" wildcards
|
||
# X-Client-Tier: "tenant-*-region-*"
|
||
# match: # all payload JSON paths must equal the configured values
|
||
# - "metadata.client": "codex"
|
||
# not-match: # payload JSON paths must not equal the configured values
|
||
# - "metadata.mode": "dev"
|
||
# exist: # all payload JSON paths must exist and not be null
|
||
# - "tools.#(type==\"web_search\").type"
|
||
# not-exist: # all payload JSON paths must be missing or null
|
||
# - "metadata.disable_payload"
|
||
# params: # JSON path (gjson/sjson syntax) -> value
|
||
# "generationConfig.thinkingConfig.thinkingBudget": 32768
|
||
# default-raw: # Default raw rules set parameters using raw JSON when missing (must be valid JSON).
|
||
# - models:
|
||
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
|
||
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
|
||
# params: # JSON path (gjson/sjson syntax) -> raw JSON value (strings are used as-is, must be valid JSON)
|
||
# "generationConfig.responseJsonSchema": "{\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"}}}"
|
||
# override: # Override rules always set parameters, overwriting any existing values.
|
||
# - models:
|
||
# - name: "gpt-*" # Supports wildcards (e.g., "gpt-*")
|
||
# protocol: "codex" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
|
||
# params: # JSON path (gjson/sjson syntax) -> value
|
||
# "reasoning.effort": "high"
|
||
# override-raw: # Override raw rules always set parameters using raw JSON (must be valid JSON).
|
||
# - models:
|
||
# - name: "gpt-*" # Supports wildcards (e.g., "gpt-*")
|
||
# protocol: "codex" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
|
||
# params: # JSON path (gjson/sjson syntax) -> raw JSON value (strings are used as-is, must be valid JSON)
|
||
# "response_format": "{\"type\":\"json_schema\",\"json_schema\":{\"name\":\"answer\",\"schema\":{\"type\":\"object\"}}}"
|
||
# filter: # Filter rules remove specified parameters from the payload.
|
||
# - models:
|
||
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
|
||
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
|
||
# params: # JSON paths (gjson/sjson syntax) to remove from the payload
|
||
# - "generationConfig.thinkingConfig.thinkingBudget"
|
||
# - "generationConfig.responseJsonSchema"
|