dguiducci
2b35312abd
Adds media.rs for per-turn attachment routing, message_builder partitioning by resolved model capabilities, controller endpoints for uploads, and server routing for /data/* behind session auth. See CLAUDE.md §Multimodal attachments for full design.
169 lines
7.4 KiB
YAML
169 lines
7.4 KiB
YAML
# Declarative OpenAI-compatible LLM providers.
|
|
#
|
|
# Loaded at boot from this file (resolved against the process working
|
|
# directory, like config.yml) — edit and `restart`, no rebuild needed. An
|
|
# invalid entry is logged and skipped; native providers (anthropic, ollama,
|
|
# openai, openrouter — whose behavior is not plain OpenAI-compatible) are
|
|
# unaffected. Entries whose `id` collides with a native provider are skipped.
|
|
#
|
|
# Entry shape (optional unless noted):
|
|
# id: unique type id stored in the DB (required)
|
|
# name: display name (required)
|
|
# kind: openai_compatible — the only kind for now
|
|
# base_url: chat base URL, OpenAI-compatible (required)
|
|
# base_url_overridable: the DB instance's base_url overrides this default
|
|
# api_key: required | optional | none (default: required)
|
|
# prompt_cache: true | false (default: false)
|
|
# ui: { color, icon, description } (color/icon required)
|
|
# fields: UI form fields [{ key, label, required, secret }]
|
|
# models: remote catalog config — omit to disable listing:
|
|
# endpoint: GET path joined to models_url (OpenAI `data` envelope)
|
|
# models_url: defaults to the resolved base_url
|
|
# auth: bearer | none (default: bearer unless api_key: none)
|
|
# static: [model ids] — alternative to endpoint
|
|
# map: per-model JSON field names, all optional:
|
|
# id / name / context_length / max_completion_tokens / knowledge_cutoff
|
|
# vision: <bool field> (also adds the `vision` capability)
|
|
# price_input_per_million / price_output_per_million: <number field>
|
|
# capability_flags: { <capability>: <bool field> } (e.g. reasoning)
|
|
# base_capabilities: capabilities every listed model gets
|
|
# defaults: { vision: bool } — used when the source omits it
|
|
# enrich: first-matching rule wins, glob on the model id
|
|
# (`*` is the only wildcard, case-insensitive):
|
|
# - match: "k3*" prefix / "*reasoner*" contains / "glm-5" exact
|
|
# mode: fill | override fill keeps endpoint values (default),
|
|
# override lets the rule win
|
|
# context_length / max_completion_tokens / vision / add_capabilities
|
|
# reasoning: reasoning knob — omit when models don't reason:
|
|
# request: how the selected value reaches the request body:
|
|
# { kind: effort, remap: { disabled: none } } {"reasoning_effort": v}
|
|
# { kind: thinking } {"thinking": {...}} (+effort)
|
|
# modes: first-matching rule wins:
|
|
# - when: { models: [globs], capability: name } both present = OR;
|
|
# values: [...] absent = every model
|
|
# default: ...
|
|
providers:
|
|
- id: moonshot
|
|
name: "Moonshot AI pay-as-you-go"
|
|
base_url: "https://api.moonshot.ai/v1"
|
|
ui:
|
|
color: "#2563eb"
|
|
icon: "bi-moon-stars"
|
|
description: "Kimi models on the Moonshot AI platform (OpenAI-compatible)"
|
|
fields:
|
|
- { key: api_key, label: "API Key", required: true, secret: true }
|
|
models:
|
|
endpoint: /models
|
|
map:
|
|
context_length: context_length
|
|
vision: supports_image_in
|
|
capability_flags:
|
|
reasoning: supports_reasoning
|
|
base_capabilities: [function_calling]
|
|
|
|
- id: moonshot_code
|
|
name: "Moonshot AI Kimi Code"
|
|
base_url: "https://api.kimi.com/coding/v1"
|
|
ui:
|
|
color: "#000000"
|
|
icon: "bi-code-slash"
|
|
description: "Kimi Code subscription models — k3 / kimi-for-coding (OpenAI-compatible)"
|
|
fields:
|
|
- { key: api_key, label: "API Key", required: true, secret: true }
|
|
models:
|
|
endpoint: /models
|
|
map:
|
|
context_length: context_length
|
|
vision: supports_image_in
|
|
capability_flags:
|
|
reasoning: supports_reasoning
|
|
base_capabilities: [function_calling]
|
|
# Fills the metadata the endpoint may omit (endpoint values always win):
|
|
# k3 → 1M context + native vision and video input; kimi-for-coding → 256k.
|
|
enrich:
|
|
- { match: "k3*", context_length: 1048576, vision: true, add_capabilities: [video] }
|
|
- { match: "kimi-for-coding*", context_length: 262144 }
|
|
reasoning:
|
|
# k3 exposes a graded reasoning_effort ("disabled" routes to K2.6);
|
|
# kimi-for-coding always thinks and has no knob.
|
|
request: { kind: effort, remap: { disabled: none } }
|
|
modes:
|
|
- when: { models: ["k3*"] }
|
|
values: [disabled, low, high, max]
|
|
default: max
|
|
|
|
- id: deepseek
|
|
name: "DeepSeek"
|
|
base_url: "https://api.deepseek.com/v1"
|
|
ui:
|
|
color: "#0ea5e9"
|
|
icon: "bi-search"
|
|
fields:
|
|
- { key: api_key, label: "API Key", required: true, secret: true }
|
|
models:
|
|
endpoint: /models
|
|
models_url: "https://api.deepseek.com"
|
|
map:
|
|
context_length: context_length
|
|
base_capabilities: [function_calling]
|
|
# Known metadata wins over whatever the endpoint returns.
|
|
enrich:
|
|
- { match: "*coder*", context_length: 16384, mode: override }
|
|
- { match: "*reasoner*", context_length: 65536, mode: override, add_capabilities: [reasoning] }
|
|
- { match: "deepseek-v4*", context_length: 1048576, mode: override, max_completion_tokens: 393216 }
|
|
- { match: "deepseek-chat*", context_length: 65536, mode: override }
|
|
- { match: "deepseek-v3*", context_length: 65536, mode: override }
|
|
reasoning:
|
|
# Thinking toggle + graded reasoning_effort; low/medium map to high
|
|
# server-side, xhigh to max.
|
|
request: { kind: thinking }
|
|
modes:
|
|
- when: { capability: reasoning, models: ["*reasoner*", "deepseek-v4*"] }
|
|
values: [disabled, low, medium, high, xhigh, max]
|
|
default: high
|
|
|
|
- id: zai
|
|
name: "Z.AI"
|
|
base_url: "https://api.z.ai/api/paas/v4"
|
|
ui:
|
|
color: "#4f46e5"
|
|
icon: "bi-stars"
|
|
description: "Zhipu AI GLM models (OpenAI-compatible)"
|
|
fields:
|
|
- { key: api_key, label: "API Key", required: true, secret: true }
|
|
models:
|
|
# Z.AI exposes no GET /models endpoint; this mirrors the console menu.
|
|
static: [glm-5.2, glm-5.1, glm-5, glm-5-turbo, glm-4.7, glm-4.6, glm-4.5, glm-4-32b-0414-128k]
|
|
defaults: { vision: false }
|
|
base_capabilities: [function_calling]
|
|
enrich:
|
|
- { match: "*128k*", context_length: 131072 }
|
|
- { match: "glm-5*", context_length: 1048576 }
|
|
- { match: "glm-4.7*", context_length: 200000 }
|
|
- { match: "glm-4.6*", context_length: 200000 }
|
|
- { match: "glm-4.5*", context_length: 131072 }
|
|
reasoning:
|
|
request: { kind: thinking }
|
|
modes:
|
|
# GLM-5.2+ adds a graded effort on top of the thinking toggle.
|
|
- when: { models: ["glm-5.2*"] }
|
|
values: [disabled, minimal, low, medium, high, xhigh, max]
|
|
default: max
|
|
- when: { models: ["glm-5*", "glm-4.7*", "glm-4.6*", "glm-4.5*"] }
|
|
values: [disabled, enabled]
|
|
default: enabled
|
|
|
|
- id: lm_studio
|
|
name: "LM Studio"
|
|
base_url: "http://localhost:1234/v1"
|
|
base_url_overridable: true
|
|
api_key: none
|
|
ui:
|
|
color: "#6b7280"
|
|
icon: "bi-window-stack"
|
|
description: "Local models via LM Studio"
|
|
fields:
|
|
- { key: base_url, label: "Base URL", required: false, secret: false }
|
|
models:
|
|
endpoint: /models
|