wuyang
75 lines
3.4 KiB
Markdown
75 lines
3.4 KiB
Markdown
# Architecture
|
|
|
|
## Single Agent path
|
|
|
|
Open WebUI owns authenticated users, conversation history, and rendering.
|
|
Every normal model request is delegated to the K1412 Runtime. There is no
|
|
second Chat loop and no per-conversation mode state.
|
|
|
|
## Agent loop
|
|
|
|
The first strategy is intentionally modular:
|
|
|
|
- `ModelProvider` owns provider transport.
|
|
- `ContextPolicy` owns visible-message cleanup and compaction.
|
|
- `ToolRegistry` owns tool schemas and dispatch.
|
|
- `AgentLoop` owns iteration, safe parallel scheduling, and delegation.
|
|
- `RuntimeStore` owns events, plans, and durable Agent memory.
|
|
- `ExecutionProvider` owns local or SSH Docker execution.
|
|
|
|
Every run records its model ID, strategy version, scheduler version, context
|
|
policy, model/tool events, failures, and completion. This event stream is the
|
|
foundation for replay, evaluation, and future experiment assignment.
|
|
|
|
Luna, Terra, and Sol are three independent Ollama models. Each advertises
|
|
boolean thinking support, but none advertises adjustable reasoning effort.
|
|
DeepSeek V4 Pro is a fourth model configured with thinking enabled and maximum
|
|
reasoning effort. Provider selection and credentials remain server-side.
|
|
Thinking state is preserved across tool turns when the provider requires the
|
|
assistant's `reasoning_content` to be returned with following tool results.
|
|
The Agent never publishes hidden reasoning as its own user-facing output.
|
|
|
|
Completion is evidence-gated. Requests for scripts, reports, code, or
|
|
other concrete artifacts are not accepted as complete until a file mutation
|
|
has succeeded and a later read, diff, or command has verified the latest
|
|
mutation. Bare interactive shell commands are rejected. If the iteration
|
|
budget is exhausted without evidence, Runtime returns an explicit incomplete
|
|
checkpoint instead of repeating an unverified model claim.
|
|
|
|
Read-only tools and read-only child Agents may run concurrently. Workspace
|
|
mutations are serialized. A child Agent cannot delegate again, and read-only
|
|
children receive only read-only tools.
|
|
|
|
## Execution providers
|
|
|
|
`local-docker` connects the Workspace Gateway to the local Docker daemon.
|
|
`ssh-docker` connects the same Docker SDK operations to a remote physical
|
|
machine through SSH. Both create the same workspace image, persistent per-user
|
|
volume, and dedicated per-user bridge network, so moving execution off the web
|
|
host changes configuration rather than Agent behavior.
|
|
|
|
For SSH mode, layer `compose.ssh.yaml` over the development Compose file, or
|
|
`deploy/docker-compose.ssh.yml` over the two production Compose files. The
|
|
override removes the local Docker socket and mounts only the selected SSH
|
|
configuration directory read-only.
|
|
|
|
Only Open WebUI publishes a host port. Runtime, Gateway, Postgres, and Redis
|
|
remain unpublishing services. Runtime and Gateway also join an egress-only
|
|
bridge so the model API and a future SSH Docker host are reachable without
|
|
exposing either service on the host.
|
|
|
|
## Workspace file path
|
|
|
|
```text
|
|
browser with Open WebUI session
|
|
-> /api/v1/k1412/workspace/*
|
|
-> Open WebUI backend verifies the user
|
|
-> backend mints a short-lived signed identity JWT
|
|
-> Workspace Gateway verifies service key + user JWT
|
|
-> provider selects only that user's hashed container and volume
|
|
```
|
|
|
|
The file API exposes read-only browse, file download, and streamed directory
|
|
archive operations. Paths pass through the same `/workspace` normalization as
|
|
Agent tools. The browser never talks to Gateway or Docker directly.
|