claude
9ef6f286a9
Pure move. Praxis, Nexus and Hexis go to ecosystem.go with a note on why they stay three identical two-field types instead of one shared EndpointConfig: the block a reader greps for is the service they are debugging. The workstation block, its two defaults and its normalise arm go to workstation.go. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
67 lines
2.4 KiB
Go
67 lines
2.4 KiB
Go
package config
|
|
|
|
import (
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// WorkstationConfig — the big model on the owner's desktop (workpc, a
|
|
// 7900 GRE with 16GB), fronted by mavgpud.
|
|
//
|
|
// homesrv cannot grow a GPU, so the resident Qwen3-1.7B is the floor and this
|
|
// is the preferred model above it (owner's call, 2026-08-02, docs/offload.md).
|
|
// The workstation is never assumed up: its card is often held by a CPT run and
|
|
// the machine sleeps. No block, or an empty URL, and homesrv behaves exactly as
|
|
// it does today.
|
|
//
|
|
// Only the prompt crosses the LAN, and the workstation is not "the box". The
|
|
// rules in CLAUDE.md about what may leave still apply.
|
|
type WorkstationConfig struct {
|
|
// URL — where mavgpud listens, e.g. "http://192.168.1.105:8080". Empty ⇒
|
|
// the whole block is normalised to nil and nothing probes anything.
|
|
URL string `json:"url,omitempty"`
|
|
|
|
// Health — the admission endpoint. Empty ⇒ URL + "/health", which is what
|
|
// mavgpud serves. It answers 503 while the card is held, and that is the
|
|
// signal, so it must be the supervisor's endpoint and not llama-server's.
|
|
Health string `json:"health,omitempty"`
|
|
|
|
// Probe — how often admission is re-checked. 0 ⇒ DefaultWorkstationProbe.
|
|
// Nothing on the hot path waits for it: the answer is cached and read
|
|
// atomically, so this only sets how late Maven notices the card came back.
|
|
Probe Duration `json:"probe,omitempty"`
|
|
|
|
// Timeout — the per-request budget for a completion on the workstation.
|
|
// 0 ⇒ DefaultWorkstationTimeout. A big model on a LAN host is slower than
|
|
// the resident one, and a request that overruns falls back to the floor.
|
|
Timeout Duration `json:"timeout,omitempty"`
|
|
}
|
|
|
|
// Workstation defaults, applied in normaliseWorkstation.
|
|
const (
|
|
DefaultWorkstationProbe = 15 * time.Second
|
|
DefaultWorkstationTimeout = 90 * time.Second
|
|
)
|
|
|
|
// normaliseWorkstation applies the block's defaults. No address, no preferred
|
|
// model: an unconfigured workstation is the default deploy and must be
|
|
// indistinguishable from today.
|
|
func (c *Config) normaliseWorkstation() {
|
|
if c.Workstation != nil && strings.TrimSpace(c.Workstation.URL) == "" {
|
|
c.Workstation = nil
|
|
}
|
|
if c.Workstation == nil {
|
|
return
|
|
}
|
|
w := c.Workstation
|
|
if strings.TrimSpace(w.Health) == "" {
|
|
w.Health = strings.TrimRight(w.URL, "/") + "/health"
|
|
}
|
|
if w.Probe <= 0 {
|
|
w.Probe = Duration(DefaultWorkstationProbe)
|
|
}
|
|
if w.Timeout <= 0 {
|
|
w.Timeout = Duration(DefaultWorkstationTimeout)
|
|
}
|
|
}
|