Maven/internal/config/workstation.go

package config

import (
	"net/url"
	"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"`

	// Token — the bearer credential mavgpud requires, expanded from the
	// environment like every other secret here. It is what stops anything on
	// the LAN spending the card, so a URL that is not loopback needs one.
	// Wrong or missing reads as a workstation that is down, and Maven falls
	// back to the resident model.
	Token string `json:"token,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"`

	// Stt — CrisperWhisper 2.0 on the same machine, a separate service on its
	// own port. Absent ⇒ every utterance goes to mavsttd, which is today.
	Stt *WorkstationSttConfig `json:"stt,omitempty"`
}

// WorkstationSttConfig — speech-to-text on the workstation.
//
// It is a second service and not a second endpoint on mavgpud: whisper.cpp
// cannot load CrisperWhisper 2.0 at all, because it derives its language count
// from the vocabulary size and CW2's 51897 tokens shift seven special token
// ids. So CW2 runs under transformers, and this block addresses it.
//
// Worth the trouble: CW2 turbo scores 10.4% WER in Russian against 27.5% for
// the ggml-small.bin homesrv loads
// (docs/evals/2026-08-09-crisperwhisper2-russian-wer.md).
type WorkstationSttConfig struct {
	// URL — the transcribe endpoint, e.g.
	// "http://192.168.1.105:8081/transcribe". Empty ⇒ the block is normalised
	// to nil and mavsttd takes every turn.
	URL string `json:"url,omitempty"`

	// Health — the admission endpoint. Empty ⇒ the URL's origin + "/health".
	// It answers 503 while the card is held, and that is the signal.
	Health string `json:"health,omitempty"`

	// Token — the bearer token the service checks. Audio is the most sensitive
	// thing that crosses this seam, so a LAN deployment should set one. Write
	// it as ${MAVEN_STT_TOKEN} and keep the value in deploy/telegram.env, the
	// way every other secret in this file is written.
	Token string `json:"token,omitempty"`

	// Probe — how often admission is re-checked. 0 ⇒ DefaultWorkstationProbe.
	Probe Duration `json:"probe,omitempty"`

	// Timeout — the per-request budget for one utterance. 0 ⇒
	// DefaultWorkstationSttTimeout. A request that overruns falls back to
	// mavsttd, which costs a worse transcript and not the turn.
	Timeout Duration `json:"timeout,omitempty"`
}

// Workstation defaults, applied in normaliseWorkstation.
const (
	DefaultWorkstationProbe   = 15 * time.Second
	DefaultWorkstationTimeout = 90 * time.Second
	// One utterance, not one completion. A voice turn waits on this, so the
	// budget is a few seconds and not a minute and a half.
	DefaultWorkstationSttTimeout = 10 * 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)
	}
	normaliseWorkstationStt(w)
}

// normaliseWorkstationStt applies the speech-to-text block's defaults. No
// address, no remote: mavsttd then takes every utterance, which is today.
func normaliseWorkstationStt(w *WorkstationConfig) {
	if w.Stt != nil && strings.TrimSpace(w.Stt.URL) == "" {
		w.Stt = nil
	}
	if w.Stt == nil {
		return
	}
	s := w.Stt
	if strings.TrimSpace(s.Health) == "" {
		s.Health = healthOrigin(s.URL)
	}
	if s.Probe <= 0 {
		s.Probe = Duration(DefaultWorkstationProbe)
	}
	if s.Timeout <= 0 {
		s.Timeout = Duration(DefaultWorkstationSttTimeout)
	}
}

// healthOrigin derives the admission endpoint from the transcribe endpoint.
// The URL names a path, so appending to it would ask for /transcribe/health.
func healthOrigin(raw string) string {
	u, err := url.Parse(raw)
	if err != nil || u.Host == "" {
		return strings.TrimRight(raw, "/") + "/health"
	}
	return u.Scheme + "://" + u.Host + "/health"
}