Maven/internal/phraser/world.go

package phraser

import (
	"context"
	"errors"
	"log"

	"github.com/kami/maven/internal/llm"
)

// Remote — the workstation model, seen from the phraser. `*llm.Pair` satisfies
// it, and a test fake satisfies it in three lines.
//
// Only the refusing half of Pair is here on purpose. Pair.Complete falls back to
// its own floor client, and the phraser already owns a floor: the llama-server it
// spawned. Two floors under one call is one too many, so the phraser asks whether
// the remote will take work, uses it when it will, and otherwise does exactly
// what it did before this file existed.
type Remote interface {
	// Available is an atomic read of a cached probe, so it is free to call per
	// turn. See llm.Pair.
	Available() bool
	// CompleteRemote runs on the workstation or returns ErrRemoteUnavailable. It
	// never falls back.
	CompleteRemote(ctx context.Context, r llm.Req) (string, error)
}

// ErrNoWorldModel — a world question was asked, a workstation model is
// configured to answer it, and that machine is not answering. The caller turns
// this into a gap he is told about ("не могу сейчас"), never into an answer from
// the resident model.
//
// This is the naming half of the degradation rule in docs/offload.md. The
// resident Qwen3-1.7B does not answer a world question worse than the 12B, it
// invents: measured, the workstation model scores knowledge 9/9 on the talk
// fixture against the resident model's confabulations
// (docs/evals/2026-08-02-workstation-gemma4-12b.md).
var ErrNoWorldModel = errors.New("phraser: no world model available")

// defaultChatTemperature — what the phraser's own transport has always sampled
// at, and what Config.Temperature falls back to. Named so the remote path
// cannot drift from the resident one silently.
const defaultChatTemperature = 0.7

// temperature — the sampling temperature for every phrasing call, resident or
// remote. Both paths read this, so a sweep moves them together.
func (p *LLMPhraser) temperature() float64 {
	if p.cfg.Temperature > 0 {
		return p.cfg.Temperature
	}
	return defaultChatTemperature
}

// UseRemote points the phraser at the workstation model. Wiring time only, once,
// before anything phrases: the field is read without a lock on every call
// because a per-turn lock to answer a question that changes at deploy time is
// not worth paying for.
//
// A nil remote is the normal state of a box with no `workstation` block, and it
// must behave exactly as the box behaved before this seam existed.
func (p *LLMPhraser) UseRemote(r Remote) {
	p.remote = r
}

// PhraseWorld answers a question about the world — either from the model's own
// knowledge (no sources) or from a passage someone fetched (a live search, a ZIM
// article, a page he named). Three outcomes, and the middle one is the point:
//
//   - No workstation configured. The resident model answers, exactly as it does
//     today. Naming a gap needs a gap: on a box that never had a second model,
//     refusing every world question would remove a capability he has now.
//   - Workstation configured and taking work. It answers.
//   - Workstation configured and down. ErrNoWorldModel, and the caller says so.
//
// The prompts are the ones PhraseQuery uses, built by the same two functions, so
// the two models are asked the same question in the same words.
func (p *LLMPhraser) PhraseWorld(ctx context.Context, utterance string, sources []string) (string, error) {
	sources = nonEmpty(sources)
	if p.remote == nil {
		return p.PhraseQuery(ctx, utterance, sources)
	}
	var sys, user string
	if len(sources) == 0 {
		sys, user = p.knowledgePrompt(utterance)
	} else {
		sys, user = p.evidencePrompt(utterance, sources)
	}
	if !p.remote.Available() {
		return "", ErrNoWorldModel
	}
	resp, err := p.remote.CompleteRemote(ctx, llm.Req{
		System:      sys,
		User:        user,
		Grammar:     p.grammar(),
		MaxTokens:   768,
		Temperature: p.temperature(),
	})
	if err != nil {
		// The cached probe was one interval stale, or the card went away
		// mid-request. Either way this is the gap, not an error to log and
		// paper over with the smaller model.
		log.Printf("phraser: world model: %v", err)
		return "", errors.Join(ErrNoWorldModel, err)
	}
	resp = stripThink(resp)
	text, _, perr := parseResponseMood(resp)
	if perr != nil {
		log.Printf("phraser: PhraseWorld: %v", perr)
		return "", errors.Join(ErrNoWorldModel, perr)
	}
	if text != "" {
		return text, nil
	}
	if resp == "" {
		return "", ErrNoWorldModel
	}
	return resp, nil
}

// remoteChat is the silent half, for the phrasing paths where the workstation
// model is only better: a nudge, a reminder, a reply, a question answered from
// his own notes. It reports whether it answered; it never reports why not,
// because the caller's next move is the resident model either way.
//
// He is not told which of the two models phrased his reply. That is the rule.
func (p *LLMPhraser) remoteChat(ctx context.Context, system, user string, maxTokens int) (string, bool) {
	if p.remote == nil || !p.remote.Available() {
		return "", false
	}
	out, err := p.remote.CompleteRemote(ctx, llm.Req{
		System:      system,
		User:        user,
		Grammar:     p.grammar(),
		MaxTokens:   maxTokens,
		Temperature: p.temperature(),
	})
	if err != nil {
		log.Printf("phraser: workstation model declined, phrasing here instead: %v", err)
		return "", false
	}
	if out = stripThink(out); out == "" {
		return "", false
	}
	return out, true
}