tapir/internal/adapters/chat/chat.go

// Package chat implements the per-video deeper-dive chat (ADR-027): a read-only
// QA over a video's ALREADY-STORED transcript (ADR-021). It is the enforcement
// point for the feature's load-bearing safety property — stored-transcript-only:
// the Service has NO VideoSource and NO caption-fetch dependency, only a
// Completer factory, so it CANNOT reach YouTube or the rate gate by construction.
// The caller supplies the stored transcript text; chat never fetches.
//
// It reuses the same LiteLLM gateway as the summarizer (a chat is a different
// call, not a new integration) and the same transcript-truncation discipline
// (TAPIR_MAX_TRANSCRIPT_CHARS) so a long transcript fits a small-context model.
package chat

import (
	"context"
	"fmt"
	"log/slog"
	"strings"
	"time"
	"unicode/utf8"

	"gitea.d-ma.be/mathias/tapir/internal/metrics"
)

// Completer is the minimal LLM chat surface the Service needs. *llm.Client
// satisfies it; tests use a fake. It is the SAME surface the summarizer uses.
type Completer interface {
	Complete(ctx context.Context, system, user string) (string, error)
}

// Turn is one completed exchange in an ephemeral, session-only conversation
// (ADR-027 v1: nothing is persisted).
type Turn struct {
	Question string
	Answer   string
}

// Request is one chat turn: the chosen model, the stored transcript text, the
// prior turns (for multi-turn context within the session), and the new question.
type Request struct {
	Model      string
	Transcript string
	History    []Turn
	Question   string
}

// Reply is the model's answer plus whether the transcript was bounded to fit the
// model context (so the UI can be honest that an answer about the tail of a long
// video may be incomplete).
type Reply struct {
	Answer    string
	Truncated bool
}

// Service answers questions against a stored transcript via a switchable set of
// models. models is the ordered, local-first list offered to the user (the cloud
// model is simply absent when disabled — see cmd wiring); maxChars bounds the
// transcript sent to any model (0 = unbounded). newClient builds a Completer for
// a chosen model alias (the same gateway, a different alias).
type Service struct {
	newClient func(model string) Completer
	models    []string
	maxChars  int
}

// New constructs a Service. models must be non-empty and already filtered to the
// offerable set (cloud excluded when disabled) and de-duplicated by the caller.
func New(newClient func(model string) Completer, models []string, maxChars int) *Service {
	return &Service{newClient: newClient, models: models, maxChars: maxChars}
}

// Models returns a copy of the offerable model list (local-first order).
func (s *Service) Models() []string {
	out := make([]string, len(s.models))
	copy(out, s.models)
	return out
}

// offers reports whether model is in the offerable set — the guard that keeps an
// arbitrary, un-offered alias (e.g. a forged form value) from reaching the gateway.
func (s *Service) offers(model string) bool {
	for _, m := range s.models {
		if m == model {
			return true
		}
	}
	return false
}

// DefaultModel resolves the model a fresh chat opens with: the summary's own
// model when it is still an offered option (the ADR-027 default — chat continues
// in the model that produced the summary), otherwise the first offered model.
// Returns "" only when no models are configured.
func (s *Service) DefaultModel(summaryModel string) string {
	if summaryModel != "" && s.offers(summaryModel) {
		return summaryModel
	}
	if len(s.models) > 0 {
		return s.models[0]
	}
	return ""
}

// Answer runs one chat turn. The model is forced back to a default if the request
// names an un-offered alias, so chat can never call the gateway with an arbitrary
// model. The transcript is truncated up front (reporting whether it was cut) and
// passed as system context; the running conversation is the user message.
func (s *Service) Answer(ctx context.Context, req Request) (Reply, error) {
	if len(s.models) == 0 {
		return Reply{}, fmt.Errorf("chat: no models configured")
	}
	model := req.Model
	if !s.offers(model) {
		model = s.DefaultModel("")
	}

	transcript, truncated := truncate(req.Transcript, s.maxChars)
	system := buildSystem(transcript, truncated)
	user := buildUser(req.History, req.Question)

	start := time.Now()
	out, err := s.newClient(model).Complete(ctx, system, user)
	if err != nil {
		return Reply{}, fmt.Errorf("chat: %s: %w", model, err)
	}
	dur := time.Since(start)
	metrics.ObserveChat(model, dur)
	slog.Default().Info("chat answer", "model", model, "elapsed_ms", dur.Milliseconds())
	answer := strings.TrimSpace(out)
	if answer == "" {
		return Reply{}, fmt.Errorf("chat: %s returned an empty answer", model)
	}
	return Reply{Answer: answer, Truncated: truncated}, nil
}

const systemPreamble = `You are Tapir, answering questions about ONE video using ONLY the transcript below.
Ground every answer in the transcript. If the transcript does not contain the answer, say so plainly rather than guessing.`

const truncatedNote = `
The transcript below is truncated to fit the model — if a question seems to concern something missing, note it may be beyond the available portion.`

// buildSystem frames the model as a transcript-grounded QA assistant and embeds
// the (possibly truncated) transcript as context.
func buildSystem(transcript string, truncated bool) string {
	var b strings.Builder
	b.WriteString(systemPreamble)
	if truncated {
		b.WriteString(truncatedNote)
	}
	b.WriteString("\n\nTranscript:\n")
	b.WriteString(transcript)
	return b.String()
}

// buildUser renders the running conversation as the user message: prior turns as
// Q/A pairs followed by the new question. Folding history into one message keeps
// the Completer surface (a single system+user call) unchanged — no new llm method.
func buildUser(history []Turn, question string) string {
	var b strings.Builder
	for _, t := range history {
		fmt.Fprintf(&b, "Q: %s\nA: %s\n\n", t.Question, t.Answer)
	}
	fmt.Fprintf(&b, "Q: %s", question)
	return b.String()
}

// truncate caps content to max bytes on a UTF-8 rune boundary, reporting whether
// it cut. It mirrors the summarizer's truncation discipline (ADR-022) but returns
// the cut flag so the chat UI can be honest about a bounded transcript. A
// non-positive max (or content already within budget) returns content unchanged.
func truncate(content string, max int) (string, bool) {
	if max <= 0 || len(content) <= max {
		return content, false
	}
	cut := max
	for cut > 0 && !utf8.RuneStart(content[cut]) {
		cut--
	}
	return content[:cut], true
}