feat(chat): stored-transcript QA service (ADR-027)

A read-only deeper-dive over a video's already-stored transcript (ADR-021).
Safe by construction: the Service has no VideoSource and no caption-fetch
dependency — only a Completer factory over the existing LiteLLM gateway — so it
cannot reach YouTube or the rate gate. Reuses the summarizer's truncation
discipline (TAPIR_MAX_TRANSCRIPT_CHARS), reporting the cut so the UI can be
honest about a bounded transcript. Model defaults to the summary's model and is
switchable among an offered, local-first list; an un-offered alias is forced
back to the default so chat can never call the gateway with an arbitrary model.
Ephemeral: history is carried per-request, nothing persisted.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-11 09:16:45 +02:00
co-authored by Claude Opus 4.8
parent 69a49bc603
commit cc3cda4ab8
2 changed files with 335 additions and 0 deletions
+164
View File
@@ -0,0 +1,164 @@
package chat
import (
"context"
"errors"
"strings"
"testing"
)
// recordingCompleter captures the system+user it was asked with and returns a
// canned answer (or error). It also records which model alias built it.
type recordingCompleter struct {
model string
lastSystem string
lastUser string
answer string
err error
calls *int
}
func (c *recordingCompleter) Complete(_ context.Context, system, user string) (string, error) {
*c.calls++
c.lastSystem = system
c.lastUser = user
if c.err != nil {
return "", c.err
}
return c.answer, nil
}
// factory builds a recordingCompleter per model and records the last one built so
// the test can assert which model alias was actually used for the gateway call.
type factory struct {
answer string
err error
calls int
used *recordingCompleter
}
func (f *factory) make(model string) Completer {
c := &recordingCompleter{model: model, answer: f.answer, err: f.err, calls: &f.calls}
f.used = c
return c
}
func TestModelsAreOfferedLocalFirstAndCopied(t *testing.T) {
f := &factory{answer: "ok"}
s := New(f.make, []string{"koala/phi4-mini", "iguana/gemma4-26b"}, 0)
got := s.Models()
want := []string{"koala/phi4-mini", "iguana/gemma4-26b"}
if len(got) != len(want) || got[0] != want[0] || got[1] != want[1] {
t.Fatalf("Models() = %v, want %v", got, want)
}
// Mutating the returned slice must not corrupt the Service's list.
got[0] = "tampered"
if s.Models()[0] != "koala/phi4-mini" {
t.Fatal("Models() leaked its backing slice")
}
}
func TestDefaultModelIsTheSummarysModelWhenOffered(t *testing.T) {
f := &factory{answer: "ok"}
s := New(f.make, []string{"koala/phi4-mini", "iguana/gemma4-26b", "berget/mistral-small"}, 0)
if got := s.DefaultModel("iguana/gemma4-26b"); got != "iguana/gemma4-26b" {
t.Fatalf("DefaultModel(summary) = %q, want the summary's model", got)
}
// A summary model no longer offered (e.g. cloud disabled) falls back to first.
if got := s.DefaultModel("berget/old-model"); got != "koala/phi4-mini" {
t.Fatalf("DefaultModel(un-offered) = %q, want the first offered model", got)
}
// No summary model recorded → first offered.
if got := s.DefaultModel(""); got != "koala/phi4-mini" {
t.Fatalf("DefaultModel(\"\") = %q, want the first offered model", got)
}
}
func TestAnswerGroundsOnTranscriptAndCarriesHistory(t *testing.T) {
f := &factory{answer: " The video is about attention. "}
s := New(f.make, []string{"koala/phi4-mini"}, 0)
reply, err := s.Answer(context.Background(), Request{
Model: "koala/phi4-mini",
Transcript: "ATTENTION-TRANSCRIPT-MARKER",
History: []Turn{{Question: "who", Answer: "the host"}},
Question: "what is it about",
})
if err != nil {
t.Fatalf("Answer: %v", err)
}
if reply.Answer != "The video is about attention." {
t.Fatalf("answer not trimmed: %q", reply.Answer)
}
if reply.Truncated {
t.Fatal("short transcript must not report truncated")
}
// The transcript rides in the system prompt; the conversation in the user msg.
if !strings.Contains(f.used.lastSystem, "ATTENTION-TRANSCRIPT-MARKER") {
t.Fatal("transcript not grounded into the system prompt")
}
if !strings.Contains(f.used.lastUser, "Q: who") || !strings.Contains(f.used.lastUser, "A: the host") {
t.Fatalf("history not carried into the user message: %q", f.used.lastUser)
}
if !strings.Contains(f.used.lastUser, "what is it about") {
t.Fatal("new question missing from the user message")
}
}
func TestAnswerTruncatesLongTranscriptAndReportsIt(t *testing.T) {
f := &factory{answer: "answer"}
s := New(f.make, []string{"koala/phi4-mini"}, 10)
reply, err := s.Answer(context.Background(), Request{
Model: "koala/phi4-mini",
Transcript: strings.Repeat("x", 500),
Question: "summarize",
})
if err != nil {
t.Fatalf("Answer: %v", err)
}
if !reply.Truncated {
t.Fatal("a transcript past maxChars must report Truncated")
}
if strings.Count(f.used.lastSystem, "x") != 10 {
t.Fatalf("transcript not bounded to maxChars: got %d x's", strings.Count(f.used.lastSystem, "x"))
}
}
func TestAnswerForcesAnUnofferedModelBackToDefault(t *testing.T) {
f := &factory{answer: "answer"}
s := New(f.make, []string{"koala/phi4-mini", "iguana/gemma4-26b"}, 0)
// A forged/un-offered model must never reach the gateway as-is — it is forced
// to the default offered model (the cloud-absent guarantee depends on this).
_, err := s.Answer(context.Background(), Request{
Model: "berget/secret-cloud-model",
Transcript: "t",
Question: "q",
})
if err != nil {
t.Fatalf("Answer: %v", err)
}
if f.used.model != "koala/phi4-mini" {
t.Fatalf("un-offered model reached the gateway as %q, want the default", f.used.model)
}
}
func TestAnswerPropagatesCompleterError(t *testing.T) {
f := &factory{err: errors.New("gateway down")}
s := New(f.make, []string{"koala/phi4-mini"}, 0)
_, err := s.Answer(context.Background(), Request{Model: "koala/phi4-mini", Transcript: "t", Question: "q"})
if err == nil {
t.Fatal("expected the gateway error to propagate")
}
}
func TestAnswerRejectsEmptyModelSet(t *testing.T) {
s := New(func(string) Completer { return nil }, nil, 0)
if _, err := s.Answer(context.Background(), Request{Question: "q"}); err == nil {
t.Fatal("expected an error when no models are configured")
}
}