a4069d5755
Backend (internal/llm): backend-agnostic LLMClient interface + factory
with vLLM (OpenAI-compat) and Ollama (native) clients, each Complete +
Stream. prompts.go holds the checkpoint and Ask Petal templates;
checkpoint.go salvages JSON from model output (brace-matched), enforces a
per-doc 30s RateLimiter, and truncates the doc to a latency cap.
internal/suggestions: POST /api/docs/:id/check runs a checkpoint and
replaces the doc's pending suggestions in one tx (accepted/rejected kept
as history); GET /api/docs/:id/suggestions lists pending;
POST /api/suggestions/:id/{accept,dismiss} resolves one. Throttled checks
return the current set rather than erroring.
Frontend: useCheckpoint (4s debounce, loads existing on open, stale-guard
tokens); SuggestionHighlight renders ProseMirror decorations re-anchored
by the `original` string on every doc change (not stored marks), with
precise textblock-offset→PM-position mapping; SuggestionCard shows the
type tag + diff + explanation and applies the replacement in-editor on
accept; breathing rose checkpoint dot in the StatusBar; fade-float +
breathe animations.
Tests: llm parse/rate-limit/truncate; suggestions full flow + rate-limit
over httptest with a stub client. Smoke-tested end-to-end against a fake
vLLM endpoint (anchoring verified) and the LLM-unreachable 502 path.
Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
94 lines
2.3 KiB
Go
94 lines
2.3 KiB
Go
package llm
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func TestParseCheckpoint(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
raw string
|
|
want int
|
|
wantErr bool
|
|
}{
|
|
{
|
|
name: "clean json",
|
|
raw: `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"subject-verb agreement","type":"grammar"}]}`,
|
|
want: 1,
|
|
},
|
|
{
|
|
name: "wrapped in markdown fence",
|
|
raw: "Here you go:\n```json\n{\"suggestions\":[{\"original\":\"a apple\",\"replacement\":\"an apple\",\"explanation\":\"use an before a vowel\",\"type\":\"grammar\"}]}\n```",
|
|
want: 1,
|
|
},
|
|
{
|
|
name: "empty suggestions",
|
|
raw: `{"suggestions":[]}`,
|
|
want: 0,
|
|
},
|
|
{
|
|
name: "drops items with empty original",
|
|
raw: `{"suggestions":[{"original":"","replacement":"x","explanation":"e","type":"grammar"},{"original":"teh","replacement":"the","explanation":"typo","type":"grammar"}]}`,
|
|
want: 1,
|
|
},
|
|
{
|
|
name: "no json at all",
|
|
raw: "I could not find any issues!",
|
|
wantErr: true,
|
|
},
|
|
{
|
|
name: "braces inside string values",
|
|
raw: `{"suggestions":[{"original":"use {x}","replacement":"use x","explanation":"drop the braces","type":"clarity"}]}`,
|
|
want: 1,
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got, err := ParseCheckpoint(tt.raw)
|
|
if tt.wantErr {
|
|
if err == nil {
|
|
t.Fatalf("expected error, got none")
|
|
}
|
|
return
|
|
}
|
|
if err != nil {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
if len(got) != tt.want {
|
|
t.Fatalf("got %d suggestions, want %d", len(got), tt.want)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestRateLimiter(t *testing.T) {
|
|
rl := NewRateLimiter(30 * time.Second)
|
|
|
|
if ok, _ := rl.Allow("doc1"); !ok {
|
|
t.Fatal("first call should be allowed")
|
|
}
|
|
if ok, retry := rl.Allow("doc1"); ok || retry <= 0 {
|
|
t.Fatalf("immediate second call should be throttled, got ok=%v retry=%v", ok, retry)
|
|
}
|
|
// A different document is independent.
|
|
if ok, _ := rl.Allow("doc2"); !ok {
|
|
t.Fatal("different doc should be allowed")
|
|
}
|
|
}
|
|
|
|
func TestTruncateDoc(t *testing.T) {
|
|
short := "hello"
|
|
if got := TruncateDoc(short); got != short {
|
|
t.Fatalf("short doc should be unchanged")
|
|
}
|
|
long := make([]byte, maxDocChars+500)
|
|
for i := range long {
|
|
long[i] = 'a'
|
|
}
|
|
got := TruncateDoc(string(long))
|
|
if len(got) != maxDocChars {
|
|
t.Fatalf("truncated length = %d, want %d", len(got), maxDocChars)
|
|
}
|
|
}
|