Files
tapir/internal/adapters/llm/client.go
T
mathiasandClaude Opus 4.8 0aeb3aa99e feat(adapters): copy stdlib llm package (Client + Router) per ADR-004
Copy hyperguild/ingestion/internal/llm into internal/adapters/llm and own it.
Tapir owes that repo nothing at the dependency level — no module dep added.
Router gives the local-Primary -> BYO-Fallback path needed for ai_routing.feature.

Copied tests rewritten from testify to stdlib testing to keep go.mod
dependency-free (repo has zero deps; acceptance tests are stdlib too).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 17:01:56 +02:00

125 lines
3.1 KiB
Go

// Package llm is a COPY of hyperguild/ingestion/internal/llm (ADR-004). Tapir
// owns this copy; it is not a module dependency on that repo. The package is
// stdlib-only. Client calls an OpenAI-compatible chat completions endpoint;
// Router (router.go) implements the local-Primary -> BYO-Fallback pattern Tapir
// needs for docs/use-cases/ai_routing.feature.
package llm
import (
"bytes"
"context"
"encoding/json"
"fmt"
"io"
"net/http"
"strconv"
"strings"
"time"
)
// Client calls an OpenAI-compatible chat completions endpoint.
type Client struct {
baseURL string
apiKey string
model string
httpClient *http.Client
}
// New constructs a Client.
func New(baseURL, apiKey, model string, timeout time.Duration) *Client {
return &Client{
baseURL: strings.TrimRight(baseURL, "/"),
apiKey: apiKey,
model: model,
httpClient: &http.Client{Timeout: timeout},
}
}
type chatRequest struct {
Model string `json:"model"`
Messages []message `json:"messages"`
Temperature float64 `json:"temperature"`
}
type message struct {
Role string `json:"role"`
Content string `json:"content"`
}
type chatResponse struct {
Choices []struct {
Message message `json:"message"`
} `json:"choices"`
}
// Complete sends a system + user message and returns the assistant's reply.
// Retries once on HTTP 429 using Retry-After header or 5s backoff.
func (c *Client) Complete(ctx context.Context, system, user string) (string, error) {
body := chatRequest{
Model: c.model,
Messages: []message{
{Role: "system", Content: system},
{Role: "user", Content: user},
},
Temperature: 0.2,
}
b, err := json.Marshal(body)
if err != nil {
return "", fmt.Errorf("marshal request: %w", err)
}
do := func() (*http.Response, error) {
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.baseURL+"/chat/completions", bytes.NewReader(b))
if err != nil {
return nil, fmt.Errorf("build request: %w", err)
}
req.Header.Set("Content-Type", "application/json")
if c.apiKey != "" {
req.Header.Set("Authorization", "Bearer "+c.apiKey)
}
return c.httpClient.Do(req)
}
resp, err := do()
if err != nil {
return "", fmt.Errorf("call LLM: %w", err)
}
if resp.StatusCode == http.StatusTooManyRequests {
_ = resp.Body.Close()
wait := 5 * time.Second
if ra := resp.Header.Get("Retry-After"); ra != "" {
if secs, err := strconv.Atoi(ra); err == nil {
wait = time.Duration(secs) * time.Second
}
}
select {
case <-ctx.Done():
return "", ctx.Err()
case <-time.After(wait):
}
resp, err = do()
if err != nil {
return "", fmt.Errorf("retry LLM call: %w", err)
}
}
defer resp.Body.Close() //nolint:errcheck
out, err := io.ReadAll(resp.Body)
if err != nil {
return "", fmt.Errorf("read response: %w", err)
}
if resp.StatusCode != http.StatusOK {
return "", fmt.Errorf("LLM returned %d: %s", resp.StatusCode, out)
}
var cr chatResponse
if err := json.Unmarshal(out, &cr); err != nil {
return "", fmt.Errorf("parse response: %w", err)
}
if len(cr.Choices) == 0 {
return "", fmt.Errorf("LLM returned no choices")
}
return cr.Choices[0].Message.Content, nil
}