fix(llm): read a bounded response body, 8 MiB on success and the error bound on failure (#53)

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

internal/adapters/llm/client.go

@@ -37,6 +37,21 @@ type Client struct {
 	temp       float64
 	httpClient *http.Client
 	usageHook  func(model string, prompt, completion int)
+	maxBody    int64
+}
+
+// defaultMaxResponseBytes bounds a success body. A completion is a few KB of text; this
+// leaves room for a long one and none for a gateway that streams forever (#53).
+const defaultMaxResponseBytes = 8 << 20
+
+// WithMaxResponseBytes overrides the bound on a success response body. A non-positive n is
+// ignored (keeps the default).
+func WithMaxResponseBytes(n int64) Option {
+	return func(c *Client) {
+		if n > 0 {
+			c.maxBody = n
+		}
+	}
 }
 
 // Option configures a Client at construction. Variadic so the existing 4-arg
@@ -101,6 +116,7 @@ func New(baseURL, apiKey, model string, timeout time.Duration, opts ...Option) *
 		maxTokens:  defaultMaxTokens,
 		temp:       defaultTemperature,
 		httpClient: &http.Client{Timeout: timeout},
+		maxBody:    defaultMaxResponseBytes,
 	}
 	for _, opt := range opts {
 		opt(c)
@@ -184,12 +200,17 @@ func (c *Client) Complete(ctx context.Context, system, user string) (string, err
 	}
 	defer resp.Body.Close() //nolint:errcheck
 
-	out, err := io.ReadAll(resp.Body)
+	if resp.StatusCode != http.StatusOK {
+		// Only the bounded head is ever used (HTTPError.Error truncates to it), so read no more.
+		head, _ := io.ReadAll(io.LimitReader(resp.Body, maxErrorBody+1))
+		return "", &HTTPError{Code: resp.StatusCode, Body: string(head)}
+	}
+	out, err := io.ReadAll(io.LimitReader(resp.Body, c.maxBody+1))
 	if err != nil {
 		return "", fmt.Errorf("read response: %w", err)
 	}
-	if resp.StatusCode != http.StatusOK {
-		return "", &HTTPError{Code: resp.StatusCode, Body: string(out)}
+	if int64(len(out)) > c.maxBody {
+		return "", fmt.Errorf("LLM response exceeds %d bytes", c.maxBody)
 	}
 
 	var cr chatResponse