Implement layered timeout enforcement

internal/llm/openai_compatible_client.go

@@ -55,7 +55,7 @@ func NewOpenAICompatibleClient(cfg OpenAICompatibleConfig) (*OpenAICompatibleCli
 	var client *http.Client
 	if cfg.HTTPClient != nil {
 		cloned := *cfg.HTTPClient
-		if cloned.Timeout == 0 {
+		if cloned.Timeout <= 0 {
 			cloned.Timeout = timeout
 		}
 		client = &cloned
@@ -99,7 +99,17 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
 		return nil, fmt.Errorf("%w: failed to encode request: %v", ErrRequestFailed, err)
 	}
 
-	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, endpoint, bytes.NewReader(payload))
+	requestContext := ctx
+	if req.Target.TimeoutSeconds > 0 {
+		var cancel context.CancelFunc
+		requestContext, cancel = context.WithTimeout(
+			ctx,
+			time.Duration(req.Target.TimeoutSeconds)*time.Second,
+		)
+		defer cancel()
+	}
+
+	httpReq, err := http.NewRequestWithContext(requestContext, http.MethodPost, endpoint, bytes.NewReader(payload))
 	if err != nil {
 		return nil, fmt.Errorf("%w: failed to create request: %v", ErrRequestFailed, err)
 	}
@@ -118,18 +128,6 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
 	if httpClient == nil {
 		httpClient = &http.Client{Timeout: defaults.LLMRequestTimeoutDefault}
 	}
-	if req.Target.TimeoutSeconds > 0 {
-		effectiveTimeout := time.Duration(req.Target.TimeoutSeconds) * time.Second
-		if httpClient.Timeout != effectiveTimeout {
-			cloned := *httpClient
-			cloned.Timeout = effectiveTimeout
-			httpClient = &cloned
-		}
-	} else if req.TargetPresence.TimeoutSeconds && httpClient.Timeout != 0 {
-		cloned := *httpClient
-		cloned.Timeout = 0
-		httpClient = &cloned
-	}
 
 	httpResp, err := httpClient.Do(httpReq)
 	if err != nil {